A substation fault identification method and system based on image detection

Abstract

The present invention discloses a substation fault identification method and system based on image detection, which relates to the technical field of substation fault identification. The method comprises: collecting historical imaging data within the substation and generating an original data set in combination with weather data at the time of imaging acquisition; calculating the global influence coefficient of weather data on the imaging data based on the original data set; collecting historical diagnostic data of equipment faults within the substation and generating a training data set in combination with the original data set; establishing a fault identification model using the global influence coefficient and the training data set; acquiring imaging data collected by the imaging device in real time, obtaining a fault identification result after applying the data to the fault identification model, and forwarding the fault identification result to the operation and maintenance personnel within the substation. The present invention greatly reduces the fault identification cycle and the amount of training required for the fault identification model, thereby achieving improved identification accuracy while reducing the consumption of computing resources.

Description

Technical Field

[0001] The present invention relates to the technical field of substation fault identification, and in particular to a substation fault identification method and system based on image detection. Background Art

[0002] Currently, infrared imaging technology plays a crucial role in identifying equipment faults in substations. By detecting infrared radiation emitted by power equipment and converting it into visible images, the system can identify the device's temperature distribution. Deep learning algorithms then use this temperature information to identify whether the equipment is faulty. Abnormal temperatures are often a precursor to equipment failure, making infrared imaging technology an effective preventative measure. However, infrared imaging technology is significantly affected by weather conditions (such as temperature and light). Infrared images of the same equipment at noon and at night can be inconsistent. Accurately identifying a single device fault requires a significant amount of imaging and annotated data. The workload and data required to identify equipment faults within a substation are enormous, and this inevitably leads to significant computational resources and time consumption. Therefore, improving algorithm efficiency and reducing resource consumption while ensuring accurate and real-time fault identification has become a pressing challenge for researchers in this field. Summary of the Invention

[0003] The present invention provides a substation fault identification method based on image detection, comprising:

[0004] Step 1: Collect historical imaging data within the substation and generate the original dataset by combining it with the weather data at the time of imaging acquisition.

[0005] Step 2: Calculate the global impact coefficient of weather data on imaging data based on the original data set;

[0006] Step 3: Collect historical diagnostic data of equipment failures in the substation and generate a training dataset based on the original dataset.

[0007] Step 4: Use the global impact coefficient and training data set to establish a fault identification model;

[0008] Step 5: Obtain the imaging data collected by the imaging equipment in real time, obtain the fault identification results through the fault identification model, and forward the fault identification results to the operation and maintenance personnel in the substation.

[0009] The above-mentioned method for identifying substation faults based on image detection, wherein the global influence coefficient of weather data on imaging data is calculated based on the original data set, is specifically divided into the following sub-steps:

[0010] Extract the color features of each image in the original data set to replace the imaging data in the original data pair;

[0011] De-duplicate and sort the replaced data according to the values ​​of each weather data;

[0012] The global influence coefficient of weather data on imaging data is calculated based on the deviations between adjacent data pairs.

[0013] The above-mentioned substation fault identification method based on image detection collects historical diagnostic data of equipment faults in the substation and generates a training dataset by combining it with the original dataset. The method is specifically divided into the following sub-steps:

[0014] Vectorize the equipment fault history diagnosis data into text;

[0015] The vectorized diagnostic data is used as output, and the color features of the historical imaging used for diagnosis and the weather data at that time are used as input to form input-output pairs.

[0016] These input-output pairs are organized into a dataset to form a training dataset.

[0017] The above-mentioned method for identifying substation faults based on image detection uses a global influence coefficient and a training data set to establish a fault identification model. The method is specifically divided into the following sub-steps:

[0018] Create a fault identification model based on the global impact coefficient;

[0019] Use the training dataset to train and tune the fault identification model;

[0020] Verify the accuracy of the fault identification model and put it into production environment after it reaches the preset standard.

[0021] The present invention also provides a substation fault identification system based on image detection, comprising: a raw data sorting module, a weather impact quantification module, a training data preparation module, a fault identification model establishment module, and a fault identification module;

[0022] The raw data collation module is used to collect historical imaging data within the substation and generate the raw data set by combining it with the weather data at the time of imaging acquisition;

[0023] Weather impact quantification module, used to calculate the global impact coefficient of weather data on imaging data based on the original data set;

[0024] The training data preparation module is used to collect historical diagnostic data of equipment faults in the substation and generate a training data set by combining it with the original data set;

[0025] A fault identification model building module is used to build a fault identification model using the global influence coefficient and the training data set;

[0026] The fault identification module is used to obtain the imaging data collected by the imaging equipment in real time, obtain the fault identification results through the trained fault identification model, and forward the fault identification results to the operation and maintenance personnel in the substation.

[0027] The beneficial effects achieved by the present invention are as follows: quantifying the impact of weather on imaging in advance greatly saves the fault identification cycle and the amount of training of the fault identification model, thereby improving the recognition accuracy while reducing the consumption of computing resources; it can achieve real-time recognition, further improve the efficiency of equipment maintenance, and reduce equipment loss caused by untimely processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments described in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0029] Figure 1 This is a flow chart of a substation fault identification method based on image detection provided in Example 1 of the present application;

[0030] Figure 2 This is a schematic diagram of a substation fault identification system based on image detection provided in Example 2 of the present application. DETAILED DESCRIPTION

[0031] The following is a clear and complete description of the technical solutions in the embodiments of the present invention, in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0032] Example 1

[0033] like Figure 1 As shown, the first embodiment of the present application provides a substation fault identification method based on image detection, including:

[0034] Step S10: collecting historical imaging data within the substation and generating an original data set in combination with weather data at the time of imaging acquisition;

[0035] Weather is the main reason that affects the accuracy of imaging data. Different temperatures and light conditions will cause deviations in the imaging of the equipment. In this step, the imaging data and the weather data at that time need to be processed into data pairs (p i ,E i) and organized into original data sets to provide data basis for subsequent calculations, where p i is the i-th historical imaging data, E i The weather dataset at the time of obtaining the i-th historical imaging data.

[0036] Step S20: Calculating the global influence coefficient of weather data on imaging data based on the original data set;

[0037] It is known that weather data can affect the accuracy of imaging data. Quantifying this impact in advance can significantly reduce the fault identification cycle and the amount of training required for the fault identification model, thereby improving identification accuracy while reducing computing resource consumption. This is specifically divided into the following sub-steps:

[0038] Step S21: extracting the color features of each image in the original data set to replace the image data in the original data pair;

[0039] Because infrared imaging is usually single-channel, the grayscale mean is used here as the color feature of the imaging; the imaging data in the data pair in the original data set was originally an image, and the color feature of this image is now used to replace it.

[0040] Step S22: de-duplicate and sort the replaced data according to the values ​​of each weather data;

[0041] Remove data pairs with consistent values ​​for each weather data item to reduce the amount of calculation. Sorting is to better observe the changing trend of the data and determine the weight of the weather data. Both descending and ascending orders are acceptable.

[0042] Step S23: calculating the global influence coefficient of the weather data on the imaging data based on the deviations generated between adjacent data pairs;

[0043] The calculation formula of the global influence coefficient λ is expressed as:

[0044] where μ j is the weight of the j-th weather data (preset value), e jk is the value of the jth weather data in the kth data pair, e jk+1 is the value of the jth weather data in the k+1th data pair, c k is the imaging data in the kth data pair (replaced by the color feature of the imaging at this time), c k+1 is the imaging data in the k+1th data pair, j takes values ​​from 1 to m, m is the total number of weather data items, k takes values ​​from w-1, w is the total number of data pairs in the original dataset after deduplication, and λ is the calculated result of the global influence coefficient.

[0045] Step S30: Collect historical diagnostic data of equipment faults in the substation and generate a training data set by combining it with the original data set;

[0046] First, the historical diagnostic data of equipment failures is text-vectorized. Then, the vectorized diagnostic data is used as output, and the color features of the historical imaging used for diagnosis and the weather data at the time are used as input to form input-output pairs. Finally, these input-output pairs are organized into a dataset to form a training dataset.

[0047] Step S40: establishing a fault identification model using the global influence coefficient and the training data set;

[0048] The global influence coefficient enables the model to focus on learning the guiding relationship between faults and device imaging, greatly reducing the amount of training and computation while ensuring accuracy. Specifically:

[0049] Step S41: creating a fault identification model based on the global impact coefficient;

[0050] The data expression of the created fault identification model is:

[0051] Where Y is the output of the model, φ f is the output weight of the f-th layer of the model, d f is the output bias of the fth layer of the model, x a is the input imaging data, is the jth weather data input, μ j is the weight of the jth weather data, λ is the global influence coefficient, δ fl is the lth latent variable in the fth layer, l takes values ​​from 1 to L, L is the total number of latent variables in the fth layer, j takes values ​​from 1 to m, m is the total number of input weather data items, and f takes values ​​from 1 to F, F is the total number of layers in the model.

[0052] Step S42: using the training data set to train and tune the fault recognition model;

[0053] First, we need to design a loss function for the model, and then use the minimum loss principle to continuously iterate the parameters in the model during the training process to obtain the optimal solution for the parameters of each layer of the model. The loss function is expressed as:

[0054] Where S is the loss value calculation result, y uv is the actual classification label of the u-th training sample for fault v. If the fault actually pointed to by the training sample u is v, then y uv The value is 1, otherwise it is 0, p uvis the probability that the u-th training sample is predicted to be fault v, v ranges from 1 to V, V is the number of faults identified in the substation, and u ranges from 1 to U, U is the total number of training samples.

[0055] Step S43: Verify the accuracy of the fault identification model and put it into production environment after reaching the preset standard;

[0056] Prepare a validation dataset to verify the model's generalization ability on unfamiliar samples, observe the accuracy of the output results, and if it is lower than the preset standard, return to step S42, adjust the data training weights and re-train and tune; if it has reached the preset standard, put the trained model into the production environment for use.

[0057] Step S50: acquiring imaging data collected by the imaging device in real time, obtaining a fault identification result through the fault identification model, and forwarding the fault identification result to the operation and maintenance personnel in the substation;

[0058] Because the fault identification model of this application has fewer parameters and focuses more, the identification speed is much faster than that of traditional models. After obtaining the imaging data, the features are extracted and input into the model, and the identification results can be obtained immediately, which can achieve real-time identification. The operation and maintenance personnel can then perform timely maintenance on the equipment in the substation based on the identification results, which can further improve the efficiency of equipment maintenance and reduce equipment loss caused by untimely processing.

[0059] Example 2

[0060] like Figure 2 As shown, the second embodiment of the present application provides a substation fault identification system based on image detection, including: a raw data sorting module 21, a weather impact quantification module 22, a training data preparation module 23, a fault identification model establishment module 24, and a fault identification module 25;

[0061] The raw data collating module 21 is used to collect historical imaging data in the substation and generate a raw data set in combination with weather data at the time of imaging acquisition;

[0062] Weather is the main reason that affects the accuracy of imaging data. Different temperatures and light conditions will cause deviations in the imaging of the equipment. In this step, the imaging data and the weather data at that time need to be processed into data pairs (p i ,E i ) and organized into original data sets to provide data basis for subsequent calculations, where p i is the i-th historical imaging data, E i The weather dataset at the time of obtaining the i-th historical imaging data.

[0063] The weather impact quantification module 22 is used to calculate the global impact coefficient of weather data on imaging data based on the original data set; specifically, it includes: an original data processing submodule and a global impact coefficient calculation submodule;

[0064] 1. The raw data processing submodule is used to extract the color features of each image in the original data set to replace the image data in the original data pair, and to remove duplicates and sort the replaced data pairs according to the values ​​of various weather data;

[0065] Because infrared imaging is typically single-channel, the grayscale mean is used as the color feature of the image. The image data in the data pairs in the original dataset was originally a single image, and the color features of this image are now replaced. Removing data pairs with identical values ​​for each weather data item reduces the computational effort. Sorting is used to better observe data trends and determine the weight of the weather data. Both descending and ascending sorting are acceptable.

[0066] 2. Global influence coefficient calculation submodule, used to calculate the global influence coefficient of weather data on imaging data based on the deviation between adjacent data pairs;

[0067] The calculation formula of the global influence coefficient λ is expressed as:

[0068] Where μj is the weight of the j-th weather data (preset value), ejk is the value of the j-th weather data in the k-th data pair, and e jk+1 is the value of the jth weather data in the k+1th data pair, c k is the imaging data in the kth data pair (replaced by the color features of the imaging at this time), ck+1 is the imaging data in the k+1th data pair, j ranges from 1 to m, m is the total number of weather data items, k ranges from w-1, w is the total number of data pairs in the original dataset after deduplication, and λ is the calculated result of the global influence coefficient.

[0069] The training data preparation module 23 is used to collect historical diagnostic data of equipment failures in the substation and generate a training data set by combining the original data set;

[0070] First, the historical diagnostic data of equipment failures is text-vectorized. Then, the vectorized diagnostic data is used as output, and the color features of the historical imaging used for diagnosis and the weather data at the time are used as input to form input-output pairs. Finally, these input-output pairs are organized into a dataset to form a training dataset.

[0071] The fault identification model establishment module 24 is used to establish a fault identification model using the global influence coefficient and the training data set; specifically, it includes: a model creation submodule, a model training submodule and a model verification submodule;

[0072] 1. Model creation submodule, used to create a fault identification model using the global influence coefficient;

[0073] The data expression of the created fault identification model is:

[0074] Where Y is the output of the model, φ f is the output weight of the f-th layer of the model, d f is the output bias of the fth layer of the model, x a is the input imaging data, is the jth weather data input, μ j is the weight of the jth weather data, λ is the global influence coefficient, δ fl is the lth latent variable in the fth layer, l takes values ​​from 1 to L, L is the total number of latent variables in the fth layer, j takes values ​​from 1 to m, m is the total number of input weather data items, and f takes values ​​from 1 to F, F is the total number of layers in the model.

[0075] 2. Model training submodule, used to train and tune the fault identification model using the training data set;

[0076] First, we need to design a loss function for the model, and then use the minimum loss principle to continuously iterate the parameters in the model during the training process to obtain the optimal solution for the parameters of each layer of the model. The loss function is expressed as:

[0077] Where S is the loss value calculation result, y uv is the actual classification label of the u-th training sample for fault v. If the fault actually pointed to by the training sample u is v, then y uv The value is 1, otherwise it is 0, p uv is the probability that the u-th training sample is predicted to be fault v, v ranges from 1 to V, V is the number of faults identified in the substation, and u ranges from 1 to U, U is the total number of training samples.

[0078] 3. Model verification submodule, used to verify the accuracy of the fault identification model and put it into production environment after reaching the preset standard;

[0079] Prepare a validation dataset to verify the model's generalization ability on unfamiliar samples and observe the accuracy of the output results. If the accuracy is lower than the preset standard, return to the model training submodule, adjust the data training weights, and retrain and tune. If the preset standard has been met, the trained model will be put into production environment for use.

[0080] The fault identification module 25 is used to obtain the imaging data collected by the imaging equipment in real time, obtain the fault identification result through the trained fault identification model, and forward the fault identification result to the operation and maintenance personnel in the substation.

[0081] Corresponding to the above embodiment, an embodiment of the present invention provides a computer storage medium, comprising: at least one memory and at least one processor;

[0082] The memory is used to store one or more program instructions;

[0083] The processor is configured to run one or more program instructions to execute a substation fault identification method based on image detection.

[0084] Corresponding to the above embodiment, an embodiment of the present invention provides a computer-readable storage medium, which contains one or more program instructions, and the one or more program instructions are used by a processor to execute a substation fault identification method based on image detection.

[0085] The embodiments disclosed in the present invention provide a computer-readable storage medium, in which computer program instructions are stored. When the computer program instructions are executed on a computer, the computer executes the above-mentioned substation fault identification method based on image detection.

[0086] In the embodiments of the present invention, the processor may be an integrated circuit chip having signal processing capabilities. The processor may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0087] The methods, steps, and logic diagrams disclosed in the embodiments of the present invention can be implemented or executed. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of the present invention can be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules within the decoding processor. The software modules can be located in a storage medium well-established in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. The processor reads the information from the storage medium and, in conjunction with its hardware, completes the steps of the aforementioned methods.

[0088] The storage medium may be a memory and may be, for example, a volatile memory or a nonvolatile memory, or may include both volatile and nonvolatile memory.

[0089] Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory.

[0090] Volatile memory may be random access memory (RAM), which is used as an external cache memory. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM bus random access memory (DRRAM).

[0091] The storage media described in the embodiments of the present invention are intended to include, but are not limited to, these and any other suitable types of memory.

[0092] Those skilled in the art will appreciate that in one or more of the above examples, the functions described herein can be implemented using a combination of hardware and software. When software is used, the corresponding functions can be stored in a computer-readable medium or transmitted as one or more instructions or codes on a computer-readable medium. Computer-readable media include computer storage media and communication media, wherein communication media includes any medium that facilitates the transmission of computer programs from one place to another. The storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0093] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent replacements, improvements, etc. made on the basis of the technical solution of the present invention should be included in the scope of protection of the present invention.

Claims

1. A substation fault identification method based on image detection, characterized in that: include: Step 1: Collect historical infrared imaging data within the substation and generate the original dataset by combining it with the weather data at the time of imaging acquisition; Step 2: Calculate the global impact coefficient of weather data on imaging data based on the original data set. This is divided into the following sub-steps: Extract the color features of each image in the original data set to replace the imaging data in the original data pair; De-duplicate and sort the replaced data according to the values ​​of each weather data; Calculate the global influence coefficient of weather data on imaging data based on the deviations between adjacent data pairs; Global influence coefficient The calculation formula is expressed as: ,in is the weight of the j-th weather data, is the value of the jth weather data item in the kth data pair, is the value of the jth weather data in the k+1th data pair, is the imaging data in the kth data pair, is the imaging data in the k+1th data pair, j ranges from 1 to m, m is the total number of weather data items, k ranges from 1 to w-1, w is the total number of data pairs in the original dataset after deduplication, is the calculation result of the global influence coefficient; Step 3: Collect historical diagnostic data of equipment failures in the substation and generate a training dataset based on the original dataset. Step 4: Use the global impact coefficient and training data set to establish a fault identification model, which is divided into the following sub-steps: Create a fault identification model based on the global impact coefficient; The data expression of the created fault identification model is: , where Y is the output of the model, is the output weight of the f-th layer of the model, is the output bias of the f-th layer of the model, is the input imaging data, is the jth weather data input, is the weight of the j-th weather data, is the global influence coefficient, is the first hidden variables, The value ranges from 1 to L, where L is the total number of implicit variables in the fth layer, j ranges from 1 to m, where m is the total number of input weather data items, and f ranges from 1 to F, where F is the total number of layers in the model; Use the training dataset to train and tune the fault identification model; Verify the accuracy of the fault identification model and put it into production once it reaches the preset standard; Step 5: Obtain the imaging data collected by the imaging equipment in real time, obtain the fault identification results through the fault identification model, and forward the fault identification results to the operation and maintenance personnel in the substation.

2. A method for identifying substation faults based on image detection according to claim 1, characterized in that: Collect historical diagnostic data on equipment faults in the substation and combine it with the original data set to generate a training data set. This is divided into the following sub-steps: Vectorize the equipment fault history diagnosis data into text; The vectorized diagnostic data is used as output, and the color features of the historical imaging used for diagnosis and the weather data at that time are used as input to form input-output pairs. These input-output pairs are organized into a dataset to form a training dataset.

3. A substation fault identification system based on image detection, characterized in that: Used to execute the substation fault identification method based on image detection according to any one of claims 1-2, comprising: a raw data sorting module, a weather impact quantification module, a training data preparation module, a fault identification model establishment module, and a fault identification module; The raw data collation module is used to collect historical imaging data within the substation and generate the raw data set by combining it with the weather data at the time of imaging acquisition; Weather impact quantification module, used to calculate the global impact coefficient of weather data on imaging data based on the original data set; The training data preparation module is used to collect historical diagnostic data of equipment failures in the substation and generate a training data set by combining it with the original data set; A fault identification model building module is used to build a fault identification model using the global influence coefficient and the training data set; The fault identification module is used to obtain the imaging data collected by the imaging equipment in real time, obtain the fault identification results through the trained fault identification model, and forward the fault identification results to the operation and maintenance personnel in the substation.

4. The substation fault identification system based on image detection according to claim 3 is characterized in that: The weather impact quantification module specifically includes: a raw data processing submodule and a global impact coefficient calculation submodule; The raw data processing submodule is used to extract the color features of each image in the original data set to replace the imaging data in the original data pair, and to remove duplicates and sort the replaced data pairs according to the values ​​of various weather data; The global influence coefficient calculation submodule is used to calculate the global influence coefficient of weather data on imaging data based on the deviations generated between adjacent data pairs.

5. The substation fault identification system based on image detection according to claim 3 is characterized in that: The fault identification model building module specifically includes: model creation submodule, model training submodule and model verification submodule; A model creation submodule is used to create a fault identification model using the global influence coefficient; The model training submodule is used to train and tune the fault identification model using the training data set; The model verification submodule is used to verify the accuracy of the fault identification model and put it into the production environment after reaching the preset standard.

6. A computer storage medium, characterized in that include: at least one memory and at least one processor; a memory for storing one or more program instructions; A processor, configured to run one or more program instructions to execute the substation fault identification method based on image detection as described in any one of claims 1-2.

Images