CN117494009A - Electrical equipment state evaluation method based on insulating material pyrolysis analysis and cloud platform - Google Patents
Electrical equipment state evaluation method based on insulating material pyrolysis analysis and cloud platform Download PDFInfo
- Publication number
- CN117494009A CN117494009A CN202311526517.XA CN202311526517A CN117494009A CN 117494009 A CN117494009 A CN 117494009A CN 202311526517 A CN202311526517 A CN 202311526517A CN 117494009 A CN117494009 A CN 117494009A
- Authority
- CN
- China
- Prior art keywords
- electrical equipment
- insulation
- state
- model
- module
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 75
- 239000011810 insulating material Substances 0.000 title claims abstract description 24
- 238000004458 analytical method Methods 0.000 title description 10
- 238000000197 pyrolysis Methods 0.000 title description 4
- 238000009413 insulation Methods 0.000 claims abstract description 175
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 59
- 238000012423 maintenance Methods 0.000 claims abstract description 37
- 238000012549 training Methods 0.000 claims abstract description 31
- 230000036541 health Effects 0.000 claims abstract description 22
- 238000007726 management method Methods 0.000 claims abstract description 22
- 238000002076 thermal analysis method Methods 0.000 claims abstract description 21
- 238000000034 method Methods 0.000 claims abstract description 20
- 238000012545 processing Methods 0.000 claims abstract description 17
- 230000002068 genetic effect Effects 0.000 claims abstract description 16
- 230000036961 partial effect Effects 0.000 claims abstract description 14
- 238000005516 engineering process Methods 0.000 claims abstract description 10
- 239000013598 vector Substances 0.000 claims description 45
- 238000007637 random forest analysis Methods 0.000 claims description 21
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000005457 optimization Methods 0.000 claims description 7
- 238000005065 mining Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 5
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 238000002790 cross-validation Methods 0.000 claims description 3
- 238000013523 data management Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 abstract description 20
- 238000009826 distribution Methods 0.000 description 9
- 230000005540 biological transmission Effects 0.000 description 7
- 230000032683 aging Effects 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 4
- 230000003862 health status Effects 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 230000003449 preventive effect Effects 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 238000012706 support-vector machine Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 238000005461 lubrication Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000013024 troubleshooting Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000012774 insulation material Substances 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000002829 reductive effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Testing Relating To Insulation (AREA)
Abstract
The invention discloses an electrical equipment state evaluation method and a cloud platform based on thermal analysis of insulating materials, and relates to the technical field of electrical equipment insulating state evaluation, wherein the method comprises the following steps: acquiring insulation state characteristic gas concentration information generated by partial discharge of electrical equipment; establishing an insulation parameter database; processing the input characteristics and establishing an insulation pre-estimation model; optimizing the model to obtain the insulation estimated index value in the current day; building a training model according to the input characteristics of the insulation state of the electrical equipment at the current moment; optimizing model parameters by using a genetic algorithm to obtain an insulation state evaluation result of the electrical equipment at the current moment; comprehensively evaluating the health state of the electrical equipment; and (3) obtaining the residual service life of the equipment by using a full life cycle management technology, and performing predictive intelligent maintenance on the electrical equipment. The invention can realize the real-time monitoring and evaluation of the state of the electrical equipment, thereby improving the reliability of the electrical equipment.
Description
Technical Field
The invention relates to the technical field of electrical equipment insulation state evaluation, in particular to an electrical equipment state evaluation method based on insulation material pyrolysis analysis and a cloud platform.
Background
With the expansion of the scale of the power system and the improvement of the management level of the electrical equipment, the electrical equipment can generate partial discharge in long-term high-voltage high-flow operation, and if the partial discharge can not be found and eliminated in time, a more serious insulation breakdown or short-circuit accident can be caused, so that the safety and stable operation of the power grid are greatly damaged; meanwhile, as the maintenance cost of the electrical equipment is continuously increased in the production cost of enterprises, related enterprises gradually develop from a post maintenance stage to a state-based maintenance stage for predicting the health state of the electrical equipment based on the equipment operation data, and the equipment condition is estimated and predicted by analyzing the historical operation overhaul monitoring data, so that basis can be provided for daily maintenance, fine management is realized, the equipment availability is improved, the maintenance cost is further reduced, and the market competitiveness of the enterprises is enhanced.
For example, chinese patent 201810909793.7 discloses a system and a method for health management of electrical equipment, which establishes a mapping relationship by a data fitting method, installs various sensors in the electrical equipment to perform real-time monitoring and periodically patrol and collect data, establishes a data model and a neural network, and can perform health status assessment and fault prediction on the electrical equipment by the mapping relationship by the data fitting method. However, the electrical device health management system and method described above have the following disadvantages when applied specifically: the operation parameters of the electrical equipment are collected on line from the sensors installed on the electrical equipment mainly through the data bus, and in special environments such as power plants and the vicinity of wireless communication base stations, the sensors are difficult to collect data due to large electromagnetic wave interference, and the obtained data and actual data have large errors, so that the number of effective samples is very small, and subsequent health state assessment and fault prediction are difficult to carry out.
For the problems in the related art, no effective solution has been proposed at present.
Disclosure of Invention
Aiming at the problems in the related art, the invention provides the state evaluation method and the cloud platform of the electrical equipment based on the thermal analysis of the insulating material, which have the advantages of small interference by on-site electromagnetic waves, high sensitivity, high test speed and accurate analysis, and further solve the problems that the partial discharge can not be found in time when the electrical equipment operates for a long time in the prior art, and the safe operation of a power grid is endangered.
For this purpose, the invention adopts the following specific technical scheme:
according to an aspect of the present invention, there is provided an electrical device state evaluation method based on thermal analysis of an insulating material, the electrical device state evaluation method based on thermal analysis of an insulating material including the steps of:
s1, acquiring insulation state characteristic gas concentration information generated by partial discharge of electrical equipment, and obtaining input characteristics of an insulation state;
s2, establishing an insulation parameter database according to the input characteristics of the current day insulation state of the electrical equipment;
s3, processing input features in the insulation parameter database by using a fuzzy clustering algorithm, and establishing an insulation pre-estimated model;
s4, optimizing the insulation prediction model by using a random forest algorithm to obtain an insulation prediction index value in the current day;
s5, building an SVM algorithm training model based on the insulation state of the electrical equipment according to the input characteristics of the insulation state of the electrical equipment at the current moment;
s6, optimizing parameters of an SVM algorithm training model by using a genetic algorithm to obtain an electrical equipment insulation state evaluation result at the current moment;
s7, comprehensively evaluating the health state of the electrical equipment according to the insulation estimated index value of the current day and the insulation state evaluation result at the current moment;
s8, the residual service life of the equipment is obtained by using a full life cycle management technology, and the electrical equipment is replaced and maintained.
Further, establishing the insulation parameter database in S2 includes the following steps:
s21, collecting parameter information of daily index gas in a week as a data sample through a gas detector;
s22, selecting the concentration of the gas as a characteristic vector;
s23, distributing the feature vectors into different clusters according to different gas types;
s24, recording the characteristics of each cluster, wherein each cluster comprises the maximum value and the minimum value of the gas concentration in the current week.
Further, in S3, a calculation formula for processing the input features in the insulation parameter database by using the fuzzy clustering algorithm is as follows:
wherein Y is i Representing an initial vector of the i-th day of the current week in the insulation pre-estimated model;
x i represents the i weather body concentration at this week;
x max a maximum value of the gas concentration at the present week;
x min the minimum value of the gas concentration at the present week is shown.
Further, in S4, optimizing the insulation prediction model by using a random forest algorithm includes the following steps:
s41, collecting initial vector data in an insulation pre-estimated model, and training a random forest model;
s42, marking the insulation state degree as an index value as a prediction target;
s43, setting the number of trees according to the number of initial vectors in the insulation pre-estimated model;
s44, inputting the initial vector data into a random forest model, and calculating to obtain an insulation estimated index value.
Further, in S44, the initial vector data is input into a random forest model, and a calculation formula for calculating the insulation pre-estimated index value is as follows:
wherein, pre (Y) represents an insulation forecast index value;
j represents the jth initial vector in the insulation pre-estimated model;
k represents the number of initial vectors in the insulation pre-estimated model;
Y i the initial vector on the i-th day of the week in the insulation pre-estimated model is shown.
Further, establishing an SVM algorithm training model based on the insulation state of the electrical equipment in the S5 comprises the following steps:
s51, collecting parameter information of index gas at different whole points in the same day through a gas detector to serve as a data sample;
s52, processing missing data and abnormal values, and selecting a concentration ratio of the gas as a characteristic vector;
s53, constructing an SVM model, and obtaining a weight vector and a threshold value through SVM model learning;
s54, inputting the feature vector into a trained SVM model, and calculating to obtain a preliminary evaluation result of the insulation state at the current moment.
Further, the calculation formula for calculating the insulation state preliminary evaluation result at the current moment in S54 is as follows:
f(m)＝w·m+b
wherein f (m) represents a preliminary evaluation result of the insulation state of the electrical equipment at the current moment;
w represents a weight vector obtained by SVM model learning;
m represents an input feature vector;
b represents a threshold value learned by the SVM model.
Further, in S6, the calculation formula of the parameters of the training model of the SVM algorithm optimized by the genetic algorithm is:
P(Y’)＝δ·f(m)
wherein P (Y') represents the insulation state evaluation result of the electrical equipment at the current time;
delta represents the accuracy of the genetic algorithm in a cross-validation mode and is generally selected from 0.6 to 0.9;
f (m) represents the preliminary evaluation result of the insulation state of the electrical equipment at the present moment.
Further, in S8, using the full life cycle management technique, obtaining the remaining service life of the device includes the following steps:
s81, optimally configuring the electrical equipment, and recording basic information of the electrical equipment and data of asset conditions thereof in detail through account data management;
s82, recording the running state and the change of the state of the electrical equipment;
s83, analyzing the health state of the electrical equipment, and providing report output aiming at the requirements of different management levels by counting various technical and economic indexes of the electrical equipment;
s84, obtaining the residual service life of the electrical equipment by mining big data related to the health state of the electrical equipment;
s85, analyzing the residual service life of the electrical equipment, and maintaining and managing the electrical equipment with the residual service life less than two years.
Further, in S84, the method adopted for mining the big data related to the health status of the electrical equipment to obtain the remaining service life of the electrical equipment is ABC analysis, and the specific calculation formula is:
C＝A-B
wherein C represents the expected remaining service life of the electrical equipment;
a represents the design service life of the electrical equipment;
b represents the actual average service life of the electrical equipment.
According to another aspect of the present invention, there is provided an electrical device state evaluation cloud platform based on thermal analysis of insulating materials, the cloud platform comprising:
the acquisition module is used for acquiring insulation state characteristic gas concentration information generated by partial discharge of the electrical equipment to obtain input characteristics of an insulation state;
the database establishing module is used for establishing an insulation parameter database according to the input characteristics of the current day insulation state of the electrical equipment;
the insulation pre-estimation model module is used for processing input features in the insulation parameter database by using a fuzzy clustering algorithm and establishing an insulation pre-estimation model;
the model optimization module is used for optimizing the insulation pre-estimated model by utilizing a random forest algorithm to obtain the insulation pre-estimated index value in the current day;
the model training module is used for establishing an SVM algorithm training model based on the insulation state of the electrical equipment according to the input characteristics of the insulation state of the electrical equipment at the current moment;
the insulation state evaluation module is used for optimizing parameters of the SVM algorithm training model by utilizing a genetic algorithm to obtain an insulation state evaluation result of the electrical equipment at the current moment;
the comprehensive evaluation module is used for comprehensively evaluating the health state of the electrical equipment according to the insulation estimated index value of the current day and the insulation state evaluation result of the current moment;
the prediction maintenance module is used for obtaining the residual service life of the equipment by utilizing a full life cycle management technology and performing predictive intelligent maintenance on the electrical equipment;
the insulation prediction model module is connected with the model training module through the model optimization module, the model training module is connected with the comprehensive evaluation module through the insulation state evaluation module, and the comprehensive evaluation module is connected with the prediction maintenance module.
The beneficial effects of the invention are as follows:
(1) Real-time monitoring and evaluation: the insulation state index gas concentration information is acquired by using the gas detector, and real-time processing and state evaluation are carried out through the cloud platform, so that the system can monitor the insulation state of the electrical equipment in real time, the insulation aging condition of the electrical equipment can be accurately and effectively evaluated, and possible hidden trouble can be timely found; meanwhile, compared with the existing detection technical means, the invention has the advantages of high sensitivity, high test speed and small interference of electromagnetic waves on site.
(2) Big data analysis and prediction capabilities: analyzing and predicting the insulation state index gas monitoring data by utilizing machine learning and artificial intelligence algorithms, including a support vector machine, a random forest, fuzzy clustering and genetic algorithms; meanwhile, by mining big data, the cloud platform can realize more accurate analysis and prediction of the insulation state of the equipment, provide more accurate system maintenance decision information, obtain the residual service life of the equipment and evaluate the health state of the electrical equipment.
(3) Remote service and preventative maintenance: through the cloud platform and the monitoring host, the invention can realize remote service and preventive maintenance, not only can remotely monitor the insulation state of equipment, but also can provide timely maintenance and service for the equipment by sensing faults and troubleshooting potential fault hidden dangers in advance, and improve the reliability and usability of the electrical equipment.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of an electrical device state assessment method based on thermal analysis of insulating materials according to an embodiment of the present invention;
fig. 2 is a schematic block diagram of an electrical device state evaluation cloud platform based on thermal analysis of insulating materials according to an embodiment of the present invention.
Detailed Description
For the purpose of further illustrating the various embodiments, the present invention provides the accompanying drawings, which are a part of the disclosure of the present invention, and which are mainly used to illustrate the embodiments and, together with the description, serve to explain the principles of the embodiments, and with reference to these descriptions, one skilled in the art will recognize other possible implementations and advantages of the present invention, wherein elements are not drawn to scale, and like reference numerals are generally used to designate like elements.
According to the embodiment of the invention, an electrical equipment state evaluation method based on thermal analysis of insulating materials and a cloud platform are provided.
The invention will be further described with reference to the accompanying drawings and detailed description, as shown in fig. 1, a method for evaluating the state of an electrical device based on thermal analysis of an insulating material according to an embodiment of the invention, comprising the following steps:
s1, acquiring insulation state characteristic gas concentration information generated by partial discharge of electrical equipment, and obtaining input characteristics of an insulation state;
specifically, the invention comprises a plurality of power transmission and distribution equipment monitoring sub-points and a monitoring host, wherein each power transmission and distribution equipment monitoring sub-point is provided with a gas detector and a distribution data center, the gas detector collects the insulation state characteristic gas concentration information generated by partial discharge, and the distribution data center uploads the data collected by the gas detector to the monitoring host as the input characteristic of the insulation state; the monitoring host and each distributed data center jointly form an electrical equipment state evaluation cloud platform through cloud storage and transmission of data; the cloud platform can track and analyze the data uploaded to the cloud platform through big data, and real-time processing and state evaluation of detection data are achieved through artificial intelligence and a machine learning algorithm, so that the insulation aging state of the electrical equipment is accurately and effectively evaluated.
The specific parameters of the input characteristics of the insulation state are as follows:
s2, establishing an insulation parameter database according to the input characteristics of the current day insulation state of the electrical equipment;
s3, processing input features in the insulation parameter database by using a fuzzy clustering algorithm, and establishing an insulation pre-estimated model;
s4, optimizing the insulation prediction model by using a random forest algorithm to obtain an insulation prediction index value in the current day;
s5, building an SVM algorithm training model based on the insulation state of the electrical equipment according to the input characteristics of the insulation state of the electrical equipment at the current moment;
s6, optimizing parameters of an SVM algorithm training model by using a genetic algorithm to obtain an electrical equipment insulation state evaluation result at the current moment;
s7, comprehensively evaluating the health state of the electrical equipment according to the insulation estimated index value of the current day and the insulation state evaluation result at the current moment;
specifically, comparing and analyzing the predicted insulation state index value with the actual insulation state evaluation result, and if the predicted index value is consistent with or close to the actual evaluation result, considering that the health state of the current equipment is better; if the difference is large, the electric equipment with large difference needs to be pre-warned, and the health state of the equipment is further comprehensively judged and corresponding measures are taken by combining the running state and state change information of the electric equipment in the step S8, the residual service life of the electric equipment and the like.
S8, the residual service life of the equipment is obtained by using a full life cycle management technology, and the electrical equipment is replaced and maintained.
In one embodiment, establishing the insulation parameter database in S2 includes the steps of:
s21, collecting parameter information of daily index gas in a week as a data sample through a gas detector;
s22, selecting the concentration of the gas as a characteristic vector;
s23, distributing the feature vectors into different clusters according to different gas types;
s24, recording the characteristics of each cluster, wherein each cluster comprises the maximum value and the minimum value of the gas concentration in the current week.
In one embodiment, the calculation formula for processing the input features in the insulation parameter database in S3 using the fuzzy clustering algorithm is:
wherein Y is i Representing an initial vector of the i-th day of the current week in the insulation pre-estimated model;
x i represents the i weather body concentration at this week;
x max a maximum value of the gas concentration at the present week;
x min the minimum value of the gas concentration at the present week is shown.
In one embodiment, optimizing the insulation prediction model in S4 using a random forest algorithm includes the steps of:
s41, collecting initial vector data in an insulation pre-estimated model, and training a random forest model;
s42, marking the insulation state degree as an index value as a prediction target;
s43, setting the number of trees according to the number of initial vectors in the insulation pre-estimated model;
s44, inputting the initial vector data into a random forest model, and calculating to obtain an insulation estimated index value.
In one embodiment, in S44, the initial vector data is input into a random forest model, and the calculation formula for calculating the insulation pre-estimated index value is:
wherein, pre (Y) represents an insulation forecast index value;
j represents the jth initial vector in the insulation pre-estimated model;
k represents the number of initial vectors in the insulation pre-estimated model;
Y i the initial vector on the i-th day of the week in the insulation pre-estimated model is shown.
In one embodiment, establishing the SVM algorithm training model based on the insulation state of the electrical device in S5 includes the steps of:
s51, collecting parameter information of index gas at different whole points in the same day through a gas detector to serve as a data sample;
s52, processing missing data and abnormal values, and selecting a concentration ratio of the gas as a characteristic vector;
s53, constructing an SVM model, and obtaining a weight vector and a threshold value through SVM model learning;
s54, inputting the feature vector into a trained SVM model, and calculating to obtain a preliminary evaluation result of the insulation state at the current moment.
In one embodiment, the calculation formula for calculating the preliminary evaluation result of the insulation state at the current moment in S54 is as follows:
f(m)＝w·m+b
wherein f (m) represents a preliminary evaluation result of the insulation state of the electrical equipment at the current moment;
w represents a weight vector obtained by SVM model learning;
m represents an input feature vector;
b represents a threshold value learned by the SVM model.
In one embodiment, the calculation formula for optimizing the parameters of the SVM training model using the genetic algorithm in S6 is:
P(Y’)＝δ·f(m)
wherein P (Y') represents the insulation state evaluation result of the electrical equipment at the current time;
delta represents the accuracy of the genetic algorithm in a cross-validation mode and is generally selected from 0.6 to 0.9;
f (m) represents the preliminary evaluation result of the insulation state of the electrical equipment at the present moment.
In one embodiment, using full life cycle management techniques in S8, obtaining the remaining useful life of the device includes the steps of:
s81, optimally configuring the electrical equipment, and recording basic information of the electrical equipment and data of asset conditions thereof in detail through account data management;
specifically, the basic information of the electrical equipment and the asset status thereof have two parts of data, namely static and dynamic: the static data comprises the number, the name, the model specification, manufacturer information, the unit, the original value and the main performance parameters of the electrical equipment; the dynamic data includes net value of the electrical equipment, depreciation amount, accumulated energy consumption cost and month effective man-hour.
S82, recording the operation state and state change of the electrical equipment;
specifically, the operation state of the electrical equipment comprises recording the daily operation man-hour information, the energy consumption information and the operator information of the electrical equipment; the state change of the electrical equipment includes renting in and renting out, turning in and turning out, failure and scrapping of the electrical equipment.
S83, analyzing the health state of the electrical equipment, and providing report output aiming at the requirements of different management levels by counting various technical and economic indexes of the electrical equipment;
specifically, report output aiming at different management level requirements comprises an electrical equipment distribution table, a subordinate department electrical equipment distribution table, an engineering machinery cost accounting statement, a single machine total item accounting statement, a single machine actual cost chart, a machine operation condition, an economic accounting report and a lease electrical equipment balance accounting table.
S84, obtaining the residual service life of the electrical equipment by mining big data related to the health state of the electrical equipment;
s85, analyzing the residual service life of the electrical equipment, and intelligently maintaining the electrical equipment with the residual service life less than two years.
Specifically, intelligent maintenance of the electrical equipment comprises the steps that a manager classifies the electrical equipment according to the criticality of the electrical equipment and various economic and technical indexes of the electrical equipment, and state detection maintenance, periodic maintenance, post-maintenance and improvement maintenance are respectively adopted for different types of electrical equipment, lubrication calibration and lubrication implementation are carried out, maintenance information is recorded, and maintenance cost is calculated.
By adopting the full life cycle management technology, various statistical data and indexes are given, so that a manager can comprehensively, quickly and accurately know the current mechanical and electrical equipment assets and the service conditions of enterprises, and assist the manager in making enterprise management decisions.
In one embodiment, in S84, the method adopted to mine the big data related to the health status of the electrical device to obtain the remaining service life of the electrical device is ABC analysis, and the specific calculation formula is:
C＝A-B
wherein C represents the expected remaining service life of the electrical equipment;
a represents the design service life of the electrical equipment;
b represents the actual average service life of the electrical equipment.
As shown in fig. 2, according to another embodiment of the present invention, there is provided an electrical device state evaluation cloud platform based on thermal analysis of insulating materials, the cloud platform including:
the acquisition module 1 is used for acquiring insulation state characteristic gas concentration information generated by partial discharge of the electrical equipment to obtain input characteristics of an insulation state;
the database establishing module 2 is used for establishing an insulation parameter database according to the input characteristics of the current day insulation state of the electrical equipment;
the insulation pre-estimation model module 3 is used for processing input features in the insulation parameter database by using a fuzzy clustering algorithm and establishing an insulation pre-estimation model;
the model optimization module 4 is used for optimizing the insulation pre-estimated model by utilizing a random forest algorithm to obtain the insulation pre-estimated index value in the current day;
the model training module 5 is used for establishing an SVM algorithm training model based on the insulation state of the electrical equipment according to the input characteristics of the insulation state of the electrical equipment at the current moment;
the insulation state evaluation module 6 is used for optimizing parameters of the SVM algorithm training model by utilizing a genetic algorithm to obtain an insulation state evaluation result of the electrical equipment at the current moment;
the comprehensive evaluation module 7 is used for comprehensively evaluating the health state of the electrical equipment according to the insulation estimated index value of the current day and the insulation state evaluation result at the current moment;
the predictive maintenance module 8 is used for obtaining the residual service life of the equipment by using a full life cycle management technology and performing predictive intelligent maintenance on the electrical equipment;
the collection module 1 is connected with the insulation pre-estimation model module 3 through the database establishment module 2, the insulation pre-estimation model module 3 is connected with the model training module 5 through the model optimization module 4, the model training module 5 is connected with the comprehensive evaluation module 7 through the insulation state evaluation module 6, and the comprehensive evaluation module 7 is connected with the prediction maintenance module 8.
In order to facilitate understanding of the above technical solutions of the present invention, the following describes in detail the working principle or operation manner of the present invention in the actual process.
According to the invention, a cloud storage technology is utilized to build an electrical equipment state evaluation cloud platform, and the state evaluation is carried out on the equipment insulation characteristics by a big data algorithm means; the invention comprises a monitoring sub-point of power transmission and distribution equipment, a gas detector, a distributed data center and a monitoring host, which are used for completing acquisition, uploading, tracking and analysis of insulation state characteristic gas concentration information generated by partial discharge; the cloud platform is used for introducing the data of the insulation state index gas monitoring into the insulation state evaluation of the electrical equipment by adopting algorithms such as artificial intelligence and machine learning such as a support vector machine, a random forest algorithm, a fuzzy clustering algorithm and a genetic algorithm, so that the real-time processing and state evaluation of the detection data are realized, and the insulation aging state of the electrical equipment is accurately and effectively evaluated.
When the method is actually applied, firstly, the electric equipment state evaluation cloud platform monitors the inside of the electronic equipment in real time through the power transmission and distribution equipment monitoring sub-points, when the temperature rise or partial discharge occurs in the inside of the electronic equipment, the pyrolysis reaction of insulating materials is caused, so that index gas is generated, the gas detectors in the power transmission and distribution equipment monitoring sub-points collect the insulating state characteristic gas concentration information generated by the partial discharge, then the data collected by the gas detectors are uploaded to the monitoring host through the distributed data center as the input characteristic of the insulating state, and the monitoring host and each distributed data center jointly form the electric equipment state evaluation cloud platform through the cloud storage and transmission of the data, so that the gas concentration can be monitored in real time, the insulating state analysis and prediction of each equipment can be performed by utilizing a big data algorithm means, the equipment fault can be sensed in advance, and the fault hidden danger can be remotely serviced and previously checked; meanwhile, by adopting a full life cycle management technology and excavating big data related to the health state of the electrical equipment, more accurate system maintenance decision information such as the residual service life of the equipment is obtained, so that the maintenance is carried out from the condition-based maintenance to the predictive intelligent maintenance.
In summary, by means of the technical scheme, the state of the electrical equipment can be monitored and evaluated in real time, big data is analyzed, remote service and preventive maintenance are realized, so that the reliability of the electrical equipment is improved, faults are prevented in advance, and intelligent maintenance management is realized; the insulation state index gas concentration information is acquired by using the gas detector, and real-time processing and state evaluation are carried out through the cloud platform, so that the system can monitor the insulation state of the electrical equipment in real time, the insulation aging condition of the electrical equipment can be accurately and effectively evaluated, and possible hidden trouble can be timely found; analyzing and predicting the insulation state index gas monitoring data by utilizing a machine learning and artificial intelligence algorithm comprising a support vector machine, a random forest, fuzzy clustering and a genetic algorithm, meanwhile, by mining big data, the cloud platform can realize more accurate equipment insulation state analysis and prediction, provide more accurate system maintenance decision information, obtain the residual service life of equipment and evaluate the health state of the electrical equipment; in addition, through the cloud platform and the monitoring host, the remote service and preventive maintenance can be realized, the insulation state of the equipment can be remotely monitored, and timely maintenance and maintenance service can be provided for the electrical equipment by sensing faults and troubleshooting potential fault hidden dangers in advance, so that the reliability and usability of the electrical equipment are improved.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (10)
1. The electrical equipment state evaluation method based on the thermal analysis of the insulating material is characterized by comprising the following steps of:
s1, acquiring insulation state characteristic gas concentration information generated by partial discharge of electrical equipment, and obtaining input characteristics of an insulation state;
s2, establishing an insulation parameter database according to the input characteristics of the current day insulation state of the electrical equipment;
s3, processing input features in the insulation parameter database by using a fuzzy clustering algorithm, and establishing an insulation pre-estimated model;
s4, optimizing the insulation prediction model by using a random forest algorithm to obtain an insulation prediction index value in the current day;
s5, building an SVM algorithm training model based on the insulation state of the electrical equipment according to the input characteristics of the insulation state of the electrical equipment at the current moment;
s6, optimizing parameters of an SVM algorithm training model by using a genetic algorithm to obtain an electrical equipment insulation state evaluation result at the current moment;
s7, comprehensively evaluating the health state of the electrical equipment according to the insulation estimated index value of the current day and the insulation state evaluation result at the current moment;
s8, the residual service life of the equipment is obtained by using a full life cycle management technology, and predictive intelligent maintenance is carried out on the electrical equipment.
2. The method for evaluating the state of an electrical device based on thermal analysis of an insulating material according to claim 1, wherein the step of creating the insulating parameter database in S2 comprises the steps of:
s21, collecting parameter information of daily index gas in a week as a data sample through a gas detector;
s22, selecting the concentration of the gas as a characteristic vector;
s23, distributing the feature vectors into different clusters according to different gas types;
s24, recording the characteristics of each cluster, wherein each cluster comprises the maximum value and the minimum value of the gas concentration in the current week.
3. The electrical equipment state evaluation method based on thermal analysis of insulating materials according to claim 1, wherein the calculation formula for processing the input features in the insulating parameter database by using the fuzzy clustering algorithm in S3 is as follows:
wherein Y is i Representing an initial vector of the i-th day of the current week in the insulation pre-estimated model;
x i represents the i weather body concentration at this week;
x max a maximum value of the gas concentration at the present week;
x min the minimum value of the gas concentration at the present week is shown.
4. The method for evaluating the state of electrical equipment based on thermal analysis of insulating materials according to claim 1, wherein the optimizing the insulation pre-estimation model by using a random forest algorithm in S4 comprises the following steps:
s41, collecting initial vector data in an insulation pre-estimated model, and training a random forest model;
s42, marking the insulation state degree as an index value as a prediction target;
s43, setting the number of trees according to the number of initial vectors in the insulation pre-estimated model;
s44, inputting the initial vector data into a random forest model, and calculating to obtain an insulation estimated index value.
5. The method for evaluating the state of electrical equipment based on thermal analysis of insulating materials according to claim 4, wherein the step S44 is to input the initial vector data into a random forest model, and the calculation formula for calculating the insulation estimation index value is as follows:
wherein, pre (Y) represents an insulation forecast index value;
j represents the jth initial vector in the insulation pre-estimated model;
k represents the number of initial vectors in the insulation pre-estimated model;
Y i the initial vector on the i-th day of the week in the insulation pre-estimated model is shown.
6. The method for evaluating the state of electrical equipment based on thermal analysis of insulating materials according to claim 1, wherein the step of establishing the SVM algorithm training model based on the insulating state of the electrical equipment in S5 comprises the steps of:
s51, collecting parameter information of index gas at different whole points in the same day through a gas detector to serve as a data sample;
s52, processing missing data and abnormal values, and selecting a concentration ratio of the gas as a characteristic vector;
s53, constructing an SVM model, and obtaining a weight vector and a threshold value through SVM model learning;
s54, inputting the feature vector into a trained SVM model, and calculating to obtain a preliminary evaluation result of the insulation state at the current moment.
7. The method for evaluating the state of electrical equipment based on thermal analysis of insulating materials according to claim 6, wherein the calculation formula for calculating the preliminary evaluation result of the insulating state at the current moment in S54 is as follows:
f(m)＝w·m+b
wherein f (m) represents a preliminary evaluation result of the insulation state of the electrical equipment at the current moment;
w represents a weight vector obtained by SVM model learning;
m represents an input feature vector;
b represents a threshold value learned by the SVM model.
8. The electrical equipment state evaluation method based on thermal analysis of insulating materials according to claim 1, wherein the calculation formula of the parameters of the training model of the optimization SVM algorithm using the genetic algorithm in S6 is:
P(Y’)＝δ·f(m)
wherein P (Y') represents the insulation state evaluation result of the electrical equipment at the current time;
delta represents the accuracy of the genetic algorithm in a cross-validation mode;
f (m) represents the preliminary evaluation result of the insulation state of the electrical equipment at the present moment.
9. The method for evaluating the state of an electrical device based on thermal analysis of an insulating material according to claim 1, wherein the step of obtaining the remaining service life of the device by using a full life cycle management technique in S8 comprises the steps of:
s81, optimally configuring the electrical equipment, and recording basic information of the electrical equipment and data of asset conditions thereof in detail through account data management;
s82, recording the running state and the change of the state of the electrical equipment;
s83, analyzing the health state of the electrical equipment, and providing report output aiming at the requirements of different management levels by counting various technical and economic indexes of the electrical equipment;
s84, obtaining the residual service life of the electrical equipment by mining big data related to the health state of the electrical equipment;
s85, analyzing the residual service life of the electrical equipment, and maintaining and managing the electrical equipment with the residual service life less than two years.
10. An electrical equipment state evaluation cloud platform based on thermal analysis of insulating materials, characterized in that it is used for implementing the electrical equipment state evaluation method based on thermal analysis of insulating materials according to any one of claims 1 to 9, and comprises:
the acquisition module is used for acquiring insulation state characteristic gas concentration information generated by partial discharge of the electrical equipment to obtain input characteristics of an insulation state;
the database establishing module is used for establishing an insulation parameter database according to the input characteristics of the current day insulation state of the electrical equipment;
the insulation pre-estimation model module is used for processing input features in the insulation parameter database by using a fuzzy clustering algorithm and establishing an insulation pre-estimation model;
the model optimization module is used for optimizing the insulation pre-estimated model by utilizing a random forest algorithm to obtain the insulation pre-estimated index value in the current day;
the model training module is used for establishing an SVM algorithm training model based on the insulation state of the electrical equipment according to the input characteristics of the insulation state of the electrical equipment at the current moment;
the insulation state evaluation module is used for optimizing parameters of the SVM algorithm training model by utilizing a genetic algorithm to obtain an insulation state evaluation result of the electrical equipment at the current moment;
the comprehensive evaluation module is used for comprehensively evaluating the health state of the electrical equipment according to the insulation estimated index value of the current day and the insulation state evaluation result of the current moment;
the prediction maintenance module is used for obtaining the residual service life of the equipment by utilizing a full life cycle management technology and performing predictive intelligent maintenance on the electrical equipment;
the insulation prediction model module is connected with the model training module through the model optimization module, the model training module is connected with the comprehensive evaluation module through the insulation state evaluation module, and the comprehensive evaluation module is connected with the prediction maintenance module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311526517.XA CN117494009A (en) | 2023-11-16 | 2023-11-16 | Electrical equipment state evaluation method based on insulating material pyrolysis analysis and cloud platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311526517.XA CN117494009A (en) | 2023-11-16 | 2023-11-16 | Electrical equipment state evaluation method based on insulating material pyrolysis analysis and cloud platform |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117494009A true CN117494009A (en) | 2024-02-02 |
Family
ID=89682622
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311526517.XA Pending CN117494009A (en) | 2023-11-16 | 2023-11-16 | Electrical equipment state evaluation method based on insulating material pyrolysis analysis and cloud platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117494009A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117789954A (en) * | 2024-02-26 | 2024-03-29 | 中国人民解放军海军青岛特勤疗养中心 | Rehabilitation and nursing equipment data management method and platform |
-
2023
- 2023-11-16 CN CN202311526517.XA patent/CN117494009A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117789954A (en) * | 2024-02-26 | 2024-03-29 | 中国人民解放军海军青岛特勤疗养中心 | Rehabilitation and nursing equipment data management method and platform |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109146093B (en) | Power equipment field investigation method based on learning | |
| CN117277958B (en) | Intelligent operation and maintenance management method and system for photovoltaic power station based on big data | |
| CN117630758B (en) | Method and system for monitoring health state of power station transformer | |
| CN113036913B (en) | Method and device for monitoring state of comprehensive energy equipment | |
| CN115329812A (en) | Road infrastructure abnormity monitoring method based on artificial intelligence | |
| CN117408162B (en) | Power grid fault control method based on digital twin | |
| CN117172620B (en) | Building photovoltaic potential evaluation method and system based on parameterized analysis | |
| CN117878925B (en) | Power transmission data control method and system of smart power grid | |
| CN117494009A (en) | Electrical equipment state evaluation method based on insulating material pyrolysis analysis and cloud platform | |
| CN118432000B (en) | High-voltage isolation protection method and system | |
| CN118094262B (en) | Load abnormal value detection method based on spatial clustering | |
| CN117892882A (en) | Huang Heba bank monitoring alarm risk reporting system and method based on network communication platform | |
| CN117648543A (en) | Self-evolving substation equipment learning method | |
| CN118094379A (en) | Oil well fault diagnosis prediction method and system for multi-factor fusion analysis | |
| CN117639228A (en) | Power distribution network running state prediction method and system based on digital twin | |
| CN105958474B (en) | Dynamic capacity increasing method and system for power transmission line for power grid regulation and control system | |
| CN118152784A (en) | Modularized substation equipment data feature extraction method | |
| CN118115296A (en) | Power equipment data acquisition analysis detection platform based on multisource fusion claim settlement | |
| CN117977536A (en) | Smart power grid load identification method | |
| CN115936663A (en) | Maintenance method and device for power system | |
| CN117933713B (en) | Safety situation sensing and early warning system for power transmission line | |
| CN117688464B (en) | Hidden danger analysis method and system based on multi-source sensor data | |
| CN117113267B (en) | Prediction model training method based on big data and photovoltaic power generation performance detection method | |
| CN117933713A (en) | Safety situation sensing and early warning system for power transmission line | |
| CN118133668A (en) | Power plant equipment life assessment 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 |