A Fault Early Warning Method and System for Coal Conveyor Belt Based on Computer Vision Algorithm

Abstract

The present invention discloses a method and system for early warning of faults in a coal conveying belt based on computer vision algorithms, which relates to the technical field of early warning of faults in a coal conveying belt, and includes: collecting the gray-scale features between the belt and the target device through a sensor module; judging the edge features and position of the belt according to the gray-scale features; establishing a virtual deviation amount feature table to judge the real-time state of the belt; and judging the deviation type according to the real-time state of the belt to perform fault handling. The method for early warning of faults in a coal conveying belt based on computer vision algorithms provided by the present invention accurately identifies the features and position of the belt edge, improves the accuracy and timeliness of diagnosis, automatically performs corresponding fault handling by establishing a virtual deviation amount feature table, reduces manual intervention, improves the efficiency and quality of fault handling, thereby reducing the downtime of the belt and enhancing its operating efficiency and safety.

Description

Technical Field

[0001] The present invention relates to the technical field of coal conveyor belt fault warning, and particularly to a method and system for coal conveyor belt fault warning based on computer vision algorithms. Background Art

[0002] Coal conveyor belts are devices widely used in places such as coal mines, power plants, and ports for transporting coal. However, due to their long-term high-intensity working conditions, faults such as deviation, wear, and tear often occur, which not only affect the normal transportation of coal but may also cause serious damage to the equipment and even pose a threat to the safety of workers. Traditional methods for warning coal conveyor belt faults mainly rely on manual inspections, which have problems such as low efficiency, high misjudgment rates, and inability to provide real-time warnings.

[0003] In recent years, the development of computer vision technology has provided new possibilities for warning coal conveyor belt faults. This technology can monitor the operating state of coal conveyor belts in real time through image analysis and deep learning algorithms and give early warnings of possible faults. However, since computer vision algorithms need to process a large amount of images and depth information and need to accurately analyze and judge this information, there are still many technical problems in their application to warning coal conveyor belt faults.

[0004] Existing computer vision-based methods for warning coal conveyor belt faults can mostly handle only a single type of fault. For example, they can only handle the deviation or wear of the belt and cannot handle multiple faults simultaneously. Moreover, these methods often give passive warnings of belt faults, that is, they only deal with faults after they occur and cannot prevent faults.

[0005] Therefore, how to improve the accuracy and real-time performance of computer vision algorithm-based methods for warning coal conveyor belt faults and how to achieve simultaneous handling and prevention of multiple faults have become the main problems in the current technological development. Summary of the Invention

[0006] The purpose of this part is to outline some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Simplifications or omissions may be made in this part, as well as in the abstract and title of the present application, to avoid obscuring the purpose of this part, the abstract, and the title, but such simplifications or omissions shall not be used to limit the scope of the present invention.

[0007] In view of the above existing problems, the present invention is proposed.

[0008] Therefore, the technical problems solved by the present invention are: the existing methods for warning coal conveyor belt faults have low accuracy and cannot effectively predict and handle the deviation problem of the belt in real time, and how to improve the accuracy and timeliness of fault warning, reduce the fault downtime of coal conveyor belts, and improve production efficiency.

[0009] To solve the above technical problems, the present invention provides the following technical solution: A method for early warning of faults in a coal conveying belt based on computer vision algorithms, including:

[0010] Collect the gray-scale features between the belt and the target device through a sensor module;

[0011] Judge the edge features and position of the belt according to the gray-scale features;

[0012] Establish a virtual deviation amount feature table to judge the real-time state of the belt;

[0013] Judge the deviation type according to the real-time state of the belt and perform fault handling.

[0014] As a preferred solution of the method for early warning of faults in a coal conveying belt based on computer vision algorithms according to the present invention, wherein: The gray-scale features between the belt and the target device include capturing the surface details of the belt through a high-resolution image sensor to generate a 2D image, and the depth sensor measures the distance of the object to form a 3D model of the object, and the data is combined to form gray-scale features including the shape, texture, color and distance of the belt material.

[0015] As a preferred solution of the method for early warning of faults in a coal conveying belt based on computer vision algorithms according to the present invention, wherein: The judgment of the edge features and position of the belt includes using computer vision algorithms to activate a multi-modal sensor array, collecting and analyzing the 2D image and 3D model of the belt, denoising, filtering, and adjusting the brightness of the collected data, using the semantic segmentation technology of deep learning to process the pre-processed RGB image, identifying the edge of the belt, combining the depth information obtained by lidar, obtaining the actual distance between the edge and the target device, using the method of computational geometry, according to the 2D coordinates and depth information of the belt edge, calculating the 3D coordinates of the edge in the real world, and according to the 3D coordinates of the belt edge and the 3D coordinates of the target device, using a regression model based on machine learning to calculate the actual distance and determine the actual position of the belt.

[0016] As a preferred solution of the method for early warning of faults in a coal conveying belt based on computer vision algorithms according to the present invention, wherein: The virtual deviation amount feature table includes calculating the deviation amount of the belt according to the actual position of the belt and the preset normal position, and collecting the deviation amount a, deviation speed, deviation acceleration of the belt, as well as the condition and distribution of material accumulation, automatically calculating the instantaneous volume of the belt material flow, automatically judging whether the feeding point is centered, and recording the collected information in a dynamically updated virtual deviation amount feature table.

[0017] As a preferred solution of the coal conveying belt fault warning method based on computer vision algorithm described in the present invention, wherein: the deviation types include detecting the deviation speed when the deviation amount a > 10 mm. If the deviation speed exceeds 5 mm / s and the deviation acceleration exceeds 2 mm / s 2 when, it is determined that the fault is of level A1. When the deviation amount 5 mm ≤ a ≤ 10 mm, if both the deviation speed and the deviation acceleration are in an upward trend, it is determined that the fault is of level A2. When the deviation amount 5 mm ≤ a ≤ 10 mm, if the deviation speed ≤ 5 mm / s and the deviation acceleration ≤ 2 mm / s 2 when, it is determined that the fault is of level A3;

[0018] If it is determined that the fault is of level A1, immediately stop the belt operation, automatically calibrate the fault area, guide the operator to repair it, and monitor the repair progress in real time during the repair process;

[0019] If it is determined that the fault is of level A2, according to the real-time information of the virtual deviation amount characteristic table, judge the deviation state of the belt, automatically adjust the running speed and the position of the material falling point of the belt, automatically adjust the material accumulation and distribution, and try to solve the deviation problem. If the automatic adjustment cannot stop the simultaneous upward trend of the deviation speed and the deviation acceleration, it will be transferred to the processing of level A1 fault;

[0020] If it is determined that the fault is of level A3, continuously monitor the running state of the belt, adjust the material accumulation and distribution in real time, prevent the deviation problem caused by uneven material accumulation and distribution. If the deviation amount, deviation speed or deviation acceleration shows an upward trend in future detections, if the deviation amount, deviation speed or deviation acceleration shows an upward trend in future detections, it will be transferred to the processing of level A2 fault;

[0021] The upward trend includes showing an upward result in any one of the most recent 5 consecutive detections, and it is determined to be in an upward trend.

[0022] As a preferred solution of the coal conveying belt fault warning method based on computer vision algorithm described in the present invention, wherein: the judgment of the deviation state of the belt includes, according to the real-time information of the virtual deviation amount characteristic table, by calculating the deviation amount, deviation speed, deviation acceleration, and the condition and distribution of the material accumulation.

[0023] As a preferred embodiment of the coal conveying belt fault warning method based on computer vision algorithm of the present invention, the method for judging the belt deviation state further includes: if it is in the no-load deviation state, the position of the material falling point is accurately measured and controlled by the attitude device before the belt feeding. If the position of the material falling point deviates from the preset range, the running attitude of the belt is adjusted to correct the position of the material falling point. If the adjusted position still deviates from the preset range, the material flow rate monitor is used to monitor and adjust the material flow rate in real time. If the flow rate exceeds the threshold, the position of the material falling point and the running attitude of the belt are adjusted. If the position of the material falling point and the material flow rate still cannot be restored to the preset range, the alarm mechanism is activated to pause the belt operation for manual inspection and processing;

[0024] If it is in the heavy-load deviation state, the material accumulation monitor is used to monitor the material accumulation situation in real time. If the accumulation situation exceeds the preset range, the load of the belt is adjusted. If the adjusted load still exceeds the threshold, the material distribution monitor is used to monitor the material distribution on the belt in real time. If the distribution is uneven, the running speed of the belt is automatically adjusted by the belt speed control system according to the material accumulation and distribution conditions. If the material accumulation and distribution conditions still cannot be restored to the preset range, the system will activate the alarm mechanism and pause the belt operation for manual inspection and processing.

[0025] Another object of the present invention is to provide a system for the coal conveying belt fault warning method based on computer vision algorithm, which can collect and process the real-time image and depth information of the belt, automatically calculate and monitor the deviation amount, deviation speed and deviation acceleration of the belt, accurately judge the deviation type and implement corresponding treatment measures, and solve the problem that the traditional method cannot predict and process the belt deviation problem in real time and accurately.

[0026] A coal conveying belt fault warning system based on computer vision algorithm, characterized by including a sensor acquisition module, an image processing module, a state judgment module, and a fault processing module;

[0027] As a preferred embodiment of the coal conveying belt fault warning system based on computer vision algorithm of the present invention, the sensor acquisition module is used to collect the real-time image and depth information of the coal conveying belt, generate a 2D image and a 3D model of the belt, and obtain the gray-scale features of the object;

[0028] As a preferred embodiment of the coal conveying belt fault warning system based on computer vision algorithm of the present invention, the image processing module is used to perform preprocessing operations on the image and depth information obtained by the sensor acquisition module, use the semantic segmentation technology of deep learning to identify the edge of the belt, calculate the 3D coordinates of the edge in the real world, and calculate the actual position of the belt;

[0029] As a preferred solution of the coal conveying belt fault warning system based on computer vision algorithm described in the present invention, wherein: the state judgment module is used to calculate the deviation amount, deviation speed, and deviation acceleration parameters of the belt according to the data obtained by the image processing module, establish and maintain a virtual deviation amount feature table, judge the deviation type of the belt according to specific conditions, and make corresponding fault handling decisions;

[0030] As a preferred solution of the coal conveying belt fault warning system based on computer vision algorithm described in the present invention, wherein: the fault handling module is used to implement corresponding handling measures according to the judgment result of the state judgment module, automatically adjust the running speed and the position of the material dropping point of the belt, start the alarm mechanism and pause the operation of the belt.

[0031] A computer device includes a memory and a processor. The memory stores a computer program. It is characterized in that when the processor executes the computer program, the steps of the above-mentioned method are implemented.

[0032] A computer-readable storage medium stores a computer program thereon. It is characterized in that when the computer program is executed by a processor, the steps of the above-mentioned method are implemented.

[0033] The beneficial effects of the present invention: The coal conveying belt fault warning method based on computer vision algorithm provided by the present invention accurately identifies the features and positions of the belt edge, improves the accuracy and timeliness of diagnosis. By establishing a virtual deviation amount feature table, corresponding fault handling is automatically performed, reducing manual intervention, improving the efficiency and quality of fault handling, thereby reducing the downtime of the belt and enhancing its operating efficiency and safety. Description of the Drawings

[0034] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts. Among them:

[0035] Figure 1 It is the overall flowchart of a coal conveying belt fault warning method based on computer vision algorithm provided by an embodiment of the present invention;

[0036] Figure 2 It is the overall structure diagram of a coal conveying belt fault warning system based on computer vision algorithm provided by the second embodiment of the present invention;

[0037] Figure 3Comparison chart of verification accuracy rates under different deviation amounts for a coal conveying belt fault warning method and system based on computer vision algorithms provided in the fourth embodiment of the present invention;

[0038] Figure 4 Comparison chart of verification accuracy rates under different deviation speeds for a coal conveying belt fault warning method and system based on computer vision algorithms provided in the fourth embodiment of the present invention. Detailed implementation manners

[0039] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following provides a detailed description of the specific implementation manners of the present invention in conjunction with the accompanying drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of them. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present invention without creative efforts should fall within the protection scope of the present invention.

[0040] In the following description, many specific details are set forth to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar generalizations without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0041] Secondly, the so-called "one embodiment" or "embodiment" herein refers to specific features, structures, or characteristics that can be included in at least one implementation manner of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment that excludes other embodiments.

[0042] The present invention is described in detail in conjunction with schematic diagrams. When detailing the embodiments of the present invention, for ease of explanation, the cross-sectional views showing the device structure will be enlarged locally out of the general proportion, and the schematic diagrams are only examples and should not limit the protection scope of the present invention here. In addition, in actual production, three-dimensional spatial dimensions including length, width, and depth should be included.

[0043] At the same time, in the description of the present invention, it should be noted that the orientation or positional relationships indicated by terms such as "upper, lower, inner, and outer" are based on the orientation or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to the present invention. In addition, the terms "first, second, or third" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance.

[0044] Unless otherwise clearly specified and defined in the present invention, the terms "installation, connection, and coupling" shall be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may also be a mechanical connection, an electrical connection, or a direct connection, and may also be indirectly connected through an intermediate medium, or it may be the communication inside two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0045] Embodiment 1

[0046] Referring to Figure 1 , an embodiment of the present invention provides a method for early warning of faults in a coal conveying belt based on computer vision algorithms, including:

[0047] Collect the grayscale features between the belt and the target device through the sensor module.

[0048] The grayscale features between the belt and the target device include capturing the surface details of the belt through a high-resolution image sensor to generate a 2D image, and the depth sensor measures the distance of the object to form a 3D model of the object. The data is combined to form grayscale features including the shape, texture, color, and distance of the belt material.

[0049] Use a high-resolution image sensor and a depth sensor for feature collection, and use an IP68 protection level sealed housing to protect the device to prevent dust and humidity from affecting the device. To cope with light changes, use a high dynamic range (HDR) camera with automatic gain control and automatic exposure control.

[0050] Judge the edge features and position of the belt according to the grayscale features.

[0051] Judging the edge features and position of the belt includes using computer vision algorithms to activate a multi-modal sensor array, collecting and analyzing the 2D image and 3D model of the belt, denoising, filtering, and adjusting the brightness of the collected data, using semantic segmentation technology of deep learning to process the preprocessed RGB image to identify the edge of the belt, combining the depth information obtained by lidar to obtain the actual distance between the edge and the target device, using computational geometry methods to calculate the 3D coordinates of the edge in the real world according to the 2D coordinates and depth information of the belt edge, and using a regression model based on machine learning to calculate the actual distance according to the 3D coordinates of the belt edge and the 3D coordinates of the target device to determine the actual position of the belt.

[0052] Establish a virtual deviation amount feature table to judge the real-time state of the belt.

[0053] The virtual deviation characteristic table includes calculating the deviation of the belt according to the actual position and the preset normal position of the belt, collecting the deviation amount a of the belt, the deviation speed, the deviation acceleration, and the condition and distribution of material accumulation, automatically calculating the instantaneous volume of the belt material flow, automatically judging whether the feeding point is centered, and recording the collected information in the dynamically updated virtual deviation characteristic table.

[0054] Judge the deviation type according to the real-time state of the belt and perform fault handling.

[0055] The deviation types include detecting the deviation speed when the deviation amount a > 10 mm. If the deviation speed exceeds 5 mm / s and the deviation acceleration exceeds 2 mm / s 2 at this time, judge the fault as A1 level. When the deviation amount 5 mm ≤ a ≤ 10 mm, if the deviation speed and the deviation acceleration are both in an upward trend, judge the fault as A 2 level. When the deviation amount 5 mm ≤ a ≤ 10 mm, if the deviation speed ≤ 5 mm / s and the deviation acceleration ≤ 2 mm / s 2 at this time, judge the fault as A3 level.

[0056] If it is judged as an A1-level fault, immediately stop the belt operation, automatically calibrate the fault area, guide the operator to repair it, and during the repair process, monitor the repair progress in real time.

[0057] If it is judged as an A2-level fault, judge the belt deviation state according to the real-time information of the virtual deviation characteristic table, automatically adjust the running speed and the position of the feeding point of the belt, automatically adjust the material accumulation and distribution, and try to solve the deviation problem. If the automatic adjustment cannot stop the deviation speed and the deviation acceleration from both being in an upward trend, it will transfer to the A1-level fault handling.

[0058] If it is judged as an A3-level fault, continuously monitor the running state of the belt, adjust the material accumulation and distribution in real time, prevent the deviation problem caused by uneven material accumulation and distribution. If the deviation amount, the deviation speed or the deviation acceleration show an upward trend in future detections, if the deviation amount, the deviation speed or the deviation acceleration show an upward trend in future detections, it will transfer to the A2-level fault handling.

[0059] The upward trend includes showing an upward result in any one of the recent 5 consecutive detections, and it is judged to be in an upward trend.

[0060] In the actual belt operation process, affected by various external conditions, the belt's deviation amount, deviation speed or deviation acceleration will fluctuate. If the trend is judged based on only one or several test results, it will be affected by random fluctuations and lead to misjudgment. Select 5 consecutive tests to eliminate the influence of these random fluctuations to obtain more stable and reliable trend information. If an upward result is shown in any of the 5 consecutive tests, it means that the deviation amount, deviation speed or deviation acceleration continues to increase over a period of time. This continuous increase indicates potential problems, so it will be judged to be in an upward trend.

[0061] Judging the belt deviation state includes calculating the deviation amount, deviation speed, deviation acceleration, and material accumulation condition and distribution condition based on real-time information of the virtual deviation amount characteristic table.

[0062] If it is in an unloaded deviation state, the position of the drop point is accurately measured and controlled through the belt pre-dropping posture device. If the drop point position deviates from the preset range, the belt running posture is adjusted to correct the drop point position. If the adjusted position still deviates from the preset range, the material flow rate is monitored and adjusted in real time through the material flow rate monitor. If the flow rate exceeds the threshold, the drop point position and the belt running posture are adjusted. If the drop point position and the material flow rate still cannot be restored to the preset range, the alarm mechanism is activated to suspend the belt operation for manual inspection and processing.

[0063] The no-load deviation state includes using deep learning methods to learn the historical data of belt operation and generate a prediction model. When the belt is running, the belt status data is collected in real time and the model is used for prediction. When the prediction result shows that the belt will deviate, it is judged to be in the no-load deviation state.

[0064] Adjusting the position of the material drop point and the running posture of the belt includes using a servo motor or a stepper motor to adjust the position of the material drop device in real time to ensure that the material can accurately fall at the preset position, and by adjusting the speed and direction of the belt drive device, changing the running posture of the belt to avoid the material from running off the track due to the inertia generated by the belt movement.

[0065] The material flow rate includes using a load sensor to monitor the material flow rate in real time. If the flow rate exceeds a preset threshold, the material flow rate is adjusted by adjusting the running speed of the belt or adjusting the opening of the material feeding device.

[0066] In the case of overload deviation, the material accumulation monitor is used to monitor the material accumulation in real time. If the accumulation exceeds the preset range, the load of the belt is adjusted. If the adjusted load still exceeds the threshold, the material distribution monitor is used to monitor the material distribution on the belt in real time. If the distribution is uneven, the running speed of the belt is automatically adjusted according to the material accumulation and distribution conditions through the belt speed control system. If the material accumulation and distribution conditions still cannot be restored to the preset range, the system will activate the alarm mechanism and suspend the belt operation for manual inspection and processing.

[0067] The overload deviation state includes using load sensors and speed sensors to monitor the load and speed of the belt, applying deep learning algorithms, and through cameras installed on the belt, to monitor and analyze the material accumulation situation in real time. When the belt load exceeds the design load or the material accumulation is too much or too heavy, it is judged as the overload deviation state.

[0068] Adjusting the load of the belt includes adjusting the feeding speed of the material or the running speed of the belt in real time to adjust the load of the belt. This can be achieved by controlling the opening of the feeding device through a servo motor or a stepper motor, or by adjusting the rotation speed of the belt drive device.

[0069] Material distribution monitoring includes monitoring the material distribution on the belt in real time through cameras or laser scanners. If the distribution is uneven, the position of the feeding device or the running speed of the belt can be adjusted to make the material evenly distributed on the belt.

[0070] Automatically adjusting the running speed of the belt includes PID control technology. The analog quantity of the deviation displacement is detected and real-time feedback is provided through the visual deviation system, and the electric deviation correction device is controlled through PID data processing to correct the belt deviation. The whole system realizes closed-loop control and finally realizes the steady-state control of the belt operation.

[0071] Embodiment 2

[0072] Referring to Figure 2 , an embodiment of the present invention provides a coal conveying belt fault warning system based on computer vision algorithms, including:

[0073] A sensor acquisition module, an image processing module, a state judgment module, and a fault processing module.

[0074] The sensor acquisition module is used to collect the real-time image and depth information of the coal conveying belt, generate a 2D image and a 3D model of the belt, and obtain the gray-scale features of the object.

[0075] The image processing module is used to perform preprocessing operations on the image and depth information obtained by the sensor acquisition module, use the semantic segmentation technology of deep learning to identify the edge of the belt, calculate the 3D coordinates of the edge in the real world, and calculate the actual position of the belt.

[0076] The state judgment module is used to calculate the deviation amount, deviation speed, and deviation acceleration parameters of the belt based on the data obtained by the image processing module, establish and maintain a virtual deviation amount feature table, judge the deviation type of the belt according to specific conditions, and make corresponding fault handling decisions.

[0077] The fault handling module is used to implement corresponding handling measures according to the judgment result of the state judgment module, automatically adjust the running speed and the position of the material falling point of the belt, start the alarm mechanism and pause the belt operation.

[0078] Embodiment 3

[0079] An embodiment of the present invention, which is different from the previous two embodiments, is as follows:

[0080] If the above-mentioned functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that makes contributions to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs, etc., which can store program codes.

[0081] The logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or in combination with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device.

[0082] More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection (electronic device) having one or more wirings, a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable media can even be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or otherwise processing as appropriate, and then stored in a computer memory.

[0083] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application-specific integrated circuits having suitable combinational logic gate circuits, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0084] Example 4

[0085] Refer to Figures 3 - 4 , which is an embodiment of the present invention, provides a coal conveying belt fault warning method and system based on computer vision algorithms. In order to verify the beneficial effects of the present invention, scientific demonstrations are carried out through economic benefit calculations and simulation experiments.

[0086] MATLAB and CloudSim are used to evaluate the algorithm. The simulation has been run in an environment with an Intel processor and 12GB of RAM. The operating system used is 64-bit Windows 11 Ultimate. The point system is simulated using the MATLAB programming language, connection records are made, and a data distribution is constructed.

[0087] The experimental design will include two groups: one group using our invention method and the other group using traditional methods. These two groups will operate under the same coal conveying belt equipment and environmental conditions, and their operating status and fault handling will be tracked and recorded within 1 month.

[0088] The following key data: the number of deviation faults, the number of deviation faults correctly diagnosed, the number of deviation faults misdiagnosed, the average diagnosis time (the time from the occurrence of the fault to the completion of the diagnosis), the average repair time (the time from the occurrence of the fault to the completion of the repair), the total downtime of the belt, the operating efficiency of the belt (such as the coal conveying capacity). The experimental results are shown in Table 1.

[0089] Table 1 Comparison table of experimental results.

[0090]

[0091] As shown in Table 1, compared with the traditional method, the inventive method of our side has higher diagnostic accuracy and efficiency, faster repair time, less downtime, and higher operating efficiency.

[0092] The number of correct diagnoses is significantly more than that of the traditional method, and the average diagnosis time is greatly shortened, which greatly reduces the need for manual intervention, improves the efficiency and quality of fault handling, continuously and stably executes the fault handling process preset by the algorithm, greatly reduces the total downtime of the belt, enables the belt to maintain the running state for a longer time, thus bringing higher production efficiency, significantly improving the operating efficiency of the belt, greatly enhancing the safety of the equipment, and reducing the safety risks brought by equipment failures.

[0093] As Figures 3 - 4 shown, according to different deviation amounts and deviation speeds, simulation experiments are carried out. The experimental results show that when the deviation amount exceeds 10 mm, it indicates that the operation of the belt has deviated significantly, and the deviation prediction accuracy rate reaches 84%. When the deviation speed exceeds 5 mm / s, it indicates that the deviation speed of the belt is very fast. If not handled in time, the deviation situation will deteriorate rapidly, and the accuracy rate of judging as deviation reaches 96.4%. At the same time, if the deviation acceleration exceeds 2 mm / s 2 , it indicates that the increase in the deviation speed continues and the deviation situation continues to deteriorate. When all these three conditions are met, it indicates that the deviation problem of the belt is very serious and continues to deteriorate. Therefore, it will be judged as a Class A1 fault.

[0094] The comprehensive consideration of the deviation amount, deviation speed and deviation acceleration of the belt can not only judge whether the belt has deviation, but also identify the severity and trend of the deviation through the dynamic change of the deviation. It can not only detect and handle the deviation problem in time to prevent it from having a greater impact on the belt operation, but also predict the future development trend by observing the dynamic change of the deviation, so as to take measures in advance to reduce or avoid possible losses and prevent the further development of the deviation problem.

[0095] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

Claims

1. A fault warning method for coal conveying belts based on computer vision algorithms, characterized in that, Including: Collecting the gray - scale features between the belt and the target device through a sensor module; Judging the edge features and positions of the belt according to the gray - scale features; Establishing a virtual deviation amount feature table to judge the real - time state of the belt; Judging the deviation type according to the real - time state of the belt and performing fault handling; The types of deviation include detecting the deviation speed when the deviation amount a > 10 mm. If the deviation speed exceeds 5 mm / s and the deviation acceleration exceeds 2 mm / s 2 , it is determined that the fault is of level A1. When the deviation amount 5 mm ≤ a ≤ 10 mm, if both the deviation speed and the deviation acceleration are in an upward trend, it is determined that the fault is of 2 level A. When the deviation amount 5 mm ≤ a ≤ 10 mm, if the deviation speed ≤ 5 mm / s and the deviation acceleration ≤ 2 mm / s 2 , it is determined that the fault is of level A3; If it is judged as a Class A1 fault, immediately stop the belt operation, automatically calibrate the fault area, guide the operator to repair, and during the repair process, monitor the repair progress in real time; If it is judged as a Class A2 fault, according to the real - time information of the virtual deviation amount feature table, judge the deviation state of the belt, automatically adjust the running speed and the position of the material dropping point of the belt, automatically adjust the material accumulation and distribution, and try to solve the deviation problem. If the automatic adjustment cannot stop the deviation speed and the deviation acceleration are both in an upward trend, it will be transferred to Class A1 fault handling; If it is judged as a Class A3 fault, continuously monitor the running state of the belt, adjust the material accumulation and distribution in real time, prevent deviation problems caused by uneven material accumulation and distribution. If the deviation amount, deviation speed or deviation acceleration shows an upward trend in future detections, it will be transferred to Class A2 fault handling; The upward trend includes showing an upward result in any one of the recent 5 consecutive detections, and it is judged to be in an upward trend; Judging the deviation state of the belt includes, according to the real - time information of the virtual deviation amount feature table, calculating the deviation amount, deviation speed, deviation acceleration, and the condition and distribution of material accumulation; Judging the deviation state of the belt also includes, if it is in an unloaded deviation state, accurately measuring and controlling the position of the material dropping point through the pre - falling attitude device of the belt. If the position of the material dropping point deviates from the preset range, adjust the running attitude of the belt to correct the position of the material dropping point. If the adjusted position still deviates from the preset range, monitor and adjust the material flow rate in real time through the material flow rate monitor. If the flow rate exceeds the threshold, adjust the position of the material dropping point and the running attitude of the belt. If the position of the material dropping point and the material flow rate still cannot be restored to the preset range, start the alarm mechanism to pause the belt operation for manual inspection and processing; If it is in a heavily - loaded deviation state, monitor the material accumulation situation in real time through the material accumulation monitor. If the accumulation situation exceeds the preset range, adjust the load of the belt. If the adjusted load still exceeds the threshold, monitor the distribution of materials on the belt in real time through the material distribution monitor. If the distribution is uneven, automatically adjust the running speed of the belt through the belt speed control system according to the material accumulation and distribution conditions. If the material accumulation and distribution conditions still cannot be restored to the preset range, the system will start the alarm mechanism and pause the belt operation for manual inspection and processing.

2. The coal conveying belt fault warning method based on computer vision algorithm according to claim 1, characterized in that: The gray - scale features between the belt and the target device include capturing the surface details of the belt through a high - resolution image sensor to generate a 2D image, and the depth sensor measures the distance of the object to form a 3D model of the object. The data is combined to form gray - scale features including the shape, texture, color and distance of the belt material.

3. The coal conveying belt fault warning method based on computer vision algorithm according to claim 2, characterized in that: The determination of the edge features and position of the belt includes using computer vision algorithms to activate a multi-modal sensor array, collecting and analyzing 2D images and 3D models of the belt, denoising, filtering, and adjusting the brightness of the collected data, using semantic segmentation technology of deep learning to process the preprocessed RGB images, identifying the edge of the belt, combining the depth information obtained by lidar to obtain the actual distance between the edge and the targeting device, using computational geometry methods to calculate the 3D coordinates of the edge in the real world based on the 2D coordinates and depth information of the belt edge, and using a regression model based on machine learning to calculate the actual distance according to the 3D coordinates of the belt edge and the 3D coordinates of the targeting device to determine the actual position of the belt.

4. The coal conveying belt fault early warning method based on computer vision algorithm according to claim 3, characterized in that: The virtual deviation amount feature table includes calculating the deviation amount of the belt according to the actual position of the belt and the preset normal position, collecting the deviation amount a, deviation speed, deviation acceleration of the belt, as well as the condition and distribution of material accumulation, automatically calculating the instantaneous volume of the belt material flow, automatically judging whether the feeding point is centered, and recording the collected information in the dynamically updated virtual deviation amount feature table.

5. A system adopting the coal conveying belt fault early warning method based on computer vision algorithm as described in any one of claims 1 to 4, characterized in that, It includes: A sensor acquisition module, an image processing module, a state judgment module, and a fault handling module; The sensor acquisition module is used to collect real-time images and depth information of the coal conveying belt, generate 2D images and 3D models of the belt, and obtain the gray-scale features of the object; The image processing module is used to perform preprocessing operations on the images and depth information obtained by the sensor acquisition module, use semantic segmentation technology of deep learning to identify the edge of the belt, calculate the 3D coordinates of the edge in the real world, and calculate the actual position of the belt; The state judgment module is used to calculate the deviation amount, deviation speed, and deviation acceleration parameters of the belt according to the data obtained by the image processing module, establish and maintain a virtual deviation amount feature table, judge the deviation type of the belt according to specific conditions, and make corresponding fault handling decisions; The fault handling module is used to implement corresponding handling measures according to the judgment results of the state judgment module, automatically adjust the running speed and feeding point position of the belt, activate the alarm mechanism and pause the belt operation.

6. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method according to any one of claims 1 to 4.

Images