CVT operation error evaluation method and device, electronic equipment and storage medium

Abstract

The invention relates to a CVT operation error evaluation method and device, electronic equipment and a storage medium, and belongs to the technical field of power monitoring, and the CVT operation error evaluation method comprises the steps: determining an error evaluation index of a target CVT based on the real-time secondary voltage data of the target CVT; inputting the error evaluation index of the target CVT into an error evaluation model, and taking the output of the error evaluation model as the operation error evaluation result of the target CVT; wherein the error evaluation model performs error evaluation based on the SCN network, and the bias and the input weight of the hidden layer node of the SCN network are configured based on normal distribution. According to the method, the error evaluation accuracy is ensured, the complexity of an error evaluation model is reduced, and the iteration speed of the model is improved.

Description

Technical Field

[0001] The present invention relates to the field of power monitoring technology, and in particular to a CVT operation error evaluation method, device, electronic equipment and storage medium, which are specifically used for operation error evaluation of a capacitive voltage transformer. Background Art

[0002] Capacitor Voltage Transformer (CVT) is a measuring device that converts high voltage into low voltage signal. Affected by factors such as operating time and environment, the error performance of some CVTs is not stable enough during long-term operation, which directly leads to inaccurate electricity measurement. At present, our company and system units mainly use the periodic calibration method to calibrate CVTs with a power outage every 4 years using high-grade standard voltage transformers. However, due to the difficulty in coordinating power outages at substations and the huge workload of calibration, it is very difficult to ensure that all transformers are calibrated on schedule in actual work, resulting in the difficulty of timely detection of out-of-tolerance CVTs in operation. Once the CVT is out of tolerance, it is very easy to cause trade disputes because it is difficult to define the actual amount of electricity.

[0003] Therefore, how to evaluate the online operation error of CVT in real time without power outage has become a technical problem that needs to be solved urgently. Summary of the invention

[0004] In view of this, it is necessary to provide a CVT operation error evaluation method, device, electronic device and storage medium to solve the current problem that it is difficult to evaluate the online operation error of the CVT in real time without power outage.

[0005] In order to solve the above problems, the present invention provides a CVT operation error evaluation method, comprising:

[0006] Determining an error evaluation index of the target CVT based on real-time secondary voltage data of the target CVT;

[0007] Inputting the error evaluation index of the target CVT into an error evaluation model, and using the output of the error evaluation model as an operation error evaluation result of the target CVT;

[0008] The error assessment model is based on the SCN network for error assessment, and the bias and input weights of the hidden layer nodes of the SCN network are configured based on a normal distribution.

[0009] In a possible implementation, determining the error evaluation index of the target CVT based on the real-time secondary voltage data of the target CVT includes:

[0010] Determining a first evaluation index based on information components at all scales of the real-time secondary voltage data of the target CVT after empirical mode decomposition;

[0011] Determining a second evaluation index based on the real-time secondary voltage data of the target CVT and the rated voltage data of the target CVT;

[0012] determining a third evaluation index based on the amplitude of the three-phase voltage corresponding to the real-time secondary voltage data of the target CVT;

[0013] Based on the first evaluation index, the second evaluation index, and the third evaluation index, an error evaluation index of the target CVT is determined.

[0014] In a possible implementation, determining the error evaluation index of the target CVT based on the first evaluation index, the second evaluation index, and the third evaluation index includes:

[0015] The first evaluation index, the second evaluation index and the third evaluation index are integrated based on the FPN algorithm to obtain an error evaluation index of the target CVT.

[0016] In a possible implementation, the bias of each hidden layer node of the SCN network is randomly generated in a first normal distribution;

[0017] The input weight of each hidden layer node of the SCN network is randomly generated in a second normal distribution;

[0018] The variances of the first normal distribution and the second normal distribution are the same and are expected to be inverse numbers of each other.

[0019] In a possible implementation, the expectation and variance of the first normal distribution and the second normal distribution are obtained based on a swarm intelligence optimization algorithm.

[0020] In a possible implementation, the expectation and variance of the first normal distribution and the second normal distribution are obtained based on optimization of the BES algorithm.

[0021] In a possible implementation, the error evaluation model is obtained by training the SCN network based on historical CVT secondary voltage data and historical CVT error state data.

[0022] The present invention also provides a CVT operation error evaluation device, comprising:

[0023] A determination module, configured to determine an error evaluation index of a target CVT based on real-time secondary voltage data of the target CVT;

[0024] An evaluation module, configured to input an error evaluation index of the target CVT into an error evaluation model, and use an output of the error evaluation model as an operation error evaluation result of the target CVT;

[0025] The error assessment model is based on the SCN network for error assessment, and the bias and input weights of the hidden layer nodes of the SCN network are configured based on a normal distribution.

[0026] The present invention also provides an electronic device, including a memory and a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the CVT operation error evaluation method as described above is implemented.

[0027] The present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the CVT operation error evaluation method as described above.

[0028] The beneficial effects of the present invention are:

[0029] The CVT operation error evaluation method, device, electronic device and storage medium provided by the present invention first determine the error evaluation index of the target CVT through the real-time secondary voltage data of the target CVT to facilitate subsequent data processing, and then use the error evaluation index of the target CVT as the input of the error evaluation model, and then use the output of the error evaluation model as the operation error evaluation result of the target CVT. The error evaluation model is based on the SCN network, and the bias and input weights of the hidden layer nodes of the SCN network are configured based on the normal distribution. While ensuring the accuracy of the error evaluation, the complexity of the error evaluation model is reduced and the iteration speed of the model is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 A schematic diagram of a flow chart of an embodiment of a CVT operation error evaluation method provided by the present invention;

[0031] Figure 2 A schematic diagram of a flow chart of an embodiment of a CVT operation error evaluation process provided by the present invention;

[0032] Figure 3 A schematic structural diagram of an embodiment of a CVT operation error evaluation device provided by the present invention;

[0033] Figure 4 A schematic structural diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0034] The preferred embodiments of the present invention are described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not used to limit the scope of the present invention.

[0035] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0036] In the description of the present invention, reference to an "embodiment" means that a particular feature, structure, or characteristic described in conjunction with the embodiment may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive of other embodiments. It is explicitly and implicitly understood by those skilled in the art that the described embodiments may be combined with other embodiments.

[0037] CVT is a measuring device that converts high voltage into low voltage signal. Affected by factors such as operating time and environment, the error performance of some CVTs is not stable enough during long-term operation, which directly leads to inaccurate electricity metering. At present, power companies mainly use the periodic calibration method to calibrate CVTs with high-grade standard voltage transformers every four years. However, due to the difficulty in coordinating power outages at substations and the huge workload of calibration, it is very difficult to ensure that all transformers are calibrated on schedule in actual work, resulting in the difficulty of timely detection of out-of-tolerance CVTs in operation. Once the CVT is out of tolerance, it is very easy to cause trade disputes because it is difficult to define the actual amount of electricity.

[0038] In order to evaluate the online operation error of CVT in real time without power outage, the present invention provides a CVT operation error evaluation method.

[0039] The specific embodiments are described in detail below:

[0040] Embodiment 1:

[0041] A CVT operation error evaluation method, combined with Figure 1 Come and see, Figure 1 The flowchart of an embodiment of the CVT operation error evaluation method provided by the present invention includes step S101 and step S102, wherein:

[0042] In step S101, based on the real-time secondary voltage data of the target CVT, an error evaluation index of the target CVT is determined;

[0043] In step S102, the error evaluation index of the target CVT is input into an error evaluation model, and the output of the error evaluation model is used as the operation error evaluation result of the target CVT;

[0044] The error assessment model is based on the SCN network for error assessment, and the bias and input weights of the hidden layer nodes of the SCN network are configured based on a normal distribution.

[0045] During implementation, the real-time secondary voltage data of the target CVT may be firstly obtained, and then the error evaluation index of the target CVT may be determined according to the real-time secondary voltage data of the target CVT.

[0046] After determining the error evaluation index of the target CVT, the error evaluation index of the target CVT can be used as the input of the error evaluation model, and then the output of the error evaluation model can be used as the operating error evaluation result of the target CVT to complete the operating error evaluation of the target CVT.

[0047] Among them, the error assessment model can perform error assessment according to a stochastic configured network (SCN). In addition, in order to improve the iteration speed of the error assessment model, when configuring the bias and input weights of the hidden layer nodes of the SCN network, the present invention no longer configures them according to the average distribution, but configures them according to the normal distribution.

[0048] The CVT operation error assessment method provided by the present invention can be applied to the CVT operation error assessment scenario of a substation, and can also be applied to the CVT operation error assessment scenario in other places where CVT is used, and the present invention does not make specific limitations on this.

[0049] Compared with the prior art, the CVT operation error evaluation method provided in this embodiment first determines the error evaluation index of the target CVT through the real-time secondary voltage data of the target CVT to facilitate subsequent data processing, and then uses the error evaluation index of the target CVT as the input of the error evaluation model, and then uses the output of the error evaluation model as the operation error evaluation result of the target CVT. The error evaluation model is based on the SCN network, and the bias and input weights of the hidden layer nodes of the SCN network are configured based on the normal distribution. While ensuring the accuracy of the error evaluation, the complexity of the error evaluation model is reduced and the iteration speed of the model is improved.

[0050] Exemplarily, determining the error evaluation index of the target CVT based on the real-time secondary voltage data of the target CVT includes:

[0051] Determining a first evaluation index based on information components at all scales of the real-time secondary voltage data of the target CVT after empirical mode decomposition;

[0052] Determining a second evaluation index based on the real-time secondary voltage data of the target CVT and the rated voltage data of the target CVT;

[0053] determining a third evaluation index based on the amplitude of the three-phase voltage corresponding to the real-time secondary voltage data of the target CVT;

[0054] Based on the first evaluation index, the second evaluation index, and the third evaluation index, an error evaluation index of the target CVT is determined.

[0055] Specifically, when determining the error evaluation index of the target CVT based on the real-time secondary voltage data of the target CVT, the first evaluation index, the second evaluation index and the third evaluation index can be first determined based on the real-time secondary voltage data of the target CVT, and then the first evaluation index, the second evaluation index and the third evaluation index are integrated to obtain the error evaluation index of the target CVT.

[0056] For example, the first evaluation index can be determined based on the information components at all scales after the real-time secondary voltage data of the target CVT is subjected to empirical mode decomposition. The specific determination formula is as follows:

[0057]

[0058] Among them, X 1 represents the first evaluation index, U F represents the amplitude after empirical mode decomposition, f represents the frequency corresponding to the real-time secondary voltage data of the target CVT, : represents the information component of all scales of the real-time secondary voltage data of the target CVT after empirical mode decomposition, U F (f,:) represents the information components at all scales after empirical mode decomposition of the real-time secondary voltage data of the target CVT, and the amplitude after empirical mode decomposition at frequency f.

[0059] For another example, the second evaluation index can be determined based on the real-time secondary voltage data of the target CVT and the rated voltage data of the target CVT. The specific determination formula is as follows:

[0060]

[0061] Among them, X 2 represents the second evaluation index, U i Indicates the voltage amplitude corresponding to the real-time secondary voltage data of the target CVT, U c Indicates the rated voltage amplitude of the target CVT.

[0062] For another example, the third evaluation index can be determined according to the amplitude of the three-phase voltage corresponding to the real-time secondary voltage data of the target CVT, and the specific determination formula is as follows:

[0063]

[0064] Among them, X 3 represents the third evaluation index, U A , U B and U C They respectively represent the amplitudes of the three-phase voltages corresponding to the real-time secondary voltage data of the target CVT, and |·| represents absolute value operation.

[0065] Exemplarily, determining the error evaluation index of the target CVT based on the first evaluation index, the second evaluation index, and the third evaluation index includes:

[0066] The first evaluation index, the second evaluation index and the third evaluation index are integrated based on the FPN algorithm to obtain an error evaluation index of the target CVT.

[0067] Specifically, when determining the error evaluation index of the target CVT based on the first evaluation index, the second evaluation index and the third evaluation index, the first evaluation index, the second evaluation index and the third evaluation index can be fused according to the pyramid fusion algorithm (Feature Pyramid Networks, FPN) to obtain the error evaluation index of the target CVT.

[0068] For example, the first evaluation index, the second evaluation index, and the third evaluation index may be integrated according to the following formula to obtain the error evaluation index of the target CVT:

[0069] X 4 =λ 1 Conv(X 1 )+λ 2 Conv(ω 1 Conv(X 1 )+ω 2 X 2 )

[0070] +λ 3 Conv(ω 3 Conv(ω 1 Conv(X 1 )+ω 2 X 2 )+ω 4 X 3 )

[0071] λ 1 +λ 2 +λ 3=1

[0072] ω 1 +ω 2 +ω 3 +ω 4 =1

[0073] Among them, X 4 represents the error evaluation index of the target CVT, Conv represents the convolution operation, and λ 1 ,λ 2 and λ 3 represents the convolution weight, ω 1 ,ω 2 ,ω 3 and ω 4 Represents parameter weight.

[0074] Exemplarily, the bias of each hidden layer node of the SCN network is randomly generated in a first normal distribution;

[0075] The input weight of each hidden layer node of the SCN network is randomly generated in a second normal distribution;

[0076] The variances of the first normal distribution and the second normal distribution are the same and are expected to be inverse numbers of each other.

[0077] Specifically, the bias of each hidden layer node of the SCN network can be randomly generated in the normal distribution N{-μ, σ}, and the input weight of each hidden layer node can be randomly generated in the normal distribution N{μ, σ}, thereby improving the iteration speed of the network.

[0078] Exemplarily, the expectation and variance of the first normal distribution and the second normal distribution are obtained based on a swarm intelligence optimization algorithm.

[0079] Specifically, the expectation and variance of the first normal distribution and the second normal distribution can be optimized using a swarm intelligence optimization algorithm, such as an ant colony algorithm, a particle swarm optimization algorithm, a vulture search algorithm, and the like.

[0080] Exemplarily, the expectation and variance of the first normal distribution and the second normal distribution are obtained based on optimization of the BES algorithm.

[0081] Specifically, the present invention uses a Bald Eagle Search optimization algorithm (BES) when determining the expectation and variance of the first normal distribution and the second normal distribution.

[0082] Exemplarily, the error evaluation model is obtained by training the SCN network based on historical CVT secondary voltage data and historical CVT error state data.

[0083] Specifically, the error evaluation model can be obtained by training the SCN network based on the historical CVT secondary voltage data and the historical CVT error state data. During training, the historical CVT error evaluation index can be first determined based on the historical CVT secondary voltage data, and then the historical CVT error evaluation index can be input into the SCN network, and then the SCN network can be iteratively trained based on the difference between the output of the SCN network and the historical CVT error state data.

[0084] The following is a specific application scenario to better illustrate the technical solution of the present invention:

[0085] Combination Figure 2 Come and see, Figure 2 This is a flow chart of an embodiment of a CVT operation error evaluation process provided by the present invention, and the process specifically includes the following steps:

[0086] Step S201, obtaining historical CVT secondary voltage data and historical CVT error state data in the substation, and using the historical CVT secondary voltage data to construct a first evaluation index, a second evaluation index, and a third evaluation index of the error state.

[0087] The first evaluation metric is defined as follows:

[0088]

[0089] Among them, U F represents the amplitude of the historical CVT secondary voltage data after empirical mode decomposition, f is the frequency, and : represents the information component at all scales after empirical mode decomposition of the historical CVT secondary voltage data.

[0090] The second evaluation metric is defined as follows:

[0091]

[0092] Among them, U i Indicates the voltage amplitude of CVT in normal state, U c is the voltage amplitude collected in real time.

[0093] The third evaluation indicator is defined as follows:

[0094]

[0095] Among them, U A , U B , U C is the amplitude of the three-phase voltage, and Avg is the average value of the amplitude of the three-phase voltage.

[0096] Step S202: Use the FPN algorithm to fuse the first evaluation index, the second evaluation index, and the third evaluation index to obtain a fused fourth evaluation index.

[0097] The specific process is as follows:

[0098] X 4 =λ 1 Conv(X 1 )+λ 2 Conv(ω 1 Conv(X 1 )+ω 2 X 2 )

[0099] +λ 3 Conv(ω 3 Conv(ω 1 Conv(X 1 )+ω 2 X 2 )+ω 4 X 3 )

[0100] λ 1 +λ 2 +λ 3 =1

[0101] ω 1 +ω 2 +ω 3 +ω 4 =1

[0102] Among them, X 4 It is the fourth evaluation indicator, and Conv is the convolution operation.

[0103] Step S203: train the SCN network using the fourth evaluation index and historical CVT error state data to obtain a CVT error evaluation model.

[0104] SCN is a constructive neural network based on data-supervised random parameter configuration. It establishes a supervision mechanism in the process of network node construction to achieve synchronous optimization configuration of model structure and network parameters. Its specific construction process is:

[0105] Assume that a network with L-1 nodes has been constructed and its output is:

[0106]

[0107] Among them, β j represents the output parameter of the jth hidden layer node, b j represents the bias of the jth hidden layer node, g jrepresents the activation function of the jth hidden layer node, ω j represents the input weight of the jth hidden layer node, and L represents the number of nodes in the hidden layer.

[0108] The network error at this moment is:

[0109] e L-1 =ff L-1 =[e L-1 , 1 ,…,e L-1，m ]

[0110] Among them, m represents the number of iterations, e L-1 , m represents the network residual of the L-1th hidden layer at the mth iteration.

[0111] Traditional SCN designs a range control set, where each parameter is a range of average distribution. The average distribution node configuration method is to generate ω in multiple [-λ, λ] intervals according to the range control set. j and b j This method configures the ω j and b j Cannot exceed the boundary of the average distribution. If the range control set is not designed properly, or if the λ is constantly modified p The method of expanding the value range will increase the number of iterations of the algorithm, resulting in a decrease in the training speed of the model. j and b j Configured.

[0112] The parameters of the normal distribution are the expected value μ and the variance σ. μ and σ affect the average value and the probability of the generated random number respectively, which effectively expands the range of values. j and b j , whose range control parameter is λ p ={μ,σ}.ω j and b j Randomly generate in N{-μ, σ} and N{μ, σ}. The values ​​of μ and σ have a direct impact on the quality of the generated nodes, so it is necessary to follow an optimal parameter λ p To ensure that the network residual is minimal. In this invention, the vulture search algorithm is used to p To find the optimal position, the optimal position of the vulture population is the optimal λ p , the specific process is:

[0113] In the search space selection stage, the vulture uses the optimal position of the population, the average position of the population and the current position of the individual as empirical information to select the best search area, which is expressed as follows:

[0114] R i，new =Rbest +αγ(R mean -R i )

[0115] Among them, R best represents the optimal position determined by the vulture population, α is the control factor, γ is a random number, and R mean represents the average position of individual vultures, R i Indicates the current position of the i-th vulture.

[0116] The control factor design is:

[0117]

[0118] Among them, p is the current iteration number, and P is the maximum iteration number.

[0119] During the prey search phase, the vulture flies in a spiral pattern within the selected search space to determine the best position to dive and prey. i，new , which is expressed as follows:

[0120] R i，new =R i +y(i)(R i -R i+1 )+x(i)(R i -R mean )

[0121] Among them, x(i) and y(i) represent the position of the prey individual in the polar coordinate equation, and the value range is (-1, 1), R i+1 Indicates the current position of the i+1th vulture.

[0122] During the dive-to-catch phase, the vulture dives from the optimal position to catch the prey, which is described by the mathematical equation:

[0123] R i，new =randR best +x(i)(R i -c 1 R mean )+y(i)(R i -c 2 R mean )

[0124] where c 1 and c 2 It indicates the intensity of the vulture's movement toward the optimal position and the center position, and its value is [1, 2].

[0125] The loss function is:

[0126] Δe p =ep -e p-1

[0127] When Δe p When it is smaller, it means that the algorithm converges slowly under this parameter. p With ideal λ p The distance is far and needs to be p Make larger adjustments to expand the search range; when Δe p When it is larger, it means that the algorithm converges faster under this parameter. p In the ideal p Nearby, it is necessary to p Just make fine adjustments.

[0128] Step S204: Use the CVT error evaluation model to perform error evaluation on the CVT to be evaluated.

[0129] The secondary side voltage of the CVT to be evaluated is collected and input into the trained CVT error evaluation model to obtain the error state of the CVT.

[0130] The embodiment of the present invention also provides a CVT operation error evaluation device, combined with Figure 3 Come and see, Figure 3 This is a schematic diagram of the structure of an embodiment of a CVT operation error evaluation device provided by the present invention. The CVT operation error evaluation device 300 includes:

[0131] A determination module 301 is used to determine an error evaluation index of a target CVT based on real-time secondary voltage data of the target CVT;

[0132] An evaluation module 302, configured to input the error evaluation index of the target CVT into an error evaluation model, and use the output of the error evaluation model as an operation error evaluation result of the target CVT;

[0133] The error assessment model is based on the SCN network for error assessment, and the bias and input weights of the hidden layer nodes of the SCN network are configured based on a normal distribution.

[0134] The specific implementation methods of each module of the CVT operation error evaluation device can refer to the description of the above-mentioned CVT operation error evaluation method, and have similar beneficial effects, which will not be repeated here.

[0135] It should be noted that the CVT operation error evaluation device can be arranged in the CVT monitoring equipment of the substation, or in the substation control center, and the present invention does not make any specific limitation to this.

[0136] The embodiment of the present invention further provides an electronic device, Figure 4 Come and see, Figure 4 This is a structural schematic diagram of an embodiment of an electronic device provided by the present invention. The electronic device 400 includes a processor 401, a memory 402, and a computer program stored in the memory 402 and executable on the processor 401. When the processor 401 executes the program, the CVT operation error evaluation method as described above is implemented.

[0137] As a preferred embodiment, the electronic device 400 further includes a display 403 for displaying the CVT operation error evaluation method as executed by the processor 401 .

[0138] Exemplarily, the computer program may be divided into one or more modules / units, one or more modules / units are stored in the memory 402, and executed by the processor 401 to complete the present invention. One or more modules / units may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program in the electronic device 400. For example, the computer program may be divided into the determination module 301 and the evaluation module 302 in the above embodiment, and the specific functions of each module are as described above, and are not described one by one here.

[0139] The electronic device 400 may be a desktop computer, a notebook, a PDA or a smart phone with an adjustable camera module.

[0140] Among them, the processor 401 may be an integrated circuit chip with signal processing capabilities. The above-mentioned processor 401 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The disclosed methods, steps and logic block diagrams in the embodiments of the present invention can be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0141] The memory 402 may be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electric erasable programmable read-only memory (EEPROM), etc. The memory 402 is used to store programs, and the processor 401 executes the program after receiving the execution instruction. The process definition method disclosed in any of the embodiments of the present invention may be applied to the processor 401 or implemented by the processor 401.

[0142] The display 403 may be an LCD display screen or an LED display screen, for example, a display screen on a mobile phone.

[0143] Understandably, Figure 4 The structure shown is only a schematic diagram of the structure of the electronic device 400. The electronic device 400 may also include Figure 4 More or fewer components as shown. Figure 4 Each component shown in the figure can be implemented by hardware, software or a combination thereof.

[0144] The electronic device provided according to the above embodiment of the present invention can be implemented with reference to the specific description of the CVT operation error evaluation method as described above according to the present invention, and has similar beneficial effects as the CVT operation error evaluation method as described above, which will not be repeated here.

[0145] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the CVT operation error evaluation method as described above is implemented.

[0146] Generally speaking, the computer instructions for implementing the method of the present invention can be carried by any combination of one or more computer-readable storage media. Non-transitory computer-readable storage media can include any computer-readable media except for the signal itself that is temporarily propagating.

[0147] Computer-readable storage media may be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium that contains or stores a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0148] Computer program code for performing the operation of the present invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages, in particular, Python suitable for neural network computing and platform frameworks based on TensorFlow, PyTorch, etc. can be used. The program code can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0149] Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0150] The present invention discloses a CVT operation error evaluation method, device, electronic device and storage medium. Firstly, the error evaluation index of the target CVT is determined by the real-time secondary voltage data of the target CVT to facilitate subsequent data processing. Then, the error evaluation index of the target CVT is used as the input of an error evaluation model. Then, the output of the error evaluation model is used as the operation error evaluation result of the target CVT. The error evaluation model is based on a SCN network. At the same time, the bias and input weights of the hidden layer nodes of the SCN network are configured based on normal distribution. While ensuring the accuracy of the error evaluation, the complexity of the error evaluation model is reduced and the iteration speed of the model is improved.

[0151] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention.

Claims

1. A CVT operation error evaluation method, It is characterized in that include: Determining an error evaluation index of the target CVT based on real-time secondary voltage data of the target CVT; Inputting the error evaluation index of the target CVT into an error evaluation model, and using the output of the error evaluation model as an operation error evaluation result of the target CVT; The error assessment model is based on the SCN network for error assessment, and the bias and input weights of the hidden layer nodes of the SCN network are configured based on a normal distribution.

2. The CVT operation error evaluation method according to claim 1, It is characterized in that The step of determining the error evaluation index of the target CVT based on the real-time secondary voltage data of the target CVT includes: Determining a first evaluation index based on information components at all scales of the real-time secondary voltage data of the target CVT after empirical mode decomposition; Determining a second evaluation index based on the real-time secondary voltage data of the target CVT and the rated voltage data of the target CVT; determining a third evaluation index based on the amplitude of the three-phase voltage corresponding to the real-time secondary voltage data of the target CVT; Based on the first evaluation index, the second evaluation index, and the third evaluation index, an error evaluation index of the target CVT is determined.

3. The CVT operation error evaluation method according to claim 2, It is characterized in that The determining the error evaluation index of the target CVT based on the first evaluation index, the second evaluation index and the third evaluation index comprises: The first evaluation index, the second evaluation index and the third evaluation index are integrated based on the FPN algorithm to obtain an error evaluation index of the target CVT.

4. The CVT operation error evaluation method according to claim 1, It is characterized in that The bias of each hidden layer node of the SCN network is randomly generated in a first normal distribution; The input weight of each hidden layer node of the SCN network is randomly generated in a second normal distribution; The variances of the first normal distribution and the second normal distribution are the same and are expected to be inverse numbers of each other.

5. The CVT operation error evaluation method according to claim 4, It is characterized in that The expectation and variance of the first normal distribution and the second normal distribution are obtained based on the optimization of a swarm intelligence optimization algorithm.

6. The CVT operation error evaluation method according to claim 5, It is characterized in that The expectation and variance of the first normal distribution and the second normal distribution are obtained based on the optimization of the BES algorithm.

7. The CVT operation error evaluation method according to any one of claims 1 to 6, It is characterized in that The error evaluation model is obtained by training the SCN network based on historical CVT secondary voltage data and historical CVT error state data.

8. A CVT operation error evaluation device, It is characterized in that include: A determination module, configured to determine an error evaluation index of a target CVT based on real-time secondary voltage data of the target CVT; An evaluation module, configured to input an error evaluation index of the target CVT into an error evaluation model, and use an output of the error evaluation model as an operation error evaluation result of the target CVT; The error assessment model is based on the SCN network for error assessment, and the bias and input weights of the hidden layer nodes of the SCN network are configured based on a normal distribution.

9. An electronic device, It is characterized in that It comprises a memory and a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the CVT operation error evaluation method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, It is characterized in that A computer program is stored thereon, and when the computer program is executed by a processor, the CVT operation error evaluation method according to any one of claims 1 to 7 is implemented.

Images