Unmanned automatic inspection system for conveyor

Abstract

The invention provides an unmanned automatic inspection system for a conveyor, and relates to the technical field of unmanned automatic inspection, the unmanned automatic inspection system comprises a conveyor longitudinal beam, an automatic inspection track and inspection equipment, the inspection equipment is equipped with a driving mechanism, a monitoring mechanism and a positioning mechanism, and the unmanned automatic inspection system also comprises a data acquisition unit, a feature extraction unit and a feature analysis unit. The inspection equipment is driven by a servo motor, a belt wheel and a transmission belt to move stably, and unmanned automatic inspection is realized by matching with multi-camera omnibearing monitoring and precise positioning of a telescopic rod and a fixed roller; and meanwhile, a two-dimensional offset curve is constructed through the feature analysis unit to realize quantitative evaluation, the environment analysis unit is linked with environment data, and the offset detection output module performs hierarchical response, so that the problems of dependence on manpower, low efficiency, high omission ratio and rough data processing in the existing routing inspection are comprehensively solved, the routing inspection automation and intelligence level and the operation stability are greatly improved, and the routing inspection efficiency is improved. And safe and efficient operation of equipment is ensured.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of unmanned automatic inspection system, and particularly relates to a conveyor unmanned automatic inspection system. BACKGROUND

[0002] In the modern industrial production system, the conveyor is widely used in many fields such as mines, ports, chemical industry and power industry due to its efficient and continuous material transmission capacity, and is one of the core equipment to ensure the smooth operation of the production process. However, due to the long-term heavy load and continuous operation of the conveyor, and the characteristics of high dust, high humidity and complex space in the working environment, the parts of the equipment are prone to wear and failure. Therefore, it is important to discover and handle potential faults in time and accurately to maintain the continuity of production, reduce maintenance costs and ensure safety production.

[0003] However, the traditional conveyor inspection mainly relies on manual work, which has the problems of low efficiency, high labor intensity, serious environmental influence and difficulty in real-time and comprehensive monitoring. Manual inspection cannot timely detect early potential faults, which may easily lead to equipment failure and cause production interruption and economic loss. Although some existing automatic inspection systems improve the inspection efficiency to a certain extent, there are still deficiencies in the aspects of intelligent degree, data processing accuracy, system stability and adaptability to complex environment.

[0004] Therefore, the conveyor unmanned automatic inspection system is proposed to solve the above technical problems. SUMMARY

[0005] The present application aims to provide a conveyor unmanned automatic inspection system, which aims to realize comprehensive, real-time and accurate monitoring of the running state of the conveyor through innovative hardware design and advanced software algorithm, discover potential fault hidden dangers in time, improve the reliability of equipment operation, reduce labor costs and ensure the continuity and safety of production.

[0006] To solve the above technical problems, the conveyor unmanned automatic inspection system provided by the present application comprises a conveyor longitudinal beam and an automatic inspection track spaced apart from the conveyor longitudinal beam, the conveyor longitudinal beam and the automatic inspection track are both horizontally installed on a conveyor support leg, a driving mechanism is installed between the automatic inspection track and the conveyor longitudinal beam, the driving mechanism is rotationally installed on the upper end of an inspection device, monitoring mechanisms are installed on the upper and lower ends of the inspection device, and a positioning mechanism is installed on the upper end of the inspection device. The inspection system further comprises a data acquisition unit, a feature extraction unit and a feature analysis unit. The data acquisition unit is used to receive conveyor image data collected by the monitoring mechanism. The feature extraction unit adopts a Canny algorithm to smooth the image through Gaussian filtering, calculate gradient amplitude and direction, non-maximum suppression, and double threshold detection and edge connection steps to extract the conveyor belt edge pixel coordinates. The feature analysis unit converts the conveyor belt edge pixel coordinates into coordinate points and generates a curve by constructing an edge offset detection curve, calculates the conveyor belt width and the tightening width value, defines the offset area and calculates the offset surface value, and obtains the offset detection analysis result through mean value, variance calculation and weighting algorithm. The offset detection analysis result includes offset evaluation value, offset position evaluation value, offset amplitude evaluation value, tightening width value, tightening average width value, tightening fluctuation value, offset surface value, offset average surface value, and offset fluctuation value.

[0007] Preferably, the signal pole and the air monitoring head are respectively installed on both sides of the lower end of the inspection equipment, and the charging port is arranged at the middle of one side of the inspection equipment. A dust cover is arranged at the charging port.

[0008] Preferably, the driving mechanism comprises a driving wheel rotatably installed on one side of the upper end of the inspection equipment. The driving wheel is rotatably inserted between the automatic inspection track and the conveyor beam, and the driving wheel is connected to the first pulley through the first transmission belt. The second pulley is rotatably installed between the first pulley and the third pulley, and the second transmission belt is arranged between the second pulley and the third pulley. The servo motor is installed on one side of the inspection equipment, and the output end of the servo motor is fixedly connected to one side of the third pulley. The fixed plate is fixedly installed on one end of the servo motor, and the explosion-proof battery is installed on the inner side of the inspection equipment.

[0009] Preferably, the monitoring mechanism comprises a fixed block fixedly connected to the upper and lower ends of the inspection equipment. A plurality of cameras are installed on both sides of the fixed block at the upper and lower ends.

[0010] Preferably, the positioning mechanism comprises a connecting block fixedly connected to both sides of the upper fixed block. A recess is formed in the bottom of the connecting block, and a telescopic rod is fixedly installed in the recess. A telescopic spring is arranged outside the telescopic rod, and the other end of the telescopic rod is fixedly connected to the upper end of the moving block. A fixed roller is rotatably installed at the lower end of the moving block.

[0011] Preferably, the feature analysis unit obtains the offset detection analysis result through the following steps: The start time of the conveyor is defined as the first time, and the shutdown time is defined as the second time. If there is no shutdown time, the current time is defined as the second time. The time region between the first time and the second time is defined as the running time zone. extracting the coordinates of the two side edges of the conveying belt at all collection time points within the runtime zone; taking a fixed reference point on the conveying belt as the origin, constructing a two-dimensional edge offset detection graph: the horizontal axis is the time axis, and the vertical axis is the spatial position axis; mapping the two side edge pixel coordinates at each collection time point to the coordinate system to form two coordinate points, and constructing two curves by connecting the time sequences; calculating the distance between the two side edge pixel coordinates at the same collection time point, defined as the width of the conveying belt; subtracting the current actual width from the preset standard width of the conveying belt to obtain the tightening width value; defining the time range of a set time length before the current time as the detection time zone; setting the standard position line of the two side edges in the coordinate system; connecting the edge coordinates at the current time with the corresponding standard position to form a first line segment; connecting the edge coordinates at the start time of the detection time zone with the corresponding standard position to form a second line segment; the area enclosed by the above two line segments, the time sequence curve of the two side edges, and the standard position line is defined as the offset area, and the total area is calculated and recorded as the offset surface value; In the detection time zone, the tightening width value and the offset surface value are calculated by the mean and variance formula to obtain the tightening average width value, the tightening fluctuation value, and the offset average surface value, and the offset fluctuation value; weighting and summing the tightening width value, the tightening average width value, and the tightening fluctuation value to obtain the offset position evaluation value; weighting and summing the offset surface value, the offset average surface value, and the offset fluctuation value to obtain the offset amplitude evaluation value; obtaining the offset position evaluation value and the offset amplitude evaluation value of the multi-angle picture, setting the angle importance weight for each angle picture, and weighting and summing the offset position evaluation value and the offset amplitude evaluation value of each angle to obtain the offset evaluation value; integrating the offset evaluation value, the offset position evaluation value, the offset amplitude evaluation value, the tightening width value, the tightening average width value, the tightening fluctuation value, the offset surface value, the offset average surface value, and the offset fluctuation value into the offset detection analysis result.

[0012] As a preferred, the inspection system further comprises an environment analysis unit; The environment analysis unit is used to obtain environmental data collected by the air monitoring head; wherein the environmental data includes dust concentration and harmful gas content; Set the environment monitoring time zone, calculate the mean and fluctuation trend value of the dust concentration and harmful gas content in the environment monitoring time zone by the mean and variance formula, and record the mean and fluctuation trend value of the dust as the dust mean and its fluctuation trend value respectively, and record the mean and fluctuation trend value of each toxic gas as the mean and fluctuation trend value of each toxic gas respectively; the dust mean and its fluctuation trend value are weighted to obtain a dust evaluation value; the mean and fluctuation trend value of the harmful gas are weighted to obtain an abnormal evaluation value of the harmful gas; and the dust evaluation value and the abnormal evaluation value of each harmful gas are taken as the environment analysis result.

[0013] As preferred, the inspection system further comprises an offset detection output module; The offset detection output module is used for receiving the offset detection analysis result and generating a corresponding judgment result, specifically: A plurality of preset multi-dimensional offset judgment threshold values are provided, including an offset evaluation threshold value and an offset amplitude threshold value; the offset evaluation threshold value is divided into a serious offset threshold value and a slight offset threshold value; When the offset evaluation value is greater than or equal to the serious offset threshold value, or the offset surface value is greater than the offset amplitude threshold value, it indicates that the conveying belt is obviously offset or is about to be offset, and an emergency alarm signal is generated; the emergency alarm signal includes the offset detection analysis result, the time when the signal is generated, and the position of the conveying belt where the offset occurs; When the offset evaluation value is between the serious offset threshold value and the slight offset threshold value, and the offset surface value is less than the offset amplitude threshold value, it is judged as a slight offset state; when the conveying belt is in the slight offset state, the offset detection analysis result is stored at a set time interval, and the stored offset detection analysis result is sent to the display module at a set period; When the offset evaluation value is less than the slight offset threshold value, it indicates that the conveying belt is in a stable state, and the conveying belt does not exist offset phenomenon or is within a stable offset fluctuation range.

[0014] As preferred, the inspection system further comprises a display module; the display module is used for displaying the offset state identification encoded by color in real time; and is also used for displaying the offset detection analysis result and the environment analysis result; when the emergency alarm signal is received, it is automatically switched to a full-screen alarm interface, and the alarm type, the current offset evaluation value and the position of the conveying belt are displayed in a flashing manner.

[0015] Compared with the related art, the unmanned automatic inspection system for the conveyor provided by the present application has the following beneficial effects: The present application drives the inspection equipment to move stably through the servo motor, the pulley and the transmission belt, comprehensively captures the equipment state by combining the upper and lower end fixed blocks and the multiple cameras, and stably positions the moving path by cooperating the telescopic rod, the telescopic spring and the fixed roller, thereby improving the automatic inspection degree, the comprehensive monitoring and the positioning accuracy, realizing the unmanned automatic inspection, the omnibearing real-time monitoring and the precise inspection function, and solving the problems of the existing inspection which relies on manual operation, has low efficiency, high missing rate and is difficult to grasp the equipment running state in real time.

[0016] The present application aims at the rough data processing problem of the existing system, constructs a two-dimensional offset curve through a feature analysis unit, calculates multi-dimensional indexes and generates evaluation values, realizes accurate conversion from images to quantitative results, and the environment analysis unit links dust and harmful gas data to assist decision-making, the offset detection output module responds according to threshold classification, adapts to complex industrial environments, and greatly improves the system intelligence and operation stability. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 Fig. 1 is a schematic diagram of the overall three-dimensional structure of embodiment 1 of the conveyor unmanned automatic inspection system provided by the present application; Figure 2 Fig. 2 is another overall perspective view of the conveyor unmanned automatic inspection system provided by the present application; Figure 1 Fig. 3 is a partial bottom view of the conveyor unmanned automatic inspection system provided by the present application; Figure 3 Fig. 4 is a side view structure diagram of the conveyor unmanned automatic inspection system provided by the present application; Figure 1 Fig. 5 is a side view first perspective view of the conveyor unmanned automatic inspection system provided by the present application; Figure 4 Fig. 6 is a side view second perspective view of the conveyor unmanned automatic inspection system provided by the present application; Figure 1 Fig. 7 is a side view structure diagram of the conveyor unmanned automatic inspection system provided by the present application; Figure 5 Fig. 8 is a side view structure diagram of the conveyor unmanned automatic inspection system provided by the present application; Figure 1 Fig. 9 is a side view structure diagram of the conveyor unmanned automatic inspection system provided by the present application; Figure 6 Fig. 10 is a side view structure diagram of the conveyor unmanned automatic inspection system provided by the present application; Figure 1 Fig. 11 is a side view structure diagram of the conveyor unmanned automatic inspection system provided by the present application; Figure 7 Fig. 12 is a side view structure diagram of the conveyor unmanned automatic inspection system provided by the present application; Figure 1 Fig. 13 is a side view structure diagram of the conveyor unmanned automatic inspection system provided by the present application; Figure 8 Fig. 14 is a schematic diagram of the connection relationship of the drive pulley of the servo motor of the conveyor unmanned automatic inspection system provided by the present application; Figure 1 Fig. 15 is a principle block diagram of embodiment 2 of the conveyor unmanned automatic inspection system provided by the present application; Figure 9 Fig. 16 is an edge offset detection curve diagram of the conveyor unmanned automatic inspection system provided by the present application. Figure 10 Figure 9 Fig. 17 is a schematic diagram of the connection relationship of the drive pulley of the servo motor of the conveyor unmanned automatic inspection system provided by the present application.

[0018] Fig. 1 is a schematic diagram of the overall three-dimensional structure of embodiment 1 of the conveyor unmanned automatic inspection system provided by the present application; DETAILED DESCRIPTION

[0019] ​Clearly, the described embodiments are only some, but not all, embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts should fall into the scope of the present application.

[0020] The terminology used in the present disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the present disclosure. As used in the present disclosure and the appended claims, the singular forms "a," "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0021] It will be understood that, although the terms first, second, third, etc. can be used herein to describe various information, the information should not be limited to these terms. These terms are used only to distinguish one particular information from another. For example, a first information could be termed a second information, and, similarly, a second information could be termed a first information without departing from the scope of the present disclosure. As used herein, the term "if' can be interpreted to mean "when" or "upon" or "in response to determining" depending on the context.

[0022] Example 1

[0023] Please see Figures 1-8The application discloses a conveyor unmanned automatic inspection system, which comprises a conveyor longitudinal beam 1, an automatic inspection track 2 which is spaced apart from the conveyor longitudinal beam 1, and a conveyor support leg. The conveyor longitudinal beam 1 and the automatic inspection track 2 are horizontally installed on the conveyor support leg. A driving mechanism is installed between the automatic inspection track 2 and the conveyor longitudinal beam 1. The driving mechanism is rotationally installed on the upper end of an inspection device 3. Monitoring mechanisms are installed on the upper and lower ends of the inspection device 3. A positioning mechanism is installed on the upper end of the inspection device 3. The conveyor longitudinal beam 1 and the automatic inspection track 2 are installed on the conveyor support leg. The driving mechanism, the inspection device 3, the monitoring mechanisms and the positioning mechanism are cooperated to facilitate the construction of the conveyor unmanned automatic inspection system. Signal rods 11 and air monitoring heads 10 are installed on the lower end of the inspection device 3. A charging port 8 is arranged on one side of the middle part of the inspection device 3. Dustproof covers are arranged at the charging ports 8. The signal rods 11 and the air monitoring heads 10 are installed on the lower end of the inspection device 3. The charging port 8 and the dustproof covers are arranged on one side of the inspection device 3. The driving mechanism comprises a driving wheel 4 which is rotationally installed on one side of the upper end of the inspection device 3. The driving wheel 4 is rollingly inserted between the automatic inspection track 2 and the conveyor longitudinal beam 1. First pulleys 16 are fixedly connected to the connecting ends of the driving wheel 4 and penetrate through the inspection device 3. A limiting rod is arranged on the inner side of the lower end of the inspection device 3. Second pulleys 17 are rotationally installed on the lower end of the limiting rod. First transmission belts 12 are sleeved between the second pulleys 17 and the first pulleys 16. The driving wheel 4 on the upper end of the inspection device 3 is cooperated with the automatic inspection track 2 and the conveyor longitudinal beam 1. The first pulleys 16, the second pulleys 17, the first transmission belts 12 and the limiting rod are arranged. The stable movement of the inspection device 3 is realized by controlling a servo motor 15.

[0024] In the application, the third pulley 18 is rotatably mounted between the second pulleys 17, and the second pulley 17 and the third pulley 18 are sleeved with the second transmission belt 14, one side of the second transmission belt 14 is internally mounted with the servo motor 15 in the inspection equipment 3, the output end of the servo motor 15 is fixedly connected with the third pulley 18 on one side, and one end of the servo motor 15 is fixedly mounted with the fixed plate 6 on the inspection equipment 3, and the explosion-proof battery is mounted on the inner side of the inspection equipment 3, through the cooperation of the second pulley 17, the third pulley 18, the second transmission belt 14 and the servo motor 15, and the setting of the fixed plate 6 and the explosion-proof battery, the power source is provided for the driving mechanism and the safe operation of the equipment is ensured; the monitoring mechanism comprises the fixed blocks 5 fixedly connected on the upper and lower ends of the inspection equipment 3, and a plurality of cameras 7 are mounted on the two sides of the fixed blocks 5 on the upper and lower ends of the inspection equipment 3, through the installation of the plurality of cameras 7 on the fixed blocks 5 on the upper and lower ends of the inspection equipment 3, the omnibearing and dead angle-free monitoring of the conveyor can be realized; the positioning mechanism comprises the connecting blocks 19 fixedly connected on the two sides of the upper end fixed block 5, recesses are formed in the bottom of the connecting block 19 and upward, the telescopic rods are fixedly mounted in the recesses, the telescopic springs 13 are sleeved on the outer sides of the telescopic rods, and the other end of the telescopic rod is fixedly connected with the upper end of the moving block, and the fixed rollers 9 are rotatably mounted on the lower end of the moving block, through the connecting block 19, the telescopic rod, the telescopic spring 13, the moving block and the fixed roller 9, the positioning mechanism is formed, and the accurate positioning of the inspection equipment 3 can be realized.

[0025] Working principle: when the application is used, first, the servo motor 15 is started to drive the third pulley 18 to rotate, since the third pulley 18 is connected with the second pulley 17 through the second transmission belt 14, the second pulley 17 is rotated, then the second pulley 17 drives the first transmission belt 12 to drive the first pulley 16, and then the driving wheel 4 is inserted between the automatic inspection track 2 and the conveyor longitudinal beam 1, and rolls on the track by friction to drive the inspection equipment 3 to move along the track, the limiting rod limits the second pulley 17 to ensure the stable operation of the transmission system, then the cameras 7 mounted on the fixed blocks 5 on the upper and lower ends of the inspection equipment 3 continuously shoot the multi-angle pictures of the top, bottom and side of the conveyor during the movement of the equipment, and the running state, belt wear condition and material conveying condition of the conveyor are monitored in real time, and during the inspection, the air monitoring head 10 on the lower end of the inspection equipment 3 works synchronously to detect the air quality such as dust concentration and harmful gas content around the conveyor in real time, and the signal rod 11 transmits the image data shot by the camera 7 and the data detected by the air monitoring head 10 to the remote monitoring center, so that the staff can master the running environment of the conveyor in real time, then the fixed roller 9 is always in contact with and pressed against the automatic inspection track 2 and the conveyor longitudinal beam 1 under the elastic force of the telescopic spring 13, so that the inspection equipment 3 moves stably along the track, the deviation or shaking is avoided, and the inspection accuracy is improved Example 2

[0026] Please refer to Figures 9-10 As shown in the above, based on the conveyor unmanned automatic inspection system provided by Embodiment 1 of the present application, Embodiment 2 of the present application proposes another conveyor unmanned automatic inspection system. Embodiment 2 is only a preferred mode of Embodiment 1, and the implementation of Embodiment 2 will not affect the separate implementation of Embodiment 1.

[0027] Specifically, the conveyor unmanned automatic inspection system provided by Embodiment 2 of the present application is different in that: The inspection system further comprises a data acquisition unit, a feature extraction unit, and a feature analysis unit. The data acquisition unit is configured to receive conveyor image data collected by the monitoring mechanism. The feature extraction unit adopts the Canny algorithm to extract the conveyor belt edge pixel coordinates through the steps of Gaussian filter smoothing image, gradient amplitude and direction calculation, non-maximum suppression, and double threshold detection and edge connection. The feature analysis unit converts the conveyor belt edge pixel coordinates into coordinate points and generates a curve by constructing an edge offset detection curve, calculates the conveyor belt width and the tightening width value, defines the offset area and calculates the offset surface value, and obtains the offset detection analysis result through the mean, variance calculation and weighting algorithm; wherein the offset detection analysis result includes the offset evaluation value, the offset position evaluation value, the offset amplitude evaluation value, the tightening width value, the tightening average width value, the tightening fluctuation value, the offset surface value, the offset average surface value, and the offset fluctuation value.

[0028] By providing the data acquisition unit, the feature extraction unit, and the feature analysis unit, the image data of the monitoring mechanism is obtained by the data acquisition unit, the conveyor belt edge pixel coordinates are accurately extracted by the feature extraction unit using the Canny algorithm, and then the multi-dimensional evaluation value is obtained by the feature analysis unit through constructing the edge offset detection curve, calculating the tightening width value and the offset surface value, and using the mean, variance, and weighting algorithm, forming a complete conveyor belt offset detection analysis system, realizing the quantitative evaluation and accurate judgment of the conveyor belt offset state, providing data support for subsequent offset early warning and fault handling, and being the core technical link of the system in realizing the conveyor belt state monitoring in the unmanned automatic inspection.

[0029] In the present application, the feature analysis unit obtains the offset detection analysis result through the following steps: The start-up moment of the conveyor is taken as the first moment, and the shutdown moment is taken as the second moment; if there is no shutdown moment, the current moment is taken as the second moment; the time region between the first moment and the second moment is defined as the running time zone; The edge pixel coordinates of the conveyor belt on both sides in the running time zone are extracted; A two-dimensional edge offset detection curve is constructed with a fixed reference point on the conveying belt as the origin: the horizontal axis is the time axis, and the vertical axis is the spatial position axis; The two-side edge pixel coordinates of each collection time are mapped to the coordinate system to form two coordinate points, and two curves are constructed by connecting the time sequence. The distance between the two-side edge pixel coordinates at the same collection time is calculated, which is defined as the conveying belt width. The actual width at present is subtracted from the preset standard width of the conveying belt to obtain the tightening width value; The time range of a set time length before the current time is defined as the detection time zone for analyzing the recent offset trend; The standard position line of the two-side edges is set in the coordinate system. The edge coordinates at the current time are connected with the corresponding standard position to form a first line segment. The edge coordinates at the start time of the detection time zone are connected with the corresponding standard position to form a second line segment. The area surrounded by the above two line segments, the time sequence curve of the two-side edges and the standard position line is defined as the offset area, and the total area is calculated and recorded as the offset surface value; In the detection time zone, the tightening width value and the offset surface value are calculated by the mean and variance formula to obtain the tightening average width value, the tightening fluctuation value, the offset average surface value and the offset fluctuation value; The tightening width value, the tightening average width value and the tightening fluctuation value at the current time are weighted and summed to obtain the offset position evaluation value PY1, which reflects the comprehensive position characteristics of the current tightness deviation; The offset surface value, the offset average surface value and the offset fluctuation value at the current time are weighted and summed to obtain the offset amplitude evaluation value PY2, which reflects the comprehensive amplitude characteristics of the current edge offset; The offset position evaluation value iPY1 and the offset amplitude evaluation value iPY2 of the multi-angle picture are obtained, i represents the number corresponding to the angle picture, and the angle importance weight of each angle picture is set as iρ; the offset position evaluation value and the offset amplitude evaluation value of each angle are weighted and summed to obtain the offset evaluation value PY, and the calculation logic is: ; wherein a1 and a2 represent the preset weights corresponding to the offset position evaluation value and the offset amplitude evaluation value respectively, h represents the number of multi-angle pictures, and the offset evaluation value is used as the overall evaluation index of edge offset; The offset evaluation value, the offset position evaluation value, the offset amplitude evaluation value, the tightening width value, the tightening average width value, the tightening fluctuation value, the offset surface value, the offset average surface value and the offset fluctuation value are integrated as the offset detection analysis result.

[0030] Through the specific analysis process of the feature analysis unit, the conveying belt edge pixel coordinates are converted into quantitative indicators, the running time zone and the detection time zone are first defined, the coordinate system is constructed and the edge curve is generated, the conveying belt width, the tightening width value and the offset area (offset surface value) are calculated, then the multi-dimensional evaluation values (offset position, amplitude and overall evaluation value) are obtained through the mean, variance and weighted algorithms, and finally the offset detection analysis results are integrated to realize the accurate conversion of the conveying belt offset state from image data to quantitative evaluation, which provides a scientific basis for the system to judge the offset degree and generate an alarm signal, and is a core link to realize the automatic detection and evaluation of the conveying belt offset.

[0031] In the present application, the inspection system further comprises an environment analysis unit; The environment analysis unit is used to obtain the environment data collected by the air monitoring head 10; wherein the environment data includes dust concentration and harmful gas content; Set the environment monitoring time zone, calculate the mean and fluctuation trend value of the dust concentration and harmful gas content in the environment monitoring time zone through the mean and variance formulas, and record them as the dust mean and its fluctuation trend value, and the mean and fluctuation trend value of each toxic gas; calculate the dust evaluation value by weighting the dust mean and its fluctuation trend value; calculate the abnormal evaluation value of the harmful gas by weighting the mean and fluctuation trend value of the harmful gas; and take the dust evaluation value and the abnormal evaluation value of each harmful gas as the environment analysis result.

[0032] Through the environment analysis unit, the dust concentration, harmful gas content and other environment data collected by the air monitoring head are obtained, the mean and fluctuation trend value of each parameter are calculated in the set environment monitoring time zone, and then the dust evaluation value and the harmful gas evaluation value are generated by weighting algorithm as the environment analysis result, which realizes the quantitative analysis and comprehensive evaluation of the key parameters of the conveyor running environment, provides data support for judging whether the environment affects the equipment operation and assisting in interpreting the offset detection result, and is an important supplement to the system for monitoring the running state of the conveyor.

[0033] It should be noted that the abnormal threshold value corresponding to any result in the environment analysis result is compared with the preset abnormal threshold value of any result in the environment analysis result, for example, if the dust evaluation value is greater than its preset abnormal threshold value, it indicates that the dust is abnormal (the content is too high or the trend is abnormal), a dust abnormality corresponding alarm signal is generated and sent to the display module for display; if the abnormal evaluation value of the harmful gas is greater than its preset abnormal threshold value, it indicates that the content of the harmful gas is too high or the trend is abnormal, and a harmful gas corresponding preset alarm signal is generated and sent to the display module for display.

[0034] In the present application, the inspection system further comprises an offset detection output module; The offset detection output module is configured to receive the offset detection analysis result and generate a corresponding judgment result, specifically: The preset multi-dimensional offset judgment threshold set includes an offset evaluation threshold and an offset amplitude threshold; the offset evaluation threshold is divided into a severe offset threshold and a slight offset threshold; When the offset evaluation value is greater than or equal to the severe offset threshold, or the offset surface value is greater than the offset amplitude threshold, it indicates that the conveying belt is obviously offset or is about to be offset, and an emergency alarm signal is generated; the emergency alarm signal includes the offset detection analysis result, the time when the signal is generated, and the position of the conveying belt where the offset occurs. When the offset evaluation value is between the severe offset threshold and the slight offset threshold, and the offset surface value is less than the offset amplitude threshold, it is determined that the conveying belt is in a slight offset state; when the conveying belt is in the slight offset state, the offset detection analysis result is stored at a set time interval, and the stored offset detection analysis result is sent to the display module at a set period. When the offset evaluation value is less than the slight offset threshold, it indicates that the conveying belt is in a stable state, and there is no offset phenomenon or the conveying belt is within a stable offset fluctuation range.

[0035] By presetting the multi-dimensional offset judgment threshold in the offset detection output module, the state of the conveying belt is divided into three categories: obvious offset (emergency alarm signal is generated), slight offset (data is stored and sent to the display module at a regular time), and stable state (no special operation) according to the comparison of the offset evaluation value, the offset surface value, and the threshold, which realizes the hierarchical judgment and corresponding processing of the offset state of the conveying belt, provides clear execution logic for the system to automatically respond to the offset situation and timely warn of faults, and is a key link connecting offset detection analysis and terminal display and alarm.

[0036] In the present application, the inspection system further includes a display module; the display module is configured to display a color-coded offset state identifier in real time; and is further configured to display the offset detection analysis result and the environmental analysis result; when receiving the emergency alarm signal, the display module automatically switches to a full-screen alarm interface and flashes to display the alarm type, the current offset evaluation value, and the position of the conveying belt.

[0037] The display module displays the offset state identifier in real time by color coding, presents the offset detection analysis result and the environmental analysis result, automatically switches to a full-screen alarm interface and flashes to display key information when receiving the emergency alarm signal, realizes the visualization of the running state of the conveyor and the environmental data, provides a clear information interaction window for the staff to intuitively grasp the offset situation of the equipment and respond to the alarm in a timely manner, and is an important output link for the system to convert the detection analysis result into intuitive and perceptible information.

[0038] Other embodiments of the application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. It is intended that the application be construed as including any patent, any patent applications, and any patent publications to the extent that such patent, patent applications, and patent publications are consistent with the present disclosure. It is intended that the specification and examples be considered exemplary only, with the true scope and spirit of the application being indicated by the following claims.

[0039] It is to be understood that the application is not limited to the precise construction herein disclosed and shown in the drawings, and that various modifications and changes can be effected therein by those skilled in the art without departing from the scope of the application. The scope of the application is to be limited only by the appended claims.

Claims

1. An unmanned automatic inspection system for conveyors, characterized in that, The system includes a conveyor longitudinal beam (1) and an automatic inspection track (2) spaced a certain distance from the conveyor longitudinal beam (1). The system is characterized in that: the conveyor longitudinal beam (1) and the automatic inspection track (2) are both horizontally installed on the conveyor support legs; a drive mechanism is installed between the automatic inspection track (2) and the conveyor longitudinal beam (1); the drive mechanism is rotatably installed on the upper end of the inspection equipment (3); monitoring mechanisms are installed at both the upper and lower ends of the inspection equipment (3); and a positioning mechanism is installed on the upper end of the inspection equipment (3). The inspection system also includes a data acquisition unit, a feature extraction unit, and a feature analysis unit; The data acquisition unit is used to receive conveyor image data collected by the monitoring agency; The feature extraction unit uses the Canny algorithm to extract the pixel coordinates of the conveyor belt edge through steps such as Gaussian filtering to smooth the image, calculating the gradient magnitude and direction, non-maximum suppression, double threshold detection, and edge connection. The feature analysis unit constructs an edge offset detection curve, converts the pixel coordinates of the conveyor belt edge into coordinate points and generates a curve, calculates the conveyor belt width and tightening width value, defines the offset area and calculates the offset surface value, and obtains the offset detection analysis results through mean, variance calculation and weighting algorithm; wherein the offset detection analysis results include offset evaluation value, offset position evaluation value, offset amplitude evaluation value, tightening width value, tightening average width value, tightening fluctuation value, offset surface value, offset average surface value, and offset fluctuation value.

2. The unmanned automatic inspection system for conveyors according to claim 1, characterized in that: The inspection equipment (3) is equipped with a signal rod (11) and an air monitoring head (10) on both sides of its lower end, and a charging port (8) is installed in the middle of one side of the inspection equipment (3), with a dust cover provided at the charging port (8).

3. The unmanned automatic inspection system for conveyors according to claim 2, characterized in that: The driving mechanism includes a drive wheel (4) that is equidistantly rotatably installed on one side of the upper end of the inspection equipment (3). The drive wheel (4) is rolled between the automatic inspection track (2) and the longitudinal beam (1) of the conveyor. The drive wheel (4) is connected to a first pulley (16) through the inspection equipment (3). A limit rod is installed between the first pulleys (16) on the inner side of the lower end of the inspection equipment (3). A second pulley (17) is rotatably installed at the lower end of the limit rod. A first transmission belt (12) is sleeved between the second pulley (17) and the first pulley (16). A third pulley (18) is rotatably mounted between the second pulley (17) and a second transmission belt (14) is sleeved between the second pulley (17) and the third pulley (18). A servo motor (15) is installed inside the inspection device (3) on one side of the second transmission belt (14). The output end of the servo motor (15) is fixedly connected to one side of the third pulley (18). A fixing plate (6) is fixedly mounted on the inspection device (3) at one end of the servo motor (15). An explosion-proof battery is installed inside the inspection device (3).

4. The unmanned automatic inspection system for conveyors according to claim 3, characterized in that: The monitoring mechanism includes fixed blocks (5) that are fixedly connected to the upper and lower ends of the inspection equipment (3), and several cameras (7) are installed on both sides of the fixed blocks (5) at the upper and lower ends.

5. The unmanned automatic inspection system for conveyors according to claim 4, characterized in that: The positioning mechanism includes connecting blocks (19) that extend and are fixedly connected to both sides of the upper fixed block (5). The bottom of the connecting block (19) is provided with an upward groove, and a telescopic rod is fixedly installed in the groove. A telescopic spring (13) is sleeved on the outside of the telescopic rod, and the other end of the telescopic rod is fixedly connected to the upper end of the moving block. A fixed roller (9) is rotatably installed at the lower end of the moving block.

6. The unmanned automatic inspection system for conveyors according to claim 1, characterized in that: The feature analysis unit obtains the offset detection analysis results through the following steps: The start-up time of the conveyor is taken as the first moment, and the shutdown time is taken as the second moment; if there is no shutdown time, then the current moment is taken as the second moment; the time range between the first moment and the second moment is defined as the running time range; Extract the pixel coordinates of both sides of the conveyor belt edge at all acquisition times within the runtime area; Using a fixed reference point on the conveyor belt as the origin, a two-dimensional edge offset detection curve is constructed: the horizontal axis is the time axis, and the vertical axis is the spatial position axis. Map the pixel coordinates of the two sides at each acquisition time to this coordinate system to form two coordinate points, and construct two curves by connecting them in time sequence; calculate the distance between the pixel coordinates of the two sides at the same acquisition time, and define it as the conveyor belt width; subtract the current actual width from the preset standard width of the conveyor belt to obtain the tightening width value; Define the time range prior to the current moment as the detection time zone; In the coordinate system, set the standard position lines of the two sides; connect the edge coordinates at the current time with the corresponding standard position to form the first line segment; connect the edge coordinates at the start time of the detection time zone with the corresponding standard position to form the second line segment; the area enclosed by the above two line segments, the time series curves of the two sides, and the standard position lines is defined as the offset area, and the sum of its areas is calculated and recorded as the offset surface value. Within the detection time zone, the tightening width value, tightening fluctuation value, and offset surface value are calculated using the mean and variance formulas; The offset position evaluation value is obtained by weighted summing of the current tightening width value, tightening average width value, and tightening fluctuation value; The offset magnitude assessment value is obtained by weighted summing of the current offset surface value, the average offset surface value, and the offset fluctuation value. Obtain the offset position evaluation value and offset magnitude evaluation value of the multi-angle images, and assign an angle importance weight to each angle image; then, perform a weighted sum of the offset position evaluation value and the offset magnitude evaluation value of each angle to obtain the offset evaluation value. The offset evaluation value, offset position evaluation value, offset magnitude evaluation value, tightening width value, tightening average width value, tightening fluctuation value, offset surface value, offset average surface value, and offset fluctuation value are integrated into the offset detection analysis result.

7. The unmanned automatic inspection system for conveyors according to claim 2, characterized in that: The inspection system also includes an environmental analysis unit; The environmental analysis unit is used to acquire environmental data collected by the air monitoring head (10); the environmental data includes dust concentration and harmful gas content; An environmental monitoring time zone is set, and the mean and fluctuation trend values ​​of dust concentration and harmful gas content within the environmental monitoring time zone are calculated using mean and variance formulas and recorded as the dust mean and its fluctuation trend value, and the mean and its fluctuation trend value of each toxic gas, respectively. The dust mean and its fluctuation trend value are weighted to obtain the dust assessment value; the mean and its fluctuation trend value of harmful gases are weighted to obtain the abnormal assessment value of harmful gases; the dust assessment value and the abnormal assessment value of each harmful gas are used as the environmental analysis results.

8. The unmanned automatic inspection system for conveyors according to claim 1, characterized in that: The inspection system also includes an offset detection output module; The offset detection output module is used to receive offset detection analysis results and generate corresponding judgment results, specifically: A set of preset multidimensional offset judgment thresholds is provided, including offset evaluation threshold and offset magnitude threshold. The offset assessment threshold is divided into a severe offset threshold and a slight offset threshold; When the offset assessment value is greater than or equal to the severe offset threshold, or when the offset surface value is greater than the offset amplitude threshold, it indicates that the conveyor belt has obviously deviated or is about to deviate, and an emergency alarm signal is generated. The emergency alarm signal includes the offset detection analysis result, the signal generation time, and the location of the offset on the conveyor belt. If the offset evaluation value is between the severe offset threshold and the slight offset threshold, and the offset surface value is less than the offset amplitude threshold, it is judged to be a slight offset state. When the conveyor belt is in a slight offset state, the offset detection analysis results are stored at a set time interval, and then the stored offset detection analysis results are sent to the display module at a set period. When the offset assessment value is less than the slight offset threshold, it indicates that the conveyor belt is in a stable state and there is no offset phenomenon or it is within the stable offset fluctuation range.

9. The unmanned automatic inspection system for conveyors according to claim 8, characterized in that: The inspection system also includes a display module; the display module is used to display the offset status indicator in color coding in real time; it is also used to display the offset detection analysis results and environmental analysis results; when an emergency alarm signal is received, it automatically switches to a full-screen alarm interface, flashing to display the alarm type, the current offset evaluation value and the position of the conveyor belt.

Images