Automatic deviation rectifying method and system for belt of adhesive tape machine

Abstract

The invention provides an automatic deviation rectifying method and system for a belt of an adhesive tape machine. The method comprises the steps that bilateral vibration signals of a conveying belt at different vibration detection point positions are collected; extracting double-side vibration characteristic differences according to the double-side vibration signals on each vibration detection point, and performing characteristic fitting on the double-side vibration characteristic differences according to the sequence of the corresponding vibration detection points to obtain an offset characteristic change trend of the conveying belt; extracting the offset credibility of the offset characteristic change trend, and performing offset trend prediction on the offset characteristic change trend corresponding to each transmission period based on the offset credibility to obtain a belt offset prediction degree and a prediction offset direction; when the belt deviation prediction degree is higher than the deviation rectification threshold value, the real-time position of the carrier roller support of the conveying belt is adjusted according to the belt deviation prediction degree and the prediction deviation direction, automatic deviation rectification of the conveying belt is achieved, deviation prediction can be conducted based on the double-side vibration signals of the conveying belt, and the real-time performance of deviation rectification of the conveying belt is improved.

Description

Technical Field

[0001] The present application relates to the technical field of belt conveyors, and more specifically, to a method and system for automatically correcting the deviation of a belt conveyor. Background Art

[0002] Belt conveyor, also known as belt conveyor, belt conveyor, is a kind of mechanical equipment that uses a continuously circulating conveyor belt as a traction and load-bearing component to achieve continuous material transportation. In this application, the conveyor belt is the core component of the belt conveyor. It acts as a traction and load-bearing element and circulates under the drive of rollers and idlers. It is used to continuously transport various bulk materials or piece items. When working, the material is placed at one end of the conveyor belt, and the motor drives the conveyor belt to move through the active roller, driving the material to move continuously along the direction of the conveyor belt to achieve the purpose of material transportation.

[0003] In the actual conveying process of the existing technology, it is usually difficult to accurately place the material on the center line of the conveyor belt due to factors such as equipment structure, material characteristics and operating errors. Among them, a more typical situation is that when multiple devices are operated in series, there is a discharge angle at the discharge port of the feeding equipment, which causes the material to deviate from the center and fall; in addition, due to the existence of gravity acceleration and falling height, the material is often accompanied by impact, rolling, slipping and other behaviors in the process of falling into the conveyor belt, which further causes the material transmission path on the conveyor belt to deviate laterally. The overloading phenomenon will cause uneven loads on both sides of the conveyor belt during operation, and then cause unbalanced lateral force on the belt, generating a lateral component force, so that the conveyor belt continues to move to the heavier side, resulting in the problem of conveyor belt deviation, which greatly restricts the application and development of belt conveyors. Summary of the Invention

[0004] The present application provides a method and system for automatically correcting the deviation of a conveyor belt, which can predict the deviation based on the bilateral vibration signals of the conveyor belt, thereby improving the real-time performance of the conveyor belt correction.

[0005] In a first aspect, the present application provides a method for automatically correcting the belt deviation of a belt conveyor. The method can be executed by a network device, or can be executed by a chip configured in the network device, and the present application does not limit this.

[0006] Specifically, the method includes:

[0007] Start the belt conveyor to transport the materials through the conveyor belt;

[0008] During the current transmission cycle, bilateral vibration signals of the conveyor belt at different vibration detection points are collected;

[0009] Extracting bilateral vibration characteristic differences based on bilateral vibration signals at each vibration detection point, performing feature fitting on the bilateral vibration characteristic differences through the corresponding vibration detection point sequence, and obtaining a variation trend of the deviation characteristics of the conveyor belt;

[0010] Extracting the offset credibility of the offset feature change trend, and performing offset trend prediction on the offset feature change trend corresponding to each transmission cycle based on the offset credibility to obtain the belt offset prediction degree and predicted offset direction;

[0011] When the predicted belt deviation is higher than the deviation correction threshold, the real-time position of the roller support of the conveyor belt is adjusted according to the predicted belt deviation and the predicted deviation direction to achieve automatic deviation correction of the conveyor belt.

[0012] In combination with the first aspect, in certain implementations of the first aspect, the real-time position of the roller bracket is adjusted by an electric push rod.

[0013] In combination with the first aspect, in certain implementations of the first aspect, a piezoelectric acceleration sensor is used to collect bilateral vibration signals of the conveyor belt at different vibration detection points.

[0014] In combination with the first aspect, in certain implementations of the first aspect, before extracting the bilateral vibration characteristic difference based on the bilateral vibration signals at each vibration detection point, the method further includes: filtering the bilateral vibration signals.

[0015] In conjunction with the first aspect, in certain implementations of the first aspect, extracting the bilateral vibration characteristic difference based on the bilateral vibration signals at each vibration detection point specifically includes:

[0016] For any vibration detection point, obtain the left vibration signal and the right vibration signal of the bilateral vibration signals of the vibration detection point;

[0017] extracting the average vibration energy features of the left vibration signal and the right vibration signal respectively, and taking the difference between the average vibration energy features as the bilateral vibration feature difference of the vibration detection point;

[0018] The same method is used to obtain the bilateral vibration characteristic differences corresponding to other vibration detection points.

[0019] In conjunction with the first aspect, in certain implementations of the first aspect, performing feature fitting on the bilateral vibration characteristic difference through the corresponding vibration detection point sequence to obtain the deviation characteristic change trend of the conveyor belt specifically includes:

[0020] Obtain multiple bilateral vibration signal differences and their corresponding vibration detection points;

[0021] The transmission distance value corresponding to each vibration detection point is obtained, and the transmission distance value is used as an independent variable to sequentially fit the bilateral vibration signal difference corresponding to each vibration detection point to obtain the deviation characteristic change trend of the conveyor belt.

[0022] In conjunction with the first aspect, in certain implementations of the first aspect, performing an offset trend prediction on an offset feature change trend corresponding to each transmission period based on the offset credibility to obtain a belt offset prediction degree and a predicted offset direction specifically includes:

[0023] Obtain the offset feature change trend and corresponding offset credibility corresponding to the current transmission period and multiple historical transmission periods;

[0024] Selecting the offset feature change trend whose offset credibility is higher than a preset credibility threshold, and extracting the corresponding offset feature vector for any offset feature change trend;

[0025] Based on the offset feature vectors corresponding to the change trends of each offset feature and the corresponding transmission cycle sequence, a prediction model of the offset feature vector is constructed to perform prediction and obtain an offset prediction vector;

[0026] Cluster analysis is performed based on the deviation prediction vector to obtain the belt deviation prediction degree and the predicted deviation direction.

[0027] In a second aspect, the present application provides an automatic belt deviation correction system for a belt conveyor, which includes a transmission control unit, the transmission control unit including:

[0028] The transmission start module is used to start the belt conveyor and transport materials through the conveyor belt;

[0029] A transmission detection module, configured to collect bilateral vibration signals of the conveyor belt at different vibration detection points during a current transmission cycle;

[0030] The transmission detection module is further used to extract bilateral vibration characteristic differences based on bilateral vibration signals at each vibration detection point, and perform feature fitting on the bilateral vibration characteristic differences through the corresponding vibration detection point sequence to obtain the deviation characteristic change trend of the conveyor belt;

[0031] The transmission detection module is further configured to extract the offset credibility of the offset feature change trend, and perform offset trend prediction on the offset feature change trend corresponding to each transmission cycle based on the offset credibility to obtain the belt offset prediction degree and predicted offset direction;

[0032] The transmission correction control module is used to adjust the real-time position of the roller bracket of the conveyor belt according to the belt deviation prediction degree and the predicted deviation direction when the belt deviation prediction degree is higher than the correction threshold, so as to realize automatic correction of the conveyor belt.

[0033] In a third aspect, the present application provides a computer terminal device, which includes a memory and a processor, wherein the memory stores a code, and the processor is configured to obtain the code and execute the above-mentioned method for automatic belt deviation correction of a belt conveyor.

[0034] In a fourth aspect, the present application provides a computer-readable storage medium, which stores at least one computer program, and the computer program is loaded and executed by a processor to implement the operations performed by the above-mentioned method for automatic belt deviation correction of a belt conveyor.

[0035] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects:

[0036] The present application provides a method and system for automatic deviation correction of a belt conveyor, which comprises the following steps: first, starting the belt conveyor to convey materials through the conveyor belt; collecting bilateral vibration signals of the conveyor belt at different vibration detection points in the current transmission cycle; extracting bilateral vibration characteristic differences based on the bilateral vibration signals at each vibration detection point, performing feature fitting on the bilateral vibration characteristic differences through the corresponding vibration detection point sequence to obtain the deviation characteristic change trend of the conveyor belt; extracting the deviation credibility of the deviation characteristic change trend, and predicting the deviation trend of the deviation characteristic change trend corresponding to each transmission cycle based on the deviation credibility to obtain the predicted degree of belt deviation and the predicted deviation direction; when the predicted degree of belt deviation is higher than the deviation correction threshold, adjusting the real-time position of the roller bracket of the conveyor belt according to the predicted degree of belt deviation and the predicted deviation direction to realize automatic deviation correction of the conveyor belt.

[0037] Therefore, it can be seen that the present application, through real-time collection and difference analysis of bilateral vibration signals, can capture its early trends before physical deviation occurs significantly, providing a priori basis for prediction. It then extracts the bilateral vibration characteristic difference, reflecting the mechanical changes of the belt under load and adapting to the influence of different material stacking states, particle sizes, and weight distributions. Through the distributed layout of multiple vibration detection points, a continuous bilateral vibration characteristic difference sampling sequence is formed, and sequential fitting is performed on it, which can accurately restore the belt deviation trend per unit transmission distance. This trend function does not rely on single-point data, can effectively suppress local disturbances, and improve overall prediction stability. By overlapping and comparing with the deviation characteristic trends of historical cycles, a credibility index of the current trend is obtained, effectively filtering out false deviation signals caused by belt jitter, material drop, etc., and predicting the deviation trend based on the deviation characteristic change trends corresponding to multiple transmission cycles. Compared with traditional correction schemes that rely on passive response after detecting actual deviation, the present application predicts the direction and degree of belt deviation in advance through deviation trend prediction and credibility assessment. And by actively adjusting the roller bracket, it corrects the deviation before it occurs, improving the system's response speed and real-time performance to conveyor belt deviation problems.

[0038] In summary, the present application can predict the deviation based on the bilateral vibration signals of the conveyor belt, thereby improving the real-time performance of the conveyor belt deviation correction. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 This is an exemplary flow chart of a method for automatically correcting the deviation of a belt conveyor according to some embodiments of the present application;

[0040] Figure 2 is a schematic structural diagram of a transmission control unit according to some embodiments of the present application;

[0041] Figure 3 It is a structural schematic diagram of a computer terminal device for implementing a method for automatically correcting the deviation of a belt conveyor belt according to some embodiments of the present application. DETAILED DESCRIPTION

[0042] The present application starts a belt conveyor to transport materials through the conveyor belt; during the current transmission cycle, bilateral vibration signals of the conveyor belt at different vibration detection points are collected; the bilateral vibration characteristic difference is extracted based on the bilateral vibration signals at each vibration detection point, and the bilateral vibration characteristic difference is feature fitted through the corresponding vibration detection point sequence to obtain the offset characteristic change trend of the conveyor belt; the offset credibility of the offset characteristic change trend is extracted, and the offset trend is predicted for the offset characteristic change trend corresponding to each transmission cycle based on the offset credibility to obtain the belt offset prediction degree and predicted offset direction; when the belt offset prediction degree is higher than the correction threshold, the real-time position of the roller bracket of the conveyor belt is adjusted according to the belt offset prediction degree and the predicted offset direction to realize automatic correction of the conveyor belt, and the offset prediction can be performed based on the bilateral vibration signals of the conveyor belt, thereby improving the real-time performance of the conveyor belt correction.

[0043] In order to better understand the above technical solution, the following will be combined with the accompanying drawings and specific implementation methods to describe the above technical solution in detail. Figure 1 , which is an exemplary flow chart of a method for automatically correcting the deviation of a belt conveyor according to some embodiments of the present application. The method 100 for automatically correcting the deviation of a belt conveyor mainly includes the following steps:

[0044] In step S101, the belt conveyor is started to convey materials via the conveyor belt.

[0045] It should be noted that the belt conveyor in this application can realize horizontal conveying, inclined conveying, vertical lifting, and curved conveying according to the layout form. When the conveyor belt is in operation, when the material is not evenly distributed on the center line of the belt, it will cause uneven force on the left and right sides of the belt, thereby generating asymmetric vibration characteristics in the contact area between the belt and the roller. Through real-time collection and difference analysis of vibration signals on both sides, its early trend can be captured before the physical deviation occurs obviously, providing a priori basis for the deviation prediction of the conveyor belt.

[0046] In step S102, a plurality of vibration detection points on the conveyor belt are acquired within a current transmission cycle, and bilateral vibration signals of the conveyor belt at different vibration detection points are collected.

[0047] It should be noted that in the actual conveying process of the belt conveyor, it is difficult to accurately place the material on the center line of the conveyor belt due to factors such as equipment structure limitations, material characteristics, and operating errors. A more common situation is that when multiple devices are connected in series, there is a discharge angle at the discharge port of the feeding equipment, and the falling, impacting and rolling of the material placed on the conveyor belt will cause the material transmission path to deviate from the center line, resulting in uneven force on the conveyor belt, and then generating a lateral component of force to cause the conveyor belt to move toward the heavier side. This application detects the offset of the material by detecting the intensity of the double-sided vibration signal generated when the material passes through the roller during transportation, thereby judging the overload state of the material during transportation, and combining the offset trend prediction with the roller displacement adjustment to achieve real-time automatic deviation correction of the conveyor belt.

[0048] Optionally, in some embodiments, the period length of the transmission cycle can be calibrated based on historical experience, or the transmission cycle can be set to a fixed value of 2s. The transmission cycle refers to a time unit divided by the system in the automatic deviation correction control system of the belt conveyor in order to realize periodic detection, judgment and adjustment of the belt position. In this application, it can be regarded as the feedback interval of the deviation correction control process.

[0049] In some preferred embodiments, a piezoelectric acceleration sensor is used to collect bilateral vibration signals of the conveyor belt at different vibration detection points. The bilateral vibration signals include a left vibration signal and a right vibration signal relative to the running direction of the conveyor belt. The vibration signal is an acceleration signal value in the time domain. The sampling frequency of the bilateral vibration signal is 1Khz.

[0050] It should be noted that vibration detection points refer to specific sensor locations within a belt conveyor system to monitor the lateral forces and dynamic response of the conveyor belt and rollers. In practice, these vibration detection points can be located on both sides of the rollers near the contact surface of the conveyor belt, and multiple groups of these points can be evenly spaced along the conveying direction to form a multi-point monitoring network.

[0051] During operation, when the material falls on the conveyor belt and passes through the belt area covering the surface of the roller, the area usually inevitably has a certain degree of micro-convexity or local uneven structural features, which will cause an asymmetric vibration response when the material passes through. Based on this phenomenon, the present application uses the bilateral vibration signals collected by the acceleration sensors arranged on both sides of the roller to judge the lateral deviation trend of the material during the conveying process by comparing and analyzing the differences in their vibration intensity or spectral characteristics. Compared with the traditional method that only relies on the belt position or visual information, the energy characteristic difference of the bilateral vibration signal can more sensitively reflect the mechanical changes of the belt under load, adapt to the influence of different material stacking states, particle size and weight distribution, and has stronger robustness and generalization.

[0052] In step S103, the bilateral vibration characteristic difference is extracted based on the bilateral vibration signals at each vibration detection point, and the bilateral vibration characteristic difference is feature fitted through the corresponding vibration detection point sequence to obtain the deviation characteristic change trend of the conveyor belt.

[0053] Optionally, in some embodiments, before extracting the bilateral vibration characteristic difference based on the bilateral vibration signals at each vibration detection point, the method also includes: filtering the bilateral vibration signals. In specific implementation, the environmental low-frequency noise can be filtered out by a bandpass filter with a preset frequency band.

[0054] Preferably, in some embodiments, extracting the bilateral vibration characteristic difference based on the bilateral vibration signals at each vibration detection point specifically includes:

[0055] For any vibration detection point, obtain the left vibration signal and the right vibration signal of the bilateral vibration signals of the vibration detection point;

[0056] extracting the average vibration energy features of the left vibration signal and the right vibration signal respectively, and taking the difference between the average vibration energy features as the bilateral vibration feature difference of the vibration detection point;

[0057] The same method is used to obtain the bilateral vibration characteristic differences corresponding to other vibration detection points.

[0058] Preferably, in some embodiments, in the process of extracting the average vibration energy features of the left vibration signal and the right vibration signal, the average vibration energy feature of the left vibration signal may be determined based on the following formula:

[0059] in, is the average vibration energy characteristic of the left vibration signal, is the number of sampling points of the left vibration signal, is the i-th sampling point value of the left vibration signal. In some embodiments of the present application, the sampling value is characterized by acceleration, and the unit is m / s^2.

[0060] It should be noted that the deviation characteristic change trend of the conveyor belt described in the present application is expressed as a characteristic value function of the bilateral vibration characteristic difference based on the change in transmission distance, which is used to reflect the material deviation of each vibration detection point in the current transmission cycle. Preferably, in some embodiments, the deviation characteristic change trend of the conveyor belt is obtained by performing feature fitting on the bilateral vibration characteristic difference through the corresponding vibration detection point sequence, specifically including:

[0061] Obtain multiple bilateral vibration signal differences and their corresponding vibration detection points;

[0062] The transmission distance value corresponding to each vibration detection point is obtained, and the transmission distance value is used as an independent variable to sequentially fit the bilateral vibration signal difference corresponding to each vibration detection point to obtain the deviation characteristic change trend of the conveyor belt.

[0063] Optionally, in some embodiments, a polynomial interpolation method may be used to sequentially fit the bilateral vibration signal differences corresponding to each vibration detection point, or other commonly used sequence fitting methods in the prior art may be used, which is not limited to this.

[0064] In step S104, the offset credibility of the offset feature change trend is extracted, and based on the offset credibility, the offset trend of the offset feature change trend corresponding to each transmission period is predicted to obtain the belt offset prediction degree and the predicted offset direction.

[0065] It should be noted that in this application, the transmission time of the material on the conveyor belt is longer than the transmission cycle. Therefore, the offset credibility of the offset feature change trend corresponding to the current transmission cycle can be judged by the consistency of the detection conditions of the same material transported to different detection points in the offset feature change trend corresponding to the historical transmission cycle, thereby effectively reducing the detection error caused by environmental interference within a single cycle, such as sudden equipment jitter, roller interference, temporary disturbance, etc., and improving the accuracy and stability of offset trend identification. Preferably, in some embodiments, extracting the offset credibility based on the offset feature change trend specifically includes:

[0066] Obtain the offset feature change trend corresponding to the current transmission period, and obtain the offset feature change trends corresponding to multiple historical transmission periods;

[0067] Based on the transmission distance variable of the offset feature change trend and the preset periodic transmission distance, the offset feature change trend corresponding to each historical transmission period is time-aligned with the offset feature change trend corresponding to the current transmission period, and multiple offset feature overlapping areas corresponding to the offset feature change trend of the current transmission period in the offset feature change trends corresponding to the multiple historical transmission periods are obtained;

[0068] By comparing the offset feature change trend of the current transmission period with a plurality of offset feature overlapping areas, the offset credibility corresponding to the offset feature change trend corresponding to the current transmission period is determined.

[0069] In specific implementation, the periodic transmission distance = the transmission speed of the conveyor belt × the transmission period, and the periodic transmission distance is the displacement of the material in adjacent transmission periods. According to the periodic transmission distance, the sliding window matching method can be used to time-align the offset feature change trend corresponding to each historical transmission period with the offset feature change trend corresponding to the current transmission period, and then the mean Pearson correlation coefficient between the trend segment corresponding to the current transmission period and the overlapping segment of each historical trend is obtained as the offset credibility.

[0070] Preferably, in some embodiments, performing an offset trend prediction on the offset characteristic change trend corresponding to each transmission period based on the offset credibility to obtain the belt offset prediction degree and the predicted offset direction specifically includes:

[0071] Obtain the offset feature change trend and corresponding offset credibility corresponding to the current transmission period and multiple historical transmission periods;

[0072] Selecting the offset feature change trend whose offset credibility is higher than a preset credibility threshold, and extracting the corresponding offset feature vector for any offset feature change trend;

[0073] Based on the offset feature vectors corresponding to the change trends of each offset feature and the corresponding transmission cycle sequence, a prediction model of the offset feature vector is constructed to perform prediction and obtain an offset prediction vector;

[0074] Cluster analysis is performed based on the deviation prediction vector to obtain the belt deviation prediction degree and the predicted deviation direction.

[0075] In specific implementation, in the process of extracting the offset feature vector from the offset feature change trend, a group of feature points can be uniformly sampled at equal intervals within a preset interval for each trend curve, and the corresponding offset feature vector can be composed according to the time series.

[0076] Optionally, in some embodiments, a moving average autoregressive algorithm may be used to construct a prediction model for the offset feature vector. The following is a specific embodiment of the present application for constructing a prediction model for the offset feature vector to perform prediction and obtain an offset prediction vector:

[0077] First, the prediction length is preset to 15 transmission cycles. At this time, the offset feature vectors of the conveyor belt in the past five transmission cycles can be recorded separately to obtain a historical offset feature vector sequence. In other embodiments, the prediction length can also be preset to another number of transmission cycles. In order to eliminate the variance drift phenomenon in the historical offset feature vector, the values in each offset feature vector can be logarithmically transformed to improve the stability of the subsequent prediction model. Based on each dimension in the historical offset feature vector, an autocorrelation coefficient graph and a partial autocorrelation coefficient graph are drawn respectively. The horizontal axis is the number of lag cycles and the vertical axis is the correlation coefficient value. The horizontal axis of the time series graph corresponds to different transmission cycles. Then, the time series graph of the offset feature vector sequence set can be exponentially transformed to eliminate the trend of variance changing over time in the time series graph.

[0078] Next, based on the time series graph of the offset eigenvector sequence, an autocorrelation coefficient graph of the offset eigenvector values is plotted, wherein the horizontal axis of the autocorrelation coefficient graph represents the number of lags and the vertical axis represents the value of the autocorrelation coefficient. A partial autocorrelation coefficient graph of the offset eigenvector values is plotted, wherein the horizontal axis of the partial autocorrelation coefficient graph represents the number of lags and the vertical axis represents the value of the partial autocorrelation coefficient.

[0079] According to the characteristics of the autocorrelation coefficient graph and the partial autocorrelation coefficient graph, the order of the model and the range of coefficient values can be preliminarily determined. For example, the autocorrelation coefficient graph can be drawn to observe whether the autocorrelation coefficient shows a truncation characteristic after a certain order. When the autocorrelation coefficient drops sharply after a certain order and remains near 0, the order of the autoregressive model can be preliminarily determined; the partial autocorrelation coefficient graph can be drawn to observe whether the partial autocorrelation coefficient shows a truncation characteristic after a certain order. When the partial autocorrelation coefficient drops sharply after a certain order and remains near 0, the order of the moving average model can be preliminarily determined.

[0080] In specific implementation, we can first use the last significant autocorrelation coefficient as the order of the autocorrelation model according to the autocorrelation coefficient graph. For example, if the last significant autocorrelation coefficient in the autocorrelation coefficient graph is at order 3, the order of the autocorrelation model is 3. Then, according to the partial autocorrelation coefficient graph, we can use the last significant partial autocorrelation coefficient as the order of the moving average model. For example, when the last significant partial autocorrelation coefficient in the partial autocorrelation coefficient graph is at order 2, the order of the moving average model is 2. Finally, according to the autocorrelation coefficient graph and the partial autocorrelation coefficient graph, we can determine the order (p,q) of the autoregressive moving average model. For example, when the autocorrelation coefficient graph and the partial autocorrelation coefficient graph both decay to zero after the third order, the order of the autoregressive moving average model is (3,3); then, according to the order of the autoregressive moving average model, appropriate parameters are selected to establish an autoregressive moving average model of the offset feature vector sequence, and the offset feature vector sequence is brought into the autoregressive moving average model. The offset feature vector value of each subsequent dimension can be predicted, wherein the predicted vector value of each dimension at the end of the next transmission cycle is respectively used as the vector value of the offset prediction vector in the dimension to obtain the offset prediction vector.

[0081] Preferably, in some embodiments, a single hidden layer neural network is used to perform cluster analysis on the offset prediction vector to obtain the belt offset prediction degree and predicted offset direction, specifically including: In this embodiment, in order to achieve effective identification and prediction of the conveyor belt offset trend, a single hidden layer neural network is used to perform cluster analysis on the offset prediction vector to obtain the belt offset prediction degree and predicted offset direction. Specifically, first, an offset prediction vector is constructed based on a vibration characteristic difference sequence of multiple historical transmission cycles. The offset prediction vector is a data vector composed of bilateral vibration characteristic differences corresponding to different detection points, which represents the belt offset trend characteristics caused by the material within the prediction period. The data vector is used as input and input into a single hidden layer neural network for classification training. The single hidden layer neural network includes an input layer, a hidden layer and an output layer, wherein the hidden layer includes multiple activation function nodes for realizing nonlinear mapping and feature compression, and the output layer is used to output the offset cluster classification results. During the training phase, supervised learning is performed using a labeled training dataset. This training dataset includes the material offset prediction vectors corresponding to multiple historical cycles in the experimental environment, as well as a quantitative score and offset direction label for the actual offset degree of the conveyor belt corresponding to each offset prediction vector corresponding to the experimental results. This indicates whether there is a continuous offset trend in the belt during the corresponding time period, whether the offset direction is left or right, and whether the offset degree is low, medium, or high. During the training process, the network connection weights are continuously optimized and the hidden layer node parameters are adjusted through the error backpropagation algorithm until the error between the output clustering result and the true label converges to a preset range. Finally, when the training is completed, the offset prediction vector generated by the current transmission cycle can be input into the trained single hidden layer neural network model, and the prediction results are obtained through the output layer, including the conveyor belt offset prediction degree index, which is used to represent the offset degree prediction amount, and the predicted offset direction, which is used to indicate the left or right offset direction of the belt caused by the material offset, providing a control parameter basis for subsequent correction strategy adjustments and belt stable operation.

[0082] In step S105, when the predicted belt deviation is higher than the deviation correction threshold, the real-time position of the roller support of the conveyor belt is adjusted according to the predicted belt deviation and the predicted deviation direction to achieve automatic deviation correction of the conveyor belt.

[0083] Optionally, in some embodiments, when the predicted degree of belt deviation is lower than the correction threshold, material transportation is performed based on the preset roller support position. In specific implementation, the correction threshold can be calibrated based on multiple tests, which is not elaborated in this application.

[0084] In some preferred embodiments of the present application, when the belt deviation prediction degree is higher than the correction threshold, the correction rollers in the conveying system can be adjusted in real time based on the prediction result to achieve active intervention and dynamic correction of the belt deviation trend. Specifically, the system first monitors the belt deviation prediction degree value corresponding to the current transmission cycle in real time. If the value exceeds the preset deviation sensitivity threshold, it is determined that the current conveying system has a belt deviation risk. Subsequently, the system further obtains the predicted deviation direction corresponding to the current prediction cycle. For example, if the predicted deviation direction is right deviation, it means that the material is concentrated on the right side of the belt, and the correction roller needs to generate a left adjustment torque. Based on this, the system calls the roller control instruction module, uses the belt deviation prediction degree as a control parameter, and outputs a displacement adjustment amount opposite to the predicted direction through the signal amplifier. When the predicted deviation direction is right deviation, the right roller bracket is adjusted forward. In specific implementation, the real-time position of the roller bracket can be adjusted by the electric push rod, thereby changing the support angle of the roller, so that the conveyor belt is subjected to a lateral correction force and gradually returns to the center line before the deviation trend is formed. In practical implementation, a closed-loop feedback mechanism can be incorporated to collect real-time changes in the adjusted vibration detection signal. By comparing the changing trends of the bilateral vibration characteristic differences before and after the adjustment, the roller adjustment range can be dynamically corrected to ensure a stable and non-overshooting adjustment process while avoiding misjudgments caused by mechanical response lag or vibration interference. This approach enables proactive, interventional deviation control without waiting for significant physical deviation of the belt, improving system operational stability and the life of the conveyor equipment.

[0085] This application shifts the problem of belt deviation from result perception to trend prediction, and uses bilateral vibration signals to construct a continuous mechanical state change map, thereby achieving early identification and intelligent intervention of belt deviation, thereby effectively extending equipment life while ensuring conveying efficiency and improving operational safety and automation level.

[0086] In addition, in another aspect of the present application, in some embodiments, the present application provides an automatic deviation correction system for a belt conveyor, the system including a transmission control unit, Figure 2 , which is a schematic diagram of the exemplary hardware and / or software structure of a transmission control unit according to some embodiments of the present application. The transmission control unit 200 includes: a transmission starting module 201, a transmission detection module 202, and a transmission correction control module 203, which are described as follows:

[0087] The transmission start module 201 is used to start the belt conveyor to transport materials through the conveyor belt;

[0088] The transmission detection module 202 is used to collect the bilateral vibration signals of the conveyor belt at different vibration detection points during the current transmission cycle;

[0089] The transmission detection module 202 is further configured to extract bilateral vibration characteristic differences based on bilateral vibration signals at each vibration detection point, perform feature fitting on the bilateral vibration characteristic differences in sequence with corresponding vibration detection points, and obtain a variation trend of the deviation characteristics of the conveyor belt;

[0090] The transmission detection module 202 is further configured to extract the offset credibility of the offset feature change trend, and perform offset trend prediction on the offset feature change trend corresponding to each transmission cycle based on the offset credibility to obtain the belt offset prediction degree and predicted offset direction;

[0091] The transmission correction control module 203 is used to adjust the real-time position of the roller bracket of the conveyor belt according to the belt deviation prediction degree and the predicted deviation direction when the belt deviation prediction degree is higher than the correction threshold, so as to realize automatic correction of the conveyor belt.

[0092] The above describes in detail an example of a method and system for automatic belt deviation correction of a belt conveyor provided in an embodiment of the present application. It can be understood that in order to realize the above functions, the corresponding device includes hardware structures and / or software modules corresponding to executing each function.

[0093] Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function in the application is executed in hardware or in a computer software-driven hardware manner depends on the specific application and design constraints of the technical solution. Therefore, professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0094] In addition, the present application also provides a computer terminal device, which includes a memory and a processor, wherein the memory stores a code, and the processor is configured to obtain the code and execute the above-mentioned method for automatically correcting the belt deviation of a belt conveyor.

[0095] In some embodiments, reference Figure 3 , which is a schematic diagram of the structure of a computer terminal device for implementing a method for automatically correcting the deviation of a belt conveyor according to some embodiments of the present application. Figure 3 The computer terminal device 300 shown in FIG. 1 is implemented as shown in FIG. 1 , and the computer terminal device 300 includes at least one communication bus 301 , a communication interface 302 , a processor 303 and a memory 304 .

[0096] The processor 303 can be a general-purpose central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more processors for controlling the execution of a method for automatically correcting the belt deviation of a belt conveyor in the present application.

[0097] The communication bus 301 may include a path for transmitting information between the aforementioned components.

[0098] Memory 304 may be, but is not limited to, a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, a random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disk storage, an optical disk storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), a magnetic disk or other magnetic storage device, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer. Memory 304 may be independent and connected to processor 303 via communication bus 301. Memory 304 may also be integrated with processor 303.

[0099] Memory 304 is used to store program code for implementing the present invention, and is controlled by processor 303 for execution. Processor 303 is configured to execute the program code stored in memory 304. The program code may include one or more software modules. In the above embodiment, the determination of the belt deflection prediction accuracy can be implemented by processor 303 and one or more software modules in the program code stored in memory 304.

[0100] The communication interface 302 uses any transceiver or other device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area network (WLAN), etc.

[0101] Optionally, the computer terminal device 300 may further include a power supply 305 for providing power to various devices or circuits in the real-time computer terminal device.

[0102] In a specific implementation, as an example, a computer terminal device may include multiple processors, each of which may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. A processor herein may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0103] The aforementioned computer terminal device can be a general-purpose computer terminal device or a dedicated computer terminal device. In a specific implementation, the computer terminal device can be a desktop computer, a portable computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. The embodiments of this application do not limit the type of computer terminal device.

[0104] In addition, in other aspects of the present application, a computer-readable storage medium is provided, which stores at least one computer program, and the computer program is loaded and executed by a processor to implement the operations performed by the above-mentioned method for automatic belt deviation correction of a belt conveyor.

[0105] In summary, in an automatic deviation correction method and system for a belt conveyor disclosed in an embodiment of the present application, the belt conveyor is first started to convey materials through the conveyor belt; within the current transmission cycle, bilateral vibration signals of the conveyor belt at different vibration detection points are collected; bilateral vibration characteristic differences are extracted based on the bilateral vibration signals at each vibration detection point, and feature fitting is performed on the bilateral vibration characteristic differences through the corresponding vibration detection point sequence to obtain the deviation characteristic change trend of the conveyor belt; the deviation credibility of the deviation characteristic change trend is extracted, and the deviation trend of the deviation characteristic change trend corresponding to each transmission cycle is predicted based on the deviation credibility to obtain the belt deviation prediction degree and predicted deviation direction; when the belt deviation prediction degree is higher than the deviation correction threshold, the real-time position of the roller bracket of the conveyor belt is adjusted according to the belt deviation prediction degree and the predicted deviation direction to realize automatic deviation correction of the conveyor belt, and the deviation prediction can be performed based on the bilateral vibration signals of the conveyor belt, thereby improving the real-time performance of the deviation correction of the conveyor belt.

[0106] The above description is merely an embodiment of the present application. Common knowledge such as the specific technical solutions or features of the solutions is not described in detail herein. It should be noted that those skilled in the art may make various modifications and improvements without departing from the technical solution of the present application, and these modifications and improvements should also be considered within the scope of protection of the present application. These modifications and improvements will not affect the effectiveness of the implementation of the present application or the practical application of the patent.

[0107] The scope of protection claimed by this application shall be determined by the content of the claims. The specific embodiments and other descriptions in the specification may be used to interpret the content of the claims. Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of the invention. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application is intended to include such modifications and variations.

Claims

1. A method for automatically correcting the deviation of a belt conveyor, characterized in that: include: Start the belt conveyor to transport the materials through the conveyor belt; During the current transmission cycle, bilateral vibration signals of the conveyor belt at different vibration detection points are collected; Extracting bilateral vibration characteristic differences based on bilateral vibration signals at each vibration detection point, performing feature fitting on the bilateral vibration characteristic differences through the corresponding vibration detection point sequence, and obtaining a variation trend of the deviation characteristics of the conveyor belt; Extracting the offset credibility of the offset feature change trend, and performing offset trend prediction on the offset feature change trend corresponding to each transmission cycle based on the offset credibility to obtain the belt offset prediction degree and predicted offset direction; When the predicted belt deviation is higher than the deviation correction threshold, the real-time position of the roller support of the conveyor belt is adjusted according to the predicted belt deviation and the predicted deviation direction to achieve automatic deviation correction of the conveyor belt.

2. The method according to claim 1, wherein The real-time position of the roller bracket is adjusted by an electric push rod.

3. The method according to claim 1, wherein Piezoelectric acceleration sensors are used to collect bilateral vibration signals of the conveyor belt at different vibration detection points.

4. The method according to claim 1, wherein Before extracting the bilateral vibration characteristic difference based on the bilateral vibration signals at each vibration detection point, the method further includes: filtering the bilateral vibration signals.

5. The method according to claim 1, wherein Extracting bilateral vibration characteristic differences based on bilateral vibration signals at each vibration detection point specifically includes: For any vibration detection point, obtain the left vibration signal and the right vibration signal of the bilateral vibration signals of the vibration detection point; extracting the average vibration energy features of the left vibration signal and the right vibration signal respectively, and taking the difference between the average vibration energy features as the bilateral vibration feature difference of the vibration detection point; The same method is used to obtain the bilateral vibration characteristic differences corresponding to other vibration detection points.

6. The method according to claim 1, wherein The characteristic fitting of the bilateral vibration characteristic difference is performed by the corresponding vibration detection point sequence, and the deviation characteristic change trend of the conveyor belt is obtained, which specifically includes: Obtain multiple bilateral vibration signal differences and their corresponding vibration detection points; The transmission distance value corresponding to each vibration detection point is obtained, and the transmission distance value is used as an independent variable to sequentially fit the bilateral vibration signal difference corresponding to each vibration detection point to obtain the deviation characteristic change trend of the conveyor belt.

7. The method according to claim 1, wherein Based on the offset credibility, the offset feature change trend corresponding to each transmission cycle is predicted, and the belt offset prediction degree and predicted offset direction are obtained. Specifically, the following are included: Obtain the offset feature change trend and corresponding offset credibility corresponding to the current transmission period and multiple historical transmission periods; Selecting the offset feature change trend whose offset credibility is higher than a preset credibility threshold, and extracting the corresponding offset feature vector for any offset feature change trend; Based on the offset feature vectors corresponding to the change trends of each offset feature and the corresponding transmission cycle sequence, a prediction model of the offset feature vector is constructed to perform prediction and obtain an offset prediction vector; Cluster analysis is performed based on the deviation prediction vector to obtain the belt deviation prediction degree and the predicted deviation direction.

8. An automatic belt deviation correction system for an adhesive tape conveyor, comprising a transmission control unit, wherein the transmission control unit is configured to execute the automatic belt deviation correction method for an adhesive tape conveyor according to any one of claims 1 to 7, wherein: The transmission control unit includes: The transmission start module is used to start the belt conveyor and transport the materials through the conveyor belt; A transmission detection module, configured to collect bilateral vibration signals of the conveyor belt at different vibration detection points during a current transmission cycle; The transmission detection module is further used to extract bilateral vibration characteristic differences based on bilateral vibration signals at each vibration detection point, and perform feature fitting on the bilateral vibration characteristic differences through the corresponding vibration detection point sequence to obtain the deviation characteristic change trend of the conveyor belt; The transmission detection module is further configured to extract the offset credibility of the offset feature change trend, and perform offset trend prediction on the offset feature change trend corresponding to each transmission cycle based on the offset credibility to obtain the belt offset prediction degree and predicted offset direction; The transmission correction control module is used to adjust the real-time position of the roller bracket of the conveyor belt according to the belt deviation prediction degree and the predicted deviation direction when the belt deviation prediction degree is higher than the correction threshold, so as to realize automatic correction of the conveyor belt.

9. A computer terminal device, characterized in that: The computer terminal device includes a memory and a processor, the memory stores a code, and the processor is configured to obtain the code and execute the automatic deviation correction method for a belt conveyor according to any one of claims 1 to 7.

10. A computer-readable storage medium storing at least one computer program, characterized in that: The computer program is loaded and executed by a processor to implement the operations performed by the method for automatic deviation correction of a belt conveyor belt as claimed in any one of claims 1 to 7.

Images