Automatic Control Method and System for Multi-Mode Belt Conveyor

Abstract

Multi-mode belt conveyor automatic control method and system, which relates to the technical field of conveyor optimization; constructing a digital twin model of the belt conveyor, obtaining the conveying amplitude of the belt conveyor under different working modes and constructing a conveying amplitude curve, obtaining the amplitude influence coefficient of different working modes on the conveying amplitude and the period influence coefficient of different conveying masses on the conveying period, obtaining the optimized conveying speed according to the actual operation data combined with the amplitude influence coefficient, obtaining the optimized operation data according to the optimized conveying speed, inputting the optimized operation data into a preset period prediction model to obtain the prediction influence coefficient, and adjusting the optimized conveying speed until the prediction influence coefficient drops to zero; through the technical solution of the present invention, the vibration amplitude of the belt conveyor can be maintained within a stable floating range, which is beneficial to reducing the deviation of the conveying period while maintaining the normal conveying amplitude.

Description

Technical Field

[0001] The present invention relates to the technical field of conveyor optimization, specifically an automatic control method and system for a multi-mode belt conveyor. Background Technique

[0002] Automatically controlling a multi-mode belt conveyor is an advanced material conveying technology that combines the characteristics of automated control and multi-mode operation. It can flexibly adjust the operating state of the conveyor according to actual needs, improve the conveying efficiency and energy utilization rate, and automatically adjust parameters such as the operating speed and power of the conveyor according to preset control strategies and real-time data;

[0003] In the prior art, there are often various variables in the operating state of a belt conveyor. Different variables have different influencing effects on the operation of the belt conveyor. For example, different angles and speeds often produce different amplitudes, and different materials often cause the conveyor belt to idle and result in a delay in the conveying cycle. In the prior art, there is a lack of optimization means for these influencing factors, which leads to the inability to effectively and accurately control the belt conveyor. In view of the deficiencies of the prior art, the present invention provides an automatic control method and system for a multi-mode belt conveyor. Summary of the Invention

[0004] The purpose of the present invention is to provide an automatic control method and system for a multi-mode belt conveyor.

[0005] The purpose of the present invention can be achieved through the following technical solutions: An automatic control method for a multi-mode belt conveyor includes the following steps:

[0006] Step S1: Collect the equipment information of the belt conveyor, construct its digital twin model according to the equipment information, and conduct conveying simulations on the belt conveyor under different working modes;

[0007] Step S2: Obtain the conveying amplitudes of the belt conveyor under different working modes, respectively construct corresponding conveying amplitude curves, and obtain the amplitude influence coefficients of different working modes on the conveying amplitude according to the conveying amplitude curves;

[0008] Step S3: Set a standard mode, and obtain the cycle influence coefficients of different conveying masses on the conveying cycle under the standard mode;

[0009] Step S4: Obtain the actual operating data of the belt conveyor, obtain the optimized conveying speed according to the actual operating data combined with the amplitude influence coefficients, obtain the optimized operating data according to the optimized conveying speed, and input the optimized operating data into a preset cycle prediction model to obtain the predicted cycle influence coefficient;

[0010] Step S5: Adjust the optimized conveying speed until the predicted cycle influence coefficient drops to zero.

[0011] Further, the process of collecting the equipment information of the belt conveyor and constructing its digital twin model according to the equipment information, and performing transportation simulation on the belt conveyor under different working modes includes:

[0012] The equipment information refers to the structural parameters of each component of the belt conveyor, and the digital twin model of the belt conveyor is constructed according to the collected equipment information by using digital twin technology;

[0013] The transportation simulation refers to adjusting the transportation angle, transportation speed, and transportation length of the belt conveyor in the digital twin model respectively to simulate the switching process between different working modes of the belt conveyor and its operating state under different working modes;

[0014] The transportation angle refers to the angle between the conveyor belt in the belt conveyor and the horizontal line, the transportation speed refers to the moving speed of the conveyor belt in the belt conveyor, and the transportation length refers to the length of the conveyor belt in the belt conveyor.

[0015] Further, the process of obtaining the transportation amplitude of the belt conveyor under different working modes and constructing the corresponding transportation amplitude curves respectively includes:

[0016] An amplitude monitoring unit is set on the conveyor belt of the belt conveyor, and the vibration amplitude of the belt conveyor in its operating state is monitored through the amplitude monitoring unit to obtain the transportation amplitude;

[0017] By adjusting the transportation angle and transportation speed of the belt conveyor respectively, the transportation amplitude of the belt conveyor under different working modes is obtained by monitoring its transportation amplitude in real time during this process;

[0018] Multiple transportation amplitude curves with the transportation angle as the abscissa and the transportation amplitude as the ordinate are constructed according to the obtained transportation amplitude, and each transportation amplitude curve corresponds to a different transportation speed.

[0019] Further, the process of obtaining the amplitude influence coefficient of different working modes on the transportation amplitude according to the transportation amplitude curve includes:

[0020] The transportation amplitude curves of the belt conveyor at different transportation speeds are integrated into the same coordinate system to obtain a comprehensive amplitude curve, the comprehensive amplitude curve is regarded as a scatter plot, and its regression line is constructed, and the regression line is used as the reference amplitude line;

[0021] The shortest distance between the coordinate points of each transportation amplitude curve at different transportation angles and the reference amplitude line is obtained, and the shortest distance is used as the amplitude influence coefficient of the corresponding transportation angle and transportation speed on the transportation amplitude.

[0022] Further, a standard mode is set, and the process of obtaining the period influence coefficient of different conveying qualities on the conveying period in the standard mode includes:

[0023] Taking the intersection points of the reference amplitude line and each conveying amplitude curve as standard points, and taking the conveying angle, conveying speed, and conveying amplitude of each standard point as the standard mode. In the digital twin model, adjust the belt conveyor to different standard modes;

[0024] In different standard modes, obtain the standard conveying period when the conveying quality is zero. The conveying quality refers to the total mass of the materials conveyed on the conveyor belt of the belt conveyor, and the conveying period refers to the time interval from the conveying starting point to the conveying ending point of any point on the conveyor belt;

[0025] Keep the standard mode fixed, adjust the conveying quality, and record the adjusted conveying period under different conveying qualities. Take the difference between the adjusted conveying period and its standard conveying period as the period influence coefficient of the corresponding conveying quality on the conveying period.

[0026] Further, the process of obtaining the actual operation data of the belt conveyor and obtaining the optimized conveying speed according to the actual operation data combined with the amplitude influence coefficient includes:

[0027] Monitor the actual operation data of the belt conveyor in the actual working state. The actual operation data includes the actual conveying angle, actual conveying speed, and actual conveying amplitude;

[0028] In the comprehensive amplitude curve, obtain the theoretical conveying amplitude and amplitude influence coefficient corresponding to the actual conveying angle and actual conveying speed, and compare the theoretical conveying amplitude with the actual conveying amplitude to determine whether the actual conveying amplitude is in a normal state or an abnormal state;

[0029] When it is in an abnormal state, keep the actual conveying angle unchanged, adjust the actual conveying speed until the actual conveying amplitude returns to the normal state, and take the conveying speed of the belt conveyor at this time as the optimized conveying speed.

[0030] Further, the process of obtaining the optimized operation data according to the optimized conveying speed and inputting the optimized operation data into a preset period prediction model to obtain the prediction period influence coefficient includes:

[0031] Obtain the optimized conveying amplitude at the optimized conveying speed, and incorporate the actual conveying angle, optimized conveying speed, optimized conveying amplitude, and actual conveying quality into the optimized operation data;

[0032] Generate a period prediction set according to different conveying angles, conveying speeds, conveying amplitudes, conveying qualities and their corresponding period influence coefficients, and divide the period prediction set into a training set and a test set;

[0033] Construct a convolutional neural network, using the conveying angle, conveying speed, conveying amplitude, and conveying mass in the training set as the input data of the convolutional neural network, and using the corresponding cycle influence coefficient in the training set as the output data of the convolutional neural network, and training the convolutional neural network to obtain an initial convolutional neural network;

[0034] Use the test set to verify the model of the initial convolutional neural network, and output the initial convolutional neural network with a test error threshold less than or equal to the preset value as the corresponding cycle prediction model, and obtain the corresponding predicted cycle influence coefficient according to the optimized operation data through the cycle prediction model.

[0035] Further, the process of adjusting the optimized conveying speed until the predicted cycle influence coefficient drops to zero includes:

[0036] Continuously adjust the optimized conveying speed so that the predicted cycle influence coefficient drops to zero, mark the conveying speed at this time as the adjusted conveying speed, and based on the adjusted conveying speed, repeat steps S4 and S5 until the optimized conveying amplitude is in a normal state and the predicted cycle influence coefficient drops to zero.

[0037] The multi-mode belt conveyor automatic control system includes the following modules:

[0038] The data acquisition module is used to collect the device information of the belt conveyor, construct its digital twin model according to the device information, and perform conveying simulation on the belt conveyor under different working modes;

[0039] The first influence module is used to obtain the conveying amplitude of the belt conveyor under different working modes, respectively construct the corresponding conveying amplitude curves, and obtain the amplitude influence coefficients of different working modes on the conveying amplitude according to the conveying amplitude curves;

[0040] The second influence module is used to set the standard mode and obtain the cycle influence coefficients of different conveying masses on the conveying cycle under the standard mode;

[0041] The first optimization module is used to obtain the actual operation data of the belt conveyor, obtain the optimized conveying speed according to the actual operation data combined with the amplitude influence coefficient, obtain the optimized operation data according to the optimized conveying speed, and input the optimized operation data into the preset cycle prediction model to obtain the predicted cycle influence coefficient;

[0042] The second optimization module adjusts the optimized conveying speed until the predicted cycle influence coefficient drops to zero.

[0043] Compared with the prior art, the beneficial effects of the present invention are:

[0044] 1. The present invention monitors the conveying amplitude of a belt conveyor under different working modes and constructs corresponding conveying amplitude curves, integrates all the conveying amplitude curves to obtain a reference amplitude straight line, and takes the shortest distance between each coordinate point and the reference amplitude straight line as its amplitude influence coefficient, which can reflect the influence degree of different conveying angles and conveying speeds on the conveying amplitude. Taking this influence degree as the judgment criterion, when the difference between the theoretical conveying amplitude and the actual conveying amplitude exceeds its influence degree, it can be judged that the actual conveying amplitude is abnormal and adjusted, which is beneficial to keeping the vibration amplitude of the belt conveyor within a stable floating range and realizing effective control and optimization of its working conditions;

[0045] 2. The present invention constructs a digital twin model of a belt conveyor and simulates the cycle influence coefficient of different conveying masses on the conveying cycle under the standard mode inside it. Based on this, a cycle prediction model capable of predicting the cycle influence coefficient is constructed, and the corresponding predicted cycle influence coefficient can be obtained according to the actual data. Taking the predicted cycle influence coefficient dropping to zero as the goal, the conveying speed is adjusted, which is beneficial to reducing the deviation of the conveying cycle while maintaining the normal conveying amplitude. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 is a flowchart of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0047] As Figure 1 shown, the multi-mode belt conveyor automatic control method includes the following steps:

[0048] Step S1: Collect the equipment information of the belt conveyor and construct its digital twin model according to the equipment information, and conduct conveying simulation on the belt conveyor under different working modes;

[0049] Step S2: Obtain the conveying amplitude of the belt conveyor under different working modes, respectively construct corresponding conveying amplitude curves, and obtain the amplitude influence coefficient of different working modes on the conveying amplitude according to the conveying amplitude curves;

[0050] Step S3: Set the standard mode and obtain the cycle influence coefficient of different conveying masses on the conveying cycle under the standard mode;

[0051] Step S4: Obtain the actual operation data of the belt conveyor, obtain the optimized conveying speed according to the actual operation data combined with the amplitude influence coefficient, obtain the optimized operation data according to the optimized conveying speed, and input the optimized operation data into a preset cycle prediction model to obtain the predicted cycle influence coefficient;

[0052] Step S5: Adjust the optimized conveying speed until the predicted cycle influence coefficient drops to zero.

[0053] It should be further noted that in the specific implementation process, the process of collecting the equipment information of the belt conveyor and constructing its digital twin model based on the equipment information, and performing transportation simulation on the belt conveyor under different working modes includes:

[0054] The equipment information refers to the structural parameters of each component of the belt conveyor. The components include a conveyor belt, a driving device, a roller, a carrying roller, a tensioning device, a frame, a funnel, and a feed chute. The digital twin model of the belt conveyor is constructed using digital twin technology based on the collected equipment information;

[0055] The belt conveyor is multi-mode and has a variety of different working modes, such as horizontal mode, inclined mode, low-speed mode, high-speed mode, short-distance mode, long-distance mode, and other working modes formed by combination on this basis;

[0056] The transportation simulation refers to adjusting the transportation angle, transportation speed, and transportation length of the belt conveyor respectively in the constructed digital twin model to simulate the switching process between different working modes of the belt conveyor and its operating state under different working modes;

[0057] The transportation angle refers to the angle between the conveyor belt in the belt conveyor and the horizontal line. The transportation speed refers to the moving speed of the conveyor belt in the belt conveyor. The transportation length refers to the length of the conveyor belt in the belt conveyor.

[0058] It should be further noted that in the specific implementation process, the process of obtaining the transportation amplitude of the belt conveyor under different working modes and constructing the corresponding transportation amplitude curves respectively includes:

[0059] Taking any belt conveyor as an example, for a single belt conveyor, its transportation length is fixed. An amplitude monitoring unit is set on its conveyor belt, and the vibration amplitude of the belt conveyor during the operating state is monitored through the amplitude monitoring unit and marked as the transportation amplitude;

[0060] Under the condition that the transportation length remains unchanged, by adjusting the transportation angle and transportation speed of the belt conveyor respectively, and monitoring its transportation amplitude in real time during this process to obtain the transportation amplitude of the belt conveyor under different working modes;

[0061] For example, adjust the transportation speed to a and keep it unchanged, and continuously adjust the transportation angle from small to large. Obtain the corresponding transportation amplitudes at different transportation angles when the transportation speed of the belt conveyor is a, and construct a transportation amplitude curve with the transportation angle as the abscissa and the transportation amplitude as the ordinate;

[0062] And so on, adjust the conveying speed to be fixed at b, continuously adjust the conveying angle from small to large, obtain the corresponding conveying amplitudes at different conveying angles when the belt conveyor has a conveying speed of b, and construct a conveying amplitude curve with the conveying angle as the abscissa and the conveying amplitude as the ordinate.

[0063] It should be further noted that in the specific implementation process, the process of obtaining the amplitude influence coefficient of different working modes on the conveying amplitude according to the conveying amplitude curve includes:

[0064] Integrate the conveying amplitude curves of the belt conveyor at different conveying speeds into the same coordinate system to obtain a comprehensive amplitude curve. The abscissa of the comprehensive amplitude curve is the conveying angle, and the ordinate is the conveying amplitude. It contains multiple conveying amplitude curves inside, and each conveying amplitude curve corresponds to a different conveying speed;

[0065] Since there are multiple turning points on each conveying amplitude curve, the comprehensive amplitude curve can be regarded as a scatter plot. Construct a regression line inside the comprehensive amplitude curve and mark the constructed regression line as the reference amplitude line;

[0066] Obtain the shortest distance between the coordinate points of each conveying amplitude curve at different conveying angles and the reference amplitude line, and mark the obtained shortest distance as the amplitude influence coefficient of the corresponding conveying angle and conveying speed on the conveying amplitude.

[0067] It should be further noted that in the specific implementation process, set a standard mode. The process of obtaining the cycle influence coefficient of different conveying masses on the conveying cycle in the standard mode includes:

[0068] Mark the intersection points of the reference amplitude line and each conveying amplitude curve as standard points. Mark the corresponding conveying angle, conveying speed, and conveying amplitude of each standard point as the standard mode. In the digital twin model, adjust the belt conveyor to the standard mode;

[0069] The conveying mass refers to the total mass of the materials conveyed on the conveyor belt of the belt conveyor. The conveying cycle refers to the time interval from the conveying starting point to the conveying ending point of any point on the conveyor belt. In the standard mode, obtain the conveying cycle when the conveying mass is zero and mark it as the standard conveying cycle;

[0070] In the digital twin model, keep any standard mode fixed, adjust the conveying mass in ascending order, record the corresponding conveying cycles at different conveying masses, and mark them as the adjusted conveying cycles;

[0071] Obtain the adjusted conveying periods corresponding to different conveying qualities under different standard modes, and mark the difference between each adjusted conveying period and its standard conveying period as the period influence coefficient of the corresponding conveying quality on the conveying period.

[0072] It should be further noted that in the specific implementation process, the process of obtaining the actual operation data of the belt conveyor and obtaining the optimized conveying speed based on the actual operation data combined with the amplitude influence coefficient includes:

[0073] Monitor the actual operation data of the belt conveyor in the actual working state, and the actual operation data includes the actual conveying angle, the actual conveying speed, and the actual conveying amplitude;

[0074] In the comprehensive amplitude curve, obtain the theoretical conveying amplitude Z corresponding to the actual conveying angle and the actual conveying speed L and the amplitude influence coefficient Z y , compare the theoretical conveying amplitude Z L with the actual conveying amplitude Z S , if |Z S - Z L | < Z y , then judge that the actual conveying amplitude is in the normal state and do not perform any other operations on it;

[0075] If |Z S - Z L | ≥ Z y , then judge that the actual conveying amplitude is in the abnormal state, keep the actual conveying angle unchanged, adjust the actual conveying speed until the actual conveying amplitude is in the normal state, and mark the conveying speed of the belt conveyor at this time as the optimized conveying speed.

[0076] It should be further noted that in the specific implementation process, the process of obtaining the optimized operation data based on the optimized conveying speed and inputting the optimized operation data into the preset cycle prediction model to obtain the predicted cycle influence coefficient includes:

[0077] Obtain the optimized conveying amplitude at the optimized conveying speed, and incorporate the actual conveying angle, the optimized conveying speed, the optimized conveying amplitude, and the actual conveying quality into the optimized operation data;

[0078] The preset process of the cycle prediction model is as follows:

[0079] Generate a cycle prediction set according to different conveying angles, conveying speeds, conveying amplitudes, conveying qualities and their corresponding cycle influence coefficients, and divide the obtained cycle prediction set into a training set and a test set;

[0080] Construct a convolutional neural network. Use the conveying angle, conveying speed, conveying amplitude, and conveying mass in the training set as the input data of the convolutional neural network, and use the corresponding cycle influence coefficient in the training set as the output data of the convolutional neural network. Train the convolutional neural network to obtain an initial convolutional neural network;

[0081] Use the test set to verify the model of the initial convolutional neural network, and output the initial convolutional neural network with a test error threshold less than or equal to the preset value as the corresponding cycle prediction model;

[0082] Input the optimized operation data into the cycle prediction model. Through the cycle prediction model, according to the actual conveying angle, optimized conveying speed, optimized conveying amplitude, and actual conveying mass in the optimized operation data, output the corresponding predicted cycle influence coefficient.

[0083] It should be further noted that in the specific implementation process, the process of adjusting the optimized conveying speed until the predicted cycle influence coefficient drops to zero includes:

[0084] Since the actual conveying angle remains unchanged and the actual conveying mass changes dynamically, it is necessary to continuously adjust the optimized conveying speed so that the predicted cycle influence coefficient drops to zero, and mark the conveying speed at this time as the adjusted conveying speed;

[0085] During this process, the optimized conveying amplitude will also change accordingly. Based on adjusting the conveying speed, repeat step S4 and step S5 until the optimized conveying amplitude is in a normal state and the predicted cycle influence coefficient drops to zero.

[0086] The embodiments of the present invention further include: an automatic control system for a multi-mode belt conveyor, including the following modules:

[0087] A data acquisition module for collecting the equipment information of the belt conveyor, constructing its digital twin model according to the equipment information, and performing conveying simulation on the belt conveyor under different working modes;

[0088] A first influence module for obtaining the conveying amplitude of the belt conveyor under different working modes, respectively constructing corresponding conveying amplitude curves, and obtaining the amplitude influence coefficient of different working modes on the conveying amplitude according to the conveying amplitude curves;

[0089] A second influence module for setting a standard mode and obtaining the cycle influence coefficient of different conveying masses on the conveying cycle under the standard mode;

[0090] The first optimization module is used to obtain the actual operation data of the belt conveyor, obtain the optimized conveying speed according to the actual operation data combined with the amplitude influence coefficient, obtain the optimized operation data according to the optimized conveying speed, and input the optimized operation data into a preset periodic prediction model to obtain the predicted period influence coefficient;

[0091] The second optimization module adjusts the optimized conveying speed until the predicted period influence coefficient drops to zero.

[0092] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical method of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A multi-mode belt conveyor automatic control method, characterized in that: The following steps are involved: Step S1: Collect the equipment information of the belt conveyor, build its digital twin model according to the equipment information, and simulate the conveying of the belt conveyor in different working modes; Step S2: obtaining the conveying amplitude of the belt conveyor in different working modes, constructing corresponding conveying amplitude curves respectively, and obtaining the amplitude influence coefficient of different working modes on the conveying amplitude according to the conveying amplitude curves; Step S3: Setting a standard mode, and obtaining the period influence coefficient of different conveying qualities on the conveying period under the standard mode; Step S4: obtaining actual operation data of the belt conveyor, obtaining an optimized conveying speed according to the actual operation data combined with the amplitude influence coefficient, obtaining optimized operation data according to the optimized conveying speed, and inputting the optimized operation data into a preset cycle prediction model to obtain a predicted cycle influence coefficient; Step S5: adjusting the optimized conveying speed until the predicted cycle influence coefficient drops to zero; The process of obtaining the amplitude influence coefficient according to the conveying amplitude curve includes: The conveying amplitude curves of the belt conveyor at different conveying speeds are integrated into the same coordinate system to obtain a comprehensive amplitude curve with the horizontal coordinate being the conveying angle and the vertical coordinate being the conveying amplitude. The comprehensive amplitude curve is regarded as a scatter plot, and its regression line is constructed, and the regression line is used as the reference amplitude line. Obtain the shortest distance between the coordinate point of each conveying amplitude curve at different conveying angles and the reference amplitude straight line, and use the shortest distance as the amplitude influence coefficient of the corresponding conveying angle and conveying speed on the conveying amplitude; The process of obtaining the periodic influence coefficient in standard mode includes: In the digital twin model, the belt conveyor is adjusted to different standard modes, and the standard conveying cycle when the conveying quality is zero is obtained under different standard modes; The standard mode is kept fixed, the conveying quality is adjusted, and the adjusted conveying cycle under different conveying qualities is recorded. The difference between the adjusted conveying cycle and its standard conveying cycle is used as the period influence coefficient of the corresponding conveying quality on the conveying cycle.

2. The multi-mode belt conveyor automatic control method according to claim 1, characterized in that: The process of building a digital twin model based on equipment information and performing transportation simulation on it includes: The equipment information refers to the structural parameters of each component of the belt conveyor. The digital twin technology is used to construct a digital twin model of the belt conveyor according to the collected equipment information; The conveying simulation refers to adjusting the conveying angle, conveying speed, and conveying length of the belt conveyor in the digital twin model to simulate the switching process of the belt conveyor between different working modes and its operating status in different working modes; The conveying angle refers to the angle between the conveyor belt in the belt conveyor and the horizontal line, the conveying speed refers to the moving speed of the conveyor belt in the belt conveyor, and the conveying length refers to the length of the conveyor belt in the belt conveyor.

3. The multi-mode belt conveyor automatic control method according to claim 2, characterized in that: The process of obtaining the conveying amplitude of the belt conveyor and constructing the conveying amplitude curve includes: An amplitude monitoring unit is arranged on the conveyor belt of the belt conveyor, and the vibration amplitude of the conveyor belt in the running state is monitored by the amplitude monitoring unit to obtain the conveying amplitude; By adjusting the conveying angle and conveying speed of the belt conveyor respectively, the conveying amplitude is monitored in real time during the process to obtain the conveying amplitude of the belt conveyor in different working modes; A plurality of conveying amplitude curves are constructed according to the obtained conveying amplitude, wherein the horizontal coordinate is the conveying angle and the vertical coordinate is the conveying amplitude, and each conveying amplitude curve corresponds to a different conveying speed.

4. The multi-mode belt conveyor automatic control method according to claim 3, characterized in that: The conveying mass refers to the total mass of materials conveyed on the conveyor belt of the belt conveyor, and the conveying cycle refers to the time interval from the conveying starting point to the conveying end point at any point on the conveyor belt; The process of setting up standard mode includes: The intersection of the reference amplitude straight line and each conveying amplitude curve is taken as the standard point, and the conveying angle, conveying speed and conveying amplitude of each standard point are taken as the standard mode.

5. The multi-mode belt conveyor automatic control method according to claim 4, characterized in that: The process of optimizing the conveying speed based on actual operation data combined with the amplitude influence coefficient includes: Monitoring actual operation data of the belt conveyor in actual working state, wherein the actual operation data includes actual conveying angle, actual conveying speed, and actual conveying amplitude; In the comprehensive amplitude curve, the theoretical conveying amplitude and the amplitude influence coefficient corresponding to the actual conveying angle and the actual conveying speed are obtained, and the theoretical conveying amplitude is compared with the actual conveying amplitude to determine whether the actual conveying amplitude is in a normal state or an abnormal state; When it is in an abnormal state, the actual conveying angle is kept unchanged, and the actual conveying speed is adjusted until the actual conveying amplitude returns to a normal state. The conveying speed of the belt conveyor at this time is used as the optimized conveying speed.

6. The multi-mode belt conveyor automatic control method according to claim 5, characterized in that: The process of obtaining the optimization operation data and inputting it into the cycle forecasting model to obtain the forecast cycle impact coefficient includes: Obtain the optimized conveying amplitude under the optimized conveying speed, and incorporate the actual conveying angle, optimized conveying speed, optimized conveying amplitude, and actual conveying quality into the optimized operation data; Generate a cycle prediction set according to different conveying angles, conveying speeds, conveying amplitudes, conveying masses and their corresponding cycle influence coefficients, and divide the cycle prediction set into a training set and a test set; Construct a convolutional neural network, use the conveying angle, conveying speed, conveying amplitude, and conveying quality in the training set as input data of the convolutional neural network, use the corresponding periodic influence coefficient in the training set as output data of the convolutional neural network, and train the convolutional neural network to obtain an initial convolutional neural network; The initial convolutional neural network is model verified using the test set, and an initial convolutional neural network with a value less than or equal to a preset test error threshold is output as the corresponding cycle prediction model. The corresponding prediction cycle influence coefficient is obtained through the cycle prediction model according to the optimized operation data.

7. The multi-mode belt conveyor automatic control method according to claim 6, characterized in that: The process of adjusting the optimized conveying speed until the predicted cycle influence coefficient drops to zero includes: The optimized conveying speed is continuously adjusted so that the predicted cycle influence coefficient drops to zero. The conveying speed at this time is marked as the adjusted conveying speed. Based on the adjusted conveying speed, steps S4 and S5 are repeated until the optimized conveying amplitude is normal and the predicted cycle influence coefficient drops to zero.

8. A multi-mode belt conveyor automatic control system, which is used to implement the multi-mode belt conveyor automatic control method according to any one of claims 1 to 7, characterized in that: The system comprises: The data acquisition module is used to collect the equipment information of the belt conveyor, build its digital twin model based on the equipment information, and simulate the conveying of the belt conveyor in different working modes; The first influence module is used to obtain the conveying amplitude of the belt conveyor in different working modes, construct corresponding conveying amplitude curves respectively, and obtain the amplitude influence coefficient of different working modes on the conveying amplitude according to the conveying amplitude curve; The second impact module is used to set a standard mode and obtain the period impact coefficient of different conveying qualities on the conveying period under the standard mode; The first optimization module is used to obtain the actual operation data of the belt conveyor, obtain the optimized conveying speed according to the actual operation data combined with the amplitude influence coefficient, obtain the optimized operation data according to the optimized conveying speed, and input the optimized operation data into a preset cycle prediction model to obtain the prediction cycle influence coefficient; The second optimization module adjusts the optimized conveying speed until the prediction cycle influence coefficient drops to zero.

Images