CN114742345A - Power distribution equipment health evaluation method, system and device - Google Patents
Power distribution equipment health evaluation method, system and device Download PDFInfo
- Publication number
- CN114742345A CN114742345A CN202210191206.1A CN202210191206A CN114742345A CN 114742345 A CN114742345 A CN 114742345A CN 202210191206 A CN202210191206 A CN 202210191206A CN 114742345 A CN114742345 A CN 114742345A
- Authority
- CN
- China
- Prior art keywords
- parameter
- imf component
- data
- weight
- residual
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000036541 health Effects 0.000 title claims abstract description 78
- 238000011156 evaluation Methods 0.000 title claims abstract description 34
- 238000012549 training Methods 0.000 claims abstract description 51
- 238000013210 evaluation model Methods 0.000 claims abstract description 34
- 238000000034 method Methods 0.000 claims abstract description 30
- 238000007781 pre-processing Methods 0.000 claims abstract description 12
- 238000000354 decomposition reaction Methods 0.000 claims description 15
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 239000011159 matrix material Substances 0.000 claims description 8
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 6
- 230000001186 cumulative effect Effects 0.000 claims description 5
- 238000005065 mining Methods 0.000 claims description 4
- 230000010354 integration Effects 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 230000015572 biosynthetic process Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000003786 synthesis reaction Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
Images
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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method, a system and a device for evaluating the health of distribution equipment, and belongs to the technical field of electric power. The method comprises the following steps: acquiring historical operating parameters of the power distribution equipment, and preprocessing the data to obtain model training data; training an equipment health evaluation model by using model training data; acquiring a real-time operation parameter X of the power distribution equipment; performing EMD on the real-time operation parameter X to obtain an IMF component of the real-time operation parameter X; loading the trained equipment health evaluation model, and calculating residual values of all IMF components of the real-time operation parameter X by using the trained equipment health evaluation model; adjusting the parameter weight according to the residual value of the IMF component and a variable weight formula to obtain the variable weight of the operation parameter X; obtaining deviation scores of all IMF components by using the trained equipment health evaluation model; and calculating the equipment health evaluation score according to the deviation score and the parameter weight of the IMF component. The invention effectively improves the accuracy of comprehensive health evaluation of the current equipment.
Description
Technical Field
The invention relates to the technical field of electric power, in particular to a method, a system and a device for evaluating the health of distribution equipment.
Background
At present, the state overhaul of the power distribution equipment is in a starting research stage, and a large amount of effective equipment state quantity data information and evaluation indexes and methods for the health level of the equipment are lacked, so that the state overhaul of the power distribution equipment does not form an effective result, and practical application is lacked.
Aiming at the equipment state health evaluation method, a plurality of researches mainly carry out equipment health evaluation from clustering analysis, model fitting analysis, regression function analysis and the like, but the application of the methods has certain limitation. Firstly, the clustering method has strict requirements on the concave-convex property of data, and the clustering effect strictly depends on the form of the data; secondly, due to the non-linear and random complexity of the characteristic data, the difficulty of evaluating the health state of the equipment is increased, so that the fault tolerance of the model fitting analysis and the regression function analysis on the data is low.
Disclosure of Invention
Aiming at the problems in the prior art, the invention aims to provide a method, a system and a device for evaluating the health of power distribution equipment, which effectively improve the accuracy of comprehensive health evaluation of the current equipment by analyzing the numerical value operation situation of the current parameter of the power distribution equipment and horizontally positioning the current parameter with other similar parameters.
In order to achieve the purpose, the invention is realized by the following technical scheme:
a power distribution equipment health evaluation method comprises the following steps:
s1: acquiring historical operating parameters of the power distribution equipment, and preprocessing the data to obtain model training data;
s2: training an equipment health evaluation model by using model training data;
s3: acquiring a real-time operation parameter X of the power distribution equipment;
s4: performing EMD on the real-time operation parameter X to obtain an IMF component of the real-time operation parameter X;
s5: loading the trained equipment health evaluation model, and calculating residual values of all IMF components of the real-time operation parameter X by using the trained equipment health evaluation model;
s6: adjusting the parameter weight according to the residual value of the IMF component and a variable weight formula to obtain the variable weight of the operation parameter X;
s7: obtaining deviation scores of all IMF components by using the trained equipment health evaluation model;
s8: and multiplying the deviation score of each IMF component by the corresponding parameter weight to obtain an accumulated value, thereby obtaining the equipment health evaluation score.
Further, the step S1 includes:
acquiring historical operating parameters of the power distribution equipment, removing shutdown data in the historical operating parameters, and taking the processed historical operating parameters as historical data;
and removing abnormal data from the historical data according to the fault rule to serve as model training data.
Further, the step S2 includes:
performing EMD on the model training data to obtain corresponding IMF components, and performing EMD on the historical data to obtain corresponding IMF components;
calculating mutual information of each IMF component, and using the normalized mutual information as an initialization weight of each IMF component; calculating a training data residual error and a historical data residual error by adopting a preset RVM (relevance vector machine) model based on the IMF component of the training data and the IMF component of the historical data;
and (3) mining parameter residual scores which are respectively corresponding to parameter residual thresholds of 30,50 and 60 through confidence degrees of probability density distribution by using the historical data residual absolute values and the training data residual absolute values, and constructing a nonlinear regression relation between the parameter residual absolute values and the parameter scores through cumulative probability density distribution to obtain parameter deviation degree scores.
Further, the calculating mutual information of each IMF component, which is normalized to serve as an initialization weight of each IMF component, includes:
calculating the information entropy and the conditional entropy of each IMF component through a mutual information algorithm, wherein the difference value of the information entropy and the conditional entropy is a mutual information characteristic, and the normalized mutual information characteristic is used as a parameter constant weight;
wherein, the mutual information I (I, j) is a difference value between the information entropy H (I) of the parameter I and the conditional entropy H (I | j) of the parameter I, and the specific formula is as follows:
I(i,j)＝H(i)-H(i|j)
assuming the IMF component data set as T, an nxn mutual information matrix H can be calculated using the mutual information algorithm, as follows:
calculating a row mean value of the H matrix to obtain a one-dimensional vector R:
the normalized value of the one-dimensional vector R is used as the initialization weight of each parameter:
further, the step S6 includes:
and carrying out normalization processing on the residual error value of each IMF component to obtain a normalized residual error value delta x, and dynamically adjusting the weight of the current IMF component according to a variable weight formula, wherein the specific formula is as follows:
wherein, Δ xiNormalizing the residual value, W, of the ith IMF componentOriginal iIs the original weight of the ith IMF component, WBecome iIs the variable weight of the ith IMF component.
Further, the step S8 includes:
obtaining the ith IMF component according to the relation between the residual absolute value and the parameter fractionRating value pscore of IMFiiThe method comprises the following steps:
pscorei＝wvariable i*scorei
The direct parameter synthesis score totalScore of the transformer device is calculated according to the following formula:
wherein, scoreiIs the parameter score of the ith IMF component.
Correspondingly, the invention also discloses a power distribution equipment health evaluation system, which comprises:
the data preprocessing unit is used for acquiring historical operating parameters of the power distribution equipment, and the historical operating parameters are used as model training data after data preprocessing;
the model training unit is used for carrying out equipment health evaluation model training by utilizing the model training data;
the parameter acquisition unit is used for acquiring a real-time operation parameter X of the power distribution equipment;
the EMD decomposition unit is used for performing EMD decomposition on the real-time operation parameter X to obtain an IMF component of the real-time operation parameter X;
the calculating unit is used for loading the trained equipment health evaluation model and calculating residual values of IMF components of the real-time operation parameters X by using the trained equipment health evaluation model;
the parameter weight adjusting unit is used for adjusting the parameter weight according to the residual value of the IMF component and a variable weight formula to obtain the variable weight of the operation parameter X;
the deviation score calculating unit is used for obtaining deviation scores of all IMF components by using the trained equipment health evaluation model;
and the evaluation score calculating unit is used for multiplying the deviation score of each IMF component by the corresponding parameter weight to be taken as an accumulated value so as to obtain the equipment health evaluation score.
Correspondingly, the invention also discloses a distribution equipment health evaluation device, which comprises:
a memory for storing a computer program;
a processor for implementing the steps of the power distribution equipment health assessment method according to any of the above when executing the computer program.
Compared with the prior art, the invention has the beneficial effects that: the invention provides a method, a system and a device for evaluating the health of power distribution equipment. The invention can thoroughly analyze the numerical value operation situation of the current parameter and horizontally position the current parameter with other similar parameters, has good practical effect on the comprehensive health evaluation of the current equipment, and can effectively improve the accuracy of the state maintenance of the equipment.
Therefore, compared with the prior art, the invention has prominent substantive features and remarkable progress, and the beneficial effects of the implementation are also obvious.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a process flow diagram of an embodiment of the present invention.
FIG. 2 is a flow chart of the training of the equipment health assessment model according to an embodiment of the present invention.
FIG. 3 is a flow chart of the operation of the equipment health assessment model in accordance with an embodiment of the present invention.
FIG. 4 is a diagram illustrating IMF components of a transformer oil temperature in accordance with an embodiment of the present invention.
FIG. 5 is a diagram illustrating the estimation result of IMF1 components of the normal-state transformer oil temperature according to the embodiment of the present invention.
FIG. 6 is a schematic diagram of the effect of a fault condition IMF1 alarm in accordance with an embodiment of the present invention.
Fig. 7 is a schematic diagram of a distribution transformer equipment health assessment score curve in accordance with an embodiment of the present invention.
Fig. 8 is a system block diagram of an embodiment of the present invention.
In the figure, 1 is a data preprocessing unit; 2 is a model training unit; 3 is a parameter obtaining unit; 4 is an EMD decomposition unit; 5 is a calculating unit; 6 is a parameter weight adjusting unit; 7 is a deviation score calculating unit; and 8, an evaluation score calculating unit.
Detailed Description
The following description of the embodiments of the present invention will be made with reference to the accompanying drawings.
The first embodiment is as follows:
as shown in fig. 1, the invention discloses a power distribution equipment health evaluation method, which comprises the following steps:
s1: and acquiring historical operating parameters of the power distribution equipment, and preprocessing the data to obtain model training data.
Specifically, firstly, historical operating parameters of the power distribution equipment are obtained, shutdown data in the power distribution equipment are removed, and the processed historical operating parameters are used as historical data; and then, removing abnormal data from the historical data according to the fault rule to serve as model training data.
S2: and training the equipment health evaluation model by using the model training data.
The training process of the equipment health evaluation model is as follows:
1. EMD decomposition is carried out on the model training data to obtain corresponding IMF components, and EMD decomposition is carried out on the historical data to obtain corresponding IMF components.
2. And calculating mutual information of each IMF component, and normalizing the mutual information to be used as the initialization weight of each IMF component.
The calculation principle is as follows: and calculating the information entropy and the conditional entropy of each IMF component through a mutual information algorithm, wherein the difference value of the information entropy and the conditional entropy is the mutual information characteristic, and the normalized mutual information characteristic is taken as a constant weight of the parameter.
Wherein, the mutual information I (I, j) is a difference value between the information entropy H (I) of the parameter I and the conditional entropy H (I | j) of the parameter I, and the specific formula is as follows:
I(i,j)＝H(i)-H(i|j)
assuming the IMF component data set as T, an nxn mutual information matrix H can be calculated using the mutual information algorithm, as follows:
calculating a row mean value of the H matrix to obtain a one-dimensional vector R:
the normalized value of the one-dimensional vector R is used as the initialization weight of each parameter:
3. and calculating a training data residual error and a historical data residual error by adopting a preset RVM (relevance vector machine) model based on the IMF component of the training data and the IMF component of the historical data.
4. And (3) mining parameter residual scores which are respectively corresponding to parameter residual thresholds of 30,50 and 60 through confidence degrees of probability density distribution by using the historical data residual absolute values and the training data residual absolute values, and constructing a nonlinear regression relation between the parameter residual absolute values and the parameter scores through cumulative probability density distribution to obtain parameter deviation degree scores.
S3: and acquiring a real-time operation parameter X of the power distribution equipment.
S4: and performing EMD on the real-time operation parameter X to obtain an IMF component of the real-time operation parameter X.
S5: and loading the trained equipment health evaluation model, and calculating residual values of all IMF components of the real-time operation parameter X by using the trained equipment health evaluation model.
S6: and adjusting the parameter weight according to the residual value of the IMF component and a variable weight formula to obtain the variable weight of the operation parameter X.
Normalizing the residual value of each IMF component to obtain a normalized residual value delta x, and dynamically adjusting the weight of the current IMF component according to a variable weight formula, wherein the specific formula is as follows:
wherein, Δ xiNormalizing the residual value, W, of the ith IMF componentOriginal iIs the original weight of the ith IMF component, WVariable iIs the variable weight of the ith IMF component.
S7: and obtaining deviation scores of the IMF components by using the trained equipment health evaluation model.
S8: and multiplying the deviation score of each IMF component by the corresponding parameter weight to obtain an accumulated value, so as to obtain the equipment health evaluation score.
Obtaining a score value pscore of the ith IMF component IMFi according to the relation between the residual absolute value and the parameter scoreiThe method comprises the following steps:
pscorei＝wvariable i*scorei
The direct parameter synthesis score totalScore of the transformer device is calculated according to the following formula:
wherein, scoreiIs the parameter score of the ith IMF component.
Example two:
the embodiment discloses a power distribution equipment health evaluation method, which constructs an equipment health evaluation method based on Empirical Mode Decomposition (EMD) and Relevance Vector Machine (RVM) around the mapping relation between equipment data and state scores. The method comprises two parts, namely an equipment health evaluation model training process and an equipment health evaluation model running process.
1. As shown in fig. 2, the training of the device health assessment model includes the following steps:
step 1.1: and (4) preprocessing data.
And acquiring equipment parameters X, eliminating shutdown data, and taking the processed data as historical data. And removing abnormal data from the historical data according to the fault rule to serve as model training data.
Step 1.2: and (4) EMD decomposition.
EMD decomposition is performed on the training data to obtain a plurality of IMF components.
Taking the transformer oil temperature data as an example, taking the transformer oil temperature as a data source, extracting all the oil temperature data to obtain a data set G, eliminating shutdown and fault data, performing EMD, and taking the first 6 IMF components as shown in FIG. 4.
Step 1.3: and initializing the weight of the parameter.
And (3) calculating mutual information of each IMF component in the step 1.2, and using the normalized mutual information as the initialization weight of each component.
And calculating the information entropy and the conditional entropy of each IMF component through a mutual information algorithm, wherein the difference value of the information entropy and the conditional entropy is the mutual information characteristic, and the normalized mutual information characteristic is taken as a constant weight of the parameter.
The mutual information I (I, j) is a difference value between the information entropy H (I) of the parameter I and the conditional entropy H (I | j) of the parameter I, and the specific formula is as follows:
I(i,j)＝H(i)-H(i|j) (1)
assuming the IMF component data set as T, an n × n mutual information matrix H can be calculated using a mutual information algorithm, as follows:
calculating a row mean value of the H matrix to obtain a one-dimensional vector R:
the normalized value of the one-dimensional vector R is then used as the initialization weight for each parameter:
step 1.4: and (5) training a model.
Based on the training data IMF component and the historical data IMF component, an RVM model is used to calculate training data residuals and historical data residuals.
Specifically, the IMF component is input into the RVM model, and through multiple rounds of parameter iterative optimization, an evaluation value of normal data is obtained, and a subtraction between the evaluation value and an actual value is performed to obtain a residual sequence of the IMF component of the normal data, taking IMF1 as an example, and the model estimation result is shown in fig. 5.
Step 1.5: and constructing a mapping relation between the residual error and the evaluation score.
And (3) mining parameter residual threshold values with the scores of 30,50 and 60 respectively corresponding to the parameter residual scores by using historical residual data and training residual data absolute values through confidence degrees of probability density distribution, and constructing a nonlinear regression relation between the parameter residual absolute values and the parameter scores through cumulative probability density distribution to obtain parameter deviation degree scores.
As an example, after a historical data set including normal data and fault data is subjected to EMD decomposition, each IMF component is input into a trained RVM, the node thresholds of 60, 50 and 30 corresponding to parameter residuals are divided through service personnel information calibration, four fractional intervals of [60, 100], [50,60], [30,50] and [0,30] are used, and the corresponding relation between the parameter residual absolute value and the parameter scores is calculated according to mathematical statistics.
Taking the fractional interval [60, 100] of the IMFi as an example, according to the cumulative probability density function f (i), the relation between the residual absolute value and the parameter fraction is obtained:
Scorei＝Scorehigh-ΔScore*f(i) (4)
wherein, Scorehigh＝100，ΔScore＝100-60＝40。
2. As shown in fig. 3, the operation process of the equipment health evaluation model specifically includes the following steps:
step 2.1: and acquiring real-time operation data of the equipment parameters X.
Step 2.2: and obtaining an IMF component of the parameter X through EMD decomposition.
Step 2.3: and loading the trained RVM model, and calculating residual values of all IMF components of the real-time operation data.
As an example, a segment of transformer oil temperature data containing fault information is extracted as real-time data X, subjected to EMD decomposition, and input to a trained RVM model, taking IMF1 as an example, as shown in fig. 6, to obtain a real-time evaluation value and a residual error curve.
As can be seen from fig. 6, the residual of this component triggers the lower alarm limit. As the fault continues to develop, the residual error between the actual value and the estimated value has a remarkable downward degradation trend.
Step 2.4: and adjusting the parameter weight according to the IMF parameter residual error and a variable weight formula to obtain the variable weight of the parameter.
And (3) carrying out normalization processing on residual values of all IMF components of the real-time data to obtain delta x, and then dynamically adjusting the weight of the current IMF component according to a variable weight formula, wherein the weight is calculated as follows:
wherein, Δ xiNormalizing the residual value, W, of the ith IMF componentOriginal iIs the original weight of the ith IMF component, WVariable iIs the variable weight of the ith IMF component.
Step 2.5: and (4) obtaining the deviation score of each IMF component according to the nonlinear regression relation between the parameter residual absolute value and the parameter score in the training step 1.4.
Step 2.6: and (5) multiplying the deviation scores of the IMF components by the corresponding parameter weights in the step 2.5 to obtain accumulated values, namely the equipment health evaluation scores.
As an example, the IMFi component score value pscore is obtained according to the relation between the residual absolute value and the parameter scoreiThe following were used:
pscorei＝wvariable i*scorei (6)
The direct parameter synthesis score totalScore of the transformer device is calculated according to the following formula:
after the health evaluation model operates for a period of time, the evaluation score of the equipment obtained according to the oil temperature data of the transformer is shown in fig. 7. In 2019, from 5-15 th to 6-15 th, the equipment monitoring system finds that abnormal phenomena of poor transformer load adjustment devices and improper adjustment of transformer equipment occur, temperature abnormality begins to occur in about 6-2 th, the equipment health score is reduced from 67 to 43, and the equipment health evaluation model meets the equipment abnormal conditions of the equipment at the moment.
Correspondingly, as shown in fig. 8, the present invention also discloses a power distribution equipment health evaluation system, including:
the data preprocessing unit 1 is used for acquiring historical operating parameters of the power distribution equipment, and the historical operating parameters are used as model training data after data preprocessing.
And the model training unit 2 is used for performing equipment health evaluation model training by using the model training data.
And the parameter acquisition unit 3 is used for acquiring the real-time operation parameters X of the power distribution equipment.
And the EMD decomposition unit 4 is used for performing EMD decomposition on the real-time operation parameter X to obtain an IMF component of the real-time operation parameter X.
And the calculating unit 5 is used for loading the trained equipment health evaluation model and calculating residual values of IMF components of the real-time operation parameters X by using the trained equipment health evaluation model.
And the parameter weight adjusting unit 6 is used for adjusting the parameter weight according to the residual value of the IMF component and a variable weight formula to obtain the variable weight of the operation parameter X.
And the deviation score calculating unit 7 is used for obtaining deviation scores of the IMF components by using the trained equipment health evaluation model.
And the evaluation score calculating unit 8 is used for multiplying the deviation score of each IMF component by the corresponding parameter weight to obtain an accumulated value so as to obtain the equipment health evaluation score.
Correspondingly, the invention also discloses a power distribution equipment health evaluation device, which comprises:
a memory for storing a computer program;
a processor for implementing the steps of the power distribution equipment health assessment method according to any of the above when executing the computer program.
Those skilled in the art will readily appreciate that the techniques of the embodiments of the present invention may be implemented as software plus a required general purpose hardware platform. Based on such understanding, the technical solutions in the embodiments of the present invention may be substantially or partially embodied in the form of a software product, the computer software product is stored in a storage medium, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and various media capable of storing program codes include several instructions for enabling a computer terminal (which may be a personal computer, a server, or a second terminal, a network terminal, etc.) to execute all or part of the steps of the method in the embodiments of the present invention. The same and similar parts in the various embodiments in this specification may be referred to each other. Especially, for the terminal embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant points can be referred to the description in the method embodiment.
In the embodiments provided by the present invention, it should be understood that the disclosed system, system and method can be implemented in other ways. For example, the above-described system embodiments are merely illustrative, and for example, the division of the units is only one logical functional division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, systems or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each module may exist alone physically, or two or more modules are integrated into one unit.
Similarly, each processing unit in the embodiments of the present invention may be integrated into one functional module, or each processing unit may exist physically, or two or more processing units are integrated into one functional module.
The invention is further described with reference to the accompanying drawings and specific embodiments. It should be understood that these examples are for illustrative purposes only and are not intended to limit the scope of the present invention. Further, it should be understood that various changes or modifications of the present invention may be made by those skilled in the art after reading the teaching of the present invention, and these equivalents also fall within the scope of the present application.
Claims (8)
1. A power distribution equipment health evaluation method is characterized by comprising the following steps:
s1: acquiring historical operating parameters of the power distribution equipment, and preprocessing the data to obtain model training data;
s2: training an equipment health evaluation model by using model training data;
s3: acquiring a real-time operation parameter X of the power distribution equipment;
s4: performing EMD on the real-time operation parameter X to obtain an IMF component of the real-time operation parameter X;
s5: loading the trained equipment health evaluation model, and calculating residual values of all IMF components of the real-time operation parameter X by using the trained equipment health evaluation model;
s6: adjusting the parameter weight according to the residual value of the IMF component and a variable weight formula to obtain the variable weight of the operation parameter X;
s7: obtaining deviation scores of all IMF components by using the trained equipment health evaluation model;
s8: and multiplying the deviation score of each IMF component by the corresponding parameter weight to obtain an accumulated value, so as to obtain the equipment health evaluation score.
2. The method for evaluating the health of an electric distribution equipment according to claim 1, wherein the step S1 comprises:
acquiring historical operating parameters of the power distribution equipment, eliminating shutdown data in the power distribution equipment, and taking the processed historical operating parameters as historical data;
and removing abnormal data from the historical data according to the fault rule to serve as model training data.
3. The method for evaluating the health of an electrical distribution apparatus according to claim 2, wherein the step S2 includes:
performing EMD on the model training data to obtain corresponding IMF components, and performing EMD on the historical data to obtain corresponding IMF components;
calculating mutual information of each IMF component, and taking the normalized mutual information as the initialization weight of each IMF component;
calculating a training data residual error and a historical data residual error by adopting a preset RVM (relevance vector machine) model based on the IMF component of the training data and the IMF component of the historical data;
and (3) mining parameter residual scores which are respectively corresponding to parameter residual thresholds of 30,50 and 60 through confidence degrees of probability density distribution by using the historical data residual absolute values and the training data residual absolute values, and constructing a nonlinear regression relation between the parameter residual absolute values and the parameter scores through cumulative probability density distribution to obtain parameter deviation degree scores.
4. The method according to claim 3, wherein the step of calculating mutual information of each IMF component, and the mutual information is normalized to serve as an initialization weight of each IMF component comprises:
calculating the information entropy and the conditional entropy of each IMF component through a mutual information algorithm, wherein the difference value of the information entropy and the conditional entropy is a mutual information characteristic, and the normalized mutual information characteristic is used as a parameter constant weight;
wherein, the mutual information I (I, j) is a difference value between the information entropy H (I) of the parameter I and the conditional entropy H (I | j) of the parameter I, and the specific formula is as follows:
I(i,j)＝H(i)-H(i|j)
assuming the IMF component data set as T, an n × n mutual information matrix H can be calculated using a mutual information algorithm, as follows:
calculating a row mean value of the H matrix to obtain a one-dimensional vector R:
the normalized value of the one-dimensional vector R is then used as the initialization weight for each parameter:
5. the method for evaluating the health of an electric distribution equipment according to claim 4, wherein the step S6 comprises:
normalizing the residual value of each IMF component to obtain a normalized residual value delta x, and dynamically adjusting the weight of the current IMF component according to a variable weight formula, wherein the specific formula is as follows:
wherein, Δ xiNormalizing the residual value, W, of the ith IMF componentOriginal iIs the original weight of the ith IMF component, WVariable iIs the variable weight of the ith IMF component.
6. The method for evaluating the health of an electric distribution equipment according to claim 4, wherein the step S8 comprises:
obtaining a score value pscore of the ith IMF component IMFi according to the relation between the residual absolute value and the parameter scoreiThe method comprises the following steps:
pscorei＝wbecome i*scorei
The direct parameter integration score totalScore of the transformer device is calculated according to the following formula:
wherein, scoreiIs the parameter score of the ith IMF component.
7. A power distribution equipment health assessment system, comprising:
the data preprocessing unit is used for acquiring historical operating parameters of the power distribution equipment, and the historical operating parameters are used as model training data after data preprocessing;
the model training unit is used for performing equipment health evaluation model training by using the model training data;
the parameter acquisition unit is used for acquiring a real-time operation parameter X of the power distribution equipment;
the EMD decomposition unit is used for performing EMD decomposition on the real-time operation parameter X to obtain an IMF component of the real-time operation parameter X;
the computing unit is used for loading the trained equipment health evaluation model and computing residual values of all IMF components of the real-time operation parameter X by using the trained equipment health evaluation model;
the parameter weight adjusting unit is used for adjusting the parameter weight according to the residual value of the IMF component and a variable weight formula to obtain the variable weight of the operation parameter X;
the deviation score calculating unit is used for obtaining deviation scores of all IMF components by using the trained equipment health evaluation model;
and the evaluation score calculating unit is used for multiplying the deviation score of each IMF component by the corresponding parameter weight to obtain an accumulated value so as to obtain the equipment health evaluation score.
8. An apparatus for evaluating the health of an electrical distribution device, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the method of assessing the health of an electrical distribution apparatus according to any one of claims 1 to 6 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210191206.1A CN114742345B (en) | 2022-02-28 | Power distribution equipment health evaluation method, system and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210191206.1A CN114742345B (en) | 2022-02-28 | Power distribution equipment health evaluation method, system and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114742345A true CN114742345A (en) | 2022-07-12 |
| CN114742345B CN114742345B (en) | 2024-10-15 |
Family
ID=
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116452067A (en) * | 2023-06-12 | 2023-07-18 | 昆山工业大数据创新中心有限公司 | Degradation degree evaluation method, device and equipment for industrial equipment parameters |
| CN117563144A (en) * | 2023-12-04 | 2024-02-20 | 惠州市凌盛医疗科技有限公司 | Method and system for evaluating condition and predicting residual life of infrared therapeutic instrument |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110956312A (en) * | 2019-11-15 | 2020-04-03 | 国网浙江省电力有限公司电力科学研究院 | Photovoltaic power distribution network voltage prediction method based on EMD-CNN deep neural network |
| US20210117770A1 (en) * | 2019-10-18 | 2021-04-22 | Wuhan University | Power electronic circuit troubleshoot method based on beetle antennae optimized deep belief network algorithm |
| CN113095081A (en) * | 2021-06-11 | 2021-07-09 | 深圳市北科瑞声科技股份有限公司 | Disease identification method and device, storage medium and electronic device |
| CN113125987A (en) * | 2021-04-19 | 2021-07-16 | 安徽理工大学 | Novel hybrid lithium ion battery health state prediction method |
| CN113221441A (en) * | 2020-12-24 | 2021-08-06 | 山东鲁能软件技术有限公司 | Method and device for health assessment of power plant equipment |
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210117770A1 (en) * | 2019-10-18 | 2021-04-22 | Wuhan University | Power electronic circuit troubleshoot method based on beetle antennae optimized deep belief network algorithm |
| CN110956312A (en) * | 2019-11-15 | 2020-04-03 | 国网浙江省电力有限公司电力科学研究院 | Photovoltaic power distribution network voltage prediction method based on EMD-CNN deep neural network |
| CN113221441A (en) * | 2020-12-24 | 2021-08-06 | 山东鲁能软件技术有限公司 | Method and device for health assessment of power plant equipment |
| CN113125987A (en) * | 2021-04-19 | 2021-07-16 | 安徽理工大学 | Novel hybrid lithium ion battery health state prediction method |
| CN113095081A (en) * | 2021-06-11 | 2021-07-09 | 深圳市北科瑞声科技股份有限公司 | Disease identification method and device, storage medium and electronic device |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116452067A (en) * | 2023-06-12 | 2023-07-18 | 昆山工业大数据创新中心有限公司 | Degradation degree evaluation method, device and equipment for industrial equipment parameters |
| CN116452067B (en) * | 2023-06-12 | 2023-09-05 | 昆山工业大数据创新中心有限公司 | Degradation degree evaluation method, device and equipment for industrial equipment parameters |
| CN117563144A (en) * | 2023-12-04 | 2024-02-20 | 惠州市凌盛医疗科技有限公司 | Method and system for evaluating condition and predicting residual life of infrared therapeutic instrument |
| CN117563144B (en) * | 2023-12-04 | 2024-05-28 | 郭永强 | Method and system for evaluating condition and predicting residual life of infrared therapeutic instrument |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Catalão et al. | Short-term wind power forecasting in Portugal by neural networks and wavelet transform | |
| CN111314173B (en) | Monitoring information abnormity positioning method and device, computer equipment and storage medium | |
| CN112767190B (en) | Method and device for identifying phase sequence of transformer area based on multilayer stacked neural network | |
| Luo et al. | Graph convolutional network-based interpretable machine learning scheme in smart grids | |
| CN111178393A (en) | Electric appliance power consumption classification metering method and device based on intelligent electric meter | |
| CN108009063B (en) | Method for detecting fault threshold of electronic equipment | |
| CN111340287A (en) | Power distribution cabinet operation state prediction method and device | |
| CN111767193A (en) | Server data anomaly detection method and device, storage medium and equipment | |
| CN115577851A (en) | Energy consumption prediction method, device, equipment and storage medium | |
| CN116663746A (en) | Power load prediction method and device, computer equipment and storage medium | |
| Dai et al. | Fault Diagnosis of Data‐Driven Photovoltaic Power Generation System Based on Deep Reinforcement Learning | |
| CN115185804A (en) | Server performance prediction method, system, terminal and storage medium | |
| CN113110961B (en) | Equipment abnormality detection method and device, computer equipment and readable storage medium | |
| CN112380759A (en) | Smart meter service life prediction method based on deep learning and CoxPH model | |
| CN113987027A (en) | Equipment state determination method, device and medium based on fault prediction | |
| CN109409786A (en) | Method and system for evaluating reliability of power distribution network | |
| CN110740063B (en) | Network flow characteristic index prediction method based on signal decomposition and periodic characteristics | |
| CN116992274A (en) | Short-term wind speed prediction method and system based on improved principal component regression model | |
| CN114742345B (en) | Power distribution equipment health evaluation method, system and device | |
| CN114742345A (en) | Power distribution equipment health evaluation method, system and device | |
| CN116400266A (en) | Transformer fault detection method, device and medium based on digital twin model | |
| CN116245505A (en) | Line loss main factor analysis method and related equipment thereof | |
| CN115617604A (en) | Disk failure prediction method and system based on image pattern matching | |
| Cao et al. | Condition monitoring of wind turbine based on a novel spatio-temporal feature aggregation network integrated with adaptive threshold interval | |
| CN116149971B (en) | Equipment fault prediction method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |