Infrared image abnormality recognition method and system for electrical equipment based on parallel operation characteristics

Abstract

The application provides an electrical equipment infrared image abnormality recognition method and system based on parallel operation characteristics, belongs to the technical field of image abnormality recognition, and acquires an infrared image of electrical equipment in parallel operation; an acquired infrared image is processed by using a pre-trained abnormality recognition model to obtain a recognition result of whether the electrical equipment is abnormal or not. The application utilizes a YOLO target detection algorithm to accurately segment key components of equipment, and then combines an improved region growing algorithm to position an abnormal temperature region in the infrared image. By fully utilizing the high consistency of two parallel equipment in electrical response and thermodynamic behavior, even under the condition of no fault sample, a local temperature abnormality region can be accurately recognized, and new technical support is provided for online state monitoring and intelligent operation and maintenance of electrical equipment.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image anomaly recognition, and in particular to an electrical equipment infrared image anomaly recognition method and system based on parallel operation characteristics. BACKGROUND

[0002] The traction power supply system is the core energy hub of urban rail transit, and the operation state of the key power equipment directly affects the safe and reliable operation of the whole system. In the long-term service process, due to factors such as electrical insulation deterioration and mechanical stress accumulation, abnormal temperature rise may occur at the key parts of the equipment, which may cause a chain of failures. The infrared thermal imaging technology has become an important means of equipment state monitoring due to its non-contact, real-time and high sensitivity. However, the traditional infrared thermal fault detection method mainly relies on manual inspection, and therefore has the problems of low efficiency and high false detection rate.

[0003] Deep learning technology has strong signal processing capability and is widely used in infrared image fault diagnosis of electrical equipment. However, the recognition algorithm based on deep learning needs a large number of fault samples to train the model, but the fault samples are extremely scarce in actual operation, which to some extent limits the actual application effect of the deep learning method.

[0004] In the traction power supply system of urban rail transit, two same type devices (such as transformers, rectifiers, switch cabinets, etc.) usually adopt parallel operation mode, and their electrical parameters, load conditions and operating environments are highly consistent, and they are coupled with each other, so that the two parallel devices show strong comparability in electrical response and thermodynamic behavior. Theoretical analysis and engineering practice show that under normal operating conditions, the temperature distribution of the two parallel devices is basically consistent, and once one of them fails, the local temperature field will deviate from the normal state, which provides a solid theoretical basis for anomaly detection based on difference analysis. By comparing the temperature symmetry difference between the parallel devices, the dependence of the model on the fault sample data is significantly reduced. SUMMARY

[0005] The present application aims to provide an electrical equipment infrared image anomaly recognition method and system based on parallel operation characteristics to solve at least one of the technical problems in the background.

[0006] To achieve the above-mentioned purpose, the present application adopts the following technical solutions:

[0007] In a first aspect, the present application provides an electrical equipment infrared image anomaly recognition method based on parallel operation characteristics, comprising:

[0008] obtaining an infrared image of an electrical equipment in parallel operation;

[0009] The acquired infrared image is processed by using a pre-trained abnormality recognition model to obtain a recognition result of whether the electrical equipment is abnormal; wherein the abnormality recognition model comprises a segmentation network and a recognition network; the segmentation network is used to segment the key components of the electrical equipment by using a YOLOv8 target detection algorithm; the recognition network is used to detect the abnormal temperature of the electrical equipment by using an improved region growing algorithm, and the improved region growing algorithm comprises an initialization stage, a region growing stage and a post-processing stage; in the initialization stage, adaptive selection of seed points is performed; in the region growing stage, the current seed point is taken as the center, the temperature mean and standard deviation of the local window are calculated, and the growth threshold is dynamically adjusted in combination with the temperature gradient; in the post-processing stage, the preliminary segmentation result is optimized, the small growing regions are removed, and the neighborhood abnormality caused by noise interference is avoided.

[0010] As a further limitation of the first aspect of the application, the YOLOv8 target detection algorithm is used to segment the key components of the electrical equipment, including: pre-training the YOLOv8 model using the COCO dataset, setting the training rounds to 100 rounds, the batch size to 16, saving the best weight in the best round after training is completed; using LabelImg External Tools to label the collected electrical equipment infrared image dataset, constructing a YOLO format labeled dataset, and inputting it into the model for fine-tuning training, setting the fine-tuning rounds to 50 rounds, the batch size to 32, improving the recognition accuracy of the model for the specific task of electrical equipment infrared image recognition, and realizing accurate segmentation of the electrical equipment components.

[0011] As a further limitation of the first aspect of the application, in the initialization stage, adaptive selection of seed points is performed, including: converting the infrared temperature matrix T(x,y) to the frequency domain by two-dimensional Fourier transform to generate a complex spectrum containing spatial frequency distribution information, taking the logarithm operation of the spectrum amplitude and fitting its smooth component using a Gaussian smoothing kernel; by calculating the residual of the logarithmic spectrum and the smooth component, the high-frequency component representing local abnormal temperature change is separated out.

[0012] As a further limitation of the first aspect of the application, after inverse Fourier transform is performed on the residual, a heat map reflecting the saliency of temperature distribution is generated, the pixel regions with high saliency values are extracted as primary candidate regions, and the pixel temperature values p(x,y) in the candidate regions are analyzed by using a K-means clustering algorithm; the clustering center is iteratively optimized until the convergence condition is met; after locking the highest temperature class C3 as the target cluster, the high-temperature pixel points with high temperature distribution are extracted as candidate seeds, and the spatial distribution of the candidate seeds is verified for connectivity, the local temperature consistency of the candidate seeds is tested, and isolated points are removed, and finally the verified points are used as the initial seeds of the growing algorithm.

[0013] As a further limitation of the first aspect of the application, in the region growing stage, the temperature mean and standard deviation are calculated in a 7x7 local window centered on the current seed point, and the growth threshold is dynamically adjusted in combination with the temperature gradient; for the pixel p(x, y) to be grown, a temperature and gradient dual feature fusion criterion is introduced for similarity determination, and when S(p) < 1, it is determined that the pixel belongs to an abnormal region and is included in the growth range; during the growth process, if the gradient amplitude ||G p (x, y)|| of the current pixel exceeds the dynamic threshold G th , and there are at least 3 strong edge points in its 8-neighborhood, then the growth in that direction is terminated to prevent cross-region false merging.

[0014] As a further limitation of the first aspect of the application, in the post-processing stage, the preliminary segmentation result is optimized to remove small growing regions and avoid neighborhood abnormalities caused by noise interference: if the number of pixels contained in a region is less than a set threshold, the region is removed.

[0015] In a second aspect, the application provides an electrical equipment infrared image anomaly recognition system based on parallel operation characteristics, comprising:

[0016] An acquisition module is configured to acquire an infrared image of electrical equipment in parallel operation.

[0017] A processing module is configured to process the acquired infrared image using a pre-trained anomaly recognition model to obtain a recognition result of whether the electrical equipment is abnormal; wherein the anomaly recognition model comprises a segmentation network and a recognition network; the segmentation network is configured to segment key components of the electrical equipment using a YOLOv8 target detection algorithm; the recognition network is configured to detect abnormal temperature of the electrical equipment using an improved region growing algorithm, which comprises an initialization stage, a region growing stage, and a post-processing stage; in the initialization stage, adaptive selection of seed points is performed; in the region growing stage, the temperature mean and standard deviation are calculated in a local window centered on the current seed point, and the growth threshold is dynamically adjusted in combination with the temperature gradient; in the post-processing stage, the preliminary segmentation result is optimized to remove small growing regions and avoid neighborhood abnormalities caused by noise interference.

[0018] In a third aspect, the application provides a non-transitory computer readable storage medium for storing computer instructions, which, when executed by a processor, implement the electrical equipment infrared image anomaly recognition method based on parallel operation characteristics as described in the first aspect.

[0019] In a fourth aspect, the present application provides a computer device, comprising a memory and a processor, the processor and the memory being in communication with each other, the memory storing program instructions executable by the processor, and the processor invoking the program instructions to execute the method for identifying infrared image abnormalities of electrical equipment based on parallel operation characteristics according to the first aspect.

[0020] In a fifth aspect, the present application provides an electronic device, comprising a processor, a memory and a computer program, wherein the processor is connected with the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory to make the electronic device execute instructions for realizing the method for identifying infrared image abnormalities of electrical equipment based on parallel operation characteristics according to the first aspect.

[0021] The present application has the following advantages: the YOLO target detection algorithm is used to accurately segment the key components of the equipment, and then the improved region growing algorithm is combined to locate the abnormal temperature region in the infrared image. By fully utilizing the high consistency of the two parallel devices in electrical response and thermodynamic behavior, even under the condition of no fault sample, the local temperature abnormal region can be accurately identified, which provides new technical support for the online state monitoring and intelligent operation and maintenance of electrical equipment.

[0022] The advantages of the additional aspects of the present application will be more apparent from the following description section or will be understood through the practice of the present application. BRIEF DESCRIPTION OF DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0024] Figure 1 The flowchart of the method for identifying infrared image abnormalities of electrical equipment based on parallel operation characteristics according to the embodiments of the present application.

[0025] Figure 2 The strategy diagram of the infrared image abnormality detection of the "comparison-identification" according to the embodiments of the present application.

[0026] Figure 3 The flowchart of the improved region growing algorithm according to the embodiments of the present application.

[0027] Figure 4 The flowchart of the adaptive seed point selection according to the embodiments of the present application. DETAILED DESCRIPTION

[0028] Embodiments of the present application will be described in detail below with reference to the attached drawings, which are given by way of illustration and thus do not limit the present application. In addition, the present application can be embodied in many different forms and should not be construed as being limited to the embodiments set forth herein. Rather, these embodiments are provided by way of example so that this disclosure will convey the principles and concepts of the present application to those skilled in the art.

[0029] Those skilled in the art will appreciate that unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0030] It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.

[0031] Those skilled in the art will appreciate that unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0032] In the description of the present application, the description of the terms "one embodiment", "some embodiments”, "an example”, "a specific example” or "some examples” etc. means that the specific feature, structure, material or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In addition, the specific feature, structure, material or characteristic described can be combined in any appropriate manner in any one or more embodiments or examples. Those skilled in the art can combine and combine the features of different embodiments or examples described in the specification and the features of different embodiments or examples, without contradiction.

[0033] In order to facilitate the understanding of the present application, the present application will be further explained and described in specific embodiments below in conjunction with the accompanying drawings, and the specific embodiments do not constitute a limitation on the embodiments of the present application.

[0034] Those skilled in the art should understand that the drawings are only schematic diagrams of the embodiments, and the components in the drawings are not necessarily necessary for the implementation of the present application.

[0035] Example 1

[0036] In this embodiment 1, first provide an electrical equipment infrared image anomaly recognition system based on parallel operation characteristics, comprising: an acquisition module for acquiring infrared images of electrical equipment in parallel operation; a processing module for processing the acquired infrared images using a pre-trained anomaly recognition model to obtain a recognition result of whether the electrical equipment is abnormal; wherein the anomaly recognition model comprises a segmentation network and a recognition network; the segmentation network is used to segment the key components of the electrical equipment using a YOLOv8 target detection algorithm; the recognition network is used to detect abnormal temperature of the electrical equipment using an improved region growing algorithm, which includes an initialization stage, a region growing stage and a post-processing stage, in the initialization stage, the adaptive selection of seed points is performed; in the region growing stage, taking the current seed point as the center, the local window is taken to calculate the temperature mean and standard deviation, and the growth threshold is dynamically adjusted combined with the temperature gradient; in the post-processing stage, the preliminary segmentation result is optimized, and the small growth region is removed to avoid the neighborhood anomaly caused by noise interference.

[0037] In this embodiment, the above system is used to realize an electrical equipment infrared image anomaly recognition method based on parallel operation characteristics, comprising: acquiring infrared images of electrical equipment in parallel operation; processing the acquired infrared images using a pre-trained anomaly recognition model to obtain a recognition result of whether the electrical equipment is abnormal; wherein the anomaly recognition model comprises a segmentation network and a recognition network; the segmentation network is used to segment the key components of the electrical equipment using a YOLOv8 target detection algorithm; the recognition network is used to detect abnormal temperature of the electrical equipment using an improved region growing algorithm, which includes an initialization stage, a region growing stage and a post-processing stage, in the initialization stage, the adaptive selection of seed points is performed; in the region growing stage, taking the current seed point as the center, the local window is taken to calculate the temperature mean and standard deviation, and the growth threshold is dynamically adjusted combined with the temperature gradient; in the post-processing stage, the preliminary segmentation result is optimized, and the small growth region is removed to avoid the neighborhood anomaly caused by noise interference.

[0038] The YOLOv8 target detection algorithm is used to segment the key components of the electrical equipment, including: the YOLOv8 model is pre-trained using the COCO dataset, the training number is set to 100 rounds, the batch size is 16, and the best weight in all rounds is saved after training; the collected electrical equipment infrared image dataset is labeled using LabelImg External Tools, a YOLO format labeled dataset is constructed, and it is input into the model for fine-tuning training, the fine-tuning number is set to 50 rounds, the batch size is 32, the recognition accuracy of the model for the specific task of electrical equipment infrared image recognition is improved, and accurate segmentation of the electrical equipment components is realized.

[0039] In the initialization stage, adaptive selection of seed points is performed, including: converting the infrared temperature matrix T(x, y) to the frequency domain by two-dimensional Fourier transform to generate a complex spectrum containing spatial frequency distribution information, taking the logarithm operation of the spectrum amplitude and fitting its smooth component using a Gaussian smoothing kernel; by calculating the residual of the logarithmic spectrum and the smooth component, the high-frequency component representing the local abnormal temperature change is separated out.

[0040] After inverse Fourier transform of the residual, a heat map reflecting the significance of temperature distribution is generated, and the pixel regions with high significance values are extracted as primary candidate regions. For the pixel temperature values p(x, y) in the candidate regions, a multi-modal analysis is performed using the K-means clustering algorithm; the clustering centers are iteratively optimized until the convergence condition is met; after locking the highest temperature class C3 as the target cluster, the high-temperature pixel points with high temperature distribution are extracted as candidate seeds, and the spatial distribution of the candidate seeds is verified for connectivity. The local temperature consistency of the candidate seeds is tested, and isolated points are removed. Finally, the verified points are used as the initial seeds of the growth algorithm.

[0041] In the region growing stage, the temperature mean and standard deviation are calculated in a 7x7 local window centered on the current seed point, and the growth threshold is dynamically adjusted combined with the temperature gradient. For the pixel p(x, y) to be grown, a temperature and gradient dual-feature fusion criterion is introduced for similarity determination. When S(p) < 1, it is determined that the pixel belongs to the abnormal region and is included in the growth range. During the growth process, if the gradient amplitude ||G p (x, y)|| of the current pixel exceeds the dynamic threshold G th , and there are at least 3 strong edge points in its 8-neighborhood, then the growth in that direction is terminated to prevent cross-region false merging.

[0042] In the post-processing stage, the preliminary segmentation result is optimized to remove small growth regions and avoid neighborhood anomalies caused by noise interference: if the number of pixel points contained in a region is less than a certain threshold, the region is removed.

[0043] Embodiment 2

[0044] The embodiment provides an equipment infrared image anomaly recognition method based on parallel operation characteristics, which realizes accurate positioning of the thermal fault region of the electrical equipment infrared image. The method comprises the following steps: S1, collecting infrared images of electrical equipment under different early faults through fault simulation experiments, and constructing a corresponding infrared image dataset. S2, preprocessing the original infrared image dataset and appropriately expanding the dataset. S3, building an equipment infrared image anomaly recognition model based on parallel operation characteristics. S4, inputting the infrared image dataset into the built model to verify the performance of the model in infrared image anomaly region detection.

[0045] Further, the infrared image dataset in S1 includes common electrical faults and mechanical faults, and infrared image data in normal operation state. The raw data in S2 is preprocessed using temperature-driven cropping technology, and the image resolution is uniformly adjusted to 512×384. The data augmentation method in S2 is specifically: using mirror and rotation technology for image augmentation. In S3, based on the consistency of parallel operation of electrical equipment, an abnormality detection strategy of "contrast-recognition" is proposed, the key component segmentation is performed through YOLOv8 target detection algorithm, and the abnormal area recognition is performed based on the improved region growing algorithm, so as to build an infrared image abnormality recognition model of equipment based on parallel operation characteristics. In S4, the model is used to realize the recognition of abnormal area of infrared image of electrical equipment, based on the consistency of thermodynamic behavior of parallel operation electrical equipment, if two parallel equipment are normal, no abnormal area will be divided, if one of them has thermal fault, an overheating area will be divided.

[0046] As shown in Figure 1 , the infrared image abnormality recognition method of equipment based on parallel operation characteristics proposed in the embodiment specifically includes the following steps:

[0047] Step one: collect the infrared images of electrical equipment in typical electrical faults, mechanical faults and normal operation state through infrared thermal imager, and construct the corresponding infrared image dataset. The sampling interval is set to 2 minutes to ensure the coverage of the early temperature rise stage of fault development. The collected raw infrared image contains temperature matrix data, and the temperature value T p of each pixel point p(x,y) is calculated by the following formula:

[0048] I p = 0.299M r + 0.587M g + 0.114M b

[0049] b = T max -kY max

[0050] T p =k·I p +b

[0051] Where I p is the pixel gray value, M i is the matrix of different color channels extracted, r, g, b represent red, green and blue color channels respectively. k and b are the linear coefficients corresponding to the actual temperature value and the image gray value, T max and T min are the maximum and minimum values of the temperature value in the thermal imager software, Y max and Ymin The maximum and minimum values in the grayscale image.

[0052] Step two: Firstly, in order to solve the problem of background interference in the original infrared image, the temperature distribution histogram of the whole infrared image is calculated and analyzed, and the temperature T p The top 10% high-temperature pixel area;

[0053] Then, morphological closing operation is performed on the high-temperature pixels to connect the discrete areas, and the largest connected region is extracted as the main position of the electrical equipment. The formula of morphological closing operation is:

[0054]

[0055] wherein, represents the expansion operation, ° represents the corrosion operation, and B is a 5x5 circular structural element.

[0056] Then, the minimum circumscribed rectangle is generated, and a 10% boundary is expanded around the center of the rectangle to complete the initial cropping, and the main body of the electrical equipment and the key heat components are retained.

[0057] On this basis, geometric expansion operation is performed on the cropped non-standard size image: through horizontal mirror reflection simulation of different observation angles, random rotation within ±60° is applied, and bicubic interpolation is used to maintain temperature continuity to avoid introducing false temperature values. The interpolation formula is:

[0058]

[0059] wherein, w ij (x, y) is the weight coefficient of bicubic interpolation.

[0060] Finally, all the expanded images are uniformly scaled to 512x384 resolution, which provides higher pixel density and retains more target feature details without changing the proportion of the infrared image.

[0061] Step three: Since the two parallel electrical equipment have high similarity in design parameters and load distribution. This characteristic makes the two parallel equipment in the same substation be regarded as "twins" in design, operation and performance. Therefore, an "contrast-identification" abnormality detection strategy is proposed, and an electrical equipment infrared image abnormality recognition model is built based on this strategy, as shown in Figure 2 .

[0062] The YOLOv8 target detection algorithm is used to segment the key components of the electrical equipment, which lays the foundation for the comparison of the same type and position infrared images of the two parallel electrical equipment. The specific steps of segmentation are as follows:

[0063] First, the COCO dataset is used to pre-train the YOLOv8 model, set the training rounds to 100 rounds, the batch size to 16, and save the best weight in all rounds after training.

[0064] Secondly, the LabelImg External Tools is used to label the collected electrical equipment infrared image dataset, build a YOLO format labeled dataset, and input it into the model for fine-tuning training, set the fine-tuning rounds to 50 rounds, the batch size to 32, so as to improve the recognition accuracy of the model for the specific task of electrical equipment infrared image recognition, and realize the accurate segmentation of electrical equipment components.

[0065] After completing the above component segmentation, the improved region growing algorithm is used for electrical equipment abnormal temperature detection. The region growing algorithm mainly includes initialization, region growing and post-processing three stages, and the specific process is as shown in Figure 3 .

[0066] In the initialization stage, the adaptive selection of seed points is carried out, and the specific process is as shown in Figure 4 . First, the infrared temperature matrix T(x, y) processed by the above method is converted to the frequency domain through two-dimensional Fourier transform to generate a complex spectrum containing spatial frequency distribution information.

[0067]

[0068] Where (u, v) is the frequency domain coordinate, and F(u, v) is the complex spectrum.

[0069] On this basis, the logarithmic operation is taken on the spectrum amplitude, and the Gaussian smoothing kernel G σ (σ=3) is used to fit its smooth component L smooth .

[0070] L smooth (u, v) = log |F(u, v)| × G σ

[0071] By calculating the residual R of the logarithmic spectrum and the smooth component, the high-frequency component representing local abnormal temperature change is effectively separated.

[0072] R(u, v) = log |F(u, v)| - L smooth (u, v)

[0073] After inverse Fourier transform of the residual, a heat map reflecting the saliency of temperature distribution is generated, and the top 20% of pixel regions of the saliency value S are extracted as the primary candidate area.

[0074] S(x, y) = Re[F -1 {exp(R(u, v) + i·φ(u, v)}]

[0075] where Φ(u,v) is the original phase spectrum.

[0076] After obtaining the saliency candidate region, the pixel temperature value p(x,y) in the candidate region is analyzed by using the K-means clustering algorithm, and the objective function is:

[0077]

[0078] where C k represents the kth cluster, μ k is the cluster center temperature, and three cluster centers background temperature area, normal heating area and potential fault area are set to correspond to μ1=T 50％ , μ2=T 75％ , and μ3=T 90％ .

[0079] The cluster centers are iteratively optimized until the convergence condition is met:

[0080]

[0081] After locking the temperature highest class C3 as the target cluster, the temperature distribution of the top 5% of extreme high temperature pixel points P candidate are extracted as candidate seeds:

[0082] P candidate ={T p ∈C3|T p > μ3+1.645σ3}

[0083] The spatial distribution of the candidate seeds is verified for connectivity, and the local temperature consistency of the candidate seeds is tested to remove isolated points:

[0084] and

[0085] The temperature fluctuation in the 5x5 region N5 around the seed point is required to be no more than 3℃, and the average temperature is required to be more than 1.2 times of the global average temperature μ global , so as to exclude the interference of environmental heat sources, and the finally verified points are used as the initial seeds of the growth algorithm.

[0086] Then the region growing phase is entered. Taking the current seed point as the center, the temperature mean μ local and standard deviation σ local are calculated in a 7x7 local window, and the growth threshold is dynamically adjusted in combination with the temperature gradient:

[0087]

[0088] where, G x and G y are convolved with the temperature image to obtain.

[0089]

[0090] For the pixel p(x, y) to be grown, a temperature and gradient double feature fusion criterion is introduced to make a similarity determination. When S(p) < 1, it is determined that the pixel belongs to an abnormal region and is included in the growth range.

[0091]

[0092]

[0093] where T seed is the average temperature of the current region, cos θ is the cosine similarity of the pixel gradient direction and the average gradient direction of the region, and ||G

[0094] During the growth process, if the gradient amplitude ||G p (x, y) of the current pixel exceeds the dynamic threshold G th , and there are at least 3 strong edge points in its 8-neighborhood, then the growth in that direction is immediately terminated to prevent cross-region false merging.

[0095] G th = 0.2 x max(G)

[0096] where G is the Sobel gradient amplitude of the entire image.

[0097] Finally, the post-processing stage is entered to optimize the preliminary segmentation result, remove small growth regions, and avoid the inclusion of neighborhood abnormalities caused by noise interference. Assuming that a region R k contains A k pixel points, if the area is less than the set threshold A min , the region is removed.

[0098]

[0099]

[0100] where W x H is the image resolution, N scale is the scaling factor, and β is the safety factor.

[0101] After constructing the region growing algorithm, it is applied to the infrared image abnormal temperature detection of parallel electrical equipment to construct an equipment infrared image abnormal recognition model based on the parallel operation characteristics.

[0102] Step four: first, read the original infrared images A and B of two parallel running electrical equipment, and perform image cropping and other preprocessing. Second, use the key component segmentation in YOLO algorithm, then normalize the segmented image, and generate a difference image by difference. After obtaining the difference image, input the difference image into the region growing algorithm for recognition. Based on the consistency of the thermodynamic behavior of the parallel running electrical equipment, if both of the two parallel equipment are normal, the infrared images of A and B are the same, at this time the region growing algorithm should not divide any region; if one of them has a thermal fault, the region growing algorithm will automatically divide the different regions of the pixel points, that is, the over-temperature region is divided and recognized.

[0103] Embodiment 3

[0104] The embodiment 3 provides a non-transitory computer readable storage medium for storing computer instructions, which, when executed by a processor, implement an electrical equipment infrared image abnormality recognition method based on parallel operation characteristics as described above, the method comprising:

[0105] Obtaining infrared images of parallel running electrical equipment;

[0106] Processing the obtained infrared images by using a pre-trained abnormality recognition model to obtain a recognition result of whether the electrical equipment is abnormal; wherein the abnormality recognition model comprises a segmentation network and a recognition network; the segmentation network is used to segment the key components of the electrical equipment by using a YOLOv8 target detection algorithm; the recognition network is used to detect abnormal temperature of the electrical equipment by using an improved region growing algorithm, the improved region growing algorithm comprising an initialization stage, a region growing stage and a post-processing stage, in the initialization stage, the adaptive selection of seed points is performed; in the region growing stage, taking the current seed point as the center, the local window is used to calculate the temperature mean and standard deviation, and the growth threshold is dynamically adjusted combined with the temperature gradient; in the post-processing stage, the preliminary segmentation result is optimized, the small growing region is removed, and the neighborhood abnormality caused by noise interference is avoided.

[0107] Embodiment 4

[0108] The embodiment 4 provides a computer device, comprising a memory and a processor, the processor and the memory communicate with each other, the memory stores program instructions executable by the processor, and the processor calls the program instructions to execute an electrical equipment infrared image abnormality recognition method based on parallel operation characteristics as described above, the method comprising:

[0109] Obtaining infrared images of parallel running electrical equipment;

[0110] The acquired infrared image is processed by using a pre-trained abnormality recognition model to obtain a recognition result of whether the electrical equipment is abnormal; wherein the abnormality recognition model comprises a segmentation network and a recognition network; the segmentation network is used to segment key components of the electrical equipment by using a YOLOv8 target detection algorithm; the recognition network is used to detect abnormal temperature of the electrical equipment by using an improved region growing algorithm, the improved region growing algorithm comprises an initialization stage, a region growing stage and a post-processing stage, in the initialization stage, adaptive selection of seed points is performed; in the region growing stage, taking the current seed point as the center, the temperature mean and standard deviation are calculated in a local window, and the growth threshold is dynamically adjusted in combination with the temperature gradient; in the post-processing stage, the preliminary segmentation result is optimized, and small growth regions are removed to avoid that the neighborhood abnormality caused by noise interference is included.

[0111] Embodiment 5

[0112] The embodiment 5 provides an electronic device, comprising: a processor, a memory and a computer program; wherein the processor is connected with the memory, and the computer program is stored in the memory; when the electronic device is running, the processor executes the computer program stored in the memory, so that the electronic device executes instructions for realizing an electrical equipment infrared image abnormality recognition method based on parallel operation characteristics as described above, the method comprising:

[0113] An infrared image of the electrical equipment in parallel operation is acquired;

[0114] The acquired infrared image is processed by using a pre-trained abnormality recognition model to obtain a recognition result of whether the electrical equipment is abnormal; wherein the abnormality recognition model comprises a segmentation network and a recognition network; the segmentation network is used to segment key components of the electrical equipment by using a YOLOv8 target detection algorithm; the recognition network is used to detect abnormal temperature of the electrical equipment by using an improved region growing algorithm, the improved region growing algorithm comprises an initialization stage, a region growing stage and a post-processing stage, in the initialization stage, adaptive selection of seed points is performed; in the region growing stage, taking the current seed point as the center, the temperature mean and standard deviation are calculated in a local window, and the growth threshold is dynamically adjusted in combination with the temperature gradient; in the post-processing stage, the preliminary segmentation result is optimized, and small growth regions are removed to avoid that the neighborhood abnormality caused by noise interference is included.

[0115] Those skilled in the art will appreciate that embodiments of the present application can be readily used as software, hardware, or a combination of software and hardware. In a software embodiment, the present application can be implemented with computer-executable instructions, such as programs stored in memory of a computer and executed by a processor of the computer. Of course, the present application is not limited to software implementations.

[0116] The present application is described in relation to flow diagrams and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the present application. It is understood that each block of the flow diagrams and / or block diagrams, and combinations of blocks in the flow diagrams and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flow diagrams and / or block diagrams block or blocks. Figure 1 one or more functions specified by one or more blocks Figure 1 one or more functions specified by one or more blocks.

[0117] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the flow diagrams and / or block diagrams block or blocks. Figure 1 one or more functions specified by one or more blocks Figure 1 one or more functions specified by one or more blocks.

[0118] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the flow diagrams and / or block diagrams block or blocks. Figure 1 one or more functions specified by one or more blocks Figure 1 one or more functions specified by one or more blocks.

[0119] The above description is implemented with reference to the accompanying drawings, and is not intended to limit the scope of the present application. Those skilled in the art should understand that various modifications or variations can be made to the disclosed technical solutions without departing from the scope of the present application.

Claims

1. An electrical equipment infrared image abnormality recognition method based on parallel operation characteristics, characterized in that, The method comprises the steps of: acquiring infrared images of electrical equipment running in parallel; processing the acquired infrared images by using a pre-trained abnormality recognition model to obtain a recognition result of whether the electrical equipment is abnormal; wherein the abnormality recognition model comprises a segmentation network and a recognition network; the segmentation network is used to segment key components of the electrical equipment by using a YOLOv8 target detection algorithm; the recognition network is used to detect abnormal temperatures of the electrical equipment by using an improved region growing algorithm, which comprises an initialization stage, a region growing stage and a post-processing stage; in the initialization stage, adaptive selection of seed points is performed; in the region growing stage, taking the current seed point as the center, the temperature mean and standard deviation of the local window are calculated, and the growth threshold is dynamically adjusted in combination with the temperature gradient; in the post-processing stage, the preliminary segmentation result is optimized, and small growing regions are removed to avoid the inclusion of neighborhood abnormalities caused by noise interference; wherein removing the small growing regions comprises: assuming that the number of pixel points contained in a region is less than a minimum region area threshold, the region is removed.

2. The method according to claim 1, wherein The YOLOv8 target detection algorithm is used to segment the key components of the electrical equipment, which comprises the following steps: the YOLOv8 model is pre-trained by using the COCO dataset, the training rounds are set to 100 rounds, the batch size is set to 16, and after the training is completed, the best weight in all rounds is saved; the collected electrical equipment infrared image dataset is labeled by using LabelImg External Tools, a YOLO format labeled dataset is constructed, and the labeled dataset is input into the model for fine-tuning training; the fine-tuning rounds are set to 50 rounds, the batch size is set to 32, the recognition accuracy of the model for the specific task of electrical equipment infrared image recognition is improved, and accurate segmentation of the electrical equipment components is realized.

3. The method according to claim 1, wherein In the initialization stage, adaptive selection of seed points is performed, which comprises the following steps: the infrared temperature matrix T(x,y) is converted to the frequency domain by two-dimensional Fourier transform to generate a complex spectrum containing spatial frequency distribution information, the logarithmic operation is performed on the spectrum amplitude, and the smooth component is fitted by using a Gaussian smoothing kernel; the high-frequency component representing local abnormal temperature change is separated by calculating the residual of the logarithmic spectrum and the smooth component.

4. The method according to claim 3, wherein After inverse Fourier transform of the residual, a heat map reflecting the saliency of temperature distribution is generated, the pixel regions with high saliency values are extracted as primary candidate regions, the pixel temperature values p(x,y) in the candidate regions are analyzed by using the K-means clustering algorithm; the clustering centers are iteratively optimized until the convergence condition is met; after locking the highest temperature class C3 as the target cluster, the high-temperature pixel points with high temperature distribution are extracted as candidate seeds, the spatial distribution of the candidate seeds is verified for connectivity, the isolated points are removed, and finally the verified points are used as the initial seeds of the growing algorithm.

5. An abnormality recognition system for an electrical equipment infrared image based on parallel operation characteristics, characterized by, The method comprises the steps of: an acquisition module for acquiring infrared images of electrical equipment running in parallel; The processing module is configured to process the acquired infrared image by using a pre-trained abnormality recognition model to obtain a recognition result of whether the electrical equipment is abnormal, wherein the abnormality recognition model comprises a segmentation network and a recognition network; the segmentation network is configured to segment key components of the electrical equipment by using a YOLOv8 target detection algorithm; and the recognition network is configured to detect abnormal temperature of the electrical equipment by using an improved region growing algorithm, the improved region growing algorithm comprising an initialization stage, a region growing stage and a post-processing stage, in the initialization stage, adaptive selection of seed points is performed; in the region growing stage, a local window is taken to calculate a temperature mean value and a standard deviation with the current seed point as the center, and a growth threshold is dynamically adjusted in combination with a temperature gradient; and in the post-processing stage, a preliminary segmentation result is optimized, and a small growth region is removed to avoid a neighborhood abnormality caused by noise interference from being included; wherein the removing of the small growth region comprises: assuming that a number of pixel points contained in a region is less than a minimum region area threshold, the region is removed.

6. A non-transitory computer-readable storage medium, comprising, The non-transitory computer readable storage medium is configured to store computer instructions, which are executed by a processor to implement the electrical equipment infrared image abnormality recognition method based on parallel operation characteristics according to any one of claims 1-4.

7. A computer device, comprising: The electronic device comprises a memory and a processor, the processor and the memory are in communication with each other, the memory stores program instructions executable by the processor, and the processor invokes the program instructions to execute the electrical equipment infrared image abnormality recognition method based on parallel operation characteristics according to any one of claims 1-4.

8. An electronic device, comprising: The electronic device comprises: A processor, a memory and a computer program; wherein the processor is connected with the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory to enable the electronic device to execute instructions for implementing the electrical equipment infrared image abnormality recognition method based on parallel operation characteristics according to any one of claims 1-4.

Images