CN113657623B - Power equipment state diagnosis effect determining method, device, terminal and storage medium - Google Patents
Power equipment state diagnosis effect determining method, device, terminal and storage medium Download PDFInfo
- Publication number
- CN113657623B CN113657623B CN202110791762.8A CN202110791762A CN113657623B CN 113657623 B CN113657623 B CN 113657623B CN 202110791762 A CN202110791762 A CN 202110791762A CN 113657623 B CN113657623 B CN 113657623B
- Authority
- CN
- China
- Prior art keywords
- power equipment
- data set
- equipment monitoring
- state
- training
- 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
- 238000003745 diagnosis Methods 0.000 title claims abstract description 66
- 230000000694 effects Effects 0.000 title claims abstract description 58
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000012544 monitoring process Methods 0.000 claims abstract description 174
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 31
- 238000011156 evaluation Methods 0.000 claims abstract description 9
- 238000012549 training Methods 0.000 claims description 89
- 238000013524 data verification Methods 0.000 claims description 24
- 238000004590 computer program Methods 0.000 claims description 21
- 238000012774 diagnostic algorithm Methods 0.000 claims description 14
- 230000015654 memory Effects 0.000 claims description 14
- 230000000875 corresponding effect Effects 0.000 claims description 9
- 230000002596 correlated effect Effects 0.000 claims description 3
- 230000008901 benefit Effects 0.000 abstract description 4
- 238000012795 verification Methods 0.000 description 7
- 238000009826 distribution Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000005540 biological transmission 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
- 238000010891 electric arc Methods 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 230000008485 antagonism Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000010200 validation analysis Methods 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000011208 chromatographic data Methods 0.000 description 1
- 238000004587 chromatography analysis Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Marketing (AREA)
- Molecular Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention relates to the technical field of power equipment state diagnosis, in particular to a method, a device, a terminal and a storage medium for determining the state diagnosis effect of power equipment, wherein the method uses an LSTM deep network to predict the future trend of a power equipment monitoring quantity data set, and comprises the future trend, and performs data capacity expansion through a GAN network to solve the problem of less effective state monitoring information of the power equipment; and inputting any state diagnosis algorithm of the power equipment to be evaluated by using the expanded data set, and comparing the diagnosis result with the expanded state label data set to evaluate the diagnosis algorithm. The method has the advantage of expanding the capacity of the effective state monitoring information of the power equipment, and can solve the problem of insufficient effective monitoring data quantity of the power equipment; in addition, the invention uses the expanded monitoring quantity data set comprising future trend to evaluate the effect of any state diagnosis system or algorithm, thereby effectively solving the problem of missing evaluation means of the power equipment state diagnosis system or algorithm.
Description
Technical Field
The present invention relates to the field of power equipment status diagnosis technologies, and in particular, to a method, an apparatus, a terminal, and a storage medium for determining a power equipment status diagnosis effect.
Background
The power equipment is one of the most valuable equipment in the power transmission and transformation system, and monitoring the characteristic parameters of the power equipment and diagnosing the state of the power equipment according to the characteristic parameters are of great significance for the reliable operation of the power transmission and transformation system.
However, most of the power equipment state monitoring data collected in the current engineering belongs to data in a normal state, so that the aging and failure processes of the power equipment state cannot be effectively reflected, and the effective information amount is small. The monitoring data are historical data or current data, only the historical state or current state of the power equipment can be reflected, and the future change trend of the monitoring quantity can not be obtained. In addition, since the status of the power equipment has an important meaning for the reliability of the power transmission and transformation system, a large number of power equipment status diagnosis systems or algorithms are proposed, but there is no effective method for evaluating and comparing the effects of various diagnosis systems or algorithms. In summary, the lack of effective status monitoring information of electrical devices and the lack of methods for evaluating status diagnostic effects have hampered technological advances in this field.
Based on this, there is a need for a method of expanding the capacity of the effective state monitoring information of the electrical equipment and evaluating the effect of any state diagnostic system or algorithm.
Disclosure of Invention
The embodiment of the invention provides a method, a device, a terminal and a storage medium for determining a state diagnosis effect of power equipment, which are used for solving the problem of inaccurate evaluation of the state diagnosis effect.
In a first aspect, an embodiment of the present invention provides a method for determining a diagnostic effect of a state of an electrical device, including: acquiring a first power equipment monitoring amount data set;
predicting the first power equipment monitoring amount data set by utilizing an LSTM depth network to obtain a second power equipment monitoring amount data set and a second state label data set, wherein the second power equipment monitoring amount data set corresponds to the second power equipment monitoring amount data set;
expanding the capacity of the second power equipment monitoring amount data set and the second state label data set by using a GAN network to obtain a third power equipment monitoring amount data set and a third state label data set;
and evaluating the diagnosis effect of the power equipment state diagnosis algorithm by using the third power equipment monitoring quantity data set and the third state label data set.
In one possible implementation manner, the predicting, by using the LSTM depth network, the first power device monitoring amount data set, to obtain a second power device monitoring amount data set and a second state label data set, where the second power device monitoring amount data set corresponds to the second power device monitoring amount data set, includes:
inputting the first power equipment monitoring amount data set and the first state label data set into an LSTM depth network to train the LSTM depth network to obtain a final LSTM depth network;
and predicting future trends of the first power equipment monitoring amount data set based on the final LSTM depth network to obtain a second power equipment monitoring amount data set and a second state label data set, wherein the second power equipment monitoring amount data set corresponds to the second power equipment monitoring amount data set.
In one possible implementation manner, the expanding the second power device monitoring amount data set and the second state label data set by using the GAN network to obtain a third power device monitoring amount data set and a third state label data set includes:
inputting the second power equipment monitoring quantity data set into the GAN network, and training a generator and a discriminator in the GAN network to obtain a final generator;
And expanding the capacity of the second power equipment monitoring amount data set and the second state label data set based on the final generator to obtain a third power equipment monitoring amount data set and a third state label data set.
In one possible implementation, the determining the diagnostic effect of the target power device status diagnostic algorithm based on the third power device monitoring amount data set and the third status tag data set includes:
inputting the third power equipment monitoring amount data set into the target power equipment state diagnosis algorithm to obtain a state diagnosis result;
and determining the diagnosis effect of the target power equipment state diagnosis algorithm according to the state diagnosis result and the third state label data set.
In one possible implementation manner, the determining the diagnostic effect of the target power equipment status diagnostic algorithm according to the status diagnostic result and the third status tag data set includes:
calculating a relative error from the condition diagnosis result, the third condition label dataset, and a first formula, the first formula:
wherein ,Ep Y' is the diagnosis result of the ith element of the third electric equipment monitoring quantity data set, y i For the i-th element of the third state label dataset, Q is the total number of third state label dataset elements;
the greater the relative error, the poorer the diagnostic effect of the power device condition diagnostic algorithm.
In one possible implementation manner, the inputting the first power device monitoring amount data set and the first state label data set into an LSTM depth network trains the LSTM depth network, and inputting the first power device monitoring amount data set and the first state label data set into the LSTM depth network trains the LSTM depth network to obtain a final LSTM depth network, which includes:
dividing the first power equipment monitoring amount data set into a power equipment monitoring amount data training set and a power equipment monitoring amount data verification set;
dividing the first state label data set into a state label data training set and a state label data verification set; the power equipment monitoring amount data training set corresponds to the state label data training set, and the power equipment monitoring amount data verification set corresponds to the state label data verification set;
using the random number as an initial parameter of the LSTM depth network;
Inputting the power equipment monitoring amount data training set and the state label data training set into an LSTM deep network for training;
inputting the monitoring quantity data verification set of the power equipment and the state label data verification set into an LSTM depth network, and calculating the relative error of the trained LSTM depth network;
if the relative error meets a preset condition, obtaining the final LSTM depth network;
and if the relative error does not meet the preset condition, executing the step of inputting the power equipment monitoring amount data training set and the state label data training set into an LSTM depth network to train the LSTM depth network.
In one possible implementation manner, the inputting the second power device monitoring amount data set into the GAN network, training a generator and a arbiter in the GAN network to obtain a final generator, includes:
inputting random noise into the generator to obtain a noise data set, wherein the noise data set is the same as the type of the second power equipment monitoring amount data set;
training a discriminator: inputting the data set output by the generator and the second power equipment monitoring amount data set into the discriminator, and training the discriminator;
Circularly executing the step of training the discriminator, so that the resolution of the discriminator on the second power equipment monitoring quantity data set reaches a first threshold value, and fixing parameters of the discriminator;
training generator step: inputting the second power equipment monitoring amount data set into the generator, and training the generator;
if the similarity between the training data set generated by the generator and the second power equipment monitoring quantity data set is greater than or equal to a second threshold value, using the generator obtained by training at the moment as the final generator; if the similarity between the training data set generated by the generator and the second power equipment monitoring amount data set is smaller than a second threshold value, returning to the training discriminator step; wherein the second threshold is greater than or equal to the first threshold.
In a second aspect, an embodiment of the present invention provides an apparatus for evaluating a diagnostic effect of a state of an electrical device, including:
the data acquisition module is used for acquiring a first power equipment monitoring quantity data set;
the data prediction module is used for predicting the first power equipment monitoring amount data set by utilizing an LSTM depth network to obtain a second power equipment monitoring amount data set and a second state label data set, wherein the second power equipment monitoring amount data set corresponds to the second power equipment monitoring amount data set;
The capacity expansion module is used for expanding capacity of the second power equipment monitoring amount data set and the second state label data set by utilizing a GAN network to obtain a third power equipment monitoring amount data set and a third state label data set; the method comprises the steps of,
and the diagnostic algorithm effect determining module is used for evaluating the diagnostic effect of the power equipment state diagnostic algorithm by using the third power equipment monitoring amount data set and the third state label data set.
In a third aspect, embodiments of the present invention provide a terminal comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the method according to the first aspect or any one of the possible implementations of the first aspect, when the computer program is executed.
In a fourth aspect, embodiments of the present invention provide a computer readable storage medium storing a computer program which, when executed by a processor, implements the steps of the method as described above in the first aspect or any one of the possible implementations of the first aspect.
Compared with the prior art, the embodiment of the invention has the beneficial effects that:
The embodiment of the invention discloses a method for determining the state diagnosis effect of electric equipment, which adopts a GAN-LSTM deep learning algorithm to predict and expand the future trend of the effective state monitoring information of the existing electric equipment, wherein the GAN mainly comprises a generator and a discriminator, and the purpose of the generator is to learn the potential distribution rule of real data and generate new data conforming to the hidden distribution rule; the purpose of the discriminator is to discriminate real data and generated data, the generator and the discriminator are mutually restricted, and the purpose of 'false spurious' is finally achieved through continuous training. And evaluating any power equipment state diagnosis system or algorithm through the expanded expansion database, and judging the diagnosis effect of any power equipment state diagnosis system or algorithm according to comparison of the known result and the evaluation result.
The method for determining the state diagnosis effect of the power equipment has the advantage of expanding the effective state monitoring information of the power equipment, and can solve the problem of insufficient effective monitoring data quantity of the power equipment; in addition, the invention uses the expanded monitoring quantity data set comprising future trend to evaluate the effect of any state diagnosis system or algorithm, thereby effectively solving the problem of missing evaluation means of the power equipment state diagnosis system or algorithm.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a method for determining a diagnostic effect of a power device state according to an embodiment of the present invention;
FIG. 2 is a flowchart of LSTM deep network training operations provided by an embodiment of the present invention;
fig. 3 is a flowchart of GAN network operation provided in an embodiment of the present invention;
fig. 4 is a functional block diagram of an electric power equipment state diagnosis effect evaluation apparatus according to an embodiment of the present invention;
fig. 5 is a functional block diagram of a terminal according to an embodiment of the present invention.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth such as the particular system architecture, techniques, etc., in order to provide a thorough understanding of the embodiments of the present invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the following description will be made with reference to the accompanying drawings.
Fig. 1 is a flowchart of a method for determining a diagnostic effect of a power device according to an embodiment of the present invention.
Referring to fig. 1, a flowchart of an implementation of a method for determining a diagnostic effect of a power device status according to an embodiment of the present invention is shown, and the details are as follows:
in step 101, a first power device monitoring amount data set is acquired.
In step 102, the first electric power equipment monitoring amount data set is predicted by using the LSTM depth network, and a second electric power equipment monitoring amount data set and a second state label data set are obtained, where the second electric power equipment monitoring amount data set corresponds to the second electric power equipment monitoring amount data set.
In some embodiments, step 102 may include:
acquiring a first state label data set corresponding to the first power equipment monitoring quantity data set, inputting the first power equipment monitoring quantity data set and the first state label data set into an LSTM depth network to train the LSTM depth network, and acquiring a final LSTM depth network;
and predicting future trends of the first power equipment monitoring amount data set based on the final LSTM depth network to obtain a second power equipment monitoring amount data set and a second state label data set, wherein the second power equipment monitoring amount data set corresponds to the second power equipment monitoring amount data set.
In some embodiments, the acquiring a first state label dataset corresponding to the first power device monitoring volume dataset, inputting the first power device monitoring volume dataset and the first state label dataset into an LSTM depth network, training the LSTM depth network, and obtaining a final LSTM depth network, includes:
dividing the first power equipment monitoring amount data set into a power equipment monitoring amount data training set and a power equipment monitoring amount data verification set;
dividing the first state label data set into a state label data training set and a state label data verification set; the power equipment monitoring amount data training set corresponds to the state label data training set, and the power equipment monitoring amount data verification set corresponds to the state label data verification set;
using the random number as an initial parameter of the LSTM depth network;
inputting the power equipment monitoring amount data training set and the state label data training set into an LSTM deep network for training;
inputting the monitoring quantity data verification set of the power equipment and the state label data verification set into an LSTM depth network, and calculating the relative error of the trained LSTM depth network;
If the relative error meets a preset condition, obtaining the final LSTM depth network;
and if the relative error does not meet the preset condition, executing the step of inputting the power equipment monitoring amount data training set and the state label data training set into an LSTM depth network to train the LSTM depth network.
LSTM (Generative Adversarial Network-Long Short-Term Memory) is a threshold RNN, and the LSTM network is ingenious in that the weight coefficient between the connections is designed by adding an input gate, a forgetting gate and an output gate, so that the LSTM network can accumulate Long-Term connection between nodes with longer distance, and Long-Term Memory of data is realized.
GAN (Generative Adversarial Networks, generated antagonism network) is a generated antagonism model, which is affected by game theory, and typically consists of a generator and a arbiter. The generator captures potential distributions of the real data and generates new data samples; the discriminator is a classifier that discriminates whether the input data is real data or a sample generated by the generator.
The method includes the steps of collecting and integrating M power equipment monitoring quantities obtained through monitoring within a certain time T and corresponding state labels to form a power equipment monitoring quantity data set X and a state label data set Y.
X＝(x1，x2，……，xT)＝(x 1 ，x 2 ，……，x M ) T Can be developed as follows: (subscript indicates different time instants and superscript indicates different monitored quantities)
Wherein xt= (xt) 1 ，xt 2 ，……，xt M ) The set of measurements at time t is for M monitored measurements. Y= (Y1, Y2, … …, yT) ∈r T 。
Inputting monitoring quantity in the monitoring quantity data set of the power equipment into an LSTM depth network and training, forming a final LSTM depth network after the training effect is achieved, and predicting future trend of the monitoring quantity by the final LSTM depth network to form a data set X' = (X1, X2, … …, xT+N) containing future trend monitoring quantity. Y' = (Y1, Y2, … …, yt+n), N being an integer greater than 1, means a data set comprising at least 1 time instant in the future.
As shown in fig. 2, the training operation for LSTM depth network is as follows:
dividing a power device monitor data set into a column vector training set input X with a time step of 10 1 Output Y 1 Verification set input X 2 Output Y 2 ；
Y1= (x 11, x12, … …, xT-l+9), y2= (xT-l+1, … …, xT), where L is the time of dividing the training set and the validation set, and is any integer greater than 10. X1 and Y1 form a training pair, and X2 and Y2 form a verification pair.
The LSTM depth network is trained using a training pair, and initial parameters of the LSTM depth network are generated from random numbers.
And after training for a plurality of times, verifying the trained LSTM depth network by using a verification set, calculating the relative error of Y2' and Y2 output by the trained LSTM depth network on the verification set, and judging whether the relative error reaches the set standard or not, if the set relative error is smaller than 10%.
wherein ,xi To verify the output Y2 element of the set, x' i The elements of Y2' are output on the validation set for the trained LSTM depth network.
If the relative error of the trained LSTM depth network reaches the standard, fixing parameters of the LSTM depth network, and performing future trend prediction on the whole power equipment monitoring data set to form a data set X' = (X1, X2, … …, xT+N) containing future trend monitoring data. Y' = (Y1, Y2, … …, yt+n), N being an integer greater than 1; if not, continuing to train the LSTM depth network until the accuracy reaches the standard.
In step 103, the second power equipment monitoring amount data set and the second state label data set are expanded by using the GAN network, so as to obtain a third power equipment monitoring amount data set and a third state label data set.
In some embodiments, the step 103 may include:
inputting the second power equipment monitoring quantity data set into the GAN network, and training a generator and a discriminator in the GAN network to obtain a final generator;
And expanding the capacity of the second power equipment monitoring amount data set and the second state label data set based on the final generator to obtain a third power equipment monitoring amount data set and a third state label data set.
In some embodiments, the inputting the second power device monitor data set into the GAN network, training a generator and a arbiter in the GAN network to obtain a final generator, includes:
inputting random noise into the generator to obtain a noise data set, wherein the noise data set is the same as the type of the second power equipment monitoring amount data set;
training a discriminator: inputting the data set output by the generator and the second power equipment monitoring amount data set into the discriminator, and training the discriminator;
circularly executing the step of training the discriminator, so that the resolution of the discriminator on the second power equipment monitoring quantity data set reaches a first threshold value, and fixing parameters of the discriminator;
training generator step: inputting the second power equipment monitoring amount data set into the generator, and training the generator;
if the similarity between the training data set generated by the generator and the second power equipment monitoring quantity data set is greater than or equal to a second threshold value, using the generator obtained by training at the moment as the final generator; if the similarity between the training data set generated by the generator and the second power equipment monitoring amount data set is smaller than a second threshold value, returning to the training discriminator step; wherein the second threshold is greater than or equal to the first threshold.
Illustratively, a data set containing future trend monitoring quantities is imported into a GAN network, a generator and a discriminator in the GAN network are trained, a final generator is formed after training effects are achieved, and the data set containing the future trend monitoring quantities is expanded to generate X' = (X1, X2, … …, xT+N), wherein xt= (xT) 1 ，xt 2 ，……，xt M*J ) That is, the X column vectors are expanded into m×j columns from M columns, the data set is expanded by a factor of J, J is an integer greater than 1, and the corresponding label is updated to form an expanded label data set Y "=j×y', that is, the label set is also expanded by a factor of J.
As shown in fig. 3, the training operation for the GAN network is as follows:
the generation of random numbers initializes a generator in the GAN network, the generator being comprised of a fully connected neural network.
Random noise z= (Z1, Z2, … …, zt+n) ∈r T+N Input to the generator, output the same data set as the data set containing the future trend monitored quantity:
the output data set Z 'of the generator is input into a discriminator together with the data set X' containing the future trend monitoring amount, and the discriminator is composed of a two-class fully connected neural network.
And a step of training a discriminator: the arbiter is trained until the output of the arbiter is 0 for Z 'and 1 for X'.
The arbiter parameters are fixed and the generator is trained so that the generator is as similar as possible to the generated monitor containing future trends.
And judging whether the accuracy of the discriminator is 0.5.
If the accuracy of the discriminator is 0.5, the discrimination of the generated object of the generator and the original input cannot be achieved, the generated object of the generator is completely similar to the generated data set containing the future trend monitoring quantity, the parameters of the generator are fixed, and the data set containing the future trend monitoring quantity is expanded.
If the accuracy of the arbiter is not 0.5, returning to the arbiter training step, and continuing to train the generator and the arbiter until the accuracy of the arbiter is 0.5
In step 104, the diagnostic effect of the power device status diagnostic algorithm is evaluated based on the third power device monitoring amount data set and the third status tag data set.
In some embodiments, step 104 may include:
inputting the third power equipment monitoring amount data set into the target power equipment state diagnosis algorithm to obtain a state diagnosis result;
and determining the diagnosis effect of the target power equipment state diagnosis algorithm according to the state diagnosis result and the third state label data set.
In some embodiments, the determining the diagnostic effect of the target power device status diagnostic algorithm according to the status diagnostic result and the third status tag data set includes:
calculating a relative error from the condition diagnosis result, the third condition label dataset, and a first formula, the first formula:
wherein ,Ep Is the relative error, y' i Monitoring the diagnostic result of the ith element of the quantity data set for the third power equipment, y i For the i-th element of the third state label dataset, Q is the total number of third state label dataset elements; based on the above steps, it can be seen that:
Q＝J*(T+N)
and determining the diagnosis effect of the target power equipment state diagnosis algorithm according to the relative error, wherein the relative error is positively correlated with the diagnosis effect of the target power equipment state diagnosis algorithm, and the greater the relative error is, the worse the diagnosis effect of the target power equipment state diagnosis algorithm is.
The following describes in detail the embodiments of the present invention, and the present embodiment is implemented on the premise of the technical solution of the present invention, and a detailed implementation manner and a specific operation procedure are given, but the protection scope of the present invention is not limited to the following embodiments.
According to the embodiment, oil chromatographic monitoring data of the 500kV voltage class transformer are arranged to form 1000 transformer oil chromatographic data sets and three state label data sets of partial discharge, overheat and arc discharge. 800 pieces of data are randomly selected to form a training set, and the remaining 200 pieces of data form a verification set.
Inputting the oil chromatogram data in the data set into an LSTM depth network, training, forming a final LSTM depth network after accuracy verification, and predicting the future 3-day trend of the oil chromatogram to form an oil chromatogram data set containing the future trend monitoring quantity.
Importing a data set containing future trend oil chromatograms into a GAN network, training a generator and a discriminator in the GAN network, forming a final generator after accuracy verification, expanding the data set containing the future trend oil chromatograms to 100000, updating corresponding labels, and forming an expanded partial discharge, overheat and arc discharge label data set.
The expanded oil chromatography data is input into a three-ratio diagnosis algorithm to be evaluated, the output state diagnosis result is compared with the label data set of the partial discharge, overheat and arc discharge states after the expansion, and the diagnosis accuracy of the calculation diagnosis algorithm is 0.8, so that the traditional three-ratio method has certain accuracy.
The embodiment of the invention discloses a method for determining the state diagnosis effect of electric equipment, which adopts a GAN-LSTM deep learning algorithm to predict and expand the future trend of the effective state monitoring information of the existing electric equipment, wherein the GAN mainly comprises a generator and a discriminator, and the purpose of the generator is to learn the potential distribution rule of real data and generate new data conforming to the hidden distribution rule; the purpose of the discriminator is to discriminate real data and generated data, the generator and the discriminator are mutually restricted, and the purpose of 'false spurious' is finally achieved through continuous training. And evaluating any power equipment state diagnosis system or algorithm through the expanded expansion database, and judging the diagnosis effect of any power equipment state diagnosis system or algorithm according to comparison of the known result and the evaluation result.
The method for determining the state diagnosis effect of the power equipment has the advantage of expanding the effective state monitoring information of the power equipment, and can solve the problem of insufficient effective monitoring data quantity of the power equipment; in addition, the invention uses the expanded monitoring quantity data set comprising future trend to evaluate the effect of any state diagnosis system or algorithm, thereby effectively solving the problem of missing evaluation means of the power equipment state diagnosis system or algorithm.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present invention.
The following are device embodiments of the invention, for details not described in detail therein, reference may be made to the corresponding method embodiments described above.
Fig. 4 is a functional block diagram of an electric power equipment state diagnosis effect evaluation apparatus according to an embodiment of the present invention, and for convenience of explanation, only a part related to the embodiment of the present invention is shown, and the details are as follows:
as shown in fig. 4, an apparatus for evaluating a diagnostic effect of a power equipment state includes a data acquisition module 401, a data prediction module 402, a capacity expansion module 403, and a diagnostic algorithm effect determination module 404.
The data acquisition module 401 is configured to acquire a first power device monitoring amount data set.
The data prediction module 402 is configured to predict the first power device monitoring amount data set by using an LSTM depth network, to obtain a second power device monitoring amount data set and a second status tag data set, where the second power device monitoring amount data set corresponds to the second power device monitoring amount data set.
And the capacity expansion module 403 is configured to utilize a GAN network to expand the second power equipment monitoring amount data set and the second state label data set to obtain a third power equipment monitoring amount data set and a third state label data set.
A diagnostic algorithm effect determination module 404 configured to evaluate a diagnostic effect of a power device status diagnostic algorithm using the third power device monitoring amount data set and the third status tag data set.
Fig. 5 is a functional block diagram of a terminal according to an embodiment of the present invention. As shown in fig. 5, the terminal 5 of this embodiment includes: a processor 50, a memory 51 and a computer program 52 stored in said memory 51 and executable on said processor 50. The processor 50 implements the steps of the above-described respective power device state diagnostic effect determination methods and power device state diagnostic effect determination method embodiments, such as steps 101 to 104 shown in fig. 1, when executing the computer program 52. Alternatively, the processor 50 may perform the functions of the modules/units in the above-described embodiments of the apparatus, such as the functions of the modules/units 401 to 404 shown in fig. 4, when executing the computer program 52.
By way of example, the computer program 52 may be partitioned into one or more modules/units that are stored in the memory 51 and executed by the processor 50 to complete the present invention. The one or more modules/units may be a series of computer program instruction segments capable of performing the specified functions describing the execution of the computer program 52 in the terminal 5. For example, the computer program 52 may be split into modules/units 401 to 404 shown in fig. 4.
The terminal 5 may be a computing device such as a desktop computer, a notebook computer, a palm computer, a cloud server, etc. The terminal 5 may include, but is not limited to, a processor 50, a memory 51. It will be appreciated by those skilled in the art that fig. 5 is merely an example of the terminal 5 and is not limiting of the terminal 5, and may include more or fewer components than shown, or may combine some components, or different components, e.g., the terminal may further include input and output devices, network access devices, buses, etc.
The processor 50 may be a central processing unit (Central Processing Unit, CPU), other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field-programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The storage 51 may be an internal storage unit of the terminal 5, such as a hard disk or a memory of the terminal 5. The memory 51 may be an external storage device of the terminal 5, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the terminal 5. Further, the memory 51 may also include both an internal storage unit and an external storage device of the terminal 5. The memory 51 is used for storing the computer program as well as other programs and data required by the terminal. The memory 51 may also be used to temporarily store data that has been output or is to be output.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit. In addition, the specific names of the functional units and modules are only for distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working process of the units and modules in the above system may refer to the corresponding process in the foregoing method embodiment, and will not be described herein again.
In the foregoing embodiments, the descriptions of the embodiments are focused on, and the details or descriptions of other embodiments may be referred to for those parts of an embodiment that are not described in detail or are described in detail.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps described in connection with the embodiments disclosed herein can be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus/terminal and method may be implemented in other manners. For example, the apparatus/terminal embodiments described above are merely illustrative, e.g., the division of the modules or units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection via interfaces, devices or units, which may be in electrical, mechanical or other forms.
The units described as separate units may or may not be physically separate, and units shown 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 may be selected according to actual needs to achieve the purpose of the embodiment.
In addition, each functional unit in each embodiment of the present invention may be integrated in one processing unit, each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated modules/units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the present invention may implement all or part of the flow of the method of the above embodiment, or may be implemented by instructing related hardware by a computer program, where the computer program may be stored in a computer readable storage medium, and the computer program may implement the steps of the method for determining the state diagnostic effect of each electrical device and the method for determining the state diagnostic effect of each electrical device when executed by a processor. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth. It should be noted that the computer readable medium may include content that is subject to appropriate increases and decreases as required by jurisdictions in which such content is subject to legislation and patent practice, such as in certain jurisdictions in which such content is not included as electrical carrier signals and telecommunication signals.
The above embodiments are only for illustrating the technical solution of the present invention, and are not limited thereto; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and they should be included in the protection scope of the present invention.
Claims (6)
1. A method for determining a diagnostic effect of a state of an electrical device, comprising:
acquiring a first power equipment monitoring amount data set and a first state label data set corresponding to the first power equipment monitoring amount data set;
dividing the first power equipment monitoring amount data set into a power equipment monitoring amount data training set and a power equipment monitoring amount data verification set;
dividing the first state label data set into a state label data training set and a state label data verification set; the power equipment monitoring amount data training set corresponds to the state label data training set, and the power equipment monitoring amount data verification set corresponds to the state label data verification set;
Inputting the power equipment monitoring amount data training set and the state label data training set into an LSTM deep network, and training the LSTM deep network;
inputting the monitoring quantity data verification set of the power equipment and the state label data verification set into an LSTM depth network, and calculating the relative error of the trained LSTM depth network;
if the relative error meets a preset condition, a final LSTM depth network is obtained;
if the relative error does not meet the preset condition, executing the step of inputting the power equipment monitoring amount data training set and the state label data training set into an LSTM depth network and training the LSTM depth network;
predicting future trends of the first power equipment monitoring amount data set based on the final LSTM depth network to obtain a second power equipment monitoring amount data set and a second state label data set, wherein the second power equipment monitoring amount data set corresponds to the second state label data set;
expanding the capacity of the second power equipment monitoring amount data set and the second state label data set by using a GAN network to obtain a third power equipment monitoring amount data set and a third state label data set;
Inputting the third power equipment monitoring amount data set into a target power equipment state diagnosis algorithm to obtain a state diagnosis result;
calculating a relative error from the condition diagnosis result, the third condition label dataset, and a first formula, the first formula:
wherein ,for relative error->Monitoring a quantity dataset for the third power deviceiDiagnosis of element->Is the third state label data setiThe element, Q, is the total number of third state tag dataset elements;
determining a diagnosis effect of the target power equipment state diagnosis algorithm according to the relative error; wherein the relative error is positively correlated with a diagnostic effect of the target power device status diagnostic algorithm.
2. The method for determining a diagnostic effect of a power device status according to claim 1, wherein the expanding the second power device monitoring amount data set and the second status tag data set by using the GAN network to obtain a third power device monitoring amount data set and a third status tag data set, comprises:
inputting the second power equipment monitoring quantity data set into the GAN network, and training a generator and a discriminator in the GAN network to obtain a final generator;
And expanding the capacity of the second power equipment monitoring amount data set and the second state label data set based on the final generator to obtain the third power equipment monitoring amount data set and the third state label data set.
3. The method for determining the diagnostic effect of the power equipment state according to claim 2, wherein inputting the second power equipment monitoring amount data set into the GAN network trains a generator and a discriminator in the GAN network to obtain a final generator, comprising:
inputting random noise into the generator to obtain a noise data set, wherein the noise data set is the same as the type of the second power equipment monitoring amount data set;
training a discriminator: inputting the data set output by the generator and the second power equipment monitoring amount data set into the discriminator, and training the discriminator;
circularly executing the step of training the discriminator, so that the resolution of the discriminator on the second power equipment monitoring quantity data set reaches a first threshold value, and fixing parameters of the discriminator;
training generator step: inputting the second power equipment monitoring amount data set into the generator, and training the generator;
If the similarity between the training data set generated by the generator and the second power equipment monitoring quantity data set is greater than or equal to a second threshold value, using the generator obtained by training at the moment as the final generator; if the similarity between the training data set generated by the generator and the second power equipment monitoring amount data set is smaller than a second threshold value, returning to the training discriminator step; wherein the second threshold is greater than or equal to the first threshold.
4. An electrical equipment state diagnostic effect evaluation apparatus for realizing the electrical equipment state diagnostic effect determination method according to any one of claims 1 to 3, comprising:
the data acquisition module is used for acquiring a first power equipment monitoring quantity data set;
the data prediction module is used for acquiring a first state label data set corresponding to the first power equipment monitoring amount data set and dividing the first power equipment monitoring amount data set into a power equipment monitoring amount data training set and a power equipment monitoring amount data verification set; dividing the first state label data set into a state label data training set and a state label data verification set; the power equipment monitoring amount data training set corresponds to the state label data training set, and the power equipment monitoring amount data verification set corresponds to the state label data verification set; inputting the power equipment monitoring amount data training set and the state label data training set into an LSTM deep network, and training the LSTM deep network; inputting the monitoring quantity data verification set of the power equipment and the state label data verification set into an LSTM depth network, and calculating the relative error of the trained LSTM depth network; if the relative error meets a preset condition, a final LSTM depth network is obtained; if the relative error does not meet the preset condition, executing the step of inputting the power equipment monitoring amount data training set and the state label data training set into an LSTM depth network and training the LSTM depth network; predicting future trends of the first power equipment monitoring amount data set based on the final LSTM depth network to obtain a second power equipment monitoring amount data set and a second state label data set, wherein the second power equipment monitoring amount data set corresponds to the second state label data set;
The capacity expansion module is used for expanding capacity of the second power equipment monitoring amount data set and the second state label data set by utilizing a GAN network to obtain a third power equipment monitoring amount data set and a third state label data set; the method comprises the steps of,
the diagnostic algorithm effect determining module is used for inputting the third power equipment monitoring amount data set into a target power equipment state diagnostic algorithm to obtain a state diagnostic result; calculating a relative error from the condition diagnosis result, the third condition label dataset, and a first formula, the first formula:
wherein ,for relative error->Monitoring a quantity dataset for the third power deviceiDiagnosis of element->Is the third state label data setiThe element, Q, is the total number of third state tag dataset elements; determining a diagnosis effect of the target power equipment state diagnosis algorithm according to the relative error; wherein the relative error is positively correlated with a diagnostic effect of the target power device status diagnostic algorithm.
5. A terminal comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of the preceding claims 1 to 3 when the computer program is executed.
6. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the method according to any of the preceding claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110791762.8A CN113657623B (en) | 2021-07-13 | 2021-07-13 | Power equipment state diagnosis effect determining method, device, terminal and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110791762.8A CN113657623B (en) | 2021-07-13 | 2021-07-13 | Power equipment state diagnosis effect determining method, device, terminal and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113657623A CN113657623A (en) | 2021-11-16 |
| CN113657623B true CN113657623B (en) | 2023-09-29 |
Family
ID=78478029
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110791762.8A Active CN113657623B (en) | 2021-07-13 | 2021-07-13 | Power equipment state diagnosis effect determining method, device, terminal and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113657623B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108170994A (en) * | 2018-01-29 | 2018-06-15 | 河海大学 | A kind of oil-immersed electric reactor method for diagnosing faults based on two-way depth network |
| CN109031014A (en) * | 2017-12-28 | 2018-12-18 | 国网湖北省电力公司宜昌供电公司 | A kind of transformer synthesis reliability assessment and prediction technique based on operation data |
| CN110501585A (en) * | 2019-07-12 | 2019-11-26 | 武汉大学 | A kind of Diagnosis Method of Transformer Faults based on Bi-LSTM and dissolved gas analysis |
| CN110503187A (en) * | 2019-07-26 | 2019-11-26 | 江苏大学 | A kind of implementation method of the generation confrontation network model generated for functional magnetic resonance imaging data |
| CN110598851A (en) * | 2019-08-29 | 2019-12-20 | 北京航空航天大学合肥创新研究院 | Time series data abnormity detection method fusing LSTM and GAN |
| CN111709577A (en) * | 2020-06-17 | 2020-09-25 | 上海海事大学 | RUL prediction method based on long-range correlation GAN-LSTM |
| CN111914705A (en) * | 2020-07-20 | 2020-11-10 | 华中科技大学 | Signal generation method and device for improving health state evaluation accuracy of reactor |
| CN111930728A (en) * | 2020-06-30 | 2020-11-13 | 广州洪森科技有限公司 | Method and system for predicting characteristic parameters and fault rate of equipment |
| CN112052874A (en) * | 2020-07-31 | 2020-12-08 | 山东大学 | Physiological data classification method and system based on generation countermeasure network |
| CN112465184A (en) * | 2020-10-21 | 2021-03-09 | 广西大学 | Cloud energy storage system control method of small-sample generation type counterstudy network |
| CN112581719A (en) * | 2020-11-05 | 2021-03-30 | 清华大学 | Semiconductor packaging process early warning method and device based on time sequence generation countermeasure network |
| CN112699960A (en) * | 2021-01-11 | 2021-04-23 | 华侨大学 | Semi-supervised classification method and equipment based on deep learning and storage medium |
| KR102266838B1 (en) * | 2020-08-28 | 2021-06-18 | 대한민국 | Monitoring technique for leaching water of burial sites using field sensors and machine learning |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110426415A (en) * | 2019-07-15 | 2019-11-08 | 武汉大学 | Based on thermal fault detection method inside depth convolutional neural networks and the oil-immersed transformer of image segmentation |
-
2021
- 2021-07-13 CN CN202110791762.8A patent/CN113657623B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109031014A (en) * | 2017-12-28 | 2018-12-18 | 国网湖北省电力公司宜昌供电公司 | A kind of transformer synthesis reliability assessment and prediction technique based on operation data |
| CN108170994A (en) * | 2018-01-29 | 2018-06-15 | 河海大学 | A kind of oil-immersed electric reactor method for diagnosing faults based on two-way depth network |
| CN110501585A (en) * | 2019-07-12 | 2019-11-26 | 武汉大学 | A kind of Diagnosis Method of Transformer Faults based on Bi-LSTM and dissolved gas analysis |
| CN110503187A (en) * | 2019-07-26 | 2019-11-26 | 江苏大学 | A kind of implementation method of the generation confrontation network model generated for functional magnetic resonance imaging data |
| CN110598851A (en) * | 2019-08-29 | 2019-12-20 | 北京航空航天大学合肥创新研究院 | Time series data abnormity detection method fusing LSTM and GAN |
| CN111709577A (en) * | 2020-06-17 | 2020-09-25 | 上海海事大学 | RUL prediction method based on long-range correlation GAN-LSTM |
| CN111930728A (en) * | 2020-06-30 | 2020-11-13 | 广州洪森科技有限公司 | Method and system for predicting characteristic parameters and fault rate of equipment |
| CN111914705A (en) * | 2020-07-20 | 2020-11-10 | 华中科技大学 | Signal generation method and device for improving health state evaluation accuracy of reactor |
| CN112052874A (en) * | 2020-07-31 | 2020-12-08 | 山东大学 | Physiological data classification method and system based on generation countermeasure network |
| KR102266838B1 (en) * | 2020-08-28 | 2021-06-18 | 대한민국 | Monitoring technique for leaching water of burial sites using field sensors and machine learning |
| CN112465184A (en) * | 2020-10-21 | 2021-03-09 | 广西大学 | Cloud energy storage system control method of small-sample generation type counterstudy network |
| CN112581719A (en) * | 2020-11-05 | 2021-03-30 | 清华大学 | Semiconductor packaging process early warning method and device based on time sequence generation countermeasure network |
| CN112699960A (en) * | 2021-01-11 | 2021-04-23 | 华侨大学 | Semi-supervised classification method and equipment based on deep learning and storage medium |
Non-Patent Citations (3)
| Title |
|---|
| 基于生成对抗网络和深度残差神经网络的变电站异物检测;孙旭日;李延真;彭博;李晓悦;周超群;;电网与清洁能源(第09期);68-75 * |
| 数据匮乏场景下采用生成对抗网络的 空间负荷预测方法;肖白等;中国电机工程学报;第40卷(第24期);7990-8001 * |
| 数据驱动的人工智能技术在电力设备状态分析中的研究与应用;唐文虎;牛哲文;赵柏宁;季天瑶;李梦诗;吴青华;;高电压技术(第09期);2985-2999 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113657623A (en) | 2021-11-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wen et al. | Degradation modeling and RUL prediction using Wiener process subject to multiple change points and unit heterogeneity | |
| CN108596616B (en) | User data authenticity analysis method and device, storage medium and electronic equipment | |
| CN114297036B (en) | Data processing method, device, electronic equipment and readable storage medium | |
| CN111709756A (en) | Method and device for identifying suspicious communities, storage medium and computer equipment | |
| Park et al. | Missing-insensitive short-term load forecasting leveraging autoencoder and LSTM | |
| Ayala Solares et al. | Nonlinear model structure detection and parameter estimation using a novel bagging method based on distance correlation metric | |
| Wen et al. | Degradation assessment for the ball screw with variational autoencoder and kernel density estimation | |
| Dong et al. | Multi‐task learning method for classification of multiple power quality disturbances | |
| CN109783381B (en) | Test data generation method, device and system | |
| CN114418189A (en) | Water quality grade prediction method, system, terminal device and storage medium | |
| Zhang et al. | SOH estimation and RUL prediction of lithium batteries based on multidomain feature fusion and CatBoost model | |
| CN111325255B (en) | Specific crowd delineating method and device, electronic equipment and storage medium | |
| CN113657623B (en) | Power equipment state diagnosis effect determining method, device, terminal and storage medium | |
| CN110348581B (en) | User feature optimizing method, device, medium and electronic equipment in user feature group | |
| Dawood et al. | Power quality disturbance classification based on efficient adaptive Arrhenius artificial bee colony feature selection | |
| CN108491559A (en) | A kind of time series method for detecting abnormality based on normalized mutual information estimation | |
| CN115170304B (en) | Method and device for extracting risk feature description | |
| Li et al. | Reliability assessment based on time waveform characteristics with small sample: A practice inspired by few-shot learnings in metric space | |
| CN116090353A (en) | Product remaining life prediction method and device, electronic equipment and storage medium | |
| CN111091099A (en) | Scene recognition model construction method, scene recognition method and device | |
| CN115047262A (en) | General equipment abnormal state identification method based on power quality data | |
| Lijun et al. | An intuitionistic calculus to complex abnormal event recognition on data streams | |
| CN115423159A (en) | Photovoltaic power generation prediction method and device and terminal equipment | |
| CN113822371A (en) | Training packet model, and method and device for grouping time sequence data | |
| CN112529303A (en) | Risk prediction method, device, equipment and storage medium based on fuzzy decision |
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 |