Deep learning-based detection methods, systems, and terminals for power transmission and transformation equipment.

Abstract

This application proposes a deep learning-based method, system, and terminal for detecting power transmission and transformation equipment, relating to the technical field of power transmission and transformation equipment detection. The method includes acquiring initial infrared images and equipment detection images of the power transmission and transformation equipment; controlling a preset target detection model to analyze the equipment detection images to generate image target detection parameters; correcting the image target detection parameters according to preset image deviation parameters to generate actual target detection parameters; annotating the initial infrared images according to the actual target detection parameters to generate an annotated infrared image; acquiring environmental detection parameters of the power transmission and transformation equipment; correcting the annotated infrared image according to the environmental detection parameters to generate the actual infrared image; and analyzing the actual infrared image to generate an equipment detection report. This application improves the timeliness of power transmission and transformation equipment detection.

Description

Technical Field

[0001] This application relates to the technical field of power transmission and transformation equipment testing, and in particular to a deep learning-based method, system, and terminal for power transmission and transformation equipment testing. Background Technology

[0002] Power transmission and transformation equipment testing refers to a series of inspections, tests, and evaluations of power transmission and transformation equipment in a power system to ensure that these devices can operate safely and reliably.

[0003] In related technologies, operators carry thermal imagers and proceed to each predetermined inspection location according to a pre-established inspection plan. They use the thermal imagers to scan the temperature of the power transmission and transformation equipment and capture images, thereby obtaining infrared spectra of the equipment. Then, by comparing the infrared spectra with the infrared images of the equipment when a fault occurs, it is determined whether the equipment has malfunctioned.

[0004] Regarding the aforementioned technologies, when using thermal imagers to collect infrared spectra of power transmission and transformation equipment, it is necessary to ensure the stability of the external environment to reduce the interference of the external environment on the accuracy of the collected infrared spectra. Therefore, operators need to select a specific time to inspect the power transmission and transformation equipment, rather than inspecting the equipment in real time, resulting in poor timeliness of the inspection. Summary of the Invention

[0005] To improve the timeliness of power transmission and transformation equipment testing, this application provides a deep learning-based method, system, and terminal for power transmission and transformation equipment testing.

[0006] Firstly, this application provides a deep learning-based detection method for power transmission and transformation equipment, employing the following technical solution:

[0007] Deep learning-based detection methods for power transmission and transformation equipment include:

[0008] Acquire initial infrared images and equipment inspection images of power transmission and transformation equipment;

[0009] The preset target detection model is controlled to analyze the images detected by the device in order to generate image target detection parameters;

[0010] The image target detection parameters are corrected according to the preset image deviation parameters to generate the actual target detection parameters;

[0011] The initial infrared image is annotated based on the actual target detection parameters to generate an annotated infrared image;

[0012] Obtain environmental monitoring parameters for power transmission and transformation equipment;

[0013] The labeled infrared image is corrected based on environmental detection parameters to generate the actual infrared image;

[0014] Analyze actual infrared images to generate thermal imaging features, temperature features, and detection components of the equipment;

[0015] Determine thermal imaging fault relationships and temperature defect relationships based on the equipment detection components and the preset equipment fault characteristic relationships;

[0016] Obtain the operating parameters of the equipment's testing components;

[0017] The equipment inspection report is determined based on the equipment's thermal imaging characteristics, thermal imaging fault relationships, equipment temperature characteristics, temperature defect relationships, and equipment operating parameters.

[0018] By adopting the above technical solution, after obtaining the labeled infrared image, the environmental detection parameters of the power transmission and transformation equipment are detected. The labeled infrared image is then corrected based on the environmental detection parameters to obtain the actual infrared image, minimizing the impact of the external environment on infrared image acquisition. This allows for monitoring of the power transmission and transformation equipment in more selectable environments and time periods, thereby improving the timeliness of power transmission and transformation equipment detection.

[0019] Optionally, the step of correcting the labeled infrared image based on environmental detection parameters to generate the actual infrared image includes:

[0020] Determine whether the environmental monitoring parameters meet the preset requirements of the ideal environmental parameters;

[0021] If the conditions are met, the labeled infrared image will be defined as the actual infrared image.

[0022] If they do not meet the requirements, the environmental monitoring parameters and ideal environmental parameters will be analyzed to determine the parameters affecting the environment.

[0023] The labeled infrared images are corrected based on the environmental parameters that affect them in order to generate the actual infrared images.

[0024] By adopting the above technical solution, when the environmental detection parameters meet the requirements of ideal environmental parameters, the labeled infrared image is directly defined as the actual infrared image. When they do not meet the requirements, the environmental parameters that affect the environment are determined, and the labeled infrared image is corrected based on the environmental parameters that affect the environment, instead of correcting based on all environmental parameters, thereby improving the efficiency and accuracy of image correction.

[0025] Optionally, the step of correcting the labeled infrared image based on environmental parameters to generate the actual infrared image includes:

[0026] The environmental parameters are analyzed to generate temperature compensation items; the temperature compensation items include ambient temperature compensation items, humidity temperature compensation items, wind speed temperature compensation items, and radiation temperature compensation items.

[0027] The labeled infrared images are analyzed to generate the initial detection temperature;

[0028] The temperature compensation item and the initial detection temperature are analyzed to generate the true temperature of the equipment;

[0029] The actual pixel value is determined based on the actual temperature of the device and the preset infrared temperature mapping relationship;

[0030] The labeled infrared image is corrected based on the actual pixel values ​​to generate the actual infrared image.

[0031] By adopting the above technical solution, the temperature compensation item is determined after analyzing the environmental parameters. Then, the actual temperature of the equipment is determined after analyzing the temperature compensation item and the initial detection temperature. Based on the actual temperature of the equipment, the actual pixel value is found in the infrared temperature mapping relationship. The actual infrared image is then corrected with the actual pixel value to obtain the actual infrared image, thereby improving the accuracy of the actual infrared image.

[0032] Optionally, the steps of analyzing environmental parameters to generate temperature compensation terms include:

[0033] The temperature influence coefficient is determined based on the actual target detection parameters and the preset target coefficient mapping relationship.

[0034] The environmental parameters and temperature influence coefficients are analyzed to generate temperature compensation terms.

[0035] By adopting the above technical solution, the temperature influence coefficient is found in the target coefficient mapping relationship based on the actual target detection parameters. Then, the temperature compensation term is obtained after calculating the environmental parameters and the temperature influence coefficient, thereby improving the efficiency of determining the temperature compensation term.

[0036] Optionally, the steps of analyzing the environmental parameters and temperature influence coefficients to generate temperature compensation terms include:

[0037] Determine whether the environmental parameters affecting the environment include preset wind speed environmental parameters or preset radiation environmental parameters;

[0038] If not, the environmental parameters and temperature influence coefficients are calculated based on the preset multiple regression model to generate a temperature compensation term.

[0039] If so, the environmental parameters that affect the environment will be analyzed to generate general environmental parameters and specific environmental parameters;

[0040] The common environmental parameters and temperature influence coefficients are calculated based on the preset multiple regression model to generate common compensation terms;

[0041] Analyze specific environmental parameters to generate specific compensation terms;

[0042] The general compensation term and the specific compensation term are analyzed to generate the temperature compensation term.

[0043] By adopting the above technical solution, when the environmental parameters affecting the environment do not include wind speed or radiation parameters, the temperature compensation term is directly calculated based on the multiple regression model for the environmental parameters affecting the environment and the temperature influence coefficient. When wind speed or radiation parameters are included, the environmental parameters affecting the environment are divided into ordinary environmental parameters and specific environmental parameters. The ordinary compensation term is calculated based on the ordinary environmental parameters and the temperature influence coefficient using the multiple regression model. Then, the specific compensation term is obtained after analyzing the specific environmental parameters. Finally, the temperature compensation term is obtained by correlating the ordinary compensation term and the specific compensation term, thereby improving the efficiency and accuracy of determining the temperature compensation term.

[0044] Optionally, the steps of analyzing specific environmental parameters to generate specific compensation terms include:

[0045] Determine whether a specific environmental parameter meets the requirements of a preset specific environmental threshold.

[0046] If the conditions are met, then the specific environmental parameters and temperature influence coefficients are calculated based on the multiple regression model to generate specific compensation terms;

[0047] If the conditions are not met, specific environmental parameters and temperature influence coefficients will be calculated based on the preset hybrid model to generate specific compensation items.

[0048] By adopting the above technical solution, when a specific environmental parameter meets the requirements of a specific environmental threshold, it indicates that the influence of the specific environmental parameter on temperature is still linear. Therefore, a specific compensation term can be obtained by directly calculating the specific environmental parameter and temperature influence coefficient using a multiple regression model. However, when the parameter does not meet the requirements, it indicates that the influence of the specific environmental parameter on temperature is in a nonlinear stage. Therefore, a specific compensation term can be determined by calculating the specific environmental parameter and temperature influence coefficient using a hybrid model, thereby improving the accuracy of determining the specific compensation term.

[0049] Optionally, the steps for determining the equipment inspection report based on equipment thermal imaging characteristics, thermal imaging fault relationships, equipment temperature characteristics, temperature defect relationships, and equipment operating parameters include:

[0050] Determine whether the thermal imaging characteristics of the equipment meet the requirements of thermal imaging fault relationships;

[0051] If the conditions are met, the equipment fault characteristics are determined based on the relationship between the equipment thermal imaging characteristics and the thermal imaging fault.

[0052] If not, the equipment operating parameters will be analyzed to determine the characteristics of the equipment failure.

[0053] Determine equipment defect characteristics based on the relationship between equipment temperature characteristics and temperature defects;

[0054] Associate equipment fault characteristics and equipment defect characteristics to generate equipment inspection reports.

[0055] By adopting the above technical solution, when the thermal imaging characteristics of the equipment meet the requirements of the thermal imaging fault relationship, the equipment fault characteristics are searched in the thermal imaging fault relationship based on the equipment thermal imaging characteristics. If they do not meet the requirements, the equipment fault characteristics are determined based on the equipment operating parameters, and the equipment defect characteristics are searched in the temperature defect relationship based on the equipment temperature characteristics. Thus, the equipment fault characteristics and equipment defect characteristics are associated to obtain the equipment inspection report, thereby improving the accuracy of determining the equipment inspection report.

[0056] Optionally, the steps of analyzing equipment operating parameters to determine equipment fault characteristics include:

[0057] Determine whether the equipment's operating parameters meet the preset requirements for normal operating parameters;

[0058] If the conditions are met, the preset fault-free characteristics will be defined as equipment fault characteristics.

[0059] If not, the equipment fault characteristics are determined based on the equipment operating parameters and the preset relationship between operating fault characteristics.

[0060] By adopting the above technical solution, the equipment's working parameters and normal operating parameters are compared. If the equipment's working parameters do not meet the requirements of the normal operating parameters, it indicates that the equipment has malfunctioned. Therefore, the equipment's fault characteristics are found in the working fault characteristic relationship based on the equipment's working parameters. Thus, when the equipment fault cannot be determined by infrared images, the equipment's working parameters can be used to make up for it, thereby improving the efficiency and accuracy of determining the equipment fault characteristics.

[0061] Secondly, this application provides a deep learning-based power transmission and transformation equipment detection system, which adopts the following technical solution:

[0062] A deep learning-based power transmission and transformation equipment detection system includes:

[0063] The acquisition module is used to acquire the initial infrared image, the device detection image, and the environmental detection parameters;

[0064] A memory for storing the program of the deep learning-based power transmission and transformation equipment detection method as described in any of the preceding claims;

[0065] The processor and the program in the memory can be loaded and executed by the processor to implement the deep learning-based power transmission and transformation equipment detection method as described in any of the above.

[0066] By adopting the above technical solution, the control processor loads and executes the program of the deep learning-based power transmission and transformation equipment detection method stored in the memory, enabling the acquisition module to acquire a series of data related to the deep learning-based power transmission and transformation equipment detection. After obtaining the labeled infrared image, the environmental detection parameters of the power transmission and transformation equipment are detected, and the labeled infrared image is corrected according to the environmental detection parameters to obtain the actual infrared image. This minimizes the influence of the external environment on the infrared image acquisition, and allows for monitoring of power transmission and transformation equipment in more selectable environments and time periods, thereby improving the timeliness of power transmission and transformation equipment detection.

[0067] Thirdly, this application provides a smart terminal, which adopts the following technical solution:

[0068] A smart terminal includes a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executed as described in any of the preceding claims, a deep learning-based method for detecting power transmission and transformation equipment.

[0069] By adopting the above technical solution, the processor of the intelligent terminal loads and executes the computer program of the deep learning-based power transmission and transformation equipment detection method stored in the memory. After obtaining the labeled infrared image, the environmental detection parameters of the power transmission and transformation equipment are detected. The labeled infrared image is then corrected according to the environmental detection parameters to obtain the actual infrared image, minimizing the influence of the external environment on the infrared image acquisition. The power transmission and transformation equipment can be monitored in more selectable environments and time periods, thereby improving the timeliness of power transmission and transformation equipment detection.

[0070] In summary, this application includes at least one of the following beneficial technical effects:

[0071] 1. After obtaining the labeled infrared image, the environmental detection parameters of the power transmission and transformation equipment are detected. The labeled infrared image is then corrected based on the environmental detection parameters to obtain the actual infrared image. This minimizes the impact of the external environment on the infrared image acquisition and allows for monitoring of the power transmission and transformation equipment in more selectable environments and time periods, thereby improving the timeliness of power transmission and transformation equipment detection.

[0072] 2. When the environmental detection parameters meet the requirements of the ideal environmental parameters, the labeled infrared image is directly defined as the actual infrared image. When they do not meet the requirements, the environmental parameters that affect the environment are determined. The labeled infrared image is then corrected based on the environmental parameters that affect the environment, instead of using all environmental parameters for correction. This improves the efficiency and accuracy of image correction.

[0073] 3. When a specific environmental parameter meets the requirements of a specific environmental threshold, it indicates that the influence of the specific environmental parameter on temperature is still linear. Therefore, a specific compensation term can be obtained by directly calculating the specific environmental parameter and temperature influence coefficient using a multiple regression model. However, when the condition does not meet the requirements, it indicates that the influence of the specific environmental parameter on temperature is in a nonlinear stage. Therefore, a specific compensation term can be determined by calculating the specific environmental parameter and temperature influence coefficient using a hybrid model, thereby improving the accuracy of determining the specific compensation term. Attached Figure Description

[0074] Figure 1 This is a flowchart of a deep learning-based detection method for power transmission and transformation equipment in an embodiment of this application.

[0075] Figure 2 This is a flowchart of the steps in this application embodiment to correct the labeled infrared image based on environmental detection parameters in order to generate an actual infrared image.

[0076] Figure 3 This is a flowchart of the steps in this application embodiment to correct the labeled infrared image based on environmental parameters to generate an actual infrared image.

[0077] Figure 4 This is a flowchart of the steps in this application embodiment to analyze environmental parameters to generate a temperature compensation item.

[0078] Figure 5 This is a flowchart of the steps in this application embodiment to analyze the environmental parameters and temperature influence coefficients to generate a temperature compensation term.

[0079] Figure 6 This is a flowchart of the steps in this application embodiment to analyze specific environmental parameters to generate specific compensation items.

[0080] Figure 7 This is a flowchart illustrating the steps for determining an equipment inspection report based on equipment thermal imaging characteristics, thermal imaging fault relationships, equipment temperature characteristics, temperature defect relationships, and equipment operating parameters in this application embodiment.

[0081] Figure 8 This is a flowchart of the steps in this application embodiment to analyze the operating parameters of the equipment in order to determine the characteristics of the equipment fault. Detailed Implementation

[0082] To make the purpose, technical solution, and advantages of this application clearer, the following description is provided in conjunction with the appendix. Figures 1 to 8 The present application will be further described in detail below with reference to embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the application.

[0083] This application discloses a deep learning-based method for detecting power transmission and transformation equipment. Specifically, it discloses a front-end infrared intelligent thermal imager with an infrared thermal imaging module, an image acquisition module, a fault diagnosis module, and a processing terminal. The infrared thermal imaging module and the image acquisition module respectively acquire initial infrared images and equipment detection images of the power transmission and transformation equipment. The processing terminal then inputs the equipment detection image into a target detection model to analyze the image target detection parameters. The image target detection parameters are then adjusted based on the image deviation parameters between the infrared thermal imaging module and the image acquisition module to obtain the actual target detection parameters. These actual target detection parameters are then annotated onto the initial infrared image to form an annotated infrared image. After detecting the environmental detection parameters of the power transmission and transformation equipment, the processing terminal corrects the annotated infrared image based on the environmental detection parameters to obtain the actual infrared image. The actual infrared image is then analyzed to obtain an equipment detection report. This method avoids inaccurate infrared images detected by the infrared thermal imager due to environmental factors, allowing more time for detection and thus improving the timeliness of power transmission and transformation equipment detection.

[0084] Reference Figure 1 This application discloses a deep learning-based detection method for power transmission and transformation equipment, including the following steps:

[0085] Step S100: Acquire the initial infrared image and equipment detection image of the power transmission and transformation equipment.

[0086] The initial infrared image refers to the infrared image of the power transmission and transformation equipment directly acquired by the infrared thermal imaging module. The infrared thermal imaging module uses infrared thermal imaging technology to detect the infrared radiation of the power transmission and transformation equipment, and converts the temperature distribution map of the power transmission and transformation equipment into a video image through photoelectric conversion, signal processing and other means.

[0087] The equipment detection image refers to the image of the power transmission and transformation equipment acquired by the image acquisition module. The image acquisition module can be a camera. In this embodiment, the image acquisition module and the infrared imaging module are installed side by side to reduce the error of the target position in the initial infrared image and the equipment detection image.

[0088] Step S101: Control the preset target detection model to analyze the image detected by the device to generate image target detection parameters.

[0089] The target detection model refers to a deep learning model used to locate and detect the position and type of targets in an image. In this embodiment, the Faster R-CNN deep target detection neural network is used as an example. First, an image sample library of power transmission and transformation equipment is established. The training set of the sample library is used to train the established Faster R-CNN deep target detection neural network. The overfitting degree of the model is verified by the validation set. Then, the network model established by the training is used to perform multi-target recognition and localization on the images in the test set, thereby generating the recognition results of the target position and type. The Faster R-CNN algorithm consists of two main modules: the PRN candidate box extraction module and the Faster R-CNN detection module. The PRN is a fully convolutional neural network used to extract candidate boxes. The Faster R-CNN detects and recognizes the targets in the proposals extracted by the PRN.

[0090] Image target detection parameters refer to the location and type of the target in the image. They are obtained by the processing terminal inputting the device-detected image into the target detection model for recognition. The reason for using the device-detected image for target recognition and detection instead of the initial infrared image is that the device-detected image has a higher resolution, making it easier for the model to recognize the target and resulting in higher recognition accuracy.

[0091] Step S102: Correct the image target detection parameters according to the preset image deviation parameters to generate actual target detection parameters.

[0092] The image deviation parameter refers to the positional deviation of the target in the images acquired by the image acquisition module and the infrared thermal imaging module. The operator compares the positional deviation of the target in the images acquired by the image acquisition module and the infrared thermal imaging module, and stores the positional deviation in the processing terminal.

[0093] The actual target detection parameters refer to the position and type of the target in the infrared image. They are obtained by the processing terminal adjusting the target position in the image target detection parameters according to the position deviation corresponding to the image deviation parameters.

[0094] Step S103: Annotate the initial infrared image according to the actual target detection parameters to generate an annotated infrared image.

[0095] Among them, the labeled infrared image refers to the infrared image with the target bounding box and type marked. The processing terminal reads the target position and type from the actual target detection parameters, and then uses the drawing functions provided by the image processing library to draw the bounding box on the initial infrared image and add type annotations to obtain the labeled infrared image.

[0096] Step S104: Obtain environmental monitoring parameters for power transmission and transformation equipment.

[0097] Among them, environmental monitoring parameters refer to the parameters of the environment in which the power transmission and transformation equipment is located, including parameters such as ambient temperature, humidity, wind speed and solar radiation. These parameters are obtained by a distributed temperature and humidity sensor network, a non-contact solar radiation intensity sensor and an ultrasonic anemometer. Ambient temperature directly affects the heat exchange between the equipment surface and the environment, wind speed affects the equipment's heat dissipation efficiency, humidity affects infrared band absorption, and solar radiation causes additional temperature rise on the equipment surface, all of which may cause the infrared temperature measurement value to deviate from the true temperature.

[0098] Step S105: Correct the labeled infrared image according to the environmental detection parameters to generate the actual infrared image.

[0099] The actual infrared image refers to the true infrared image of the power transmission and transformation equipment, unaffected by the environment. It is generated by the processing terminal after correcting the labeled infrared image based on environmental detection parameters. For specific methods, please refer to [link / reference needed]. Figure 2 The steps.

[0100] Step S106: Analyze the actual infrared image to generate equipment thermal image features, equipment temperature features, and equipment detection components.

[0101] Among them, the thermal image features of the equipment refer to the thermal image features of the target in the actual infrared image. For example, the thermal image features of a current transformer fault include overall heating with the body as the center, and the thermal image features of a voltage transformer fault are that the overall temperature rise is high, and the temperature in the middle and upper parts is high. These features are obtained by the processing terminal using a trained convolutional neural network to extract the actual infrared image.

[0102] Equipment temperature characteristics refer to the temperature of the equipment. The processing terminal extracts the pixel values ​​within the bounding box of the actual infrared image, then finds the actual temperature based on the pixel value in the correspondence between pixels and temperature, and finally calculates the temperature difference and relative temperature difference between the actual temperatures to obtain the equipment temperature characteristics.

[0103] The equipment detection component refers to the specific component being detected, which is obtained by the processing terminal recognizing annotations in the actual infrared image.

[0104] Step S107: Determine the thermal imaging fault relationship and temperature defect relationship based on the equipment detection components and the preset equipment fault characteristic relationship.

[0105] Among them, the equipment fault characteristic relationship refers to the correspondence between different equipment and thermal imaging fault relationship and temperature defect relationship. It is summarized by the operator based on the defect diagnosis basis in DL / T664 "Technical Specification for Infrared Diagnosis of Live Equipment". For example, the thermal imaging characteristic of metal wire is the thermal image of the center of the wire with obvious hot spots. Then the fault characteristics are loose strands, broken strands, aging or insufficient cross-sectional area. The relative temperature difference reaches 35%. However, if the hot spot temperature does not reach the threshold, it is a general defect, etc.

[0106] Thermal imaging fault relationships refer to the fault characteristics corresponding to different thermal images of the equipment, while temperature defect relationships refer to the defect nature corresponding to different temperature characteristics of the equipment. These relationships are obtained by the processing terminal by searching the equipment fault characteristic relationships based on the component type corresponding to the equipment detection component.

[0107] Step S108: Obtain the equipment operating parameters of the equipment detection components.

[0108] Among them, the equipment operating parameters refer to the parameters of the equipment's detection components when they are working, such as volt-ampere characteristics and resistance, which are obtained by the SCADA system sending them to the processing terminal.

[0109] Step S109: Determine the equipment inspection report based on the equipment thermal imaging characteristics, thermal imaging fault relationships, equipment temperature characteristics, temperature defect relationships, and equipment operating parameters.

[0110] The equipment inspection report refers to a report on equipment malfunctions, including malfunction characteristics and defect levels. Malfunction characteristics include poor contact, loose strands, broken strands, and aging. Defect levels include general defects, severe defects, and emergency defects. These levels are determined by the processing terminal through analysis of the equipment's thermal imaging characteristics, thermal imaging-fault relationships, equipment temperature characteristics, temperature-defect relationships, and equipment operating parameters. Specific methods are detailed in [reference needed]. Figure 7 The steps.

[0111] Reference Figure 2 The steps for correcting the labeled infrared image based on environmental detection parameters to generate the actual infrared image include:

[0112] Step S200: Determine whether the environmental detection parameters meet the requirements of the preset ideal environmental parameters.

[0113] Ideal environmental parameters refer to environmental parameters that use directly detected infrared images as the actual images, such as an ambient temperature of 0 degrees Celsius, a relative humidity of 85%, a wind speed of 5 m / s, and a solar radiation intensity of 0 W / m². 2 The requirement for ideal environmental parameters means that they do not exceed the error range of ideal environmental parameters. The error range is determined by the operator based on the actual situation.

[0114] By processing the terminal to determine whether the environmental detection parameters do not exceed the error range of the ideal environmental parameters, it can be determined whether the labeled infrared images collected by the infrared thermal imaging module can be used directly.

[0115] Step S201: If the conditions are met, the labeled infrared image is defined as the actual infrared image.

[0116] If the processing terminal determines that the environmental detection parameters do not exceed the error range of the ideal environmental parameters, it indicates that the environment in which the power transmission and transformation equipment is located has little impact on the temperature of the power transmission and transformation equipment. The infrared image collected by the infrared thermal imaging module is the real temperature image of the power transmission and transformation equipment. Therefore, the labeled infrared image is defined as the actual infrared image.

[0117] Step S202: If it does not meet the requirements, analyze the environmental monitoring parameters and ideal environmental parameters to determine the parameters affecting the environment.

[0118] If the processing terminal determines that the environmental detection parameters exceed the error range of the ideal environmental parameters, it indicates that the environment in which the power transmission and transformation equipment is located has affected the actual temperature of the equipment. This may cause the temperature of the equipment to be higher than the actual operating temperature or lower than the actual operating temperature. Therefore, after analyzing the environmental detection parameters and the ideal environmental parameters, the influencing environmental parameters are determined to provide data support for the subsequent correction of the labeled infrared images.

[0119] Environmental parameters that affect the temperature of power transmission and transformation equipment are defined as environmental parameters that affect the temperature of power transmission and transformation equipment. The processing terminal compares the environmental detection parameters with the ideal environmental parameters, and defines the environmental detection parameters that exceed the error range of the ideal environmental parameters as environmental parameters that affect the temperature.

[0120] Step S2021: Correct the labeled infrared image according to the environmental parameters to generate the actual infrared image.

[0121] In this step, the actual infrared image is consistent with the actual infrared image in step S105. The processing terminal analyzes the environmental parameters to determine the influencing temperature, and then uses the influencing temperature to perform pixel correction on the labeled infrared image to obtain the actual infrared image. The specific method is described in [reference needed]. Figure 3 The steps.

[0122] Reference Figure 3 The steps for correcting the labeled infrared image based on environmental parameters to generate the actual infrared image include:

[0123] Step S300: Analyze the environmental parameters to generate temperature compensation items; the temperature compensation items include ambient temperature compensation items, humidity temperature compensation items, wind speed temperature compensation items, and radiation temperature compensation items.

[0124] Among them, the temperature compensation item refers to the temperature impact of the environment on power transmission and transformation equipment, including ambient temperature compensation, humidity temperature compensation, wind speed temperature compensation, and radiation temperature compensation. This is determined by the processing terminal after analyzing and calculating the environmental parameters. Specific methods are detailed in [reference needed]. Figure 4 The steps.

[0125] Step S301: Analyze the labeled infrared image to generate the initial detection temperature.

[0126] The initial detection temperature refers to the temperature of the power transmission and transformation equipment detected by the infrared thermal imaging module. The initial detection temperature is obtained by the processing terminal by looking up the pixels within the bounding box in the marked infrared image in the correspondence between pixels and temperatures.

[0127] Step S302: Analyze the temperature compensation item and the initial detection temperature to generate the true temperature of the equipment.

[0128] Among them, the actual equipment temperature refers to the actual temperature of the power transmission and transformation equipment after removing the influence of the environment. It is determined by the sum of the temperature compensation item calculated by the processing terminal and the initial detection temperature.

[0129] Step S303: Determine the actual pixel value based on the actual temperature of the device and the preset infrared temperature mapping relationship.

[0130] Among them, the infrared temperature mapping relationship refers to the correspondence between pixel values ​​and temperature. Operators form a mapping table by mapping different temperatures to different pixel values.

[0131] The true pixel value refers to the pixel value of the actual temperature of the power transmission and transformation equipment, which is obtained by the processing terminal by looking up the actual temperature of the equipment in the infrared temperature mapping relationship.

[0132] Step S304: Correct the labeled infrared image based on the actual pixel values ​​to generate the actual infrared image.

[0133] In this step, the actual infrared image is consistent with the actual infrared image in step S2021. The processing terminal uses the image processing library to correct the pixel values ​​of the standard infrared image to the real pixel values, thereby obtaining the actual infrared image, which reflects the real temperature of the power transmission and transformation equipment.

[0134] Reference Figure 4 The steps for analyzing environmental parameters to generate temperature compensation terms include:

[0135] Step S400: Determine the temperature influence coefficient based on the actual target detection parameters and the preset target coefficient mapping relationship.

[0136] Among them, the target coefficient mapping relationship refers to the temperature influence coefficients corresponding to different types of targets, including the ambient temperature influence coefficient, humidity influence coefficient, wind speed influence coefficient and solar radiation influence coefficient. These coefficients are obtained by operators through coefficient calibration tests on different power transmission and transformation equipment, and a mapping table is formed by mapping the target type to the temperature influence coefficient.

[0137] The temperature influence coefficient refers to the coefficient of temperature of power transmission and transformation equipment affected by the environment, including the ambient temperature influence coefficient, humidity influence coefficient, wind speed influence coefficient and solar radiation influence coefficient. It is obtained by the processing terminal by looking up the target type in the target coefficient mapping table according to the target detection parameters.

[0138] Step S401: Analyze the environmental parameters and temperature influence coefficients to generate a temperature compensation term.

[0139] The temperature compensation item in this step is the same as the temperature compensation item in step S300. It is obtained by the processing terminal after calculating the environmental parameters and temperature influence coefficient. The specific method is as follows: Figure 5 The steps.

[0140] Reference Figure 5 The steps for analyzing environmental parameters and temperature influence coefficients to generate temperature compensation terms include:

[0141] Step S500: Determine whether the environmental parameters affecting the environment include preset wind speed environmental parameters or preset radiation environmental parameters.

[0142] Among them, wind speed environmental parameters refer to environmental parameters that are wind speed, and radiation environmental parameters refer to environmental parameters that are solar radiation, which are stored by the operator in the processing terminal.

[0143] By processing the terminal, it is determined whether the environmental parameters include wind speed or radiation parameters, thereby determining whether the temperature compensation term can be directly calculated.

[0144] Step S501: If not, calculate the environmental parameters and temperature influence coefficients according to the preset multiple regression model to generate a temperature compensation term.

[0145] If the processing terminal determines that the environmental parameters do not include wind speed or radiation, it indicates that the environmental parameters have a linear effect on the temperature of the power transmission and transformation equipment. Therefore, the environmental parameters and temperature influence coefficients are input into the multiple regression model to calculate the temperature compensation term.

[0146] Multiple regression models are models used to calculate temperature compensation, including temperature compensation models, humidity compensation models, wind speed compensation models, and solar radiation compensation models. The formula for the temperature compensation model is the difference between the ambient temperature and the ideal ambient temperature multiplied by the ambient temperature influence coefficient. The formula for the humidity compensation model is the humidity influence coefficient multiplied by the ambient relative humidity. The formula for the wind speed compensation model is the negative exponential form of the ambient wind speed multiplied by the wind speed influence coefficient, reflecting that the heat dissipation efficiency slows down as the wind speed increases. The formula for the solar radiation compensation model is the solar radiation coefficient multiplied by the solar radiation intensity.

[0147] The temperature compensation term in this step is the same as the temperature compensation term in step S401. The processing terminal calls the corresponding model in the multiple regression model based on the environmental impact parameters, and then inputs the environmental impact parameters and temperature impact coefficient into the model for calculation.

[0148] Step S502: If so, analyze the environmental parameters to generate general environmental parameters and specific environmental parameters.

[0149] If the processing terminal determines that the environmental parameters include wind speed or radiation, it indicates that the environment has both linear and nonlinear effects on the temperature of power transmission and transformation equipment. Therefore, after analyzing the environmental parameters, we can determine the general and specific environmental parameters to provide data support for the subsequent calculation of temperature compensation terms.

[0150] Ordinary environmental parameters refer to parameters that do not cause nonlinear effects among the environmental parameters, namely environmental temperature and humidity parameters, which are obtained by the processing terminal by identifying the environmental temperature or relative humidity parameters among the environmental parameters.

[0151] Specific environmental parameters refer to parameters that may cause nonlinear effects among environmental parameters, namely wind speed parameters and solar radiation intensity, which are obtained by the processing terminal by identifying wind speed parameters or solar radiation intensity among the environmental parameters.

[0152] Step S503: Calculate the common environmental parameters and temperature influence coefficients according to the preset multiple regression model to generate common compensation terms.

[0153] The multiple regression model in this step is the same as the multiple regression model in step S501, and will not be described again here.

[0154] The general compensation term refers to the temperature compensation caused by general environmental parameters to power transmission and transformation equipment. The processing terminal selects the corresponding model from the multiple regression model based on the general environmental parameters, and then inputs the general environmental parameters and temperature influence coefficient into the model to calculate the general compensation term.

[0155] Step S504: Analyze specific environmental parameters to generate specific compensation items.

[0156] Among them, the specific compensation item refers to the temperature compensation caused by specific environmental parameters to power transmission and transformation equipment. It is determined by the processing terminal after analyzing the specific environmental parameters. The specific method is as follows: Figure 6 The steps.

[0157] Step S505: Analyze the general compensation term and the specific compensation term to generate the temperature compensation term.

[0158] The temperature compensation term in this step is the same as the temperature compensation term in step S401, and is obtained by the processing terminal by calculating the sum of the ordinary compensation term and the specific compensation term.

[0159] Reference Figure 6 The steps for analyzing specific environmental parameters to generate specific compensation items include:

[0160] Step S600: Determine whether a specific environmental parameter meets the requirements of a preset specific environmental threshold.

[0161] Among them, the specific environmental threshold refers to the threshold at which the influence of the environment on temperature enters the nonlinear stage, such as a wind speed of 10 m / s and a solar radiation intensity of 1000 W / m. 2 The requirement for a specific environmental threshold means not exceeding the specific environmental threshold.

[0162] By processing the terminal to determine whether a specific environmental parameter does not exceed a specific environmental threshold, it can be determined whether the impact of a specific environment on power transmission and transformation equipment has reached the nonlinear stage.

[0163] Step S601: If the conditions are met, calculate the specific environmental parameters and temperature influence coefficients according to the multiple regression model to generate specific compensation terms.

[0164] If the processing terminal determines that a specific environmental parameter does not exceed a specific environmental threshold, it indicates that the impact of the specific environment on the power transmission and transformation equipment has not reached the nonlinear stage. Therefore, the specific compensation term is still obtained by calculating the specific environmental parameter and temperature influence coefficient using the model in the multiple regression model.

[0165] Step S602: If it does not meet the requirements, then calculate the specific environmental parameters and temperature influence coefficients according to the preset hybrid model to generate specific compensation items.

[0166] If the processing terminal determines that a specific environmental parameter exceeds a specific environmental threshold, it indicates that the impact of the specific environment on the power transmission and transformation equipment has reached the nonlinear stage. Therefore, a specific compensation term is calculated based on the specific environmental parameter and temperature influence coefficient according to the hybrid model.

[0167] A hybrid model is a model obtained by adding nonlinear factors to the original wind speed compensation model and solar radiation compensation model. The formula for the hybrid model is the original model formula plus the square of the original model formula, for example, A+A. 2 .

[0168] Reference Figure 7 The steps for determining an equipment inspection report based on equipment thermal imaging characteristics, thermal imaging fault relationships, equipment temperature characteristics, temperature defect relationships, and equipment operating parameters include:

[0169] Step S700: Determine whether the thermal imaging characteristics of the equipment meet the requirements of the thermal imaging fault relationship.

[0170] The requirement for a thermal imaging fault relationship is that it exists in the thermal image corresponding to the thermal imaging fault relationship. The processing terminal determines whether the equipment's thermal imaging features exist in the thermal image corresponding to the thermal imaging fault relationship, thereby determining whether the equipment has malfunctioned.

[0171] Step S701: If the conditions are met, determine the equipment fault characteristics based on the relationship between the equipment thermal imaging characteristics and the thermal imaging fault.

[0172] If the processing terminal determines that the thermal image features of the device exist in the thermal image corresponding to the thermal image fault relationship, it indicates that the device has malfunctioned. Therefore, the device fault features are determined based on the device thermal image features and the thermal image fault relationship.

[0173] Equipment fault characteristics refer to the specific faults that occur in the equipment, which are obtained by the processing terminal by looking up the equipment's thermal imaging characteristics in the mapping table corresponding to the thermal imaging fault relationship.

[0174] Step S702: If it does not meet the requirements, then analyze the equipment operating parameters to determine the equipment fault characteristics.

[0175] If the processing terminal determines that the thermal image features of the device do not exist in the thermal image corresponding to the thermal image fault relationship, it indicates that the device may or may not have a fault. Therefore, the device status cannot be determined from the thermal image features. Thus, the device operating parameters of the device detection components are analyzed to provide data support for the subsequent determination of device fault features.

[0176] The equipment fault characteristics in this step are consistent with the equipment fault characteristic definitions in step S701. They are determined by the processing terminal after analyzing the equipment operating parameters. For specific methods, please refer to [link / reference needed]. Figure 8 The steps.

[0177] Step S703: Determine the equipment defect characteristics based on the relationship between equipment temperature characteristics and temperature defects.

[0178] Among them, equipment defect characteristics refer to the nature of equipment defects, including general defects, serious defects and emergency defects, which are obtained by the processing terminal by looking up the corresponding mapping table of temperature defect relationship based on the equipment temperature characteristics.

[0179] Step S704: Associate equipment fault characteristics and equipment defect characteristics to generate an equipment inspection report.

[0180] In this step, the equipment inspection report is consistent with the equipment inspection report in step S109. The processing terminal stores the fault characteristics corresponding to the equipment fault characteristics and the defect nature corresponding to the equipment defect characteristics in the same database.

[0181] Reference Figure 8 The steps for analyzing equipment operating parameters to determine equipment fault characteristics include:

[0182] Step S800: Determine whether the equipment operating parameters meet the preset normal operating parameter requirements.

[0183] Among them, normal operating parameters refer to the parameters of the equipment when it is working normally, such as the volt-ampere characteristics, which are obtained by the operator testing the normal equipment. The requirement for normal operating parameters is that they are within the range of normal operating parameters.

[0184] By processing the terminal to determine whether the device's operating parameters are within the normal operating parameter range, it can be determined whether the device's detection components are in a normal state.

[0185] Step S801: If the condition is met, the preset fault-free characteristic is defined as the equipment fault characteristic.

[0186] If the processing terminal determines that the device's operating parameters are within the normal operating parameter range, it indicates that the device's detection components are in a normal state. Therefore, the fault-free characteristic is defined as the device's fault characteristic.

[0187] Fault-free characteristics refer to the absence of any fault characteristics in the equipment, which are stored in the processing terminal by the operator.

[0188] Step S802: If not, determine the equipment fault characteristics based on the equipment operating parameters and the preset working fault characteristic relationship.

[0189] If the processing terminal determines that the device's operating parameters are not within the normal operating parameter range, it indicates that the device's detection component is in a fault state. Therefore, the device fault characteristics are obtained by searching the mapping table corresponding to the operating fault characteristic relationship based on the device's operating parameters.

[0190] The working fault characteristic relationship refers to the correspondence between working parameters and fault characteristics. When a fault occurs in the equipment's detection component, the operator detects the working parameters at the corresponding moment and forms a mapping table by matching the fault characteristics with the working parameters one by one.

[0191] Based on the same inventive concept, embodiments of this application provide a deep learning-based power transmission and transformation equipment detection system, comprising:

[0192] The acquisition module is used to acquire the initial infrared image, the device detection image, the environmental detection parameters, and the device operating parameters;

[0193] The memory is used to store the program for the deep learning-based detection method for power transmission and transformation equipment.

[0194] The processor and memory can load and execute programs to implement a deep learning-based detection method for power transmission and transformation equipment.

[0195] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional modules is used as an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device, and unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0196] This application provides a computer-readable storage medium storing a computer program that can be loaded by a processor and executed as a deep learning-based method for detecting power transmission and transformation equipment.

[0197] Computer storage media include, for example, USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, optical disks, and other media that can store program code.

[0198] Based on the same inventive concept, embodiments of this application provide a smart terminal, including a memory and a processor, wherein the memory stores a computer program that can be loaded and executed by the processor for a deep learning-based power transmission and transformation equipment detection method.

[0199] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional modules is used as an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device, and unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0200] The above are all preferred embodiments of this application and are not intended to limit the scope of protection of this application. Any feature disclosed in this specification (including the abstract and drawings) may be replaced by other equivalent or similar features unless specifically stated otherwise. That is, unless specifically stated otherwise, each feature is only one example of a series of equivalent or similar features.

Claims

1. A deep learning-based detection method for power transmission and transformation equipment, characterized in that, include: Acquire initial infrared images and equipment inspection images of power transmission and transformation equipment; The preset target detection model is controlled to analyze the images detected by the device in order to generate image target detection parameters; The image target detection parameters are corrected according to the preset image deviation parameters to generate the actual target detection parameters; The initial infrared image is annotated based on the actual target detection parameters to generate an annotated infrared image; Obtain environmental monitoring parameters for power transmission and transformation equipment; The labeled infrared image is corrected based on environmental detection parameters to generate the actual infrared image; Analyze actual infrared images to generate thermal imaging features, temperature features, and detection components of the equipment; Determine thermal imaging fault relationships and temperature defect relationships based on the equipment detection components and the preset equipment fault characteristic relationships; Obtain the operating parameters of the equipment's testing components; The equipment inspection report is determined based on the equipment's thermal imaging characteristics, thermal imaging fault relationships, equipment temperature characteristics, temperature defect relationships, and equipment operating parameters. The steps for correcting the labeled infrared image based on environmental detection parameters to generate the actual infrared image include: Determine whether the environmental monitoring parameters meet the preset requirements of the ideal environmental parameters; If the conditions are met, the labeled infrared image will be defined as the actual infrared image. If they do not meet the requirements, the environmental monitoring parameters and ideal environmental parameters will be analyzed to determine the parameters affecting the environment. The labeled infrared images are corrected based on the environmental parameters to generate the actual infrared images; The steps for correcting the labeled infrared image based on environmental parameters to generate the actual infrared image include: The environmental parameters are analyzed to generate temperature compensation items; the temperature compensation items include ambient temperature compensation items, humidity temperature compensation items, wind speed temperature compensation items, and radiation temperature compensation items. The labeled infrared images are analyzed to generate the initial detection temperature; The temperature compensation item and the initial detection temperature are analyzed to generate the true temperature of the equipment; The actual pixel value is determined based on the actual temperature of the device and the preset infrared temperature mapping relationship; The labeled infrared image is corrected based on the actual pixel values ​​to generate the actual infrared image; The steps for analyzing environmental parameters to generate temperature compensation terms include: The temperature influence coefficient is determined based on the actual target detection parameters and the preset target coefficient mapping relationship. The environmental parameters and temperature influence coefficients are analyzed to generate temperature compensation terms; The steps for analyzing environmental parameters and temperature influence coefficients to generate temperature compensation terms include: Determine whether the environmental parameters affecting the environment include preset wind speed environmental parameters or preset radiation environmental parameters; If not, the environmental parameters and temperature influence coefficients are calculated based on the preset multiple regression model to generate a temperature compensation term. If so, the environmental parameters that affect the environment will be analyzed to generate general environmental parameters and specific environmental parameters; The common environmental parameters and temperature influence coefficients are calculated based on the preset multiple regression model to generate common compensation terms; Analyze specific environmental parameters to generate specific compensation terms; Analyze general and specific compensation terms to generate temperature compensation terms; The steps for analyzing specific environmental parameters to generate specific compensation terms include: Determine whether a specific environmental parameter meets the requirements of a preset specific environmental threshold. If the conditions are met, then the specific environmental parameters and temperature influence coefficients are calculated based on the multiple regression model to generate specific compensation terms; If not, the specific environmental parameters and temperature influence coefficients are calculated according to the preset hybrid model to generate a specific compensation term; the hybrid model is the sum of the squares of the multiple regression model and the multiple regression model.

2. The deep learning-based detection method for power transmission and transformation equipment according to claim 1, characterized in that, The steps for determining an equipment inspection report based on equipment thermal imaging characteristics, thermal imaging fault relationships, equipment temperature characteristics, temperature defect relationships, and equipment operating parameters include: Determine whether the thermal imaging characteristics of the equipment meet the requirements of thermal imaging fault relationships; If the conditions are met, the equipment fault characteristics are determined based on the relationship between the equipment thermal imaging characteristics and the thermal imaging fault. If the conditions are not met, the equipment operating parameters will be analyzed to determine the characteristics of the equipment failure. Determine equipment defect characteristics based on the relationship between equipment temperature characteristics and temperature defects; Associate equipment fault characteristics and equipment defect characteristics to generate equipment inspection reports.

3. The deep learning-based detection method for power transmission and transformation equipment according to claim 1, characterized in that, The steps for analyzing equipment operating parameters to determine equipment fault characteristics include: Determine whether the equipment's operating parameters meet the preset requirements for normal operating parameters; If the conditions are met, the preset fault-free characteristics will be defined as equipment fault characteristics. If not, the equipment fault characteristics are determined based on the equipment operating parameters and the preset relationship between operating fault characteristics.

4. A deep learning-based detection system for power transmission and transformation equipment, characterized in that, include: The acquisition module is used to acquire the initial infrared image, the device detection image, and the environmental detection parameters; A memory for storing the program of the deep learning-based power transmission and transformation equipment detection method as described in any one of claims 1 to 3; The processor and the program in the memory can be loaded and executed by the processor to implement the deep learning-based power transmission and transformation equipment detection method as described in any one of claims 1 to 3.

5. A smart terminal, characterized in that, It includes a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executed as described in any one of claims 1 to 3, which is based on deep learning for detecting power transmission and transformation equipment.

Images