CN117010216B - Simulation evaluation method for surface disinfection effect of microbial aerosol - Google Patents
Simulation evaluation method for surface disinfection effect of microbial aerosol Download PDFInfo
- Publication number
- CN117010216B CN117010216B CN202311276141.1A CN202311276141A CN117010216B CN 117010216 B CN117010216 B CN 117010216B CN 202311276141 A CN202311276141 A CN 202311276141A CN 117010216 B CN117010216 B CN 117010216B
- Authority
- CN
- China
- Prior art keywords
- data
- disinfection
- aerosol
- test
- microbial
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000004659 sterilization and disinfection Methods 0.000 title claims abstract description 704
- 239000000443 aerosol Substances 0.000 title claims abstract description 447
- 230000000694 effects Effects 0.000 title claims abstract description 278
- 230000000813 microbial effect Effects 0.000 title claims abstract description 200
- 238000011156 evaluation Methods 0.000 title claims abstract description 69
- 238000004088 simulation Methods 0.000 title claims abstract description 38
- 238000012360 testing method Methods 0.000 claims abstract description 250
- 244000005700 microbiome Species 0.000 claims abstract description 129
- 238000000034 method Methods 0.000 claims abstract description 84
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 56
- 238000005457 optimization Methods 0.000 claims abstract description 48
- 238000012706 support-vector machine Methods 0.000 claims abstract description 22
- 238000007781 pre-processing Methods 0.000 claims abstract description 13
- 230000007613 environmental effect Effects 0.000 claims description 120
- 238000012549 training Methods 0.000 claims description 50
- 238000009826 distribution Methods 0.000 claims description 36
- 238000004364 calculation method Methods 0.000 claims description 18
- 230000010354 integration Effects 0.000 claims description 14
- 230000002159 abnormal effect Effects 0.000 claims description 13
- 238000010606 normalization Methods 0.000 claims description 13
- 238000005516 engineering process Methods 0.000 claims description 9
- 238000013507 mapping Methods 0.000 claims description 8
- 238000007619 statistical method Methods 0.000 claims description 7
- 238000013461 design Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 description 20
- 230000008859 change Effects 0.000 description 18
- 230000008569 process Effects 0.000 description 18
- 230000001954 sterilising effect Effects 0.000 description 14
- 230000006870 function Effects 0.000 description 12
- 238000012545 processing Methods 0.000 description 9
- 230000009286 beneficial effect Effects 0.000 description 7
- 230000008901 benefit Effects 0.000 description 7
- 239000007921 spray Substances 0.000 description 7
- 239000000645 desinfectant Substances 0.000 description 6
- 239000002245 particle Substances 0.000 description 6
- 230000000875 corresponding effect Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000009423 ventilation Methods 0.000 description 5
- 238000010276 construction Methods 0.000 description 4
- 230000036541 health Effects 0.000 description 4
- 241000894006 Bacteria Species 0.000 description 3
- 241000700605 Viruses Species 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000009792 diffusion process Methods 0.000 description 2
- 238000012854 evaluation process Methods 0.000 description 2
- 230000002349 favourable effect Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- VEXZGXHMUGYJMC-UHFFFAOYSA-M Chloride anion Chemical compound [Cl-] VEXZGXHMUGYJMC-UHFFFAOYSA-M 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000010224 classification analysis Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000012136 culture method Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000008021 deposition Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 230000002779 inactivation Effects 0.000 description 1
- 230000002906 microbiologic effect Effects 0.000 description 1
- 238000001000 micrograph Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 238000005507 spraying Methods 0.000 description 1
- 230000008685 targeting Effects 0.000 description 1
- 230000001550 time effect Effects 0.000 description 1
- 231100000331 toxic Toxicity 0.000 description 1
- 230000002588 toxic effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Apparatus Associated With Microorganisms And Enzymes (AREA)
Abstract
The invention relates to the technical field of disinfection, in particular to a simulation evaluation method for the surface disinfection effect of microbial aerosol. The method comprises the following steps: the method comprises the steps of collecting and preprocessing microorganism aerosol data of target equipment to be detected to generate microorganism aerosol data; integrating and classifying aerosol related data of the target equipment to be detected by utilizing the aerosol disinfection data to generate classified test aerosol disinfection effect data; performing microbial aerosol surface disinfection data prediction model establishment and model optimization by using a support vector machine algorithm and classification test aerosol disinfection effect data to generate an optimized disinfection data prediction model; transmitting the real-time data to be disinfected to an optimized disinfection data prediction model for disinfection data prediction, and generating disinfection prediction data; and carrying out disinfection simulation operation of the equipment to be detected by using the disinfection prediction data, and generating a simulated disinfection effect evaluation report. The invention realizes more accurate disinfection evaluation report.
Description
Technical Field
The invention relates to the field of disinfection effect evaluation, in particular to a simulation evaluation method for the surface disinfection effect of microbial aerosol.
Background
The surface disinfection of the microorganism aerosol is an important sanitary measure, is used for effectively removing micro-harmful organisms such as bacteria, viruses and the like suspended in the air, and can be used for covering the surface of the aerosol by spraying a disinfectant through spray disinfection, so as to destroy the cell structure of the microorganism, achieve the effect of killing, ensure the disinfection in the environment with increased germ reproduction and transmission possibility, and ensure the health and safety of users. However, the conventional surface sterilization of a microbial aerosol cannot judge the content of the microbial aerosol, so that the health of people may be affected by too much sterilization spray, or too little sterilization spray dose cannot effectively perform the surface sterilization of the microbial aerosol, resulting in poor surface sterilization effect of the microbial aerosol.
Disclosure of Invention
Based on the above, the present invention provides a method for simulating and evaluating the surface disinfection effect of a microbial aerosol, so as to solve at least one of the above technical problems.
In order to achieve the above purpose, a simulation evaluation method for the disinfection effect of a microbial aerosol surface comprises the following steps:
step S1: acquiring target equipment to be detected; the method comprises the steps of collecting and preprocessing microorganism aerosol data of target equipment to be detected to generate microorganism aerosol data;
Step S2: acquiring aerosol disinfection data; performing a microbial aerosol surface disinfection test on the target equipment to be detected by using aerosol disinfection data, and performing disinfection test efficiency calculation to generate disinfection test efficiency data; data integration is carried out on the microorganism aerosol data, the aerosol disinfection data and the disinfection test efficiency data, and test aerosol disinfection effect data is generated;
step S3: the method comprises the steps that a sensor is used for collecting environmental data around target equipment to be detected, and environmental data are generated; classifying the test aerosol disinfection effect data according to the environment data to obtain disinfection environment type data, and generating classified test aerosol disinfection effect data;
step S4: performing microbial aerosol surface disinfection data prediction model establishment and model optimization by using a support vector machine algorithm and classification test aerosol disinfection effect data to generate an optimized disinfection data prediction model;
step S5: the method comprises the steps of updating and integrating microorganism aerosol data and environment data in real time to generate real-time data to be disinfected; transmitting the real-time data to be disinfected to an optimized disinfection data prediction model for disinfection data prediction, and generating disinfection prediction data;
Step S6: and establishing a physical model of the equipment to be detected according to the target equipment to be detected and the real-time data to be disinfected, and performing disinfection simulation operation of the equipment to be detected by utilizing the disinfection prediction data to generate a simulated disinfection effect evaluation report.
According to the invention, through actively acquiring the microbial aerosol data of the surface of the target equipment, the microbial load condition of the surface of the equipment, including the distribution density and the types of microorganisms such as bacteria and viruses, can be deeply known, the accuracy of subsequent analysis and model establishment is ensured, a real and detailed data basis is provided for subsequent disinfection effect evaluation, and the evaluation of the disinfection effect is more real and reliable. By acquiring aerosol disinfection data and performing a disinfection test on target equipment, the actual disinfection operation can be simulated, and the effectiveness of the disinfection method is verified. When the disinfection test is carried out, the disinfection effect of different disinfection strategies on the microbial aerosol can be quantitatively measured by calculating the disinfection test efficiency data, so that objective indexes are provided for comparison and optimization of different disinfection conditions, the microbial aerosol data, the aerosol disinfection data and the disinfection test efficiency data are integrated, comprehensive test aerosol disinfection effect data can be established, a foundation is provided for subsequent analysis and model construction, and the disinfection effect and the operation efficiency are further improved. By collecting environmental data around the target device by using the sensor, environmental information closely related to the disinfection effect, such as temperature, humidity, air flow and the like, can be acquired, the factors can influence the disinfection effect, and after the environmental data are generated, the environmental background of the disinfection operation is known more accurately, so that more accurate background information is provided for explanation and prediction of the follow-up disinfection effect. When the test aerosol disinfection effect data is classified according to the environment data, the disinfection effects under different environment conditions can be grouped to form a disinfection environment type data classification, the influence degree of different environments on the disinfection effect is deeply analyzed, the potential influence mechanism of environmental factors on disinfection is revealed, the disinfection effect difference under different conditions can be better understood by generating the classification test aerosol disinfection effect data, and richer data input is provided for the establishment and optimization of a follow-up disinfection effect prediction model. By utilizing a support vector machine algorithm and classifying test aerosol disinfection effect data to establish a prediction model and performing model optimization, potential rules and correlations are mined from the existing classification data, so that a more accurate and reliable microbial aerosol surface disinfection data prediction model is established, the influence of environmental factors, disinfection conditions, microbial loads and other aspects can be fully considered by the prediction model, the prediction accuracy is improved, and the performance of the prediction model is further improved through model optimization, so that the prediction model has stronger applicability and stability under different environments and conditions. The real-time to-be-sterilized data is generated by updating and integrating the microbial aerosol data and the environment data in real time, the real-time to-be-sterilized data is transmitted to the optimized sterilizing data prediction model for prediction, and the prediction and monitoring of the real-time sterilizing effect are realized. By establishing a physical model according to target equipment to be detected and real-time data to be disinfected and performing simulation operation by utilizing disinfection prediction data, the simulation evaluation of the disinfection effect of the equipment to be detected is realized, and the simulation operation can simulate the process of actual disinfection operation in a virtual environment, so that the prediction of the disinfection effect under different conditions is realized, the difference of the disinfection effects under different conditions is better understood, the possible problems and improvement space are found, and guidance and reference are provided for the actual operation. Therefore, the simulation evaluation method of the microbial aerosol surface disinfection effect can judge the content of the microbial aerosol, can not cause excessive disinfection spray to influence the health of people, and can not effectively disinfect the microbial aerosol surface because of too little disinfection spray dose, thereby ensuring the disinfection effect of the microbial aerosol surface.
Preferably, step S1 comprises the steps of:
step S11: acquiring target equipment to be detected;
step S12: the method comprises the steps of carrying out regional microorganism aerosol data acquisition on target equipment to be detected by utilizing electron microscope equipment, and generating regional microorganism aerosol image data;
step S13: and carrying out aerosol data preprocessing of the target equipment to be detected according to the regional microorganism aerosol image data to generate microorganism aerosol data.
The method and the device for acquiring the target equipment to be detected establish a foundation for subsequent acquisition and analysis of the microbial aerosol data, ensure that the acquired data are closely related to the actual equipment to be detected, and further improve the accuracy and reliability of the evaluation result. The method has the advantages that the electron microscope equipment is utilized to collect regional microorganism aerosol data of the target equipment to be detected, high-resolution image data is obtained, the high-resolution image data can show the characteristics of distribution, density, morphology and the like of microorganisms in more detail, more abundant information is provided for subsequent analysis, and the regional collection can focus on the microorganism load difference of different areas, so that evaluation is more detailed and comprehensive, and the calculated amount of data processing is reduced. And performing aerosol data preprocessing according to the regional microbial aerosol image data to generate microbial aerosol data, wherein the preprocessing can convert the regional microbial aerosol image data into microbial aerosol data of corresponding target equipment to be detected, so that the aerosol data extracted from the image has better interpretability and usability.
Preferably, step S13 comprises the steps of:
step S131: carrying out statistical analysis on the microbial aerosol distribution of the regional microbial aerosol image data to generate regional biological aerosol data;
step S132: calculating the average value of the whole microbial aerosol data of the target equipment to be detected according to the regional microbial aerosol data, and generating initial microbial aerosol data;
step S133: and carrying out data normalization on the initial microbial aerosol data by using a minimum-maximum normalization method to generate microbial aerosol data.
According to the invention, through carrying out statistical analysis on the microbial aerosol distribution of regional microbial aerosol image data, the distribution situation of microorganisms in different regions can be known on a fine scale, the statistical analysis can reveal the spatial distribution difference of microbial loads, and the method is helpful for identifying possible high-load regions and low-load regions, and the difference information has important significance for formulating disinfection strategies and evaluation effect accuracy for different regions. By calculating the overall microorganism aerosol data average value of the target equipment to be detected according to the regional microorganism aerosol data, a preliminary overall data index can be obtained, the overall microorganism load condition of the equipment is reflected, and more accurate microorganism aerosol content is provided for subsequent analysis and comparison. The data normalization is carried out on the initial microbial aerosol data by a minimum-maximum normalization method, the data is mapped into a specific range, the normalization treatment can eliminate the influence caused by different data scales, so that more visual and comparable analysis can be carried out among different data, the normalized data is helpful for better understanding the distribution situation of the microbial aerosol, and a more consistent data base is provided for the establishment and prediction of a subsequent model.
Preferably, step S2 comprises the steps of:
step S21: acquiring aerosol disinfection data;
step S22: performing a microbial aerosol surface disinfection test on the target equipment to be detected by utilizing aerosol disinfection data, and performing microbial aerosol data acquisition of the disinfection test to generate aerosol disinfection test data;
step S23: performing disinfection efficiency calculation on aerosol disinfection test data by using a microbial aerosol disinfection efficiency algorithm to generate disinfection test efficiency data;
step S24: and integrating the data of the microorganism aerosol, the aerosol disinfection data and the disinfection test efficiency data to generate test aerosol disinfection effect data.
The invention acquires aerosol disinfection data, ensures that the actual disinfection operation result is acquired, can comprise disinfection effect information of different disinfection strategies, conditions and disinfection time, can reflect the influence of different operation conditions on microbial aerosol, and provides reliable actual data sources for subsequent disinfection effect evaluation and prediction. The method has the advantages that the microorganism aerosol surface disinfection test is carried out on the target equipment by utilizing the aerosol disinfection data, the data acquisition is carried out, the aerosol disinfection test data are generated, the operability test can simulate real disinfection operation, the data of the sterilized microorganism aerosol are actually measured, and an experimental data basis is provided for subsequent disinfection effect evaluation and analysis. The disinfection efficiency calculation is carried out on the aerosol disinfection test data by utilizing the microbial aerosol disinfection efficiency algorithm, so that the disinfection test efficiency data is generated, the killing efficiency of the microbial aerosol under different disinfection strategies or conditions can be clearly shown, and objective indexes are provided for evaluating the effectiveness of different operation schemes by the disinfection efficiency data. The method has the advantages that the microorganism aerosol data, the aerosol disinfection data and the disinfection test efficiency data are subjected to data integration to generate test aerosol disinfection effect data, the data of different layers can be integrated, a complete data set is provided for subsequent analysis, the integrated data can better reveal the disinfection effect difference under different operation conditions, and the method is beneficial to more accurately carrying out subsequent model establishment and prediction.
Preferably, the microbial aerosol sterilization efficiency algorithm in step S23 is as follows:
;
wherein P is expressed as disinfection test efficiency data, t 2 Expressed as the end time of the disinfection test, t 1 Expressed as the start time of the disinfection test, N is expressed as an equal area image block of the target device to be detected, A i Denoted as initial concentration of microbial aerosol in the ith image block, t denoted as current time node of the disinfection test, B i Expressed as final concentration of microbial aerosol in the ith image patch, M is expressed as area size of the image patch, M Total (S) Expressed as the total area of the test area, k expressed as the average density of the microbial aerosol, Q expressed as the air supply rate of the target device to be tested, and τ expressed as the abnormal adjustment value of the disinfection test efficiency data.
The invention utilizes a microbial aerosol disinfection efficiency algorithm which fully considers the end time t of disinfection test 2 Start time t of disinfection test 1 Equal area image block N of target to-be-detected equipment and initial concentration A of microorganism aerosol in ith image block i The current time node t of the disinfection test, the final concentration B of the microbial aerosol in the ith image block i The area size M of the image block and the total area M of the test area Total (S) The average density k of the microbial aerosol, the air supply rate Q of the target device to be detected, and the function to form a functional relationship:
that is to say,the function relation is used for calculating the efficiency of the disinfection test on aerosol disinfection test data, so that the evaluation process of the disinfection efficiency is better grasped, and meanwhile, the influence of different factors on the disinfection effect can be more accurately identified and explained, and a more powerful support is provided for the subsequent disinfection decision. The end time and the start time of the disinfection test determine the time range of the disinfection test, are helpful for determining the duration of disinfection, and can be adjusted according to actual conditions so as to capture the whole change track of the disinfection process; the number of the equal-area image blocks of the target equipment to be detected can be more accurately used for capturing the distribution change of the microbial aerosol at different positions by dividing the equipment to be detected into a plurality of small blocks; the initial concentration and the final concentration of the microbial aerosol in the ith image block show the change of the concentration of the microbial aerosol in calculation, are directly related to the evaluation of the disinfection effect, and are helpful for more accurately evaluating the disinfection conditions of different areas; the size of the area of the image block and the total area of the test area, and the contribution of different image blocks can be weighted according to the size of the image block by using the area parameters, so that the overall effect is reflected more accurately; the average density of the microbial aerosol and the air supply rate of the device take the characteristics of microbial propagation into account in the algorithm, so that the algorithm can take the propagation and change of the microbes under different conditions into account, the density of the microbes can influence the reduction rate of the microbes, and thus the evaluation of the disinfection effect is influenced, and the air supply rate influences the propagation and distribution of the microbial aerosol, so that the influence of different air supply rates on the disinfection efficiency is taken into account in the calculation. And the function relation is adjusted and corrected by using the abnormal adjustment value tau of the disinfection test efficiency data, so that the error influence caused by abnormal data or error items is reduced, the disinfection test efficiency data P is generated more accurately, and the accuracy and reliability of the calculation of the disinfection efficiency of the aerosol disinfection test data are improved. Meanwhile, the adjustment value in the formula can be adjusted according to actual conditions and is applied to different aerosol disinfection test data, so that the flexibility and applicability of the algorithm are improved.
Preferably, step S3 comprises the steps of:
step S31: the method comprises the steps that a sensor is used for collecting environmental data around target equipment to be detected, and environmental data are generated;
step S32: performing environment type design of equipment to be detected according to the environment data to generate environment type data;
step S33: and classifying the test aerosol disinfection effect data according to the environment type data to generate classified test aerosol disinfection effect data.
According to the invention, the sensor is used for collecting the surrounding environment data of the target equipment to generate the environment data, the background information related to the disinfection effect, such as temperature, humidity, air flow and the like, can be provided, the follow-up evaluation can better consider the influence of external factors on the disinfection effect, and the accuracy and the practicability of the evaluation result are improved. According to the environmental data, the environmental category of the target equipment is designed, the environmental category number is generated, the characteristics and differences under different environmental conditions can be identified by analyzing and classifying the environmental data, the change and influence of different disinfection environments can be considered better, and a foundation is provided for subsequent classification evaluation. The test aerosol disinfection effect data is subjected to disinfection environment type data classification according to the environment type data to generate classification test aerosol disinfection effect data, and the classification can distinguish disinfection effects under different environment conditions to reveal differences of the disinfection effects under different environment backgrounds, so that the test aerosol disinfection effect data is favorable for more accurately evaluating the real situation of the disinfection effects, and richer data input is provided for model establishment and prediction.
Preferably, step S4 comprises the steps of:
step S41: establishing a mapping relation of microbial aerosol surface disinfection data prediction by using a support vector machine algorithm, and generating an initial disinfection effect prediction model;
step S42: performing data division on time sequence on the classified test aerosol disinfection effect data to generate a classified test aerosol disinfection effect training set and a classified test aerosol disinfection effect testing set;
step S43: transmitting the classified test aerosol disinfection effect training set to an initial disinfection effect prediction model for model training, and generating a disinfection effect prediction model;
step S44: optimizing and adjusting the environmental impact parameter weight of the model for the disinfection data prediction model by using an environmental impact parameter model optimizing algorithm, and performing iterative training by using a classified test aerosol disinfection effect training set to generate an adjusted disinfection data prediction model;
step S45: and performing model test on the adjustment disinfection data prediction model by using the classified test aerosol disinfection effect test set to generate an optimization disinfection data prediction model.
According to the invention, the mapping relation of the microbial aerosol surface disinfection data prediction is established by using a support vector machine algorithm, and the initial disinfection effect prediction model is generated, so that the connection between the microbial aerosol disinfection effect and other variables can be established under the condition that too much priori information is not available, the initial model provides a basic framework, and a starting point is provided for the optimization and adjustment of the follow-up model. The data of the classified test aerosol disinfection effect data are divided in time sequence to generate a classified test aerosol disinfection effect training set and a test set, and the data division can divide the data set into two parts for model training and testing, so that the model is ensured to evaluate and verify on different data, and the phenomenon of over fitting or under fitting is prevented. The training set for classifying and testing the aerosol disinfection effect is transmitted to the initial disinfection effect prediction model for model training, the disinfection effect prediction model is generated, the training process adjusts the initial model by utilizing the existing data, so that the training process is more in line with the actual situation, the training model can learn the relevance and rules among the data, and the accuracy of prediction is improved. The environmental impact parameter model optimization algorithm is utilized to carry out optimization adjustment on the environmental impact parameter weight of the disinfection data prediction model, and meanwhile, the classification test aerosol disinfection effect training set is utilized to carry out iterative training to generate the adjustment disinfection data prediction model. And performing model test on the adjustment disinfection data prediction model by using the classification test aerosol disinfection effect test set to generate an optimization disinfection data prediction model, and verifying generalization capability and prediction effect of the model through the model test to ensure that the model is reliable in performance on new data, so that the prediction model is more stable and reliable, thereby providing high-quality prediction model support for the prediction of actual disinfection effects.
Preferably, the environmental impact parametric model optimization algorithm in step S44 is as follows:
;
where K is expressed as an optimization weight of the environmental impact parameter, R is expressed as the number of input samples of the model, y i The predicted disinfection test efficiency expressed as the i-th sample,the actual disinfection test efficiency, z, expressed as the i-th sample i Humidity data, b, expressed as the i-th sample i Denoted as the ith sample temperature data, P is denoted as the initial weight of the environmental impact parameter,/for the sample temperature data>Expressed as the length of time the test microorganism aerosol was sterilized, with delta expressed as the abnormal adjustment of the optimization weights of the environmental impact parameters, to which the i-th sample relates.
The invention utilizes an environmental impact parameter model optimization algorithm which fully considers the input sample number R of the model and the forecast disinfection test efficiency y of the ith sample i Actual disinfection test efficiency of ith sampleHumidity data z of the ith sample i Ith sample temperature data b i Initial weight of environmental influence parameter P, test microorganism aerosol disinfection time length related to ith sample +.>And interactions between functions to form a functional relationship:
that is to say,the initial weight of the environmental impact parameters of the model is optimized through the functional relation, and the microbial aerosol has stronger resistance to sterilization in a high-humidity high-heat environment, so that the environmental impact parameters of the model are considered seriously. The input sample number of the model reflects a large number of sample numbers, so that the change of disinfection effects under different environmental conditions can be better captured, and the model can learn the mode of environmental influence more accurately by increasing the sample numbers, so that the reliability and the robustness of prediction are improved; the difference between the predicted disinfection test efficiency of the ith sample and the actual disinfection test efficiency is helpful for judging the accuracy and error of the model, and the reference of the actual disinfection effect can be obtained by considering the actual efficiency, so that the predicted result can be adjusted more accurately; the influence of environment on the disinfection effect can be captured by considering environmental parameters such as humidity, temperature and the like, and the comprehensive consideration enables the model to more accurately predict the disinfection effect under different environmental conditions, so that the applicability and the accuracy of the model are improved; the initial weight of the environment influence parameter is the weight of the original environment influence parameter of the model, and the accuracy of the model can be higher by optimizing the original weight; considering the length of disinfection time may better reflect the time factors of the actual disinfection process. This is important for efficacy assessment at different disinfection times, helping the model to predict more accurately. The operations of indexes, logarithms, trigonometric functions and the like in the algorithm enable the relevance among different parameters to be considered, are beneficial to capturing complex relations among environmental parameters, and improve the expression capacity of the model. The attention degree of the model to the environmental influence factors can be adjusted by carrying out weighted average on the difference between the predicted value and the actual value of the model, which is helpful for reducing the interference of environmental change and improving the sensitivity of the model to the disinfection effect. Adjusting and correcting the functional relation by using an abnormal adjustment value delta of the optimization weight of the environmental influence parameter, and reducing errors caused by abnormal data or error items The influence is achieved, so that the optimization weight K of the environmental influence parameter is generated more accurately, and the accuracy and the reliability of the optimization adjustment of the environmental influence parameter weight of the model for the model of the sterile data prediction are improved. Meanwhile, the adjustment value in the formula can be adjusted according to actual conditions and is applied to different parameters of the disinfection data prediction model, so that the flexibility and applicability of the algorithm are improved.
Preferably, step S5 comprises the steps of:
step S51: the method comprises the steps of carrying out real-time updating treatment on microorganism aerosol data to generate real-time microorganism aerosol data;
step S52: according to the real-time microbial aerosol data, the environment data is updated in real time to generate real-time environment data;
step S53: data integration is carried out on the real-time microorganism aerosol data and the real-time environment data, and real-time data to be disinfected are generated;
step S54: and transmitting the real-time data to be disinfected to an optimized disinfection data prediction model for disinfection data prediction, and generating disinfection prediction data.
The invention generates the real-time microorganism aerosol data by carrying out the real-time updating processing on the microorganism aerosol data, and the real-time updating ensures that the data can reflect the latest microorganism aerosol load condition, ensures that the data used by the prediction model is always consistent with the actual condition, and can more accurately reflect the microorganism condition of target equipment, thereby providing actual data support for the subsequent disinfection effect prediction. The environment data is updated in real time according to the real-time microbial aerosol data, the real-time environment data is generated, the real-time environment data can reflect the change of the current environment, the latest environment influence factors are ensured to be considered when the model is predicted, the accuracy and the practicability of the prediction model are improved, and the prediction is more in line with the actual situation. The real-time microbial aerosol data and the real-time environment data are subjected to data integration to generate real-time to-be-disinfected data, and the two parts of data can be integrated to combine the microbial aerosol load and the environment condition to form actual to-be-disinfected data, so that the comprehensiveness of the to-be-disinfected data, including the comprehensive influence of the microbial load and the environment factors, is ensured. The real-time data to be disinfected is transmitted to the optimized disinfection data prediction model to predict the disinfection data, disinfection prediction data are generated, the real-time data are applied to the prediction model, the instant prediction of the disinfection effect is realized, a prediction result can be provided when the disinfection operation is carried out, and an operator is guided to carry out necessary adjustment, so that the disinfection operation is more efficient and effective.
Preferably, step S6 comprises the steps of:
step S61: building a physical model framework of the equipment to be detected on the target equipment to be detected by utilizing a three-dimensional modeling technology, and filling data by utilizing real-time data to be disinfected to generate a physical model of the target equipment to be detected;
step S62: and carrying out disinfection simulation operation of the equipment to be detected on the physical model of the target equipment to be detected by using the disinfection prediction data, and generating a simulated disinfection effect evaluation report.
According to the invention, the physical model of the target equipment to be detected is constructed by utilizing the three-dimensional modeling technology, and meanwhile, the real-time data to be disinfected is utilized to carry out data filling, so that the physical model of the target equipment to be detected is generated, the actual equipment can be converted into a model which can be processed by a computer, the construction of a virtual simulation environment is realized, the model can reflect the current microorganism load condition more accurately by filling the real-time data, and the authenticity and reliability of simulation evaluation are ensured. The physical model of the target equipment to be detected is subjected to disinfection simulation operation by using the disinfection prediction data, a simulated disinfection effect evaluation report is generated, and the disinfection simulation operation is performed in a virtual environment, so that the distribution and the disinfection effect of the microorganism aerosol under different disinfection strategies and conditions can be simulated, the effect of different disinfection schemes can be predicted by the guidance of the disinfection prediction data, and a detailed evaluation report is generated, so that the disinfection effect difference under different operation conditions is revealed.
The method has the beneficial effects that the disinfection effect can be comprehensively evaluated in real conditions and virtual environments by integrating the real-time microorganism aerosol data, the environment data and the disinfection prediction data, so that the evaluation is more objective and accurate, and meanwhile, the influence of external environment factors on the disinfection effect is considered. By establishing an optimized disinfection data prediction model, the method can accurately predict disinfection effects under different environmental conditions, and the prediction accuracy of the model is improved by adopting methods such as a support vector machine algorithm, environmental influence parameter optimization and the like, so that reliable guidance is provided for actual disinfection operation. By using a support vector machine algorithm and the like, a disinfection data prediction model is established, and real-time microorganism aerosol data, environment data and disinfection prediction data are combined, so that not only is the microorganism load considered, but also the environmental influence factor is considered, and the model is more accurate and reliable. Through iterative optimization of the model, the model can be better adapted to different environmental conditions, and the prediction accuracy and practicality are improved. The microbial aerosol data and the environmental data are updated in real time, and the disinfection data prediction model is combined, so that the instant prediction of the disinfection effect is realized, the disinfection strategy can be adjusted in real time according to the prediction result, the real-time performance and the flexibility of operation are improved, the combination of the real-time data and the prediction model enables the prediction result to better reflect the current disinfection effect, an operator can make a timely decision according to the real-time prediction, and the real-time performance and the flexibility of operation are improved. By performing disinfection simulation operation in the virtual environment, resource waste and risk in actual operation are avoided, effects of different strategies can be explored in the virtual environment by simulation evaluation, and disinfection operation is optimized, so that resource cost and experimental risk are reduced. By generating a detailed simulated disinfection effect evaluation report, the method can provide a basis for scientific decision making for an operator, and the report contains effect comparison under different operation conditions, so that the operator can select an optimal disinfection strategy, and the scientificity and reliability of decision making are improved. By combining the real-time disinfection related data to continuously optimize the disinfection data prediction model, operators can be guided to select a more effective disinfection strategy, the disinfection effect is improved, the load of microorganism aerosol is reduced, and a safer working environment is created. Powerful support and guidance are provided for actual disinfection operation from data acquisition to prediction model establishment to virtual simulation operation, and a scientific, efficient and accurate method for evaluation and operation of disinfection effects is provided.
Drawings
FIG. 1 is a schematic flow chart of a method for simulating and evaluating the disinfection effect of a microbial aerosol surface according to the present invention;
FIG. 2 is a flowchart illustrating the detailed implementation of step S2 in FIG. 1;
FIG. 3 is a flowchart illustrating the detailed implementation of step S4 in FIG. 1;
FIG. 4 is a flowchart illustrating the detailed implementation of step S5 in FIG. 1;
the achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
The following is a clear and complete description of the technical method of the present patent in conjunction with the accompanying drawings, and it is evident that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, are intended to fall within the scope of the present invention.
Furthermore, the drawings are merely schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus a repetitive description thereof will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. The functional entities may be implemented in software or in one or more hardware modules or integrated circuits or in different networks and/or processor methods and/or microcontroller methods.
It will be understood that, although the terms "first," "second," etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another element. For example, a first element could be termed a second element, and, similarly, a second element could be termed a first element, without departing from the scope of example embodiments. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.
In order to achieve the above objective, referring to fig. 1 to 4, the present invention provides a simulation evaluation method for the disinfection effect of a microbial aerosol surface, comprising the following steps:
step S1: acquiring target equipment to be detected; the method comprises the steps of collecting and preprocessing microorganism aerosol data of target equipment to be detected to generate microorganism aerosol data;
step S2: acquiring aerosol disinfection data; performing a microbial aerosol surface disinfection test on the target equipment to be detected by using aerosol disinfection data, and performing disinfection test efficiency calculation to generate disinfection test efficiency data; data integration is carried out on the microorganism aerosol data, the aerosol disinfection data and the disinfection test efficiency data, and test aerosol disinfection effect data is generated;
Step S3: the method comprises the steps that a sensor is used for collecting environmental data around target equipment to be detected, and environmental data are generated; classifying the test aerosol disinfection effect data according to the environment data to obtain disinfection environment type data, and generating classified test aerosol disinfection effect data;
step S4: performing microbial aerosol surface disinfection data prediction model establishment and model optimization by using a support vector machine algorithm and classification test aerosol disinfection effect data to generate an optimized disinfection data prediction model;
step S5: the method comprises the steps of updating and integrating microorganism aerosol data and environment data in real time to generate real-time data to be disinfected; transmitting the real-time data to be disinfected to an optimized disinfection data prediction model for disinfection data prediction, and generating disinfection prediction data;
step S6: and establishing a physical model of the equipment to be detected according to the target equipment to be detected and the real-time data to be disinfected, and performing disinfection simulation operation of the equipment to be detected by utilizing the disinfection prediction data to generate a simulated disinfection effect evaluation report.
According to the invention, through actively acquiring the microbial aerosol data of the surface of the target equipment, the microbial load condition of the surface of the equipment, including the distribution density and the types of microorganisms such as bacteria and viruses, can be deeply known, the accuracy of subsequent analysis and model establishment is ensured, a real and detailed data basis is provided for subsequent disinfection effect evaluation, and the evaluation of the disinfection effect is more real and reliable. By acquiring aerosol disinfection data and performing a disinfection test on target equipment, the actual disinfection operation can be simulated, and the effectiveness of the disinfection method is verified. When the disinfection test is carried out, the disinfection effect of different disinfection strategies on the microbial aerosol can be quantitatively measured by calculating the disinfection test efficiency data, so that objective indexes are provided for comparison and optimization of different disinfection conditions, the microbial aerosol data, the aerosol disinfection data and the disinfection test efficiency data are integrated, comprehensive test aerosol disinfection effect data can be established, a foundation is provided for subsequent analysis and model construction, and the disinfection effect and the operation efficiency are further improved. By collecting environmental data around the target device by using the sensor, environmental information closely related to the disinfection effect, such as temperature, humidity, air flow and the like, can be acquired, the factors can influence the disinfection effect, and after the environmental data are generated, the environmental background of the disinfection operation is known more accurately, so that more accurate background information is provided for explanation and prediction of the follow-up disinfection effect. When the test aerosol disinfection effect data is classified according to the environment data, the disinfection effects under different environment conditions can be grouped to form a disinfection environment type data classification, the influence degree of different environments on the disinfection effect is deeply analyzed, the potential influence mechanism of environmental factors on disinfection is revealed, the disinfection effect difference under different conditions can be better understood by generating the classification test aerosol disinfection effect data, and richer data input is provided for the establishment and optimization of a follow-up disinfection effect prediction model. By utilizing a support vector machine algorithm and classifying test aerosol disinfection effect data to establish a prediction model and performing model optimization, potential rules and correlations are mined from the existing classification data, so that a more accurate and reliable microbial aerosol surface disinfection data prediction model is established, the influence of environmental factors, disinfection conditions, microbial loads and other aspects can be fully considered by the prediction model, the prediction accuracy is improved, and the performance of the prediction model is further improved through model optimization, so that the prediction model has stronger applicability and stability under different environments and conditions. The real-time to-be-sterilized data is generated by updating and integrating the microbial aerosol data and the environment data in real time, the real-time to-be-sterilized data is transmitted to the optimized sterilizing data prediction model for prediction, and the prediction and monitoring of the real-time sterilizing effect are realized. By establishing a physical model according to target equipment to be detected and real-time data to be disinfected and performing simulation operation by utilizing disinfection prediction data, the simulation evaluation of the disinfection effect of the equipment to be detected is realized, and the simulation operation can simulate the process of actual disinfection operation in a virtual environment, so that the prediction of the disinfection effect under different conditions is realized, the difference of the disinfection effects under different conditions is better understood, the possible problems and improvement space are found, and guidance and reference are provided for the actual operation. Therefore, the simulation evaluation method of the microbial aerosol surface disinfection effect can judge the content of the microbial aerosol, can not cause excessive disinfection spray to influence the health of people, and can not effectively disinfect the microbial aerosol surface because of too little disinfection spray dose, thereby ensuring the disinfection effect of the microbial aerosol surface.
In the embodiment of the present invention, as described with reference to fig. 1, a step flow diagram of a method for simulating and evaluating the disinfection effect of a surface of a microbial aerosol according to the present invention is provided, and in the embodiment, the method for simulating and evaluating the disinfection effect of a surface of a microbial aerosol includes the following steps:
step S1: acquiring target equipment to be detected; the method comprises the steps of collecting and preprocessing microorganism aerosol data of target equipment to be detected to generate microorganism aerosol data;
in the embodiment of the invention, a surgical table in an operating room is selected as target equipment to be detected. The method comprises the steps of using high-resolution electron microscope equipment to sample the surface of an operating table by using test paper to obtain microorganism aerosol data, scanning different areas under the microscope, capturing area images of microorganism particles, performing image processing on each area image, including monitoring the microorganism aerosol of the area image, and performing average calculation on the microorganism aerosol of each area image to accurately extract the quantity information and approximate distribution areas of the microorganism particles so as to obtain detailed data about microorganism load.
Step S2: acquiring aerosol disinfection data; performing a microbial aerosol surface disinfection test on the target equipment to be detected by using aerosol disinfection data, and performing disinfection test efficiency calculation to generate disinfection test efficiency data; data integration is carried out on the microorganism aerosol data, the aerosol disinfection data and the disinfection test efficiency data, and test aerosol disinfection effect data is generated;
In the embodiment of the invention, recorded aerosol disinfection data are firstly obtained, and the data comprise parameters such as the use condition, concentration, time and the like of the disinfectant under different conditions. In a laboratory environment, a selected target surgical table is subjected to a microbial aerosol surface disinfection test, disinfectant with a certain concentration is smeared on the surface of the surgical table, disinfection time is recorded, an actual disinfection process is simulated, after disinfection, a sampling plate and other modes are used for collecting microbial aerosol samples, the change of the number of microorganisms before and after disinfection is calculated through a culture method, and the disinfection efficiency is calculated according to the changed number of microorganisms. For example, a disinfectant containing chloride was selected at a concentration of 1000 ppm, uniformly applied to the surface of the operating table, and after 15 minutes of disinfection, a sample was collected from the surface, and the disinfection efficiency was 80% based on the calculation. The efficiency data is integrated with the previously collected microbial aerosol data and aerosol disinfection data to obtain test aerosol disinfection effect data.
Step S3: the method comprises the steps that a sensor is used for collecting environmental data around target equipment to be detected, and environmental data are generated; classifying the test aerosol disinfection effect data according to the environment data to obtain disinfection environment type data, and generating classified test aerosol disinfection effect data;
In an embodiment of the present invention, a set of sensors, including temperature, humidity, ventilation rate, etc., are disposed around the target surgical table. The sensors monitor the environment of the operating table in real time, for example, the sensors record the environment of the operating table, namely, the environment in which the disinfectant is suitable to fully play a role, with the temperature of 25 ℃, the humidity of 50% and the ventilation rate of 500 cubic meters per hour, according to the real-time environment data. The test aerosol disinfection effect data obtained before are classified according to the standard environment just divided. If the ambient temperature, humidity and ventilation rate are all within the range suitable for disinfection, these data are labeled as being of the same category, such as "good environment", thereby generating categorized test aerosol disinfection effect data, which distinguishes between disinfection effect data under different environmental conditions.
Step S4: performing microbial aerosol surface disinfection data prediction model establishment and model optimization by using a support vector machine algorithm and classification test aerosol disinfection effect data to generate an optimized disinfection data prediction model;
in the embodiment of the invention, a Support Vector Machine (SVM) algorithm is selected, a microbial aerosol surface disinfection data prediction model is established for classified test aerosol disinfection effect data, data in an excellent environment in the classified test aerosol disinfection effect data is used as a training set, the data comprises related microbial aerosol data, disinfection data and environment data, the SVM algorithm is used for training the model, and a mapping relation between the microbial aerosol disinfection data and the disinfection effect is established. The classified test aerosol disinfection effect data is divided into a training set and a test set. The training set is transmitted to an initial disinfection effect prediction model for training, a preliminary disinfection data prediction model is obtained, optimization adjustment of environmental parameter weights is carried out on the model according to actual environmental data, iterative training is carried out by using the testing set, and performance of the model is continuously optimized. Finally, an optimized disinfection data prediction model is obtained, and disinfection effects under different environmental conditions can be predicted more accurately.
Step S5: the method comprises the steps of updating and integrating microorganism aerosol data and environment data in real time to generate real-time data to be disinfected; transmitting the real-time data to be disinfected to an optimized disinfection data prediction model for disinfection data prediction, and generating disinfection prediction data;
in the embodiment of the invention, the real-time updating and the data integration of the microorganism aerosol data and the environment data are started to generate the real-time data to be disinfected. The real-time sensor continuously collects environmental data around the operating table, such as current temperature, humidity, ventilation rate and the like, and as the surface of the operating table may have continuous microorganism deposition and diffusion, electron microscope scanning is periodically performed to acquire new microorganism aerosol data, and the new data are continuously integrated and updated with the data recorded before. The real-time environment data is combined with the latest microorganism aerosol data to generate real-time to-be-disinfected data, for example, microorganisms can be more easily bred and spread in a hot and humid environment, and the real-time to-be-disinfected data reflects the microorganism load condition under the current environment condition. The real-time data to be disinfected is transmitted to a previously established disinfection data prediction model, and the model predicts the disinfection effect under the current condition according to the real-time environment data and the microbial aerosol data, for example, in a high-temperature and high-humidity environment, the model can predict that the disinfection effect is poor, and the disinfection dosage and time need to be adjusted, so that real-time disinfection prediction data is generated, and the disinfection effect under different environment conditions is reflected.
Step S6: and establishing a physical model of the equipment to be detected according to the target equipment to be detected and the real-time data to be disinfected, and performing disinfection simulation operation of the equipment to be detected by utilizing the disinfection prediction data to generate a simulated disinfection effect evaluation report.
In the embodiment of the invention, based on the detailed image of the target surgical table and the real-time data to be disinfected collected before, a physical model of equipment to be detected is built, the details such as the appearance, the surface characteristics and the like of the surgical table are accurately converted into a digitalized physical model through a three-dimensional modeling technology, and the real-time data to be disinfected is used for filling the physical model to reflect the current distribution situation of the microbial aerosol. After the physical model is built, the disinfection prediction data obtained before the physical model is introduced are predicted according to different environmental conditions and disinfection effects, the disinfection process of an operating table is simulated, for example, in a high-temperature and high-humidity environment, the predicted disinfection effect is poor, the microorganism residue condition can be observed in the simulation, and the disinfection process under different conditions can be simulated by introducing the disinfection prediction data into the physical model, so that the distribution condition of microorganism aerosol can be predicted. A simulated disinfection effect assessment report is generated based on the simulated disinfection effect, and the report details simulation results of the combination of disinfection prediction data and a physical model under different environmental conditions, for example, the report may indicate that the disinfection effect may be non-ideal under certain environmental conditions, thereby providing advice for medical cleaning personnel to optimize the disinfection process.
Preferably, step S1 comprises the steps of:
step S11: acquiring target equipment to be detected;
step S12: the method comprises the steps of carrying out regional microorganism aerosol data acquisition on target equipment to be detected by utilizing electron microscope equipment, and generating regional microorganism aerosol image data;
step S13: and carrying out aerosol data preprocessing of the target equipment to be detected according to the regional microorganism aerosol image data to generate microorganism aerosol data.
The method and the device for acquiring the target equipment to be detected establish a foundation for subsequent acquisition and analysis of the microbial aerosol data, ensure that the acquired data are closely related to the actual equipment to be detected, and further improve the accuracy and reliability of the evaluation result. The method has the advantages that the electron microscope equipment is utilized to collect regional microorganism aerosol data of the target equipment to be detected, high-resolution image data is obtained, the high-resolution image data can show the characteristics of distribution, density, morphology and the like of microorganisms in more detail, more abundant information is provided for subsequent analysis, and the regional collection can focus on the microorganism load difference of different areas, so that evaluation is more detailed and comprehensive, and the calculated amount of data processing is reduced. And performing aerosol data preprocessing according to the regional microbial aerosol image data to generate microbial aerosol data, wherein the preprocessing can convert the regional microbial aerosol image data into microbial aerosol data of corresponding target equipment to be detected, so that the aerosol data extracted from the image has better interpretability and usability.
In the embodiment of the invention, first, a target to-be-detected device is selected, and a surgical table is taken as an example. This is a device that requires high levels of sterilization in a typical medical environment, selecting a surgical table as the target device, and specifically targeting the collection of microbiological aerosol data. By using advanced electron microscope equipment to collect the microbial aerosol data in different areas of the surface of the surgical table, key information such as the distribution, aggregation degree and density of the microbes can be captured through high-resolution microscope images, and the images can be used as the basis for generating the microbial aerosol data. Based on the acquired regional microorganism aerosol image data, we perform aerosol data preprocessing. Firstly, we split the image, separate different regions and microorganism particles, quantify the number, size and distribution of microorganism particles in each region by image processing technology, integrate these data, and generate microorganism aerosol data for the target device.
Preferably, step S13 comprises the steps of:
step S131: carrying out statistical analysis on the microbial aerosol distribution of the regional microbial aerosol image data to generate regional biological aerosol data;
Step S132: calculating the average value of the whole microbial aerosol data of the target equipment to be detected according to the regional microbial aerosol data, and generating initial microbial aerosol data;
step S133: and carrying out data normalization on the initial microbial aerosol data by using a minimum-maximum normalization method to generate microbial aerosol data.
According to the invention, through carrying out statistical analysis on the microbial aerosol distribution of regional microbial aerosol image data, the distribution situation of microorganisms in different regions can be known on a fine scale, the statistical analysis can reveal the spatial distribution difference of microbial loads, and the method is helpful for identifying possible high-load regions and low-load regions, and the difference information has important significance for formulating disinfection strategies and evaluation effect accuracy for different regions. By calculating the overall microorganism aerosol data average value of the target equipment to be detected according to the regional microorganism aerosol data, a preliminary overall data index can be obtained, the overall microorganism load condition of the equipment is reflected, and more accurate microorganism aerosol content is provided for subsequent analysis and comparison. The data normalization is carried out on the initial microbial aerosol data by a minimum-maximum normalization method, the data is mapped into a specific range, the normalization treatment can eliminate the influence caused by different data scales, so that more visual and comparable analysis can be carried out among different data, the normalized data is helpful for better understanding the distribution situation of the microbial aerosol, and a more consistent data base is provided for the establishment and prediction of a subsequent model.
In the embodiment of the invention, the acquired regional microorganism aerosol image data is analyzed in detail, the distribution condition and density of microorganism particles in the image are identified through image processing and analysis technology, and key characteristics such as the number, the size, the shape and the like of the microorganism particles in different regions are counted to obtain regional microorganism aerosol data. According to the microbial aerosol data of the area, calculating the microbial aerosol data average value of the whole surface of the target equipment to be detected, integrating the data of different areas, calculating the average value, and obtaining the more accurate microbial aerosol quantity of the whole operating table through the average value so as to obtain a more global microbial aerosol distribution trend, thereby providing a foundation for subsequent data processing and analysis. In order to ensure the consistency and comparability of the data, a minimum-maximum normalization method is used for normalizing the initial microbial aerosol data, the value range of the data is mapped to a unified interval, the influence caused by different data scales is eliminated, and the data is more comparability and explanatory.
Preferably, step S2 comprises the steps of:
step S21: acquiring aerosol disinfection data;
Step S22: performing a microbial aerosol surface disinfection test on the target equipment to be detected by utilizing aerosol disinfection data, and performing microbial aerosol data acquisition of the disinfection test to generate aerosol disinfection test data;
step S23: performing disinfection efficiency calculation on aerosol disinfection test data by using a microbial aerosol disinfection efficiency algorithm to generate disinfection test efficiency data;
step S24: and integrating the data of the microorganism aerosol, the aerosol disinfection data and the disinfection test efficiency data to generate test aerosol disinfection effect data.
The invention acquires aerosol disinfection data, ensures that the actual disinfection operation result is acquired, can comprise disinfection effect information of different disinfection strategies, conditions and disinfection time, can reflect the influence of different operation conditions on microbial aerosol, and provides reliable actual data sources for subsequent disinfection effect evaluation and prediction. The method has the advantages that the microorganism aerosol surface disinfection test is carried out on the target equipment by utilizing the aerosol disinfection data, the data acquisition is carried out, the aerosol disinfection test data are generated, the operability test can simulate real disinfection operation, the data of the sterilized microorganism aerosol are actually measured, and an experimental data basis is provided for subsequent disinfection effect evaluation and analysis. The disinfection efficiency calculation is carried out on the aerosol disinfection test data by utilizing the microbial aerosol disinfection efficiency algorithm, so that the disinfection test efficiency data is generated, the killing efficiency of the microbial aerosol under different disinfection strategies or conditions can be clearly shown, and objective indexes are provided for evaluating the effectiveness of different operation schemes by the disinfection efficiency data. The method has the advantages that the microorganism aerosol data, the aerosol disinfection data and the disinfection test efficiency data are subjected to data integration to generate test aerosol disinfection effect data, the data of different layers can be integrated, a complete data set is provided for subsequent analysis, the integrated data can better reveal the disinfection effect difference under different operation conditions, and the method is beneficial to more accurately carrying out subsequent model establishment and prediction.
As an example of the present invention, referring to fig. 2, a detailed implementation step flow diagram of step S2 in fig. 1 is shown, where step S2 includes:
step S21: acquiring aerosol disinfection data;
in the embodiment of the invention, aerosol disinfection data are acquired through professional equipment, and the data cover disinfection operation processes under different conditions. These data may include key parameters of the concentration, time of action, temperature, etc. of the disinfectant, as well as microbial aerosol sampling data at various points in time.
Step S22: performing a microbial aerosol surface disinfection test on the target equipment to be detected by utilizing aerosol disinfection data, and performing microbial aerosol data acquisition of the disinfection test to generate aerosol disinfection test data;
in the embodiment of the invention, the aerosol disinfection data is utilized to carry out the microbial aerosol surface disinfection test on the target equipment to be detected. During the disinfection process, the distribution of the microbial aerosol is sampled, and the disinfected microbial aerosol data is obtained, wherein the data records the distribution and the quantity of the microbes after the disinfection operation.
Step S23: performing disinfection efficiency calculation on aerosol disinfection test data by using a microbial aerosol disinfection efficiency algorithm to generate disinfection test efficiency data;
In an embodiment of the invention, the disinfection efficiency is calculated using a microbial aerosol disinfection efficiency algorithm based on disinfection test data. The algorithm considers the inactivation rate and the disinfection effect of microorganisms under different conditions, so that the disinfection efficiency is quantitatively evaluated, and disinfection test efficiency data are obtained, so that a basis is provided for subsequent data integration.
Step S24: and integrating the data of the microorganism aerosol, the aerosol disinfection data and the disinfection test efficiency data to generate test aerosol disinfection effect data.
In the embodiment of the invention, the microbial aerosol data, the aerosol disinfection data and the disinfection test efficiency data which are collected before are integrated to generate the test aerosol disinfection effect data, and the test aerosol disinfection effect data comprises microbial aerosol distribution condition and disinfection efficiency information before and after disinfection operation.
Preferably, the microbial aerosol sterilization efficiency algorithm in step S23 is as follows:
;
wherein P is expressed as disinfection test efficiency data, t 2 Expressed as the end time of the disinfection test, t 1 Expressed as the start time of the disinfection test, N is expressed as an equal area image block of the target device to be detected, A i Denoted as initial concentration of microbial aerosol in the ith image block, t denoted as current time node of the disinfection test, B i Expressed as final concentration of microbial aerosol in the ith image patch, M is expressed as area size of the image patch, M Total (S) Expressed as the total area of the test area, k expressed as the average density of the microbial aerosol, Q expressed as the air supply rate of the target device to be tested, and τ expressed as the abnormal adjustment value of the disinfection test efficiency data.
The invention utilizes a microbial aerosol disinfection efficiency algorithm which fully considers the end time t of disinfection test 2 Start time t of disinfection test 1 Equal area image block N of target to-be-detected equipment and initial concentration A of microorganism aerosol in ith image block i The current time node t of the disinfection test, the final concentration B of the microbial aerosol in the ith image block i The area size M of the image block and the total area M of the test area Total (S) The average density k of the microbial aerosol, the air supply rate Q of the target device to be detected, and the function to form a functional relationship:
that is to say,the function relation is used for calculating the efficiency of the disinfection test on aerosol disinfection test data, so that the evaluation process of the disinfection efficiency is better grasped, and meanwhile, the influence of different factors on the disinfection effect can be more accurately identified and explained, and a more powerful support is provided for the subsequent disinfection decision. The end time and the start time of the disinfection test determine the time range of the disinfection test, are helpful for determining the duration of disinfection, and can be adjusted according to actual conditions so as to capture the whole change track of the disinfection process; the number of the equal-area image blocks of the target equipment to be detected can be more accurately used for capturing the distribution change of the microbial aerosol at different positions by dividing the equipment to be detected into a plurality of small blocks; the initial concentration and the final concentration of the microbial aerosol in the ith image block show the change of the concentration of the microbial aerosol in calculation, are directly related to the evaluation of the disinfection effect, and are helpful for more accurately evaluating the disinfection conditions of different areas; the size of the area of the image block and the total area of the test area, and the contribution of different image blocks can be weighted according to the size of the image block by using the area parameters, so that the overall effect is reflected more accurately; the average density of the microbial aerosol and the air supply rate of the device take the characteristics of microbial propagation into account in the algorithm, so that the algorithm can take the propagation and change of the microbes under different conditions into account, the density of the microbes can influence the reduction rate of the microbes, and thus the evaluation of the disinfection effect is influenced, and the air supply rate influences the propagation and distribution of the microbial aerosol, so that the influence of different air supply rates on the disinfection efficiency is taken into account in the calculation. And the function relation is adjusted and corrected by using the abnormal adjustment value tau of the disinfection test efficiency data, so that the error influence caused by abnormal data or error items is reduced, the disinfection test efficiency data P is generated more accurately, and the accuracy and reliability of the calculation of the disinfection efficiency of the aerosol disinfection test data are improved. Meanwhile, the adjustment value in the formula can be adjusted according to actual conditions and is applied to different aerosol disinfection test data, so that the flexibility and applicability of the algorithm are improved.
Preferably, step S3 comprises the steps of:
step S31: the method comprises the steps that a sensor is used for collecting environmental data around target equipment to be detected, and environmental data are generated;
step S32: performing environment type design of equipment to be detected according to the environment data to generate environment type data;
step S33: and classifying the test aerosol disinfection effect data according to the environment type data to generate classified test aerosol disinfection effect data.
According to the invention, the sensor is used for collecting the surrounding environment data of the target equipment to generate the environment data, the background information related to the disinfection effect, such as temperature, humidity, air flow and the like, can be provided, the follow-up evaluation can better consider the influence of external factors on the disinfection effect, and the accuracy and the practicability of the evaluation result are improved. According to the environmental data, the environmental category of the target equipment is designed, the environmental category number is generated, the characteristics and differences under different environmental conditions can be identified by analyzing and classifying the environmental data, the change and influence of different disinfection environments can be considered better, and a foundation is provided for subsequent classification evaluation. The test aerosol disinfection effect data is subjected to disinfection environment type data classification according to the environment type data to generate classification test aerosol disinfection effect data, and the classification can distinguish disinfection effects under different environment conditions to reveal differences of the disinfection effects under different environment backgrounds, so that the test aerosol disinfection effect data is favorable for more accurately evaluating the real situation of the disinfection effects, and richer data input is provided for model establishment and prediction.
In the embodiment of the invention, the professional sensor is used for collecting data of the environment around the target equipment to be detected, the key parameters comprise temperature, humidity, air flow speed and the like, the sensor can acquire environment information in real time, and the accuracy of subsequent data analysis and processing is ensured. Environmental data obtained by the sensor designs proper environmental categories which can comprise different temperature ranges, humidity levels, ventilation states and the like, and the environmental category design can better reflect real environmental conditions and provides proper basis for subsequent classification analysis. Based on environment type data, the test aerosol disinfection effect data obtained before are classified, and the environment type and the disinfection effect data are matched, so that the classified test aerosol disinfection effect data under different environment conditions can be obtained, and the method is beneficial to more accurately evaluating the change of the disinfection effect under different environment conditions.
Preferably, step S4 comprises the steps of:
step S41: establishing a mapping relation of microbial aerosol surface disinfection data prediction by using a support vector machine algorithm, and generating an initial disinfection effect prediction model;
step S42: performing data division on time sequence on the classified test aerosol disinfection effect data to generate a classified test aerosol disinfection effect training set and a classified test aerosol disinfection effect testing set;
Step S43: transmitting the classified test aerosol disinfection effect training set to an initial disinfection effect prediction model for model training, and generating a disinfection effect prediction model;
step S44: optimizing and adjusting the environmental impact parameter weight of the model for the disinfection data prediction model by using an environmental impact parameter model optimizing algorithm, and performing iterative training by using a classified test aerosol disinfection effect training set to generate an adjusted disinfection data prediction model;
step S45: and performing model test on the adjustment disinfection data prediction model by using the classified test aerosol disinfection effect test set to generate an optimization disinfection data prediction model.
According to the invention, the mapping relation of the microbial aerosol surface disinfection data prediction is established by using a support vector machine algorithm, and the initial disinfection effect prediction model is generated, so that the connection between the microbial aerosol disinfection effect and other variables can be established under the condition that too much priori information is not available, the initial model provides a basic framework, and a starting point is provided for the optimization and adjustment of the follow-up model. The data of the classified test aerosol disinfection effect data are divided in time sequence to generate a classified test aerosol disinfection effect training set and a test set, and the data division can divide the data set into two parts for model training and testing, so that the model is ensured to evaluate and verify on different data, and the phenomenon of over fitting or under fitting is prevented. The training set for classifying and testing the aerosol disinfection effect is transmitted to the initial disinfection effect prediction model for model training, the disinfection effect prediction model is generated, the training process adjusts the initial model by utilizing the existing data, so that the training process is more in line with the actual situation, the training model can learn the relevance and rules among the data, and the accuracy of prediction is improved. The environmental impact parameter model optimization algorithm is utilized to carry out optimization adjustment on the environmental impact parameter weight of the disinfection data prediction model, and meanwhile, the classification test aerosol disinfection effect training set is utilized to carry out iterative training to generate the adjustment disinfection data prediction model. And performing model test on the adjustment disinfection data prediction model by using the classification test aerosol disinfection effect test set to generate an optimization disinfection data prediction model, and verifying generalization capability and prediction effect of the model through the model test to ensure that the model is reliable in performance on new data, so that the prediction model is more stable and reliable, thereby providing high-quality prediction model support for the prediction of actual disinfection effects.
As an example of the present invention, referring to fig. 3, a detailed implementation step flow diagram of step S4 in fig. 1 is shown, where step S4 includes:
step S41: establishing a mapping relation of microbial aerosol surface disinfection data prediction by using a support vector machine algorithm, and generating an initial disinfection effect prediction model;
in the embodiment of the invention, a Support Vector Machine (SVM) algorithm is used for establishing the prediction mapping relation between the surface disinfection data of the microbial aerosol and the disinfection effect, and the initial disinfection effect prediction model is based on the existing disinfection data and the microbial aerosol data, so that the prediction of the microbial distribution situation after the disinfection operation can be helped.
Step S42: performing data division on time sequence on the classified test aerosol disinfection effect data to generate a classified test aerosol disinfection effect training set and a classified test aerosol disinfection effect testing set;
in the embodiment of the invention, in order to perform model training and testing, the classified test aerosol disinfection effect data is divided in time sequence to obtain a classified test aerosol disinfection effect training set and a test set, and the data sets are used for training and testing the accuracy and generalization capability of the model.
Step S43: transmitting the classified test aerosol disinfection effect training set to an initial disinfection effect prediction model for model training, and generating a disinfection effect prediction model;
in the embodiment of the invention, the classified test aerosol disinfection effect training set divided before is transmitted to an initial disinfection effect prediction model for model training, and the model learns how to correlate the microbial aerosol data with the disinfection effect, so that the initial disinfection effect prediction model is generated.
Step S44: optimizing and adjusting the environmental impact parameter weight of the model for the disinfection data prediction model by using an environmental impact parameter model optimizing algorithm, and performing iterative training by using a classified test aerosol disinfection effect training set to generate an adjusted disinfection data prediction model;
in the embodiment of the invention, the disinfection data prediction model is further optimized by using an environmental impact parameter model optimization algorithm, the algorithm considers the influence of different environmental factors on the disinfection effect, such as environmental information of humidity, temperature and the like and environmental impact parameter weights before the model, and the weight is adjusted according to the classified test aerosol disinfection effect training set, so that the adjusted disinfection data prediction model is generated, and the environmental impact is more accurately considered.
Step S45: and performing model test on the adjustment disinfection data prediction model by using the classified test aerosol disinfection effect test set to generate an optimization disinfection data prediction model.
In the embodiment of the invention, the adjusted disinfection data prediction model is tested by using the classified test aerosol disinfection effect test set, and the performance and accuracy of the model can be evaluated by comparing the adjusted disinfection data prediction model with actual data, so that a final optimized disinfection data prediction model is generated.
Preferably, the environmental impact parametric model optimization algorithm in step S44 is as follows:
;
where K is expressed as an optimization weight of the environmental impact parameter, R is expressed as the number of input samples of the model, y i The predicted disinfection test efficiency expressed as the i-th sample,the actual disinfection test efficiency, z, expressed as the i-th sample i Humidity data, b, expressed as the i-th sample i Denoted as the ith sample temperature data, P is denoted as the initial weight of the environmental impact parameter,/for the sample temperature data>Expressed as the length of time the test microorganism aerosol was sterilized, with delta expressed as the abnormal adjustment of the optimization weights of the environmental impact parameters, to which the i-th sample relates.
The invention utilizes an environmental impact parameter model optimization algorithm which fully considers the input sample number R of the model and the forecast disinfection test efficiency y of the ith sample i Actual disinfection test efficiency of ith sampleHumidity data z of the ith sample i Ith sample temperature data b i Initial weight of environmental influence parameter P, test microorganism aerosol disinfection time length related to ith sample +.>And interactions between functions to form a functional relationship:
that is to say,by the function ofThe initial weight of the environmental impact parameters of the model is optimized, and the microbial aerosol has stronger resistance to sterilization in a high-humidity and high-heat environment, so that the environmental impact parameters of the model are considered seriously. The input sample number of the model reflects a large number of sample numbers, so that the change of disinfection effects under different environmental conditions can be better captured, and the model can learn the mode of environmental influence more accurately by increasing the sample numbers, so that the reliability and the robustness of prediction are improved; the difference between the predicted disinfection test efficiency of the ith sample and the actual disinfection test efficiency is helpful for judging the accuracy and error of the model, and the reference of the actual disinfection effect can be obtained by considering the actual efficiency, so that the predicted result can be adjusted more accurately; the influence of environment on the disinfection effect can be captured by considering environmental parameters such as humidity, temperature and the like, and the comprehensive consideration enables the model to more accurately predict the disinfection effect under different environmental conditions, so that the applicability and the accuracy of the model are improved; the initial weight of the environment influence parameter is the weight of the original environment influence parameter of the model, and the accuracy of the model can be higher by optimizing the original weight; considering the length of disinfection time may better reflect the time factors of the actual disinfection process. This is important for efficacy assessment at different disinfection times, helping the model to predict more accurately. The operations of indexes, logarithms, trigonometric functions and the like in the algorithm enable the relevance among different parameters to be considered, are beneficial to capturing complex relations among environmental parameters, and improve the expression capacity of the model. The attention degree of the model to the environmental influence factors can be adjusted by carrying out weighted average on the difference between the predicted value and the actual value of the model, which is helpful for reducing the interference of environmental change and improving the sensitivity of the model to the disinfection effect. And the function relation is adjusted and corrected by utilizing the abnormal adjustment value delta of the optimization weight of the environmental impact parameter, so that the error influence caused by abnormal data or error items is reduced, the optimization weight K of the environmental impact parameter is generated more accurately, and the accuracy and the reliability of the optimization adjustment of the environmental impact parameter weight of the model for the model of the aseptic data prediction model are improved. Meanwhile, the adjustment value in the formula can be adjusted according to actual conditions and is applied to cancellation Among different parameters of the toxic data prediction model, the flexibility and applicability of the algorithm are improved.
Preferably, step S5 comprises the steps of:
step S51: the method comprises the steps of carrying out real-time updating treatment on microorganism aerosol data to generate real-time microorganism aerosol data;
step S52: according to the real-time microbial aerosol data, the environment data is updated in real time to generate real-time environment data;
step S53: data integration is carried out on the real-time microorganism aerosol data and the real-time environment data, and real-time data to be disinfected are generated;
step S54: and transmitting the real-time data to be disinfected to an optimized disinfection data prediction model for disinfection data prediction, and generating disinfection prediction data.
The invention generates the real-time microorganism aerosol data by carrying out the real-time updating processing on the microorganism aerosol data, and the real-time updating ensures that the data can reflect the latest microorganism aerosol load condition, ensures that the data used by the prediction model is always consistent with the actual condition, and can more accurately reflect the microorganism condition of target equipment, thereby providing actual data support for the subsequent disinfection effect prediction. The environment data is updated in real time according to the real-time microbial aerosol data, the real-time environment data is generated, the real-time environment data can reflect the change of the current environment, the latest environment influence factors are ensured to be considered when the model is predicted, the accuracy and the practicability of the prediction model are improved, and the prediction is more in line with the actual situation. The real-time microbial aerosol data and the real-time environment data are subjected to data integration to generate real-time to-be-disinfected data, and the two parts of data can be integrated to combine the microbial aerosol load and the environment condition to form actual to-be-disinfected data, so that the comprehensiveness of the to-be-disinfected data, including the comprehensive influence of the microbial load and the environment factors, is ensured. The real-time data to be disinfected is transmitted to the optimized disinfection data prediction model to predict the disinfection data, disinfection prediction data are generated, the real-time data are applied to the prediction model, the instant prediction of the disinfection effect is realized, a prediction result can be provided when the disinfection operation is carried out, and an operator is guided to carry out necessary adjustment, so that the disinfection operation is more efficient and effective.
As an example of the present invention, referring to fig. 4, a detailed implementation step flow diagram of step S4 in fig. 1 is shown, where step S5 includes:
step S51: the method comprises the steps of carrying out real-time updating treatment on microorganism aerosol data to generate real-time microorganism aerosol data;
in the embodiment of the invention, the microbial aerosol data are collected at regular intervals and the new data are processed to ensure the timely update of the data, for example, the microbial aerosol data are collected every hour to obtain the latest situation of microbial distribution after the current disinfection operation.
Step S52: according to the real-time microbial aerosol data, the environment data is updated in real time to generate real-time environment data;
in the embodiment of the invention, the environmental data is updated according to the real-time collected microbial aerosol data, for example, when the temperature data corresponding to the real-time microbial aerosol data is changed, if the original environmental data is used, the accuracy of the disinfection effect may be affected, so that the environmental data needs to be updated in real time to reflect the current disinfection environmental state.
Step S53: data integration is carried out on the real-time microorganism aerosol data and the real-time environment data, and real-time data to be disinfected are generated;
In the embodiment of the invention, the real-time updated microorganism aerosol data is integrated with the real-time environment data to generate the real-time data to be disinfected, so that the accurate data to be disinfected is ensured to be generated under the condition of considering the latest microorganism distribution and environment state.
Step S54: and transmitting the real-time data to be disinfected to an optimized disinfection data prediction model for disinfection data prediction, and generating disinfection prediction data.
In the embodiment of the invention, the real-time data to be disinfected is transmitted to the previously established disinfection data prediction model, and the model utilizes the latest data to predict the disinfection data to generate the disinfection prediction data, for example, the real-time data to be disinfected indicates that the concentration of microorganisms is higher and the environmental condition is poor, and the disinfection data prediction model is optimized to output disinfection dosage, disinfection time and corresponding effects after disinfection.
Preferably, step S6 comprises the steps of:
step S61: building a physical model framework of the equipment to be detected on the target equipment to be detected by utilizing a three-dimensional modeling technology, and filling data by utilizing real-time data to be disinfected to generate a physical model of the target equipment to be detected;
step S62: and carrying out disinfection simulation operation of the equipment to be detected on the physical model of the target equipment to be detected by using the disinfection prediction data, and generating a simulated disinfection effect evaluation report.
According to the invention, the physical model of the target equipment to be detected is constructed by utilizing the three-dimensional modeling technology, and meanwhile, the real-time data to be disinfected is utilized to carry out data filling, so that the physical model of the target equipment to be detected is generated, the actual equipment can be converted into a model which can be processed by a computer, the construction of a virtual simulation environment is realized, the model can reflect the current microorganism load condition more accurately by filling the real-time data, and the authenticity and reliability of simulation evaluation are ensured. The physical model of the target equipment to be detected is subjected to disinfection simulation operation by using the disinfection prediction data, a simulated disinfection effect evaluation report is generated, and the disinfection simulation operation is performed in a virtual environment, so that the distribution and the disinfection effect of the microorganism aerosol under different disinfection strategies and conditions can be simulated, the effect of different disinfection schemes can be predicted by the guidance of the disinfection prediction data, and a detailed evaluation report is generated, so that the disinfection effect difference under different operation conditions is revealed.
In the embodiment of the invention, an advanced three-dimensional modeling technology is utilized to establish a physical model architecture of the device to be detected based on the actual size and shape of the target device to be detected, for example, for a complex medical device, computer aided design software is used to create a highly accurate three-dimensional model comprising various components, details and connecting parts. The real-time data to be disinfected is applied to the physical model for data filling, for example, the real-time data show the distribution of the microbial aerosol, and the data are mapped to corresponding parts in the physical model so as to consider the distribution of the microbes and the disinfection effect in the simulation process. And performing disinfection simulation operation on the physical model of the target equipment to be detected by using the previously generated disinfection prediction data, wherein the prediction data shows that the disinfection effect of certain areas may be poor, and the simulation process simulates the diffusion and elimination condition of microorganisms in the actual disinfection operation so as to evaluate the disinfection effect. By simulating the disinfection effect evaluation report, detailed disinfection effect analysis can be obtained, and the disinfection effect analysis can possibly comprise information such as disinfection degree of each part, microorganism residue condition, possible risk area and the like, so as to be helpful for evaluating the effectiveness of disinfection operation.
The method has the beneficial effects that the disinfection effect can be comprehensively evaluated in real conditions and virtual environments by integrating the real-time microorganism aerosol data, the environment data and the disinfection prediction data, so that the evaluation is more objective and accurate, and meanwhile, the influence of external environment factors on the disinfection effect is considered. By establishing an optimized disinfection data prediction model, the method can accurately predict disinfection effects under different environmental conditions, and the prediction accuracy of the model is improved by adopting methods such as a support vector machine algorithm, environmental influence parameter optimization and the like, so that reliable guidance is provided for actual disinfection operation. By using a support vector machine algorithm and the like, a disinfection data prediction model is established, and real-time microorganism aerosol data, environment data and disinfection prediction data are combined, so that not only is the microorganism load considered, but also the environmental influence factor is considered, and the model is more accurate and reliable. Through iterative optimization of the model, the model can be better adapted to different environmental conditions, and the prediction accuracy and practicality are improved. The microbial aerosol data and the environmental data are updated in real time, and the disinfection data prediction model is combined, so that the instant prediction of the disinfection effect is realized, the disinfection strategy can be adjusted in real time according to the prediction result, the real-time performance and the flexibility of operation are improved, the combination of the real-time data and the prediction model enables the prediction result to better reflect the current disinfection effect, an operator can make a timely decision according to the real-time prediction, and the real-time performance and the flexibility of operation are improved. By performing disinfection simulation operation in the virtual environment, resource waste and risk in actual operation are avoided, effects of different strategies can be explored in the virtual environment by simulation evaluation, and disinfection operation is optimized, so that resource cost and experimental risk are reduced. By generating a detailed simulated disinfection effect evaluation report, the method can provide a basis for scientific decision making for an operator, and the report contains effect comparison under different operation conditions, so that the operator can select an optimal disinfection strategy, and the scientificity and reliability of decision making are improved. By combining the real-time disinfection related data to continuously optimize the disinfection data prediction model, operators can be guided to select a more effective disinfection strategy, the disinfection effect is improved, the load of microorganism aerosol is reduced, and a safer working environment is created. Powerful support and guidance are provided for actual disinfection operation from data acquisition to prediction model establishment to virtual simulation operation, and a scientific, efficient and accurate method for evaluation and operation of disinfection effects is provided.
The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.
The foregoing is only a specific embodiment of the invention to enable those skilled in the art to understand or practice the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. The simulation evaluation method of the surface disinfection effect of the microbial aerosol is characterized by comprising the following steps of:
step S1: acquiring target equipment to be detected; the method comprises the steps of collecting and preprocessing microorganism aerosol data of target equipment to be detected to generate microorganism aerosol data;
step S2: acquiring aerosol disinfection data; performing a microbial aerosol surface disinfection test on the target equipment to be detected by using aerosol disinfection data, and performing disinfection test efficiency calculation to generate disinfection test efficiency data; data integration is carried out on the microorganism aerosol data, the aerosol disinfection data and the disinfection test efficiency data, and test aerosol disinfection effect data is generated;
Step S3: the method comprises the steps that a sensor is used for collecting environmental data around target equipment to be detected, and environmental data are generated; classifying the test aerosol disinfection effect data according to the environment data to obtain disinfection environment type data, and generating classified test aerosol disinfection effect data;
step S4: performing microbial aerosol surface disinfection data prediction model establishment and model optimization by using a support vector machine algorithm and classification test aerosol disinfection effect data to generate an optimized disinfection data prediction model;
step S5: the method comprises the steps of updating and integrating microorganism aerosol data and environment data in real time to generate real-time data to be disinfected; transmitting the real-time data to be disinfected to an optimized disinfection data prediction model for disinfection data prediction, and generating disinfection prediction data;
step S6: and establishing a physical model of the equipment to be detected according to the target equipment to be detected and the real-time data to be disinfected, and performing disinfection simulation operation of the equipment to be detected by utilizing the disinfection prediction data to generate a simulated disinfection effect evaluation report.
2. The method for simulated evaluation of the disinfection effect of a microbial aerosol surface according to claim 1, wherein step S1 comprises the steps of:
Step S11: acquiring target equipment to be detected;
step S12: the method comprises the steps of carrying out regional microorganism aerosol data acquisition on target equipment to be detected by utilizing electron microscope equipment, and generating regional microorganism aerosol image data;
step S13: and carrying out aerosol data preprocessing of the target equipment to be detected according to the regional microorganism aerosol image data to generate microorganism aerosol data.
3. A method for the simulated evaluation of the disinfection effect of a microbial aerosol surface according to claim 2, wherein step S13 comprises the steps of:
step S131: carrying out statistical analysis on the microbial aerosol distribution of the regional microbial aerosol image data to generate regional biological aerosol data;
step S132: calculating the average value of the whole microbial aerosol data of the target equipment to be detected according to the regional microbial aerosol data, and generating initial microbial aerosol data;
step S133: and carrying out data normalization on the initial microbial aerosol data by using a minimum-maximum normalization method to generate microbial aerosol data.
4. A method for the simulated evaluation of the disinfection effect of a microbial aerosol surface according to claim 3, wherein step S2 comprises the steps of:
Step S21: acquiring aerosol disinfection data;
step S22: performing a microbial aerosol surface disinfection test on the target equipment to be detected by utilizing aerosol disinfection data, and performing microbial aerosol data acquisition of the disinfection test to generate aerosol disinfection test data;
step S23: performing disinfection efficiency calculation on aerosol disinfection test data by using a microbial aerosol disinfection efficiency algorithm to generate disinfection test efficiency data;
step S24: and integrating the data of the microorganism aerosol, the aerosol disinfection data and the disinfection test efficiency data to generate test aerosol disinfection effect data.
5. The method for simulated evaluation of the disinfection effect of a microbial aerosol surface according to claim 4, wherein the microbial aerosol disinfection efficiency algorithm in step S23 is as follows:
;
wherein P is expressed as disinfection test efficiency data, t 2 Expressed as the end time of the disinfection test, t 1 Expressed as the start time of the disinfection test, N is expressed as an equal area image block of the target device to be detected, A i Denoted as initial concentration of microbial aerosol in the ith image block, t denoted as current time node of the disinfection test, B i Expressed as final concentration of microbial aerosol in the ith image patch, M is expressed as area size of the image patch, M Total (S) Expressed as the total area of the test area, k expressed as the average density of the microbial aerosol, Q expressed as the air supply rate of the target device to be tested, and τ expressed as the abnormal adjustment value of the disinfection test efficiency data.
6. The method for simulated evaluation of the disinfection effect of a microbial aerosol surface according to claim 5, wherein step S3 comprises the steps of:
step S31: the method comprises the steps that a sensor is used for collecting environmental data around target equipment to be detected, and environmental data are generated;
step S32: performing environment type design of equipment to be detected according to the environment data to generate environment type data;
step S33: and classifying the test aerosol disinfection effect data according to the environment type data to generate classified test aerosol disinfection effect data.
7. The method for simulated evaluation of the disinfection effect of a microbial aerosol surface according to claim 6, wherein step S4 comprises the steps of:
step S41: establishing a mapping relation of microbial aerosol surface disinfection data prediction by using a support vector machine algorithm, and generating an initial disinfection effect prediction model;
step S42: performing data division on time sequence on the classified test aerosol disinfection effect data to generate a classified test aerosol disinfection effect training set and a classified test aerosol disinfection effect testing set;
Step S43: transmitting the classified test aerosol disinfection effect training set to an initial disinfection effect prediction model for model training, and generating a disinfection effect prediction model;
step S44: optimizing and adjusting the environmental impact parameter weight of the model for the disinfection data prediction model by using an environmental impact parameter model optimizing algorithm, and performing iterative training by using a classified test aerosol disinfection effect training set to generate an adjusted disinfection data prediction model;
step S45: and performing model test on the adjustment disinfection data prediction model by using the classified test aerosol disinfection effect test set to generate an optimization disinfection data prediction model.
8. The method for simulated evaluation of the disinfection effect of a microbial aerosol surface according to claim 7, wherein the environmental impact parametric model optimization algorithm in step S44 is as follows:
;
where K is expressed as an optimization weight of the environmental impact parameter, R is expressed as the number of input samples of the model, y i The predicted disinfection test efficiency expressed as the i-th sample,the actual disinfection test efficiency, z, expressed as the i-th sample i Humidity data, b, expressed as the i-th sample i Denoted as the ith sample temperature data, P is denoted as the initial weight of the environmental impact parameter,/for the sample temperature data >The length of time the test microorganism aerosol was sterilized, denoted as the ith sample involved, delta is denoted as environmental impactAbnormal adjustment value of optimization weight of parameter.
9. The method for simulated evaluation of the disinfection effect of a microbial aerosol surface according to claim 8, wherein step S5 comprises the steps of:
step S51: the method comprises the steps of carrying out real-time updating treatment on microorganism aerosol data to generate real-time microorganism aerosol data;
step S52: according to the real-time microbial aerosol data, the environment data is updated in real time to generate real-time environment data;
step S53: data integration is carried out on the real-time microorganism aerosol data and the real-time environment data, and real-time data to be disinfected are generated;
step S54: and transmitting the real-time data to be disinfected to an optimized disinfection data prediction model for disinfection data prediction, and generating disinfection prediction data.
10. The method for simulated evaluation of the disinfection effect of a microbial aerosol surface according to claim 9, wherein step S6 comprises the steps of:
step S61: building a physical model framework of the equipment to be detected on the target equipment to be detected by utilizing a three-dimensional modeling technology, and filling data by utilizing real-time data to be disinfected to generate a physical model of the target equipment to be detected;
Step S62: and carrying out disinfection simulation operation of the equipment to be detected on the physical model of the target equipment to be detected by using the disinfection prediction data, and generating a simulated disinfection effect evaluation report.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311276141.1A CN117010216B (en) | 2023-09-29 | 2023-09-29 | Simulation evaluation method for surface disinfection effect of microbial aerosol |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311276141.1A CN117010216B (en) | 2023-09-29 | 2023-09-29 | Simulation evaluation method for surface disinfection effect of microbial aerosol |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117010216A CN117010216A (en) | 2023-11-07 |
CN117010216B true CN117010216B (en) | 2023-12-19 |
Family
ID=88565747
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311276141.1A Active CN117010216B (en) | 2023-09-29 | 2023-09-29 | Simulation evaluation method for surface disinfection effect of microbial aerosol |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117010216B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118095967B (en) * | 2024-04-24 | 2024-07-12 | 深圳市广达盛金属制品有限公司 | Intelligent analysis-based disinfection cabinet production and processing quality control method and system |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116541785A (en) * | 2023-07-05 | 2023-08-04 | 北京建工环境修复股份有限公司 | Toxicity prediction method and system based on deep integration machine learning model |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TWI786697B (en) * | 2021-06-24 | 2022-12-11 | 國立中央大學 | Aerosol Optical Depth Spectrum Differentiation Method Applied to Differentiation of Type and Content |
-
2023
- 2023-09-29 CN CN202311276141.1A patent/CN117010216B/en active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116541785A (en) * | 2023-07-05 | 2023-08-04 | 北京建工环境修复股份有限公司 | Toxicity prediction method and system based on deep integration machine learning model |
Also Published As
Publication number | Publication date |
---|---|
CN117010216A (en) | 2023-11-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Günther et al. | Nowcasting the COVID‐19 pandemic in Bavaria | |
CN117010216B (en) | Simulation evaluation method for surface disinfection effect of microbial aerosol | |
Zurell et al. | The virtual ecologist approach: simulating data and observers | |
Christopher Frey et al. | Identification and review of sensitivity analysis methods | |
ROBLEDO‐ARNUNCIO et al. | Estimation of the seed dispersal kernel from exact identification of source plants | |
Pei et al. | Inference and control of the nosocomial transmission of methicillin-resistant Staphylococcus aureus | |
Jones et al. | Measuring long‐distance seed dispersal in complex natural environments: an evaluation and integration of classical and genetic methods | |
Wilson et al. | Rates of surgical site infection after hip replacement as a hospital performance indicator: analysis of data from the English mandatory surveillance system | |
Landguth et al. | Evaluating sample allocation and effort in detecting population differentiation for discrete and continuously distributed individuals | |
CN117575178B (en) | STIRPAT model-based water environment treatment and carbon emission reduction synergy evaluation method | |
CN110974161A (en) | Olfactory function evaluation system based on human olfactory detection | |
Kelcey et al. | Sample size planning for cluster-randomized interventions probing multilevel mediation | |
Stachel et al. | Implementation and evaluation of an automated surveillance system to detect hospital outbreak | |
Naqvi et al. | Data considerations for developing deep learning models for dairy applications: A simulation study on mastitis detection | |
JP5110891B2 (en) | Statistical prediction method and apparatus for influent water quality in water treatment facilities | |
CN116863410B (en) | Data acquisition and processing method and system based on pest control | |
Argáez et al. | Prediction of potential areas of species distributions based on presence-only data | |
CN113642669B (en) | Feature analysis-based fraud prevention detection method, device, equipment and storage medium | |
Schlosser et al. | Use of a Markov-chain Monte Carlo model to evaluate the time value of historical testing information in animal populations | |
Pan et al. | A new electronic nose for downwind livestock farm odour measurement | |
Hunt et al. | False determinations of chaos in short noisy time series | |
CN117408441A (en) | Health monitoring method, system, equipment and medium combining indoor and outdoor environments | |
CN117872925A (en) | Monitoring device and monitoring method for internal TVOC of intelligent cabinet | |
Anglart et al. | Modeling cow somatic cell count using sensor data as input to generalized additive models | |
CN118428607A (en) | On-line monitoring and management method and system for full life cycle of antibiotics |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |