CN117668655A - Transformer fault identification method, device, equipment and medium - Google Patents
Transformer fault identification method, device, equipment and medium Download PDFInfo
- Publication number
- CN117668655A CN117668655A CN202311651889.5A CN202311651889A CN117668655A CN 117668655 A CN117668655 A CN 117668655A CN 202311651889 A CN202311651889 A CN 202311651889A CN 117668655 A CN117668655 A CN 117668655A
- Authority
- CN
- China
- Prior art keywords
- target
- population
- vector
- initial population
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 62
- 238000005457 optimization Methods 0.000 claims abstract description 63
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 51
- 241000283153 Cetacea Species 0.000 claims abstract description 46
- 238000012549 training Methods 0.000 claims abstract description 41
- 238000012545 processing Methods 0.000 claims abstract description 33
- 239000013598 vector Substances 0.000 claims description 124
- 238000012360 testing method Methods 0.000 claims description 21
- 238000004590 computer program Methods 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 13
- 230000007246 mechanism Effects 0.000 claims description 9
- 230000035772 mutation Effects 0.000 claims description 7
- 230000002431 foraging effect Effects 0.000 claims description 5
- 238000004891 communication Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 3
- 238000011056 performance test Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 230000008602 contraction Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000001172 regenerating effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- 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
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The embodiment of the application discloses a transformer fault identification method, device, equipment and medium. Wherein the method comprises the following steps: processing the initial population of the whale optimization algorithm through the cauchy reverse learning to obtain a reverse initial population; determining a target initial population according to the initial population and the reverse initial population; performing iterative optimization on the target initial population by adopting a whale optimization algorithm, outputting an optimal solution, and determining a target input weight and a target node bias according to the optimal solution; according to the target input weight and the target node bias, determining a transformer fault identification model to be trained, training the transformer fault identification model to be trained based on the training sample to obtain the transformer fault identification model, and processing the target transformer through the transformer fault identification model to obtain the fault type of the target transformer. According to the technical scheme, the fault type of the transformer is accurately identified, and meanwhile, the convergence speed of the model is increased.
Description
Technical Field
The present invention relates to the field of transformer technologies, and in particular, to a method, an apparatus, a device, and a medium for identifying a transformer fault.
Background
At present, a plurality of methods for diagnosing faults of the transformer exist, on one hand, workers can patrol the transformer, judge whether the transformer has faults according to past experience, and on the other hand, can identify dissolved gas in the transformer to obtain the fault type of the transformer.
However, the identification of the dissolved gas in the transformer has the defects of incomplete coding, excessively absolute coding boundary and the like, namely, the relation between the fault type of the transformer and the corresponding information of the dissolved gas is not clear enough, so that the accuracy of the identification result is poor.
Disclosure of Invention
The invention provides a method, a device, equipment and a medium for identifying faults of a transformer, which can obtain a transformer fault identification model through an improved optimization algorithm and accurately identify the fault type of the transformer through the transformer fault identification model.
According to an aspect of the present invention, there is provided a method for identifying a transformer fault, the method comprising:
processing the initial population of the whale optimization algorithm through the cauchy reverse learning to obtain a reverse initial population;
determining a target initial population according to the initial population and the reverse initial population;
performing iterative optimization on a target initial population by adopting a whale optimization algorithm, outputting an optimal solution, and determining a target input weight and a target node bias according to the optimal solution;
determining a transformer fault identification model to be trained according to the target input weight and the target node bias, training the transformer fault identification model to be trained based on the training sample to obtain a transformer fault identification model, and processing the target transformer through the transformer fault identification model to obtain the fault type of the target transformer; the training samples are historical dissolved gas data.
According to another aspect of the present invention, there is provided an identification device for transformer faults, including:
the reverse initial population determining module is used for processing the initial population of the whale optimization algorithm through cauchy reverse learning to obtain a reverse initial population;
the target initial population determining module is used for determining a target initial population according to the initial population and the reverse initial population;
the iterative optimization module is used for carrying out iterative optimization on the target initial population by adopting a whale optimization algorithm, outputting an optimal solution, and determining a target input weight and a target node bias according to the optimal solution;
the model training module is used for determining a transformer fault identification model to be trained according to the target input weight and the target node bias, training the transformer fault identification model to be trained based on the training sample to obtain a transformer fault identification model, and processing the target transformer through the transformer fault identification model to obtain the fault type of the target transformer; the training samples are historical dissolved gas data.
According to another aspect of the present invention, there is provided an electronic apparatus including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of identifying a transformer fault according to any one of the embodiments of the present invention.
According to another aspect of the present invention, there is provided a computer readable storage medium storing computer instructions for causing a processor to implement the method for identifying a transformer fault according to any one of the embodiments of the present invention when executed.
The technical scheme of the embodiment of the application comprises the following steps: processing the initial population of the whale optimization algorithm through the cauchy reverse learning to obtain a reverse initial population; determining a target initial population according to the initial population and the reverse initial population; performing iterative optimization on a target initial population by adopting a whale optimization algorithm, outputting an optimal solution, and determining a target input weight and a target node bias according to the optimal solution; determining a transformer fault identification model to be trained according to the target input weight and the target node bias, training the transformer fault identification model to be trained based on the training sample to obtain a transformer fault identification model, and processing the target transformer through the transformer fault identification model to obtain the fault type of the target transformer; the training samples are historical dissolved gas data. According to the technical scheme, the optimized whale optimization algorithm is used for obtaining the optimal target input weight and target node bias, a model capable of identifying the fault type of the transformer is built according to the optimal target input weight and target node bias, and the convergence speed of the model is accelerated while the fault type of the transformer is accurately identified.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments 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 identifying a transformer fault according to a first embodiment of the present application;
fig. 2 is a flowchart of a method for identifying a transformer fault according to a second embodiment of the present application;
FIG. 3 is a schematic diagram of a population update mechanism of a whale optimization algorithm according to a second embodiment of the present application;
fig. 4 is a schematic structural diagram of a transformer fault recognition device according to a third embodiment of the present application;
fig. 5 is a schematic structural diagram of an electronic device implementing a method for identifying a transformer fault according to an embodiment of the present application.
Detailed Description
In order to make the present invention better understood by those skilled in the art, the following description will be made in detail, with reference to the accompanying drawings, in which embodiments of the present invention are shown, and it is apparent that the described embodiments are only some, but not all, embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," "target," and the like in the description and claims of the present invention and in the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
Fig. 1 is a flowchart of a method for identifying a transformer fault according to an embodiment of the present application, where the method may be implemented by a device for identifying a transformer fault, where the device for identifying a transformer fault may be implemented in hardware and/or software, and the device for identifying a transformer fault may be configured in an electronic device with data processing capability. As shown in fig. 1, the method includes:
s110, processing the initial population of the whale optimization algorithm through cauchy reverse learning to obtain a reverse initial population.
The method comprises the steps of carrying out initial population processing through cauchy reverse learning, specifically, carrying out processing on individuals in the initial population, namely generating cauchy reverse points corresponding to the individuals in the initial population one by one, wherein the cauchy reverse points are points randomly generated between a middle point and a common reverse point. The individuals in the reverse initial population are in one-to-one correspondence with the individuals in the initial population, and the individuals in the reverse initial population can be specifically cauchy reverse points corresponding to the individuals in the initial population.
Specifically, after initial parameters of a whale optimization algorithm are set, an initial population of the whale optimization algorithm is generated, individuals in the initial population of the whale optimization algorithm are processed through cauchy reverse learning, reverse individuals corresponding to the individuals one by one are obtained, and a reverse initial population is determined according to the reverse individuals.
S120, determining a target initial population according to the initial population and the reverse initial population.
After the initial population and the reverse initial population are obtained, half of individuals with better fitness are selected to form the target initial population according to fitness values corresponding to individuals in the two populations.
In this embodiment, optionally, determining the target initial population according to the initial population and the reverse initial population includes: and comparing the fitness value corresponding to the target individuals in the initial population with the fitness value corresponding to the reverse individuals in the reverse initial population, and determining the individuals with smaller fitness values as the individuals in the target initial population.
Specifically, for a pair of individuals (in which a target individual is located in an initial population, a reverse individual is located in a reverse initial population, the reverse individual is a cauchy reverse point of the target individual), calculating an fitness value corresponding to the target individual, then calculating a fitness value corresponding to the reverse individual, comparing the two fitness values, and determining the individual with the smaller fitness value as the individual in the target initial population; according to the steps, traversing the other pairs of individuals to obtain a target initial population, wherein obviously, the number of the individuals in the target initial population is the same as that of the initial population and the individuals in the reverse initial population.
The method and the device are set in this way, so that the convergence of the population is quickened, and the iteration speed of the whale optimization algorithm is quickened.
S130, performing iterative optimization on the target initial population by adopting a whale optimization algorithm, outputting an optimal solution, and determining a target input weight and a target node bias according to the optimal solution.
The optimal solution is an individual with optimal fitness in the last generation population after the whale optimization algorithm is iterated. The input weight and the node bias are two very important quantities in the transformer fault identification model to be trained, and the target input weight and the target node bias are the optimized input weight and node bias.
Specifically, after the initial population is replaced by the target initial population, starting an iteration process of a whale optimization algorithm, obtaining a final population after the maximum iteration times are reached, calculating fitness values corresponding to all individuals in the final population, determining the individuals with the minimum fitness values as optimal solutions, and determining the optimal solutions as target input weights or target node offsets.
S140, determining a transformer fault recognition model to be trained according to the target input weight and the target node bias, training the transformer fault recognition model to be trained based on the training sample to obtain a transformer fault recognition model, and processing the target transformer through the transformer fault recognition model to obtain the fault type of the target transformer; the training samples are historical dissolved gas data.
The transformer fault recognition model to be trained can be any machine learning model for a classification algorithm, and the type of the model is not limited in the embodiment of the application. For example, the transformer fault recognition model to be trained may be an Extreme Learning Machine (ELM) model.
Specifically, after the target input weight and the target node bias are obtained, determining model parameters of a transformer fault identification model to be trained according to the target input weight and the target node bias, training the transformer fault identification model to be trained by adopting a training sample to obtain a trained transformer fault identification model, processing target dissolved gas data of the target transformer through the transformer fault identification model, and outputting the fault type of the target transformer. It should be noted that the training sample is historical dissolved gas data, and the historical dissolved gas data may be H 2 、CH 4 、C 2 H 6 、C 2 H 4 And C 2 H 2 The label of the training sample can be six types of fault-free, medium and low temperature overheat at 150-700 ℃, high temperature overheat at more than 700 ℃, low energy discharge, high energy discharge and partial discharge.
The technical scheme of the embodiment of the application comprises the following steps: processing the initial population of the whale optimization algorithm through the cauchy reverse learning to obtain a reverse initial population; determining a target initial population according to the initial population and the reverse initial population; performing iterative optimization on a target initial population by adopting a whale optimization algorithm, outputting an optimal solution, and determining a target input weight and a target node bias according to the optimal solution; determining a transformer fault identification model to be trained according to the target input weight and the target node bias, training the transformer fault identification model to be trained based on the training sample to obtain a transformer fault identification model, and processing the target transformer through the transformer fault identification model to obtain the fault type of the target transformer; the training samples are historical dissolved gas data. According to the technical scheme, the optimized whale optimization algorithm is used for obtaining the optimal target input weight and target node bias, a model capable of identifying the fault type of the transformer is built according to the optimal target input weight and target node bias, and the convergence speed of the model is accelerated while the fault type of the transformer is accurately identified.
Example two
Fig. 2 is a flowchart of a method for identifying a transformer fault according to a second embodiment of the present application, where the method is optimized based on the foregoing embodiments.
As shown in fig. 2, the method in the embodiment of the application specifically includes the following steps:
s210, processing the initial population of the whale optimization algorithm through cauchy reverse learning to obtain a reverse initial population.
S220, determining a target initial population according to the initial population and the reverse initial population.
S230, determining an individual with the smallest fitness value in the current population as a target vector according to each iteration process; the target initial population is the current population at the first iteration.
It should be noted that S230, S240, and S250 are applicable to each iteration process, that is, each iteration may perform S230, S240, and S250, and the specific contents of the three steps.
In the embodiment of the application, for the first iteration, the current population is the target initial population, and for the second and third … … iterations, the current population at each iteration is the updated population after the last iteration.
Specifically, the fitness value corresponding to each individual in the current population is calculated, and the individual with the smallest fitness value is determined as the target vector. It should be noted that, the fitness function required for calculating the fitness value may be any fitness function, and the fitness function is not limited in this embodiment of the present application.
S240, determining a variation vector according to the current population and a population updating mechanism of a whale optimization algorithm.
The population update mechanism of the whale optimization algorithm is shown in fig. 3.
Specifically, according to a population updating mechanism of a whale optimization algorithm, a variation vector is determined to be generated according to search foraging, a variation vector is determined to be generated according to shrinkage surrounding, or a variation vector is generated according to spiral updating positions, and then the variation vector is determined by adopting the following formula:
V i (t)＝X r1 (t)+F(X r2 (t)-X r3 (t))；
wherein r1+.r2+.r3, V i (t) is a variation vector, X r1 (t)、X r2 (t) and X r3 (t) is any three nonrepeating individual vectors in the current population, F is a variation scale factor, F is [0,1]]. Exemplary, X r1 And (t) is a target vector.
In this embodiment, optionally, determining the variance vector according to the current population and the population update mechanism of the whale optimization algorithm includes: generating a random factor of a whale optimization algorithm and a target coefficient vector; the random factor is greater than or equal to 0 and less than or equal to 1; the target coefficient vector is used for controlling balance between local search and global search; if the random factor is smaller than 0.5 and the modulus of the target coefficient vector is larger than 1, generating a variation vector according to search foraging; if the random factor is smaller than 0.5 and the modulus of the target coefficient vector is smaller than 1, generating a variation vector according to shrinkage enclosure; if the random factor is greater than 0.5, generating a variation vector according to the spiral updating position; the mutation vector is determined according to the target vector and two vectors which are different from the target vector in the current population.
Illustratively, a random factor p is generated, and a target coefficient vector a, if p is less than 0.5 and the modulus of the coefficient a is greater than 1, a variation vector is generated according to the search foraging; if p is smaller than 0.5 and the modulus of the coefficient A is smaller than 1, generating a variation vector according to contraction wrapping; if p is greater than 0.5, a variance vector is generated according to the spiral update position.
The definition of the coefficient A is: a=2a×r-a;
wherein r is [0,1]]The random vector in between, a is called the control parameter,t is the current generation selection times; max_iter is the maximum number of iterations. It can be seen that a decreases linearly from 2 to 0 with increasing iteration number t and thus the value of coefficient |a| decreases from 2 to 0.
Further, after the mutation vector is obtained, the validity of the mutation vector is checked, and if the mutation vector is valid, the subsequent steps are continued; whether or notThen change X r2 (t) and X r3 (t) regenerating a variation vector. When the validity of the variation vector is checked, specifically, the performance test is performed on the variation vector through a test function, and if the performance test is passed, the performance test is valid.
S250, determining individuals in the next generation population according to the target vector and the variation vector.
Specifically, the target vector and the variance vector are subjected to cross operation to obtain a test vector, the test vector and the target vector can be compared, and one of the test vector and the target vector is determined as an individual in the next generation population.
Further, the crossing mode may be a binomial crossing and an exponential crossing, and specifically, a random number between [0,1] is generated, and if the random number is less than or equal to the crossing probability, the test vector is a variation vector; otherwise, the test vector is the target vector. Wherein the crossover probability CR E [0,1].
In this embodiment, optionally, determining the individual in the next generation population according to the target vector and the variance vector includes: performing cross operation on the target vector and the variation vector to obtain a test vector; if the fitness value corresponding to the test vector is smaller than the fitness value corresponding to the target vector, determining the test vector as an individual in the next generation population; otherwise, the target vector is determined as an individual in the next generation population.
Specifically, after the test vector is obtained, the test vector is brought into an fitness function to obtain a fitness value corresponding to the test vector, the target vector is also brought into the fitness function to obtain a fitness value corresponding to the target vector, and if the fitness value corresponding to the test vector is smaller than the fitness value corresponding to the target vector, the test vector is determined to be an individual in the next generation population; otherwise, the target vector is determined as an individual in the next generation population.
In this embodiment, optionally, after determining the individuals in the next generation population according to the target vector and the variance vector, the method further includes: generating a random number between 0 and 1; and if the random number is smaller than or equal to the jump rate, updating the next generation population, and entering the next iteration based on the updated next generation population.
In the scheme, if the random number is smaller than or equal to the jump rate, updating the next generation population; otherwise, the next generation population is not processed.
Specifically, after the next generation population is obtained according to the steps, generating a random number between 0 and 1; if the random number is smaller than or equal to the jump rate, updating the next generation population, and entering the next iteration based on the updated next generation population; otherwise, the population is not required to be updated, and the next iteration is directly carried out according to the next generation population.
In this embodiment, optionally, updating the next generation population includes: processing the next generation population through cauchy reverse learning to obtain a reverse next generation population; comparing the fitness value corresponding to the target individuals in the next generation population with the fitness value corresponding to the reverse individuals in the reverse next generation population, and determining the individuals with smaller fitness values as the individuals in the updated next generation population.
And S260, after iteration is completed, determining an individual with the smallest fitness value in the last generation population as an optimal solution, and determining a target input weight and a target node bias according to the optimal solution.
S270, determining a transformer fault recognition model to be trained according to the target input weight and the target node bias, training the transformer fault recognition model to be trained based on the training sample to obtain a transformer fault recognition model, and processing the target transformer through the transformer fault recognition model to obtain the fault type of the target transformer; the training samples are historical dissolved gas data.
The technical scheme of the embodiment of the application comprises the following steps: processing the initial population of the whale optimization algorithm through the cauchy reverse learning to obtain a reverse initial population; determining a target initial population according to the initial population and the reverse initial population; for each iteration process, determining an individual with the smallest fitness value in the current population as a target vector; the target initial population is the current population at the first iteration; determining a variation vector according to a population updating mechanism of a current population and a whale optimization algorithm; determining individuals in the next generation population according to the target vector and the variation vector; after iteration is completed, determining an individual with the smallest fitness value in the population of the last generation as an optimal solution, and determining a target input weight and a target node bias according to the optimal solution; determining a transformer fault identification model to be trained according to the target input weight and the target node bias, training the transformer fault identification model to be trained based on the training sample to obtain a transformer fault identification model, and processing the target transformer through the transformer fault identification model to obtain the fault type of the target transformer; the training samples are historical dissolved gas data. According to the technical scheme, the algorithm can be quickly converged in early stage through the Cauchy reverse learning, namely the improved whale optimization algorithm can be quickly converged, the problem of local optimization is solved, the accuracy of diagnosis is improved, the diversity of whale optimization algorithm population is effectively maintained through the crossing and selecting strategy, the algorithm can jump out of local extremum in time, and the convergence accuracy of the algorithm is improved.
Example III
Fig. 4 is a schematic structural diagram of a transformer fault recognition device provided in the third embodiment of the present application, where the device may execute the transformer fault recognition method provided in any embodiment of the present invention, and the device has a functional module and beneficial effects corresponding to the execution method. As shown in fig. 4, the apparatus includes:
the reverse initial population determining module 310 is configured to process an initial population of the whale optimization algorithm through cauchy reverse learning to obtain a reverse initial population;
a target initial population determining module 320, configured to determine a target initial population according to the initial population and the reverse initial population;
the iterative optimization module 330 is configured to perform iterative optimization on the target initial population by using a whale optimization algorithm, output an optimal solution, and determine a target input weight and a target node bias according to the optimal solution;
the model training module 340 is configured to determine a transformer fault identification model to be trained according to a target input weight and a target node bias, and train the transformer fault identification model to be trained based on a training sample to obtain a transformer fault identification model, so as to process a target transformer through the transformer fault identification model to obtain a fault type of the target transformer; the training samples are historical dissolved gas data.
The technical scheme of the embodiment of the application comprises the following steps: the reverse initial population determining module 310 is configured to process an initial population of the whale optimization algorithm through cauchy reverse learning to obtain a reverse initial population; a target initial population determining module 320, configured to determine a target initial population according to the initial population and the reverse initial population; the iterative optimization module 330 is configured to perform iterative optimization on the target initial population by using a whale optimization algorithm, output an optimal solution, and determine a target input weight and a target node bias according to the optimal solution; the model training module 340 is configured to determine a transformer fault identification model to be trained according to a target input weight and a target node bias, and train the transformer fault identification model to be trained based on a training sample to obtain a transformer fault identification model, so as to process a target transformer through the transformer fault identification model to obtain a fault type of the target transformer; the training samples are historical dissolved gas data. According to the technical scheme, the optimized whale optimization algorithm is used for obtaining the optimal target input weight and target node bias, a model capable of identifying the fault type of the transformer is built according to the optimal target input weight and target node bias, and the convergence speed of the model is accelerated while the fault type of the transformer is accurately identified.
Optionally, the target initial population determination module 320 includes:
the target initial population determining unit is used for comparing the fitness value corresponding to the target individuals in the initial population with the fitness value corresponding to the reverse individuals in the reverse initial population, and determining the individuals with smaller fitness values as the individuals in the target initial population.
Optionally, the iterative optimization module 330 includes:
the target vector determining unit is used for determining an individual with the smallest fitness value in the current population as a target vector according to each iteration process; the target initial population is the current population at the first iteration;
the variation vector determining unit is used for determining a variation vector according to a population updating mechanism of the current population and a whale optimization algorithm;
the next generation population determining unit is used for determining individuals in the next generation population according to the target vector and the variation vector;
and the optimal solution determining unit is used for determining an individual with the smallest fitness value in the final generation population as an optimal solution after the iteration is completed.
Optionally, the mutation vector determining unit includes:
the random factor generation unit is used for generating random factors of a whale optimization algorithm and a target coefficient vector; the random factor is greater than or equal to 0 and less than or equal to 1; the target coefficient vector is used for controlling balance between local search and global search;
a variation vector determining subunit, configured to generate a variation vector according to the search foraging if the random factor is less than 0.5 and the modulus of the target coefficient vector is greater than 1;
if the random factor is smaller than 0.5 and the modulus of the target coefficient vector is smaller than 1, generating a variation vector according to shrinkage enclosure;
if the random factor is greater than 0.5, generating a variation vector according to the spiral updating position;
the mutation vector is determined according to the target vector and two vectors which are different from the target vector in the current population.
Optionally, the next generation population determining unit includes:
the test vector determining subunit is used for performing cross operation on the target vector and the variation vector to obtain a test vector;
the next generation population determining subunit is configured to determine the test vector as an individual in the next generation population if the fitness value corresponding to the test vector is smaller than the fitness value corresponding to the target vector;
otherwise, the target vector is determined as an individual in the next generation population.
Optionally, the apparatus further includes:
a random number generation unit for generating a random number between 0 and 1;
and the population updating unit is used for updating the next generation population if the random number is smaller than or equal to the jump rate, and entering the next iteration based on the updated next generation population.
Optionally, the population updating unit includes:
the reverse population determining subunit is used for processing the next generation population through cauchy reverse learning to obtain a reverse next generation population;
and the population updating subunit is used for comparing the fitness value corresponding to the target individual in the next generation population with the fitness value corresponding to the reverse individual in the reverse next generation population, and determining the individual with the smaller fitness value as the individual in the updated next generation population.
The transformer fault identification device provided by the embodiment of the application can execute the transformer fault identification method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
Example IV
Fig. 5 shows a schematic diagram of the structure of an electronic device 10 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 5, the electronic device 10 includes at least one processor 11, and a memory, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, etc., communicatively connected to the at least one processor 11, in which the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 may also be stored. The processor 11, the ROM 12 and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.
Various components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, etc.; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as the method of identifying transformer faults.
In some embodiments, the method of identifying transformer faults may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the above-described method of identifying a transformer fault may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the method of identifying a transformer fault in any other suitable way (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. A method for identifying a transformer fault, comprising:
processing the initial population of the whale optimization algorithm through the cauchy reverse learning to obtain a reverse initial population;
determining a target initial population according to the initial population and the reverse initial population;
performing iterative optimization on a target initial population by adopting a whale optimization algorithm, outputting an optimal solution, and determining a target input weight and a target node bias according to the optimal solution;
determining a transformer fault identification model to be trained according to the target input weight and the target node bias, training the transformer fault identification model to be trained based on the training sample to obtain a transformer fault identification model, and processing the target transformer through the transformer fault identification model to obtain the fault type of the target transformer; the training samples are historical dissolved gas data.
2. The method of claim 1, wherein determining a target initial population from the initial population and a reverse initial population comprises:
and comparing the fitness value corresponding to the target individuals in the initial population with the fitness value corresponding to the reverse individuals in the reverse initial population, and determining the individuals with smaller fitness values as the individuals in the target initial population.
3. The method of claim 1, wherein iteratively optimizing the target initial population using a whale optimization algorithm to output an optimal solution, comprising:
for each iteration process, determining an individual with the smallest fitness value in the current population as a target vector; the target initial population is the current population at the first iteration;
determining a variation vector according to a population updating mechanism of a current population and a whale optimization algorithm;
determining individuals in the next generation population according to the target vector and the variation vector;
after the iteration is completed, the individual with the smallest fitness value in the last generation population is determined as the optimal solution.
4. A method according to claim 3, wherein determining the variance vector based on the current population and a population update mechanism of a whale optimization algorithm comprises:
generating a random factor of a whale optimization algorithm and a target coefficient vector; the random factor is greater than or equal to 0 and less than or equal to 1; the target coefficient vector is used for controlling balance between local search and global search;
if the random factor is smaller than 0.5 and the modulus of the target coefficient vector is larger than 1, generating a variation vector according to search foraging;
if the random factor is smaller than 0.5 and the modulus of the target coefficient vector is smaller than 1, generating a variation vector according to shrinkage enclosure;
if the random factor is greater than 0.5, generating a variation vector according to the spiral updating position;
the mutation vector is determined according to the target vector and two vectors which are different from the target vector in the current population.
5. A method according to claim 3, wherein determining individuals in a next generation population from the target vector and the variance vector comprises:
performing cross operation on the target vector and the variation vector to obtain a test vector;
if the fitness value corresponding to the test vector is smaller than the fitness value corresponding to the target vector, determining the test vector as an individual in the next generation population;
otherwise, the target vector is determined as an individual in the next generation population.
6. A method according to claim 3, wherein after determining individuals in a next generation population based on the target vector and the variance vector, the method further comprises:
generating a random number between 0 and 1;
and if the random number is smaller than or equal to the jump rate, updating the next generation population, and entering the next iteration based on the updated next generation population.
7. The method of claim 6, wherein the next generation population is updated, comprising:
processing the next generation population through cauchy reverse learning to obtain a reverse next generation population;
comparing the fitness value corresponding to the target individuals in the next generation population with the fitness value corresponding to the reverse individuals in the reverse next generation population, and determining the individuals with smaller fitness values as the individuals in the updated next generation population.
8. A transformer fault identification device, comprising:
the reverse initial population determining module is used for processing the initial population of the whale optimization algorithm through cauchy reverse learning to obtain a reverse initial population;
the target initial population determining module is used for determining a target initial population according to the initial population and the reverse initial population;
the iterative optimization module is used for carrying out iterative optimization on the target initial population by adopting a whale optimization algorithm, outputting an optimal solution, and determining a target input weight and a target node bias according to the optimal solution;
the model training module is used for determining a transformer fault identification model to be trained according to the target input weight and the target node bias, training the transformer fault identification model to be trained based on the training sample to obtain a transformer fault identification model, and processing the target transformer through the transformer fault identification model to obtain the fault type of the target transformer; the training samples are historical dissolved gas data.
9. An electronic device, the electronic device comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of identifying a transformer fault of any one of claims 1-7.
10. A computer readable storage medium, characterized in that it stores computer instructions for causing a processor to implement the method for identifying a transformer fault according to any one of claims 1-7 when executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311651889.5A CN117668655A (en) | 2023-12-04 | 2023-12-04 | Transformer fault identification method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311651889.5A CN117668655A (en) | 2023-12-04 | 2023-12-04 | Transformer fault identification method, device, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117668655A true CN117668655A (en) | 2024-03-08 |
Family
ID=90082125
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311651889.5A Pending CN117668655A (en) | 2023-12-04 | 2023-12-04 | Transformer fault identification method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117668655A (en) |
-
2023
- 2023-12-04 CN CN202311651889.5A patent/CN117668655A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112487173B (en) | Man-machine conversation method, device and storage medium | |
| CN113239157B (en) | Method, device, equipment and storage medium for training conversation model | |
| CN112966744A (en) | Model training method, image processing method, device and electronic equipment | |
| CN115147687A (en) | Student model training method, device, equipment and storage medium | |
| CN112580733A (en) | Method, device and equipment for training classification model and storage medium | |
| CN115116559A (en) | Method, device, equipment and medium for determining and training atomic coordinates in amino acid | |
| CN114528387A (en) | Deep learning conversation strategy model construction method and system based on conversation flow bootstrap | |
| CN113657468A (en) | Pre-training model generation method and device, electronic equipment and storage medium | |
| CN113642727A (en) | Training method of neural network model and processing method and device of multimedia information | |
| CN116228301A (en) | Method, device, equipment and medium for determining target user | |
| CN114419327B (en) | Image detection method and training method and device of image detection model | |
| CN114120180B (en) | Time sequence nomination generation method, device, equipment and medium | |
| CN117668655A (en) | Transformer fault identification method, device, equipment and medium | |
| CN115665783A (en) | Abnormal index tracing method and device, electronic equipment and storage medium | |
| CN114610953A (en) | Data classification method, device, equipment and storage medium | |
| CN114611609A (en) | Graph network model node classification method, device, equipment and storage medium | |
| CN116737888B (en) | Training method of dialogue generation model and method and device for determining reply text | |
| CN115131453B (en) | Color filling model training, color filling method and device and electronic equipment | |
| CN115471717B (en) | Semi-supervised training and classifying method device, equipment, medium and product of model | |
| CN114241243B (en) | Training method and device for image classification model, electronic equipment and storage medium | |
| CN115131709B (en) | Video category prediction method, training method and device for video category prediction model | |
| CN117217777A (en) | Evaluation method, device, equipment and medium based on contrast learning | |
| CN116913407A (en) | Transformer fault identification method, device, equipment and medium | |
| CN116913406A (en) | Transformer fault identification method, device, equipment and medium | |
| CN116881857A (en) | Product recommendation method, device, equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |