Machine learning based monitoring method and system for wind-induced vibration of a suspension belt conveyor

Abstract

The application discloses a wind vibration monitoring method and system for a suspension belt conveyor based on machine learning, and relates to the field of intelligent monitoring of belt conveyors. The application is based on wind vibration observation and prediction of a suspension cable span inner marker post by high-definition cameras and various sensors, and plays an important auxiliary role in ensuring the safe operation, danger early warning and emergency control of the suspension belt conveyor during conveying work. The application can realize less-person monitoring, reduce operation and maintenance costs, improve the intelligent degree of the suspension belt conveyor, and improve the automation degree and accuracy of the monitoring process, thereby ensuring the safe operation of the suspension belt conveyor under wind vibration conditions.

Description

Technical Field

[0001] This invention relates to the field of intelligent monitoring of belt conveyors, specifically to a method and system for monitoring wind vibration of suspension belt conveyors based on machine learning. Background Technology

[0002] The statements in this section are provided only as background information in connection with this disclosure and may not constitute prior art.

[0003] In regions of my country with harsh terrain, the transportation of materials such as ores typically employs curved belt conveyors or circular tube belt conveyors. Regardless of the method used, the layout of the conveyor lines is extremely difficult, inevitably requiring the use of very tall support towers and large-span trusses, and may also involve the excavation of tunnels and the construction of bridges.

[0004] For situations with complex terrain, there is also a suspension belt conveyor solution. However, during the conveying process, the suspension cables of this type of conveyor will experience pendulum-like displacement due to factors such as material, belt tension, wind, rain, and snow. Because its structure differs from conventional belt conveyors, there is no readily available monitoring system, and excessive displacement may lead to abnormal situations such as material spillage and changes in structural stress. These potential hazards not only affect the normal operation of the belt conveyor but may also cause economic losses or even safety accidents in severe cases.

[0005] Machine learning technology, with its powerful nonlinear fitting capabilities, constructs a mapping relationship between input and output, enabling the analysis and prediction of multiple factors and outcomes. The development of machine learning technology has broadened the application scenarios of intelligent monitoring and provided a theoretical basis for wind vibration monitoring of cable-stayed conveyors. Summary of the Invention

[0006] The purpose of this invention is to provide a machine learning-based method and system for monitoring wind-induced vibration of cable-stayed conveyors, addressing the problems existing in the prior art and solving the problem of intelligent monitoring of wind-induced vibration in cable-stayed conveyors.

[0007] The technical solution of the present invention is as follows:

[0008] A machine learning-based method for monitoring wind-induced vibration in cable-stayed belt conveyors includes:

[0009] Step S1: Data Acquisition and Transmission; Automated acquisition of video, environmental data, and suspension belt conveyor operation data with target detection benchmarks, and chronological storage and transmission; Real-time transmission to the local server, with remote servers retrieving time-axis data as needed;

[0010] Step S2: Image correction and data processing; determine the video frame interval and extract the time-series data corresponding to the video frame; calibrate the camera's intrinsic parameters and measure the extrinsic parameters in real time to complete the correction of the video frame; preprocess the obtained data segments to obtain time-domain features and time-frequency domain features;

[0011] Step S3: Model Establishment and Mapping Construction; Establish a target detection model and obtain the distance to the benchmark and the wind vibration offset at the benchmark; Establish a wind vibration prediction model based on the collected data and the real-time detection results of the suspension belt conveyor; Construct the mapping relationship between the wind vibration data at the benchmark and the wind vibration data at the point of maximum wind vibration;

[0012] Step S4: Automatic monitoring and early warning; real-time acquisition of wind vibration data calculated by the target detection model and comparison with wind vibration threshold analysis; before reaching the wind vibration anomaly time point predicted by the deep learning model, timely notification to maintenance personnel or intervention to control the suspension belt conveyor to decelerate or stop.

[0013] Furthermore, the target detection marker is a long strip mark that needs to be set to a fixed length according to the detection distance, and its color should be different from the environment color. It is placed horizontally in a certain span of the suspension belt conveyor.

[0014] Furthermore, the required length or width of the target detection benchmark is selected according to the following formula:

[0015]

[0016] in:

[0017] l represents the length of the target detection benchmark;

[0018] α represents the percentage of the screen occupied by the benchmark.

[0019] f is the focal length;

[0020] w cam This is the actual width of the camera image sensor.

[0021] D represents the expected distance between the benchmark and the camera.

[0022] Further, step S1 includes:

[0023] Step S1-1: Acquire video data of the suspension belt conveyor with target detection benchmarks using a camera and transmit it;

[0024] Steps S1-2: Obtain wind direction and speed data through an anemometer and store them in chronological order; obtain wind and rain load information through a rain and snow sensor and store and transmit it in chronological order.

[0025] Steps S1-3: Obtain vibration data of the suspension belt conveyor through vibration sensors and store it in chronological order; obtain the belt speed of the conveyor through a tachometer and store and transmit it in chronological order.

[0026] Further, step S2 includes:

[0027] Step S2-1: Select an appropriate video frame interval based on the number of frames in the monitoring video; extract the data collected from the anemometer, rain and snow sensor, vibration sensor and tachometer into time-series segments, corresponding to the time interval of the video frames;

[0028] Step S2-2: Measure the intrinsic parameters of the camera by obtaining the focal length, pixel size, principal coordinates of the optical axis, and camera distortion parameters using the Zhang Zhengyou calibration method; and measure the extrinsic parameters of the camera in real time, namely the rotation matrix and translation matrix.

[0029] Step S2-3: Preprocess the extracted time series data. Obtain the time-frequency characteristics of the anemometer, rain and snow sensor and tachometer, and obtain the time-frequency domain characteristics of the vibration sensor.

[0030] Further, step S3 includes:

[0031] Step S3-1: Establish an object detection model and train it based on the benchmark dataset; input video frames into the model to obtain the benchmark distance and wind vibration offset at the benchmark.

[0032] Step S3-2: Based on the time series data of wind direction and speed, rain and snow load, and operation of the suspension belt conveyor, establish and train the wind vibration prediction model until the evaluation indicators meet the requirements;

[0033] Step S3-3: Based on the coordinates of the two towers and the benchmark, construct the theoretical maximum wind vibration location coordinates of the suspended cable conveyor and the mapping relationship between its wind vibration data and the wind vibration data at the benchmark.

[0034] Further, step S4 includes:

[0035] Step S4-1: Establish an autonomous monitoring algorithm to receive video data in real time; use the target detection model to calculate the theoretical maximum wind vibration location coordinates and wind vibration data, and compare and analyze them with the danger judgment threshold to judge wind vibration anomalies in real time.

[0036] Step S4-2: Receive environmental conditions and suspension belt conveyor operation data in real time, predict and calculate the critical time points of wind-induced vibration and their wind-induced vibration data;

[0037] Step S4-3: Construct an automated early warning and control system; when wind-induced vibration abnormalities are observed or predicted, the early warning control function is automatically activated, and early warning information is pushed to the on-duty personnel. In case of emergency, the system intervenes in the conveyor control system to reduce speed or stop the machine.

[0038] This invention also proposes a machine learning-based wind vibration monitoring system for cable-stayed conveyors, used to implement the aforementioned wind vibration monitoring method for cable-stayed conveyors, including:

[0039] Data acquisition module, information processing module, wind vibration monitoring module, and early warning and control module;

[0040] The data acquisition module includes: an anemometer, a rain and snow sensor, a high-definition camera, a vibration sensor, and a tachometer; it is used to collect on-site environmental data such as wind, rain, and snow, video with a benchmark, and operating data of the suspension belt conveyor, and transmit the data to the information processing module.

[0041] The information processing module includes: a lens distortion correction algorithm, a fast Fourier transform algorithm, a time-domain feature extraction method, and a time-frequency domain feature extraction method; it is used to process various types of data transmitted from the data acquisition module and transmit the data to the wind vibration monitoring module.

[0042] The wind vibration monitoring module includes: machine vision algorithm, distance offset algorithm, wind vibration prediction algorithm, and maximum wind vibration calculation method; it is used to receive various types of data transmitted by the data acquisition module, establish and train the model; observe and predict the wind vibration data and abnormal time points of the suspension belt conveyor, and transmit the data to the early warning control module.

[0043] The early warning control module includes: an autonomous monitoring algorithm, an alarm push device, an automatic control algorithm, and a control linkage system; it is used to receive wind vibration data transmitted by the wind vibration monitoring module, monitor the operation of the suspension belt conveyor in real time, and realize autonomous monitoring and early warning.

[0044] Furthermore, the machine vision algorithm is used to identify the benchmark and obtain its position information in the image; the ranging and offset algorithm is used to calculate the distance from the benchmark to the camera and obtain the wind vibration offset of the benchmark relative to its static position; the wind vibration prediction algorithm is used to predict the future wind vibration data of the benchmark under the current data and obtain the critical time point; the maximum wind vibration calculation method is used to calculate the position information of the benchmark across the maximum wind vibration point and the wind vibration data.

[0045] Furthermore, the autonomous monitoring algorithm is used to monitor the operating status of the suspension belt conveyor in real time and determine whether the wind vibration data of the suspension belt conveyor exceeds the threshold; the automatic control algorithm is used to activate the early warning equipment, remind the on-duty personnel to reduce the conveying volume, slow down or stop the machine in an emergency, and intervene to control the suspension belt conveyor in an emergency.

[0046] Compared with existing technologies, the advantages of this invention are:

[0047] 1. This invention uses high-definition cameras and various sensors to observe and predict wind vibration of the inner span of the suspension bridge, which plays an important auxiliary role in ensuring the safe operation, hazard warning and emergency control of the suspension belt conveyor during the conveying process.

[0048] 2. This invention achieves less-manned monitoring and reduces operation and maintenance costs by using an anemometer, rain and snow sensor, high-definition camera, vibration sensor and tachometer to ensure real-time acquisition of the operating conditions and data of the suspension belt conveyor.

[0049] 3. This invention realizes real-time analysis of wind vibration data of suspension belt conveyors and predicts the time point of wind vibration anomalies by using machine vision algorithm, distance offset algorithm, wind vibration prediction algorithm and maximum wind vibration calculation method, thereby improving the intelligence level of suspension belt conveyors.

[0050] 4. This invention achieves real-time monitoring of the operation of the suspension belt conveyor through autonomous monitoring algorithms, automatic control algorithms, and alarm push devices, and can provide timely early warning and emergency control in case of wind vibration abnormalities, thereby improving the automation and intelligence of the monitoring process. Attached Figure Description

[0051] Figure 1 This is a flowchart of a machine learning-based method for monitoring wind vibration in a cable-stayed conveyor, as proposed in this invention.

[0052] Figure 2 This invention presents a machine learning-based wind vibration monitoring system for a suspension belt conveyor, and provides a structural diagram for implementing the wind vibration monitoring method.

[0053] Figure 3 This is a schematic diagram of the implementation layout of a suspension belt conveyor wind vibration monitoring system based on machine learning proposed in this invention;

[0054] Figure 4 This is a schematic diagram of the camera arrangement in the suspension belt conveyor wind vibration monitoring system of the present invention;

[0055] Figure 5 This is a benchmark of the suspension belt conveyor wind vibration monitoring system of the present invention, as shown in the schematic diagram of the video frame;

[0056] Figure 6 This is a schematic diagram showing the wind vibration offset between the current position of the benchmark and the marked position in the wind vibration monitoring system for the suspension belt conveyor of the present invention.

[0057] in, Figures 3 to 4 The correspondence between the reference numerals and component names in the attached drawings is as follows:

[0058] 1-Steel wire rope; 2-Suspension frame; 3-Idler roller assembly; 4-Cable tower; 5-Target detection benchmark; 6-Camera. Detailed Implementation

[0059] It should be noted that relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0060] The features and performance of the present invention will be further described in detail below with reference to embodiments.

[0061] Example 1

[0062] This invention provides a machine learning-based method for monitoring wind-induced vibration in cable-stayed conveyors, such as... Figure 1 ,include:

[0063] Step S1: Data Acquisition and Transmission. Automated acquisition of video with target detection benchmarks, environmental data such as wind, rain, and snow, and operational data of the suspension belt conveyor are stored and transmitted sequentially in chronological order.

[0064] Step S1 specifically includes:

[0065] Step S1-1: Acquire and transmit video data of the suspension belt conveyor with target detection benchmarks via camera.

[0066] Steps S1-2: Obtain wind direction and speed data through an anemometer and store them in chronological order; obtain wind and rain load information through a rain and snow sensor and store and transmit it in chronological order.

[0067] Steps S1-3: Obtain vibration data of the suspension belt conveyor through vibration sensors and store it in chronological order; obtain the belt speed of the conveyor through a tachometer and store and transmit it in chronological order.

[0068] Step S2: Image Correction and Data Processing. Determine the video frame interval and extract the time-series data corresponding to the video frames; calibrate the camera's intrinsic parameters and measure the extrinsic parameters in real time to complete the correction of the video frames; preprocess the obtained data segments to obtain temporal and time-frequency domain features.

[0069] Step S2 specifically includes:

[0070] Step S2-1: Select an appropriate video frame interval based on the number of frames in the monitoring video; extract the data collected from the anemometer, rain and snow sensor, vibration sensor and tachometer into time-series segments, corresponding to the time interval of the video frames.

[0071] Step S2-2: Measure the intrinsic parameters of the camera by obtaining the focal length, pixel size, principal coordinates of the optical axis, and camera distortion parameters using the Zhang Zhengyou calibration method; and measure the extrinsic parameters of the camera in real time, namely the rotation matrix and translation matrix.

[0072] Step S2-3: Preprocess the extracted time-series data. Obtain the time-domain characteristics of the anemometer, rain and snow sensor, and tachometer, and obtain the time-frequency domain characteristics of the vibration sensor.

[0073] Step S3: Factor Analysis and Wind Vibration Prediction. A deep learning model is established to integrate wind vibration data with factors such as wind direction and speed, rain and snow load, and operating data of the cable-stayed conveyor. Based on this model, the time points and abnormal wind vibration data of the cable-stayed conveyor are predicted.

[0074] Step S3 specifically includes:

[0075] Step S3-1: Establish an object detection model and train it based on the benchmark dataset; input video frames into the model to obtain the benchmark distance and wind vibration offset at the benchmark.

[0076] Step S3-2: Based on the time series data of wind direction and speed, rain and snow load, and operation of the suspension belt conveyor, establish and train the wind vibration prediction model until the evaluation indicators meet the requirements.

[0077] Step S3-3: Based on the coordinates of the two towers and the benchmark, construct the theoretical maximum wind vibration location coordinates of the suspended cable conveyor and the mapping relationship between its wind vibration data and the wind vibration data at the benchmark.

[0078] Step S4: Automatic monitoring and early warning. Real-time acquisition of wind vibration data calculated by the model and comparison with wind vibration threshold analysis; timely notification of maintenance personnel or intervention to control the suspension belt conveyor to slow down or stop before the abnormal wind vibration time point.

[0079] Step S4 specifically includes:

[0080] Step S4-1: Establish an autonomous monitoring algorithm to receive video data in real time; use the target detection model to calculate the theoretical maximum wind vibration location coordinates and wind vibration data, and compare and analyze them with the danger judgment threshold to judge wind vibration anomalies in real time.

[0081] Step S4-2: Receive environmental conditions and suspension belt conveyor operation data in real time, predict and calculate the critical time points of wind-induced vibration and their wind-induced vibration data.

[0082] Step S4-3: Construct an automated early warning and control system. When abnormal wind vibration is observed or predicted, the early warning control function is automatically activated, and early warning information is pushed to the on-duty personnel. In case of emergency, the system intervenes in the conveyor control system to reduce speed or stop the machine.

[0083] This invention provides a machine learning-based wind vibration monitoring system for cable-stayed conveyors, such as... Figure 2 It includes: a data acquisition module, an information processing module, a wind vibration monitoring module, and an early warning and control module.

[0084] The data acquisition module is used to collect on-site environmental data such as wind, rain, and snow, video with benchmarks, and operating data of the suspension belt conveyor. Specifically, it includes: an anemometer, rain and snow sensor, high-definition camera, vibration sensor, tachometer, and benchmarks.

[0085] The information processing module is used to process environmental data such as wind, rain, and snow on site, video with benchmarks, and operating data of the suspension belt conveyor. Specifically, it includes: lens distortion correction, fast Fourier transform, time-domain feature extraction, and time-frequency domain feature extraction.

[0086] The wind vibration monitoring module is used to receive various types of data transmitted by the data acquisition module, and to observe and predict the wind vibration data and abnormal time points of the suspension belt conveyor in real time. Specifically, it includes: machine vision algorithm, distance offset algorithm, wind vibration prediction algorithm, and maximum wind vibration calculation method.

[0087] The early warning control module is used to receive wind vibration data transmitted by the wind vibration monitoring module, monitor and judge the safe operation of the suspension belt conveyor in real time, and take corresponding early warning or control actions, specifically including: autonomous monitoring algorithm, alarm push device, and automatic control algorithm.

[0088] In specific implementations of this invention, the machine vision algorithm prioritizes the target detection algorithm based on the YOLO model of deep learning; the wind vibration prediction algorithm prioritizes the Long Short-Term Memory Network (LSTM) or Gated Recurrent Unit (GRU) suitable for time-series data.

[0089] The specific implementation of the ranging offset algorithm includes:

[0090] Distance from camera to the target plane:

[0091] Distance from the marker to the center of the image in the x direction:

[0092] Distance in the y-direction from the marker to the center of the image:

[0093]

[0094] In the formula: f is the focal length in millimeters; dx is the actual length of the image sensor per pixel in the x-direction in millimeters / pixel; dy is the actual length of the image sensor per pixel in the y-direction in millimeters / pixel; cx and cy are the coordinates of the principal point of the optical axis in pixels; l is the length of the scale in meters; X l X r Y t Y b These are the coordinates of the four sides (left, right, top, and bottom) of the target detection box, in pixels.

[0095] In the specific implementation of the maximum wind vibration calculation method, the vibration of the cable-stayed conveyor is considered to be a small-amplitude vibration, and its dynamic equation during vibration is simplified to the vibration equation of the static catenary. The catenary equation of the suspension cable is solved based on the coordinates of the two towers and the reference point; the equation of the straight line connecting the two towers is solved based on the coordinates of the two towers; the difference between the line connecting the towers and the catenary is taken as the extreme value of the vibration pendulum length; a vertical line is drawn through the reference point and intersects the line connecting the towers to obtain the vibration pendulum length; based on the ratio of the amplitude at the reference point to the vibration pendulum length extreme value, the amplitude at the extreme value of the pendulum length is derived.

[0096] This invention provides a machine learning-based wind vibration monitoring system for a cable-stayed conveyor, with the specific layout as follows: Figure 3 As shown, target detection marker 5 is positioned at a certain location within the span of two cable towers in the cable-stayed conveyor belt. It has a fixed length and a color different from the ambient color. For example... Figure 4 As shown, the camera is positioned above the center of the tower 4, aimed at the target detection pole 5, and positioned as close to the center of the video feed as possible.

[0097] The embodiments described above merely illustrate specific implementation methods of this application, and while the descriptions are detailed and specific, they should not be construed as limiting the scope of protection of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the technical solution of this application, and these modifications and improvements all fall within the scope of protection of this application.

[0098] This background section is provided to generally present the context of the invention. The work of the currently named inventors, the work to the extent described in this background section, and aspects of this section that did not constitute prior art at the time of application are neither expressly nor impliedly acknowledged as prior art to the invention.

Claims

1. A machine learning-based method for monitoring wind-induced vibration in a cable-stayed belt conveyor, characterized in that, include: Step S1: Data acquisition and transmission; The system automatically collects video, environmental data, and suspension belt conveyor operation data with target detection benchmarks, stores and transmits them sequentially in chronological order, and transmits them to a local server in real time. Remote servers can retrieve data with timelines as needed. Step S2: Image correction and data processing; determine the video frame interval and extract the time-series data corresponding to the video frame; calibrate the camera's intrinsic parameters and measure the extrinsic parameters in real time to complete the correction of the video frame; preprocess the obtained data segments to obtain time-domain features and time-frequency domain features; Step S3: Model building and mapping construction; A target detection model was established, and the distance to the benchmark and the wind vibration offset at the benchmark were obtained. A wind vibration prediction model was established based on the collected data and the real-time detection results of the suspension belt conveyor. A mapping relationship between the wind vibration data at the benchmark and the wind vibration data at the point of maximum wind vibration was constructed. Step S4: Automatic monitoring and early warning; real-time acquisition of wind vibration data calculated by the target detection model and comparison with wind vibration threshold analysis; before reaching the wind vibration anomaly time point predicted by the deep learning model, timely notification to maintenance personnel or intervention to control the suspension belt conveyor to decelerate or stop.

2. The method for monitoring wind-induced vibration of a suspension belt conveyor based on machine learning according to claim 1, characterized in that, The target detection marker is a long strip mark that needs to be set to a fixed length according to the detection distance, and its color should be different from the environment color. It is placed horizontally in a certain span of the suspension belt conveyor.

3. The machine learning-based wind vibration monitoring method for cable-stayed conveyors according to claim 2, characterized in that, The required length or width of the target detection benchmark shall be selected according to the following formula: in: l represents the length of the target detection benchmark; α represents the percentage of the screen occupied by the benchmark. f is the focal length; w cam This is the actual width of the camera image sensor. D represents the expected distance between the benchmark and the camera.

4. The method for monitoring wind-induced vibration of a cable-stayed conveyor based on machine learning according to claim 1, characterized in that, Step S1 includes: Step S1-1: Acquire video data of the suspension belt conveyor with target detection benchmarks using a camera and transmit it; Steps S1-2: Obtain wind direction and speed data through an anemometer and store them in chronological order; obtain wind and rain load information through a rain and snow sensor and store and transmit it in chronological order. Steps S1-3: Obtain vibration data of the suspension belt conveyor through vibration sensors and store it in chronological order; obtain the belt speed of the conveyor through a tachometer and store and transmit it in chronological order.

5. The method for monitoring wind-induced vibration of a suspension belt conveyor based on machine learning according to claim 1, characterized in that, Step S2 includes: Step S2-1: Select an appropriate video frame interval based on the number of frames in the monitoring video; extract the data collected from the anemometer, rain and snow sensor, vibration sensor and tachometer into time-series segments, corresponding to the time interval of the video frames; Step S2-2: Measure the intrinsic parameters of the camera by obtaining the focal length, pixel size, principal coordinates of the optical axis, and camera distortion parameters using the Zhang Zhengyou calibration method; and measure the extrinsic parameters of the camera in real time, namely the rotation matrix and translation matrix. Step S2-3: Preprocess the extracted time series data. Obtain the time-frequency characteristics of the anemometer, rain and snow sensor and tachometer, and obtain the time-frequency domain characteristics of the vibration sensor.

6. The method for monitoring wind-induced vibration of a suspension belt conveyor based on machine learning according to claim 1, characterized in that, Step S3 includes: Step S3-1: Establish an object detection model and train it based on the benchmark dataset; input video frames into the model to obtain the benchmark distance and wind vibration offset at the benchmark; Step S3-2: Based on the time series data of wind direction and speed, rain and snow load, and operation of the suspension belt conveyor, establish and train the wind vibration prediction model until the evaluation indicators meet the requirements; Step S3-3: Based on the coordinates of the two towers and the benchmark, construct the theoretical maximum wind vibration location coordinates of the suspended cable conveyor and the mapping relationship between its wind vibration data and the wind vibration data at the benchmark.

7. The method for monitoring wind-induced vibration of a suspension belt conveyor based on machine learning according to claim 1, characterized in that, Step S4 includes: Step S4-1: Establish an autonomous monitoring algorithm to receive video data in real time; use the target detection model to calculate the theoretical maximum wind vibration location coordinates and wind vibration data, and compare and analyze them with the danger judgment threshold to judge wind vibration anomalies in real time. Step S4-2: Receive environmental conditions and suspension belt conveyor operation data in real time, predict and calculate the critical time points of wind-induced vibration and their wind-induced vibration data; Step S4-3: Construct an automated early warning and control system; when wind-induced vibration abnormalities are observed or predicted, the early warning control function is automatically activated, and early warning information is pushed to the on-duty personnel. In case of emergency, the system intervenes in the conveyor control system to reduce speed or stop the machine.

8. A machine learning-based wind-induced vibration monitoring system for cable-stayed belt conveyors, characterized in that, The method for monitoring wind-induced vibration of a suspension belt conveyor as described in any one of claims 1-7 includes: Data acquisition module, information processing module, wind vibration monitoring module, and early warning and control module; The data acquisition module includes: an anemometer, a rain and snow sensor, a high-definition camera, a vibration sensor, and a tachometer; it is used to collect on-site environmental data such as wind, rain, and snow, video with a benchmark, and operating data of the suspension belt conveyor, and transmit the data to the information processing module. The information processing module includes: a lens distortion correction algorithm, a fast Fourier transform algorithm, a time-domain feature extraction method, and a time-frequency domain feature extraction method; it is used to process various types of data transmitted from the data acquisition module and transmit the data to the wind vibration monitoring module. The wind vibration monitoring module includes: machine vision algorithm, distance offset algorithm, wind vibration prediction algorithm, and maximum wind vibration calculation method; it is used to receive various types of data transmitted by the data acquisition module, establish and train the model; observe and predict the wind vibration data and abnormal time points of the suspension belt conveyor, and transmit the data to the early warning control module. The early warning control module includes: an autonomous monitoring algorithm, an alarm push device, an automatic control algorithm, and a control linkage system; it is used to receive wind vibration data transmitted by the wind vibration monitoring module, monitor the operation of the suspension belt conveyor in real time, and realize autonomous monitoring and early warning.

9. The machine learning-based wind vibration monitoring system for cable-stayed conveyors according to claim 8, characterized in that, The machine vision algorithm is used to identify the benchmark and obtain its position information in the image; the distance measurement and offset algorithm is used to calculate the distance from the benchmark to the camera and obtain the wind vibration offset of the benchmark relative to its static position; the wind vibration prediction algorithm is used to predict the future wind vibration data of the benchmark under the current data and obtain the critical time point; the maximum wind vibration calculation method is used to calculate the position information of the benchmark across the maximum wind vibration point and the wind vibration data.

10. The machine learning-based wind vibration monitoring system for cable-stayed conveyors according to claim 8, characterized in that, The autonomous monitoring algorithm is used to monitor the operating status of the suspension belt conveyor in real time and determine whether the wind vibration data of the suspension belt conveyor exceeds the threshold; the automatic control algorithm is used to activate the early warning equipment, remind the on-duty personnel to reduce the conveying volume, slow down or stop the machine in an emergency, and intervene to control the suspension belt conveyor in an emergency.

Images