Belt conveyor motor overheat detection method based on infrared image

Abstract

The present invention relates to the field of image data processing technology, and in particular to a belt conveyor motor overheat detection method based on infrared images, comprising: collecting continuous frame images during the working process of the belt conveyor motor, and obtaining the Otsu threshold of the target image, wherein the target image is any one of the continuous frame images; calculating the temperature abnormality degree and the temperature display degree of each pixel in the target image, multiplying the temperature abnormality degree, the temperature display degree and the Otsu threshold to obtain the segmentation threshold of each pixel in the target image, segmenting the target image based on the segmentation threshold to obtain the foreground area of ​​the target image; obtaining the motor temperature in the foreground area, and controlling the motor to send out an early warning signal when the motor temperature is greater than the set temperature threshold. The present invention solves the problem of being unable to accurately identify the overheating area of ​​the motor.

Description

Technical Field

[0001] The present invention relates to the technical field of image data processing, and more specifically, to a belt conveyor motor overheat detection method based on infrared images. Background Art

[0002] In modern industrial production, belt conveyors are generally used in the fields of material handling, transportation and processing. As a key component, the normal operation of the motor directly affects its conveying efficiency and the overall performance of the equipment. However, the motor is prone to overheating during long-term high-load operation, which not only reduces the working efficiency of the motor, but also may cause equipment damage and production stagnation. With the rapid development of infrared imaging technology, new solutions are provided for motor temperature monitoring. Infrared images can capture the temperature distribution on the surface of the motor non-contactly, with high sensitivity and real-time performance, and can effectively identify the overheating area of ​​the motor. At the same time, with the help of image processing technology, the collected infrared images can be deeply analyzed to extract key temperature features and abnormal areas. This method not only improves the accuracy of temperature monitoring, but also provides important data support for fault warning and maintenance.

[0003] The patent application document with application publication number CN108445393A discloses a permanent magnet synchronous motor fault detection method and system. The patent application document includes: collecting multiple series of time-series original image data of normal and faulty thermal change processes of permanent magnet synchronous motors, and using image processing technology to segment pixel areas with higher surface temperature of permanent magnet synchronous motors, and then extracting features to determine the motor state category.

[0004] However, although the above scheme realizes the temperature detection of permanent magnet synchronous motor, the accuracy of existing image processing and segmentation technology in identifying high temperature areas is not fully considered when collecting and processing motor thermal imaging data. This deficiency may lead to the inability to accurately identify the overheating area of ​​the motor, thereby reducing the accuracy and effectiveness of motor temperature monitoring. Summary of the invention

[0005] In order to solve the problem raised in the above background technology that the overheating area of ​​the motor cannot be accurately identified, thereby reducing the accuracy and effectiveness of motor temperature monitoring, the present invention provides the following solution.

[0006] In a first aspect, the present invention provides a belt conveyor motor overheat detection method based on infrared images, comprising: collecting continuous frame images of the belt conveyor motor during operation, and obtaining the Otsu threshold of the target image; calculating the temperature abnormality degree of each pixel in the target image:

[0007] ;

[0008] In the formula, The target image Line The temperature anomaly degree of the column pixel, is an exponential function with the natural constant e as the base, || is the absolute value, For the Line The pixel points of the column and its The neighborhood The difference in grayscale value between pixels, For the Line Column pixels The neighborhood The Laplace gradient value of the pixel point, represents an empirical constant, and , To obtain the maximum value; calculate the temperature display degree of each pixel in the target image:

[0009] ;

[0010] In the formula, The target image Line The temperature display degree of the pixel points, is the first Line The range of the gray value of the pixel point in the column, Indicates taking the maximum value of the range. is the first The first image Line The gray value of the pixel. is the first The first image Line The gray value of the pixel. is the number of consecutive frame images, >1, represents an empirical constant, and ; The product of the temperature abnormality degree, the temperature display degree and the Otsu threshold is used as the segmentation threshold, and the target image is segmented based on the segmentation threshold to obtain the foreground area of ​​the target image; the motor temperature in the foreground area is obtained, and when the motor temperature is greater than the set temperature threshold, the motor is controlled to send a warning signal.

[0011] The above technical solution can effectively extract the foreground area of ​​the target image by segmenting the target image using the improved Otsu threshold, thereby realizing accurate temperature monitoring. The technical solution can effectively identify abnormal areas caused by temperature changes during the operation of the motor, especially improve the sensitivity to local temperature anomalies. The calculation of the temperature display degree combines the change characteristics of the gray value, so that the solution can more intuitively reflect the temperature information and accurately detect whether the motor is in a high temperature state, thereby triggering a warning signal in time when the temperature exceeds the set threshold, improving the safety and reliability of the motor operation, helping to prevent motor failures, increase the life and operating efficiency of the equipment, and ensure the continuity and stability of industrial production.

[0012] Furthermore, the target image is:

[0013] Calculate the reference degree of each pixel of the continuous frame image, the reference degree is positively correlated with the grayscale value of each pixel in the continuous frame image, and is negatively correlated with the extreme difference of the grayscale value of each pixel in the continuous frame image and the average value of the sum of the grayscale values ​​of each pixel in the continuous frame image; calculate the grayscale value of each pixel in the target image based on the reference degree:

[0014] ;

[0015] In the formula, The target image Line The gray value of the pixel. is the first Line The sum of the reference degrees of the pixels in the column, For the In the image Line The reference degree of the column pixels, For the In the image Line The gray value of the pixel. is the number of consecutive frame images, represents an empirical constant, and .

[0016] The above technical solution calculates the reference degree of each pixel in the continuous frame image, and optimizes the gray value generation process of each pixel in the target image based on its correlation with the gray value and the range. Through the weighted average method, it can more accurately reflect the importance of each pixel in the target image, thereby improving the quality and detail performance of the target image. This method can effectively reduce the impact of noise, enhance the clarity and consistency of the image, and achieve better visual effects when processing dynamic scenes or multi-frame image fusion.

[0017] Furthermore, the reference degree is:

[0018] ;

[0019] In the formula, For the In the image Line The reference degree of the column pixels, For the In the image Line The gray value of the pixel. is the first Line The average value of the sum of the grayscale values ​​of the pixels in the column, The first Line The range of the gray value of the pixel point in the column, represents an empirical constant, and .

[0020] The above technical solution effectively evaluates the importance of each pixel in the image by introducing a reference degree calculation formula based on the grayscale value of each pixel. The definition of the reference degree combines the deviation of the pixel grayscale value from the average value and the extreme difference of the grayscale value, so that when the target image is generated, useful information can be more accurately identified and highlighted. This method not only improves the retention of image details and the suppression of noise, but also enhances the contrast and clarity of the overall image, thereby improving the visual quality and practicality of the final target image.

[0021] Furthermore, a CMOS camera is used to collect continuous frame images of the belt conveyor motor during its operation.

[0022] Furthermore, the Otsu threshold of the target image is obtained, specifically, grayscale processing is performed on the target image, a grayscale histogram is calculated, and the Otsu threshold is determined according to the principle of maximizing the inter-class variance.

[0023] The above technical solution realizes efficient image segmentation by graying the target image and calculating the grayscale histogram, and using the principle of maximizing the inter-class variance to determine the optimal Otsu threshold. By optimizing the threshold, the foreground and background can be effectively distinguished, the contrast and clarity of the image can be improved, and the accuracy of subsequent processing and analysis can be enhanced. This method can improve the performance of target detection and recognition in practical applications and has important practical value.

[0024] Furthermore, the method also includes gray-scaling and Gaussian filtering the continuous frame images.

[0025] Furthermore, the Laplace edge detection algorithm is used to calculate the Laplace gradient value of the pixel point.

[0026] The beneficial effects of the present invention are:

[0027] The present invention significantly improves the accuracy and real-time performance of motor temperature monitoring. Through dynamic analysis of continuous frame images, abnormal changes in motor temperature can be captured in a timely manner, reducing the risk of equipment failure caused by overheating. At the same time, combined with the optimization of the Otsu threshold and the calculation of the temperature display degree, the segmentation effect of the target image is more accurate, thereby clearly identifying potential overheating areas. The method also introduces Laplace edge detection and grayscale processing, which further enhances the ability to extract image details and helps to improve the sensitivity and accuracy of detection. Overall, this efficient monitoring method can effectively improve the safety and reliability of production equipment, and provide an important guarantee for enterprises to save costs and improve production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0029] Figure 1 is a flow chart schematically showing a belt conveyor motor overheat detection method based on infrared images according to an embodiment of the present invention;

[0030] Figure 2 is a grayscale diagram schematically showing a belt conveyor according to an embodiment of the present invention. DETAILED DESCRIPTION

[0031] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0032] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0033] Embodiment of the belt conveyor motor overheat detection method based on infrared image.

[0034] like Figure 1 As shown, a flow chart of a belt conveyor motor overheat detection method based on infrared images according to an embodiment of the present invention comprises the following steps:

[0035] S1: Collect continuous frame images of the belt conveyor motor during operation and obtain the Otsu threshold of the target image.

[0036] In one embodiment, a CMOS camera or a CCD camera can be used to collect continuous frame images of the working process of the belt conveyor motor. This method ensures that the dynamic changes of the motor under different working conditions can be obtained. Next, one of the collected continuous frame images is selected as the target image for subsequent processing and analysis; and the target image can be any one of the continuous frame images.

[0037] In another embodiment, the target image may be:

[0038] Calculating a reference degree of each pixel in the continuous frame images, wherein the reference degree is positively correlated with the grayscale value of each pixel in the continuous frame images and the average value of the sum of the grayscale values ​​of each pixel in the continuous frame images, and is negatively correlated with the extreme difference of the grayscale value of each pixel in the continuous frame images;

[0039] In one embodiment, the reference degree is:

[0040] ;

[0041] In the formula, For the In the image Line The reference degree of the column pixels, For the In the image Line The gray value of the pixel. is the first Line The average value of the sum of the grayscale values ​​of the pixels in the column, is the first Line The range of the gray value of the pixel point in the column, represents an empirical constant, and .

[0042] In another embodiment, the reference degree is:

[0043] ;

[0044] In the formula, For the In the image Line The reference degree of the column pixels, For the In the image Line The gray value of the pixel. is the median grayscale value of pixels in continuous frame images, The first Line The range of the gray value of the pixel point in the column, represents an empirical constant, and ; When the median and mean are equal, the mean is the first choice.

[0045] The above scheme effectively evaluates the importance of each pixel in the image by introducing a reference degree calculation formula based on the grayscale value of each pixel. The definition of reference degree combines the deviation of the pixel grayscale value from the average value and the extreme difference of the grayscale value, so that when the target image is generated, useful information can be more accurately identified and highlighted.

[0046] Calculate the grayscale value of each pixel in the target image based on the reference degree:

[0047] ;

[0048] In the formula, The target image Line The gray value of the pixel. The first Line The sum of the reference degrees of the pixels in the column, For the In the image Line The reference degree of the column pixels, For the In the image Line The gray value of the pixel. is the number of consecutive frame images, represents an empirical constant, and .

[0049] Before processing the target image, all continuous frame images need to be grayscaled. This step aims to convert the color image into a grayscale image, thereby simplifying the subsequent analysis process. After grayscale, Gaussian filtering is then performed to reduce noise and details in the image, thereby enhancing the main features of the image. This smoothing process helps to improve the accuracy of subsequent threshold segmentation.

[0050] After completing the above processing, the distribution of each gray level in the image can be obtained by calculating the grayscale histogram of the target image. According to the principle of maximizing inter-class variance, the optimal Otsu threshold needs to be determined next. Specifically, using this principle, the foreground and background areas in the image can be effectively distinguished, thereby achieving more accurate image segmentation. This process not only improves the processing effect of the target image, but also provides a solid data foundation for subsequent fault detection and analysis.

[0051] S2: Calculate the temperature anomaly degree and temperature display degree of each pixel in the target image.

[0052] In one embodiment, the temperature anomaly degree of each pixel in the target image is calculated:

[0053] ;

[0054] In the formula, The target image Line The temperature anomaly degree of the column pixel, is an exponential function with the natural constant e as the base, || is the absolute value, For the Line The pixel points of the column and its The neighborhood The difference in grayscale value between pixels, For the Line Column pixels The neighborhood The Laplace gradient value of the pixel point is represents an empirical constant, and , To take the maximum value; wherein, the Laplace gradient value of each pixel is directly obtained through the Laplace edge detection algorithm.

[0055] In one embodiment, the temperature display degree of each pixel in the target image is calculated:

[0056] ;

[0057] In the formula, The target image Line The temperature display degree of the pixel points in the column, The first Line The range of the gray value of the pixel point in the column, Indicates taking the maximum value of the range. The first The first image Line The gray value of the pixel. The first The first image Line The gray value of the pixel. is the number of consecutive frame images, >1, represents an empirical constant, and .

[0058] The above scheme calculates the temperature display degree of each pixel in the target image, effectively combines the extreme difference of grayscale values ​​with the relative changes in continuous frame images, and provides a more intuitive way to express image information. It not only improves the visualization effect of temperature information in the target image, but also helps to achieve more accurate temperature monitoring and analysis in practical applications, thereby improving the practical value and information transmission capability of the image.

[0059] S3: Multiply the temperature anomaly degree, the temperature display degree and the Otsu threshold to calculate the segmentation threshold of each pixel in the target image, and segment the target image to obtain the foreground area of ​​the target image.

[0060] In one embodiment, the temperature anomaly degree, temperature display degree and Otsu threshold of each pixel are calculated and multiplied to calculate the segmentation threshold of each pixel in the target image. Specifically, for each pixel of the target image, the corresponding temperature anomaly degree and temperature display degree are first calculated, and then these two values ​​are multiplied by the Otsu threshold. In this way, the obtained segmentation threshold can be dynamically adjusted according to the temperature information of different pixels, providing higher flexibility and accuracy for subsequent image segmentation.

[0061] Once the segmentation threshold of each pixel is determined, the target image can be segmented. The grayscale value of each pixel in the target image is compared with its corresponding segmentation threshold. If the grayscale value of the pixel is higher than its segmentation threshold, the pixel is determined to be a foreground area, indicating that the area may have a temperature anomaly; otherwise, it is determined to be a background area. This method can not only effectively identify the high-temperature area of ​​the motor, but also accurately exclude the background area with normal temperature, thereby improving the accuracy and reliability of fault detection.

[0062] S4: Acquire the motor temperature in the foreground area, and when the motor temperature is greater than a set temperature threshold, control the motor to send out a warning signal.

[0063] In one embodiment, after successfully extracting the foreground area of ​​the target image through the above steps, the temperature data in this area will be focused on. Using the above efficient image processing technology, the temperature information of the motor can be extracted from the foreground area. Through thermal imaging data, the corresponding temperature value can be obtained for each pixel in the foreground area. These temperature values ​​will be integrated into a temperature distribution map to provide a basis for subsequent temperature analysis.

[0064] like Figure 2 As shown, a grayscale image of a belt conveyor according to an embodiment of the present invention includes a belt conveyor and a motor.

[0065] Next, set a temperature threshold. The above temperature threshold can be 80, and of course, it can be determined according to the actual situation. This temperature threshold should be reasonably configured according to the normal operating temperature range of the motor and historical data. For example, a safe upper temperature limit can be determined by analyzing the temperature performance of the motor under different loads and environmental conditions. When the operating temperature of the motor exceeds this set temperature threshold, there may be a risk of overheating, which will directly affect the performance and service life of the motor. If the temperature value of a pixel is detected to be greater than the set threshold, the system will immediately trigger the early warning mechanism. This mechanism can be implemented in a variety of ways. For example, the system can issue an audible and visual alarm to remind the operator to take timely measures; at the same time, the system can also send real-time alarm information to the management personnel through the monitoring platform for remote monitoring and management. This early warning signal can not only attract the attention of the operator in a short time, but also effectively prevent motor damage or other safety hazards caused by excessive temperature.

[0066] The solution of the present invention significantly improves the accuracy and reliability of motor temperature monitoring by real-time acquisition and processing of continuous frame images. By comprehensively evaluating the degree of temperature anomaly and the degree of temperature display, potential overheating risks can be effectively identified, reducing the possibility of false alarms and missed alarms. The introduction of the optimization processing of the Otsu threshold enhances the separation effect of the foreground and background, ensures the accurate extraction of the target area, and thus improves the effectiveness of image segmentation. In addition, the combination of the calculation of the Laplace gradient and the reference degree not only improves the expression of image details, but also enhances the visualization effect of temperature changes, making the monitoring results more intuitive. This technical solution not only helps to provide early warning and prevent equipment failures, but also improves the operating safety and efficiency of belt conveyors, and has good application potential and practical value.

[0067] In the description of this specification, "plurality" or "several" means at least two, such as two, three or more, etc., unless otherwise clearly and specifically defined.

[0068] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

Claims

1. A belt conveyor motor overheat detection method based on infrared images, characterized in that: include: Collect continuous frame images of the belt conveyor motor during operation and obtain the Otsu threshold of the target image; The target image is: Calculating a reference degree of each pixel point in the continuous frame images, wherein the reference degree is positively correlated with the grayscale value of each pixel point in the continuous frame images, and is negatively correlated with the extreme difference of the grayscale value of each pixel point in the continuous frame images and the average value of the sum of the grayscale values ​​of each pixel point in the continuous frame images; Calculate the grayscale value of each pixel in the target image based on the reference degree: ； In the formula, The target image Line The gray value of the pixel. is the first Line The sum of the reference degrees of the pixels in the column, For the In the image Line The reference degree of the column pixels, For the In the image Line The gray value of the pixel. is the number of consecutive frame images, represents an empirical constant, and ; Calculate the temperature anomaly degree of each pixel in the target image: ； In the formula, The target image Line The temperature anomaly degree of the column pixel, is an exponential function with the natural constant e as the base, || is the absolute value, For the Line The pixel points of the column The neighborhood The difference in grayscale value between pixels, For the Line Column pixels The neighborhood The Laplace gradient value of the pixel point is represents an empirical constant, and , To obtain the maximum value; calculate the temperature display degree of each pixel in the target image: ； In the formula, The target image Line The temperature display degree of the pixel points in the column, is the first Line The range of the gray value of the pixel point in the column, Indicates taking the maximum value of the range. is the first The first image Line The gray value of the pixel. is the first The first image Line The gray value of the pixel. is the number of consecutive frame images, >1, represents an empirical constant, and ; The product of the temperature abnormality degree, the temperature display degree and the Otsu threshold is used as the segmentation threshold, and the target image is segmented based on the segmentation threshold to obtain the foreground area of ​​the target image; the motor temperature in the foreground area is obtained, and when the motor temperature is greater than the set temperature threshold, the motor is controlled to send a warning signal.

2. The belt conveyor motor overheat detection method based on infrared image according to claim 1 is characterized in that: The reference degree is: ； In the formula, For the In the image Line The reference degree of the column pixels, For the In the image Line The gray value of the pixel. is the first Line The average value of the sum of the grayscale values ​​of the pixels in the column, is the first Line The range of the gray value of the pixel point in the column, represents an empirical constant, and .

3. The belt conveyor motor overheat detection method based on infrared image according to claim 1 is characterized in that: The CMOS camera is used to collect continuous frame images of the belt conveyor motor during its operation.

4. The belt conveyor motor overheat detection method based on infrared image according to claim 1 is characterized in that: Obtaining the Otsu threshold of the target image is specifically as follows: graying the target image, calculating the grayscale histogram, and determining the Otsu threshold according to the principle of maximizing the inter-class variance.

5. The belt conveyor motor overheat detection method based on infrared image according to claim 1 is characterized in that: It also includes grayscale conversion and Gaussian filtering of continuous frame images.

6. The belt conveyor motor overheat detection method based on infrared image according to claim 1 is characterized in that: The Laplace edge detection algorithm is used to calculate the Laplace gradient value of the pixel point.

Images