CN117291575A - Equipment maintenance method, equipment maintenance device, computer equipment and storage medium - Google Patents
Equipment maintenance method, equipment maintenance device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN117291575A CN117291575A CN202311290480.5A CN202311290480A CN117291575A CN 117291575 A CN117291575 A CN 117291575A CN 202311290480 A CN202311290480 A CN 202311290480A CN 117291575 A CN117291575 A CN 117291575A
- Authority
- CN
- China
- Prior art keywords
- data
- equipment
- state
- state evaluation
- evaluation result
- 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.)
- Pending
Links
- 238000012423 maintenance Methods 0.000 title claims abstract description 82
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000003860 storage Methods 0.000 title claims abstract description 13
- 238000011156 evaluation Methods 0.000 claims abstract description 120
- 238000012360 testing method Methods 0.000 claims abstract description 34
- 238000012544 monitoring process Methods 0.000 claims description 40
- 238000004590 computer program Methods 0.000 claims description 21
- 230000011218 segmentation Effects 0.000 claims description 18
- 238000005516 engineering process Methods 0.000 claims description 12
- 238000006243 chemical reaction Methods 0.000 claims description 11
- 238000004140 cleaning Methods 0.000 claims description 11
- 238000005065 mining Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 8
- 238000010295 mobile communication Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 description 16
- 238000007405 data analysis Methods 0.000 description 12
- 238000012545 processing Methods 0.000 description 12
- 230000008569 process Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 238000001914 filtration Methods 0.000 description 8
- 238000007726 management method Methods 0.000 description 8
- 230000036541 health Effects 0.000 description 6
- 238000001514 detection method Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 4
- 230000018109 developmental process Effects 0.000 description 4
- 238000007689 inspection Methods 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 230000003862 health status Effects 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 230000008439 repair process Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000013499 data model Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000009472 formulation Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000012098 association analyses Methods 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000000528 statistical test Methods 0.000 description 1
- 230000003442 weekly effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- 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
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- Educational Administration (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a device maintenance method, a device, a computer device and a storage medium. The method comprises the following steps: acquiring relevant multidimensional data of the equipment; performing state evaluation on the equipment according to the multidimensional data to obtain a state evaluation result of the equipment; the state evaluation result comprises a plurality of state quantities; selecting equipment to be overhauled from the equipment based on a state evaluation result, matching the state quantity corresponding to the equipment to be overhauled with equipment test data and historical overhauling data as a keyword, and acquiring the fault probability of the equipment to be detected according to the successful frequency of the state quantity matching; and setting an overhaul strategy according to the state evaluation result and the fault probability. By adopting the method, the establishment of the overhaul strategy can be optimized, and the aim of improving the overhaul efficiency is fulfilled.
Description
Technical Field
The present disclosure relates to the field of data processing technologies, and in particular, to an equipment maintenance method, an apparatus, a computer device, and a storage medium.
Background
With the improvement of management and digitization levels, the asset management system puts forward new requirements on maintenance operation efficiency, and from the aspects of safety, efficiency and cost, the maintenance planning is strengthened and guided by carrying out data analysis on the scenes such as power grid operation state scenes, equipment reliability, external influence conditions and the like, the power grid operation mode is reasonably arranged, and the power outage strategy is optimized, so that the operation maintenance work efficiency is improved, the maintenance operation lean management level is improved, and the integration of informatization and production processes is realized.
However, existing repair methods still rely primarily on post-fault repair and scheduled repair. After the fault, the maintenance work is arranged after the fault occurs, and obviously, the maintenance mode can bring unexpected loss to production and life. Most maintenance objects for planned maintenance are judged according to state maintenance management regulations, technical improvement maintenance requirements and experience of basic staff, and the maintenance objects lack of flexibility and depend on experience seriously, so that the maintenance efficiency is low.
Disclosure of Invention
In view of the foregoing, it is desirable to provide an equipment inspection method, apparatus, computer device, and storage medium that can more accurately locate an inspection object and improve inspection efficiency.
In a first aspect, the present application provides an equipment servicing method, comprising:
acquiring relevant multidimensional data of the equipment; the multidimensional data comprises equipment basic data, quasi-real-time monitoring data, equipment test data and historical overhaul data;
performing state evaluation on the equipment according to the multidimensional data to obtain a state evaluation result of the equipment; the state evaluation result comprises a plurality of state quantities;
selecting equipment to be overhauled from the equipment based on a state evaluation result, matching the state quantity corresponding to the equipment to be overhauled with equipment test data and historical overhauling data as a keyword, and acquiring the fault probability of the equipment to be detected according to the successful frequency of the state quantity matching;
and setting an overhaul strategy according to the state evaluation result and the fault probability.
In one embodiment, evaluating a device for status based on multidimensional data includes:
performing data cleaning, data exploration and data conversion on the multidimensional data to obtain effective data;
and performing state evaluation based on the valid data.
In one embodiment, performing state evaluation on the device according to the multidimensional data, and obtaining a state evaluation result of the device includes:
matching the effective data corresponding to the quasi-real-time monitoring data with a state evaluation rule to obtain a state evaluation result;
and the effective data corresponding to the quasi-real-time monitoring data are classified and managed according to different equipment types.
In one embodiment, matching the state quantity corresponding to the equipment to be overhauled with the equipment test data and the historical overhauling data as a keyword includes:
preprocessing equipment test data and historical overhaul data to obtain a plurality of word segmentation units;
converting the word segmentation unit into feature representation of the word segmentation;
extracting features of the feature representations of the segmented words to obtain feature data;
text mining and pattern extraction are carried out according to the characteristic data, fault key influence factors corresponding to the equipment types are obtained, and a fault root cause library is established according to the key influence factors;
and matching the state quantity corresponding to the equipment to be overhauled with the fault root cause library corresponding to the equipment type of the equipment to be overhauled by taking the state quantity corresponding to the equipment to be overhauled as a keyword.
In one embodiment, the determining the overhaul strategy according to the state evaluation result and the fault probability includes:
based on a predictive evaluation guide, establishing a maintenance strategy model of a state evaluation result and a fault probability;
and carrying out maintenance decision statistics according to the maintenance strategy model corresponding to each device, and making a maintenance strategy according to the statistics result.
In one embodiment, acquiring relevant multidimensional data of a device includes:
and acquiring multidimensional data from the state monitoring system, the data platform and the equipment management system in a preset triggering mode through unified data interface specifications and mobile communication technology.
In a second aspect, the present application provides an equipment servicing device, the device comprising:
the data acquisition module is used for acquiring relevant multidimensional data of the equipment; the multidimensional data comprises equipment basic data, quasi-real-time monitoring data, equipment test data and historical overhaul data;
the state evaluation module is used for performing state evaluation on the equipment according to the multidimensional data to obtain a state evaluation result of the equipment; the state evaluation result comprises a plurality of state quantities;
the fault prediction module is used for selecting equipment to be overhauled from the equipment based on the state evaluation result, matching the state quantity corresponding to the equipment to be overhauled with the equipment test data and the historical overhauling data as a keyword, and acquiring the fault probability of the equipment to be detected according to the successful frequency of the state quantity matching;
and the strategy making module is used for making an overhaul strategy according to the state evaluation result and the fault probability.
In a third aspect, the present application provides a computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
acquiring relevant multidimensional data of the equipment; the multidimensional data comprises equipment basic data, quasi-real-time monitoring data, equipment test data and historical overhaul data;
performing state evaluation on the equipment according to the multidimensional data to obtain a state evaluation result of the equipment; the state evaluation result comprises a plurality of state quantities;
selecting equipment to be overhauled from the equipment based on a state evaluation result, matching the state quantity corresponding to the equipment to be overhauled with equipment test data and historical overhauling data as a keyword, and acquiring the fault probability of the equipment to be detected according to the successful frequency of the state quantity matching;
and setting an overhaul strategy according to the state evaluation result and the fault probability.
In a fourth aspect, the present application provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of:
acquiring relevant multidimensional data of the equipment; the multidimensional data comprises equipment basic data, quasi-real-time monitoring data, equipment test data and historical overhaul data;
performing state evaluation on the equipment according to the multidimensional data to obtain a state evaluation result of the equipment; the state evaluation result comprises a plurality of state quantities;
selecting equipment to be overhauled from the equipment based on a state evaluation result, matching the state quantity corresponding to the equipment to be overhauled with equipment test data and historical overhauling data as a keyword, and acquiring the fault probability of the equipment to be detected according to the successful frequency of the state quantity matching;
and setting an overhaul strategy according to the state evaluation result and the fault probability.
In a fifth aspect, the present application provides a computer program product comprising a computer program which, when executed by a processor, performs the steps of:
acquiring relevant multidimensional data of the equipment; the multidimensional data comprises equipment basic data, quasi-real-time monitoring data, equipment test data and historical overhaul data;
performing state evaluation on the equipment according to the multidimensional data to obtain a state evaluation result of the equipment; the state evaluation result comprises a plurality of state quantities;
selecting equipment to be overhauled from the equipment based on a state evaluation result, matching the state quantity corresponding to the equipment to be overhauled with equipment test data and historical overhauling data as a keyword, and acquiring the fault probability of the equipment to be detected according to the successful frequency of the state quantity matching;
and setting an overhaul strategy according to the state evaluation result and the fault probability.
The equipment maintenance method, the equipment maintenance device, the computer equipment and the storage medium acquire relevant multidimensional data of the equipment; performing state evaluation on the equipment according to the multidimensional data to obtain a state evaluation result of the equipment; the state evaluation result comprises a plurality of state quantities; selecting equipment to be overhauled from the equipment based on a state evaluation result, matching the state quantity corresponding to the equipment to be overhauled with equipment test data and historical overhauling data as a keyword, and acquiring the fault probability of the equipment to be detected according to the successful frequency of the state quantity matching; and setting an overhaul strategy according to the state evaluation result and the fault probability. Through carrying out state evaluation on the equipment, selecting equipment with negative state evaluation as equipment to be overhauled, and reducing the analysis range; and finally, a part of equipment can be purposefully arranged with important and dense detection tasks according to the state evaluation result and the fault probability, and conventional detection is carried out on other equipment, so that the optimization of an overhaul strategy is completed. Compared with the traditional post-fault maintenance and planned maintenance scheme, the method greatly reduces the possibility of faults, improves the maintenance efficiency and ensures the safe operation of the power grid.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the related art, the drawings that are required to be used in the embodiments or the related technical descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to the drawings without inventive effort for a person having ordinary skill in the art.
FIG. 1 is a diagram of an application environment for a method of equipment servicing in one embodiment;
FIG. 2 is a schematic flow diagram of a method of servicing an apparatus in one embodiment;
FIG. 3 is a flow diagram of efficient data acquisition in one embodiment;
FIG. 4 is a flow chart illustrating probability of failure prediction in one embodiment;
FIG. 5 is a flow diagram of fault root library generation in one embodiment;
FIG. 6 is a flow diagram of an embodiment of obtaining an overhaul strategy;
FIG. 7 is a schematic flow chart of a maintenance plan in one embodiment;
FIG. 8 is a flow diagram of a method of equipment servicing in one embodiment;
FIG. 9 is a block diagram of an equipment servicing device in one embodiment;
fig. 10 is an internal structural view of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The equipment maintenance method provided by the embodiment of the application can be applied to an application environment shown in figure 1. Wherein the terminal 102 communicates with the server 104 via a network. The data storage system may store data that the server 104 needs to process. The data storage system may be integrated on the server 104 or may be located on a cloud or other network server. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, internet of things devices, and portable wearable devices, where the internet of things devices may be smart speakers, smart televisions, smart air conditioners, smart vehicle devices, and the like. The portable wearable device may be a smart watch, smart bracelet, headset, or the like. The server 104 may be implemented as a stand-alone server or as a server cluster of multiple servers.
In an exemplary embodiment, as shown in fig. 2, an equipment maintenance method is provided, and an example of application of the method to the terminal 102 in fig. 1 is described, including the following steps 202 to 208. Wherein:
step 202, acquiring relevant multidimensional data of equipment; the multidimensional data includes equipment base data, near real-time monitoring data, equipment test data, and historical service data.
The data acquisition of the equipment is the basis of the fault prediction of the subsequent equipment, so the acquired data must be capable of correctly reflecting the service requirements, otherwise, the analysis conclusion can lead to misleading of the service. In the data analysis process, firstly, the data requirement range of the equipment is required to be combed, specific data requirement ranges are listed, secondly, information such as a data source, data quality, a data structure and the like is further confirmed according to the current service situation and actual analysis requirements, and accordingly data collection work is conducted.
The collected data should be multidimensional, including equipment base data, equipment test data, and historical overhaul data in addition to near real-time monitoring data that is capable of reflecting the health status of the equipment, in order to more fully analyze and predict the future health status of the equipment.
In addition, the multi-dimensional data may also include environmental data that aids in predicting the future health of the device.
And uploading the acquired multidimensional data to a data analysis platform for subsequent data extraction and analysis.
Step 204, performing state evaluation on the equipment according to the multidimensional data to obtain a state evaluation result of the equipment; the state evaluation result includes a number of state quantities.
The equipment state evaluation is to analyze and evaluate the data reflecting the equipment state index item according to the equipment state characteristics and the state evaluation related standard, complete the health state evaluation of the main parts of the equipment, and finally obtain the whole health state grade of the equipment according to the state evaluation result of the parts. The state level such as health state, attention state, abnormal state, serious state, etc. can be set according to the number and name of the state level.
And 206, selecting equipment to be overhauled from the equipment based on the state evaluation result, matching the state quantity corresponding to the equipment to be overhauled with the equipment test data and the historical overhauling data as a keyword, and acquiring the fault probability of the equipment to be detected according to the successful frequency of the state quantity matching.
And selecting equipment with a negative state evaluation result from the equipment as equipment to be overhauled, wherein the state evaluation is, for example, attention state, abnormal state, serious state and the like. It should be noted that, the equipment to be overhauled in this embodiment is screened equipment to be overhauled with emphasis, which does not mean that only the part of the equipment is overhauled in actual operation, and other equipment can still be overhauled routinely.
Matching the state quantity with the equipment experimental data and the historical maintenance data, wherein the higher the occurrence frequency is, the more the state of the equipment is matched with the condition needing maintenance in the historical record, and the higher the probability of the equipment failure is.
And step 208, formulating an overhaul strategy according to the state evaluation result and the fault probability.
The state evaluation result and the fault probability reflect the urgency of equipment overhaul, and the overhaul strategy is formulated according to the urgency. And (3) when carrying out maintenance feasibility analysis according to the state evaluation result and the fault probability, starting from multiple aspects such as resources, time, cost, benefit and the like, determining a maintenance plan, determining maintenance guarantee resources, and giving the activity time, place and maintenance content of maintenance advice.
According to the embodiment, through carrying out state evaluation on the equipment, equipment with negative state evaluation is selected as equipment to be overhauled, so that the analysis range is reduced; and finally, a part of equipment can be purposefully arranged with important and dense detection tasks according to the state evaluation result and the fault probability, and the other equipment can be conventionally detected, so that the optimization of an overhaul strategy is completed, and predictive maintenance is realized. Predictive maintenance is maintenance based on a state, and when the equipment is in operation, the main (or needed) part of the equipment is subjected to periodic (or continuous) state monitoring and fault diagnosis, the state of the equipment is judged, the future development trend of the state of the equipment is predicted, and a predictive maintenance plan is formulated in advance according to the state development trend of the equipment and possible fault modes to determine the time, content, mode and necessary technology and material support of the machine to be repaired. Compared with the traditional post-fault maintenance and planned maintenance scheme, the method greatly reduces the possibility of faults, improves the maintenance efficiency and ensures the safe operation of the power grid.
In one embodiment, as shown in FIG. 3, in step 204, evaluating the status of the device based on the multidimensional data includes: performing data cleaning, data exploration and data conversion on the multidimensional data to obtain effective data; and performing state evaluation based on the valid data.
The multidimensional data collected in step 202 is different in source and diverse in data, so that the multidimensional data needs to be preprocessed, the data type and scale are defined, the data is primarily understood, meanwhile, the noise in the data is processed, the effective number is extracted to support the subsequent data analysis, and the effective number is input into an analysis model.
The data processing comprises data selection, data cleaning, data exploration, data conversion and the like, and the selection and cleaning of data objects are carried out based on a business scene analysis target, so that the data can be required to highlight the basic characteristics of corresponding business characteristics and processes, the data exploration provides support for model construction for finding the characteristics and rules of the data, and the data conversion is carried out for normalizing the data, so that certain data requirements are met.
The data cleaning means that data missing and bad data exist in original data acquired from a data source, and if the original data are not processed, model failure can be caused, so that the original data are filtered and denoised, and effective data are extracted. The specific data cleaning thought is to finish the data cleaning work by combining the actual service condition with the data analysis requirement, judging the abnormal value, processing the missing value, unifying the data structure and the like strictly according to the logic relation between the source data. Meanwhile, data cleaning can more effectively promote development of data exploration.
Data exploration refers to finding patterns, trends, anomalies, and associations in data. Through data exploration, data characteristics and rules are found preliminarily, and input basis is provided for subsequent data modeling. Common data exploration methods include data feature description, correlation analysis, principal component analysis and the like. The data exploration and the data cleaning are interactively performed, so that the data quality is improved, and a data basis is provided for data analysis.
The data conversion comprises the generation of derivative variables, the unification, the standardization and the like, and the purposes of data format conversion, data integration and data reconstruction are realized.
The multidimensional data after data conversion can obtain effective data and carry out subsequent state evaluation.
In one embodiment, step 204 includes: matching the effective data corresponding to the quasi-real-time monitoring data with a state evaluation rule to obtain a state evaluation result; and the effective data corresponding to the quasi-real-time monitoring data are classified and managed according to different equipment types.
The state evaluation rule is formulated for an expert, and the existing form can be a state evaluation standard library, and various state quantities of the power equipment of each type and state scores corresponding to the state quantities are listed in detail. And matching and scoring the state evaluation rule and the state quantity of the equipment to obtain the state evaluation result of each part of the equipment, thereby obtaining the state evaluation result of the whole equipment.
Because the types of the power equipment are numerous, the operation parameters of the equipment are different, in order to improve the quasi-real-time performance of equipment state evaluation, the recording and the inquiring of the quasi-real-time data are ensured, when the quasi-real-time monitoring data are managed, different data information is appointed according to the different equipment types on the data information appointing, namely, the data information is managed by different classifications of the equipment types.
The real-time state data of the equipment are continuously collected by a plurality of monitoring equipment to increase the source of the quasi-real-time monitoring data of the equipment, and the quasi-real-time monitoring data are stored in a data analysis platform in a classified mode, so that the correlation between the quasi-real-time monitoring data and the equipment state evaluation is achieved. In this embodiment, the device code is used to automatically collect the device quasi-real-time monitoring data, and the system defaults to collect the last data at the time point.
In one embodiment, the corresponding real-time monitoring data collected over time becomes historical monitoring data. And if the historical state of the equipment is required to be evaluated, extracting the historical monitoring data of the relevant historical nodes to evaluate.
In one embodiment, the status assessment may be performed once after each day of near real-time monitoring data updates. The update time and the state evaluation time can be freely set as needed. When the quasi-real-time monitoring data is taken, if the state quantity contains an average value, the average value is taken as an evaluation basis. For example, when a certain state quantity is obtained as an average value of quasi-real-time monitoring data at each point in a whole day, the state quantity is evaluated based on the average value.
In one embodiment, matching the state quantity corresponding to the equipment to be serviced as a key with the equipment test data and the historical service data in step 206 includes: preprocessing equipment test data and historical overhaul data to obtain a plurality of word segmentation units; converting the word segmentation unit into feature representation of the word segmentation; extracting features of the feature representations of the segmented words to obtain feature data; text mining and pattern extraction are carried out according to the characteristic data, fault key influence factors corresponding to the equipment types are obtained, and a fault root cause library is established according to the key influence factors; and matching the state quantity corresponding to the equipment to be overhauled with the fault root cause library corresponding to the equipment type of the equipment to be overhauled by taking the state quantity corresponding to the equipment to be overhauled as a keyword.
In this embodiment, the device test data and the historical maintenance data are corresponding effective data obtained after data processing. Wherein, the historical overhaul data comprises patrol data, overhaul data and the like. Both the equipment test data and the historical overhaul data are presented in text form.
The core of predictive maintenance is fault prediction analysis, the basic idea is to collect and summarize information of equipment with faults, decompose different fault key influence factors of various types of equipment, establish an equipment fault root cause library, and select a proper algorithm according to various fault characteristics of different equipment to establish a prediction analysis model.
As shown in fig. 4, text mining, statistical analysis and information association are performed according to the effective data obtained by data processing, key influence factors corresponding to different faults are found, a root cause library of equipment faults is constructed, different equipment and faults correspond to different root cause libraries, and a predictive analysis model is built based on the root cause library for subsequent state evaluation and auxiliary decision making by an overhaul strategy.
The specific operation of constructing root cause library is shown in fig. 5, and the equipment test data and the historical overhaul data are used as the text sources. The text source is preprocessed first, including word segmentation, filtering of the imaginary words and merging of the root words. The word segmentation process is a basic task in natural language processing, and aims to segment a continuous text into a series of words with semantic meaning according to the rule of language, and the words are called word segmentation units. The term "refers to a word having no actual meaning in grammatical function, such as prepositions, conjunctions, articles, and the like. These terms are generally not helpful to the meaning analysis and understanding task of the text, so in some text processing tasks we need to filter or exclude terms. Combining the root words means combining the root words in the words so as to reduce the redundancy of the words and extract the core meaning of the words. Combining the root words can be achieved through morphological analysis, stem extraction and other technologies.
After the word segmentation unit is acquired, the word segmentation unit is converted into a characteristic representation, namely, the text is represented into a characteristic form which can be processed by a machine learning or deep learning model. In the conversion process, operations such as filtering characteristics, calculating weights, combining characteristics and the like can be performed. Wherein the filtering features aim at improving the effect and generalization capability of the model by removing irrelevant or redundant features, and the filtering methods comprise variance filtering, correlation filtering, filtering methods based on statistical tests, L1 regularization and the like. The importance and influence of the features in the model are determined by calculating the weight values, and the implementation method comprises information gain, gini coefficient and the like. Combining features refers to combining multiple features into one higher level feature to capture more complex patterns and associations.
Next, feature extraction is performed on the above feature representation, including feature reduction and weight adjustment steps. Feature reduction refers to the fact that the dimension of data is reduced by reducing the number of features, redundant features and noise can be removed in the process, and generalization capability and model accuracy of a model are improved. The weight adjustment step is a process of adjusting based on the weight obtained in the feature representation conversion process, and the aim is to enable the feature to be predicted more effectively in the model and improve the model performance. And acquiring feature data through feature extraction.
The method comprises the steps of performing text mining and pattern extraction on feature data, and specifically comprises the steps of obtaining a classification model through text classification and obtaining a clustering model through text clustering through association analysis and obtaining association rules. According to the embodiment, the text mining technology is utilized to mine the equipment test data and the historical overhaul data, so that all types of faults and influencing factors causing the faults of the equipment are found out, wherein the influencing factors comprise all equipment test data corresponding to the equipment, all types of defects and all quasi-real-time monitoring data indexes influencing the state of the equipment. Finally, through the steps, a root cause library is constructed.
On the basis of a fault root cause library, matching is carried out with the current state flow, and the occurrence frequency of the matched keywords is used as the basis of the probability of possible faults of the equipment.
In one real-time, the fault root library is subjected to fault prediction through a decision tree algorithm, a neural network and an association rule mining technology.
In one embodiment, as shown in FIG. 6, step 208 includes: based on a predictive evaluation guide, establishing a maintenance strategy model of a state evaluation result and a fault probability; and carrying out maintenance decision statistics according to the maintenance strategy model corresponding to each device, and making a maintenance strategy according to the statistics result.
The predictive evaluation guideline is formulated by a professional, the following general principle is that the worse the equipment state evaluation result is, the larger the equipment predictive failure rate is, the more the maintenance is preferentially arranged, and the specific details are based on the actual formulation. Based on the predictive evaluation guideline, an overhaul strategy model of the state evaluation result and the fault probability can be constructed.
And according to the overhaul strategy model, the state evaluation result and the fault probability corresponding to each device, obtaining an overhaul plan corresponding to each device, and making an overhaul strategy according to the overhaul plan.
In one embodiment, when executing the overhaul strategy, inquiring the overhaul plan according to the inquiry conditions of the transformer substation, the interval unit, the equipment type and the like; and carrying out maintenance plan statistics according to the statistical items such as the auditing state, the archiving, the evaluation result, the recommended maintenance category and the like, and assisting a user in developing the establishment of maintenance strategies and the execution of maintenance work.
In one embodiment, after the maintenance strategy is formulated, an auxiliary decision is generated and the staff is reminded in a short message mode, and an auxiliary decision report is generated for the staff to review.
As shown in fig. 7, in the process of preparing the maintenance plan, the task pool may create an auxiliary decision source, and when the related operator clicks the auxiliary decision source during task creation of the task pool, the system synchronizes the related information of the auxiliary decision to the created task. The newly-built task synchronization information comprises: information such as power station, voltage class, equipment type, equipment name, service type, recommended service time, etc. After the newly built maintenance task passes the examination, the maintenance plan can be executed by the staff.
In one embodiment, step 202 includes: and acquiring multidimensional data from the state monitoring system, the data platform and the equipment management system in a preset triggering mode through unified data interface specifications and mobile communication technology.
The data acquisition step is obtained through an online state monitoring system, a data platform and an equipment management system. The multidimensional data acquisition gathers information for analyzing the equipment state from an information system to a data analysis platform in a certain triggering mode through unified data interface specifications and mobile communication technology for subsequent data processing. The triggering mode is fixed time point triggering, interval time triggering, data updating triggering and the like.
The embodiment can realize the acquisition of data by multiple platforms by developing unified data interface specifications and mobile communication technology, thereby acquiring multidimensional data.
In one embodiment, as shown in fig. 8, the equipment servicing method comprises the steps of:
1. and acquiring various basic data, quasi-real-time monitoring data, equipment test data, historical overhaul data, environmental data and the like of various equipment reflecting the equipment health status indexes in the existing equipment asset related system, the equipment status online monitoring system and the data platform through interfaces, and storing the various data in the data analysis platform.
2. And filtering, converting, combining and other processing and processing the data based on the equipment state evaluation and equipment fault prediction data model by utilizing various data of the equipment stored in the data analysis platform, so that the data finally becomes a state quantity index reflecting the health state of the equipment.
3. Based on the state quantity index, the current equipment health state grade is evaluated from equipment state evaluation and fault prediction, the future state development trend of the equipment is analyzed and predicted, and monitoring and early warning are given to the equipment in real time.
4. Based on the result of the data analysis, optimizing the maintenance sequence, maintenance time and maintenance grade arrangement of the equipment, and finally outputting the data to relevant responsible persons in a report form.
5. And according to the result of the auxiliary decision, the method is used for preparing a maintenance plan to achieve the aim of efficiently executing maintenance work.
The establishment of the traditional overhaul scheme depends on experience or an immobilized overhaul flow, and effective summarization analysis of the existing state, historical operation data and other important data of the equipment is not performed, so that on one hand, low utilization rate of the existing important data is caused, and on the other hand, efficient support of an overhaul plan is not realized.
The invention performs summarized analysis on information such as equipment real-time state, historical operation data (including equipment historical state, defects, detection records and the like), equipment years, equipment environmental factors, familial defects and the like, and completes mining prediction of the information according to an established data model, thereby realizing the following aims:
1. specific predictive maintenance information is formed by summarizing and analyzing the equipment related information, and a maintenance plan is formulated for assisting a transportation and inspection person to develop predictive maintenance work according to the predictive maintenance auxiliary decision report.
2. The data is processed and analyzed through big data to form a predictive analysis result, equipment data meeting the predictive maintenance condition is provided for corresponding responsibilities, and whether the corresponding responsibilities are included in the annual, monthly and weekly scheduled maintenance is checked, so that the purposes of reducing the time for manually confirming maintenance objects and improving the working efficiency are achieved.
3. After the maintenance object is clearly maintained, according to the predicted result, the time, the content, the mode and the necessary technology for equipment maintenance are suggested, and the maintenance plan is further supported.
4. After overhaul is completed, fault information, solutions, technical means and other information are recorded, effective and reasonable data support is provided for predictive overhaul work of the power grid, and virtuous circle of the predictive overhaul work is promoted.
It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides an equipment maintenance device for realizing the equipment maintenance method. The implementation of the solution provided by the device is similar to the implementation described in the above method, so the specific limitation in the embodiment of one or more equipment servicing devices provided below may be referred to the limitation of the equipment servicing method hereinabove, and will not be repeated herein.
In one exemplary embodiment, as shown in fig. 9, there is provided an equipment servicing apparatus comprising: a data acquisition module 902, a status evaluation module 904, a fault prediction module 906, and a policy formulation module 908, wherein:
a data acquisition module 902, configured to acquire relevant multidimensional data of the device; the multidimensional data includes equipment base data, near real-time monitoring data, equipment test data, and historical service data.
The state evaluation module 904 is configured to perform state evaluation on the device according to the multidimensional data, and obtain a state evaluation result of the device; the state evaluation result includes a number of state quantities.
The fault prediction module 906 is configured to select a device to be overhauled from the devices based on the state evaluation result, match a state quantity corresponding to the device to be overhauled with the device test data and the historical overhauling data as a keyword, and obtain a fault probability of the device to be detected according to a frequency of successful matching of the state quantity.
And a policy making module 908, configured to make an overhaul policy according to the state evaluation result and the fault probability.
The state evaluation module 904 is further configured to perform data cleaning, data exploration and data conversion on the multidimensional data to obtain effective data; and performing state evaluation based on the valid data.
The state evaluation module 904 is further configured to match valid data corresponding to the quasi-real-time monitoring data with a state evaluation rule, and obtain a state evaluation result; and the effective data corresponding to the quasi-real-time monitoring data are classified and managed according to different equipment types.
The fault prediction module 906 is further configured to preprocess the equipment test data and the historical overhaul data, and obtain a plurality of word segmentation units; converting the word segmentation unit into feature representation of the word segmentation; extracting features of the feature representations of the segmented words to obtain feature data; text mining and pattern extraction are carried out according to the characteristic data, fault key influence factors corresponding to the equipment types are obtained, and a fault root cause library is established according to the key influence factors; and matching the state quantity corresponding to the equipment to be overhauled with the fault root cause library corresponding to the equipment type of the equipment to be overhauled by taking the state quantity corresponding to the equipment to be overhauled as a keyword.
The policy making module 908 is further configured to establish an overhaul policy model of the state evaluation result and the failure probability based on the predictive evaluation guideline; and carrying out maintenance decision statistics according to the maintenance strategy model corresponding to each device, and making a maintenance strategy according to the statistics result.
The data acquisition module 902 is further configured to acquire multidimensional data from the state monitoring system, the data platform and the device management system in a preset triggering manner through a unified data interface specification and a mobile communication technology.
The various modules in the above-described equipment servicing device may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one exemplary embodiment, a computer device is provided, which may be a server, and the internal structure thereof may be as shown in fig. 10. The computer device includes a processor, a memory, an Input/Output interface (I/O) and a communication interface. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface is connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is for storing multidimensional data. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of service.
It will be appreciated by those skilled in the art that the structure shown in fig. 10 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In an exemplary embodiment, a computer device is provided, comprising a memory and a processor, the memory having stored therein a computer program, the processor performing the steps of all the method embodiments described above when the computer program is executed.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, carries out the steps of all the method embodiments described above.
In an embodiment, a computer program product is provided comprising a computer program which, when executed by a processor, implements the steps of all the method embodiments described above.
It should be noted that, the user information (including, but not limited to, user equipment information, user personal information, etc.) and the data (including, but not limited to, data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party, and the collection, use, and processing of the related data are required to meet the related regulations.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.
Claims (10)
1. A method of servicing an apparatus, the method comprising:
acquiring relevant multidimensional data of the equipment; the multi-dimensional data comprises equipment basic data, quasi-real-time monitoring data, equipment test data and historical overhaul data;
performing state evaluation on the equipment according to the multidimensional data to obtain a state evaluation result of the equipment; the state evaluation result comprises a plurality of state quantities;
selecting equipment to be overhauled from the equipment based on the state evaluation result, matching the state quantity corresponding to the equipment to be overhauled with the equipment test data and the historical overhauling data as a keyword, and acquiring the fault probability of the equipment to be detected according to the frequency of successful matching of the state quantity;
and setting an overhaul strategy according to the state evaluation result and the fault probability.
2. The method of claim 1, wherein said evaluating the status of the device from the multidimensional data comprises:
performing data cleaning, data exploration and data conversion on the multidimensional data to obtain effective data;
and carrying out state evaluation based on the effective data.
3. The method according to claim 2, wherein the performing the state evaluation on the device according to the multidimensional data, and obtaining the state evaluation result of the device includes:
matching the effective data corresponding to the quasi-real-time monitoring data with a state evaluation rule to obtain a state evaluation result;
and the effective data corresponding to the quasi-real-time monitoring data are classified and managed according to different equipment types.
4. The method of claim 1, wherein matching the state quantity corresponding to the equipment to be overhauled as a keyword with the equipment test data and the historical overhauling data comprises:
preprocessing the equipment test data and the historical overhaul data to obtain a plurality of word segmentation units;
converting the word segmentation unit into a feature representation of the word segmentation;
extracting the characteristics of the characteristic representations of the word segmentation to obtain characteristic data;
text mining and pattern extraction are carried out according to the characteristic data, fault key influence factors corresponding to all equipment types are obtained, and a fault root cause library is established according to the key influence factors;
and matching the state quantity corresponding to the equipment to be overhauled with the fault root cause library corresponding to the equipment type of the equipment to be overhauled by taking the state quantity as a keyword.
5. The method of claim 1, wherein the formulating a service strategy based on the status evaluation result and the failure probability comprises:
establishing an overhaul strategy model of the state evaluation result and the fault probability based on a predictive evaluation guideline;
and carrying out maintenance decision statistics according to the maintenance strategy model corresponding to each device, and making the maintenance strategy according to the statistical result.
6. The method of claim 1, wherein the acquiring the relevant multidimensional data of the device comprises:
and acquiring the multidimensional data from the state monitoring system, the data platform and the equipment management system in a preset triggering mode through unified data interface specifications and mobile communication technology.
7. An equipment servicing device, the device comprising:
the data acquisition module is used for acquiring relevant multidimensional data of the equipment; the multi-dimensional data comprises equipment basic data, quasi-real-time monitoring data, equipment test data and historical overhaul data;
the state evaluation module is used for performing state evaluation on the equipment according to the multi-dimensional data and acquiring a state evaluation result of the equipment; the state evaluation result comprises a plurality of state quantities;
the fault prediction module is used for selecting equipment to be overhauled from the equipment based on the state evaluation result, matching the state quantity corresponding to the equipment to be overhauled with the equipment test data and the historical overhauling data as a keyword, and acquiring the fault probability of the equipment to be detected according to the frequency of successful matching of the state quantity;
and the strategy making module is used for making an overhaul strategy according to the state evaluation result and the fault probability.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 6 when the computer program is executed.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311290480.5A CN117291575A (en) | 2023-09-28 | 2023-09-28 | Equipment maintenance method, equipment maintenance device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311290480.5A CN117291575A (en) | 2023-09-28 | 2023-09-28 | Equipment maintenance method, equipment maintenance device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117291575A true CN117291575A (en) | 2023-12-26 |
Family
ID=89253229
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311290480.5A Pending CN117291575A (en) | 2023-09-28 | 2023-09-28 | Equipment maintenance method, equipment maintenance device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117291575A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118133095A (en) * | 2024-05-08 | 2024-06-04 | 南京国电南自轨道交通工程有限公司 | Rail transit equipment fault prediction method based on large language model |
-
2023
- 2023-09-28 CN CN202311290480.5A patent/CN117291575A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118133095A (en) * | 2024-05-08 | 2024-06-04 | 南京国电南自轨道交通工程有限公司 | Rail transit equipment fault prediction method based on large language model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP4195112A1 (en) | Systems and methods for enriching modeling tools and infrastructure with semantics | |
| CN112181960B (en) | Intelligent operation and maintenance framework system based on AIOps | |
| US11681282B2 (en) | Systems and methods for determining relationships between defects | |
| CN112613789A (en) | Risk control data processing method and risk early warning rule prepositive data monitoring method | |
| CN110334208B (en) | LKJ fault prediction diagnosis method and system based on Bayesian belief network | |
| CN117291575A (en) | Equipment maintenance method, equipment maintenance device, computer equipment and storage medium | |
| CN116993306A (en) | Knowledge graph-based construction method and device of network collaborative manufacturing system | |
| CN116861331A (en) | Expert model decision-fused data identification method and system | |
| CN115063035A (en) | Customer evaluation method, system, equipment and storage medium based on neural network | |
| CN115719283A (en) | Intelligent accounting management system | |
| CN114968727A (en) | Database through infrastructure fault positioning method based on artificial intelligence operation and maintenance | |
| CN113778766B (en) | Hard disk fault prediction model establishment method based on multidimensional characteristics and application thereof | |
| CN117114600A (en) | RPA virtual employee management method and system for power grid production command center | |
| Bond et al. | A hybrid learning approach to prognostics and health management applied to military ground vehicles using time-series and maintenance event data | |
| CN116737681A (en) | Real-time abnormal log detection method and device, computer equipment and storage medium | |
| Mahammad et al. | Machine Learning Approach to Predict Asthma Prevalence with Decision Trees | |
| CN115187122A (en) | Enterprise policy deduction method, device, equipment and medium | |
| US20220374401A1 (en) | Determining domain and matching algorithms for data systems | |
| Anderson et al. | A Bayesian hierarchical assessment of night shift working for offshore wind farms | |
| CN114529383A (en) | Method and system for realizing tax payment tracking and tax loss early warning | |
| CN113610225A (en) | Quality evaluation model training method and device, electronic equipment and storage medium | |
| CN113743695A (en) | International engineering project bid quotation risk management method based on big data | |
| CN114386647A (en) | Method and system for predicting energy consumption of oil and gas field industry | |
| CN117391626A (en) | Engineering cost data processing method based on big data | |
| CN116523179A (en) | Urban updating right person relation chain analysis system and method |
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 |