Equipment fault automatic identification method and system based on infrared thermal imaging

Abstract

The invention discloses an equipment fault automatic identification method and system based on infrared thermal imaging, relates to the technical field of fault identification, and solves the problems that in the prior art, infrared thermal imaging captured by an infrared sensor outside equipment is insufficient to reflect the equipment fault state, and an infrared sensor in the equipment is difficult to replace. The infrared sensing equipment can be installed inside and outside the equipment, whether the infrared sensing equipment inside the equipment is damaged or not is recognized based on the trained infrared sensing equipment fault recognition model, if yes, the infrared thermal imaging of the infrared sensing equipment outside the equipment is adopted to automatically recognize the fault, and if not, the infrared thermal imaging of the infrared sensing equipment outside the equipment is adopted to automatically recognize the fault. And if so, infrared thermal imaging of the infrared sensing device in the device is adopted to automatically identify the fault. Generally speaking, the electrical equipment fault identification method ensures that the electrical equipment fault identification has certain accuracy, and meanwhile, the electrical equipment does not need to be replaced when the infrared sensing device in the electrical equipment is damaged, so that the replacement cost is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of fault identification, and in particular to an automatic identification method and system for equipment faults based on infrared thermal imaging. Background Art

[0002] At present, significant progress has been made in the means of training machine learning models based on infrared thermal imaging to identify equipment failures. By using deep learning algorithms, such as convolutional neural networks (CNN), features can be effectively extracted from infrared images and abnormal conditions of equipment can be identified. For example, some studies have used clustering and statistical feature extraction of infrared images combined with support vector machines (SVM) for intelligent diagnosis. In addition, there are studies that use deconvolution feature learning and random matrix theory to identify potential faults in advance and achieve fault diagnosis and prediction. These methods have played an important role in improving the accuracy and efficiency of fault detection.

[0003] However, the accuracy of this machine learning fault identification method based on infrared thermal imaging is not always ideal. A major challenge is that if the infrared thermal imaging is captured by an external infrared sensor, it may not reflect the fault condition of the equipment as accurately as the infrared sensor installed inside the electrical equipment. Internal sensors can provide more direct temperature readings, thereby more accurately detecting local overheating or other signs of faults. In addition, once the internal infrared sensor is damaged, it can be very difficult to replace, which can lead to high maintenance costs and time-consuming. Therefore, researchers are seeking a better method for electrical equipment fault identification based on infrared sensing to improve identification accuracy, reduce maintenance difficulties, and ultimately achieve more efficient equipment monitoring and maintenance.

[0004] In view of this, a method and system for automatically identifying equipment faults based on infrared thermal imaging is needed. Summary of the invention

[0005] In view of the problem in the prior art that the infrared thermal image captured by the infrared sensor outside the equipment is not sufficient to reflect the equipment fault status and the infrared sensor inside the equipment is difficult to replace, the present invention provides a method and system for automatically identifying equipment faults based on infrared thermal imaging, which can install infrared sensor devices both inside and outside the equipment, and identify whether the infrared sensor device inside the equipment is damaged based on the trained infrared sensor device fault identification model. If damaged, the infrared thermal imaging of the infrared sensor device outside the equipment is used to automatically identify the fault. If not damaged, the infrared thermal imaging of the infrared sensor device inside the equipment is used to automatically identify the fault. The specific technical solution is as follows:

[0006] A method for automatically identifying equipment faults based on infrared thermal imaging, comprising the following steps:

[0007] Install infrared sensing equipment inside the equipment to collect infrared thermal images inside the electrical equipment;

[0008] Based on the collected infrared thermal imaging of the inside of the electrical equipment, after data preprocessing, the key features in the thermal imaging image are extracted, including temperature distribution, hot spot area, and edge contour;

[0009] The collected infrared images are labeled, including the normal state and fault state of the equipment. The labeled infrared images constitute the training set and the verification set.

[0010] Use the labeled data to train the model, use the validation set data to test the model performance, and adjust the model parameters or structure as needed to optimize the performance, and finally form an infrared fault recognition model for electrical equipment;

[0011] Collect infrared thermal images inside electrical equipment in real time, and use the infrared fault recognition model inside the electrical equipment to identify whether the electrical equipment has a fault.

[0012] Preferably, the method further comprises the following steps:

[0013] Collect infrared image data of infrared sensing equipment in normal working state and damaged state;

[0014] Extract key features from the collected infrared images, including image brightness, contrast, noise level, and bad pixel distribution;

[0015] The collected infrared images are labeled, including normal infrared sensor equipment and abnormal infrared sensor equipment. The labeled images constitute the training set and the verification set.

[0016] Use the labeled data to train the model, use the validation set data to test the model performance, and adjust the model parameters or structure as needed to optimize the performance, and finally form an infrared sensor equipment fault recognition model;

[0017] Infrared thermal images obtained by the infrared sensor device inside the equipment are collected in real time, and the infrared sensor device fault recognition model is used to identify whether the infrared sensor device is broken. If the result is that the infrared sensor device is normal, the infrared fault recognition model inside the electrical equipment is further used to identify whether the electrical equipment is damaged and output the recognition result of the infrared fault recognition model inside the electrical equipment. If the result is that the infrared sensor device is abnormal, the recognition result of the infrared sensor device abnormality is output.

[0018] Preferably, the method further comprises the following steps:

[0019] Install infrared sensing equipment on the outside of the equipment to collect infrared thermal images of the outside of the electrical equipment;

[0020] Based on the infrared thermal imaging of the outside of the electrical equipment, after data preprocessing, the key features in the thermal imaging image are extracted, including temperature distribution, hot spot area, and edge contour;

[0021] The collected infrared images are labeled, including the normal state and fault state of the equipment. The labeled infrared images constitute the training set and the verification set.

[0022] Use the labeled data to train the model, use the validation set data to test the model performance, and adjust the model parameters or structure as needed to optimize the performance, and finally form an external infrared fault recognition model for electrical equipment;

[0023] Infrared thermal images obtained by the infrared sensor device inside the equipment are collected in real time, and the infrared sensor device fault recognition model is used to identify whether the infrared sensor device is broken. If the result is that the infrared sensor device is normal, the infrared fault recognition model inside the electrical equipment is further used to identify whether the electrical equipment is damaged and output the recognition result of the infrared fault recognition model inside the electrical equipment. If the result is that the infrared sensor device is abnormal, infrared thermal images of the outside of the electrical equipment are further collected by the infrared sensor device installed outside the equipment, and the infrared fault recognition model outside the electrical equipment is used to identify whether the electrical equipment is damaged and output the recognition result of the infrared fault recognition model outside the electrical equipment.

[0024] Preferably, before identifying whether the electrical equipment is damaged by using the external infrared fault identification model of the electrical equipment, the following steps are also included:

[0025] Based on the infrared sensor equipment fault identification model, it is used to identify whether the infrared sensor equipment installed outside the electrical equipment is faulty;

[0026] If the identification result is a fault, after replacing the infrared sensing device outside the device, the infrared fault identification model outside the device is further used to identify whether the electrical device is damaged;

[0027] If the identification result is normal, the external infrared fault identification model of the electrical equipment is used to identify whether the electrical equipment is damaged.

[0028] Preferably, the infrared sensing device adopts an infrared thermal imager or an infrared sensor.

[0029] Preferably, the training of the model is specifically to train the model through its learning algorithm, and the machine learning algorithm includes convolutional neural network and support vector machine.

[0030] An automatic equipment fault identification system based on infrared thermal imaging, applied to the method as described above, comprises:

[0031] The data acquisition unit includes an infrared sensor device installed inside the electrical equipment, which is used to collect infrared thermal images inside the equipment and transmit the infrared thermal images to the model training unit and the model recognition unit;

[0032] The model training unit is connected to the data acquisition unit and the model recognition unit. The model training unit trains the deep neural network based on the infrared thermal imaging data collected by the data acquisition unit, thereby obtaining an infrared fault recognition model in the electrical equipment that can identify whether the electrical equipment has a fault, and transmits the infrared fault recognition model in the electrical equipment to the equipment recognition unit.

[0033] The model recognition unit is connected to the model training unit, the data acquisition unit and the communication unit. The model recognition unit recognizes the infrared thermal imaging in the device collected in real time by the data acquisition unit based on the infrared fault recognition model in the electrical device output by the model training unit, and outputs the result of whether the electrical device has a fault.

[0034] A communication unit is connected to the model recognition unit and the terminal, and transmits the output result of the model recognition unit to the terminal;

[0035] The terminal receives the output result from the model recognition unit based on the communication unit.

[0036] Preferably, the model training unit also collects infrared image data of the infrared sensing device in normal working state and damaged state, and trains to generate a fault recognition model of the infrared sensing device; it also collects infrared thermal imaging of the outside of the electrical equipment, extracts key features in the thermal imaging image after data preprocessing, and then generates an external infrared fault recognition model of the electrical equipment based on deep neural network training.

[0037] A computer-readable storage medium includes a stored program, wherein when the program is run, the device where the computer-readable storage medium is located is controlled to execute the above-mentioned method for automatic identification of equipment faults based on infrared thermal imaging.

[0038] A processor is used to run a program, wherein when the program is run, the method for automatically identifying equipment faults based on infrared thermal imaging as described above is executed.

[0039] Compared with the prior art, the present invention has the following beneficial effects:

[0040] The present invention collects infrared thermal imaging based on infrared sensing devices installed inside and outside the electrical equipment, and based on the collected infrared thermal imaging, extracts different features, and trains infrared fault recognition models inside the electrical equipment, infrared sensing device fault recognition models, and infrared fault recognition models outside the electrical equipment based on machine learning. Infrared sensing devices can be installed inside and outside the equipment, and based on the trained infrared sensing device fault recognition model, it can be identified whether the infrared sensing device inside the equipment is damaged. If it is damaged, the infrared thermal imaging of the infrared sensing device outside the equipment is used to automatically identify the fault. If it is not damaged, the infrared thermal imaging of the infrared sensing device inside the equipment is used to automatically identify the fault. Furthermore, when the infrared sensing device inside the electrical equipment is not damaged, it is identified whether the electrical equipment has a fault based on the infrared fault recognition model inside the electrical equipment. When the infrared sensing device inside the electrical equipment is damaged, it is identified whether the electrical equipment has a fault based on the infrared fault recognition model outside the electrical equipment. In this way, while ensuring that the fault recognition of the electrical equipment has a certain degree of accuracy, it is not necessary to replace the infrared sensing device inside the electrical equipment when it is damaged, thereby reducing the cost of replacement. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for the specific embodiments or the description of the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn according to the actual scale.

[0042] Figure 1 is a flow chart of the method of the present invention;

[0043] Figure 2 It is a system principle diagram of the present invention. DETAILED DESCRIPTION

[0044] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0045] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0046] It should also be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0047] It should be further understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0048] In one embodiment of the present invention, a method for automatically identifying equipment faults based on infrared thermal imaging is provided. Figure 1 As shown, the following steps are included:

[0049] S1: Infrared sensing devices are installed inside and outside the equipment to collect infrared thermal images inside and outside the electrical equipment.

[0050] S1: Based on the collected infrared thermal images of the inside and outside of the equipment, train the infrared fault recognition model for the electrical equipment, the infrared sensing equipment fault recognition model, and the infrared fault recognition model for the outside of the electrical equipment;

[0051] Among them, the infrared fault identification model in electrical equipment is based on the infrared thermal imaging inside the electrical equipment to identify whether the electrical equipment has a fault. This is also the first choice for identifying whether the electrical equipment has a fault, because the infrared thermal imaging inside the electrical equipment can better reflect the fault condition of the electrical equipment. In other words, the accuracy of fault identification using the information of infrared thermal imaging inside the electrical equipment is higher.

[0052] The infrared fault identification model outside the electrical equipment is based on the infrared thermal imaging outside the electrical equipment to identify whether the electrical equipment has a fault. This is a secondary option for identifying whether the electrical equipment has a fault. This is because the infrared thermal imaging outside the electrical equipment has a larger error than the infrared thermal imaging inside the electrical equipment. Therefore, if the infrared sensor device inside the electrical equipment is not damaged, the infrared thermal imaging inside the electrical equipment is still used to identify the fault. However, once the infrared sensor device inside the electrical equipment is damaged, the replacement cost is very high. Usually, the electrical equipment itself needs to be disassembled to replace the infrared sensor device. If some electrical equipment is embedded in the wall, the disassembly cost will be even higher. Therefore, at this time, the infrared thermal imaging of the infrared sensor device outside the equipment is used for identification. Although the accuracy is not as high as the infrared thermal imaging inside the equipment, its advantage lies in the fast replacement speed.

[0053] The following describes the specific training process of each model:

[0054] 1. Infrared fault identification model in electrical equipment:

[0055] Based on the collected infrared thermal imaging of the inside of the electrical equipment, after data preprocessing, the key features in the thermal imaging image are extracted, including temperature distribution, hot spot area, and edge contour;

[0056] The collected infrared images are labeled, including the normal state and fault state of the equipment. The labeled infrared images constitute the training set and the verification set.

[0057] Use the labeled data to train the model, use the validation set data to test the model performance, and adjust the model parameters or structure as needed to optimize the performance, and finally form an infrared fault recognition model for electrical equipment;

[0058] 2. Fault identification model of infrared sensing equipment:

[0059] Collect infrared image data of infrared sensing equipment in normal working state and damaged state;

[0060] Extract key features from the collected infrared images, including image brightness, contrast, noise level, and bad pixel distribution;

[0061] The collected infrared images are labeled, including normal infrared sensor equipment and abnormal infrared sensor equipment. The labeled images constitute the training set and the verification set.

[0062] The model is trained using labeled data, and the model performance is tested using validation set data. The model parameters or structure are adjusted as needed to optimize the performance, ultimately forming an infrared sensing equipment fault identification model.

[0063] 3. External infrared fault identification model of electrical equipment:

[0064] Install infrared sensing equipment on the outside of the equipment to collect infrared thermal images of the outside of the electrical equipment;

[0065] Based on the infrared thermal imaging of the outside of the electrical equipment, after data preprocessing, the key features in the thermal imaging image are extracted, including temperature distribution, hot spot area, and edge contour;

[0066] The collected infrared images are labeled, including the normal state and fault state of the equipment. The labeled infrared images constitute the training set and the verification set.

[0067] The model is trained using labeled data, and the model performance is tested using validation set data. The model parameters or structure are adjusted as needed to optimize the performance, ultimately forming an external infrared fault recognition model for electrical equipment.

[0068] The order in which these models are used is:

[0069] Collect infrared thermal images from the infrared sensor device inside the equipment in real time, and use the infrared sensor device fault identification model to identify whether the infrared sensor device is broken;

[0070] If the result is that the infrared sensing device is normal, then further identify whether the electrical device is damaged by using the infrared fault identification model in the electrical device and output the identification result of the infrared fault identification model in the electrical device;

[0071] If the result is that the infrared sensor device is abnormal, then the infrared sensor device installed outside the electrical device is identified to be faulty based on the infrared sensor device fault identification model;

[0072] If the identification result is a fault, after replacing the infrared sensing device outside the device, the infrared fault identification model outside the device is further used to identify whether the electrical device is damaged;

[0073] If the identification result is normal, the external infrared fault identification model of the electrical equipment is used to identify whether the electrical equipment is damaged.

[0074] In one embodiment of the present invention, a device fault automatic identification system based on infrared thermal imaging is provided. Figure 2 As shown, including:

[0075] The data acquisition unit includes an infrared sensor device installed inside the electrical equipment, which is used to collect infrared thermal images inside the equipment and transmit the infrared thermal images to the model training unit and the model recognition unit;

[0076] The model training unit is connected to the data acquisition unit and the model recognition unit. The model training unit trains the deep neural network based on the infrared thermal imaging data collected by the data acquisition unit, and then obtains an infrared fault recognition model inside the electrical equipment that can identify whether the electrical equipment is faulty, and transmits the infrared fault recognition model inside the electrical equipment to the equipment recognition unit; the model training unit also collects infrared image data of the infrared sensing device in normal working state and damaged state, and trains to generate an infrared sensing device fault recognition model; it also collects infrared thermal imaging of the outside of the electrical equipment, extracts key features in the thermal imaging image after data preprocessing, and then generates an infrared fault recognition model for the outside of the electrical equipment based on the deep neural network training.

[0077] The model recognition unit is connected to the model training unit, the data acquisition unit and the communication unit. The model recognition unit recognizes the infrared thermal imaging in the device collected in real time by the data acquisition unit based on the infrared fault recognition model in the electrical device output by the model training unit, and outputs the result of whether the electrical device has a fault.

[0078] A communication unit is connected to the model recognition unit and the terminal, and transmits the output result of the model recognition unit to the terminal;

[0079] The terminal receives the output result from the model recognition unit based on the communication unit.

[0080] In summary, the present invention collects infrared thermal imaging based on infrared sensing devices installed inside and outside the electrical equipment, and based on the collected infrared thermal imaging, extracts different features, and trains infrared fault recognition models inside the electrical equipment, infrared sensing device fault recognition models, and infrared fault recognition models outside the electrical equipment based on machine learning. Infrared sensing devices can be installed inside and outside the equipment, and based on the trained infrared sensing device fault recognition model, it can be identified whether the infrared sensing device inside the equipment is damaged. If it is damaged, the infrared thermal imaging of the infrared sensing device outside the equipment is used to automatically identify the fault. If it is not damaged, the infrared thermal imaging of the infrared sensing device inside the equipment is used to automatically identify the fault. Furthermore, when the infrared sensing device inside the electrical equipment is not damaged, it is identified whether the electrical equipment has a fault based on the infrared fault recognition model inside the electrical equipment. When the infrared sensing device inside the electrical equipment is damaged, it is identified whether the electrical equipment has a fault based on the infrared fault recognition model outside the electrical equipment. In this way, while ensuring that the fault recognition of the electrical equipment has a certain degree of accuracy, it is not necessary to replace the infrared sensing device inside the electrical equipment when it is damaged, thereby reducing the cost of replacement.

[0081] Those of ordinary skill in the art will appreciate that the units of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition of each example has been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0082] In the embodiments provided by the present invention, it should be understood that the division of units is only a logical function division, and there may be other division methods in actual implementation, for example, multiple units can be combined into one unit, one unit can be split into multiple units, or some features can be ignored, etc.

[0083] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0084] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-0nlyMemory), random access memory (RAM, RandomAccessMemory), mobile hard disk, magnetic disk or optical disk, etc., which can store program code.

[0085] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. A method for automatic identification of equipment faults based on infrared thermal imaging, characterized in that: The following steps are involved: Install infrared sensing equipment inside the equipment to collect infrared thermal images inside the electrical equipment; Based on the collected infrared thermal imaging of the inside of the electrical equipment, after data preprocessing, the key features in the thermal imaging image are extracted, including temperature distribution, hot spot area, and edge contour; The collected infrared images are labeled, including the normal state and fault state of the equipment. The labeled infrared images constitute the training set and the verification set. Use the labeled data to train the model, use the validation set data to test the model performance, and adjust the model parameters or structure as needed to optimize the performance, and finally form an infrared fault recognition model for electrical equipment; Collect infrared thermal images inside electrical equipment in real time, and use the infrared fault recognition model inside the electrical equipment to identify whether the electrical equipment has a fault.

2. According to claim 1, a method for automatic identification of equipment faults based on infrared thermal imaging is characterized in that: The following steps are also included: Collect infrared image data of infrared sensing equipment in normal working state and damaged state; Extract key features from the collected infrared images, including image brightness, contrast, noise level, and bad pixel distribution; The collected infrared images are labeled, including normal infrared sensor equipment and abnormal infrared sensor equipment. The labeled images constitute the training set and the verification set. Use the labeled data to train the model, use the validation set data to test the model performance, and adjust the model parameters or structure as needed to optimize the performance, and finally form an infrared sensor equipment fault recognition model; Infrared thermal images obtained by the infrared sensor device inside the equipment are collected in real time, and the infrared sensor device fault recognition model is used to identify whether the infrared sensor device is broken. If the result is that the infrared sensor device is normal, the infrared fault recognition model inside the electrical equipment is further used to identify whether the electrical equipment is damaged and output the recognition result of the infrared fault recognition model inside the electrical equipment. If the result is that the infrared sensor device is abnormal, the recognition result of the infrared sensor device abnormality is output.

3. The method for automatic identification of equipment faults based on infrared thermal imaging according to claim 2 is characterized in that: The following steps are also included: Install infrared sensing equipment on the outside of the equipment to collect infrared thermal images of the outside of the electrical equipment; Based on the infrared thermal imaging of the outside of the electrical equipment, after data preprocessing, the key features in the thermal imaging image are extracted, including temperature distribution, hot spot area, and edge contour; The collected infrared images are labeled, including the normal state and fault state of the equipment. The labeled infrared images constitute the training set and the verification set. Use the labeled data to train the model, use the validation set data to test the model performance, and adjust the model parameters or structure as needed to optimize the performance, and finally form an external infrared fault recognition model for electrical equipment; Infrared thermal images obtained by the infrared sensor device inside the equipment are collected in real time, and the infrared sensor device fault recognition model is used to identify whether the infrared sensor device is broken. If the result is that the infrared sensor device is normal, the infrared fault recognition model inside the electrical equipment is further used to identify whether the electrical equipment is damaged and output the recognition result of the infrared fault recognition model inside the electrical equipment. If the result is that the infrared sensor device is abnormal, infrared thermal images of the outside of the electrical equipment are further collected by the infrared sensor device installed outside the equipment, and the infrared fault recognition model outside the electrical equipment is used to identify whether the electrical equipment is damaged and output the recognition result of the infrared fault recognition model outside the electrical equipment.

4. The method for automatic identification of equipment faults based on infrared thermal imaging according to claim 3 is characterized in that: Before identifying whether the electrical equipment is damaged by using the external infrared fault identification model of the electrical equipment, the following steps are also included: Based on the infrared sensor equipment fault identification model, it is used to identify whether the infrared sensor equipment installed outside the electrical equipment is faulty; If the identification result is a fault, after replacing the infrared sensing device outside the device, the infrared fault identification model outside the device is further used to identify whether the electrical device is damaged; If the identification result is normal, the external infrared fault identification model of the electrical equipment is used to identify whether the electrical equipment is damaged.

5. The method for automatic identification of equipment faults based on infrared thermal imaging according to claim 1 is characterized in that: Infrared sensing equipment uses infrared thermal imagers or infrared sensors.

6. The method for automatic identification of equipment faults based on infrared thermal imaging according to claim 2 is characterized in that: The training of the model is specifically to train the model through its learning algorithm, and the machine learning algorithm includes convolutional neural network and support vector machine.

7. An automatic equipment fault identification system based on infrared thermal imaging, characterized in that: The method applied to any one of claims 1 to 6 comprises: The data acquisition unit includes an infrared sensor device installed inside the electrical equipment, which is used to collect infrared thermal images inside the equipment and transmit the infrared thermal images to the model training unit and the model recognition unit; The model training unit is connected to the data acquisition unit and the model recognition unit. The model training unit trains the deep neural network based on the infrared thermal imaging data collected by the data acquisition unit, thereby obtaining an infrared fault recognition model in the electrical equipment that can identify whether the electrical equipment has a fault, and transmits the infrared fault recognition model in the electrical equipment to the equipment recognition unit. The model recognition unit is connected to the model training unit, the data acquisition unit and the communication unit. The model recognition unit recognizes the infrared thermal imaging in the device collected in real time by the data acquisition unit based on the infrared fault recognition model in the electrical device output by the model training unit, and outputs the result of whether the electrical device has a fault. A communication unit is connected to the model recognition unit and the terminal, and transmits the output result of the model recognition unit to the terminal; The terminal receives the output result from the model recognition unit based on the communication unit.

8. The automatic equipment fault identification system based on infrared thermal imaging according to claim 7 is characterized in that: The model training unit also collects infrared image data of the infrared sensing device in normal working state and damaged state, and trains to generate a fault recognition model of the infrared sensing device; it also collects infrared thermal imaging of the outside of the electrical equipment, extracts key features in the thermal imaging image after data preprocessing, and then generates an external infrared fault recognition model of the electrical equipment based on deep neural network training.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is running, the device where the computer-readable storage medium is located is controlled to execute the method for automatic identification of equipment faults based on infrared thermal imaging according to any one of claims 1 to 6.

10. A processor, characterized in that: The processor is used to run a program, wherein when the program is run, the method for automatically identifying equipment faults based on infrared thermal imaging as described in any one of claims 1 to 6 is executed.

Images