On-line monitoring device and on-line monitoring method for detecting belt slipping

Abstract

The invention provides an on-line monitoring device and an on-line monitoring method for detecting belt slipping. The on-line monitoring device comprises a millimeter wave radar sensor, a machine vision module, an anti-jumping rocker arm speed measuring mechanism and a central processing unit. The belt speed is directly measured through the millimeter wave radar, meanwhile, the rotating speed of the roller is calculated by analyzing images of the induction strips arranged on the end face of the roller through the machine vision module, and the slip ratio between the belt and the roller is accurately calculated by fusing data of the two sensors; the high anti-interference capability of the millimeter wave radar and the visual accuracy of machine vision are utilized to form advantage complementation, real-time and high-precision online monitoring and early warning of belt slipping are achieved through a data fusion algorithm, and the problems that in the prior art, the system is prone to being affected by the environment and measurement is inaccurate are effectively solved.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of safety monitoring of industrial conveying equipment, and relates to an online monitoring device for detecting belt slip and an online monitoring method. BACKGROUND

[0002] The belt conveyor is a key equipment for continuous bulk material transportation. The slip between the belt and the driving drum is a common fault, which may cause material spilling, reduced transportation efficiency, belt wear, breakage, fire and other serious accidents. Therefore, it is crucial to monitor the belt slip in real time and reliably.

[0003] The existing belt speed measurement technologies mainly include contact type speed measurement such as speed measuring wheels, which have the disadvantages of easy wear and tear, slip, and large error when the belt is not in good contact with the speed measuring wheels. The proximity switch counting type calculates the speed by detecting the sensing sheet on the drum shaft, which has the disadvantages of indirect measurement and inability to reflect the real slip between the belt and the drum, and is susceptible to electromagnetic interference. Single non-contact sensors such as laser speed meters, but their performance decreases sharply in high dust conditions; or ordinary camera visual recognition, but their reliability is low in the case of light changes and dust shielding. These methods have certain limitations and are difficult to achieve continuous, stable, and high-precision monitoring in complex and harsh conditions in the coal industry.

[0004] Therefore, there is an urgent need for a belt slip monitoring solution that can adapt to harsh environments, has strong anti-interference ability, and high measurement accuracy. SUMMARY

[0005] In view of the deficiencies of the prior art, the purpose of the present application is to provide an online monitoring device for detecting belt slip and an online monitoring method, especially a belt slip online monitoring device and method based on millimeter wave radar and machine vision, which is suitable for belt conveyors in coal mines, ports, power plants and other fields. In the present application, the strong anti-interference ability of the millimeter wave radar and the intuitive accuracy of the machine vision are complementary, and through a data fusion algorithm, real-time and high-precision online monitoring and early warning of belt slip are realized, effectively overcoming the problems of the prior art that are susceptible to environmental influences and inaccurate measurement.

[0006] To achieve this purpose, the present application adopts the following technical solutions:

[0007] In a first aspect, the present application provides an online monitoring device for detecting belt slip, which comprises a millimeter wave radar sensor, a machine vision module, a jump-proof swing arm speed measurement mechanism, and a central processing unit.

[0008] The millimeter wave radar sensor is used to emit a frequency-modulated continuous wave to the driving drum or the surface of the belt of the belt conveyor and receive the echo, and to obtain the linear velocity data of the belt through signal processing;

[0009] The machine vision module comprises a camera and a light source, the camera is correspondingly arranged on the induction strip on the end plate of the rotating drum, used to collect image sequences of the rotating drum, and the rotating angular velocity of the drum is calculated through an image processing algorithm;

[0010] The anti-swing arm speed measurement mechanism comprises a speed measurement wheel, a rocker, a rotating shaft and a counterweight, the speed measurement wheel is in contact with the non-material bearing surface of the belt, used to obtain the linear speed reference data of the belt;

[0011] The central processor is electrically connected with the millimeter wave radar sensor, the machine vision module and the anti-swing arm speed measurement mechanism respectively.

[0012] Preferably, the online monitoring device further comprises a communication module electrically connected with the central processor, the communication module is used to remotely transmit the slip warning signal, the speed data and the slip rate to the upper monitoring system.

[0013] Preferably, the central processor adopts an adaptive weighted data fusion algorithm to fuse the speed data measured by the millimeter wave radar sensor and the machine vision module, obtains the final linear speed of the belt, and calculates the slip rate according to the fused linear speed of the belt and the rotating speed of the drum measured by the machine vision, and generates a slip warning signal when the slip rate exceeds a preset threshold.

[0014] Preferably, the central processor fuses the data in the following manner:

[0015] The central processor dynamically adjusts the weight coefficients of the data of the millimeter wave radar sensor and the data of the machine vision module according to the environmental dust concentration, increases the data weight of the millimeter wave radar sensor when the dust concentration is high, and increases the data weight of the machine vision module when the dust concentration is low and the light is good.

[0016] In the second aspect, the present application provides an online monitoring method for detecting belt slip, which adopts the online monitoring device of the first aspect.

[0017] Preferably, the online monitoring method comprises:

[0018] (1) obtaining the linear speed data v1 of the belt through the millimeter wave radar sensor;

[0019] (2) obtaining the rotating angular velocity of the drum through the machine vision module, and calculating the corresponding theoretical linear speed v2 of the belt;

[0020] (3) through the central processor, using an adaptive weighted data fusion algorithm to fuse v1 and v2, obtaining the accurate linear speed v of the belt;

[0021] (4) calculating the real-time slip rate of the belt according to a slip rate formula;

[0022] (5) comparing the slip rate with a preset safety threshold, and triggering a slip warning if the threshold is exceeded.

[0023] Preferably, in step (3), in the data fusion step, the weight coefficient of the adaptive weighted data fusion algorithm is dynamically adjusted according to the real-time monitored environmental dust concentration and image definition.

[0024] Preferably, in step (4), the slip rate formula is: η = (v-v2) / v x 100%.

[0025] Preferably, in step (5), the preset safety threshold is not more than 1.5%, for example, it can be 1.5%, 1.2%, 1%, 0.8%, 0.6%, 0.5%, etc., but is not limited to the listed values, and other values not listed in this range are also applicable.

[0026] Preferably, the online monitoring method specifically comprises:

[0027] (1) obtaining the linear velocity data v1 of the belt through a millimeter wave radar sensor;

[0028] (2) obtaining the angular velocity of the drum rotation through a machine vision module, and calculating the corresponding theoretical linear velocity v2 of the belt;

[0029] (3) through a central processing unit, using an adaptive weighted data fusion algorithm to perform data fusion on v1 and v2 to obtain the accurate linear velocity v of the belt;

[0030] (4) calculating the real-time slip rate of the belt according to a slip rate formula;

[0031] (5) comparing the slip rate with a preset safety threshold, and triggering a slip warning if the threshold is exceeded.

[0032] In step (3), in the data fusion step, the weight coefficient of the adaptive weighted data fusion algorithm is dynamically adjusted according to the real-time monitored environmental dust concentration and image definition.

[0033] In step (4), the slip rate formula is: η = (v-v2) / v x 100%.

[0034] In step (5), the preset safety threshold is not more than 1.5%.

[0035] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present application, nor to limit the scope of the present application. Other features of the present application will become apparent through the following description.

[0036] Compared with the prior art, the present application has the following advantages:

[0037] The present application provides a high-precision, environmentally adaptable and reliable online monitoring device for belt slip based on multi-sensor fusion, which significantly reduces the random error and systematic error of a single sensor through mutual verification and compensation of multi-sensor data fusion; the millimeter wave radar has strong anti-interference ability, and the machine vision is intuitive and accurate, and the combination of the two ensures the stable operation of the device in complex working conditions such as high dust and strong interference in the coal industry; the redundant design allows the system to rely on other sensors for degraded operation when a sensor fails, while issuing a fault alarm, ensuring the continuity of monitoring; it can calculate the slip rate in real time and issue an early warning at the initial stage of slip, which wins time for taking measures and effectively avoids accidents. BRIEF DESCRIPTION OF DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0039] Figure 1 The structure diagram of the online monitoring device for detecting belt slip is provided for a specific embodiment of the present application;

[0040] Figure 2 The flowchart of the millimeter wave radar speed measurement principle in the present application;

[0041] Figure 3 The software algorithm flowchart of the machine vision module calculating the drum speed in the present application;

[0042] Figure 4 The core algorithm flowchart of the central processor for data fusion and slip judgment in the present application;

[0043] Among them, 1 is the upper layer belt (material bearing surface) of the belt conveyor, 2 is the movable drum, 3 is the millimeter wave radar sensor, 4 is the camera, 5 is the induction strip, 6 is the anti-jumping rocker arm speed measurement mechanism, 7 is the speed measurement wheel, and 8 is the central processor. DETAILED DESCRIPTION

[0044] In the following, the technical solutions in the embodiments of the present application will be described clearly and completely in combination with the accompanying drawings in the embodiments of the present application, so that those skilled in the art can better understand the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work should fall within the protection scope of the present application.

[0045] It should be noted that the terms "first", "second" and the like in the description of the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or a chronological sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not necessarily have to include those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to the process, method, product or device.

[0046] It should be noted that in the description of the present application, unless otherwise explicitly specified and limited, the terms "set", "connected", "connected" should be understood broadly, for example, it can be fixedly connected, or it can be detachably connected, or integrally connected; it can be mechanically connected, or it can be electrically connected; it can be directly connected, or it can be indirectly connected through an intermediate medium, or it can be connected inside two elements. For those skilled in the art, the specific meaning of the above-mentioned terms in the present application can be understood through specific circumstances.

[0047] The technical solutions of the present application will be further illustrated in combination with the accompanying drawings and through specific embodiments.

[0048] In one specific embodiment, the present application provides an online monitoring device for detecting belt slip, such as Figure 1As shown, the online monitoring device includes a millimeter wave radar sensor 3, a machine vision module, an anti-bounce rocker speed measurement mechanism 6, and a central processor 8; the millimeter wave radar sensor 3 is used to emit frequency-modulated continuous waves to the moving drum 2 or the belt surface of the belt conveyor and receive echoes, and through signal processing, the linear speed data of the belt is obtained; the machine vision module includes a camera 4 and a light source, the camera 4 is correspondingly arranged on the inductive strip 5 on the end plate of the moving drum 2, used to collect image sequences of the drum rotation, and the rotational angular velocity of the drum is calculated through an image processing algorithm; the anti-bounce rocker speed measurement mechanism 6 includes a speed measurement wheel 7, a rocker, a rotating shaft, and a counterweight, the speed measurement wheel 7 is in contact with the non-material bearing surface of the belt, used to obtain the linear speed reference data of the belt; the central processor 8 is electrically connected with the millimeter wave radar sensor 3, the machine vision module, and the anti-bounce rocker speed measurement mechanism 6 respectively.

[0049] As shown in the formula (1), the belt surface of the belt conveyor can be represented as the upper belt (material bearing surface) 1 of the belt conveyor.

[0050] As shown in the formula (1), the belt surface of the belt conveyor can be represented as the upper belt (material bearing surface) 1 of the belt conveyor. Figure 2 As shown in the formula (1), the belt surface of the belt conveyor can be represented as the upper belt (material bearing surface) 1 of the belt conveyor. As shown in the formula (1), the belt surface of the belt conveyor can be represented as the upper belt (material bearing surface) 1 of the belt conveyor.

[0051] As shown in the formula (1), the belt surface of the belt conveyor can be represented as the upper belt (material bearing surface) 1 of the belt conveyor. Figure 3 As shown in the formula (1), the belt surface of the belt conveyor can be represented as the upper belt (material bearing surface) 1 of the belt conveyor.

[0052] As shown in the formula (1), the belt surface of the belt conveyor can be represented as the upper belt (material bearing surface) 1 of the belt conveyor. Figure 4 As shown in the formula (1), the belt surface of the belt conveyor can be represented as the upper belt (material bearing surface) 1 of the belt conveyor.

[0053] It should be noted that the millimeter wave radar sensor 3 in the application is installed on the side of the driving drum 2, directly measures the running linear speed of the belt based on the principle of Doppler effect, has good penetration, is less affected by dust, smoke and light changes, and can work stably in harsh environments; the machine vision module includes a high-speed industrial camera and an auxiliary light source, the camera 4 is aligned and installed on a specific sensing strip 5 (such as a reflective strip) on the drum end plate, the position change of the sensing strip 5 in the continuous image sequence is analyzed, the rotational angular velocity of the drum is accurately calculated, and then the theoretical linear speed of the belt is converted; the anti-jumping rocker arm speed measurement mechanism 6 serves as an auxiliary and backup speed measurement unit, the speed measurement wheel 7 thereof is always in good contact with the non-material bearing surface of the belt under the action of the counterweight, and provides a direct speed reference; the central processor 8 is the core of the system, is responsible for receiving and processing all sensor data, and adopts an adaptive weighted data fusion algorithm, which is not a simple data average, but dynamically allocates the weights of the millimeter wave radar data and the machine vision data according to real-time environmental parameters (such as dust concentration and environmental illumination derived from image clarity). For example, when the dust is large and the image quality is poor, the millimeter wave radar data is given a higher weight; when the environment is clear, the vision data is trusted more. Finally, the fused high-precision belt linear speed is output, and compared with the theoretical linear speed of the drum measured by the vision, the slip rate is calculated in real time.

[0054] It should be noted that the millimeter wave radar sensor 3 in the application is installed on the side of the driving drum 2, directly measures the running linear speed of the belt based on the principle of Doppler effect, has good penetration, is less affected by dust, smoke and light changes, and can work stably in harsh environments; the machine vision module includes a high-speed industrial camera and an auxiliary light source, the camera 4 is aligned and installed on a specific sensing strip 5 (such as a reflective strip) on the drum end plate, the position change of the sensing strip 5 in the continuous image sequence is analyzed, the rotational angular velocity of the drum is accurately calculated, and then the theoretical linear speed of the belt is converted; the anti-jumping rocker arm speed measurement mechanism 6 serves as an auxiliary and backup speed measurement unit, the speed measurement wheel 7 thereof is always in good contact with the non-material bearing surface of the belt under the action of the counterweight, and provides a direct speed reference; the central processor 8 is the core of the system, is responsible for receiving and processing all sensor data, and adopts an adaptive weighted data fusion algorithm, which is not a simple data average, but dynamically allocates the weights of the millimeter wave radar data and the machine vision data according to real-time environmental parameters (such as dust concentration and environmental illumination derived from image clarity). For example, when the dust is large and the image quality is poor, the millimeter wave radar data is given a higher weight; when the environment is clear, the vision data is trusted more. Finally, the fused high-precision belt linear speed is output, and compared with the theoretical linear speed of the drum measured by the vision, the slip rate is calculated in real time.

[0055] In some embodiments, the on-line monitoring device further comprises a communication module electrically connected to the central processor 8, and the communication module is used for remotely transmitting the slip warning signal, the speed data and the slip rate to an upper monitoring system.

[0056] In some embodiments, the central processor 8 adopts an adaptive weighted data fusion algorithm to fuse the speed data measured by the millimeter wave radar sensor 3 and the machine vision module, obtains the final linear speed of the belt, calculates the slip rate according to the fused belt linear speed and the drum rotational speed measured by the machine vision, and generates a slip warning signal when the slip rate exceeds a preset threshold.

[0057] In some embodiments, the central processor 8 fuses the data in the following manner:

[0058] The central processor 8 dynamically adjusts the weight coefficient of the data of the millimeter wave radar sensor 3 and the data of the machine vision module according to the environmental dust concentration. When the dust concentration is high, the data weight of the millimeter wave radar sensor 3 is increased. When the dust concentration is low and the light is good, the data weight of the machine vision module is increased.

[0059] In one specific embodiment, the present application provides an online monitoring method for detecting belt slip, which is carried out by using the online monitoring device described above. The online monitoring method comprises:

[0060] (1) The line speed data v1 of the belt is obtained by the millimeter wave radar sensor 3;

[0061] (2) The rotational angular velocity of the drum is obtained by the machine vision module, and the corresponding theoretical line speed v2 of the belt is calculated;

[0062] (3) The data of v1 and v2 are fused by the central processor 8 using an adaptive weighted data fusion algorithm to obtain the accurate line speed v of the belt;

[0063] (4) The real-time slip rate of the belt is calculated according to the slip rate formula;

[0064] (5) The slip rate is compared with the preset safety threshold value. If the threshold value is exceeded, the slip warning is triggered.

[0065] In some embodiments, in step (3), in the data fusion step, the weight coefficient of the adaptive weighted data fusion algorithm is dynamically adjusted according to the real-time monitored environmental dust concentration and image clarity.

[0066] In some embodiments, in step (4), the slip rate formula is: η=(v-v2) / v×100%.

[0067] In some embodiments, in step (5), the preset safety threshold value is not more than 1.5%, for example, it can be 1.5%, 1.2%, 1%, 0.8%, 0.6%, 0.5%, etc., but it is not limited to the listed values. Other values not listed in this range are also applicable.

[0068] It should be noted that the working process of the online monitoring device in the present application can include:

[0069] Data acquisition: each sensor starts data acquisition synchronously.

[0070] Signal processing: the millimeter wave radar performs FFT processing on the intermediate frequency signal, extracts the Doppler frequency and calculates the speed v1. The machine vision module pre-processes the collected images, extracts features (recognizes the sensing strip 5), calculates the drum angular velocity by the displacement of the sensing strip 5 between consecutive frames, and converts it into the theoretical speed v2 of the belt.

[0071] Data fusion: the central processor 8 reads the environmental sensor data (or indirectly judges the environmental condition through image definition), dynamically determines the weights w1 and w2 (w1+w2=1) of v1 and v2 according to the preset weight model, and calculates the fusion speed v = w1×v2 + w2×v2.

[0072] Slip judgment and early warning: the slip rate η is calculated according to the formula, and if η exceeds the set threshold value (such as 1.5%) for many times in succession, it is judged as slip, and the sound and light alarm is triggered and the monitoring center is reported through the communication module.

[0073] Embodiment 1

[0074] The embodiment provides an online monitoring device for detecting belt slip, wherein:

[0075] The online monitoring device comprises a millimeter wave radar sensor 3, a machine vision module, a skip-resistant rocker arm speed measurement mechanism 6 and a central processor 8; the millimeter wave radar sensor 3 is used for transmitting frequency-modulated continuous wave to the dynamic drum 2 or the belt surface of the belt conveyor and receiving the echo, and the linear speed data of the belt is obtained through signal processing; the machine vision module comprises a camera 4 and a light source, the camera 4 is correspondingly arranged on the induction strip 5 on the end plate of the dynamic drum 2, and is used for collecting image sequences of the drum rotation and calculating the angular velocity of the drum rotation through image processing algorithm; the skip-resistant rocker arm speed measurement mechanism 6 comprises a speed measurement wheel 7, a rocker, a rotating shaft and a counterweight, the speed measurement wheel 7 is in contact with the non-material bearing surface of the belt, and is used for obtaining the linear speed reference data of the belt; and the central processor 8 is electrically connected with the millimeter wave radar sensor 3, the machine vision module and the skip-resistant rocker arm speed measurement mechanism 6 respectively.

[0076] The online monitoring device further comprises a communication module, the communication module is electrically connected with the central processor 8, and the communication module is used for remotely transmitting the slip early warning signal, the speed data and the slip rate to the upper monitoring system.

[0077] The central processor 8 adopts an adaptive weighted data fusion algorithm to fuse the speed data measured by the millimeter wave radar sensor 3 and the machine vision module, obtains the final linear speed of the belt, and calculates the slip rate according to the fused linear speed of the belt and the drum rotating speed measured by the machine vision, and generates a slip early warning signal when the slip rate exceeds a preset threshold value.

[0078] The central processor 8 fuses the data in the following manner: the central processor 8 dynamically adjusts the weight coefficients of the data of the millimeter wave radar sensor 3 and the data of the machine vision module according to the environmental dust concentration, increases the data weight of the millimeter wave radar sensor 3 when the dust concentration is high, and increases the data weight of the machine vision module when the dust concentration is low and the light is good.

[0079] The online monitoring method of the online monitoring device in the embodiment comprises:

[0080] (1) Obtain the linear velocity data v1 of the belt through millimeter-wave radar sensor 3;

[0081] (2) Obtain the rotational angular velocity of the roller through the machine vision module and calculate the corresponding theoretical linear velocity v2 of the belt;

[0082] (3) The central processing unit 8 uses an adaptive weighted data fusion algorithm to fuse v1 and v2 to obtain the precise linear velocity v of the belt;

[0083] (4) Calculate the real-time slip rate of the belt according to the slip rate formula;

[0084] (5) Compare the slip rate with the preset safety threshold. If the threshold is exceeded, a slip warning will be triggered.

[0085] Taking a coal mine belt conveyor as an example, the slippage warning threshold is set at 1.5%. When the system detects that the slippage rate exceeds 1.5% for 3 consecutive seconds, the central processing unit 8 immediately generates a first-level warning signal; if the slippage rate further increases to 5%, a second-level severe alarm signal is generated, and the control system can be linked to take measures such as reducing the load or shutting down the machine.

[0086] This invention, through the creative combination of millimeter-wave radar and machine vision, effectively solves the problem of accurate monitoring of belt slippage in complex industrial environments, and has significant practical significance and application value.

[0087] In summary, this invention provides an online monitoring device for conveyor belt slippage based on multi-sensor fusion, characterized by high measurement accuracy, good environmental adaptability, and strong reliability. Through multi-sensor data fusion and mutual verification and compensation, the random and systematic errors of individual sensors are significantly reduced. Millimeter-wave radar offers strong anti-interference capabilities, while machine vision provides intuitive and accurate data; the combination of these two ensures stable operation of the device under complex conditions such as high dust and strong interference in the coal industry. Redundant design allows the system to rely on other sensors for degraded operation when one sensor fails, while simultaneously issuing a fault alarm, ensuring continuous monitoring. It can calculate the slip rate in real time and issue timely warnings at the initial stage of slippage, buying time for corrective measures and effectively preventing the accident from escalating.

[0088] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. An on-line monitoring device for detecting belt slip, characterized in that The online monitoring device comprises a millimeter wave radar sensor, a machine vision module, an anti-bounce rocker speed measurement mechanism and a central processor. The millimeter wave radar sensor is used for transmitting frequency-modulated continuous waves to the moving drum or the belt surface of the belt conveyor and receiving echoes, and obtaining linear speed data of the belt through signal processing. The machine vision module comprises a camera and a light source, the camera is correspondingly arranged on an inductive strip on the end plate of the moving drum, is used for collecting image sequences of the rotation of the drum, and calculates the angular velocity of the rotation of the drum through an image processing algorithm. The anti-bounce rocker speed measurement mechanism comprises a speed measurement wheel, a rocker, a rotating shaft and a counterweight, the speed measurement wheel is in contact with the non-material bearing surface of the belt, and is used for obtaining reference data of the linear speed of the belt. The central processor is electrically connected with the millimeter wave radar sensor, the machine vision module and the anti-bounce rocker speed measurement mechanism respectively.

2. The on-line monitoring device according to claim 1, characterized in that The online monitoring device further comprises a communication module, the communication module is electrically connected with the central processor, and the communication module is used for remotely transmitting a slip warning signal, speed data and a slip rate to an upper monitoring system.

3. An online monitoring device according to claim 1 or 2, characterised in that, The central processor adopts an adaptive weighted data fusion algorithm to fuse the speed data measured by the millimeter wave radar sensor and the machine vision module, obtains the final linear speed of the belt, and calculates the slip rate according to the fused linear speed of the belt and the drum rotating speed measured by the machine vision, and generates a slip warning signal when the slip rate exceeds a preset threshold.

4. An on-line monitoring device according to claim 3, characterised in that, The central processor fuses data in the following manner: The central processor dynamically adjusts the weight coefficients of the data of the millimeter wave radar sensor and the data of the machine vision module according to the environmental dust concentration, increases the data weight of the millimeter wave radar sensor when the dust concentration is high, and increases the data weight of the machine vision module when the dust concentration is low and the light is good.

5. An on-line monitoring method of detecting belt slip, characterized by, The online monitoring method is performed by using the online monitoring device in any one of claims 1-4.

6. The on-line monitoring method according to claim 5, characterized in that, The online monitoring method comprises: (1) obtaining linear speed data v1 of the belt through the millimeter wave radar sensor; (2) obtaining the angular velocity of the rotation of the drum through the machine vision module, and calculating the corresponding theoretical linear speed v2 of the belt; (3) using an adaptive weighted data fusion algorithm to fuse v1 and v2 through the central processor, and obtaining the accurate linear speed v of the belt; (4) calculating the real-time slip rate of the belt according to a slip rate formula; (5) comparing the slip rate with a preset safety threshold, and triggering a slip warning if the threshold is exceeded.

7. The on-line monitoring method according to claim 6, characterized in that, In the data fusion step in step (3), the weight coefficient of the adaptive weighted data fusion algorithm is dynamically adjusted according to the real-time monitored environmental dust concentration and image clarity.

8. The on-line monitoring method according to claim 6 or 7, characterized in that In step (4), the slip rate formula is: η=(v-v2) / v×100%.

9. The on-line monitoring method according to any one of claims 6-8, characterized in that, In step (5), the preset safety threshold is not more than 1.5%.

10. The on-line monitoring method according to claim 6, characterized in that, The online monitoring method specifically comprises: (1) obtaining linear speed data v1 of the belt through the millimeter wave radar sensor; (2) obtaining the angular velocity of the rotation of the drum through the machine vision module, and calculating the corresponding theoretical linear speed v2 of the belt; (3) Through the central processing unit, the adaptive weighted data fusion algorithm is used to perform data fusion on v1 and v2 to obtain the accurate linear speed v of the belt; (4) The real-time slip rate of the belt is calculated according to a slip rate formula; (5) The slip rate is compared with a preset safety threshold value, and if the slip rate exceeds the threshold value, a slip warning is triggered; In step (3), in the data fusion step, the weight coefficient of the adaptive weighted data fusion algorithm is dynamically adjusted according to the real-time monitored environmental dust concentration and image definition; In step (4), the slip rate formula is: η = (v-v2) / v x 100%; In step (5), the preset safety threshold value is not more than 1.5%.

Images