CN116579192A - Intelligent assessment method and system for health state of mobile power box - Google Patents
Intelligent assessment method and system for health state of mobile power box Download PDFInfo
- Publication number
- CN116579192A CN116579192A CN202310864041.4A CN202310864041A CN116579192A CN 116579192 A CN116579192 A CN 116579192A CN 202310864041 A CN202310864041 A CN 202310864041A CN 116579192 A CN116579192 A CN 116579192A
- Authority
- CN
- China
- Prior art keywords
- index
- matrix
- mobile power
- module
- power supply
- 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.)
- Granted
Links
- 230000036541 health Effects 0.000 title claims abstract description 53
- 238000000034 method Methods 0.000 title claims description 36
- 239000011159 matrix material Substances 0.000 claims abstract description 157
- 230000008859 change Effects 0.000 claims abstract description 116
- 238000011156 evaluation Methods 0.000 claims abstract description 41
- 230000007613 environmental effect Effects 0.000 claims abstract description 19
- 230000006870 function Effects 0.000 claims description 58
- 239000013598 vector Substances 0.000 claims description 21
- 238000013507 mapping Methods 0.000 claims description 17
- 230000003862 health status Effects 0.000 claims description 15
- 238000013210 evaluation model Methods 0.000 claims description 13
- 238000013461 design Methods 0.000 claims description 11
- 238000013528 artificial neural network Methods 0.000 claims description 9
- 230000008447 perception Effects 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 5
- 238000012512 characterization method Methods 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 abstract description 21
- 238000012423 maintenance Methods 0.000 abstract description 6
- 230000005012 migration Effects 0.000 abstract description 5
- 238000013508 migration Methods 0.000 abstract description 5
- 238000012545 processing Methods 0.000 abstract description 5
- 238000012098 association analyses Methods 0.000 abstract description 3
- 230000015572 biosynthetic process Effects 0.000 abstract 1
- 238000005286 illumination Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000012546 transfer Methods 0.000 description 3
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 229910001416 lithium ion Inorganic materials 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- RNFJDJUURJAICM-UHFFFAOYSA-N 2,2,4,4,6,6-hexaphenoxy-1,3,5-triaza-2$l^{5},4$l^{5},6$l^{5}-triphosphacyclohexa-1,3,5-triene Chemical compound N=1P(OC=2C=CC=CC=2)(OC=2C=CC=CC=2)=NP(OC=2C=CC=CC=2)(OC=2C=CC=CC=2)=NP=1(OC=1C=CC=CC=1)OC1=CC=CC=C1 RNFJDJUURJAICM-UHFFFAOYSA-N 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000000576 coating method Methods 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 230000005670 electromagnetic radiation Effects 0.000 description 1
- 238000004146 energy storage Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000003063 flame retardant Substances 0.000 description 1
- 238000011010 flushing procedure Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000002269 spontaneous effect Effects 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
- 230000007704 transition 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
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- 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
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides an intelligent evaluation method and system for the health state of a mobile power supply box, which relate to the technical field of data processing, and are characterized in that a first characteristic function of the mobile power supply box is acquired, a component identification output protection module set is carried out to generate a first module distribution matrix, a first index change matrix is generated based on an initial scene and a target scene, connection relation analysis of the module and an index is carried out, a first incidence matrix is output, a first safety index is evaluated, first evaluation reminding information is generated, the problem that state evaluation is carried out based on hard standards at present, influence caused by environmental migration is ignored, the accuracy of an evaluation result and the scene fit degree are insufficient, the subsequent operation and maintenance are limited is solved, the protection health state and the power supply health state of the mobile power supply box under the scene movement condition are taken as evaluation directions, and matrix formation and association analysis of component and index parameters are carried out, and the order flexible analysis and the accurate evaluation of the state of the power supply under the environment fluctuation are carried out.
Description
Technical Field
The application relates to the technical field of data processing, in particular to an intelligent assessment method and system for the health state of a mobile power box.
Background
The mobile power box is used as outdoor emergency power supply equipment, is powered on the basis of a built-in lithium ion battery, can store electric energy, has an alternating-current output function, can provide reliable emergency power supply guarantee for various loads, and meanwhile has the safety problem of being the current application hot spot problem.
The state difference of the mobile power box under different environments can influence the acquisition efficiency of the power supply, at present, the state evaluation is carried out based on hard standards, the influence caused by environment migration is ignored, the accuracy of an evaluation result and the scene conformity degree are insufficient, and the follow-up operation and maintenance are limited.
Disclosure of Invention
The application provides an intelligent assessment method and system for the health state of a mobile power box, which are used for solving the technical problems that the accuracy and scene conformity degree of an assessment result are insufficient and the follow-up operation and maintenance are limited because the influence caused by environmental migration is ignored in the prior art because state assessment is carried out based on hard standards.
In view of the above problems, the application provides a method and a system for intelligently evaluating the health status of a mobile power box.
In a first aspect, the present application provides a method for intelligently evaluating the health status of a mobile power box, the method comprising:
acquiring a first characteristic function of a mobile power supply box, wherein the first characteristic function is a function for identifying the protection attribute of the mobile power supply box;
identifying a component of the mobile power box according to the first characteristic function, outputting a protection module set, and generating a first module distribution matrix according to the protection module set, wherein each coordinate in the first module distribution matrix corresponds to one module;
acquiring an initial scene and a target scene of the mobile power box for moving, and generating a first index change matrix according to scene change indexes between the initial scene and the target scene;
analyzing the connection relation between each module in the first module distribution matrix and each index in the first index change matrix, and outputting a first incidence matrix for identifying the change perception degree between each module and each index;
evaluating the mobile power supply box according to the first incidence matrix and the first index change matrix, and outputting a first safety index, wherein the first safety index is a protection health state of the mobile power supply box under the condition of identifying scene movement;
and generating first evaluation reminding information according to the first safety index.
In a second aspect, the present application provides a mobile power box health status intelligent assessment system, the system comprising:
the function acquisition module is used for acquiring a first characteristic function of the mobile power supply box, wherein the first characteristic function is a function for identifying the protection attribute of the mobile power supply box;
the module distribution matrix generation module is used for identifying the components of the mobile power box according to the first characteristic function, outputting a protection module set and generating a first module distribution matrix according to the protection module set, wherein each coordinate in the first module distribution matrix corresponds to one module;
the index change matrix generation module is used for acquiring an initial scene and a target scene of the mobile power box for moving and generating a first index change matrix according to scene change indexes between the initial scene and the target scene;
the first incidence matrix output module is used for analyzing the connection relation between each module in the first module distribution matrix and each index in the first index change matrix and outputting a first incidence matrix for identifying the change perception degree between each module and each index;
the safety index output module is used for evaluating the mobile power supply box according to the first incidence matrix and the first index change matrix and outputting a first safety index, wherein the first safety index is a protection health state of the mobile power supply box under the condition of marking scene movement;
and the reminding information generation module is used for generating first evaluation reminding information according to the first safety index.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
according to the intelligent assessment method for the health state of the mobile power supply box, which is provided by the embodiment of the application, a first characteristic function of the mobile power supply box, namely a function of identifying the protection attribute of the mobile power supply box, is obtained; identifying components of the mobile power box according to the first characteristic function, outputting a protection module set, generating a first module distribution matrix according to the protection module set, acquiring an initial scene and a target scene of the mobile power box for moving, determining scene change indexes and generating a first index change matrix; analyzing the connection relation between each module in the first module distribution matrix and each index in the first index change matrix, and outputting a first incidence matrix for identifying the change perception degree between each module and each index; the mobile power box is evaluated according to the first incidence matrix and the first index change matrix, a first safety index is output to generate first evaluation reminding information, the problems that the state evaluation is carried out based on hard standards at present in the prior art, influence caused by environmental migration is ignored, the accuracy of an evaluation result and the scene fit degree are insufficient, the follow-up operation and maintenance are limited are solved, the protection health state and the power supply health state of the mobile power box under the scene movement condition are taken as evaluation directions, the matrixing and the incidence analysis of components and index parameters are carried out, and the flexible analysis of the order of the power supply and the accurate evaluation of the state under the environment fluctuation are carried out.
Drawings
FIG. 1 is a schematic flow chart of a method for intelligently evaluating the health status of a mobile power box;
fig. 2 is a schematic diagram of a scene index acquisition number acquisition flow in a mobile power box health status intelligent assessment method;
FIG. 3 is a schematic diagram of a first security index obtaining process in a method for intelligently evaluating the health status of a mobile power box according to the present application;
fig. 4 is a schematic structural diagram of an intelligent evaluation system for health status of a mobile power box.
Reference numerals illustrate: the system comprises a function acquisition module 11, a module distribution matrix generation module 12, an index change matrix generation module 13, a first incidence matrix output module 14, a safety index output module 15 and an evaluation reminding information generation module 16.
Detailed Description
The application provides an intelligent evaluation method and system for the health state of a mobile power box, which are used for acquiring a first characteristic function of the mobile power box, carrying out component identification and outputting a protection module set to generate a first module distribution matrix, determining scene change indexes and generating a first index change matrix based on an initial scene and a target scene, carrying out matrix connection relation analysis on each module and the first index change matrix, outputting a first incidence matrix, carrying out first safety index evaluation and generating first evaluation reminding information, and are used for solving the technical problems that the state evaluation is carried out based on hard standards at present in the prior art, influence caused by environmental migration is ignored, the accuracy of an evaluation result and the scene contract degree are insufficient, and the subsequent operation and maintenance are limited.
Example 1
As shown in fig. 1, the application provides a method for intelligently evaluating the health status of a mobile power box, which comprises the following steps:
step S100: acquiring a first characteristic function of a mobile power supply box, wherein the first characteristic function is a function for identifying the protection attribute of the mobile power supply box;
specifically, the mobile power box is used as outdoor emergency power supply equipment, is powered on by a built-in lithium ion battery, can store electric energy, has an alternating-current output function, can provide reliable emergency power supply guarantee for various loads, and meanwhile has the safety problem of the current application hot spot problem. According to the intelligent assessment method for the health state of the mobile power box, provided by the application, the protection health state and the power supply health state of the mobile power box under the scene movement condition are taken as the assessment directions, and the matrixing and the association analysis of the components and the index parameters are carried out, so that the flexible analysis of the order of the power supply under the environment fluctuation and the accurate assessment of the state are carried out.
Specifically, the mobile power box has a certain protection attribute, and based on the specification configuration structure of the mobile power box, the protection function is determined and marked, for example, the shell has a certain flame retardance so as to prevent the spontaneous combustion of the battery core from explosion protection; the fuse limiting current carries out overvoltage and overcurrent protection; performing power supply interference protection based on common mode inductance filtering; the change of the power supply environment brings certain transient pulse, the path impedance is adjusted based on the avalanche breakdown effect, high-voltage pulse protection and the like are performed through drainage, the protection function of the mobile power supply box is identified and extracted, mapping association and identification are performed with a corresponding hardware or software matrix structure, the protection function is used as the first characteristic function of the mobile power supply box, and the first characteristic function is a reference basis for power supply state analysis.
Step S200: identifying a component of the mobile power box according to the first characteristic function, outputting a protection module set, and generating a first module distribution matrix according to the protection module set, wherein each coordinate in the first module distribution matrix corresponds to one module;
further, the step S200 of the present application further includes:
step S210: judging whether the mobile power supply box is of a detachable structure, and determining a first detachable part when the mobile power supply box is of the detachable structure, wherein the first detachable part is a part needing scene movement;
step S220: and confirming the components of the mobile power box according to the first disassembly part, and outputting the screened protection module set.
Specifically, the first characteristic function is identified, and components corresponding to the characteristic functions, such as explosion-proof and flame-retardant performances, corresponding to the shell structure, such as materials, coatings and the like, are determined; the reverse connection prevention protection corresponds to the diode structure, and is a component for confirming each characteristic function due to unidirectional conductivity and the like, and is used as a component of the mobile power supply box.
Furthermore, the mobile power box is subjected to the detachability analysis, namely the analysis of the transfer structure during scene movement is performed, for example, when the power supply is assembled on the base and the scene position is transferred, the removal of the transfer structure is only required based on the base, and the protection analysis is performed on the removal structure. Specifically, whether the mobile power box is of a detachable structure is judged, and if the mobile power box is of a detachable structure, a structure part to be detached for scene position transfer is determined to be used as the first detachable part.
Further, the components of the mobile power supply box are traversed, the first disassembly part is matched, the components which are successfully matched are screened, corresponding protection modules are obtained, the protection module sets are generated, and the protection module sets are in one-to-one correspondence with the screened components and are used for carrying out protection analysis on the components. Based on the protection module set, corresponding matrix coordinates, such as (1, 1) representing explosion-proof performance of the shell structure, and (2, 1) representing impact resistance of the shell, are determined, a plurality of matrix coordinates are determined, a member is further taken as a matrix row, a characteristic function is taken as a matrix column, the plurality of matrix coordinates are regulated, the first module distribution matrix is generated, and the first module distribution matrix is an analysis basis for transferring parameter fluctuation influence analysis.
Step S300: acquiring an initial scene and a target scene of the mobile power box for moving, and generating a first index change matrix according to scene change indexes between the initial scene and the target scene;
further, as shown in fig. 2, step S300 of the present application further includes:
step S310: identifying environmental parameters based on the first characteristic function, and acquiring a first initial k value;
step S320: analyzing the first index change matrix to determine a K value selection interval;
step S330: and carrying out optimizing clustering on all the environmental parameters according to a K-clustering method, outputting a first preset K value, and determining the number of scene index acquisitions according to the first preset K value.
Specifically, the initial scene is a working scene before the mobile power box moves, the target scene is a scene to be worked after the mobile power box moves, the initial scene and the target scene are obtained, differential calibration of the scenes is carried out, scene change indexes between the two are determined, for example, the environment temperature is changed from 20 to 25, the environment temperature is added into the scene change indexes, if the environment temperature is not changed, all indexes with scene change are not added, the amplitude and the change direction of the scene change indexes are analyzed and screened, an index change vector is determined, the first index change matrix is generated through integration regulation, and the first index change matrix is the orderly integration of fluctuation indexes of scene transition.
Further, based on the first characteristic function, determining environmental parameters with functional influence, such as environmental temperature, illumination, electromagnetic radiation, dust and the like, and counting the number of parameters with influence correlation with the mobile power box as the first initial K value. Further, based on the first index change matrix, environmental parameters are screened, relevant environmental parameters meeting the current environmental change conditions are determined, and a section formed by the maximum number value and the minimum number value of the adapted environmental parameters is used as the K value selection section. And then combining a K-clustering method to perform optimizing of the K value selection interval.
Specifically, based on all environment parameters, randomly determining a plurality of environment parameters as clustering centers, respectively calculating the distance between each environment parameter and the rest environment parameters, taking the shortest distance as response to the shortest distance to divide attribution of the environment parameters, further setting a distance threshold, namely defining the maximum distance of attribution of the environment parameters by self-definition, dividing the environment parameters with all the distances larger than the distance threshold into a group again, and determining a plurality of clustering results; further, the determination of the clustering center and the division of the environmental parameters are carried out again for the clustering results, the people with the distance larger than the distance threshold are screened and regrouped, the clustering results are repeated for a plurality of times until convergence conditions are met, for example, the maximum division times are met, the clustering results are obtained, wherein the clustering results with the quantity larger than 1 in the class are considered as a term when the similarity of the internal environmental parameters is too high, the quantity of the clustering results is counted and is used as the first preset K value, namely, the quantity of scene index collection is carried out, and the data quantity can be reduced on the basis of guaranteeing the effectiveness and completeness of index collection.
Step S400: analyzing the connection relation between each module in the first module distribution matrix and each index in the first index change matrix, and outputting a first incidence matrix for identifying the change perception degree between each module and each index;
step S500: evaluating the mobile power supply box according to the first incidence matrix and the first index change matrix, and outputting a first safety index, wherein the first safety index is a protection health state of the mobile power supply box under the condition of identifying scene movement;
step S600: and generating first evaluation reminding information according to the first safety index.
Specifically, based on the first module distribution matrix, traversing the distribution coordinates corresponding to the modules, respectively performing relevance analysis with the first index change matrix, namely, judging that index relevance exists when index change affects the state of the module, and exemplarily, identifying and judging by retrieving call history data, determining the relevance influence degree based on the history data to obtain relevance coefficients, determining relevance indexes corresponding to the modules and performing mapping identification of the relevance coefficients. Further, the modules are used as matrix rows, the relevance indexes are used as matrix columns, distributed arrangement of the modules and the relevance indexes is carried out, the first relevance matrix is generated, and the first relevance matrix is a bottom support for safety evaluation.
Further, based on a health state evaluation model, the first correlation matrix and the first index change matrix are calculated, and the first safety index, namely, a parameter for identifying the protection health state of the mobile power box under the scene movement condition is output. Judging whether the second safety index meets a safety threshold or not, and if not, generating the first evaluation reminding information to carry out early warning and warning.
Further, as shown in fig. 3, the mobile power box is evaluated according to the first association matrix and the first index change matrix, and a first security index is output, and step S500 of the present application further includes:
step S510: obtaining the change value of each index in the first index change matrix;
step S520: based on a first mapping function, a pre-trained three-layer fully-connected neural network is obtained, wherein the first mapping function is a mapping relation between vectors in the first incidence matrix and vectors in the first index change matrix:
step S530: and training the neural network by taking each coordinate vector in the first incidence matrix as a weight network layer and taking the change value of each index in the first index change matrix as input data to obtain a health state evaluation model, and outputting a first safety index according to the health state evaluation model.
Further, step S530 of the present application further includes:
step S531-1: the expression of the health state assessment model is as follows:； wherein ,/>Characterizing a health state assessment model; />Watch (Table)First association matrix->Vector coordinates>；/>Characterizing a first index change matrix->Vector coordinates>，/>,/>All are->Is a matrix of (a); />Characterizing regularization term->The characterization is based on regularized weight coefficients.
Specifically, the first index change matrix is identified, and the change value of each index is determined. Mapping and corresponding the first incidence matrix and the first index change matrix, and determining a mapping relation of matrix vectors, wherein the mapping relation is used as the first mapping function for determining a change value of a corresponding index of a module. When the risk analysis is performed, input data are input and analyzed in groups, the input order and the input accuracy of the data can be guaranteed based on the first mapping function, and each group of data respectively comprises the association coefficient and the corresponding index change value. And constructing a model framework of the health state evaluation model based on the first mapping function, and obtaining a pre-trained three-layer fully-connected neural network.
Further, each coordinate vector in the first correlation matrix is used as a weight network layer for index weight configuration, wherein the larger the correlation coefficient is, the larger the index change value is, and the higher the corresponding configuration weight value is. And inputting the change values of all indexes in the first index change matrix into the neural network for training to obtain the constructed health state evaluation model, wherein the expression of the health state evaluation model is as follows:； wherein ,/>Characterizing a health state assessment model; />Characterizing a first correlation matrix->Vector coordinates>；/>Characterizing a first index change matrix->Vector coordinates>，/>,/>All are->Is a matrix of (a); />Characterizing regularization term->The characterization of the regularized weight coefficient can be obtained based on the earlier steps of the embodiment of the application, and the parameters are known parameters. And calculating risk coefficients corresponding to all modules based on the expression of the health state assessment model, taking the reciprocal of the risk coefficients and adding the reciprocal as the first safety index, wherein the first safety index is a parameter for measuring the health state of the mobile power box.
Further, step S530 of the present application further includes:
step S531-2: obtaining structural design information of the mobile power box;
step S532-2: determining whether the protection module set comprises an exposed module according to the structural design information, and determining the exposed module set if the protection module set comprises the exposed module;
step S533-2: and generating a risk adjustment coefficient set according to the exposed module set, generating an adjustment network layer according to the risk adjustment coefficient set, and optimizing the health state evaluation model.
Specifically, structural design determination is performed based on specification configuration information of the mobile power supply box, for example, identification and extraction of the mechanism design information are performed based on a specification of the mobile power supply box, and structural design information of the mobile power supply box is obtained. Based on the structural design information, traversing the protection module set to judge the existence of the exposed modules, for example, configuring an external fuse to perform fuse overcurrent protection, and adding the construction into the exposed module set. And aiming at the exposed module set, determining the risk degree of the built-in module under the same environment state based on the corresponding association index, and generating the risk adjustment coefficient set, wherein the risk adjustment coefficient set is provided with sign marks and is used for representing the risk level under the condition that the built-in module correspondingly configured is taken as a reference. And generating the regulation network layer based on the risk regulation coefficient set, and optimizing the health state assessment model. The adjusting network layer is used for carrying out risk calibration, guaranteeing the structural assembly fitting degree of an analysis result and the mobile power supply box, and improving the accuracy of the output first safety index.
Further, the present application also includes step S700, including:
step S710: identifying a supply source of the mobile power box to obtain a power supply source;
step S720: generating a second index change matrix according to the scene change index between the initial scene and the target scene;
step S730: outputting a second incidence matrix according to the connection relation between the power supply source and each index in the second index change matrix;
step S740: evaluating the mobile power supply box according to the second incidence matrix and the second index change matrix, and outputting a second safety index, wherein the second safety index is a power supply health state of the mobile power supply box under the condition of scene movement identification;
step S750: and calculating according to the first safety index and the second safety index to generate second evaluation reminding information.
Specifically, the supply sources of the mobile power supply boxes are different, and the fitness of the mobile power supply boxes for different scenes is different. And carrying out supply source identification on the mobile power box, and determining the power supply source. For the initial scene and the target scene, the scene change index is determined based on the change of the power supply source, for example, if the power supply source is a solar mobile power supply, the power supply source is solar energy, the requirements on states in the illumination environment and the non-illumination environment are different, the instant switching and instant flushing can be performed based on the illumination condition, and the energy storage is required to be sufficient under the non-illumination condition.
Further, under the condition of determining scene change, performing index normalization based on the influence change index of the power supply source to generate the second index change matrix, wherein the generation mode and the distribution state of the second index change matrix and the first index change matrix are the same. Further, performing relevance analysis on the power supply source and the second index change matrix, determining relevance indexes influencing the states of all modules, taking the modules as matrix rows, taking the relevance indexes as matrix columns, and performing relevance index normalization to generate the second relevance matrix.
Further, according to the health state evaluation model, weighting is carried out on each coordinate vector in the second association matrix based on the weight network layer, the change value of each index in the second index change matrix is used as input data, calculation and analysis are carried out based on the expression of the health state evaluation model, the second safety index is output, and the second safety index is the power supply health state of the mobile power box under the condition of scene movement identification. The first security index and the second security index are same in analysis and calculation mode, and specific analysis dimensions and data are different. And further carrying out weight configuration on the first safety index and the second safety index based on safety standards, and carrying out weighted summation calculation to determine the comprehensive safety index.
And further setting a safety threshold, namely, based on the mobile power box use standard and a critical safety index determined by expert experience, if the comprehensive safety index does not meet the safety threshold, indicating that potential use risks exist, generating the second evaluation reminding information to warn so as to repair and avoid risks in time.
The intelligent evaluation method for the health state of the mobile power box has the following technical effects:
1. the method comprises the steps of obtaining a first characteristic function of a mobile power box, carrying out component identification and outputting a protection module set to generate a first module distribution matrix, generating a first index change matrix based on an initial scene and a target scene, carrying out connection relation analysis of the module and the index, outputting a first association matrix, evaluating a first safety index and generating first evaluation reminding information, solving the technical problems that the accuracy and scene conformity of an evaluation result are insufficient and the follow-up operation and maintenance are limited due to the fact that state evaluation is carried out based on a hard standard in the prior art, carrying out matrixing and association analysis of component and index parameters under the condition that the protection health state and the power supply health state of the mobile power box are taken as evaluation directions under the condition of scene movement, and carrying out ordered flexible analysis and accurate evaluation of the state of the power under the condition fluctuation.
2. And (3) index screening is carried out by taking the environmental change relevance and the structural detachability as the standard, the scene necessity index parameters are determined, and redundant information is removed on the basis of guaranteeing the completeness of the data so as to improve the processing efficiency.
3. And (3) building a health state evaluation model for calculation processing, and analyzing and compensating based on the assembly position of the structure, so that the accuracy and objectivity of a processing result are ensured.
Example two
Based on the same inventive concept as the intelligent assessment method for the health status of the mobile power supply box in the foregoing embodiment, as shown in fig. 4, the present application provides an intelligent assessment system for the health status of the mobile power supply box, which includes:
a function obtaining module 11, where the function obtaining module 11 is configured to obtain a first feature function of a mobile power box, where the first feature function is a function of identifying a protection attribute of the mobile power box;
the module distribution matrix generation module 12 is configured to identify a component of the mobile power box according to the first feature function, output a protection module set, and generate a first module distribution matrix according to the protection module set, where each coordinate in the first module distribution matrix corresponds to one module;
the index change matrix generation module 13 is used for acquiring an initial scene and a target scene of the mobile power box for moving, and generating a first index change matrix according to scene change indexes between the initial scene and the target scene;
the first correlation matrix output module 14 is configured to analyze a connection relationship between each module in the first module distribution matrix and each index in the first index change matrix, and output a first correlation matrix that identifies a change perception degree between each module and each index;
the safety index output module 15 is configured to evaluate the mobile power box according to the first association matrix and the first index change matrix, and output a first safety index, where the first safety index is a protection health state of the mobile power box under a condition of identifying scene movement;
the evaluation reminding information generating module 16 is configured to generate first evaluation reminding information according to the first security index by using the evaluation reminding information generating module 16.
Further, the index change matrix generation module further includes:
the parameter identification module is used for identifying the environmental parameters based on the first characteristic function and acquiring a first initial k value;
the interval determining module is used for analyzing the first index change matrix and determining a K value selection interval;
the acquisition quantity output module is used for optimizing and clustering all environmental parameters according to a K-clustering method, outputting a first preset K value and determining the acquisition quantity of scene indexes according to the first preset K value.
Further, the system further comprises:
the supply source identification module is used for identifying a supply source of the mobile power box and acquiring a power supply source;
the second index change matrix generation module is used for generating a second index change matrix according to the scene change indexes between the initial scene and the target scene;
the second incidence matrix output module is used for outputting a second incidence matrix according to the connection relation between the power supply source and each index in the second index change matrix;
the second safety index output module is used for evaluating the mobile power box according to the second incidence matrix and the second index change matrix and outputting a second safety index, wherein the second safety index is a power supply health state of the mobile power box under the condition of marking scene movement;
the second evaluation reminding information generation module is used for calculating according to the first safety index and the second safety index to generate second evaluation reminding information.
Further, the module distribution matrix generating module further includes:
the structure judging module is used for judging whether the mobile power supply box is of a detachable structure or not, and determining a first detachable part when the mobile power supply box is of the detachable structure, wherein the first detachable part is a part needing scene movement;
and the component confirmation module is used for confirming the components of the mobile power box according to the first disassembly part and outputting a screened protection module set.
Further, the safety index output module further includes:
the index change value acquisition module is used for acquiring the change value of each index in the first index change matrix;
the neural network training module is used for acquiring a pre-trained three-layer fully-connected neural network based on a first mapping function, wherein the first mapping function is a mapping relation between vectors in the first incidence matrix and vectors in the first index change matrix:
the model acquisition module is used for training the neural network by taking each coordinate vector in the first incidence matrix as a weight network layer and the change value of each index in the first index change matrix as input data to acquire a health state assessment model, and outputting a first safety index according to the health state assessment model.
Further, the model acquisition module further includes:
an expression acquisition module for the health status assessment model, the expression being as follows:； wherein ,/>Characterizing a health state assessment model; />Characterizing a first correlation matrix->Vector coordinates>；/>Characterizing a first index change matrix->Vector coordinates>，/>,/>All are->Is a matrix of (a); />Characterizing regularization term->The characterization is based on regularized weight coefficients.
Further, the model acquisition module further includes:
the structure design information acquisition module is used for acquiring the structure design information of the mobile power supply box;
the exposed module judging module is used for determining whether the protection module set comprises an exposed module or not according to the structural design information, and determining the exposed module set if the protection module set comprises the exposed module;
the model optimization module is used for generating a risk adjustment coefficient set according to the exposed module set, generating an adjustment network layer according to the risk adjustment coefficient set, and optimizing the health state assessment model.
Through the foregoing detailed description of a method for intelligently evaluating the health status of a mobile power box, those skilled in the art can clearly know a method and a system for intelligently evaluating the health status of a mobile power box in this embodiment, and for the device disclosed in the embodiment, the description is relatively simple because it corresponds to the method disclosed in the embodiment, and the relevant points refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. 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 application. Thus, the present application 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 (8)
1. An intelligent assessment method for health status of a mobile power box is characterized by comprising the following steps:
acquiring a first characteristic function of a mobile power supply box, wherein the first characteristic function is a function for identifying the protection attribute of the mobile power supply box;
identifying a component of the mobile power box according to the first characteristic function, outputting a protection module set, and generating a first module distribution matrix according to the protection module set, wherein each coordinate in the first module distribution matrix corresponds to one module;
acquiring an initial scene and a target scene of the mobile power box for moving, and generating a first index change matrix according to scene change indexes between the initial scene and the target scene;
analyzing the connection relation between each module in the first module distribution matrix and each index in the first index change matrix, and outputting a first incidence matrix for identifying the change perception degree between each module and each index;
evaluating the mobile power supply box according to the first incidence matrix and the first index change matrix, and outputting a first safety index, wherein the first safety index is a protection health state of the mobile power supply box under the condition of identifying scene movement;
and generating first evaluation reminding information according to the first safety index.
2. The method of claim 1, wherein the method further comprises:
identifying environmental parameters based on the first characteristic function, and acquiring a first initial k value;
analyzing the first index change matrix to determine a K value selection interval;
and carrying out optimizing clustering on all the environmental parameters according to a K-clustering method, outputting a first preset K value, and determining the number of scene index acquisitions according to the first preset K value.
3. The method of claim 1, wherein the method further comprises:
identifying a supply source of the mobile power box to obtain a power supply source;
generating a second index change matrix according to the scene change index between the initial scene and the target scene;
outputting a second incidence matrix according to the connection relation between the power supply source and each index in the second index change matrix;
evaluating the mobile power supply box according to the second incidence matrix and the second index change matrix, and outputting a second safety index, wherein the second safety index is a power supply health state of the mobile power supply box under the condition of scene movement identification;
and calculating according to the first safety index and the second safety index to generate second evaluation reminding information.
4. The method of claim 1, wherein the method further comprises:
judging whether the mobile power supply box is of a detachable structure, and determining a first detachable part when the mobile power supply box is of the detachable structure, wherein the first detachable part is a part needing scene movement;
and confirming the components of the mobile power box according to the first disassembly part, and outputting the screened protection module set.
5. The method of claim 1, wherein the mobile power box is evaluated according to the first correlation matrix and the first index change matrix, and a first security index is output, the method comprising:
obtaining the change value of each index in the first index change matrix;
based on a first mapping function, a pre-trained three-layer fully-connected neural network is obtained, wherein the first mapping function is a mapping relation between vectors in the first incidence matrix and vectors in the first index change matrix:
and training the neural network by taking each coordinate vector in the first incidence matrix as a weight network layer and taking the change value of each index in the first index change matrix as input data to obtain a health state evaluation model, and outputting a first safety index according to the health state evaluation model.
6. The method of claim 5, wherein the expression of the health assessment model is as follows:； wherein ,/>Characterizing a health state assessment model; />Characterizing a first correlation matrix->Vector coordinates>；/>Characterizing a first index change matrix->Vector coordinates>，/>,/>All are->Is a matrix of (a); />Characterizing regularization term->The characterization is based on regularized weight coefficients.
7. The method of claim 5, wherein the method further comprises:
obtaining structural design information of the mobile power box;
determining whether the protection module set comprises an exposed module according to the structural design information, and determining the exposed module set if the protection module set comprises the exposed module;
and generating a risk adjustment coefficient set according to the exposed module set, generating an adjustment network layer according to the risk adjustment coefficient set, and optimizing the health state evaluation model.
8. An intelligent assessment system for health status of a mobile power box, the system comprising:
the function acquisition module is used for acquiring a first characteristic function of the mobile power supply box, wherein the first characteristic function is a function for identifying the protection attribute of the mobile power supply box;
the module distribution matrix generation module is used for identifying the components of the mobile power box according to the first characteristic function, outputting a protection module set and generating a first module distribution matrix according to the protection module set, wherein each coordinate in the first module distribution matrix corresponds to one module;
the index change matrix generation module is used for acquiring an initial scene and a target scene of the mobile power box for moving and generating a first index change matrix according to scene change indexes between the initial scene and the target scene;
the first incidence matrix output module is used for analyzing the connection relation between each module in the first module distribution matrix and each index in the first index change matrix and outputting a first incidence matrix for identifying the change perception degree between each module and each index;
the safety index output module is used for evaluating the mobile power supply box according to the first incidence matrix and the first index change matrix and outputting a first safety index, wherein the first safety index is a protection health state of the mobile power supply box under the condition of marking scene movement;
and the reminding information generation module is used for generating first evaluation reminding information according to the first safety index.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310864041.4A CN116579192B (en) | 2023-07-14 | 2023-07-14 | Intelligent assessment method and system for health state of mobile power box |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310864041.4A CN116579192B (en) | 2023-07-14 | 2023-07-14 | Intelligent assessment method and system for health state of mobile power box |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116579192A true CN116579192A (en) | 2023-08-11 |
| CN116579192B CN116579192B (en) | 2023-09-12 |
Family
ID=87541769
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310864041.4A Active CN116579192B (en) | 2023-07-14 | 2023-07-14 | Intelligent assessment method and system for health state of mobile power box |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116579192B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103337043A (en) * | 2013-06-27 | 2013-10-02 | 广东电网公司电力调度控制中心 | Pre-warning method and system for running state of electric power communication equipment |
| CN111460656A (en) * | 2020-03-31 | 2020-07-28 | 合肥优尔电子科技有限公司 | Method and system for evaluating operation life of communication power supply of electric power machine room |
| CN115859588A (en) * | 2022-11-22 | 2023-03-28 | 交控科技股份有限公司 | Equipment health state estimation method based on noise influence, equipment and storage medium |
-
2023
- 2023-07-14 CN CN202310864041.4A patent/CN116579192B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103337043A (en) * | 2013-06-27 | 2013-10-02 | 广东电网公司电力调度控制中心 | Pre-warning method and system for running state of electric power communication equipment |
| CN111460656A (en) * | 2020-03-31 | 2020-07-28 | 合肥优尔电子科技有限公司 | Method and system for evaluating operation life of communication power supply of electric power machine room |
| CN115859588A (en) * | 2022-11-22 | 2023-03-28 | 交控科技股份有限公司 | Equipment health state estimation method based on noise influence, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116579192B (en) | 2023-09-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Rao et al. | Machine learning for solar array monitoring, optimization, and control | |
| CN108334894B (en) | Unsupervised machine learning-based transformer oil temperature abnormity identification method | |
| CN116311854B (en) | Method and system for early warning of abnormal operation of lithium battery energy storage station | |
| CN111931556B (en) | Power transmission line icing monitoring and management system | |
| Jia et al. | Validity evaluation of transformer DGA online monitoring data in grid edge systems | |
| Deboever et al. | Practical data-driven methods to improve the accuracy and detail of hosting capacity analysis | |
| CN113125903A (en) | Line loss anomaly detection method, device, equipment and computer-readable storage medium | |
| CN115167530A (en) | Live working investigation data processing method and system based on multi-dimensional sensing | |
| CN116824517A (en) | Substation operation and maintenance safety control system based on visualization | |
| CN116579192B (en) | Intelligent assessment method and system for health state of mobile power box | |
| CN116522565B (en) | BIM-based power engineering design power distribution network planning method and computer equipment | |
| CN109508820A (en) | Campus electricity demand forecasting modeling method based on differentiation modeling | |
| CN117372954A (en) | Charging station safety monitoring method, device, system and computer equipment | |
| CN116308883A (en) | Regional power grid data overall management system based on big data | |
| CN116884159A (en) | Intelligent fire-fighting early warning method and system based on AI (advanced technology attachment) identification | |
| CN116383937A (en) | Digital twin protection evaluation method for villages | |
| CN113988189B (en) | Migration fault diagnosis method for cross-wind turbine generator | |
| CN110188964A (en) | A kind of photovoltaic power generation output forecasting method based on correlation | |
| CN116662840A (en) | Low-voltage station user phase identification method based on machine learning | |
| CA2884384C (en) | System data compression system and method thereof | |
| CN114818871A (en) | Abnormal electricity utilization detection method for power distribution network with distributed power supply | |
| CN113421029A (en) | State acquisition and identification terminal for transformer substation protection pressing plate | |
| Moradzadeh et al. | Image processing-based data integrity attack detection in dynamic line rating forecasting applications | |
| CN116934057B (en) | Camera layout method, device and equipment | |
| CN110232090A (en) | A kind of integrated detection of multi-angle of view time series abnormal point and method for visualizing |
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 |