CN117115527A - Power equipment fault detection method and system based on infrared thermal imaging - Google Patents
Power equipment fault detection method and system based on infrared thermal imaging Download PDFInfo
- Publication number
- CN117115527A CN117115527A CN202311048542.1A CN202311048542A CN117115527A CN 117115527 A CN117115527 A CN 117115527A CN 202311048542 A CN202311048542 A CN 202311048542A CN 117115527 A CN117115527 A CN 117115527A
- Authority
- CN
- China
- Prior art keywords
- thermal imaging
- infrared thermal
- power equipment
- fault detection
- detection method
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001931 thermography Methods 0.000 title claims abstract description 68
- 238000001514 detection method Methods 0.000 title claims abstract description 37
- 238000004458 analytical method Methods 0.000 claims abstract description 27
- 238000000034 method Methods 0.000 claims abstract description 17
- 238000007781 pre-processing Methods 0.000 claims abstract description 6
- 238000004519 manufacturing process Methods 0.000 claims abstract description 5
- 238000010586 diagram Methods 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 8
- 238000012549 training Methods 0.000 claims description 8
- 230000002708 enhancing effect Effects 0.000 claims description 4
- 230000001629 suppression Effects 0.000 claims description 4
- 238000012360 testing method Methods 0.000 claims description 3
- 239000004744 fabric Substances 0.000 claims description 2
- 230000007547 defect Effects 0.000 abstract description 5
- 230000002159 abnormal effect Effects 0.000 abstract description 3
- 238000012545 processing Methods 0.000 description 9
- 238000004590 computer program Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000012805 post-processing Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 238000009826 distribution Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012821 model calculation Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000011179 visual inspection Methods 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 238000005315 distribution function Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Radiation Pyrometers (AREA)
Abstract
The application provides a power equipment fault detection method and system based on infrared thermal imaging, which relate to the technical field of power equipment state detection and comprise the following steps of S1: collecting and manufacturing a data set, and preprocessing, wherein the data set comprises original infrared thermal imaging of the power equipment; step S2: according to the preprocessed data set, a YOLOV5 model based on a PyTorch frame is established; step S3: and acquiring real-time infrared thermal imaging of the power equipment, inputting a YOLOV5 model based on PyTorch for predictive analysis, and judging whether early warning is needed according to an analysis result. The method can accurately capture the tiny defects or abnormal conditions on the surface of the power equipment, and meanwhile improves the reliability and consistency of detection.
Description
Technical Field
The application relates to the technical field of power equipment state detection, in particular to a power equipment fault detection method and system based on infrared thermal imaging.
Background
Whether the power equipment abnormally heats is a very important factor for judging whether the transformer substation can safely operate. Various equipment such as a voltage transformer and a current transformer in a transformer substation cause a lot of potential safety hazards due to various reasons such as aging and discharging, so that the equipment state maintenance problem is gradually paid attention to.
Conventional power equipment detection methods rely primarily on visual inspection and manual measurement, and have some limitations. First, visual inspection is limited by the ability of the human eye to perceive, and may not accurately capture microscopic defects or anomalies on the surface of the cannula. Second, manual measurement requires a lot of time and labor and is susceptible to operator skill levels, resulting in some degree of deviation in reliability and consistency of results.
Disclosure of Invention
Aiming at the defects of the prior art, the application provides the power equipment fault detection method and system based on infrared thermal imaging, which can accurately capture the tiny defects or abnormal conditions of the surface of the power equipment and improve the reliability and consistency of detection.
The technical scheme of the application is realized as follows:
an infrared thermal imaging-based power equipment fault detection method comprises the following steps:
step S1: collecting and manufacturing a data set, and preprocessing, wherein the data set comprises original infrared thermal imaging of the power equipment;
step S2: according to the preprocessed data set, a YOLOV5 model based on a PyTorch frame is established;
step S3: and acquiring real-time infrared thermal imaging of the power equipment, inputting a YOLOV5 model based on PyTorch for predictive analysis, and judging whether early warning is needed according to an analysis result.
Preferably, the pretreatment step of step S1 is as follows:
step S11: normalizing the data set;
step S12: performing histogram equalization operation on the image to improve contrast;
step S13: and filtering by using a Gaussian-Laplace operator, enhancing details, simultaneously ensuring that noise in the original data is inhibited to a certain extent, and overlapping the sharpened image with the original image after the sharpened image is obtained.
Preferably, in step S2, the preprocessed image is labeled, divided into a training set and a test set, and input into the YOLOV5 model for training.
Preferably, the preprocessed data set is input into the YOLOV5 model for training to generate a model file, and the model file is converted into a model file based on a pyrerch framework.
Preferably, in step S3, the image size of the collected real-time infrared thermal imaging data is set to 256×256, and the image size is input into a YOLOV5 model based on a pyrerch frame to extract features, obtain feature graphs with different dimensions, predict, judge the possibility of the target category according to the predicted value, and judge whether early warning is needed.
Preferably, the prediction in the YOLOV5 model based on the pyrerch framework is output by removing low confidence prediction, decoding a prediction frame, non-maximum suppression and filtering category probability.
Preferably, the predicted value includes a location coordinate of the bounding box, a category label, and a confidence score.
An infrared thermal imaging-based power equipment fault detection system comprises an image acquisition module, a model operation module, an Internet of things module and an early warning module; an image acquisition module: the system comprises a primary infrared thermal imaging module, a real-time infrared thermal imaging module and a real-time infrared thermal imaging module, wherein the primary infrared thermal imaging module is used for acquiring the power equipment;
model operation module: the method comprises the steps of establishing a YOLOV5 model based on a PyTorch frame and performing predictive analysis on real-time infrared thermal imaging of acquired power equipment;
and the early warning module is used for: the early warning device is used for early warning according to the prediction analysis result output by the model operation unit;
the internet of things module: the system comprises an image acquisition module, a model operation unit, a pre-warning unit and a pre-warning unit, wherein the image acquisition module is used for acquiring the original infrared thermal imaging and the real-time infrared thermal imaging of the power equipment, and the model operation unit is used for outputting the prediction analysis result of the model operation unit to the pre-warning unit.
Preferably, the image acquisition module adopts an intelligent cloth control ball.
Preferably, the model operation module comprises a CPU and an NPU, and the NPU is used for outputting the acquired infrared thermal imaging as a characteristic map; and the CPU is used for carrying out predictive analysis on the feature map output by the NPU.
Compared with the prior art, the application has the following advantages:
by adopting the scheme, the original infrared thermal imaging comprising the power equipment is collected, the original infrared thermal imaging is manufactured into a data set and is preprocessed, a YOLOV5 model based on a PyTorch frame is established according to the preprocessed data set so as to be used for carrying out predictive analysis on the collected real-time infrared thermal imaging of the power equipment, and finally, whether early warning is needed or not is judged according to an analysis result. The method can accurately capture the tiny defects or abnormal conditions on the surface of the power equipment, and meanwhile improves the reliability and consistency of detection.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the application, and that other drawings can be obtained according to these drawings without inventive faculty for a person skilled in the art.
FIG. 1 is a flow chart of an infrared thermal imaging-based power equipment fault detection method of the application;
FIG. 2 is a flowchart of the preprocessing of step S1;
FIG. 3 is a block diagram of an infrared thermal imaging based power equipment fault detection system of the present application;
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
In the description of the present application, it will be understood that the terms "comprises" and "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations, e.g., a and/or B, may represent: a exists alone, A and B exist together, and B exists alone. In addition, the character "/" herein generally indicates that the front and rear associated objects are an "or" relationship.
It should be understood that although the terms first, second, third, etc. may be used to describe the preset ranges, etc. in the embodiments of the present application, these preset ranges should not be limited to these terms. These terms are only used to distinguish one preset range from another. For example, a first predetermined range may also be referred to as a second predetermined range, and similarly, a second predetermined range may also be referred to as a first predetermined range without departing from the scope of embodiments of the present application.
Example 1
The application provides an infrared thermal imaging-based power equipment fault detection method, which is shown in fig. 1 and comprises the following steps:
step S1: collecting and manufacturing a data set, and preprocessing, wherein the data set comprises original infrared thermal imaging of the power equipment;
step S2: according to the preprocessed data set, a YOLOV5 model based on a PyTorch frame is established;
step S3: and acquiring real-time infrared thermal imaging of the power equipment, inputting a YOLOV5 model based on PyTorch for predictive analysis, and judging whether early warning is needed according to an analysis result.
In this embodiment, as shown in fig. 2, the preprocessing step of step S1 is as follows:
s11: the normalization operation is performed on the data set, and the step aims at normalizing the infrared thermal imaging data in the data set to ensure that the numerical range of the infrared thermal imaging data is in a uniform interval for subsequent processing. Normalization can be achieved by:
calculating the minimum value and the maximum value of all data in the data set;
the following formula is applied to normalize each data point in the dataset: normalized_value= (original_value-min_value)/(max_value-min_value), where original_value is the original value and min_value and max_value are the minimum and maximum values of the dataset.
S12: and carrying out histogram equalization operation on the image to improve the contrast ratio, wherein the histogram equalization can lead the pixel value distribution of the image to be more uniform, thereby improving the contrast ratio of the image. This step may be accomplished in the following manner:
converting an input image into a gray scale image;
calculating a histogram of the gray image to obtain the frequency distribution of each pixel value;
a Cumulative Distribution Function (CDF) is calculated and pixel values are remapped according to the CDF such that the pixel values are more evenly distributed.
S13: filtering using the gaussian-laplace operator, enhancing the details and superimposing, this step aims at enhancing the details of the image while reducing noise. The method can be carried out according to the following steps:
gaussian filtering is applied to the normalized and histogram equalized image to reduce noise;
applying a laplacian operator to the gaussian filtered image to enhance details of the image;
and superposing the image enhanced by the Laplacian operator with the original image so as to preserve the characteristics of the original image.
In this embodiment, in step S2, the preprocessed image is labeled and divided into a training set and a test set, the Filter, the Batch Size, the learning rate, the regularization parameters, the adjustment of the model structure and the enhancement of the data thereof of the YOLOV5 model are input into the YOLOV5 model after the adjustment for training, the '. Pt' model file is generated, and the '. Pt' model file is converted into the model file based on the PyTorch frame.
In the embodiment, in step S3, the image size of the collected real-time infrared thermal imaging data is set to 256×256, and the captured real-time infrared thermal imaging data is input into a YOLOV5 model based on a PyTorch frame to extract features, obtain feature graphs with different dimensions, predict, judge the possibility of belonging to a target class according to the predicted value, and judge whether early warning is needed. In a YOLOv5 model of the PyTorch, outputting boundary box position and category information of target detection in a prediction stage, wherein each boundary box is provided with a confidence coefficient score and category probability in the output prediction value, and the prediction comprises calculation of coordinate loss, category loss and confidence coefficient loss;
the coordinate loss is used for measuring the difference between the predicted boundary frame position and the actual boundary frame position, and the mean square error loss calculation is adopted, and the formula is as follows:
coordinate loss=1/N Σ [ for each sample ] (coordinate weight Σ [ for each bounding box ] (true position-predicted position)/(2))
The class loss is used for measuring the difference between the predicted class and the real class, and the cross entropy loss calculation is adopted, and the formula is as follows:
class loss = -1/N = -per sample Σper class [ (true class label × log (predicted class probability) + (1-true class label) × log (1-predicted class probability))
The confidence loss is used for measuring the difference between the confidence score of the prediction boundary box and the true confidence, and the mean square error loss calculation is also adopted, and the formula is as follows:
confidence loss = 1/N Σ [ for each sample ] (confidence weight Σ [ for each bounding box ] (true confidence-predictive confidence)/(2))
And the formulas of the mean square error loss and the cross entropy loss are respectively as follows:
wherein: n: sample number,Actual target value, (-) ->Target value of model prediction, C: category number, y ij : whether sample i belongs to category j (actual tag, 0 or 1), or +.>The model predicts the probability that sample i belongs to category j.
In this embodiment, prediction in the YOLOV5 model based on the pyrerch framework performs output of a predicted value by removing post-processing steps of low confidence prediction, decoding a prediction frame, non-maximum suppression, class probability filtering. Removing low confidence predictions, i.e., in YOLOv5, typically sets a threshold (e.g., 0.3 or 0.5) as the confidence threshold. All bounding boxes with confidence scores below this threshold will be filtered out, i.e. those targets with lower predicted confidence will be removed. The predicted frame position of the decoded predicted frame, YOLOv5 output, is relative to the size and coordinates of the input image. At the time of post-processing, the coordinates of these predicted frames are decoded to obtain the actual position on the original image. Non-maximal suppression (NMS) is a technique used to eliminate redundant overlapping prediction blocks. Which IOU (Intersection over Union) overlaps the larger other prediction block. The class probability filtering, namely, for each prediction frame, selects the class with the highest class probability as the final target class, and outputs the final target class together with the confidence of the prediction frame. Finally, the YOLOv5 model outputs the position coordinates, class labels and confidence scores of the filtered and decoded prediction bounding boxes through a post-processing step. This information will help determine the categories of objects present in the input image and their location, thereby performing object detection and recognition tasks. The target class may cover: electric wires, electric workers, electric vehicles, utility poles, high voltage cables, transformers, electric towers, electric equipment.
Example 2
The application also provides a power equipment fault detection system based on infrared thermal imaging, which is shown in fig. 3 and comprises an image acquisition module, a model operation module, an internet of things module and an early warning module;
an image acquisition module: the system comprises a primary infrared thermal imaging module, a real-time infrared thermal imaging module and a real-time infrared thermal imaging module, wherein the primary infrared thermal imaging module is used for acquiring the power equipment;
model operation module: the method comprises the steps of establishing a YOLOV5 model based on a PyTorch frame and performing predictive analysis on real-time infrared thermal imaging of acquired power equipment;
and the early warning module is used for: the early warning device is used for early warning according to the prediction analysis result output by the model operation unit;
the internet of things module: the system comprises an image acquisition module, a model operation unit, a pre-warning unit and a pre-warning unit, wherein the image acquisition module is used for acquiring the original infrared thermal imaging and the real-time infrared thermal imaging of the power equipment, and the model operation unit is used for outputting the prediction analysis result of the model operation unit to the pre-warning unit.
In this embodiment, the image acquisition module adopts an intelligent control ball, and the intelligent control ball has a dual-camera function of visible light and thermal imaging, and the visible light realizes high-definition zoom to control risk and observe equipment details of power field operation.
In this embodiment, the model operation module includes a CPU and an NPU, where the NPU is configured to output the acquired infrared thermal image as a feature map; the CPU is used for carrying out predictive analysis on the feature map output by the NPU.
In this embodiment, the early warning module includes an NPU, which is configured to preset rules, and output the target result output by the model operation module after further classification and analysis, that is, trigger a corresponding early warning notification or processing measure.
Principle of: the intelligent control ball is used for acquiring infrared images, and various target objects such as people, vehicles, animals and the like can be contained in the infrared images. These images are passed as inputs to the NPU of the model calculation module for analysis. The NPU of the model operation module is a hardware accelerator that uses YOLOV5 model for target detection and identification. The model operation module receives the infrared image as input, carries out convolution operation on the NPU of the model operation module, and outputs a characteristic diagram of the image through the inference process of the deep learning model. These feature maps are passed to the CPU of the model calculation module for further processing and analysis. The CPU of the model operation module processes the prediction frame in the feature map to identify the classification of the target object and the specific coordinate position of the target object on the image, and then superimposes the classification and the coordinate information of the target object on the original infrared image to generate an image with a target detection result. And the image with the target position and the category label becomes the output of the early warning module. The image with the target detection result is transmitted to the NPU of the early warning module for further analysis. The NPU of the early warning module performs further classification and analysis on the targets in the image according to a preset early warning rule, and then outputs the target, and the output generally triggers a corresponding early warning notification or processing measure. This may be an alarm, alarm information, image archiving, etc. for further processing or decision making.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, computer program product. Accordingly, the present application may take the form of an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus and computer program products according to embodiments of the application. It will be understood that each flowchart and/or block of the flowchart illustrations and/or block diagrams, and combinations of flowcharts and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may 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 flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may 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 instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may 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 functions specified in the flowchart and/or block diagram block or blocks.
The foregoing description of the preferred embodiments of the application is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the application.
Claims (10)
1. The utility model provides a power equipment fault detection method based on infrared thermal imaging which characterized in that: the method comprises the following steps:
step S1: collecting and manufacturing a data set, and preprocessing, wherein the data set comprises original infrared thermal imaging of the power equipment;
step S2: according to the preprocessed data set, a YOLOV5 model based on a PyTorch frame is established;
step S3: and acquiring real-time infrared thermal imaging of the power equipment, inputting a YOLOV5 model based on PyTorch for predictive analysis, and judging whether early warning is needed according to an analysis result.
2. The power equipment fault detection method based on infrared thermal imaging according to claim 1, wherein the method comprises the following steps: the pretreatment step of the step S1 is as follows:
step S11: normalizing the data set;
step S12: performing histogram equalization operation on the image to improve contrast;
step S13: and filtering by using a Gaussian-Laplace operator, enhancing details, simultaneously ensuring that noise in the original data is inhibited to a certain extent, and overlapping the sharpened image with the original image after the sharpened image is obtained.
3. The power equipment fault detection method based on infrared thermal imaging according to claim 1, wherein the method comprises the following steps: in the step S2, the preprocessed image is labeled, divided into a training set and a testing set, and input into a YOLOV5 model for training.
4. The power equipment fault detection method based on infrared thermal imaging according to claim 1, wherein the method comprises the following steps: in the step S2, the preprocessed data set is input into the YOLOV5 model for training to generate a model file, and the model file is converted into a model file based on the PyTorch framework.
5. The power equipment fault detection method based on infrared thermal imaging according to claim 1, wherein the method comprises the following steps: in the step S3, the image size of the collected real-time infrared thermal imaging data is set to 256×256, and the collected real-time infrared thermal imaging data is input into a CNN network in a YOLOV5 model based on a pyrerch frame to extract features, so as to obtain feature graphs with different dimensions, predict the feature graphs, judge the possibility of the target class according to the predicted value, and judge whether early warning is needed or not.
6. The power equipment fault detection method based on infrared thermal imaging according to claim 5, wherein the power equipment fault detection method based on infrared thermal imaging is characterized in that: prediction in the YOLOV5 model based on the pyrerch framework is output by removing low confidence prediction, decoding a prediction frame, non-maximum suppression and filtering category probability.
7. The power equipment fault detection method based on infrared thermal imaging according to claim 6, wherein the power equipment fault detection method based on infrared thermal imaging is characterized in that: the predicted values include location coordinates of the bounding box, class labels, and confidence scores.
8. An infrared thermal imaging-based power equipment fault detection system implemented by using an infrared thermal imaging-based power equipment fault detection method as claimed in any one of claims 1 to 7, wherein: the system comprises an image acquisition module, a model operation module, an Internet of things module and an early warning module;
an image acquisition module: the system comprises a primary infrared thermal imaging module, a real-time infrared thermal imaging module and a real-time infrared thermal imaging module, wherein the primary infrared thermal imaging module is used for acquiring the power equipment;
model operation module: the method comprises the steps of establishing a YOLOV5 model based on a PyTorch frame and performing predictive analysis on real-time infrared thermal imaging of acquired power equipment;
and the early warning module is used for: the early warning device is used for early warning according to the prediction analysis result output by the model operation unit;
the internet of things module: the system comprises an image acquisition module, a model operation unit, a pre-warning unit and a pre-warning unit, wherein the image acquisition module is used for acquiring the original infrared thermal imaging and the real-time infrared thermal imaging of the power equipment, and the model operation unit is used for outputting the prediction analysis result of the model operation unit to the pre-warning unit.
9. The power equipment fault detection method based on infrared thermal imaging according to claim 8, wherein the power equipment fault detection method based on infrared thermal imaging is characterized in that: the image acquisition module adopts intelligent cloth control balls.
10. The power equipment fault detection method based on infrared thermal imaging according to claim 8, wherein the power equipment fault detection method based on infrared thermal imaging is characterized in that: the model operation module comprises a CPU and an NPU, and the NPU is used for outputting the acquired infrared thermal imaging as a characteristic diagram; and the CPU is used for carrying out predictive analysis on the feature map output by the NPU.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311048542.1A CN117115527A (en) | 2023-08-18 | 2023-08-18 | Power equipment fault detection method and system based on infrared thermal imaging |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311048542.1A CN117115527A (en) | 2023-08-18 | 2023-08-18 | Power equipment fault detection method and system based on infrared thermal imaging |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117115527A true CN117115527A (en) | 2023-11-24 |
Family
ID=88804929
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311048542.1A Pending CN117115527A (en) | 2023-08-18 | 2023-08-18 | Power equipment fault detection method and system based on infrared thermal imaging |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117115527A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117409083A (en) * | 2023-12-14 | 2024-01-16 | 珠海市金锐电力科技有限公司 | Cable terminal identification method and device based on infrared image and improved YOLOV5 |
| CN117911401A (en) * | 2024-03-15 | 2024-04-19 | 国网山东省电力公司泗水县供电公司 | Power equipment fault detection method, system, storage medium and equipment |
-
2023
- 2023-08-18 CN CN202311048542.1A patent/CN117115527A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117409083A (en) * | 2023-12-14 | 2024-01-16 | 珠海市金锐电力科技有限公司 | Cable terminal identification method and device based on infrared image and improved YOLOV5 |
| CN117409083B (en) * | 2023-12-14 | 2024-03-22 | 珠海市金锐电力科技有限公司 | Cable terminal identification method and device based on infrared image and improved YOLOV5 |
| CN117911401A (en) * | 2024-03-15 | 2024-04-19 | 国网山东省电力公司泗水县供电公司 | Power equipment fault detection method, system, storage medium and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117115527A (en) | Power equipment fault detection method and system based on infrared thermal imaging | |
| CN111797890A (en) | Method and system for detecting defects of power transmission line equipment | |
| CN108664840A (en) | Image-recognizing method and device | |
| CN107782733A (en) | Image recognition the cannot-harm-detection device and method of cracks of metal surface | |
| CN110728681B (en) | Mura defect detection method and device | |
| US20220300809A1 (en) | Data generation system, learning apparatus, data generation apparatus, data generation method, and computer-readable storage medium storing a data generation program | |
| CN106407928A (en) | Transformer composite insulator bushing monitoring method and transformer composite insulator bushing monitoring system based on raindrop identification | |
| CN112364740B (en) | Unmanned aerial vehicle room monitoring method and system based on computer vision | |
| CN110120155A (en) | A kind of chemical industry plant area vehicle overload overload intelligent monitoring and alarming system | |
| CN114782892A (en) | Illegal behavior target detection method, device, equipment and storage medium | |
| CN116012762A (en) | Traffic intersection video image analysis method and system for power equipment | |
| CN110334775B (en) | Unmanned aerial vehicle line fault identification method and device based on width learning | |
| CN109102486B (en) | Surface defect detection method and device based on machine learning | |
| CN116542956B (en) | Automatic detection method and system for fabric components and readable storage medium | |
| CN113012107A (en) | Power grid defect detection method and system | |
| CN111428987A (en) | Artificial intelligence-based image identification method and system for relay protection device | |
| Li et al. | Pin bolt state identification using cascaded object detection networks | |
| CN115761606A (en) | Box electric energy meter identification method and device based on image processing | |
| CN114418983A (en) | Equipment risk detection method based on intelligent Internet of things | |
| CN113487538A (en) | Multi-target segmentation defect detection method and device and computer storage medium thereof | |
| CN113361470A (en) | Electric power external insulation equipment automatic positioning and identifying method based on deep learning | |
| CN112686162A (en) | Method, device, equipment and storage medium for detecting clean state of warehouse environment | |
| CN114911813B (en) | Updating method and device of vehicle-mounted perception model, electronic equipment and storage medium | |
| CN117764993B (en) | Water quality on-line monitoring system and method based on image analysis | |
| CN117409376B (en) | Infrared online monitoring method and system for high-voltage sleeve |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |