Disclosure of Invention
The present invention is directed to a method, a system, a terminal device and a readable storage medium for managing the health of a substation device, so as to solve one or more of the above technical problems. The method and the system can realize real-time evaluation of the power transformation equipment, diagnose through combination of a machine and an expert algorithm, give out a corresponding auxiliary decision according to an evaluation diagnosis result department, and can perform real-time and accurate health management on the power transformation equipment.
In order to achieve the purpose, the invention adopts the following technical scheme:
the invention discloses a health management method of substation equipment, which comprises the following steps:
acquiring real-time data values of various parameters in the operation process of the power transformation equipment;
evaluating the real-time data values of the parameters in real time based on a preset evaluation guide rule to obtain an evaluation result; diagnosing based on the evaluation result to obtain an analysis result;
and obtaining an auxiliary decision suggestion by combining equipment life cycle data based on the analysis result, and realizing the health management of the power transformation equipment.
The invention is further improved in that the step of evaluating the real-time data values of the parameters in real time based on a preset evaluation guide rule to obtain an evaluation result specifically comprises:
filtering the real-time data values of the parameters to obtain filtered data; wherein, the filtering process is to filter out real-time data values with null data and zero data;
comparing the real-time data values of the filtered parameters with the preset threshold ranges of the parameters, and judging whether the real-time data values of the parameters are in the threshold ranges of the parameters or not; when the current state is within the threshold range, the equipment state is considered to be normal; and when the device state exceeds the threshold range, the device state is considered to be abnormal, and the device state is obtained according to a preset evaluation guide rule.
The further improvement of the present invention is that, when the threshold value range is exceeded, the device status is considered to be abnormal, and the step of obtaining the device status according to the preset evaluation guidance specifically includes:
when the real-time data value of a certain parameter exceeds the threshold range, the state quantity of a deduction item in a corresponding system 2016 edition evaluation guide is searched for in a fuzzy mode through the name of the parameter to be matched, and the deduction item comprises a deduction component, a judgment basis and a single deduction value; fuzzy searching for the state quantity of a deduction item in a corresponding PMS 2008 edition evaluation guide rule through the name of the monitoring parameter for matching, wherein the deduction item comprises a deduction component, a judgment basis and a single deduction value;
the evaluation guide rules of the 2016 edition of the system and the guide rules of the 2008 edition of the PMS are matched twice and then are summarized; if the same part is repeatedly deducted, taking the 2016 type evaluation guide of the system as a standard, and removing a deduction item of the part corresponding to the PMS 2008 type; if not, the deduction value of the component is normally summarized;
and according to the single deduction and the total deduction range of the summarized components, referring to a preset general guideline evaluation standard to obtain the state of each sub-component, and taking the most serious component state in the evaluation as the final state of the evaluation.
In a further improvement of the present invention, the step of performing a diagnosis based on the evaluation result and obtaining an analysis result specifically comprises:
and when the equipment state is abnormal, fusing an analysis result according to an expert algorithm and a machine algorithm.
The further improvement of the present invention is that, when the equipment status is abnormal, the step of obtaining the analysis result according to the fusion of the expert algorithm and the machine algorithm specifically comprises:
when the equipment state is abnormal, different groups of data are selected after the operation data are monitored;
performing fusion analysis of an expert algorithm and a machine algorithm on the selected groups of different data; wherein the step of fusion analysis comprises:
according to the statistics of the system case base, the diagnostic algorithms and the diagnostic results of different fault cases are counted, N is the number of fault types, M is the number of algorithms, a weight matrix of N x M is formed, and the weight factors of the algorithms are determined;
calculating the algorithm state priority coefficient:
in the formula, Flag
iRepresenting algorithm screening tags, ω
ijA weighting factor representing the algorithm for different diagnostic states; and obtaining a final analysis result based on the obtained algorithm state priority coefficient.
The further improvement of the present invention is that the step of obtaining an aid decision suggestion based on the analysis result and in combination with the equipment life cycle data to realize the health management of the power transformation equipment specifically includes:
when the analysis result is in a normal state, no auxiliary decision suggestion is made;
and when the analysis result is in an abnormal state, searching the case base and outputting an auxiliary decision suggestion in the corresponding case base.
The further improvement of the present invention is that the step of searching the case base and outputting the assistant decision suggestion in the corresponding case base when the analysis result is in the abnormal state specifically comprises:
and when the analysis result is in an abnormal state, case matching is carried out in the system case library, and a processing method and a rectification measure of the historical case with the data similarity higher than 83% are pushed, so that the health management of the power transformation equipment is realized.
The invention relates to a health management system of power transformation equipment, which comprises:
the data acquisition module is used for acquiring and acquiring real-time data values of various parameters in the operation process of the power transformation equipment;
the data analysis module is used for evaluating the real-time data values of the parameters in real time based on a preset evaluation guide rule to obtain an evaluation result; diagnosing based on the evaluation result to obtain an analysis result;
and the auxiliary decision module is used for obtaining an auxiliary decision suggestion according to the analysis result and by combining the equipment life cycle data, and realizing the health management of the power transformation equipment.
An electronic device of the present invention includes: a processor; a memory for storing computer program instructions; when the computer program instructions are loaded and executed by the processor, the processor executes any one of the above-described substation equipment health management methods of the present invention.
A computer-readable storage medium of the present invention stores computer program instructions, and when the computer program instructions are loaded and executed by a processor, the processor executes the method for managing the health of a power transformation device according to any one of the above embodiments of the present invention.
Compared with the prior art, the invention has the following beneficial effects:
the invention can realize real-time automatic evaluation of the power transformation equipment, can timely find equipment with degradation trend by means of real-time evaluation and diagnosis, can timely provide troubleshooting of fault reasons and suggestions for auxiliary decision-making through diagnosis results, and can carry out real-time and accurate health management on the power transformation equipment.
According to the invention, real-time data are monitored on line by accessing the power transformation equipment, and automatic evaluation is carried out according to a preset evaluation guide rule, so that the real-time performance and the accuracy of the evaluation are ensured. The algorithm has good performance on certain fault types and is complementary to the fault types, and the invention provides a method for carrying out fusion diagnosis on a machine algorithm and an expert algorithm and deducing a maintenance suggestion with higher accuracy.
Based on the embodiment of the invention, the online monitoring data is accessed for real-time automatic evaluation, compared with the PMS evaluation result, the reliability of equipment evaluation is improved by 20%, the accuracy of the diagnosis algorithm is up to 93.6% through the fusion of expert experience and the machine algorithm, the accuracy of the diagnosis is obviously improved, and the auxiliary decision suggestion is more accurate.
Detailed Description
In order to make the purpose, technical effect and technical solution of the embodiments of the present invention clearer, the following clearly and completely describes the technical solution of the embodiments of the present invention with reference to the drawings in the embodiments of the present invention; it is to be understood that the described embodiments are only some of the embodiments of the present invention. Other embodiments, which can be derived by one of ordinary skill in the art from the disclosed embodiments without inventive faculty, are intended to be within the scope of the invention.
Referring to fig. 1, a method for managing health of a power transformation device according to an embodiment of the present invention is a method for managing health of a power transformation device embedded in an intelligent analysis and control system based on power grid operation and inspection, and specifically includes the following steps:
step 1, data acquisition: collecting real-time parameter data values in the operation process of equipment; illustratively, in the operation process of the equipment, the online monitoring data of the equipment is collected in real time, and the real-time data values of various parameters are recorded;
step 2, data analysis: real-time evaluation and diagnosis are carried out on the real-time data values of all parameters in the running state of the equipment;
and step 3, auxiliary decision making: and according to the analysis result, different auxiliary decision suggestions are given according to different analysis results, so that the health management of the power transformation equipment is realized.
In the method provided by the embodiment of the invention, the generation of the operation data of the power transformation equipment can automatically initiate the evaluation of the equipment state in real time, and the equipment abnormal type and handling measures are given by combining the whole life data of the equipment.
In the embodiment of the present invention, the data analysis includes the following steps:
comparing the acquired real-time data, and filtering the data if the data is null and zero;
comparing the filtered data with each parameter threshold;
judging whether each item of real-time data is in a corresponding parameter threshold range;
when the data value does not exceed the preset parameter threshold value, the equipment state is normal;
and when the data value exceeds a preset parameter threshold value, obtaining the equipment state (attention, abnormity and severity) according to the evaluation guide rule.
In the embodiment of the invention, when the equipment state is abnormal, diagnosis is carried out, and analysis results (normal, high-temperature overheat, low-energy discharge, partial discharge, high-energy discharge, low-energy discharge and overheat, medium-temperature overheat, low-temperature overheat, high-energy discharge and overheat) are obtained according to fusion of an expert algorithm and a machine algorithm.
In the embodiment of the present invention, the assistant decision includes the following steps:
when the final analysis processing result is normal, no auxiliary decision suggestion is provided;
and when the final analysis processing result is in an abnormal state, searching the case base and outputting an auxiliary decision suggestion in the corresponding case base.
In the embodiment of the invention, the data of the power transformation equipment is collected to the intelligent analysis and control of power grid operation inspection, the system monitors the threshold value of the collected data by using a real-time monitoring mechanism, the equipment state evaluation is carried out by using a state evaluation guide rule, and the reason and the handling measure of the abnormality of the defect diagnosis analysis equipment are provided; the case base is used as a training set for the disposal measures, the case matched with the real-time data is trained through a cosine similarity algorithm, the state of the power transformation equipment can be accurately and timely monitored, and the possibility of equipment accidents and degradation is prevented.
Referring to fig. 2 and 3, the data analysis processing of the monitored device includes the following specific steps:
when the operation data is monitored, performing null judgment and zero judgment on each monitored data, and if the data is null or zero, performing filtering processing on the data which is invalid;
comparing the filtered monitoring data with the threshold values of all parameters;
when the monitored real-time data values are all within the threshold range, outputting a prompt that the equipment is normal;
when data in the monitored real-time data exceed a threshold value, the state quantity of a deduction item in a corresponding system 2016 edition evaluation guide rule is searched for in a fuzzy mode through the name of a monitoring parameter for matching, the deduction item comprises a deduction component, and a judgment basis is a single deduction value. And by analogy, performing matching processing on each piece of online data to obtain the single deduction value of the part corresponding to each piece of data. And then, the state quantity of a deduction item in a PMS 2008 edition evaluation guide rule corresponding to the monitoring parameter is searched in a fuzzy mode through the name of the monitoring parameter for matching, the deduction item comprises a deduction component, and the deduction item is judged according to a single deduction value.
And by analogy, performing matching processing on each piece of monitoring data to obtain the single deduction value of the part corresponding to each piece of data.
And the system is summarized after the 2016 edition evaluation guide rule and the PMS 2008 edition guide rule are matched twice. If the same part is repeatedly deducted by the two matching, the deduction item of the part corresponding to the PMS 2008 version is removed based on the 2016 type evaluation guide of the system. If no duplicate credits occur, the credit value of the component is summarized normally.
According to the single deduction and the total deduction range of the summarized components, the states (normal, attention, abnormal and serious) of the sub-components are obtained by referring to a general guide evaluation standard (taking a transformer as an example, and the states corresponding to different deduction ranges are shown in table 1). The most severe component condition in this evaluation was taken as the final condition (normal, attentive, abnormal, severe) of this evaluation.
TABLE 1 states corresponding to different deduction ranges
In the embodiment of the invention, when the equipment state is abnormal, different groups of data are manually selected after the operation data are monitored; performing fusion analysis of an expert algorithm and a machine algorithm on the selected groups of different data;
according to the statistics of the system case base, the diagnosis algorithms and diagnosis results of different fault cases are counted, N is the number of fault types, M is the number of algorithms, a weight matrix of N x M is formed, and the weight factors of each algorithm are determined as shown in table 2:
TABLE 2 weight factors for the respective algorithms
Serial number
|
Algorithm
|
Low energy discharge
|
Low energy discharge and superheat
|
High energy discharge
|
High energy discharge and discharge
|
High temperature superheating
|
Medium and low temperature superheating
|
1
|
Random forest
|
0.2111
|
0.1795
|
0.2500
|
0.2500
|
0.2704
|
0.2642
|
2
|
GBDT
|
0.2000
|
0.1795
|
0.2500
|
0.5000
|
0.2575
|
0.2642
|
3
|
Decision tree
|
0.2222
|
0.1795
|
0.2500
|
0.2500
|
0
|
0.2830
|
4
|
SVM
|
0.1778
|
0
|
0
|
0
|
0
|
0
|
5
|
Three ratio of
|
0
|
0.2051
|
0.2500
|
0
|
0.2189
|
0.1887
|
6
|
Big satellite triangle
|
0.1889
|
0.2308
|
0
|
0
|
0
|
0
|
7
|
Pentagon David
|
0
|
0.2051
|
0
|
0
|
0.2531
|
0 |
Calculating the algorithm state priority coefficient:
in the formula, Flag
iRepresenting algorithm screening tags, ω
ijRepresenting the weighting factors of the algorithm for different diagnostic states.
The monitored operation data is taken as oil chromatogram data for illustration, and 7 diagnosis results corresponding to 7 algorithms are respectively as follows: high-temperature overheating, medium-low-temperature overheating and high-temperature overheating. If 4 algorithms diagnose high temperature overheating and 2 algorithms diagnose medium and low temperature overheating, the following conclusion can be drawn for the oil chromatogram data:
the state priority coefficient of "high temperature overheating" is 0.2704 × 1+0.2575 × 1+0 × 1+ 0.5279
The state priority coefficient of "medium-low temperature overheating" is 0.2830 × 1+0.1887 × 1+0 × 1 ═ 0.4717
The condition priority coefficient of the high temperature overheating is found to be larger than the condition priority coefficient of the medium and low temperature overheating, so that the final diagnosis conclusion of the chromatographic data of the oil is the high temperature overheating.
And giving different maintenance suggestions according to the diagnosis result of the monitoring data, and if the diagnosis result is normal, no auxiliary decision is made.
And if the abnormal condition is diagnosed (high-temperature overheating, low-energy discharging, partial discharging, high-energy discharging, low-energy discharging and overheating, medium-temperature overheating, low-temperature overheating and high-energy discharging and overheating), case matching is carried out in a system case library, and a processing method and a rectification measure of the historical case with the data similarity higher than 83% are pushed, so that the health management of the power transformation equipment is realized.
In summary, the traditional intelligent evaluation only accesses the offline and routine data of the equipment, and the equipment evaluation is performed according to the PMS evaluation guide rule, but does not access the online data for real-time automatic evaluation, and the real-time performance and accuracy of the evaluation are lacked. The traditional fault diagnosis only accesses an expert algorithm, the accuracy of the expert algorithm in various fault diagnoses is not very high, the supplement of practical application cases and the application of machine algorithms are not carried out, and the overhaul suggestions lack powerful data support. The embodiment of the invention provides a power transformation equipment health management method embedded based on a power grid operation inspection intelligent analysis management and control system, and relates to the field of power transformation equipment. The invention accesses the on-line monitoring real-time data of the transformer equipment, and automatically evaluates according to the new evaluation guide rule, thereby ensuring the real-time performance and the accuracy of the evaluation. The algorithms are good in performance on certain fault types and are complementary to each other, so that a machine algorithm and an expert algorithm are proposed to be fused and diagnosed, and a maintenance suggestion with high accuracy is provided. Compared with the prior art, the technical scheme has the advantages that: the online monitoring data is accessed for real-time automatic evaluation, compared with PMS evaluation, the reliability of equipment evaluation is improved by 20%, the accuracy of a diagnosis algorithm is up to 93.6% through the fusion of an expert algorithm (David triangle, David pentagon and Tri ratio) and a machine algorithm (random forest, gradient lifting tree, K neighbor and decision tree), the accuracy of diagnosis is obviously improved, and an auxiliary decision suggestion is more accurate.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art can make modifications and equivalents to the embodiments of the present invention without departing from the spirit and scope of the present invention, which is set forth in the claims of the present application.