CN113269400B - Low-voltage distribution network equipment state evaluation method based on historical operation and maintenance information - Google Patents
Low-voltage distribution network equipment state evaluation method based on historical operation and maintenance information Download PDFInfo
- Publication number
- CN113269400B CN113269400B CN202110463464.6A CN202110463464A CN113269400B CN 113269400 B CN113269400 B CN 113269400B CN 202110463464 A CN202110463464 A CN 202110463464A CN 113269400 B CN113269400 B CN 113269400B
- Authority
- CN
- China
- Prior art keywords
- data
- equipment
- state
- distribution network
- network equipment
- 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.)
- Active
Links
- 238000009826 distribution Methods 0.000 title claims abstract description 119
- 238000012423 maintenance Methods 0.000 title claims abstract description 41
- 238000011156 evaluation Methods 0.000 title claims abstract description 27
- 238000000034 method Methods 0.000 claims abstract description 46
- 230000036541 health Effects 0.000 claims abstract description 22
- 230000015654 memory Effects 0.000 claims abstract description 19
- 230000009467 reduction Effects 0.000 claims abstract description 17
- 238000012545 processing Methods 0.000 claims abstract description 11
- 238000013528 artificial neural network Methods 0.000 claims abstract description 8
- 230000011218 segmentation Effects 0.000 claims abstract description 4
- 238000012549 training Methods 0.000 claims description 15
- 238000004422 calculation algorithm Methods 0.000 claims description 11
- 238000004140 cleaning Methods 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 8
- 230000007787 long-term memory Effects 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 5
- 239000000203 mixture Substances 0.000 claims 1
- 239000002994 raw material Substances 0.000 claims 1
- 238000000638 solvent extraction Methods 0.000 claims 1
- 230000008878 coupling Effects 0.000 abstract description 5
- 238000010168 coupling process Methods 0.000 abstract description 5
- 238000005859 coupling reaction Methods 0.000 abstract description 5
- 230000007613 environmental effect Effects 0.000 abstract description 5
- 238000012360 testing method Methods 0.000 description 12
- 238000012544 monitoring process Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 10
- 238000004088 simulation Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 4
- 230000032683 aging Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 239000002699 waste material Substances 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000006403 short-term memory Effects 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000008531 maintenance mechanism Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012795 verification 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
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
- Y02E40/70—Smart grids as climate change mitigation technology in the energy generation sector
-
- 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
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Evolutionary Computation (AREA)
- Marketing (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Development Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Testing Electric Properties And Detecting Electric Faults (AREA)
Abstract
The invention discloses a low-voltage distribution network equipment state evaluation method based on historical operation and maintenance information, which is used for carrying out dimension reduction processing on the historical operation and maintenance information of distribution equipment based on a depth self-encoder; the method comprises the steps of completing segmentation of historical operation and maintenance information of the equipment and identification of state evolution characteristics in a sliding window mode, and extracting health factors of the power distribution equipment by using a support vector regression strategy; fusing the processed data and the health factors, and inputting the fused data and the health factors into a long-time memory network to identify the deep state evolution characteristics of the power distribution equipment, so as to complete the identification of the long-time memory network parameters; and inputting the online measured equipment operation information into the trained deep neural network to finish the online evaluation of the operation state of the distribution network equipment. When the most essential characteristics of the data are reserved, the method reduces the interference of environmental noise or other coupling components on the data signals, improves the accuracy of the operation state identification of the distribution network equipment, reduces the dimensionality of the data, improves the processing efficiency of the state data of the distribution network equipment, and saves computing resources.
Description
Technical Field
The invention relates to the technical field of intelligent detection, in particular to a low-voltage distribution network equipment state evaluation method based on historical operation and maintenance information.
Background
With the increasing demand of national economy development and the progress of distribution network technology, the scale of low-voltage distribution networks in China shows a continuous expansion trend. And the safety and stability of the distribution network equipment are the basis for reliable operation of the power system. Once the distribution network equipment fails, the normal production and life of people are affected; and the safety accidents are caused, and the great economic loss and the adverse social influence are caused. Therefore, the operation state of the distribution network equipment is evaluated in real time, early warning of potential faults of the distribution network equipment is achieved, damaged equipment is maintained and replaced in time, and the method has important significance for improving the reliability of operation of a power system.
For a long time, the problems of insufficient maintenance, excessive maintenance and the like exist in a regular maintenance mechanism pushed by a power enterprise to the distribution network equipment, so that not only is great resource waste caused, but also the reliability of equipment power supply is influenced to a certain extent. Therefore, based on the historical and current operation states of the distribution network equipment, the state maintenance work of the distribution network equipment is imperatively carried out by utilizing data such as online monitoring and offline experiments. With the progress of communication, computer and control technology, the fault monitoring system is widely applied to distribution network equipment at present, mass data are accumulated, and the problem that how to deeply analyze the data and further maintain the safe operation of the distribution network equipment is urgently solved at the present stage is already a problem.
Due to the characteristics of various types, complex parameters, large monitoring data amount, various operating environments and the like, equipment information acquired by the sensor is possibly polluted by environmental noise and signals from other coupling parts, and key information reflecting the equipment state is covered; meanwhile, a plurality of sensor information also comprises a plurality of redundant information, and if the information is directly processed, the waste of computing resources is caused. Data collected by the sensors are label-free data (health states corresponding to the devices are not included), the data cannot directly enter the deep learning network for learning, and the premise of deep learning network training is how to obtain the health factors of the distribution network devices in the full life cycle. In addition, the aging failure process of the distribution network equipment is influenced by various factors, and at the moment, if the equipment failure process is physically modeled by means of expert experience and manual feature extraction, the efficiency is inevitably low, the aging process of the distribution network equipment cannot be comprehensively and accurately described, and how to automatically extract the fault features of the distribution network equipment is also a difficult problem for realizing the operation state evaluation of the distribution network equipment.
Disclosure of Invention
This section is for the purpose of summarizing some aspects of embodiments of the invention and to briefly introduce some preferred embodiments. In this section, as well as in the abstract and the title of the invention of this application, simplifications or omissions may be made to avoid obscuring the purpose of the section, the abstract and the title, and such simplifications or omissions are not intended to limit the scope of the invention.
The present invention has been made in view of the above-mentioned conventional problems.
Therefore, the invention provides a low-voltage distribution network equipment state evaluation method based on historical operation and maintenance information, which can solve the problems that the aging process of distribution network equipment cannot be comprehensively and accurately described and the fault characteristics of the distribution network equipment cannot be automatically extracted.
In order to solve the technical problems, the invention provides the following technical scheme: the method comprises the steps that the historical operation and maintenance information of the power distribution equipment is subjected to dimension reduction processing based on a depth self-encoder; the segmentation of the historical operation and maintenance information of the equipment and the identification of state evolution characteristics are completed in a sliding window mode, and health factors of the power distribution equipment are extracted by using a support vector regression strategy; fusing the processed data and the health factors, and inputting the fused data and the health factors into a long-time memory network to identify the deep state evolution characteristics of the power distribution equipment, so as to complete the identification of the long-time memory network parameters; and inputting the online measured equipment operation information into the trained deep neural network to finish the online evaluation of the operation state of the distribution network equipment.
As a preferred scheme of the low voltage distribution network equipment state evaluation method based on historical operation and maintenance information, the method comprises the following steps: the method comprises the steps of constructing a stacked depth automatic encoder network to clean original historical data of the power distribution equipment, utilizing the depth automatic encoder to perform dimensionality reduction processing on data information of the power distribution equipment, completing cleaning of data, reducing signal noise and eliminating redundant information.
As a preferred scheme of the low voltage distribution network equipment state evaluation method based on historical operation and maintenance information, the method comprises the following steps: inputting historical data information of the power distribution equipment into the constructed neural network for training; setting the sum of squares of the difference between the input data and the output result as a penalty function; and updating the weight parameters of the neural network by adopting a random gradient descent algorithm until the reconstruction of the historical operating data of the power distribution equipment is completed, and completing the cleaning treatment of dimension reduction and noise reduction of the data of the power distribution equipment.
As a preferred scheme of the low voltage distribution network equipment state evaluation method based on historical operation and maintenance information, the method comprises the following steps: the method comprises the steps of dividing cleaned distribution network equipment time sequence state information based on the sliding window method; extracting device state evolution characteristics in each window; and storing the extracted state characteristics of the distribution network equipment in a matrix form, and setting the initial 10% of data as a healthy state and a healthy label as 1, and setting the final 10% of data as a failed state and a healthy label as 0.
As a preferred scheme of the low voltage distribution network equipment state evaluation method based on historical operation and maintenance information, the method comprises the following steps: inputting the label data into the constructed support vector regression network, and taking the square sum of the difference value between the output value of the support vector regression network and the label value as a penalty function; updating the weight parameters of the support vector regression network by adopting the random gradient descent algorithm to complete the parameter identification of the support vector regression network; and inputting the rest 80% of data into the trained support vector regression network, wherein the obtained result is the health factor corresponding to the distribution network equipment.
As a preferred scheme of the low voltage distribution network equipment state evaluation method based on historical operation and maintenance information, the method comprises the following steps: the method comprises the steps of cleaning original historical operation data of the distribution network equipment based on a stack type depth automatic encoder network and calculating and analyzing a support vector regression network to obtain clean and low-dimensional data with health labels.
As a preferred scheme of the low voltage distribution network equipment state evaluation method based on historical operation and maintenance information, the method comprises the following steps: inputting the cleaned historical operation and maintenance information of the distribution network equipment into a long-time and short-time memory network for training, identifying deep state evolution characteristics of the distribution equipment, and completing identification of weight parameters in the long-time and short-time memory network.
As a preferred scheme of the low voltage distribution network equipment state evaluation method based on historical operation and maintenance information, the method comprises the following steps: the method also comprises the steps of acquiring running state information of the distribution network equipment in real time by adopting a sensor; inputting the acquired state information into the trained stack-type depth automatic encoder network for denoising and dimensionality reduction to obtain clean and low-dimensionality running state data; and inputting the processed running state data into the long-time memory network after training is completed, and finishing the evaluation of the running state of the distribution network equipment.
The invention has the beneficial effects that: according to the invention, the data of the distribution network equipment is cleaned by adopting the stack type depth automatic encoder, so that when the most essential characteristics of the data are kept, the interference of environmental noise or other coupling components on data signals is reduced, the accuracy of the identification of the running state of the distribution network equipment is improved, the dimensionality of the data is reduced, the processing efficiency of the state data of the distribution network equipment is improved, and the computing resources are saved; the evolution trend of the running state of the distribution network equipment is extracted by adopting a sliding window and a support vector regression method, the historical operation and maintenance data of the distribution network equipment can be directly set as a health state label to obtain the health factor of the distribution equipment, the label data of the distribution network equipment is obtained without adopting an experiment or simulation method, the data processing efficiency is improved, and the authenticity of the data is improved; the failure process of the distribution network equipment is extremely complex and is influenced by various factors such as the operating environment, the working state and the like, the description of the failure process of the distribution network equipment is difficult to realize in a physical modeling mode, and the long-time memory network can automatically extract the state evolution characteristics of the large-time span and long-distance influence of the distribution network equipment, so that the failure process of the distribution network equipment can be more comprehensively and accurately described; the invention utilizes the sensor to collect the running state data of the distribution network equipment in real time and inputs the data into the trained long-time and short-time memory network, thereby automatically evaluating the state of the distribution network equipment and realizing all-weather and on-line monitoring of the faults of the distribution network equipment.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the description below are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive labor. Wherein:
fig. 1 is a schematic flowchart of a method for evaluating a state of a low-voltage distribution network device based on historical operation and maintenance information according to a first embodiment of the present invention;
fig. 2 is a schematic diagram of a comparison curve of a low-voltage distribution network equipment state evaluation method based on historical operation and maintenance information according to a second embodiment of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, specific embodiments accompanied with figures are described in detail below, and it is apparent that the described embodiments are a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making creative efforts based on the embodiments of the present invention, shall fall within the protection scope of the present invention.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways than those specifically described and will be readily apparent to those of ordinary skill in the art without departing from the spirit of the present invention, and therefore the present invention is not limited to the specific embodiments disclosed below.
Furthermore, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one implementation of the invention. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
The present invention will be described in detail with reference to the drawings, wherein the cross-sectional views illustrating the structure of the device are not enlarged partially in general scale for convenience of illustration, and the drawings are only exemplary and should not be construed as limiting the scope of the present invention. In addition, the three-dimensional dimensions of length, width and depth should be included in the actual fabrication.
Meanwhile, in the description of the present invention, it should be noted that the terms "upper, lower, inner and outer" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of describing the present invention and simplifying the description, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation and operate, and thus, cannot be construed as limiting the present invention. Furthermore, the terms first, second, or third are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
The terms "mounted, connected" and "connected" in the present invention are to be construed broadly, unless otherwise explicitly specified or limited, for example: can be fixedly connected, detachably connected or integrally connected; they may be mechanically, electrically, or directly connected, or indirectly connected through intervening media, or may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Example 1
Referring to fig. 1, a first embodiment of the present invention provides a method for evaluating a state of a low-voltage distribution network device based on historical operation and maintenance information, including:
s1: and carrying out dimension reduction processing on the historical operation and maintenance information of the power distribution equipment based on the depth self-encoder.
S2: and completing the segmentation of the historical operation and maintenance information of the equipment and the identification of state evolution characteristics by adopting a sliding window mode, and extracting the health factor of the power distribution equipment by utilizing a support vector regression strategy.
S3: and fusing the processed data and the health factors, and inputting the fused data and the health factors into a long-term and short-term memory network to identify the deep state evolution characteristics of the power distribution equipment, so as to complete the identification of the long-term and short-term memory network parameters.
S4: and inputting the online measured equipment operation information into the trained deep neural network to finish the online evaluation of the operation state of the distribution network equipment.
Specifically, a stack-type depth automatic encoder network is constructed to complete cleaning of historical operation and maintenance information of distribution network equipment, historical data of the distribution network equipment is constructed into a matrix of X, X = { X (1), X (2), X (3), … X (N) }, and X (i) belongs to R M And adding a certain amount of 'damage noise' into the matrix X to obtain data X containing noise, wherein X-qD (X | X) is satisfied, qD is a noise distribution form, namely 'damage noise' is added according to qD distribution, and the X is coded to obtain y based on an automatic coder network, so that y can be close to or reconstruct original input X.
The specific process is as follows:
(1) Constructing a depth automatic encoder model, setting parameters of a network learning rate epsilon and a sparse parameter rho, and randomly initializing a model connection weight W and an offset b;
(2) Setting batch training number and iteration number in a forward propagation algorithm, executing the forward propagation algorithm, and calculating average activation rho j ;
(3) Constructing a loss function based on the input and output of the depth self-encoder;
(4) And (4) executing a back propagation method, updating the network weight parameters W and b based on a random gradient descent algorithm, completing the training of the depth self-encoder, and realizing the noise reduction and dimension reduction of the operation and maintenance information of the distribution network equipment.
It is easy to understand that the cleaned distribution network equipment time sequence state information is segmented based on a sliding window method, the equipment state evolution characteristics (such as state mean value and change rate information) in each window are extracted, the extracted distribution network equipment state characteristics are stored in a matrix form, the initial 10% of data is considered as a healthy state, the healthy label is set to be 1, the final 10% of data is considered as a failed state, and the healthy label is set to be 0.
Inputting the label data into the constructed support vector regression network, taking the square sum of the difference value between the output value of the support vector regression network and the label value as a penalty function, updating the weight parameters of the support vector regression network by adopting a random gradient descent algorithm, completing the parameter identification of the support vector regression network, inputting the remaining 80% of data into the trained support vector regression network, and obtaining the result, namely the health factor corresponding to the distribution network equipment.
Preferably, based on the cleaning of the original distribution network equipment historical operation and maintenance information by the stacked depth automatic encoder network and the calculation and analysis of the support vector regression network, clean and low-dimensional data with health labels can be obtained, the cleaned distribution network equipment historical operation and maintenance information is input into the long-term memory network for training, the deep state evolution characteristics of the distribution equipment are identified, and the identification of the weight parameters in the long-term memory network is completed.
The specific implementation process is as follows:
(1) Building a long-time and short-time memory network, setting a network learning rate epsilon by adopting a stacked long-time and short-time memory network in consideration of complexity of an operation environment of distribution network equipment and a sample training scale, and randomly initializing a model weight W and an offset b;
(2) The cleaned data are denoted as X = (X) 1 ,X 2 ,X 3 ,…X l ) Dividing the data into a test set and a training set, and inputting the training set data into the test set and the training setExecuting a forward propagation algorithm in a time memory network, and calculating a loss function;
(3) Based on the loss function of forward calculation, a random gradient descent algorithm is adopted to execute a back propagation algorithm, and weight parameters of each layer of the memory network at long and short times are updated;
(4) And inputting the test set data into the completed long-time and short-time memory network, and verifying the effect of the long-time and short-time memory network.
Preferably, based on the process, the training of the deep automatic encoder network, the support vector regression network and the long-time and short-time memory network is completed through historical data of the distribution network equipment, and at the moment, based on the distribution network equipment operation information acquired on line, the on-line evaluation of the distribution network equipment operation state can be completed.
The specific process is as follows:
(1) Collecting various running state data of the distribution network equipment by adopting a sensor, and inputting the data into a deep automatic encoder network to carry out the cleaning processes of noise reduction and dimension reduction to obtain clean and low-dimensional sensor data;
(2) And inputting the cleaned data into the long-term memory network to obtain the current running state information of the distribution network equipment, and sending the running state information to the operation and maintenance personnel as a basis for the operation and maintenance personnel to overhaul the equipment.
Example 2
Referring to fig. 2, a second embodiment of the present invention is different from the first embodiment in that an experimental test verification of a low-voltage distribution network equipment state evaluation method based on historical operation and maintenance information is provided, which specifically includes:
in order to verify and explain the technical effects adopted in the method of the present invention, the present embodiment selects to compare the traditional fault monitoring system with the method of the present invention for testing, and compares the test results by means of scientific demonstration to verify the actual effects of the method of the present invention.
The traditional fault monitoring system accumulates mass data, and cannot deeply analyze the data so as to maintain the safe operation of distribution network equipment, and the distribution network equipment has the characteristics of various types, complex parameters, large monitoring data quantity, various operating environments and the like, so that equipment information acquired by a sensor is possibly polluted by environmental noise and signals from other coupling parts, and key information reflecting the equipment state is covered; meanwhile, a plurality of sensor information also comprises a plurality of redundant information, and if the information is directly processed, the waste of computing resources is caused.
In order to verify that the method has the characteristics of reducing the interference of environmental noise or other coupling components on data signals, improving the accuracy of the identification of the running state of the distribution network equipment, reducing the dimensionality of data, improving the processing efficiency of the state data of the distribution network equipment and saving computing resources compared with the traditional method, the traditional fault monitoring system and the method are adopted in the embodiment to carry out real-time measurement and comparison on the state of the low-voltage distribution network equipment of the simulation platform respectively.
And (3) testing environment: inputting the parameters of the low-voltage distribution network equipment to a simulation platform for simulation operation, adopting historical operation and maintenance information as a test sample, respectively carrying out evaluation test by utilizing the monitoring operation of a traditional fault monitoring system and obtaining test result data; by adopting the method, the automatic test equipment is started, MATLB is used for realizing the simulation test of the method, simulation data are obtained according to the experimental result, 10000 groups of data are tested in each method, the time difference of each group of data is calculated, and the error comparison calculation is carried out with the actual predicted value of the simulation input.
Referring to fig. 2, a solid line is a curve output by the method of the present invention, a dotted line is a curve output by a conventional method, and according to the schematic diagram of fig. 2, it can be seen intuitively that the solid line and the dotted line show different trends along with the increase of time, the solid line shows a stable rising trend in the former period compared with the dotted line, although the solid line slides down in the latter period, the fluctuation is not large and is always above the dotted line and keeps a certain distance, and the dotted line shows a large fluctuation trend and is unstable, so that the state recognition accuracy of the solid line is always greater than that of the dotted line, i.e., the real effect of the method of the present invention is verified.
It should be noted that the above-mentioned embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, which should be covered by the claims of the present invention.
Claims (4)
1. A low-voltage distribution network equipment state evaluation method based on historical operation and maintenance information is characterized by comprising the following steps: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
carrying out dimension reduction processing on the historical operation and maintenance information of the power distribution equipment based on a depth self-encoder;
the segmentation of the historical operation and maintenance information of the equipment and the identification of state evolution characteristics are completed in a sliding window mode, and health factors of the power distribution equipment are extracted by using a support vector regression strategy;
fusing the processed data and the health factors, and inputting the fused data and the health factors into a long-time memory network to identify the deep state evolution characteristics of the power distribution equipment, so as to complete the identification of the long-time memory network parameters;
inputting the online measured equipment operation information into the trained deep neural network to complete online evaluation of the operation state of the distribution network equipment; also comprises constructing a stack-type depth automatic encoder network to clean original distribution equipment historical data, utilizing the depth automatic encoder to perform dimension reduction processing on the distribution equipment data information, completing the cleaning of data, reducing signal noise and eliminating redundant information,
inputting the historical data information of the power distribution equipment into the constructed neural network for training;
setting the sum of squares of the difference between the input data and the output result as a penalty function;
updating the weight parameters of the neural network by adopting a random gradient descent algorithm until the reconstruction of the historical operating data of the power distribution equipment is completed, and completing the cleaning treatment of dimension reduction and noise reduction of the data of the power distribution equipment;
also comprises the following steps of (1) preparing,
partitioning the cleaned time sequence state information of the distribution network equipment based on the sliding window method;
extracting device state evolution characteristics in each window;
storing the extracted state characteristics of the distribution network equipment in a matrix form, considering the initial 10% of data as a healthy state, setting a healthy label as 1, considering the final 10% of data as a failed state, and setting the healthy label as 0;
also comprises the following steps of (1) preparing,
inputting label data into a constructed support vector regression network, and taking the square sum of the difference values of the output value of the support vector regression network and the label value as a penalty function;
updating the weight parameters of the support vector regression network by adopting the random gradient descent algorithm to complete the parameter identification of the support vector regression network;
and inputting the rest 80% of data into the trained support vector regression network, wherein the obtained result is the health factor corresponding to the distribution network equipment.
2. The low-voltage distribution network equipment state evaluation method based on historical operation and maintenance information as claimed in claim 1, wherein the method comprises the following steps: the method comprises the steps of cleaning original historical operation data of the distribution network equipment based on a stack type depth automatic encoder network and calculating and analyzing a support vector regression network to obtain clean and low-dimensional data with health labels.
3. The low-voltage distribution network equipment state evaluation method based on historical operation and maintenance information, according to claim 2, is characterized in that: inputting the cleaned historical operation and maintenance information of the distribution network equipment into a long-term memory network for training, identifying deep state evolution characteristics of the distribution equipment, and completing identification of weight parameters in the long-term memory network.
4. The low-voltage distribution network equipment state evaluation method based on historical operation and maintenance information, according to claim 3, is characterized in that: also comprises the following steps of (1) preparing,
acquiring running state information of distribution network equipment in real time by adopting a sensor;
inputting the collected state information into the trained stack-type depth automatic encoder network for noise reduction and dimension reduction processing to obtain clean and low-dimensional running state data;
and inputting the processed running state data into the long-time memory network after training is completed, and finishing the evaluation of the running state of the distribution network equipment.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110463464.6A CN113269400B (en) | 2021-04-25 | 2021-04-25 | Low-voltage distribution network equipment state evaluation method based on historical operation and maintenance information |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110463464.6A CN113269400B (en) | 2021-04-25 | 2021-04-25 | Low-voltage distribution network equipment state evaluation method based on historical operation and maintenance information |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113269400A CN113269400A (en) | 2021-08-17 |
CN113269400B true CN113269400B (en) | 2022-12-06 |
Family
ID=77229553
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110463464.6A Active CN113269400B (en) | 2021-04-25 | 2021-04-25 | Low-voltage distribution network equipment state evaluation method based on historical operation and maintenance information |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113269400B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117040030B (en) * | 2023-10-10 | 2024-04-02 | 国网浙江宁波市鄞州区供电有限公司 | New energy consumption capacity risk management and control method and system |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107092894A (en) * | 2017-04-28 | 2017-08-25 | 孙恩泽 | A kind of motor behavior recognition methods based on LSTM models |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106908736B (en) * | 2017-03-17 | 2019-02-22 | 哈尔滨工业大学 | Lithium battery method for predicting residual useful life |
CN110781592B (en) * | 2019-10-25 | 2020-12-22 | 中国人民解放***箭军工程大学 | Method and system for predicting residual life of equipment |
CN112232404B (en) * | 2020-10-13 | 2023-12-22 | 中国铁路上海局集团有限公司南京供电段 | Reliability calculation method and system based on historical abnormality and operation and maintenance information of railway power supply equipment |
CN112231975A (en) * | 2020-10-13 | 2021-01-15 | 中国铁路上海局集团有限公司南京供电段 | Data modeling method and system based on reliability analysis of railway power supply equipment |
-
2021
- 2021-04-25 CN CN202110463464.6A patent/CN113269400B/en active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107092894A (en) * | 2017-04-28 | 2017-08-25 | 孙恩泽 | A kind of motor behavior recognition methods based on LSTM models |
Non-Patent Citations (1)
Title |
---|
基于北斗RDSS的核辐射监测应急通讯方法;王廷银等;《计算机***应用》;20191215(第12期);252-256 * |
Also Published As
Publication number | Publication date |
---|---|
CN113269400A (en) | 2021-08-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112232404B (en) | Reliability calculation method and system based on historical abnormality and operation and maintenance information of railway power supply equipment | |
CN111382542B (en) | Highway electromechanical device life prediction system facing full life cycle | |
CN101799674B (en) | Method for analyzing service state of numerical control equipment | |
CN110555230A (en) | rotary machine residual life prediction method based on integrated GMDH framework | |
CN111400371A (en) | Voltage correlation verification-based user variable relationship identification method | |
CN111325403B (en) | Method for predicting residual life of electromechanical equipment of highway tunnel | |
CN107944571B (en) | Method for predicting residual service life of power transformer | |
CN112231975A (en) | Data modeling method and system based on reliability analysis of railway power supply equipment | |
CN103154845A (en) | Machine learning for power grids | |
CN114723285B (en) | Power grid equipment safety evaluation prediction method | |
CN113723010A (en) | Bridge damage early warning method based on LSTM temperature-displacement correlation model | |
CN109471698B (en) | System and method for detecting abnormal behavior of virtual machine in cloud environment | |
CN112884089A (en) | Power transformer fault early warning system based on data mining | |
CN109598052B (en) | Intelligent ammeter life cycle prediction method and device based on correlation coefficient analysis | |
CN114035468B (en) | Method and system for predictively monitoring overhaul flow of fan based on XGBoost algorithm | |
CN113792939B (en) | Electric energy meter reliability prediction method and device based on mixed Weibull distribution | |
CN103207944A (en) | Electric power statistical index relevance analysis method | |
CN111337244A (en) | Method and device for monitoring and diagnosing faults of input shaft of fan gearbox | |
CN113269400B (en) | Low-voltage distribution network equipment state evaluation method based on historical operation and maintenance information | |
CN112070322A (en) | High-voltage cable line running state prediction method based on long-short term memory network | |
CN112803398A (en) | Load prediction method and system based on empirical mode decomposition and deep neural network | |
CN116541790A (en) | New energy vehicle health assessment method and device based on multi-feature fusion | |
CN105568732A (en) | Disc mill control method | |
CN116430164A (en) | Cable online monitoring method based on distributed temperature measurement and fault waveform analysis | |
CN116893293A (en) | Transient voltage stability evaluation method based on spatial attention correction neural network |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |