Multi-stage collaborative intelligent safety deviation correction system and method for power plant coal conveying system

Abstract

This invention discloses a multi-level collaborative intelligent safety deviation correction system and method for power plant coal conveying systems. This invention relates to the field of conveyor belt technology and solves the problem that existing deviation correction methods only focus on correcting conveyor belt deviation itself, without comprehensively assessing potential safety hazards such as abnormal temperature and vibration accompanying the deviation process. This invention does not simply rely on deviation data for debugging; it accurately identifies potential hazards such as abnormal temperature and vibration, and classifies risk levels accordingly, achieving closed-loop management of "deviation identification - risk assessment - graded handling." In medium-risk zones, through collaborative debugging of adjacent idlers and targeted prevention and control, the escalation of hazards is effectively curbed. In high-risk zones, based on the cross-characteristics of abnormal data, large-scale or full-scale debugging is flexibly selected to simultaneously prevent major safety accidents such as conveyor belt tearing and friction-induced fires. This significantly improves the safety and stability of the coal conveying system and reduces the incidence of safety accidents and equipment maintenance costs.

Description

Technical Field

[0001] This invention relates to the field of conveyor belt technology, specifically to a multi-level collaborative intelligent safety correction system and method for coal conveying systems in power plants. Background Technology

[0002] The coal conveying system is a core auxiliary system of thermal power plants. Its main function is to stably and efficiently transport coal from the coal storage yard to the boiler combustion system. The continuous and stable operation of the coal conveying system directly determines the power generation efficiency and safety level of the thermal power plant. As the core conveying component of the coal conveying system, the stability of its operating state is crucial. Belt misalignment is one of the most common abnormal phenomena during conveyor belt operation. If it is not corrected in a timely and effective manner, it can easily lead to a series of safety hazards and equipment failures. Currently, the conveyor belt misalignment methods used in power plant coal conveying systems are mostly based on manual monitoring, manual adjustment, or single mechanical correction, which have many technical shortcomings and cannot meet the high-efficiency, safe, and unattended operation and maintenance requirements of smart power plants. Specifically, existing deviation correction methods generally suffer from the following problems: First, the accuracy of deviation identification is low, relying heavily on manual visual observation or single sensor monitoring, making it difficult to accurately identify subtle deviations in the conveyor belt. Furthermore, they are easily affected by environmental factors such as high dust levels and dim lighting in power plant coal conveying corridors, leading to untimely locking of abnormal idlers and a high rate of false positives and false negatives, failing to curb the expansion of deviation risks at the source. Second, the deviation correction adjustment is highly haphazard. Most existing methods directly activate the deviation correction mechanism for adjustment after deviation is detected, without classifying and assessing the degree of deviation and the risk of anomalies. This easily leads to over-adjustment or under-adjustment, not only failing to achieve the desired correction effect but also potentially exacerbating the deviation. The problems include: 1) Belt wear and tear, idler damage, and even secondary failures such as reverse belt deviation; 2) Lagging risk control, with existing correction methods focusing only on correcting the belt deviation itself without considering potential safety hazards such as abnormal temperature and vibration during the deviation process. This makes it difficult to identify major safety risks such as fires and belt tears caused by friction heating and bearing jamming, leading to passive safety accident prevention; 3) Low level of intelligence, with most correction operations requiring full manual intervention, which not only increases the workload of maintenance personnel but also suffers from large human error and slow response, failing to adapt to the development trend of unmanned operation in smart power plants.

[0003] In addition, although some existing deviation correction methods attempt to introduce machine vision or multi-sensor data, they have failed to form a systematic closed loop of identification, evaluation, and debugging. They can either only identify deviations but cannot accurately locate abnormal idlers, or they can only perform simple deviation corrections but cannot implement differentiated treatments based on risk levels. They are unable to meet the multiple needs of deviation correction accuracy, safety control, and equipment protection.

[0004] As thermal power plants develop towards intelligence, efficiency, and safety, the existing conveyor belt correction methods for coal conveying systems can no longer meet the actual operation and maintenance needs. Therefore, developing a method that can accurately identify deviation, quickly lock abnormal idlers, assess risks, and provide differentiated intelligent correction has become an urgent technical problem to be solved in the current operation and maintenance field of power plant coal conveying systems. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides a multi-level collaborative intelligent safety deviation correction system and method for power plant coal conveying systems. This solves the problem that existing deviation correction methods only focus on correcting the conveyor belt deviation itself, without comprehensively assessing potential safety hazards such as abnormal temperature and vibration that accompany the deviation process.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a multi-level collaborative intelligent safety correction method for power plant coal conveying systems, comprising the following steps: Step 1: Use machine vision equipment to acquire and confirm the monitoring image of the conveyor belt, and use the Sobel algorithm to determine the edge contours existing in the monitoring image, lock the gap features, and mark abnormal idlers according to the gap features. The specific method is as follows: The acquired monitoring images are converted to grayscale to confirm the grayscale image associated with the corresponding monitoring images. Then, the grayscale values ​​associated with different points in the monitoring images are confirmed in turn to obtain the grayscale image associated with the corresponding monitoring images. The Sobel algorithm is used to identify the horizontal and vertical gradients associated with different gray-level points within a grayscale image. Based on the identified horizontal and vertical gradients, a composite gradient is determined. ; Gray points with a comprehensive gradient ≥ Y1 are recorded as gradient points; otherwise, no marking is performed. Y1 is a preset value. The lines connecting several consecutive gradient points are recorded as gradient lines. Identify the gap characteristics of the idler roller sections. Based on the marked gradient lines, confirm the gap generated by the gradient lines between the conveyor belt and the frame. Also, identify the shortest distance between different connection points on both sides of the gap. Average these shortest distances and lock the average distance. Finally, calculate the difference between the average distances on both sides and lock the characteristic difference W1. i Then, from the multiple sets of closest distances associated with the gap on one side, confirm the minimum and maximum values, and use: (maximum value - minimum value) = correlation difference to lock the correlation difference. Then, average the correlation differences on both sides to confirm the correlation error W2. i , where i represents different idler roller zones; Used: W1 i ×C1+W2i ×C2=XD i Confirm the gap feature XD associated with the corresponding idler section. i Where C1 and C2 are preset fixed coefficient factors, and C1 + C2 = 1, XD i If XD ≤ Y2, then the idler roller zone is marked as a normal zone; if XD i If Y2 is greater than or equal to Y2, the idler section is marked as a section to be confirmed, and the associated idler is marked as an abnormal idler, where Y2 is a preset value. Step 2: Compare the gap characteristics of the abnormal idler with the set value to identify the fine-tuning zone and the zone to be adjusted. For the fine-tuning zone, directly adjust the angle of the side associated with the abnormal idler. For the zone to be adjusted, confirm the infrared thermal imaging data and vibration spectrum data associated with the zone. The specific method is as follows: If Y2≤XD i If Y3 < Y3, the corresponding idler roller zone will be marked as a fine-tuning zone, where Y3 is a preset value; If Y3≤XD i Then the corresponding idler roller zone will be marked as the zone to be adjusted; In step two, the specific method for adjusting the angle of the fine-tuning zone is as follows: Identify the average distance associated with the gaps on both sides of the fine-tuning zone, and mark the side with the smaller average distance as the side to be adjusted. Then, increase the angle of the corresponding idler roller relative to the side to be adjusted, with each increase not exceeding 0.5°-1°. After the angle is increased, check whether the gap characteristics meet XD. i If the value is less than or equal to Y2, the value will be adjusted upwards. If the value is satisfied, the fine-tuning process of the fine-tuning partition will be completed. In step two, the specific method for confirming the infrared thermal imaging data and bearing vibration spectrum data associated with the partition to be adjusted is as follows: Lock the side of the partition whose mean value is smaller and mark it as the side to be adjusted; A set of monitoring cycles is defined, and the monitoring cycle is a preset cycle. Within the monitoring cycle, an infrared thermal imager is used to monitor the infrared thermal imaging data associated with the side to be investigated and generate an infrared thermal imaging change curve. Simultaneously, vibration monitoring sensors are used to confirm the vibration spectrum data generated by the side to be adjusted during the monitoring period and generate vibration spectrum change curves. Step 3: Perform feature verification on the infrared thermal imaging data and vibration spectrum data associated with the area to be adjusted, identify abnormal data, and based on the comprehensive characteristics of the abnormal data, mark the area to be adjusted as a medium-risk area or a high-risk area. The specific method is as follows: Regarding the generated infrared thermal imaging curve: Based on the set temperature range, two sets of temperature range lines are generated within the infrared thermal imaging curve. The temperature difference between the two sets of temperature range lines is consistent with the temperature range. The two sets of temperature range lines maintain a constant temperature difference and move up and down synchronously, locking the optimal movement process during the movement. For each movement process, the length L of the curve segment included within the two sets of temperature range lines is confirmed. k Where k represents different movement processes, and L k The movement process associated with max is called the optimal movement process, and the position of the temperature range line associated with the optimal movement process is called the determined position. The part of the curve that exceeds the determined position is called the abnormal temperature curve. For the generated vibration spectrum change curve: Based on the set vibration range, two sets of vibration range lines are generated within the vibration spectrum change curve, and the range difference between the vibration range lines is consistent with the vibration range. The abnormal vibration curve is locked within the vibration range line using the same determination method as the abnormal temperature curve. If neither the abnormal temperature curve nor the abnormal vibration curve exists, the area to be adjusted is marked as the fine-tuning area, and the fine-tuning area debugging process is executed. If only an abnormal temperature curve exists but no abnormal vibration curve exists, or if only an abnormal vibration curve exists but no abnormal temperature curve exists, then the area to be adjusted will be marked as a medium-risk area. If both abnormal temperature curves and abnormal vibration curves exist, the area to be adjusted will be marked as a high-risk area. Step 4: Based on the marked medium-risk and high-risk zones, different debugging methods are used to partially debug the medium-risk zones and extensively or completely debug the high-risk zones. The specific methods are as follows: Identify the side to be adjusted marked by the section to be adjusted, mark the two sets of idler sections adjacent to the section to be adjusted as the following area, and mark the gaps on both sides of the side to be adjusted within the following area as the following side. Based on the marked sides to be adjusted and the following sides, a synchronous adjustment method is adopted to adjust the angle of the corresponding sides of the three sets of idlers upwards, with each adjustment not exceeding 1°-2°. After the angle is adjusted, it is identified whether the gap characteristics meet XD. i If the value is less than or equal to Y2, the value will be continuously increased; if the value is met, the debugging process will be partially completed. The specific method for partially debugging high-risk zones is as follows: Identify the marked abnormal temperature curves and abnormal vibration curves, confirm the time period associated with the abnormal temperature curve and record it as the abnormal temperature time period, simultaneously confirm the time period associated with the abnormal vibration curve and record it as the abnormal vibration time period, identify the cross-time periods generated between the abnormal temperature time period and the abnormal vibration time period, and record the proportion of the cross-time period located in the abnormal temperature time period ZB1, and then record the proportion of the cross-time period located in the abnormal vibration time period ZB2. Then, simultaneously perform average processing on the two confirmed time period proportions ZB1 and ZB2, lock the average proportion, if the average proportion ≤ 0.3, then execute a large number of debugging processes, if the average proportion > 0.3, then execute all debugging processes; Extensive debugging process: All other idler rollers on the same side as the side to be adjusted are designated as following sides. Using the side to be adjusted as the center, at least half of the adjacent following sides are designated as synchronous debugging sides. The angles of both the synchronous debugging sides and the side to be adjusted are adjusted upwards, with each adjustment not exceeding 1°-2°. After the angle adjustment, it is determined whether the gap characteristics meet the XD standard. i If the value is less than or equal to Y2, the value will be continuously increased; if the value is met, the debugging process will be partially completed. Full debugging process: Adjust the angle of all idlers on the same side as the side to be adjusted upwards, with each upward adjustment not exceeding 1°-2°. After the angle is adjusted, check whether the gap characteristics meet XD. i If the value is less than or equal to Y2, the value will be continuously increased; if the value is met, the debugging process will be partially completed.

[0007] Preferred, a multi-level collaborative intelligent safety correction system for power plant coal conveying systems includes: At the abnormal idler marking end, machine vision equipment is used to acquire and confirm the monitoring image of the conveyor belt, and the Sobel algorithm is used to determine the edge contours existing in the monitoring image, lock the gap features, and mark the abnormal idler based on the gap features. The abnormal idler processing end compares the gap characteristics of the marked abnormal idler with the set value, locks the fine-tuning zone and the zone to be adjusted. For the fine-tuning zone, the angle of the side associated with the abnormal idler is directly adjusted. For the zone to be adjusted, the infrared thermal imaging data and vibration spectrum data associated with the zone to be adjusted are confirmed. The partition to be adjusted verification end performs feature verification on the infrared thermal imaging data and vibration spectrum data associated with the partition to be adjusted, identifies abnormal data, and marks the partition to be adjusted as a medium-risk partition or a high-risk partition based on the comprehensive feature performance of the abnormal data. The integrated debugging and processing terminal adopts different debugging and processing methods according to the marked medium-risk and high-risk zones. Partial debugging is carried out on medium-risk zones, and extensive or complete debugging is carried out on high-risk zones to ensure the normal operation of the conveyor belt.

[0008] This invention provides a multi-level collaborative intelligent safety correction system and method for coal conveying systems in power plants. Compared with existing technologies, it has the following advantages: Based on gap features XD i The numerical range is used to divide the abnormal idler into fine-tuning zones and zones to be adjusted. The zones to be adjusted are further subdivided into medium-risk zones and high-risk zones by combining infrared thermal imaging data and vibration spectrum data. Different debugging methods are adopted for different zones: the fine-tuning zone only needs to make small-amplitude, high-frequency fine-tuning on the side associated with the abnormal idler, while the zones to be adjusted are subject to partial, large-scale, or full debugging based on the risk level. This ensures the correction effect and avoids secondary problems such as idler damage and conveyor belt reverse deviation caused by over-adjustment. Instead of relying solely on deviation data for debugging, the system simultaneously collects infrared thermal imaging data and vibration spectrum data for the areas to be debugged. By generating change curves and locking abnormal curves, it accurately identifies potential hazards such as abnormal temperature and vibration, and classifies them according to risk levels. This achieves closed-loop management of "deviation identification - risk assessment - graded handling". Medium-risk areas effectively curb the escalation of hazards through coordinated debugging of adjacent idlers and targeted prevention and control. High-risk areas flexibly select large-scale or full debugging based on the cross-characteristics of abnormal data, and simultaneously prevent major safety accidents such as conveyor belt tearing and friction fire. This significantly improves the safety and stability of the coal conveying system and reduces the incidence of safety accidents and equipment maintenance costs. Attached Figure Description

[0009] Figure 1 This is a schematic diagram of the method flow of the present invention; Figure 2 This is a schematic diagram of the principle framework of the present invention. Detailed Implementation

[0010] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0011] First Embodiment Please see Figure 1 This application provides a multi-level collaborative intelligent safety correction method for coal conveying systems in power plants, including the following steps: Step 1: Use machine vision equipment to acquire images of the conveyor belt, confirm the monitoring image, and use the Sobel algorithm to determine the edge contours within the monitoring image, lock the gap features, and mark abnormal idlers based on the gap features. Specifically, based on the gap distance between the conveyor belt and the surrounding frame, it can effectively confirm whether the corresponding conveyor belt is offset, and quickly lock the corresponding abnormal idlers according to the confirmation process. The specific method for locking the gap features is as follows: The acquired monitoring images are converted to grayscale to confirm the grayscale image associated with the corresponding monitoring images. The RGB value of a certain point in the monitoring images is confirmed, and the grayscale value associated with the corresponding point is confirmed using the formula: 0.299×R+0.114×G+0.587×B=grayscale value. Then, the grayscale values ​​associated with different points in the monitoring images are confirmed in turn to obtain the grayscale image associated with the corresponding monitoring images. The Sobel algorithm is used to identify the horizontal and vertical gradients associated with different gray-level points within a grayscale image. Based on the identified horizontal and vertical gradients, a composite gradient is determined. When confirming gradient data, different points are associated with different gray values. The gray points exist in a nine-square grid. The middle gray point and the surrounding gray points are convolved and summed according to the set weight factors to lock the horizontal gradient and vertical gradient corresponding to the middle gray point, thereby locking the corresponding comprehensive gradient. This allows for quick and effective confirmation of the comprehensive gradient associated with each point. Gray points with a comprehensive gradient ≥ Y1 are recorded as gradient points; otherwise, no marking is made. Y1 is a preset value, the specific value of which is determined by the operator based on experience. The lines generated between several consecutive gradient points are recorded as gradient lines. After the gradient lines are confirmed, they are generally the two side edge lines of the conveyor belt and the two side edge lines of the entire frame. Based on the idler numbers involved in the monitoring screen (their numbers are generally marked on the top of the frame and can be directly identified), the idler partition associated with each idler number is locked. The area contained between the same idler numbers on both sides belongs to a group of idler partitions, and both idler numbers on both sides are marked as points to be connected. By connecting the corresponding points to be connected, the corresponding idler partitions can be confirmed on the surface of the conveyor belt. Identify the gap characteristics of the idler roller sections. Based on the marked gradient lines, confirm the gap generated by the gradient lines between the conveyor belt and the frame. Also, identify the shortest distance between different connection points on both sides of the gap. Average these shortest distances and lock the average distance. Finally, calculate the difference between the average distances on both sides and lock the characteristic difference W1. i(After difference processing, absolute value processing is also required.) Then, from the multiple sets of nearest distances associated with the gap on one side, confirm the minimum and maximum values, and use: (maximum value - minimum value) = correlation difference to lock the correlation difference. Then, average the correlation differences on both sides to confirm the correlation error W2. i , where i represents different idler roller zones; Used: W1 i ×C1+W2 i ×C2=XD i Confirm the gap feature XD associated with the corresponding idler section. i C1 and C2 are preset fixed coefficient factors, the specific values ​​of which are determined by the operator based on experience, and C1 + C2 = 1, XD i If XD ≤ Y2, then the idler roller zone is marked as a normal zone; if XD i If Y2 is greater than or equal to Y2, the idler section is marked as a section to be confirmed, and the associated idler is marked as an abnormal idler. Y2 is a preset value, and its specific value is determined by the operator based on experience. It is generally 20mm. Step 2: For the marked abnormal idler, compare the gap characteristics of the abnormal idler with the set value, lock the fine-tuning zone and the zone to be adjusted. For the fine-tuning zone, directly adjust the angle of the side associated with the abnormal idler. For the zone to be adjusted, confirm the infrared thermal imaging data and vibration spectrum data associated with the zone to be adjusted. The specific method for confirming the fine-tuning partition and the partition to be adjusted is as follows: If Y2≤XD i If <Y3, the corresponding idler roller zone will be marked as a fine-tuning zone, where Y3 is a preset value, typically 50mm. If Y3≤XD i Then the corresponding idler roller zone will be marked as the zone to be adjusted; The specific method for adjusting the angle of the fine-tuning zone is as follows: Identify the average distance associated with the gaps on both sides of the fine-tuning zone, and mark the side with the smaller average distance as the side to be adjusted. Then, increase the angle of the corresponding idler roller relative to the side to be adjusted, with each increase not exceeding 0.5°-1°. After the angle is increased, check whether the gap characteristics meet XD. i If the value is less than or equal to Y2, the value will be adjusted upwards. If the value is satisfied, the fine-tuning process of the fine-tuning partition will be completed. The specific method for confirming the infrared thermal imaging data and bearing vibration spectrum data associated with the partition to be adjusted is as follows: Lock the side of the partition whose mean value is smaller and mark it as the side to be adjusted; A set of monitoring cycles is defined, which are preset cycles. The specific values ​​are determined by the operators based on their experience. Within the monitoring cycle, an infrared thermal imager is used to monitor the infrared thermal imaging data associated with the side to be adjusted and to generate an infrared thermal imaging change curve. Simultaneously, vibration monitoring sensors are used to confirm the vibration spectrum data generated by the side to be adjusted during the monitoring period and generate vibration spectrum change curves. Specifically, in order to identify the specific characteristics associated with the partition to be adjusted, it is necessary to monitor and confirm the relevant data associated with the partition to be adjusted. Based on the generated infrared thermal imaging change curve and vibration spectrum change curve, some abnormal characteristics of the partition to be adjusted can be identified. Subsequently, based on these characteristics, the cause of the abnormality of the partition to be adjusted can be comprehensively evaluated, and corresponding measures can be taken in real time.

[0012] Step 3: Perform feature verification on the infrared thermal imaging data and vibration spectrum data associated with the area to be adjusted, identify abnormal data, and mark the area to be adjusted as a medium-risk area or a high-risk area based on the comprehensive characteristics of the abnormal data. Regarding the generated infrared thermal imaging curve: Based on the set temperature range, two sets of temperature range lines are generated within the infrared thermal imaging curve. The temperature difference between the two sets of temperature range lines is consistent with the temperature range. The two sets of temperature range lines maintain a constant temperature difference and move up and down synchronously, locking the optimal movement process during the movement. For each movement process, the length L of the curve segment included within the two sets of temperature range lines is confirmed. k Where k represents different movement processes, and L k The movement process associated with max is called the optimal movement process, and the position of the temperature range line associated with the optimal movement process is called the determined position. The part of the curve that exceeds the determined position is called the abnormal temperature curve. For the generated vibration spectrum change curve: Based on the set vibration range, two sets of vibration range lines are generated within the vibration spectrum change curve, and the range difference between the vibration range lines is consistent with the vibration range. The abnormal vibration curve is locked within the vibration range line using the same determination method as the abnormal temperature curve. If neither the abnormal temperature curve nor the abnormal vibration curve exists, the area to be adjusted is marked as the fine-tuning area, and the fine-tuning area debugging process is executed. If only an abnormal temperature curve exists but no abnormal vibration curve exists, or if only an abnormal vibration curve exists but no abnormal temperature curve exists, then the area to be adjusted will be marked as a medium-risk area. If both abnormal temperature curves and abnormal vibration curves exist, the area to be adjusted will be marked as a high-risk area. Step 4: Based on the marked medium-risk and high-risk zones, adopt different debugging methods to partially debug the medium-risk zones and extensively or completely debug the high-risk zones to ensure the normal operation of the conveyor belt. The specific method for partially adjusting the medium-risk zones is as follows: Identify the side to be adjusted marked by the section to be adjusted, mark the two sets of idler sections adjacent to the section to be adjusted as the following area, and mark the gaps on both sides of the side to be adjusted within the following area as the following side. Based on the marked sides to be adjusted and the following sides, a synchronous adjustment method is adopted to adjust the angle of the corresponding sides of the three sets of idlers upwards, with each adjustment not exceeding 1°-2°. After the angle is adjusted, it is identified whether the gap characteristics meet XD. i If the value is less than or equal to Y2, the value will be continuously increased; if the value is met, the debugging process will be partially completed. The specific method for partially debugging high-risk zones is as follows: Identify the marked abnormal temperature curves and abnormal vibration curves, confirm the time period associated with the abnormal temperature curve and record it as the abnormal temperature time period, simultaneously confirm the time period associated with the abnormal vibration curve and record it as the abnormal vibration time period, identify the cross-time periods generated between the abnormal temperature time period and the abnormal vibration time period, and record the proportion of the cross-time period located in the abnormal temperature time period ZB1, and then record the proportion of the cross-time period located in the abnormal vibration time period ZB2. Then, simultaneously perform average processing on the two confirmed time period proportions ZB1 and ZB2, lock the average proportion, if the average proportion ≤ 0.3, then execute a large number of debugging processes, if the average proportion > 0.3, then execute all debugging processes; Extensive debugging process: All other idler rollers on the same side as the side to be adjusted are designated as following sides. Using the side to be adjusted as the center, at least half of the adjacent following sides are designated as synchronous debugging sides. The angles of both the synchronous debugging sides and the side to be adjusted are adjusted upwards, with each adjustment not exceeding 1°-2°. After the angle adjustment, it is determined whether the gap characteristics meet the XD standard. i If the value is less than or equal to Y2, the value will be continuously increased; if the value is met, the debugging process will be partially completed. Full debugging process: Adjust the angle of all idlers on the same side as the side to be adjusted upwards, with each upward adjustment not exceeding 1°-2°. After the angle is adjusted, check whether the gap characteristics meet XD. i If the value is less than or equal to Y2, the value will be continuously increased; if the value is met, the debugging process will be partially completed.

[0013] Second Embodiment A multi-level collaborative intelligent safety correction system for power plant coal conveying systems includes: At the abnormal idler marking end, machine vision equipment is used to acquire and confirm the image of the conveyor belt, and then the Sobel algorithm is used to determine the edge contours existing in the monitoring image, lock the gap features, and mark the abnormal idler based on the gap features. The abnormal idler processing end compares the gap characteristics of the marked abnormal idler with the set value, locks the fine-tuning zone and the zone to be adjusted. For the fine-tuning zone, the angle of the side associated with the abnormal idler is directly adjusted. For the zone to be adjusted, the infrared thermal imaging data and vibration spectrum data associated with the zone to be adjusted are confirmed. The partition to be adjusted verification end performs feature verification on the infrared thermal imaging data and vibration spectrum data associated with the partition to be adjusted, identifies abnormal data, and marks the partition to be adjusted as a medium-risk partition or a high-risk partition based on the comprehensive feature performance of the abnormal data. The integrated debugging and processing terminal adopts different debugging and processing methods according to the marked medium-risk and high-risk zones. Partial debugging is carried out on medium-risk zones, and extensive or complete debugging is carried out on high-risk zones to ensure the normal operation of the conveyor belt.

[0014] Some of the data in the above formulas are numerical calculations with dimensions removed, and the contents not described in detail in this specification are all prior art known to those skilled in the art.

[0015] The above embodiments are only used to illustrate the technical methods of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of the present invention without departing from the spirit and scope of the technical methods of the present invention.

Claims

1. A multi-level collaborative intelligent safety correction method for coal conveying systems in power plants, characterized in that, Includes the following steps: Step 1: Use machine vision equipment to acquire and confirm the monitoring image of the conveyor belt, and use the Sobel algorithm to determine the edge contours existing in the monitoring image, lock the gap features, and mark abnormal idlers according to the gap features. Step 2: Compare the gap characteristics of the abnormal idler with the set value, lock the fine-tuning zone and the zone to be adjusted. For the fine-tuning zone, directly adjust the angle of the side associated with the abnormal idler. For the zone to be adjusted, confirm the infrared thermal imaging data and vibration spectrum data associated with the zone to be adjusted. Step 3: Perform feature verification on the infrared thermal imaging data and vibration spectrum data associated with the area to be adjusted, identify abnormal data, and mark the area to be adjusted as a medium-risk area or a high-risk area based on the comprehensive feature performance of the abnormal data. Step 4: Based on the marked medium-risk and high-risk zones, use different debugging methods to partially debug the medium-risk zones and extensively or completely debug the high-risk zones.

2. The multi-level collaborative intelligent safety correction method for power plant coal conveying systems according to claim 1, characterized in that, In step one, the specific method for locking the gap feature is as follows: The acquired monitoring images are converted to grayscale to confirm the grayscale image associated with the corresponding monitoring images. Then, the grayscale values ​​associated with different points in the monitoring images are confirmed in turn to obtain the grayscale image associated with the corresponding monitoring images. The Sobel algorithm is used to identify the horizontal and vertical gradients associated with different gray-level points within a grayscale image. Based on the identified horizontal and vertical gradients, the composite gradient is then determined. That: ; Gray points with a comprehensive gradient ≥ Y1 are recorded as gradient points; otherwise, no marking is performed. Y1 is a preset value. The lines connecting several consecutive gradient points are recorded as gradient lines. Identify the gap characteristics of the idler roller sections. Based on the marked gradient lines, confirm the gap generated by the gradient lines between the conveyor belt and the frame. Also, identify the shortest distance between different connection points on both sides of the gap. Average these shortest distances and lock the average distance. Finally, calculate the difference between the average distances on both sides and lock the characteristic difference W1. i Then, from the multiple sets of closest distances associated with the gap on one side, confirm the minimum and maximum values, and use: (maximum value - minimum value) = correlation difference to lock the correlation difference. Then, average the correlation differences on both sides to confirm the correlation error W2. i , where i represents different idler roller zones; Used: W1 i ×C1+W2 i ×C2=XD i Confirm the gap feature XD associated with the corresponding idler section. i Where C1 and C2 are preset fixed coefficient factors, and C1 + C2 = 1, XD i If XD ≤ Y2, then the idler roller zone is marked as a normal zone; if XD i If Y2 is greater than or equal to Y2, the idler section is marked as a section to be confirmed, and the associated idler is marked as an abnormal idler. Y2 is a preset value.

3. The multi-level collaborative intelligent safety correction method for power plant coal conveying systems according to claim 1, characterized in that, In step two, the specific method for confirming the fine-tuning partition and the partition to be adjusted is as follows: If Y2≤XD i If Y3 < Y3, the corresponding idler roller zone will be marked as a fine-tuning zone, where Y3 is a preset value; If Y3≤XD i If so, the corresponding idler roller zone will be marked as the zone to be adjusted.

4. The multi-level collaborative intelligent safety correction method for power plant coal conveying systems according to claim 3, characterized in that, In step two, the specific method for adjusting the angle of the fine-tuning zone is as follows: Identify the average distance associated with the gaps on both sides of the fine-tuning zone, and mark the side with the smaller average distance value as the side to be adjusted. Then, increase the angle of the corresponding idler roller relative to the side to be adjusted, with each increase not exceeding 0.5°-1°. After the angle is increased, check whether the gap characteristics meet XD. i If the value is less than or equal to Y2, the value will be continuously increased; if the value is satisfied, the fine-tuning process of the fine-tuning partition will be completed.

5. The multi-level collaborative intelligent safety correction method for power plant coal conveying systems according to claim 3, characterized in that, In step two, the specific method for confirming the infrared thermal imaging data and bearing vibration spectrum data associated with the partition to be adjusted is as follows: Lock the side of the partition whose mean value is smaller and mark it as the side to be adjusted; A set of monitoring cycles is defined, and the monitoring cycle is a preset cycle. Within the monitoring cycle, an infrared thermal imager is used to monitor the infrared thermal imaging data associated with the side to be investigated and generate an infrared thermal imaging change curve. Simultaneously, vibration monitoring sensors are used to confirm the vibration spectrum data generated by the side to be adjusted during the monitoring period and generate vibration spectrum change curves.

6. The multi-level collaborative intelligent safety correction method for power plant coal conveying systems according to claim 1, characterized in that, In step three, the specific method for marking the partition to be adjusted as a medium-risk partition or a high-risk partition is as follows: Regarding the generated infrared thermal imaging curve: Based on the set temperature range, two sets of temperature range lines are generated within the infrared thermal imaging curve. The temperature difference between the two sets of temperature range lines is consistent with the temperature range. The two sets of temperature range lines maintain a constant temperature difference and move up and down synchronously, locking the optimal movement process during the movement. For each movement process, the length L of the curve segment included within the two sets of temperature range lines is confirmed. k Where k represents different movement processes, and L k The movement process associated with max is called the optimal movement process, and the position of the temperature range line associated with the optimal movement process is called the determined position. The part of the curve that exceeds the determined position is called the abnormal temperature curve. For the generated vibration spectrum change curve: Based on the set vibration range, two sets of vibration range lines are generated within the vibration spectrum change curve, and the range difference between the vibration range lines is consistent with the vibration range. The abnormal vibration curve is locked within the vibration range line using the same determination method as the abnormal temperature curve. If neither the abnormal temperature curve nor the abnormal vibration curve exists, the area to be adjusted is marked as the fine-tuning area, and the fine-tuning area debugging process is executed. If only an abnormal temperature curve exists but no abnormal vibration curve exists, or if only an abnormal vibration curve exists but no abnormal temperature curve exists, then the area to be adjusted will be marked as a medium-risk area. If both abnormal temperature curves and abnormal vibration curves exist, the area to be adjusted will be marked as a high-risk area.

7. The multi-level collaborative intelligent safety correction method for power plant coal conveying systems according to claim 6, characterized in that, In step four, the specific method for partially debugging the medium-risk zone is as follows: Identify the side to be adjusted marked by the section to be adjusted, mark the two sets of idler sections adjacent to the section to be adjusted as the following area, and mark the gaps on both sides of the side to be adjusted within the following area as the following side. Based on the marked sides to be adjusted and the following sides, a synchronous adjustment method is adopted to adjust the angle of the corresponding sides of the three sets of idlers upwards, with each adjustment not exceeding 1°-2°. After the angle is adjusted, it is identified whether the gap characteristics meet XD. i If the value is less than or equal to Y2, the value will be continuously increased; if the value is met, the debugging process will be partially completed.

8. The multi-level collaborative intelligent safety correction method for power plant coal conveying systems according to claim 6, characterized in that, In step four, the specific method for partially debugging the high-risk partition is as follows: Identify the marked abnormal temperature curves and abnormal vibration curves, confirm the time period associated with the abnormal temperature curve and record it as the abnormal temperature time period, simultaneously confirm the time period associated with the abnormal vibration curve and record it as the abnormal vibration time period, identify the cross-time periods generated between the abnormal temperature time period and the abnormal vibration time period, and record the proportion of the cross-time period located in the abnormal temperature time period ZB1, and then record the proportion of the cross-time period located in the abnormal vibration time period ZB2. Then, simultaneously perform average processing on the two confirmed time period proportions ZB1 and ZB2, lock the average proportion, if the average proportion ≤ 0.3, then execute a large number of debugging processes, if the average proportion > 0.3, then execute all debugging processes; Extensive debugging process: All other idler rollers on the same side as the side to be adjusted are designated as following sides. Using the side to be adjusted as the center, at least half of the adjacent following sides are designated as synchronous debugging sides. The angles of both the synchronous debugging sides and the side to be adjusted are adjusted upwards, with each adjustment not exceeding 1°-2°. After the angle adjustment, it is determined whether the gap characteristics meet the XD standard. i If the value is less than or equal to Y2, the value will be continuously increased; if the value is met, the debugging process will be partially completed. Full debugging process: Adjust the angle of all idlers on the same side as the side to be adjusted upwards, with each upward adjustment not exceeding 1°-2°. After the angle is adjusted, check whether the gap characteristics meet XD. i If the value is less than or equal to Y2, the value will be continuously increased; if the value is met, the debugging process will be partially completed.

9. A multi-level collaborative intelligent safety correction system for power plant coal conveying systems, the system operating according to any one of claims 1-8, characterized in that, include: At the abnormal idler marking end, machine vision equipment is used to acquire and confirm the monitoring image of the conveyor belt, and the Sobel algorithm is used to determine the edge contours existing in the monitoring image, lock the gap features, and mark the abnormal idler based on the gap features. The abnormal idler processing end compares the gap characteristics of the marked abnormal idler with the set value, locks the fine-tuning zone and the zone to be adjusted. For the fine-tuning zone, the angle of the side associated with the abnormal idler is directly adjusted. For the zone to be adjusted, the infrared thermal imaging data and vibration spectrum data associated with the zone to be adjusted are confirmed. The partition to be adjusted verification end performs feature verification on the infrared thermal imaging data and vibration spectrum data associated with the partition to be adjusted, identifies abnormal data, and marks the partition to be adjusted as a medium-risk partition or a high-risk partition based on the comprehensive feature performance of the abnormal data. The integrated debugging and processing terminal adopts different debugging and processing methods according to the marked medium-risk and high-risk zones. Partial debugging is carried out on medium-risk zones, and extensive or complete debugging is carried out on high-risk zones to ensure the normal operation of the conveyor belt.

Images