A method for monitoring the operating status of a hydraulic shaft piercer based on image processing

Abstract

The present invention relates to the field of image processing technology, and more specifically, the present invention relates to a method for monitoring the operating status of a hydraulic axle piercer based on image processing, comprising: collecting a thermal sensing image of the hydraulic axle piercer, and graying it to obtain a grayscale image; for any pixel point in the grayscale image, calculating the degree of change of the pixel point. The present invention detects the thermal sensing image of the hydraulic axle piercer collected during the operating status, calculates the monitoring feature quantity of the pixel point according to the characteristics of the hydraulic axle piercer when working, and then determines the pixel point cluster according to the monitoring feature quantity, divides the pixel point cluster, and then obtains the degree of abnormality of the cluster according to the characteristics of the cluster. It is possible to obtain the precise location of the abnormality while determining the abnormality based on the cluster. Through real-time monitoring and timely warning, unplanned downtime is reduced, thereby improving overall production efficiency and avoiding losses to overall production efficiency or safety hazards.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and more specifically, to a method for monitoring the operating state of a hydraulic shaft piercing device based on image processing. Background Art

[0002] The hydraulic piercer operating status monitoring method based on image processing significantly improves the reliability and maintenance efficiency of the hydraulic system through modern computer vision and intelligent algorithms. The core of this method is to capture the image data of the hydraulic piercer in real time, usually through a high-definition camera or thermal imaging equipment. First of all, this method can achieve real-time monitoring. The monitoring system continuously acquires images and processes them to detect the operating status of the piercer. The image processing algorithm can quickly analyze the captured images and identify any abnormal appearance features, such as cracks, wear or corrosion, which are potential signs of failure. Secondly, by applying machine learning and image analysis techniques, the system is able to identify and classify faults. For example, using deep learning models such as convolutional neural networks (CNNs), effective classifiers can be trained to identify different types of damage or abnormalities.

[0003] In the related art, for example, Chinese patent application document with publication number CN117307566A discloses a hydraulic axle piercing device. The present invention integrates the entire hydraulic system together to facilitate subsequent use and carrying.

[0004] At present, when monitoring the operation of the hydraulic axle piercer, it is difficult to use the superpixel algorithm to accurately distinguish the normal and abnormal positions because the changes in the thermal sensing image are extremely small in the early stage of the abnormality. As a result, it is impossible to accurately monitor the operating status and achieve real-time monitoring and timely warning, which increases the time and cost of manual inspection, reduces the overall production efficiency, and may also cause losses to the work or safety hazards. Summary of the invention

[0005] The present invention provides a method for monitoring the operating status of a hydraulic axle piercer based on image processing, aiming to solve the problem in the related technology that it is difficult to use a superpixel algorithm to accurately distinguish between normal and abnormal positions, thus resulting in the inability to accurately monitor the operating status, and the inability to achieve real-time monitoring and timely warning, which increases the time and cost of manual inspection and reduces the overall production efficiency.

[0006] In the first aspect, the present invention provides a method for monitoring the operating status of a hydraulic axle piercing device based on image processing, comprising: collecting a thermal sensing image of the hydraulic axle piercing device, and graying it to obtain a grayscale image; for any pixel point in the grayscale image, calculating the degree of change of the pixel point, the degree of change reflects the magnitude of the change in the grayscale value of the pixel point in a continuous time; establishing a window with any pixel point in the grayscale image as the center, and calculating the monitoring feature value of the pixel point, and the calculation formula is: , where Indicates The monitoring feature quantity of the pixel point, Indicates The pixel corresponds to the The gradient value of a pixel, represents the gradient variance within the window, Represents pixel The corresponding window The degree of change of pixels, Indicates the number of pixels in the window. represents the standard normalization function; the grayscale image is divided into blocks, and for any block, the pixel point with the largest monitoring feature value in the block is selected as the seed point, and the pixel points are clustered according to the difference between the monitoring feature values ​​of the seed point and the pixels in its neighborhood, and the abnormality degree of cluster A is calculated. , the calculation formula is: ; In the formula, represents the number of pixels in cluster A, Indicates the maximum value of the monitoring feature value of the pixel points of cluster A, Represents the minimum value of the monitoring feature quantity of the pixel points of cluster A; according to the degree of abnormality of the cluster, the abnormal position is determined to monitor the operating status.

[0007] The effect is: according to the characteristic that the temperature of the hydraulic axle piercer will rise smoothly when working, the monitoring feature quantity of the hydraulic axle piercer at each pixel point in the image is calculated, and the precise position of the hydraulic axle piercer abnormality is found according to the monitoring feature quantity, thereby improving the monitoring efficiency and accuracy.

[0008] Furthermore, the abnormal position is determined according to the degree of abnormality of the cluster, including: in response to the degree of abnormality of the cluster being greater than a first threshold, the cluster is determined to be an abnormal cluster, an alarm is issued, and the position of the pixel point in the abnormal cluster is determined to be the abnormal position.

[0009] The effect is that after the abnormal cluster is determined, the precise location of the abnormality on the hydraulic piercing device can be obtained, thereby improving the monitoring effect.

[0010] Furthermore, the degree of change of the pixel point is calculated, including: acquiring a thermal sensing image of the hydraulic axle piercing device at the current moment, and obtaining multiple consecutive thermal sensing images before the current moment, and calculating the change in the grayscale value of the pixel point in the multiple consecutive thermal sensing images as the degree of change of the pixel point.

[0011] The effect is that by acquiring a plurality of continuous thermal sensing images before the current moment, the change of the gray value of the pixel point can be accurately calculated.

[0012] Furthermore, the degree of change of the pixel is calculated, and the calculation formula is: ; In the formula, Indicates The degree of change of pixels, Indicates The gray value of a pixel, Indicates the current time Thermal image of The gray value of the pixel, Indicates time Thermal image of The degree of change of pixels, Indicates the total number of thermal images.

[0013] Furthermore, pixel point clusters are divided according to the difference in monitoring feature quantities between the seed point and the pixel points in its neighborhood, including: determining whether the seed point and the pixel points in its neighborhood are in the same cluster; in response to the absolute value of the difference between the monitoring feature quantity of the seed point a and the monitoring feature quantity of the pixel point b in its neighborhood being less than a second threshold, the seed point a and the pixel point b are divided into the same cluster.

[0014] The effect is that through the above method, similar clusters can be quickly divided into the same cluster, thereby improving the efficiency of monitoring.

[0015] Furthermore, the pixel point clustering division also includes: for any two seed points, when the judgment areas of the two seed points overlap, the judgment values ​​of the seed points of the two clusters are calculated; in response to the judgment values ​​of the seed points of the two clusters being less than a third threshold, the two clusters are recorded as the same cluster.

[0016] The effect is that similar clusters can be merged through a simple method, thereby improving the computing efficiency.

[0017] Furthermore, it is determined whether the seed point and the pixels in its neighborhood are in the same cluster. The determination formula is: In the formula, Represents the judgment value of the neighborhood pixel point b of the seed point a, Represents the monitoring feature quantity of seed point a, Represents the monitoring feature of the neighborhood pixel point b of the seed point a.

[0018] Furthermore, it also includes: determining an alarm level according to the number of the abnormal clusters, and the alarm level is divided into a high level and a low level.

[0019] Further, determining the alarm level according to the number of abnormal clusters includes: in response to the number of abnormal clusters being greater than a first preset value, determining the alarm level to be a high level; in response to the number of abnormal clusters being less than the first preset value, determining the alarm level to be a low level.

[0020] Beneficial effects: By detecting the thermal sensing image of the hydraulic shaft piercer collected during operation, the monitoring feature quantity of the pixel point is calculated according to the characteristics of the hydraulic shaft piercer during operation (the temperature will rise smoothly), and then the pixel point cluster is judged according to the monitoring feature quantity, and the pixel point cluster is divided, and then the abnormality degree of the cluster is obtained according to the characteristics of the cluster. It is possible to judge the abnormality based on the cluster and obtain the precise location of the abnormality. Through real-time monitoring and timely warning, unplanned downtime is reduced, thereby improving overall production efficiency and avoiding losses to overall production efficiency or safety hazards. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The following detailed description is read with reference to the accompanying drawings, which illustrate several embodiments of the present invention in an exemplary and non-limiting manner, and in which like or corresponding reference numerals represent like or corresponding parts, wherein:

[0022] Figure 1 FIG. 1 is a flow chart schematically illustrating a method for determining an abnormal position on a hydraulic shaft penetration device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0023] 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.

[0024] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0025] S101: Collecting a thermal image of the hydraulic shaft penetration device.

[0026] In one embodiment, a thermal image of the hydraulic axle piercer is collected and grayscaled to obtain a grayscale image. Specifically, images are collected when the hydraulic axle piercer starts working, and one image is collected at a preset time interval. In this embodiment, the preset time is 5 seconds. In other embodiments, the preset time can be 3 seconds or 4 seconds, etc., which can be adjusted according to the specific implementation situation. It should be noted that when collecting images, a professional thermal imaging camera is used to collect the thermal image of the hydraulic axle piercer. Then, a grayscale algorithm is used to grayscale the thermal image of the hydraulic axle piercer to obtain a corresponding grayscale image to facilitate subsequent steps.

[0027] In one embodiment, the grayscale algorithm is a process of converting a color image into a grayscale image, and the thermal sensing image can be converted into a grayscale image. Common grayscale algorithms include: weighted average method or maximum value method.

[0028] In one embodiment, under normal circumstances, the temperature of the hydraulic axle piercer will gradually increase during operation (friction and resistance will be generated between the components of the hydraulic axle piercer during operation, and these friction and resistance will be converted into heat, causing the temperature of the hydraulic axle piercer to increase; or the oil in the hydraulic system will absorb heat during the circulation process, especially under high pressure, high speed or high load conditions, the temperature rise of the oil will be more obvious, causing the temperature of the hydraulic axle piercer to increase), and in the stable operation of the hydraulic axle piercer, the temperature rise of the hydraulic axle piercer changes relatively smoothly, so in the continuous time image, the grayscale value corresponding to the pixel point should also be gradually and smoothly rising. Therefore, based on the above characteristics, the degree of change of each pixel point can be calculated to monitor the subsequent operation status of the hydraulic axle piercer.

[0029] S102: Calculate the degree of change of the pixel points.

[0030] In one embodiment, for any pixel in the grayscale image, the degree of change of the pixel is calculated, and the degree of change reflects the magnitude of the change in the grayscale value of the pixel in a continuous time. The greater the degree of change, the greater the change in the grayscale value of the pixel in a short period of time, which means that the temperature change of the hydraulic piercing device in a short period of time is greater.

[0031] In one embodiment, the degree of change of the pixel point is calculated, including: acquiring a thermal sensing image of the hydraulic axle piercing device at the current moment, and obtaining a plurality of consecutive thermal sensing images before the current moment, and calculating the change of the grayscale value of the pixel point in the plurality of consecutive thermal sensing images as the degree of change of the pixel point. The greater the change of the grayscale value of the pixel point in the plurality of consecutive thermal sensing images, the greater the degree of change; conversely, the smaller the change of the grayscale value of the pixel point in the plurality of consecutive thermal sensing images, the smaller the degree of change.

[0032] In one embodiment, the degree of change of the pixel is calculated using the following formula: ; In the formula, Indicates The degree of change of pixels, Indicates The gray value of a pixel, Indicates the current time Thermal image of The gray value of the pixel, Indicates time Thermal image of The gray value of the pixel, Indicates the total number of thermal images.

[0033] In one embodiment, during the operation of the hydraulic axle piercer, the temperature will gradually increase. As the temperature increases, the grayscale value of the pixel in the grayscale image will gradually increase. At the same time, because the hydraulic axle piercer is a whole, as the temperature increases, the temperature change amplitude within a small range is extremely similar. Therefore, the monitoring feature quantity of the pixel can be calculated based on the change in the grayscale value of the pixel within the range on the hydraulic axle piercer. The monitoring feature quantity reflects the difference amplitude between the characteristics of the pixel and its surrounding pixels. The larger the difference amplitude, the larger the monitoring feature quantity, and the greater the abnormal probability of the hydraulic axle piercer. The smaller the difference amplitude, the smaller the monitoring feature quantity, and the smaller the abnormal probability of the hydraulic axle piercer.

[0034] S103: Calculate the monitoring feature quantity of the pixel point.

[0035] In one embodiment, a window is established with any pixel in the grayscale image as the center, and the monitoring feature of the pixel is calculated according to the difference between the change degree of the pixel and the change degree of the pixels in the window, and the monitoring feature is positively correlated with the difference. In this embodiment, the window size is In other embodiments, the window size may be or Etc., can be adjusted according to actual conditions.

[0036] In one embodiment, the monitoring feature quantity of the pixel point is calculated using the following formula: ; In the formula, Indicates The larger the value of the monitoring feature of the pixel point, the The greater the difference between the characteristics of the pixel and the surrounding pixels, the smaller the value. The more similar the characteristics of the pixel are to those of the surrounding pixels; Indicates The pixel corresponds to the The gradient value of a pixel, Indicates the gradient variance within the window, reflecting whether the grayscale values ​​of the pixels in the window are approximately uniform; Represents pixel The corresponding window The degree of change of pixels, Indicates the number of pixels in the window. represents the standard normalization function. It reflects the temperature change of the pixel window position in the image in a short period of time. The larger the value, the greater the temperature change, and the greater the monitoring feature of the pixel.

[0037] In one embodiment, when an abnormality occurs in the thermal grayscale image of each hydraulic piercer, the temperature change will be uneven, resulting in inconsistent grayscale values ​​and large differences in the thermal grayscale image. For example, when a crack appears on the hydraulic piercer, the integrity of the hydraulic piercer is destroyed at the crack, which causes problems with temperature conduction, resulting in uneven temperature on the hydraulic piercer. When the temperature is uneven, there are differences in the grayscale image, and the larger the difference, the larger the monitoring feature value of the pixel point, so the monitoring feature value of the pixel point is analyzed next.

[0038] S104: Divide the pixel points into clusters and calculate the abnormality level of each cluster.

[0039] In one embodiment, the grayscale image is divided into blocks. Preferably, the grayscale image is divided into blocks according to The size of the block can also be divided into The size of the block can be set according to the specific situation. For any block, the pixel point with the largest monitoring feature value in the block is selected as the seed point. According to the difference between the monitoring feature value of the seed point and the pixel points in its neighborhood, the pixel points are clustered to obtain multiple clusters, and the abnormality degree of each cluster is calculated.

[0040] In one embodiment, judging whether the seed point and the pixels in its neighborhood are in the same cluster includes: if the absolute value of the difference between the monitoring feature quantity of the seed point a and the monitoring feature quantity of the pixel point b in its neighborhood is less than the second threshold, the seed point a and the pixel point b are divided into the same cluster. In this embodiment, the empirical value of the second threshold is 0.2. In other embodiments, the empirical value of the second threshold is 0.25 or 0.3, etc., which can be adjusted according to actual conditions. Specifically, the eight neighborhood pixels of the seed point a are obtained, and the seed point a and its eight neighborhood pixels are judged first. After the judgment is completed, the sixteen neighborhood pixels of the seed point a are continued to be judged until all the pixels in the block are judged.

[0041] In one embodiment, the seed point and the pixels in its neighborhood are judged to be in the same cluster, and the judgment formula is: In the formula, Represents the judgment value of the neighborhood pixel point b of the seed point a, Represents the monitoring feature quantity of seed point a, Represents the monitoring feature of the neighborhood pixel point b of the seed point a.

[0042] For example, when judging the neighboring pixel point h of the seed point c, the judgment value between the seed point c and the neighboring pixel point h is calculated as , The absolute value of is less than the second threshold, and the seed point c and the pixel point h are divided into the same cluster.

[0043] It should be noted that, for any two seed points, when the judgment areas of the two seed points overlap, the judgment values ​​of the seed points corresponding to the two clusters are calculated according to the above method; if the judgment values ​​of the seed points of the two clusters are less than the third threshold, the two clusters are recorded as the same cluster. In this embodiment, the empirical value of the third threshold is 0.2, and in other embodiments, the empirical value of the third threshold can be 0.18 or 0.24, etc., which can be adjusted according to the actual scenario.

[0044] For example: seed point c and pixel point h are in the same cluster, and the neighborhood pixel point of seed point b also includes pixel point h. At this time, the judgment values ​​of seed point c and seed point b are calculated. If the judgment values ​​of seed point c and seed point b are less than the third threshold, the cluster of seed point c and the cluster of seed point b are divided into the same cluster.

[0045] In one embodiment, the abnormality degree of the cluster is calculated using the following formula: ; In the formula, Indicates the abnormality degree of cluster A. The larger the value, the greater the possibility that the pixels in the cluster have abnormal operation. The reason is that the abnormal area only occupies a small part compared with the normal area. Therefore, the more pixels in the cluster, the smaller the possibility that the pixels in the cluster have abnormalities. The smaller the number of pixels in the cluster, the greater the possibility that the pixels in the cluster have abnormalities. represents the number of pixels in cluster A, Indicates the maximum value of the monitoring feature value of the pixel points of cluster A, Indicates the minimum value of the monitoring feature quantity of the pixel points of cluster A, represents the standard normalization function. It reflects the maximum difference in the cluster. The larger its value is, the worse the uniformity of the cluster is, and the more likely it is that there is an abnormality problem in the location of the cluster.

[0046] Step S105: Determine the abnormal position according to the abnormal degree of the cluster.

[0047] In one embodiment, after obtaining the abnormality degree of the cluster, if the abnormality degree of the cluster is greater than the first threshold, the cluster is determined as an abnormal cluster, an alarm is given, and the position of the pixel point in the abnormal cluster is determined as the abnormal position. In this way, the operating state of the hydraulic axle piercing device is accurately monitored. When an abnormality occurs, the abnormal position can be checked and obtained in a timely manner. In this embodiment, the empirical value of the first threshold is 0.8. In other embodiments, the empirical value of the first threshold can be 0.85 or 0.82, etc., which can be adjusted according to the actual scenario.

[0048] In one embodiment, because there may be multiple clusters, the alarm level can be determined according to the number of abnormal clusters, and the alarm level is divided into a high level and a low level. Specifically, when the number of abnormal clusters is greater than a first preset value, the alarm level is determined to be a high level; when the number of abnormal clusters is less than the first preset value, the alarm level is determined to be a low level. In this embodiment, the empirical value of the first preset value is 2, and in other embodiments, the empirical value of the first preset value may be 3 or 4, etc.

[0049] According to the above steps: by detecting the thermal sensing image of the hydraulic shaft wearer collected during the operation state, the monitoring feature quantity of the pixel point is obtained according to the characteristics of the thermal sensing image of the hydraulic shaft wearer, and then the pixel point cluster is determined according to the monitoring feature quantity, and the pixel point cluster is divided, and then the abnormality degree of the cluster is obtained according to the characteristics of the cluster. It is possible to determine the abnormality based on the cluster and obtain the precise location of the abnormality. Through real-time monitoring and timely warning, unplanned downtime is reduced, thereby improving overall production efficiency and avoiding losses to overall production efficiency or safety hazards.

[0050] The present invention also provides a hydraulic axle piercing device operating status monitoring system based on image processing. The system includes a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a hydraulic axle piercing device operating status monitoring method based on image processing according to the first aspect of the present invention is implemented.

[0051] The system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface. The configuration and functions of these components are known in the art and will not be described in detail herein.

[0052] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of a device or accessible or connectable to a device. Any application or module described in the present invention may be implemented using computer-readable / executable instructions that may be stored or otherwise maintained by such a computer-readable medium.

[0053] In the description of this specification, "plurality" or "several" means at least two, such as two, three or more, etc., unless otherwise clearly defined.

[0054] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0055] The above-mentioned embodiments only express several implementation methods of the present invention, and the description is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent application. It should be pointed out that for ordinary technicians in this field, several modifications and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention.

Claims

1. A method for monitoring the operating status of a hydraulic shaft piercer based on image processing, characterized in that: include: Collect the thermal sensing image of the hydraulic shaft penetration device, and grayscale it to obtain a grayscale image; For any pixel in the grayscale image, calculating the degree of change of the pixel, wherein the degree of change reflects the magnitude of the change in the grayscale value of the pixel over a continuous period of time; A window is established with any pixel in the grayscale image as the center, and the monitoring feature quantity of the pixel is calculated. The calculation formula is: , where Indicates The monitoring feature quantity of the pixel point, Indicates The pixel corresponds to the The gradient value of a pixel, represents the gradient variance within the window, Represents pixel The corresponding window The degree of change of pixels, Indicates the number of pixels in the window. represents the standard normalization function; The grayscale image is divided into blocks. For any block, the pixel point with the largest monitoring feature value in the block is selected as the seed point. The pixel points are divided into clusters according to the difference between the monitoring feature values ​​of the seed point and the pixels in its neighborhood, and the abnormality degree of cluster A is calculated. , the calculation formula is: ; In the formula, represents the number of pixels in cluster A, Indicates the maximum value of the monitoring feature value of the pixel points of cluster A, Indicates the minimum value of the monitoring feature quantity of the pixel points of cluster A, represents the standard normalization function; According to the degree of abnormality of the cluster, the abnormal location is determined to monitor the operating status.

2. The method for monitoring the operating status of a hydraulic shaft piercing device based on image processing according to claim 1 is characterized in that: According to the abnormality of the cluster, determine the abnormal location, including: In response to the abnormality degree of the cluster being greater than a first threshold, the cluster is determined to be an abnormal cluster, an alarm is given, and the position of the pixel point in the abnormal cluster is determined to be an abnormal position.

3. The method for monitoring the operating status of a hydraulic shaft piercing device based on image processing according to claim 1 is characterized in that: Calculate the degree of change of the pixel, including: The thermal image of the hydraulic axle piercing device at the current moment is collected, and multiple consecutive thermal images before the current moment are obtained, and the change in the grayscale value of the pixel point in the multiple consecutive thermal images is calculated as the change degree of the pixel point.

4. The method for monitoring the operating status of a hydraulic shaft piercing device based on image processing according to claim 3 is characterized in that: Calculate the degree of change of the pixel point, the calculation formula is: ； In the formula, Indicates The degree of change of pixels, Indicates The gray value of a pixel, Indicates the current time Thermal image of The gray value of the pixel, Indicates time Thermal image of The degree of change of pixels, Indicates the total number of thermal images.

5. The method for monitoring the operating status of a hydraulic shaft piercing device based on image processing according to claim 1 is characterized in that: According to the difference between the monitoring feature quantity of the seed point and the pixels in its neighborhood, the pixel points are divided into clusters, including: Determine whether the seed point and the pixels in its neighborhood belong to the same cluster; In response to the absolute value of the difference between the monitoring feature quantity of the seed point a and the monitoring feature quantity of the pixel point b in its neighborhood being less than the second threshold, the seed point a and the pixel point b are divided into the same cluster.

6. The method for monitoring the operating status of a hydraulic shaft piercing device based on image processing according to claim 5 is characterized in that: The pixel clustering also includes: For any two seed points, when the judgment areas of the two seed points overlap, the judgment values ​​of the seed points of the two clusters are calculated to determine whether the seed points and the pixels in their neighborhood belong to the same cluster. The judgment formula is: In the formula, Represents the judgment value of the neighborhood pixel point b of the seed point a, Represents the monitoring feature quantity of seed point a, Represents the monitoring feature quantity of the neighborhood pixel point b of the seed point a; In response to the judgment value of the seed points of the two clusters being smaller than the third threshold, the two clusters are recorded as the same cluster.

7. The method for monitoring the operating status of a hydraulic shaft piercing device based on image processing according to claim 2 is characterized in that: Also includes: An alarm level is determined according to the number of the abnormal clusters, and the alarm level is divided into a high level and a low level.

8. The method for monitoring the operating status of a hydraulic shaft piercing device based on image processing according to claim 7 is characterized in that: The alarm level is determined according to the number of abnormal clusters, including: In response to the number of the abnormal clusters being greater than a first preset value, the alarm level is determined to be a high level; In response to the number of the abnormal clusters being less than a first preset value, the alarm level is determined to be a low level.

Images