Fault self-diagnosis early warning method, device and system for intelligent electric box

Abstract

The invention relates to the technical field of equipment fault diagnosis, in particular to a fault self-diagnosis early warning method, equipment and system for an intelligent electric box, and the method comprises the steps: obtaining an infrared thermal imaging image in the intelligent electric box in real time; performing contour extraction on the infrared thermal imaging image at the current moment to obtain at least one contour area; screening an aging suspected area according to the temperature difference in each contour area; screening to obtain an aging region according to the heating expression of the suspected aging region in the historical time period; calculating the area and the position of the aging region according to the coordinate information corresponding to the aging region; and sending the temperature average value of the aging region at the current moment and the area and the position of the aging region to a preset terminal. According to the method, the contour region in the infrared thermal imaging image is obtained, and the suspected aging region is screened out; and then, verification is carried out according to the heating characteristics of the aging area to determine whether the aging area is the aging area, so that the identification of the abnormal temperature area in the intelligent electric box is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment fault diagnosis, and specifically to a fault self-diagnosis and early warning method, equipment and system for a smart electrical box. Background Art

[0002] The smart power box is a power management system based on the Internet of Things technology. Its core function is to achieve real-time monitoring, precise control and efficient management of electric energy through integrated sensors, communication equipment and intelligent algorithms. The main goal of this device is to ensure the rational allocation and use of power resources, thereby improving energy efficiency and reducing energy waste. Specifically, the smart power box can monitor a variety of key parameters including current, voltage, and power in real time, so that users can fully understand the power consumption and make corresponding adjustments and optimizations. Through these real-time data, users can better understand the patterns and trends of power consumption, and then take measures to reduce unnecessary power waste. In addition, the smart power box also has an abnormality detection function, which can promptly detect current overloads, voltage anomalies and other potential power problems, and quickly issue alarms so that users can take timely measures to avoid equipment damage or power accidents. This preventive measure greatly improves the safety and reliability of the power system.

[0003] However, despite the many advantages of smart power boxes in power management, some problems may occur when the internal wiring ages. Although the current, voltage and power parameters may appear normal on the surface and do not meet the triggering conditions of the abnormal detection function, the aging of such lines may actually have laid hidden dangers for equipment failure. Existing technical means are often unable to accurately diagnose and warn the specific location and potential failure risks of these aging lines. Summary of the invention

[0004] In order to solve the above technical problems, the purpose of the present invention is to provide a fault self-diagnosis and early warning method, device and system for a smart power box. In order to achieve the above purpose, the technical solution adopted by the present invention is as follows: In a first aspect, the present application provides a fault self-diagnosis and early warning method for a smart electric box, the method comprising: acquiring an infrared thermal imaging image inside the smart electric box in real time; performing contour extraction on the infrared thermal imaging image at a current moment to obtain at least one contour area; screening suspected aging areas according to the temperature difference in each of the contour areas; screening the aging areas according to the heating performance of the suspected aging areas in a historical time period; calculating the area and position of the aging areas according to the coordinate information corresponding to the aging areas; sending the average temperature of the aging area at the current moment, the area and position of the aging area to a preset terminal, the average temperature being calculated from the grayscale value of the infrared thermal imaging image of the aging area at the current moment.

[0005] In combination with the first aspect, in a possible implementation method, contour extraction is performed on the infrared thermal imaging image at the current moment to obtain at least one contour area, including: using an edge detection mathematical model to perform edge detection on the infrared thermal imaging image at the current moment to obtain a number of edge pixel points; based on all the edge pixel points, region extraction is performed in the infrared thermal imaging image at the current moment to obtain at least one contour area.

[0006] In combination with the first aspect, in a possible implementation manner, the edge detection mathematical model is a Sobel edge detection algorithm.

[0007] In combination with the first aspect, in a possible implementation method, the suspected aging area is screened according to the temperature difference in each of the contour areas, including: converting the grayscale values ​​contained in each of the contour areas into temperature values ​​one by one according to a preset temperature mapping formula; calculating the temperature difference of each of the contour areas according to the temperature values ​​in the contour areas; and judging the temperature difference of each of the contour areas one by one according to a preset first threshold to obtain the suspected aging area.

[0008] In combination with the first aspect, in a possible implementation method, the temperature difference of each contour area is calculated according to the temperature value in the contour area, including: counting the total number of contour areas in the infrared thermal imaging image at the current moment and the maximum temperature value in each contour area; performing mean calculation based on the temperature value in each contour area to obtain the average temperature value corresponding to each contour area; and calculating the temperature difference of each contour area according to a first preset formula, the total number of contour areas in the infrared thermal imaging image, the maximum temperature value in each contour area and the average temperature value corresponding to each contour area.

[0009] In combination with the first aspect, in a possible implementation manner, the preset first threshold is 0.8.

[0010] In combination with the first aspect, in a possible implementation method, the aging areas are screened out according to the heating performance of the suspected aging areas in the historical time period, including: converting the grayscale values ​​contained in each of the suspected aging areas into temperature values ​​one by one according to a preset temperature mapping formula; performing mean calculation based on the temperature values ​​in each of the suspected aging areas to obtain the average temperature value corresponding to each of the suspected aging areas; counting the number of operating days of the smart power box and the temperature value corresponding to each of the suspected aging areas at each historical moment in the historical time period; obtaining the auxiliary discrimination value corresponding to each of the suspected aging areas according to the number of operating days of the smart power box, the average temperature value corresponding to each of the suspected aging areas, and the temperature value at each historical moment; judging whether the suspected aging area is an aging area based on the auxiliary discrimination value corresponding to each of the suspected aging areas.

[0011] In combination with the first aspect, in a possible implementation method, whether the suspected aging area is an aging area is determined based on the auxiliary discrimination value corresponding to each of the suspected aging areas, and the method also includes: counting the number of temperature values ​​in the suspected aging area; performing mean calculation based on the temperature values ​​in the suspected aging area to obtain the average temperature value corresponding to the suspected aging area; performing variance calculation based on the temperature values ​​in the suspected aging area to obtain the variance corresponding to the suspected aging area; calculating the degree of temperature chaos corresponding to the suspected aging area according to the number of temperature values ​​corresponding to the suspected aging area, the temperature average value and the variance; and updating the auxiliary discrimination value based on the degree of temperature chaos corresponding to the suspected aging area.

[0012] In the second aspect, the present application also provides a fault self-diagnosis and early warning system for a smart electric box, including: an acquisition module, used to acquire the infrared thermal imaging image inside the smart electric box in real time; a contour extraction module, used to perform contour extraction on the infrared thermal imaging image at the current moment to obtain at least one contour area; a first screening module, used to screen suspected aging areas according to the temperature difference in each of the contour areas; a second screening module, used to screen the aging areas according to the heating performance of the suspected aging areas in a historical time period; an information calculation module, used to calculate the area and position of the aging area according to the coordinate information corresponding to the aging area; an early warning module, used to send the average temperature of the aging area at the current moment, the area and position of the aging area to a preset terminal, the average temperature being calculated from the grayscale value of the infrared thermal imaging image of the aging area at the current moment.

[0013] On the third aspect, the present application also provides a fault self-diagnosis and early warning device for a smart power box, comprising: a memory for storing a computer program; and a processor for implementing the steps of the fault self-diagnosis and early warning method of the smart power box when executing the computer program.

[0014] The present invention has the following beneficial effects: In the present invention, firstly, by acquiring the infrared thermal imaging image at the current moment, several contour areas in the image are identified and extracted. Then, according to the temperature difference of all contour areas in the infrared thermal imaging image at the current moment, a detailed temperature difference analysis and calculation are performed on each contour area. In this way, several possible suspected aging areas can be effectively screened out. Subsequently, according to the heating characteristics of the aging area under real conditions, each suspected aging area is further screened and verified to determine whether it actually belongs to the aging area. The aging area obtained based on the above steps has a high feasibility, so this information can be used to calculate the area, position and average temperature of the aging area. Finally, these accurate and reliable aging area information are used to provide strong support and guarantee for the fault self-diagnosis early warning system, ensure the accuracy and timeliness of the early warning, and effectively avoid the high temperature hazards caused by line aging. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 A schematic diagram of a flow chart of a fault self-diagnosis and early warning method for a smart electric box provided in Embodiment 1 of the present invention; Figure 2 A schematic flow chart of step S2 provided in Example 1 of the present invention; Figure 3 A schematic flow chart of step S3 provided in Example 1 of the present invention; Figure 4 A schematic flow chart of step S4 provided in Example 1 of the present invention; Figure 5 This is a structural diagram of the fault self-diagnosis and early warning system of the smart power box described in Example 2 of the present invention.

[0017] Figure 6 This is a schematic diagram of the structure of the fault self-diagnosis and early warning device of the smart power box described in Example 3 of the present invention.

[0018] Markings in the figure: 800, fault self-diagnosis and early warning device of the smart power box; 801, processor; 802, memory; 803, multimedia component; 804, I / O interface; 805, communication component. DETAILED DESCRIPTION

[0019] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the fault self-diagnosis and early warning method, device and system of a smart electric box proposed by the present invention, its specific implementation method, structure, characteristics and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0020] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0021] Embodiment 1:

[0022] The specific scheme of the fault self-diagnosis and early warning method of a smart electric box provided by the present invention is described in detail below with reference to the accompanying drawings.

[0023] See also Figure 1 , which shows a flow chart of a fault self-diagnosis and early warning method for a smart power box provided by an embodiment of the present invention. The figure shows that this embodiment includes steps S1 to S6.

[0024] S1. Obtain infrared thermal imaging images inside the smart electric box in real time; In this embodiment, the acquisition of infrared thermal imaging images is achieved through an infrared sensor installed inside the smart electrical box. The infrared sensor is responsible for capturing the temperature distribution inside the electrical box and converting the captured information into image data. In order to ensure the continuity and accuracy of the data, the smart electrical box automatically collects infrared thermal imaging image data every second during operation. In this way, this embodiment can obtain a series of infrared thermal imaging images at historical moments, as well as an infrared thermal imaging image corresponding to the latest current moment. These image data will be used for subsequent quantitative data analysis of the aging area in order to more accurately evaluate the temperature changes inside the electrical box.

[0025] In order to ensure the quality of infrared thermal imaging images, each infrared thermal imaging image is preprocessed in this embodiment. During the preprocessing process, the median filtering algorithm is used to remove noise points in the image. Median filtering is a nonlinear filtering technology that can effectively remove sharp noise in the image while retaining the edge information of the image, which is crucial for subsequent image analysis and accurate capture of temperature changes. By acquiring and preprocessing infrared thermal imaging images in real time, the temperature distribution inside the smart electric box can be monitored in real time, and any abnormal temperature changes can be captured in time, thereby ensuring the accuracy and reliability of the data.

[0026] S2, extracting the contour of the infrared thermal imaging image at the current moment to obtain at least one contour area; In this embodiment, the contour area extraction is achieved by combining the edge detection algorithm and the contour extraction algorithm. Figure 2 , the figure shows that step S2 includes steps S21 and S22.

[0027] S21, using an edge detection mathematical model to perform edge detection on the infrared thermal imaging image at the current moment to obtain a number of edge pixel points; It should be noted that, in this embodiment, the edge detection mathematical model is preferably the Sobel edge detection algorithm. Specifically, in this step, according to the grayscale value of the pixel in the infrared thermal imaging image at the current moment, the Sobel edge detection algorithm is used to detect the edge of the image. The Sobel algorithm is a classic image processing algorithm that extracts the edge in the image by calculating the gradient of the grayscale value of the image. At the same time, for those skilled in the art, in addition to the Sobel edge detection algorithm, other edge detection algorithms such as the Canny edge detection algorithm, the Prewitt edge detection algorithm, the Roberts edge detection algorithm, etc. can also be used. Those skilled in the art can make a choice according to the actual situation, and no specific restrictions are made in this embodiment.

[0028] In this embodiment, in order to achieve efficient edge detection, the Sobel edge detection algorithm is preferably used as a mathematical model for edge detection. Specifically, in the infrared thermal imaging image processing process at the current moment, the Sobel edge detection algorithm is used to perform edge detection based on the gray value of each pixel in the image. The Sobel algorithm is a classic algorithm widely used in the field of image processing. It effectively extracts edge information in the image by calculating the gray value gradient of each pixel in the image.

[0029] For those skilled in the art, in addition to the Sobel edge detection algorithm, there are many other edge detection algorithms to choose from, such as the Canny edge detection algorithm, the Prewitt edge detection algorithm, the Roberts edge detection algorithm, etc. These algorithms each have their own characteristics and applicable scenarios, and the technicians can flexibly select the most suitable edge detection algorithm according to specific application requirements and actual conditions. In this embodiment, no specific restrictions are made on the selected edge detection algorithm.

[0030] S22: performing region extraction in the infrared thermal imaging image at the current moment based on all the edge pixels to obtain at least one contour region.

[0031] Furthermore, in this step, region extraction is performed based on the use of a contour extraction algorithm. Specifically, in this embodiment, the contour extraction algorithm adopts a Douglas-Peucker algorithm, a Snake model, etc. Through precise edge detection and contour extraction, the boundaries and shapes in the infrared image can be accurately identified, providing clear region division for subsequent temperature difference analysis.

[0032] In this step, a contour extraction algorithm is further used to extract regions to ensure that the boundaries and shapes in the infrared image can be accurately identified. Specifically, in this embodiment, the Snake model is used for contour extraction. The Snake model dynamically adjusts the contour line through the energy minimization principle to adapt to the complex shapes and edges in the image, further improving the accuracy and reliability of contour extraction, thereby providing clear regional division for subsequent temperature difference analysis.

[0033] S3, screening suspected aging areas according to the temperature difference within each contour area; In this embodiment, it is considered that the aging of the internal circuit of the smart power box will cause the local temperature to rise, forming a significant temperature difference with other normal areas. Therefore, in this embodiment, a method based on temperature difference analysis is proposed. By detecting and analyzing the temperature distribution inside the smart power box, the suspected aging area can be effectively identified. This method helps to warn of potential line aging problems in advance and helps maintenance personnel quickly locate the problem area, so as to take corresponding maintenance measures to ensure the safe and stable operation of the smart power box. For details, please refer to Figure 3 , the figure shows steps S31 to S33 included in this step S3.

[0034] S31, converting the grayscale values ​​contained in each contour area into temperature values ​​one by one according to a preset temperature mapping formula; It should be noted that, since the infrared sensor directly outputs a grayscale image, the grayscale value of each pixel represents the radiation intensity of the point, rather than a direct temperature value. Therefore, in this step, it is also necessary to parse the temperature value from the grayscale value corresponding to each pixel in the contour area. Among them, the temperature mapping formula mentioned in this step is a mapping table or conversion formula of grayscale value and temperature provided by the infrared sensor manufacturer. Because it involves the infrared sensor calibration parameters and the atmospheric environment in which the infrared sensor is located. Therefore, the specific formula content is listed in this embodiment, and those skilled in the art can decide according to the actual use of the infrared sensor, and no specific restrictions are made in this embodiment.

[0035] It should be noted that the infrared sensor only has the function of directly outputting grayscale images. The grayscale value of each pixel in the image represents the radiation intensity of that point. However, these grayscale values ​​do not directly reflect the temperature value. Therefore, in the data processing stage, the temperature value must be parsed from the grayscale value.

[0036] In order to realize this analysis process, it is necessary to use a mapping table or conversion formula between grayscale value and temperature provided by the infrared sensor manufacturer. These mapping tables or formulas take into account factors such as the calibration parameters of the infrared sensor and the atmospheric environment in which the sensor is located. In view of the above-mentioned influencing factors, a specific temperature mapping formula is not provided in this embodiment. Technicians in this field should determine the appropriate temperature mapping method based on the specific situation of the infrared sensor actually used, with reference to the calibration parameters and conversion formula provided by the manufacturer. In this way, technicians can flexibly adjust and optimize the accuracy of temperature measurement according to actual needs and environmental conditions.

[0037] S32, calculating the temperature difference of each contour area according to the temperature value in the contour area; Specifically, in this embodiment, step S32 includes steps S321 to S323.

[0038] S321, counting the total number of contour areas in the infrared thermal imaging image at the current moment and the maximum temperature value in each contour area; S322, performing mean calculation based on the temperature values ​​in each contour area to obtain a temperature average value corresponding to each contour area; S323, calculating the temperature difference of each contour area according to the first preset formula, the total number of contour areas in the infrared thermal imaging image, the maximum temperature value in each contour area and the average temperature value corresponding to each contour area.

[0039] In order to facilitate the understanding of those skilled in the art, in this step, the infrared thermal imaging image at the current moment is used as the first The first preset formula for a contour area is illustrated as follows:

[0040] in, Indicates the infrared thermal imaging image at the current moment Temperature differences in each contour area; represents the linear normalization function; represents the maximum value function; Indicates the infrared thermal imaging image at the current moment The maximum value of all temperature values ​​in the contour area; Indicates the total number of contour areas in the infrared thermal imaging image at the current moment; Indicates the infrared thermal imaging image at the current moment. The average value of all temperature values ​​within the contour area; Indicates the infrared thermal imaging image at the current moment The average value of all temperature values ​​in the contour area; represents the absolute value function.

[0041] In the above calculation formula: the infrared thermal imaging image at the current moment The larger the maximum temperature value in the contour area, the higher the infrared thermal imaging image at the current moment. The greater the possibility that the temperature of the contour area is different from that of other areas. contour area and other contour areas The sum of the absolute values ​​of the differences, that is, The greater the difference between the first contour area and other contour areas, the ... The greater the temperature difference of the contour area, the greater the difference in the temperature of the contour area. Therefore, the above calculation formula can better reflect the Temperature differences in the contour area.

[0042] S33, judging the temperature difference of each contour area one by one according to a preset first threshold value to obtain an aging suspected area.

[0043] It should be noted that the first threshold value preset in this embodiment is 0.8. Meanwhile, for those skilled in the art, different first threshold values ​​may be selected according to actual conditions, and no specific limitation is made in this embodiment.

[0044] In this embodiment, it is taken into account that when aging occurs inside the smart electric box, the local temperature rises, which is quite different from other normal areas. Therefore, by extracting the grayscale value of each pixel in the infrared thermal imaging image at the current moment, the grayscale value is converted into a temperature value using the temperature mapping formula, and the temperature difference of each contour area is calculated according to the first preset formula. The area with large temperature difference, that is, the contour area with temperature difference greater than the first threshold, is the suspected aging area. Through temperature difference analysis, areas that may have aging problems can be preliminarily identified, thereby preparing for further screening and verification.

[0045] In this embodiment, the problem of local temperature rise caused by the aging phenomenon inside the smart power box is taken into consideration. By acquiring the infrared thermal imaging image at the current moment, the grayscale value of each pixel in the image is extracted. The grayscale value is converted into a temperature value using the temperature mapping formula, and the temperature difference of each contour area is calculated according to the first preset formula. In this way, areas with large temperature differences can be effectively identified, which are generally considered to be suspected aging areas.

[0046] S4, screening the suspected aging area according to the fever performance of the suspected aging area in a historical time period to obtain the aging area; In this embodiment, considering that the smart power box may generate more heat due to a sudden increase in load during operation, this situation may be misjudged as a suspected aging area. However, the aging area is a process in which the heat generation and heating area increase steadily over time. Therefore, in this embodiment, it is also necessary to screen each suspected aging area based on its heating performance in the historical time period.

[0047] See Figure 4 , the figure shows that this step also includes steps S41 to S45: S41, performing mean calculation based on the temperature values ​​in each of the suspected aging regions to obtain a temperature average value corresponding to each of the suspected aging regions; It should be noted that the temperature value in the suspected aging area mentioned in this step has been converted in step S31, so it will not be repeated in this step.

[0048] S42, counting the number of days the smart power box is in operation and the temperature value corresponding to each suspected aging area at each historical moment in a historical time period; It should be noted that the temperature value corresponding to the suspected aging area at each historical moment in the historical time period mentioned in this step is based on the pixel coordinate information of the suspected aging area at the current moment, and all temperature values ​​corresponding to the pixel coordinate information are queried in the infrared thermal imaging image at each historical moment.

[0049] The historical time period refers to a period of time from the time when the smart power box is running to the time when the previous data is collected at the current time. The time contained in the historical time period is called the historical moment. In this implementation, the infrared thermal imaging images corresponding to several historical moments are divided into multiple infrared thermal imaging images arranged in time sequence based on the day as the basic unit, and each infrared thermal imaging image in each historical moment has also undergone the grayscale value conversion to temperature value in step S31, and its specific implementation process has been described above. Therefore, it will not be repeated in this step.

[0050] S43, calculating the auxiliary discrimination value corresponding to each suspected aging area according to the number of days the smart power box is in operation, the average temperature corresponding to each suspected aging area, and the temperature value at each historical moment; In this embodiment, the performance characteristics of the aging area in historical moments are taken into account. Specifically, as time goes by, these aging areas will show obvious heating phenomena, including the expansion of the heating area and the increase in the amount of heat. In other words, within the same area, if the temperature average value corresponding to the suspected aging area at the current moment is compared with the temperature average value at the historical moment, the greater the difference, then the possibility that the suspected aging area truly belongs to the aging area is greater. This phenomenon shows that as time goes by, the temperature of the aging area will gradually increase, making its performance in temperature monitoring more significant. By monitoring and analyzing this temperature change, we can more accurately identify the real aging area, so as to take corresponding maintenance and repair measures to ensure the normal operation and safety of the equipment. Therefore, based on the above-mentioned derivation characteristics, in this step, the first temperature in the infrared thermal imaging image at the current moment is used. An example of the calculation formula for the auxiliary discrimination value of a suspected aging area is as follows:

[0051] in, Indicates the infrared thermal imaging image at the current moment Auxiliary discrimination value corresponding to the suspected aging area; Indicates the number of days the smart power box has been running up to the current moment; Indicates the infrared thermal imaging image at the current moment The average temperature corresponding to the suspected aging area; Indicates the number before the current time. The number of infrared thermal imaging images acquired per day; Indicates that the The day obtained Infrared thermal imaging image The average temperature is obtained by averaging the temperatures corresponding to the suspected aging areas.

[0052] Furthermore, in this embodiment, the accuracy of screening of aging areas is further improved. This embodiment considers that under normal load conditions, the heat distribution of a line is usually uniform. However, when the line is aged, it will show significant temperature concentration in certain specific areas, and the temperature difference in these areas will increase significantly. Based on this observation, this embodiment proposes to assist in judging the aging situation by calculating the degree of temperature confusion in each suspected aging area. Specifically, the method utilizes the characteristic of temperature concentration in a specific area of ​​the aging line, and corrects the auxiliary discrimination value by quantitatively analyzing the degree of temperature confusion, so as to more accurately identify the aging area. This method not only improves the accuracy of screening, but also provides a more reliable basis for subsequent maintenance and repair work. Therefore, in this embodiment, step S44 is also included: updating the auxiliary discrimination value according to the distribution of temperature values ​​in the aging area. Specifically, step S44 includes steps S441-step S445 to achieve the above purpose.

[0053] S441, counting the number of temperature values ​​in the suspected aging area; S442, performing mean calculation based on the temperature values ​​in the suspected aging area to obtain an average temperature value corresponding to the suspected aging area; S443, performing variance calculation based on the temperature value in the suspected aging area to obtain a temperature variance corresponding to the suspected aging area; S444, calculating the temperature disorder degree corresponding to the suspected aging area according to the number of temperature values ​​corresponding to the suspected aging area, the temperature average value and the variance; In order to facilitate the understanding of those skilled in the art, in this embodiment, the infrared thermal imaging image at the current moment is continued. For example, the suspected aging area, the infrared image of the smart power box at the current moment The specific calculation formula corresponding to the temperature disorder degree of each suspected aging area is:

[0054] in, Indicates the infrared thermal imaging image at the current moment The degree of temperature disturbance in the suspected aging area; Indicates the infrared thermal imaging image at the current moment The number of temperature values ​​in the suspected aging area; Indicates the infrared thermal imaging image at the current moment The temperature variance corresponding to the suspected aging area; Indicates the infrared thermal imaging image at the current moment In the suspected aging area Temperature values; Indicates the infrared thermal imaging image at the current moment The average temperature corresponding to the suspected aging area; represents the absolute value function.

[0055] According to the above calculation formula, the infrared thermal imaging image at the current moment The greater the difference between all the temperature values ​​of the suspected aging area, the greater the difference between the suspected aging area and the The greater the degree of temperature disorder in the suspected aging area; and Proportional, The larger the value of is, the The higher the temperature non-uniformity of a suspected aging area, the greater the degree of temperature chaos.

[0056] S445. Update the auxiliary discrimination value based on the temperature disorder degree corresponding to the suspected aging area.

[0057] In this embodiment, the larger the auxiliary discrimination value before the update and the greater the degree of temperature disorder, the greater the possibility that the suspected aging area is the aging area. Therefore, the auxiliary discrimination value is updated by using the above characteristics. See the following update formula for details:

[0058] in, Indicates the infrared thermal imaging image at the current moment The updated auxiliary discrimination value corresponding to the suspected aging area; represents the linear normalization function; Indicates the infrared thermal imaging image at the current moment Auxiliary discrimination value corresponding to the suspected aging area; Indicates the infrared thermal imaging image at the current moment The degree of temperature disorder in the suspected aging area.

[0059] S45: determining whether the suspected aging region is an aging region based on the auxiliary discrimination value corresponding to each of the suspected aging regions.

[0060] In the current step, this embodiment adopts a threshold-based judgment method to confirm whether the suspected aging area is indeed an aging area. Specifically, in this example, a second threshold is set to 0.85 to assist in the judgment. In other words, in this embodiment, the suspected aging area with an auxiliary judgment value greater than or equal to 0.85 is determined to be an aging area. This embodiment can more accurately identify the aging area by analyzing the temperature data at historical moments and combining the heating characteristics of the line, thereby effectively reducing misjudgments and improving the reliability of the screening results.

[0061] S5. Calculate the area and position of the aging area according to the coordinate information corresponding to the aging area; In this embodiment, the specific method includes converting the pixel coordinates of the contour area into actual physical coordinates and calculating the area and position. Accurately calculating the area and position of the aging area helps to locate the problem area and provide specific operation guidance for maintenance personnel.

[0062] In this embodiment, the specific method steps used include converting the coordinates of each pixel point in the contour area into actual physical coordinates. This process involves mapping the pixel coordinates in the image to specific locations in the actual object or scene, so that these coordinates can be described in physical units (such as millimeters, centimeters, etc.) to determine the specific location of the aging area in the overall object or scene. Subsequently, by calculating the area of ​​the area enclosed by these physical coordinates, the actual area size of the aging area can be obtained.

[0063] Through the above calculations, this embodiment accurately locates the specific location of the problem part of the smart power box, thereby providing maintenance personnel with more detailed and specific operation guidance. Such guidance not only includes the location information of the aging area. In this way, maintenance personnel can perform repair or replacement work more efficiently and accurately, thereby improving overall work efficiency and equipment reliability.

[0064] S6. Sending the average temperature value of the aging area at the current moment, the area and the position of the aging area to a preset terminal, wherein the average temperature value is calculated from the gray value of the infrared thermal imaging image of the aging area at the current moment.

[0065] Specifically, in this embodiment, the area, location and average temperature of the aging area are transmitted to the maintenance personnel by using a preset terminal, so as to assist the maintenance personnel in timely warning, prevent the occurrence of electrical box failure and fire, and improve the safety and reliability of the smart electrical box.

[0066] In this embodiment, the preset terminal device can be a device that is directly wirelessly connected to the smart power box, such as a mobile device with preset alarm software installed, or a computer terminal device that is indirectly connected to the smart power box through a cloud platform. In this embodiment, by making full use of the functions of the cloud platform and mobile devices, the area or specific location information of the aging area can be promptly transmitted to the maintenance personnel. The main purpose of this approach is to help maintenance personnel quickly receive early warning information, thereby effectively preventing power box failures and fires. In this way, the safety and reliability of the smart power box can be significantly improved, ensuring the stable operation of the power system.

[0067] Specifically, once an aging area is detected, the cloud platform or a mobile device with preset alarm software will immediately send an early warning message to the maintenance personnel through the mobile device. After receiving this information, the maintenance personnel can quickly locate the specific aging area and take corresponding maintenance measures, such as replacing aging parts or repairing them. This process not only improves maintenance efficiency, but also effectively reduces safety hazards caused by electrical box failures and fires, ensuring the stable operation of the smart electrical box.

[0068] Embodiment 2:

[0069] like Figure 5 As shown, this embodiment provides a fault self-diagnosis and early warning system for a smart power box, the system comprising: An acquisition module is used to acquire infrared thermal imaging images inside the smart electric box in real time; A contour extraction module, used to extract the contour of the infrared thermal imaging image at the current moment to obtain at least one contour area; A first screening module, used for screening suspected aging areas according to the temperature difference within each contour area; A second screening module is used to screen out aging areas according to the fever performance of the suspected aging areas in a historical time period; An information calculation module, used for calculating the area and position of the aging area according to the coordinate information corresponding to the aging area; The early warning module is used to send the average temperature value of the aging area at the current moment, the area and the position of the aging area to a preset terminal, wherein the average temperature value is calculated by the gray value of the infrared thermal imaging image of the aging area at the current moment.

[0070] It should be noted that, regarding the system in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0071] Embodiment 3:

[0072] Corresponding to the above method embodiment, this embodiment also provides a fault self-diagnosis and early warning device for a smart electrical box. The fault self-diagnosis and early warning device for a smart electrical box described below and the fault self-diagnosis and early warning method for a smart electrical box described above can be referenced to each other.

[0073] Figure 6 FIG. 8 is a block diagram of a fault self-diagnosis warning device 800 for a smart power box according to an exemplary embodiment. Figure 6As shown, the fault self-diagnosis warning device 800 of the smart power box may include: a processor 801 and a memory 802. The fault self-diagnosis warning device 800 of the smart power box may also include one or more of a multimedia component 803, an I / O interface 804, and a communication component 805.

[0074] The processor 801 is used to control the overall operation of the fault self-diagnosis warning device 800 of the smart electric box to complete all or part of the steps in the above-mentioned fault self-diagnosis warning method of the smart electric box. The memory 802 is used to store various types of data to support the operation of the fault self-diagnosis warning device 800 of the smart electric box. These data may include, for example, instructions for any application or method used to operate on the fault self-diagnosis warning device 800 of the smart electric box, as well as application-related data, such as contact data, sent and received messages, pictures, audio, video, etc. The memory 802 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, disk or optical disk. The multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 802 or sent via the communication component 805. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 804 provides an interface between the processor 801 and other interface modules, and the above-mentioned other interface modules can be keyboards, mice, buttons, etc. These buttons can be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the fault self-diagnosis and early warning device 800 of the smart power box and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 805 can include: Wi-Fi module, Bluetooth module, NFC module.

[0075] In an exemplary embodiment, the fault self-diagnosis and warning device 800 of the smart electrical box can be implemented by one or more application specific integrated circuits (Application Specific Integrated Circuit, referred to as ASIC), digital signal processors (Digital Signal Processing Device, referred to as DSP), digital signal processing devices (Digital Signal Processing Device, referred to as DSPD), programmable logic devices (Programmable Logic Device, referred to as PLD), field programmable gate arrays (Field Programmable Gate Array, referred to as FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned smart electrical box fault self-diagnosis and warning method.

[0076] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned smart electric box fault self-diagnosis warning method are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 802 including program instructions, and the above-mentioned program instructions can be executed by the processor 801 of the smart electric box fault self-diagnosis warning device 800 to complete the above-mentioned smart electric box fault self-diagnosis warning method.

[0077] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0078] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A fault self-diagnosis and early warning method for a smart electric box, characterized in that: The method comprises: Acquire infrared thermal imaging images inside the smart electric box in real time; Performing contour extraction on the infrared thermal imaging image at the current moment to obtain at least one contour area; Screening suspected aging areas according to the temperature difference within each contour area; The aging area is obtained by screening according to the fever performance of the suspected aging area in the historical time period; Calculate the area and position of the aging area according to the coordinate information corresponding to the aging area; Sending the average temperature value of the aging area at the current moment, the area and the position of the aging area to a preset terminal, wherein the average temperature value is calculated by the gray value of the infrared thermal imaging image of the aging area at the current moment; Perform contour extraction on the infrared thermal imaging image at the current moment to obtain at least one contour area, including: Use edge detection mathematical model to detect the edge of the infrared thermal imaging image at the current moment and obtain several edge pixel points; Performing region extraction in the infrared thermal imaging image at the current moment based on all the edge pixels to obtain at least one contour region; The aging areas are screened based on the fever performance of the suspected aging areas in the historical time period, including: Converting the grayscale values ​​contained in each of the suspected aging areas into temperature values ​​one by one according to a preset temperature mapping formula; Performing mean calculation based on the temperature values ​​in each of the suspected aging regions to obtain the average temperature value corresponding to each of the suspected aging regions; Counting the number of days the smart power box has been in operation and the temperature value corresponding to each suspected aging area at each historical moment in a historical time period; The auxiliary discrimination value corresponding to each suspected aging area is calculated according to the number of days the smart power box is in operation, the average temperature corresponding to each suspected aging area, and the temperature value at each historical moment; Based on the auxiliary discrimination value corresponding to each of the suspected aging regions, it is determined whether the suspected aging region is an aging region.

2. The fault self-diagnosis and early warning method of the smart electric box according to claim 1 is characterized in that: The edge detection mathematical model is the Sobel edge detection algorithm.

3. The fault self-diagnosis and early warning method of the smart electric box according to claim 1 is characterized in that: Screening suspected aging areas based on the temperature difference within each contour area, including: Converting the grayscale values ​​contained in each contour area into temperature values ​​one by one according to a preset temperature mapping formula; Calculate the temperature difference of each contour area according to the temperature value in the contour area; The temperature difference of each contour area is judged one by one according to a preset first threshold value to obtain an aging suspected area.

4. The fault self-diagnosis and early warning method of the smart electric box according to claim 3 is characterized in that: The temperature difference of each contour area is calculated according to the temperature value in the contour area, including: Counting the total number of contour areas in the infrared thermal imaging image at the current moment and the maximum temperature value in each contour area; Performing mean calculation based on the temperature values ​​within each contour area to obtain the average temperature value corresponding to each contour area; The temperature difference of each contour area is calculated according to the first preset formula, the total number of contour areas in the infrared thermal imaging image, the maximum temperature value in each contour area and the average temperature value corresponding to each contour area.

5. The fault self-diagnosis and early warning method of the smart electric box according to claim 3 is characterized in that: The preset first threshold is 0.

8.

6. The fault self-diagnosis and early warning method of the smart electric box according to claim 1 is characterized in that: Based on the auxiliary discrimination value corresponding to each of the suspected aging regions, it is determined whether the suspected aging region is an aging region, and the method further includes: Counting the number of temperature values ​​in the suspected aging area; Performing mean calculation based on the temperature values ​​in the suspected aging area to obtain the average temperature value corresponding to the suspected aging area; Performing variance calculation based on the temperature value in the suspected aging area to obtain the variance corresponding to the suspected aging area; The temperature disorder degree corresponding to the suspected aging area is calculated according to the number of temperature values ​​corresponding to the suspected aging area, the temperature average value and the variance; The auxiliary discrimination value is updated based on the degree of temperature disorder corresponding to the suspected aging area.

7. A fault self-diagnosis and early warning system for a smart electric box, characterized in that: include: An acquisition module is used to acquire infrared thermal imaging images inside the smart electric box in real time; A contour extraction module, used to extract the contour of the infrared thermal imaging image at the current moment to obtain at least one contour area; A first screening module, for screening suspected aging areas according to the temperature difference within each contour area; A second screening module is used to screen out aging areas according to the fever performance of the suspected aging areas in a historical time period; An information calculation module, used for calculating the area and position of the aging area according to the coordinate information corresponding to the aging area; An early warning module, used to send the average temperature value of the aging area at the current moment, the area and the position of the aging area to a preset terminal, wherein the average temperature value is calculated by the gray value of the infrared thermal imaging image of the aging area at the current moment; Perform contour extraction on the infrared thermal imaging image at the current moment to obtain at least one contour area, including: Use edge detection mathematical model to detect the edge of the infrared thermal imaging image at the current moment and obtain several edge pixel points; Performing region extraction in the infrared thermal imaging image at the current moment based on all the edge pixels to obtain at least one contour region; The aging areas are screened based on the fever performance of the suspected aging areas in the historical time period, including: Converting the grayscale values ​​contained in each of the suspected aging areas into temperature values ​​one by one according to a preset temperature mapping formula; Performing mean calculation based on the temperature values ​​in each of the suspected aging regions to obtain the average temperature value corresponding to each of the suspected aging regions; Counting the number of days the smart power box has been in operation and the temperature value corresponding to each suspected aging area at each historical moment in a historical time period; The auxiliary discrimination value corresponding to each suspected aging area is calculated according to the number of days the smart power box is in operation, the average temperature corresponding to each suspected aging area, and the temperature value at each historical moment; Based on the auxiliary discrimination value corresponding to each of the suspected aging regions, it is determined whether the suspected aging region is an aging region.

8. A fault self-diagnosis and early warning device for a smart electric box, characterized in that: include: Memory for storing computer programs; A processor, used to implement the steps of the fault self-diagnosis and early warning method of the smart power box as described in any one of claims 1 to 6 when executing the computer program.

Images