Scraper conveyer coal flow quantity detection method based on composite intelligent camera

Abstract

The invention discloses a scraper conveyor coal flow and coal quantity detection method based on a composite intelligent camera, and relates to the technical field of coal mining, and the coal flow and coal quantity detection method comprises the steps of equipment installation and calibration, image acquisition and processing, coal flow feature extraction, coal quantity calculation and result output, result verification and algorithm optimization. The coal flow quantity monitoring system has the advantages that comprehensive, real-time and intelligent monitoring of the coal flow quantity of the scraper conveyor is realized by integrating the composite intelligent camera, the light supplementing lamp, the illumination intensity sensor and the coal quality detection means, the coal quality change can be found in time by detecting the coal quality every other week, the coal density is re-evaluated according to the change, and the coal flow quantity can be accurately detected. According to the comprehensive intelligent monitoring and coal quality adaptability optimization strategy, the coal quantity detection precision is improved, the adaptability and reliability of the system are enhanced, and more accurate data support is provided for coal mine production.

Description

Technical Field

[0001] The invention relates to the technical field of coal mining, and in particular to a method for detecting coal flow and amount of a scraper conveyor based on a composite intelligent camera. Background Art

[0002] In the field of coal mining production, the scraper conveyor is the core equipment for coal transportation. The accurate monitoring of coal flow and coal quantity is crucial for production scheduling, cost control and safety monitoring. However, the traditional coal quantity detection method has many shortcomings and cannot meet the intelligent needs of modern coal mining production. Traditional coal quantity detection methods mostly rely on manual measurement or simple sensor monitoring. These methods are not only inefficient and easily affected by human errors and environmental factors, but also unable to capture changes in coal quality in a timely manner, making it difficult to ensure the accuracy of coal quantity detection results. To this end, we propose a scraper conveyor coal flow and coal quantity detection method based on a composite intelligent camera. Summary of the invention

[0003] The purpose of the present invention is to provide a method for detecting the coal flow and amount of a scraper conveyor based on a composite intelligent camera.

[0004] In order to solve the problems raised in the above background technology, the present invention provides the following technical solution: a method for detecting coal flow and coal volume of a scraper conveyor based on a composite intelligent camera, comprising the following steps: Step 1: Equipment installation and calibration: Install a composite intelligent camera, fill light, and light intensity sensor in the detection area, and calibrate the ratio coefficient between pixels and actual size; Step 2: Image acquisition and processing: The coal flow image data is collected in real time by a composite intelligent camera, the collected image data is grayed, and a grayscale histogram is constructed; Step 3: Extract coal flow features. According to the grayscale differences between coal, scraper and belt, set the threshold for segmentation. According to the proportional relationship between pixels and actual size, calculate the cross-sectional area and volume of the coal flow. Step 4: Calculate the coal quantity and output the result. According to the volume of the coal flow and the density of the coal, use the formula to calculate the coal quantity and send the calculation result to the display screen of the detection system. Step 5: Verify the results: use the weighing method to obtain the amount of coal transported within a period of time, compare it with the amount of coal obtained by calculation, and output the verification results; Step six: Algorithm optimization: optimize the coal quantity calculation algorithm based on the verification results.

[0005] As a further solution of the present invention: in the step one, the installation position of the composite intelligent camera and the fill light is the upper bridge of the scraper conveyor, and the installation position of the light intensity sensor is the monitoring area of ​​the composite intelligent camera. If the light intensity in the detection area is not within the threshold range of the light intensity sensor, turn on the fill light, and dynamically adjust the light intensity of the fill light according to the feedback from the light intensity sensor. The method of calibrating the proportional coefficient of pixels to actual size is to place a square calibration plate with a side length of 1 meter on the conveyor belt, measure the number of pixels corresponding to its side length in the image, and calculate the proportional relationship between the pixels and the actual size.

[0006] As a further solution of the present invention: in the step 2, the resolution of the image data collected by the composite intelligent camera is set to 1080p, the frame rate is set to 30fps, the exposure time is set to 1 / 100s, the image is compressed into JPEG format, the image data is grayed out by using a weighted average method to calculate the gray value of each pixel, and the grayscale histogram is constructed by using the calcHist function in the image processing library to calculate the histogram of the image.

[0007] As a further solution of the present invention: in step 3, the calculation formula of the cross-sectional area of ​​the coal flow is as follows:

[0008] Among them, S is the cross-sectional area of ​​the coal flow, L is the actual length of the coal flow, and W is the actual width of the coal flow. is the number of pixels corresponding to the length of the coal flow area in the image, is the number of pixels corresponding to the width of the coal flow area in the image, k is the ratio coefficient between pixels and actual size, and the volume calculation formula of the coal flow is as follows:

[0009] Among them, V represents the volume of coal flow, v represents the running speed of scraper conveyor, f represents the image acquisition frame rate, S represents the cross-sectional area of ​​coal flow, n represents the number of frames, and H represents the depth of coal flow.

[0010] As a further solution of the present invention: in step 4, the calculation formula of the coal amount is as follows: in, Indicates the amount of coal, Indicates that the unit volume is 1m 3 , represents the density of coal, It indicates the coal quantity per unit volume error. The value of M is checked every 10 minutes. If the value of M is not within the set range, the equipment abnormality alarm is triggered.

[0011] As a further solution of the present invention: In step five, the specific method of result verification is to install a weighing device at the end of the scraper conveyor, measure the total weight of the coal within 5 minutes every 8 hours, compare the coal quantity obtained by weighing with the coal quantity obtained by calculation, and output the verification result according to the error size.

[0012] As a further solution of the present invention: the result verification also includes coal quality testing, specifically, every other week, samples are randomly taken from the coal flow of the scraper conveyor for coal quality testing, and the moisture content and ash content of the coal are tested. If the error of the moisture content and ash content compared with the previous test results exceeds 5%, the density of the coal is re-evaluated.

[0013] As a further solution of the present invention: the coal quality detection also includes coal quality assessment. The specific method of coal quality assessment is to use a composite intelligent camera to analyze the moisture content, ash content, volatile matter, fixed carbon content, calorific value and sulfur content parameters of the sample coal, and compare the analysis results with the preset coal quality standards. If all parameters of the analysis results are within the preset coal quality standards, it is assessed as high-quality. If any one or more measured values ​​of the coal sample parameters deviate from the preset standards by more than 5%, it is assessed as poor quality coal.

[0014] As a further solution of the present invention: in step five, the type of verification result is: if the error value is less than 5%, the algorithm is judged to be accurate and the algorithm is not modified; if the error value is greater than or equal to 5%, the algorithm is judged to be inaccurate and the algorithm is modified; if the error value is greater than 20%, the equipment is judged to be faulty and the equipment is repaired and retested.

[0015] As a further solution of the present invention: In step 6, the specific method of algorithm optimization is as follows: if the verification result shows that the actual amount of coal is greater than the calculated amount of coal, the depth and cross-sectional area of ​​the coal flow are checked, and according to the check result, the values ​​of S and H are adjusted, and the verification is repeated; if the verification result shows that the actual amount of coal is less than the calculated amount of coal, the value of S and H is adjusted. The value of is adjusted in such a way that when the error value increases by 10%, Lower the value by 10% and verify again.

[0016] As a further solution of the present invention: in the algorithm optimization stage of step six, an intelligent early warning module is provided, and the intelligent early warning module is used to compare the coal quantity calculation result after algorithm optimization with the preset normal threshold value of coal quantity. When the coal quantity calculation result exceeds the preset normal threshold range, the intelligent early warning module will be automatically activated and send a warning signal to the designated maintenance personnel through the wireless network.

[0017] By adopting the above technical solution, compared with the prior art, the beneficial effects of the present invention are: 1. The present invention realizes comprehensive, real-time and intelligent monitoring of the coal flow and quantity of the scraper conveyor by integrating a composite intelligent camera, a fill light, a light intensity sensor and a coal quality detection method. Through coal quality detection every other week, changes in coal quality can be discovered in time, and the density of coal can be re-evaluated according to these changes, thereby ensuring the accuracy of coal quantity calculation. This comprehensive intelligent monitoring and coal quality adaptability optimization strategy not only improves the accuracy of coal quantity detection, but also enhances the adaptability and reliability of the system, providing more accurate data support for coal mine production; 2. The present invention can monitor and adjust the lighting conditions in real time by installing a light intensity sensor in the detection area and linking it with a fill light, ensuring that the composite intelligent camera collects images under the best lighting environment. This dynamic regulation can improve the quality of image collection, thereby improving the accuracy of coal flow feature extraction and ensuring that the calculation of coal flow and coal quantity is more reliable; 3. The present invention includes weighing method verification and coal quality detection steps, which are used to discover errors in coal quantity calculation and optimize the algorithm accordingly. In particular, when the verification result shows that there is a significant difference between the actual coal quantity and the calculated coal quantity, the system will trigger corresponding alarms or adjustment measures, such as adjusting parameters such as the depth of the coal flow, the cross-sectional area or the density of the coal, to ensure the accuracy of the coal quantity calculation. This closed-loop feedback mechanism improves the accuracy and stability of coal quantity detection and enhances the self-repair and optimization capabilities of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 Schematic diagram of the steps of the coal quantity detection method in an embodiment of the present invention. DETAILED DESCRIPTION

[0019] 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 only 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] Embodiment 1:

[0021] Please refer to the attached Figure 1 The present invention provides a method for detecting coal flow and coal volume of a scraper conveyor based on a composite intelligent camera, comprising the following steps: Step 1: Equipment installation and calibration: Install a composite intelligent camera, fill light, and light intensity sensor in the detection area, and calibrate the ratio coefficient between pixels and actual size; Step 2: Image acquisition and processing: The coal flow image data is collected in real time by a composite intelligent camera, the collected image data is grayed, and a grayscale histogram is constructed; Step 3: Extract coal flow features. According to the grayscale differences between coal, scraper and belt, set the threshold for segmentation. According to the proportional relationship between pixels and actual size, calculate the cross-sectional area and volume of the coal flow. Step 4: Calculate the coal quantity and output the result. According to the volume of the coal flow and the density of the coal, use the formula to calculate the coal quantity and send the calculation result to the display screen of the detection system. Step 5: Verify the results: use the weighing method to obtain the amount of coal transported within a period of time, compare it with the amount of coal obtained by calculation, and output the verification results; Step six: Algorithm optimization: optimize the coal quantity calculation algorithm based on the verification results.

[0022] Specific work flow: In a coal quantity detection system of a scraper conveyor in a coal mine, the detection method of the present invention is adopted. During the operation of one month, coal quality detection is carried out once a week. In the third week of detection, it is found that the water content of the coal has increased from 8% to 12%, and the ash content has increased from 15% to 20%. According to the coal quality and density relationship model provided by the coal quality detection laboratory, when the water content and ash content change, the density of the coal is adjusted from the original 1350kg / m³ to 1300kg / m³. During this week, the composite intelligent camera is used to collect image data, and the average volume of the coal flow is calculated to be 5m³. The coal quantity calculated according to the density before adjustment is 5×1350=6750kg, and the coal quantity calculated according to the adjusted density is 5×1300=6500kg. The subsequent verification by weighing method is within the allowable error range (for example, the error is less than 3%), which proves that the coal quantity calculated after adjusting the density according to the coal quality change is more accurate, thereby reflecting the adaptability of the system to coal quality changes and the improvement of the coal quantity calculation accuracy.

[0023] Furthermore, by integrating composite intelligent cameras, fill lights, light intensity sensors and coal quality detection methods, comprehensive, real-time and intelligent monitoring of the coal flow and coal quantity of scraper conveyors is achieved. Through coal quality testing every week, changes in coal quality can be discovered in a timely manner, and the coal density can be re-evaluated based on these changes, thereby ensuring the accuracy of coal quantity calculations. This comprehensive intelligent monitoring and coal quality adaptability optimization strategy not only improves the accuracy of coal quantity detection, but also enhances the adaptability and reliability of the system, providing more accurate data support for coal mine production.

[0024] Embodiment 2:

[0025] Based on the first embodiment, in step one, the installation positions of the composite intelligent camera and the fill light are the upper bridge of the scraper conveyor, and the installation position of the light intensity sensor is the monitoring area of ​​the composite intelligent camera. If the light intensity in the detection area is not within the threshold range of the light intensity sensor, the fill light is turned on, and the light intensity of the fill light is dynamically adjusted according to the feedback of the light intensity sensor. The method of calibrating the proportional coefficient of pixels to actual size is to place a square calibration plate with a side length of 1 meter on the conveyor belt, measure the number of pixels corresponding to its side length in the image, and calculate the proportional relationship between the pixels and the actual size; In step 2, the resolution of the image data collected by the composite intelligent camera is set to 1080p, the frame rate is set to 30fps, the exposure time is set to 1 / 100s, the image is compressed into JPEG format, the image data is grayed out by using the weighted average method to calculate the gray value of each pixel, and the gray histogram is constructed by using the calcHist function in the image processing library to calculate the histogram of the image; In step 3, the cross-sectional area of ​​the coal flow is calculated as follows:

[0026] Among them, S is the cross-sectional area of ​​the coal flow, L is the actual length of the coal flow, and W is the actual width of the coal flow. is the number of pixels corresponding to the length of the coal flow area in the image, is the number of pixels corresponding to the width of the coal flow area in the image, k is the ratio coefficient between pixels and actual size, and the volume calculation formula of the coal flow is as follows:

[0027] Wherein, V represents the volume of coal flow, v represents the running speed of the scraper conveyor, f represents the image acquisition frame rate, S represents the cross-sectional area of ​​the coal flow, n represents the number of frames, and H represents the depth of the coal flow; In step 4, the calculation formula for coal quantity is as follows:

[0028] in, Indicates the amount of coal, Indicates that the unit volume is 1m 3 , represents the density of coal, It indicates the coal quantity per unit volume error. The value of M is checked every 10 minutes. If the value of M is not within the set range, the equipment abnormality alarm is triggered.

[0029] Specific working process: The device of the present invention is installed at the scraper conveyor of another coal mine. At different times of the day, especially in the early morning and evening when the light is weak and at noon when the light is too strong, the light intensity sensor plays a role. For example, in the early morning, the light intensity is only 200 lux, which is lower than the set threshold (the set threshold is 300 lux). The fill light is automatically turned on, and the light intensity is gradually adjusted to a suitable level according to the sensor feedback, so that the clarity and contrast of the image collected by the composite intelligent camera can reach a better state. Under this image collection with optimized lighting conditions, the image is collected. The accuracy of coal flow area segmentation has increased from 80% before lighting control to 90%. Taking the coal flow detection in a certain period of time as an example, the cross-sectional area of ​​the coal flow is calculated to be 2m² and the length is 10m (calculated by parameters such as speed and frame rate). If the segmentation result is based on the previous segmentation result when the lighting is not optimized, the cross-sectional area calculation error may reach 0.3m², resulting in a coal quantity calculation error of about 15% (assuming the density is 1400kg / m³). After optimizing the lighting, the coal quantity calculation error is controlled within 5%, which strongly proves the role of lighting control in improving the reliability of coal quantity calculation.

[0030] Furthermore, by installing a light intensity sensor in the detection area and linking it with the fill light, the lighting conditions can be monitored and adjusted in real time to ensure that the composite intelligent camera acquires images under the optimal lighting environment. This dynamic control can improve the quality of image acquisition, thereby improving the accuracy of coal flow feature extraction and ensuring that the calculation of coal flow and coal quantity is more reliable.

[0031] Embodiment three:

[0032] Based on the second embodiment, in step 5, the specific method of result verification is to install a weighing device at the end of the scraper conveyor, measure the total weight of the coal within 5 minutes every 8 hours, compare the coal quantity obtained by weighing method with the coal quantity obtained by calculation, and output the verification result according to the error size; The result verification also includes coal quality testing. The specific method is to randomly select samples from the coal flow of the scraper conveyor every other week to test the moisture content and ash content of the coal. If the error of moisture content and ash content compared with the previous test results exceeds 5%, the density of the coal is re-evaluated; Coal quality testing also includes coal quality assessment. The specific method of coal quality assessment is to use a composite intelligent camera to analyze the moisture content, ash content, volatile matter, fixed carbon content, calorific value and sulfur content parameters of the sample coal, and compare the analysis results with the preset coal quality standards. If all parameters of the analysis results are within the preset coal quality standards, it is assessed as high-quality. If any one or more measured values ​​of the coal sample parameters deviate from the preset standards by more than 5%, it is assessed as low-quality coal. In step 5, the type of verification result is: if the error value is less than 5%, the algorithm is judged to be accurate and the algorithm is not modified; if the error value is greater than or equal to 5%, the algorithm is judged to be inaccurate and the algorithm is modified; if the error value is greater than 20%, the device is judged to be faulty and the device is repaired and retested; In step 6, the specific method of algorithm optimization is as follows: if the verification result shows that the actual coal volume is greater than the calculated coal volume, check the depth and cross-sectional area of ​​the coal flow, adjust the values ​​of S and H according to the verification result, and verify again; if the verification result shows that the actual coal volume is less than the calculated coal volume, adjust The value of is adjusted in such a way that when the error value increases by 10%, The value of is lowered by 10% and verified again; In the algorithm optimization stage of step six, an intelligent early warning module is set up. The intelligent early warning module is used to compare the coal quantity calculation result after algorithm optimization with the preset normal threshold value of coal quantity. When the coal quantity calculation result exceeds the preset normal threshold range, the intelligent early warning module will be automatically activated and send a warning signal to the designated maintenance personnel through the wireless network.

[0033] Specific workflow: In the application of coal quantity detection of a scraper conveyor in a large coal mine, the weighing method verification is performed every 6 hours. During one verification process, it was found that the error between the calculated coal quantity and the actual coal quantity obtained by the weighing method reached 15% (greater than 5%). The system immediately started the algorithm optimization process. First, the depth and cross-sectional area parameters of the coal flow were checked. Through further image analysis and on-site measurement, it was found that the actual coal flow depth was 0.2m shallower than the value used in the previous calculation due to the change in the shape of the coal flow accumulation on the scraper conveyor. Therefore, the coal flow depth parameter was adjusted according to the actual situation and the coal quantity was recalculated. When verified again, the error was reduced to within 3%. In addition, in another verification, it was found that the error reached 25% (greater than 20%). The system judged that there might be equipment failure. After inspection, it was found that the lens of the composite intelligent camera was dusty and affected the image acquisition quality. After cleaning the lens and re-testing, the coal quantity calculation returned to normal accuracy, which reflects the effectiveness of the closed-loop feedback mechanism in ensuring the accuracy and stability of coal quantity detection and the self-repair and optimization capabilities of the system.

[0034] Furthermore, it includes weighing method verification and coal quality testing steps to discover errors in coal quantity calculation and optimize the algorithm accordingly. In particular, when the verification results show that there is a significant difference between the actual coal quantity and the calculated coal quantity, the system will trigger corresponding alarms or adjustment measures, such as adjusting parameters such as the depth of the coal flow, the cross-sectional area or the density of the coal, to ensure the accuracy of the coal quantity calculation. This closed-loop feedback mechanism improves the accuracy and stability of coal quantity detection and enhances the system's self-repair and optimization capabilities.

[0035] The above shows and describes the basic principles, main features and advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A method for detecting coal flow of a scraper conveyor based on a composite intelligent camera, characterized in that: The following steps are involved: Step 1: Equipment installation and calibration: Install a composite intelligent camera, fill light, and light intensity sensor in the detection area, and calibrate the ratio coefficient between pixels and actual size; Step 2: Image acquisition and processing: The coal flow image data is collected in real time by a composite intelligent camera, the collected image data is grayed, and a grayscale histogram is constructed; Step 3: Extract coal flow features. According to the grayscale differences between coal, scraper and belt, set the threshold for segmentation. According to the proportional relationship between pixels and actual size, calculate the cross-sectional area and volume of the coal flow. Step 4: Calculate the coal quantity and output the result. According to the volume of the coal flow and the density of the coal, use the formula to calculate the coal quantity and send the calculation result to the display screen of the detection system. Step 5: Verify the results: use the weighing method to obtain the amount of coal transported within a period of time, compare it with the amount of coal obtained by calculation, and output the verification results; Step six: Algorithm optimization: optimize the coal quantity calculation algorithm based on the verification results.

2. The method for detecting coal flow and amount of a scraper conveyor based on a composite intelligent camera according to claim 1 is characterized in that: In the step one, the installation positions of the composite intelligent camera and the fill light are the upper bridge of the scraper conveyor, and the installation position of the light intensity sensor is the monitoring area of ​​the composite intelligent camera. If the light intensity in the detection area is not within the threshold range of the light intensity sensor, turn on the fill light, and dynamically adjust the light intensity of the fill light according to the feedback of the light intensity sensor. The method of calibrating the proportional coefficient of pixels to actual size is to place a square calibration plate with a side length of 1 meter on the conveyor belt, measure the number of pixels corresponding to its side length in the image, and calculate the proportional relationship between pixels and actual size.

3. The method for detecting coal flow and amount of a scraper conveyor based on a composite intelligent camera according to claim 1, characterized in that: In the step 2, the resolution of the image data collected by the composite intelligent camera is set to 1080p, the frame rate is set to 30fps, the exposure time is set to 1 / 100s, the image is compressed into JPEG format, the image data is grayed out by using the weighted average method to calculate the gray value of each pixel, and the grayscale histogram is constructed by using the calcHist function in the image processing library to calculate the histogram of the image.

4. The method for detecting coal flow and amount of a scraper conveyor based on a composite intelligent camera according to claim 1, characterized in that: In step 3, the calculation formula for the cross-sectional area of ​​the coal flow is as follows: ； Among them, S is the cross-sectional area of ​​the coal flow, L is the actual length of the coal flow, and W is the actual width of the coal flow. is the number of pixels corresponding to the length of the coal flow area in the image, is the number of pixels corresponding to the width of the coal flow area in the image, k is the ratio coefficient between pixels and actual size, and the volume calculation formula of the coal flow is as follows: ； Among them, V represents the volume of coal flow, v represents the running speed of scraper conveyor, f represents the image acquisition frame rate, S represents the cross-sectional area of ​​coal flow, n represents the number of frames, and H represents the depth of coal flow.

5. The method for detecting coal flow and amount of a scraper conveyor based on a composite intelligent camera according to claim 4 is characterized in that: In step 4, the calculation formula of the coal quantity is as follows: ； in, Indicates the amount of coal, Indicates that the unit volume is 1m 3 , represents the density of coal, It indicates the coal quantity per unit volume error. The value of M is checked every 10 minutes. If the value of M is not within the set range, the equipment abnormality alarm is triggered.

6. The method for detecting coal flow and amount of a scraper conveyor based on a composite intelligent camera according to claim 5 is characterized in that: In step five, the specific method of result verification is to install a weighing device at the end of the scraper conveyor, measure the total weight of the coal within 5 minutes every 8 hours, compare the coal quantity obtained by weighing with the coal quantity obtained by calculation, and output the verification result according to the error size.

7. The method for detecting coal flow and amount of a scraper conveyor based on a composite intelligent camera according to claim 6, characterized in that: The result verification also includes coal quality testing, which is carried out by randomly taking samples from the coal flow of the scraper conveyor every week to test the moisture content and ash content of the coal. If the error of moisture content and ash content compared with the previous test results exceeds 5%, the density of the coal is re-evaluated.

8. The method for detecting coal flow and amount of a scraper conveyor based on a composite intelligent camera according to claim 7, characterized in that: The coal quality inspection also includes coal quality assessment. The specific method of coal quality assessment is to use a composite intelligent camera to analyze the moisture content, ash content, volatile matter, fixed carbon content, calorific value and sulfur content parameters of the sample coal, and compare the analysis results with the preset coal quality standards. If all parameters of the analysis results are within the preset coal quality standards, it is assessed as high-quality. If any one or more measured values ​​of the coal sample parameters deviate from the preset standards by more than 5%, it is assessed as poor quality coal.

9. The method for detecting coal flow and amount of a scraper conveyor based on a composite intelligent camera according to claim 6, characterized in that: In step five, the type of verification result is: if the error value is less than 5%, the algorithm is judged to be accurate and the algorithm is not modified; if the error value is greater than or equal to 5%, the algorithm is judged to be inaccurate and the algorithm is modified; if the error value is greater than 20%, the device is judged to be faulty and the device is repaired and retested.

10. The method for detecting coal flow of a scraper conveyor based on a composite intelligent camera according to claim 8, characterized in that: In step 6, the specific method of algorithm optimization is as follows: if the verification result shows that the actual amount of coal is greater than the calculated amount of coal, the depth and cross-sectional area of ​​the coal flow are checked, and the values ​​of S and H are adjusted according to the verification result, and the verification is repeated; if the verification result shows that the actual amount of coal is less than the calculated amount of coal, the value of S and H is adjusted. The value of is adjusted in such a way that when the error value increases by 10%, Lower the value by 10% and verify again.

11. The method for detecting coal flow and amount of a scraper conveyor based on a composite intelligent camera according to claim 8, characterized in that: In the algorithm optimization stage of step six, an intelligent early warning module is provided. The intelligent early warning module is used to compare the coal quantity calculation result after algorithm optimization with the preset normal threshold value of coal quantity. When the coal quantity calculation result exceeds the preset normal threshold range, the intelligent early warning module will be automatically activated and send a warning signal to the designated maintenance personnel through the wireless network.

Images