A method for controlling loading of material

Abstract

The present application relates to a kind of material loading control method, comprising: collecting the volume data of loading material in time period, calculate volume according to the volume data collected, utilize fitting algorithm to calculate mapping relationship;Install camera device, real-time capture material flow image, use algorithm to calculate flowability parameter in flow velocity vector field;The flowability parameter calculated is substituted into mapping relationship, and mapping relationship is revised, and the volume mapping relationship model after revision is established;The prediction result is compared with the volume of material monitored in real time, and control parameter is dynamically adjusted according to the comparison result, by real-time monitoring the volume of material and flowability parameter, dynamically adjusts control parameter according to the volume mapping relationship model after revision, deviation in loading process can be found and corrected in time, improve the control precision of material loading.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of automation, and in particular to a material loading control method. BACKGROUND

[0002] In modern industrial production, material loading is a key link that directly affects the efficiency and accuracy of the production line. With the continuous development of automation and intelligent technology, accurate control of the material loading process has become an urgent demand in the industry. Traditional material loading methods often rely on manual operation and experience-based judgment, which has low efficiency and large errors. Therefore, it is particularly important to develop an efficient and accurate material loading control method. The core of the material loading control method is the real-time monitoring and accurate prediction of the volume and flow state of the material. In the past, due to technical limitations, the volume of the material was often measured by estimation or intermittent measurement, which not only has limited accuracy but also cannot reflect the changes in the volume of the material in real time. With the advancement of sensor technology and data processing algorithms, continuous and real-time material volume data collection can now be achieved. By installing appropriate sensors such as laser scanners, stereo vision systems, etc., the volume changes of the material during the loading process can be accurately measured, providing accurate data basis for subsequent control.

[0003] For example, Chinese patent application No. 202411237495.X discloses a material loading control method and device. The method is to determine the loading material weight and volume corresponding to multiple sampling times in a first time period; determine the total length of time in a second time period based on the loading material weight corresponding to the multiple sampling times; determine the first mapping relationship between the target time and the loading material volume based on the loading material volume corresponding to the multiple sampling times; determine the target loading material volume corresponding to the target sampling time based on the first mapping relationship and the total length of time; and determine the parameter value of the control parameter in the second time period based on the target loading material volume. This method uses the target sampling time as the time point of the full loading of the material, accurately calculates the loading volume of the material under full loading conditions, and adjusts the parameter value of the control parameter in the second time period based on the target loading material volume to achieve accurate material loading under full loading conditions and effectively improve the accuracy of material loading.

[0004] In existing patent documents, relying solely on volume data is not enough to achieve accurate material loading control. The material flow is affected by various factors such as the speed of the conveyor belt, the physical properties of the material (such as density, shape, friction coefficient, etc.), and possible collision and adhesion phenomena. These factors can cause instability in the material flow state, affecting the accuracy and efficiency of loading. Therefore, real-time monitoring and identification of the flow state of the material are needed. SUMMARY

[0005] The present application aims at the technical problems existing in the prior art, and provides a material loading control method, which can timely find and correct the deviation in the loading process by monitoring the volume and flowability parameters of the material in real time and dynamically adjusting the control parameters according to the corrected volume mapping relationship model, so as to improve the control precision of the material loading.

[0006] The technical scheme for solving the above technical problems is as follows: a material loading control method, comprising:

[0007] S101, collecting volume data of the loading material in a time period, calculating the volume according to the collected volume data, and calculating the mapping relationship between the target time and the volume of the loading material by using a fitting algorithm;

[0008] S102, installing a camera device, capturing the material flow image in real time according to the camera device, identifying the state change of the material in the flow process, and calculating the flowability parameter in the flow velocity vector field by using an algorithm;

[0009] S103, substituting the calculated flowability parameter into the mapping relationship in step S101, correcting the mapping relationship, and establishing a corrected volume mapping relationship model;

[0010] S104, comparing the prediction result of the corrected volume mapping relationship model with the volume of the material monitored in real time, and dynamically adjusting the control parameter according to the comparison result.

[0011] Preferably, the mapping relationship between the target time and the volume of the loading material is V=f(t;θ)=at+b, wherein V is the volume of the loading material, indicating the volume size of the loading material at a certain time t; t is the target time, indicating the time interval from the start of loading to a certain sampling time, used to indicate the time progress in the loading process; a is the slope parameter, indicating the rate of change of the volume of the loading material with time, determining the degree of increase of the volume with time, if a is positive, indicating that the volume increases with time; if a is negative, indicating that the volume decreases with time; b is the intercept parameter, indicating the initial volume of the loading material when the time t=0; θ is a parameter set, containing all parameters for describing the mapping relationship, θ={a,b}.

[0012] Preferably, the flowability parameter includes the average flow velocity and the standard deviation of the flow velocity, the average flow velocity is calculated by the formula: , wherein, represents the average flow velocity, represents the module of the i-th flow velocity vector, that is, the size of the vector, and N represents the total number of vectors in the flow velocity vector field.

[0013] Preferably, the standard deviation of the flow velocity is calculated using the following formula: ,in, The standard deviation of the flow rate is represented by the standard deviation of the flow rate. This represents the difference between the magnitude of the i-th velocity vector and the average velocity. Let N represent the magnitude of the i-th velocity vector, i.e., the size of the vector, and let N represent the total number of vectors in the velocity vector field.

[0014] Preferably, by substituting the flowability parameter into the mapping relationship between the target time and the volume of material loaded, we obtain: a′=a+ × + × Where a′ is the slope parameter corrected based on the liquidity parameter. and It is a correction coefficient, which represents the degree of influence of the average flow velocity and the standard deviation of the flow velocity distribution on the parameter a. The correction coefficient is determined through experiments or data fitting. Substituting the corrected slope parameter into the mapping relationship, we get the formula: V=f(t); ′)=a′t+b, where, ' represents the corrected set of parameters. ′={a′,b}.

[0015] Preferably, the specific steps for identifying the state changes of materials during the flow process are as follows:

[0016] S201, Several static identification units are set on the conveyor belt for conveying materials according to the width, length and speed of material flow of the conveyor belt;

[0017] S202, the static recognition unit identifies the changing state of the material and determines whether the material is sticky. If the material particles are connected together and the area of ​​the connected part exceeds 15% of the total area of ​​the particles, the material is in a sticky state. Otherwise, the material is not sticky.

[0018] Preferably, the conveyor belt is divided into an inlet pre-inspection area, a dynamic balancing area, and a loading positioning area. The inlet pre-inspection area is located at the silo, the dynamic balancing area is located at the geometric center of the longest horizontal section of the conveyor belt, and the loading positioning area is located at the material unloading point.

[0019] Preferably, the method for identifying changes in the state of materials further includes:

[0020] S301, Collect material data and build a material movement trajectory prediction model based on the collected material data;

[0021] S302, when there is an undetected material contour in the identification result, inputting the image into a material motion trajectory prediction model to predict the undetected material contour;

[0022] S303, integrating the constructed material motion trajectory prediction model with the loading control system.

[0023] Preferably, the method for constructing the material motion trajectory prediction model further comprises:

[0024] S401, setting a dynamic identification unit on the conveying belt according to the sensing data of the material;

[0025] S402, establishing a physical model according to the collected sensing data, identifying information of a collision event that has occurred historically according to the dynamic identification unit and the physical model, establishing a collision event library, and extracting a rule of collision event occurrence according to the established collision event library;

[0026] S403, classifying a bouncing mode according to the data in the collision event library, and establishing a material flow prediction system according to the bouncing mode and the rule of collision event occurrence.

[0027] Preferably, the bouncing mode comprises straight-line bouncing and rotational bouncing, the straight-line bouncing is that the material bounces along a straight-line trajectory after collision, and the rotational bouncing is that the material rotates simultaneously after collision.

[0028] The present application has the advantages that: by monitoring the volume and flowability parameters of the material in real time and dynamically adjusting the control parameters according to the corrected volume mapping relationship model, deviations in the loading process can be found and corrected in time, the control precision of the material loading is improved, the loading failure caused by the change of the flow characteristics of the material is reduced, the high-speed camera device and the flowability parameter are introduced, the flow characteristics of the material are monitored in real time, the control parameters are dynamically adjusted, the change of the flow characteristics of the material can be better adapted, and the stability and precision of the loading process are improved;

[0029] By setting a plurality of static identification units on the conveying belt, the state change of the material in high-speed flow is accurately identified, the loading control system dynamically adjusts the control parameters according to the change of the material state, the residual of the viscous material on the conveying belt is reduced, the loading precision and stability are improved, the improvement of the loading precision reduces the error of the loading amount, improves the accuracy of the loading, reduces the waste of the material and the increase of the cost caused by the error, the improvement of the loading stability reduces the fluctuation and failure in the loading process, improves the reliability and safety of the loading, reduces the downtime and maintenance cost caused by the failure, and the like.

[0030] The material motion trajectory prediction model is established and verified, the complete contour information of the blocked material is inferred, and the control parameters of the loading control system are optimized, the material motion trajectory prediction model makes the identification have higher accuracy, improves the adaptability of the loading system, reduces the residue of the viscous material on the conveying belt, and improves the loading precision and stability.

[0031] The collision and bouncing phenomenon of the material is accurately identified through the dynamic identification unit, the dynamic process at the collision moment is restored, the rules are extracted from the historical collision records, the early warning and prediction support are provided for the material flow under similar conditions, the valuable collision rules are extracted from the historical data, and a scientific basis is provided for the early warning and prediction of the material flow, through the enhanced function of the dynamic identification unit, the collision and bouncing phenomenon of the material can be more accurately identified, and the comprehensiveness and accuracy of the material state identification are improved, and the collision event library further improves the efficiency and stability of the material flow. BRIEF DESCRIPTION OF DRAWINGS

[0032] Figure 1 It is a flowchart of the material loading control method of the application;

[0033] Figure 2 It is a flowchart of the identification of the state change of the material in the flow process of the application;

[0034] Figure 3 It is a flowchart of the identification of the change state of the material of the application;

[0035] Figure 4 It is a flowchart of the construction of the material motion trajectory prediction model of the application. DETAILED DESCRIPTION

[0036] The technical solutions in the embodiments of the application will be clearly and completely described below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, not all the embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the application.

[0037] In the description of the application, the terms "first", "second" are used only for the purpose of description, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Therefore, the features limited by "first", "second" can explicitly or implicitly include one or more of the features. In the description of the application, the meaning of "multiple" is two or more, unless otherwise specifically limited.

[0038] In the description of the present application, the word "for example" is used to indicate "serving as an example, instance, or illustration." Any embodiment described as "for example" in this application is not necessarily to be construed as preferred or advantageous over other embodiments. The following description is presented to enable any person skilled in the art to make and use the application. In the following description, for the purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the present application. It will be apparent, however, to one skilled in the art that the present application can be practiced without using these specific details. In other instances, well-known structures and processes are not elaborated upon in order to avoid unnecessary detail and so as to not obscure the present application. Thus, the present application is not intended to be limited by the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.

[0039] Embodiment 1: Figure 1 is a flowchart of a material loading control method according to an embodiment of the present application, comprising the following steps:

[0040] S101, collecting volume data of the loading material in a time period, calculating the volume according to the collected volume data, and calculating the mapping relationship between the target time and the volume of the loading material by using a fitting algorithm;

[0041] Specifically, the time period is a time period in which the volume of the loaded material changes from a first value to a second value, a preset laser radar is used to collect point cloud data of the loaded material, the preset laser radar is installed in the silo and is used to obtain three-dimensional shape information of the material, the laser radar forms a series of three-dimensional coordinate points by emitting laser and receiving reflected signals, the three-dimensional coordinate points constitute the point cloud data of the material, the point cloud data includes geometric features such as the shape, spatial position and size of the surface of the material, the bottom area of the material car is obtained by measurement, based on the point cloud data collected by the preset laser radar, a three-dimensional model of the material can be constructed using a Delaunay triangulation three-dimensional modeling technology, height information of the material is extracted from the constructed three-dimensional model, the height is a size of the material in a real-time vertical direction in the loading space, based on the real-time height of the material, the bottom area of the material and the shaped form of the material, a geometric calculation method is used to calculate the volume of the loaded material, if the shape of the material is approximately regular (such as a cuboid, a cylinder and the like), a corresponding volume formula can be directly used for calculation; if the shape of the material is irregular, the space of the silo can be divided into a plurality of small volume units (such as small cuboids or triangular prisms and the like), then volume calculation is performed on each small volume unit, and finally the volumes of all the small volume units are added to obtain a total volume, a fitting algorithm GBRT is used to fit the volumes of the loaded material corresponding to a plurality of sampling times in the time period, to obtain a mapping relationship between a target time and the volume of the loaded material: V=f(t;θ)=at+b, wherein V is the volume of the loaded material, represents the volume size of the loaded material at a certain time t; t is the target time, represents a time interval from the start of loading to a certain sampling time, and is used to represent the time progress in the loading process; a is a slope parameter, represents a rate at which the volume of the loaded material changes with time, and determines how fast the volume increases with time; if a is positive, the volume increases with time; if a is negative (which is not likely in an actual loading process), the volume decreases with time; b is an intercept parameter, representing an initial volume of the loaded material when t=0. In actual application, b represents the volume of the empty car at the start of loading (if the net increase volume is considered) or a certain reference volume value; θ (in the general form) is a parameter set, including all parameters used to describe the mapping relationship, θ={a,b}.

[0042] S102, install a camera device, capture material flow images in real time according to the camera device, and calculate a flowability parameter in a flow velocity vector field using an algorithm;

[0043] Further, according to the environmental conditions of the loading site, the HS1000 camera is selected, and the high-speed camera is debugged, including adjusting the focal length, aperture and exposure time and other parameters, to ensure that the camera can capture clear images, and the color and brightness of the images meet the actual needs, to observe whether the images captured by the camera are stable, whether there are shaking or blurring phenomena, to perform calibration operations to ensure that the images captured are consistent with the actual material flow situation;

[0044] The high-speed camera is started, and the images of the material flow are captured in real time, the captured images are converted into gray images, the Gaussian filter is used to remove the noise in the images, the image quality is improved, the contrast of the images is enhanced to more clearly show the details of the material flow, the optical flow algorithm Lucas-Kanade is used to calculate the motion vector of the pixels between adjacent frames, the motion vector represents the flow velocity of the material on the image plane, the calculated motion vector is combined into a flow velocity vector field to represent the flow situation of the material in the entire image area, the flowability parameters include the average flow velocity and the standard deviation, the average value of all vectors in the flow velocity vector field is calculated, the formula is: wherein, represents the average flow velocity, represents the module length of the i-th flow velocity vector, that is, the size of the vector, without considering the direction, and N represents the total number of vectors in the flow velocity vector field. In image processing, this usually corresponds to the number of all flow vectors detected in the image, the standard deviation of the vector module length in the flow velocity vector field is calculated, the formula is: wherein, represents the standard deviation of the flow velocity, represents the difference between the module length of the i-th flow velocity vector and the average flow velocity.

[0045] S103, the calculated flowability parameters are substituted into the mapping relationship in step S101 to correct the mapping relationship, and a corrected volume mapping relationship model is established;

[0046] Specifically, the flowability parameters include the average flow velocity and the standard deviation of the flow velocity distribution, the flowability parameters are substituted into the mapping relationship between the target time and the loading material volume to obtain: a′=a+ × + × wherein, a′ is a slope parameter corrected according to the flowability parameters, and is a correction coefficient, which represents the influence degree of the average flow velocity and the standard deviation of the flow velocity distribution on the parameter a, the correction coefficient is determined through experiments or data fitting, the corrected slope parameter is substituted into the mapping relationship to obtain the formula: V=f(t; ′)=a′t+b, wherein, denotes the revised parameter set, where denotes the revised parameter set, where

[0047] According to the revised volume mapping relationship model, the machine learning algorithm decision tree is used to establish the revised volume mapping relationship model. In the modeling process, the influence of the liquidity parameter on the volume mapping relationship is considered, and it is included in the structure and parameters of the model. According to the selected modeling method, the preliminary structure of the model is constructed, including the liquidity parameter and other influencing factors are determined as the input variables of the model, and the volume mapping relationship is determined as the output variable of the model. The training data set is used to fit the model, the training data is input into the model, the parameters of the model are adjusted through the optimization algorithm to minimize the prediction error, cross-validation and other methods are used to evaluate the generalization ability of the model and prevent overfitting. After fitting the training data, the preliminary parameters and form of the model are obtained, and the model can predict the output variable according to the input variable.

[0048] S104, according to the prediction result of the revised volume mapping relationship model, comparing the prediction result with the volume of the material monitored in real time, and dynamically adjusting the control parameter according to the comparison result;

[0049] Further, the volume and liquidity parameter of the material are collected in real time by using a high-speed camera device, and the collected volume and liquidity parameter are input into the revised volume mapping relationship model. The model calculates the predicted volume of the material according to the input data, compares the prediction result of the model with the actual loading condition, and monitors whether there is deviation. By adjusting the unloading speed and the telescopic length of the unloading chute, if the deviation is positive, the unloading speed is slowed down to reduce the amount of material entering the loading machine per unit time, thereby reducing the deviation of the loading volume, and the telescopic length of the unloading chute is shortened to reduce the material accumulation, thereby reducing the deviation of the loading volume. If the deviation is negative, the unloading speed is increased to increase the amount of material entering the loading machine per unit time, thereby increasing the loading volume and reducing the deviation, and the telescopic length of the unloading chute is extended to increase the material accumulation, thereby reducing the deviation of the loading volume. The control parameter is adjusted in real time to ensure smooth transition during the adjustment process and avoid impact or interference on the loading process. After adjusting the control parameter, the loading condition of the material is continuously monitored in real time.

[0050] The technical solutions in the embodiments of the present application have at least the following technical effects or advantages: improve the accuracy of volume prediction, improve the accuracy of material loading, reduce the failure of loading, by monitoring the volume and flowability parameters of the material in real time, dynamically adjusting the control parameters (such as the extension length of the feeding chute, the feeding speed, etc.) according to the corrected volume mapping relationship model, the deviation in the loading process can be found and corrected in time, the control accuracy of material loading is improved, the failure of loading caused by the change of material flow characteristics is reduced, the high-speed camera device and the flowability parameter are introduced, by monitoring the flow characteristics of the material in real time, dynamically adjusting the control parameters, the change of the material flow characteristics can be better adapted, and the stability and accuracy of the loading process are improved.

[0051] In example 2, based on the material in example 1, due to factors such as collision and friction, the material particles are broken or adhered to each other, this embodiment identifies the state change of the material in high-speed flow, and dynamically adjusts the control parameters according to the state change of the material.

[0052] As shown in Figure 2 The specific steps for identifying the state change of the material in the flow process are as follows:

[0053] S201, according to the width, length and material flow speed of the conveying belt, a plurality of static recognition units are arranged on the conveying belt conveying material;

[0054] Specifically, the static recognition unit is a system arranged on the conveying belt, which is used to identify the state change of the material (such as breaking or adhering) when the material flows at high speed, to monitor the state of the material in the conveying process in real time, a laser range finder obtains the accurate size of the conveying belt, measures the total length, width and slope of the conveying belt, and sets static recognition units in the entrance pre-check area, dynamic balance area and loading positioning area of the conveying belt. For the entrance pre-check area, one static recognition unit is arranged in the entrance pre-check area, the entrance pre-check area is near the stock bin, and the entrance pre-check area covers the full width of the conveying belt plus a certain distance on both sides. The two sides are extended to prevent material from overflowing from the edges. For the dynamic balance area, two static recognition units are arranged in the dynamic balance area, the dynamic balance area is located at the geometric center of the longest horizontal section of the conveying belt, and avoids vibration sources (such as reducers and sorting mechanisms). For the loading positioning area, one static recognition unit is arranged in the loading positioning area, the loading positioning area is near the material unloading point, the number of static recognition units is determined according to the length of the conveying belt and the material flow path, to monitor the state change of the material in the loading process in real time, the distance between the static recognition units is adjusted according to the material state change frequency on the conveying belt, to ensure that the material is always in a monitored state during the flow process, and a marking tool is used to spray paint to mark the planned static recognition unit installation position on the conveying belt.

[0055] Specific example: the conveying belt width is 1.2 meters, the conveying belt length is 30 meters, the material flow speed is 2 meters per second, the conveying belt slope is an overall flat slope, but contains several horizontal sections and slightly inclined sections, the number of static recognition units in the entrance pre-check area is 1, the entrance pre-check area is located at the entrance end of the conveying belt, at a distance of at least 5 meters from the stock bin, the static recognition unit in the entrance pre-check area is set at the central position of the entrance end, which covers the full width of the conveying belt plus an extension of 10 centimeters on both sides, i.e. the total width is 1.4 meters, to prevent the material from overflowing from the edges and not being detected; the number of static recognition units in the dynamic balance area is 2, the dynamic balance area is located at the geometric center of the longest horizontal section of the conveying belt, and avoids vibration sources such as reducers, sorting mechanisms, the two static recognition units in the dynamic balance area are respectively set on the front and rear sides of the geometric center of the horizontal section, about 5 meters apart, ensuring continuous monitoring of the dynamic balance state of the material in the flow process, and through the cooperative work of the two units, the accuracy and reliability of the monitoring can be improved; the number of static recognition units in the loading positioning area is 1, the loading positioning area is 1.2 meters away from the material unloading point, and the static recognition unit in the loading positioning area is accurately set 1.2 meters in front of the unloading point, to ensure that the last state of the material before unloading can be accurately captured, and the purpose is to accurately monitor the state of the material when it is about to be unloaded, to ensure the smooth progress of the loading process and avoid material overflow or uneven loading. The distance between the entrance pre-check area and the dynamic balance area: according to the layout of the conveying belt and the monitoring requirements, it is set to 10-15 meters to cover the process of the material entering the conveying belt to reaching the dynamic balance area, the distance in the dynamic balance area: the two static recognition units are 5 meters apart to ensure continuous and intensive monitoring of the material state, the distance between the dynamic balance area and the loading positioning area: determined according to the remaining length of the conveying belt and the material flow speed to ensure that the material is always in a monitored state during the flow process.

[0056] S202, according to the change state of the material recognized by the static recognition unit, it is judged whether the material is adhered, if the material particles are connected together, and the area of the connected part exceeds 15% of the total area of the particles, that is, the material is in the adhered state, otherwise, the material is not adhered;

[0057] Further, according to the physical properties of the material, the area ratio threshold is set to 15%, and whether the set identification threshold is reasonable is verified through experiments. Different types of materials and flow rates are used for testing, the identification effect of the identification unit is observed, and relevant data is recorded. According to the test results, the identification threshold is fine-tuned to ensure its accuracy in the actual production process. When two or more material particles are connected together and the area of the connection part exceeds 15% of the total area of the particles, it is determined that the material is adhered, otherwise, the material is not adhered. When the material flows through the static identification unit, the static identification unit captures the laser reflection signal of the material in real time. The laser reflection signal contains the surface shape, color, texture and other characteristic information of the material. The static identification unit compares the captured signal with the set identification threshold to determine whether the material is in an adhered state. The static identification unit is integrated with the loading control system. If the static identification unit determines that the material is in an adhered state, it immediately sends a signal to the loading control system. This signal contains information such as the position and degree of the adhered material. After receiving the signal, the loading control system will adjust the speed of the conveyor belt according to the pre-set control logic to change the flow state of the material, or change the loading position to avoid the adhered material entering the loading area.

[0058] The technical solutions in the above embodiments of the present application have at least the following technical effects or advantages: By setting a plurality of static identification units on the conveyor belt, the state change of the material in high-speed flow is accurately identified. The loading control system dynamically adjusts the control parameters according to the change of the material state, reduces the residue of the viscous material on the conveyor belt, and improves the loading accuracy and stability. The improvement of the loading accuracy reduces the error of the loading amount, improves the accuracy of the loading, reduces the waste of materials and the increase of costs caused by errors, and improves the reliability and safety of the loading. The improvement of the loading stability reduces the fluctuations and faults in the loading process, improves the reliability and safety of the loading, and reduces the downtime and maintenance costs caused by faults.

[0059] Embodiment 3: Based on the fact that in the process of high-speed flow of the material in Embodiment 2, the materials are easily blocked and overlapped due to high-speed flow, affecting the accuracy of material identification, this embodiment establishes a material motion trajectory model to infer the complete contour information of the blocked material, further improving the accuracy of material identification.

[0060] As shown in Figure 3 , the method for identifying the change state of the material further includes

[0061] S301, collecting data of the material, and constructing a material motion trajectory prediction model according to the collected material data;

[0062] Specifically, the data of the material includes physical property data and flow characteristic data. For the physical property data, it includes the density, shape and friction coefficient of the material. The density data is used to understand the mass distribution of the material, the shape data reflects the force condition of the material in the flow process, and the friction coefficient is an important parameter of the interaction between the material and the contact surface. The data is directly obtained through experimental measurement, and the collected physical property data is recorded. For the flow data, it includes flow rate and pressure distribution. The flow rate data is used to reflect the speed and direction of the material flow, and the pressure distribution reveals the mechanical action of the material in the flow process. The flow rate and pressure distribution are measured through experiments. The collected physical property data and flow data are preprocessed. Data cleaning is to remove error or abnormal data points, denoising is to smooth the data curve and reduce fluctuations, and normalization is to scale the data to a unified range.

[0063] A neural network in a machine learning algorithm is used to construct a material motion trajectory prediction model. The neural network includes an input layer, a hidden layer and an output layer. The input layer receives the preprocessed material physical property and flow characteristic data, and the output layer outputs the predicted material motion trajectory. The number of layers and the number of neurons in each layer of the hidden layer need to be adjusted and optimized according to specific problems. ReLU activation function is selected to increase the nonlinear expression ability of the model. The preprocessed data is divided into training set and test set. The training set is used to train the model, and the test set is used to evaluate the prediction performance of the model. The neural network model is trained using the training set data. Through optimization methods such as back propagation algorithm and gradient descent algorithm, the model parameters are adjusted to minimize the loss function. During the model training process, special attention is paid to the influence of the occlusion area. A specific network structure is designed to handle the information loss problem of the occlusion area. The test set data is used to test the trained neural network model. The accuracy, error rate and other indicators of the model are recorded to evaluate the prediction performance of the model. The model prediction result is compared with the actual data to evaluate the prediction accuracy of the model.

[0064] S302, according to the image recognized by the static recognition unit, when there is an undetected material contour in the recognition result, inputting the image to a material motion trajectory prediction model to predict the undetected material contour;

[0065] Further, the image recognized by the static recognition unit is processed using an image enhancement algorithm. The pre-processed image is processed using CLAHE to improve the brightness, contrast, and clarity of the image. The edge detection algorithm Canny edge detection is used to enhance the edges in the image and improve the profile clarity of the image. The image recognized by the static recognition unit is analyzed to find the missing material profile part due to obstruction. The difference between the complete material profile and the recognition result is compared to determine the position and shape of the missing profile. The image processing and analysis technology is used to determine the position and range of the obstruction area by analyzing the brightness, color, texture, and other features in the image. The obstruction area is marked out. The material motion trajectory prediction model is used to infer the material profile of the obstruction area based on the material motion trajectory and profile information before and after the obstruction area. The material motion trajectory prediction model outputs the inferred material profile. The inferred profile is verified by comparing it with the actual profile to evaluate the accuracy of the inference result. If there is a large difference between the inference result and the actual profile, the material motion trajectory prediction model is corrected and adjusted.

[0066] S303, integrate the constructed material motion trajectory prediction model with the loading control system;

[0067] Specifically, the material motion trajectory prediction model is integrated into the loading control system. The loading control system is connected to the material motion trajectory prediction model through an interface. The prediction results provided by the material motion trajectory prediction model are used to more accurately predict the motion trajectory of the material during the loading process. Based on the prediction results, the relevant control parameters of the loading control system, such as loading speed and position, are adjusted to ensure that the material can be accurately loaded into the vehicle.

[0068] The above technical solutions in the embodiments of the present application have at least the following technical effects or advantages: a material motion trajectory prediction model is established and verified, effective image enhancement algorithms are used, the complete profile information of the obstructed material is inferred, the control parameters of the loading control system are optimized, the material motion trajectory prediction model makes the recognition more accurate, provides more reliable input for the loading control system, can handle more types of materials and more complex flow situations, improves the adaptability of the loading system, reduces the residue of viscous materials on the conveyor belt, and improves the loading accuracy and stability.

[0069] Embodiment 4: Based on Embodiments 2 and 3, when the material moves at high speed, the material collides and bounces, causing unpredictable changes in the material motion trajectory, affecting the accuracy of the prediction model. In this embodiment, the dynamic recognition unit is used to recognize the material state. The data amount and data type in the collision event library are used to restore the dynamic process at the moment of collision, reduce the impact of collision on material recognition, and improve the accuracy of material recognition.

[0070] AsFigure 4 As shown, the method of constructing the material motion trajectory prediction model further comprises:

[0071] S401, setting a dynamic recognition unit on the conveying belt according to the sensing data of the material;

[0072] Further, real-time data at the time of the collision event is obtained by using a sensor, the sensing data of the material includes the speed and frequency of the material flow, the dynamic recognition unit is an intelligent device system integrating advanced sensor technology, data processing algorithm and real-time monitoring function, which is specially designed for monitoring and analyzing the motion state of the material during the material conveying process, it collects the dynamic parameters of the material and uses advanced data processing algorithm to analyze these parameters in real time, so as to realize the accurate recognition and judgment of the material motion state, the dynamic recognition unit is set in the collision high incidence area, the bounce monitoring belt and the trajectory correction area, for the collision high incidence area, the collision high incidence area is in the range before and after the joint point (horizontal to inclined section) of the conveying belt, the number of dynamic recognition units set in the collision high incidence area is determined according to the width, length and monitoring demand of the conveying belt, but considering that it is a high incidence area, usually a relatively dense dynamic recognition unit is set, for the bounce monitoring belt, the bounce monitoring belt is located in the material falling buffer section, the bounce monitoring belt is a high incidence area of material bounce behavior, a relatively dense dynamic recognition unit is set, for the trajectory correction area, the trajectory correction area is the calibration section before loading, the trajectory correction area is mainly used for correcting and verifying the material trajectory, usually one dynamic recognition unit is set, the adjacent dynamic recognition units in the same area in the collision high incidence area, the bounce monitoring belt and the trajectory correction area overlap the dynamic unit length by 1% to ensure the continuity and accuracy of the monitoring, the dynamic unit is set at a distance from the static unit to avoid signal interference.

[0073] Specific examples are: the width of a conveying belt is 1.2m, the length is 30m, the flow rate is 2m / s, the collision high incidence area is in the range before and after the joint point (horizontal to inclined section) of the conveying belt, the range is 2m before and after the joint point, 2 dynamic recognition units are set in the collision high incidence area, the bounce monitoring belt is in the material falling buffer section, the bounce monitoring belt is 3-5m away from the stock bin outlet, the bounce monitoring belt is a high incidence area of material bounce behavior, 2 dynamic recognition units are set in the bounce monitoring belt, the trajectory correction area is the calibration section before loading, the trajectory correction area is 0.5-2m away from the unloading point, this area is mainly used for correcting and verifying the material trajectory, so one dynamic recognition unit is set.

[0074] S402, establishing a physical model according to the collected sensing data, identifying the information of the historically occurred collision events according to the dynamic recognition unit and the physical model, establishing a collision event library, and extracting the rules of the collision event occurrence according to the established collision event library;

[0075] Specifically, according to the collected sensing data and physical principles, a physical model for accurately restoring the dynamic process at the collision moment is established, the information of the collision event is identified and recorded by using the set dynamic identification unit and the physical model, the information includes the time, place (i.e. the specific position on the conveying belt), the type of material involved, and the intensity of the collision, etc. The collision event information collected by the dynamic identification unit is summarized to establish a structured collision event library, the number of collision events occurring in different time periods (such as hours, days, weeks, months) is counted, the time distribution law of the collision events is analyzed, the number of collision events occurring at different locations (such as the connection points of the conveying belt, the turning points, the material dropping port, etc.) is counted, the location distribution law of the collision events is analyzed, the number of collision events involving different material types is counted, and the relationship between different material types and collision events is analyzed. The law of collision event occurrence is that in the morning and afternoon peak hours of weekdays, at specific locations such as the connection points of the conveying belt, the turning points, and the material dropping port, irregularly shaped, large size difference, or heavy weight materials are more likely to collide, and the collision intensity is larger.

[0076] S403, according to the data in the collision event library, classify the bounce mode, and according to the bounce mode and the law of collision event occurrence, establish a material flow prediction system;

[0077] Further, according to the data in the collision event library, analyze the bounce phenomenon of the material after collision, obtain the straight-line bounce of the material bouncing along a straight-line trajectory after collision and the rotational bounce of the material rotating after collision, construct a material flow prediction system according to the classified bounce mode and the law of collision event occurrence, and when the system detects that the material flow state meets certain characteristics in the collision law, immediately issue a warning signal. The system can predict possible future collision events according to the current material flow state and provide corresponding prediction support.

[0078] The technical solutions in the embodiments of the present application have at least the following technical effects or advantages: the dynamic identification unit accurately identifies the collision and bounce phenomenon of the material, restores the dynamic process at the collision moment, extracts the law from the historical collision records, provides early warning and prediction support for material flow under similar conditions, classifies the bounce mode and collision event library, provides rich data and model support for the control and optimization of material flow, can extract valuable collision laws from historical data, provides a scientific basis for material flow early warning and prediction, and through the enhanced function of the dynamic identification unit, the collision and bounce phenomenon of the material can be more accurately identified, the comprehensiveness and accuracy of the material state identification are improved, and the collision event library further improves the efficiency and stability of the material flow.

[0079] It should be noted that the descriptions of the various embodiments are each given with emphasis on certain features of the embodiments. The descriptions of the other embodiments can be understood with reference to the descriptions of the other embodiments.

[0080] Those skilled in the art will appreciate that embodiments of the present application can be readily used as a method, a system or a computer program product. Accordingly, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) embodying computer readable program code thereon.

[0081] The present application is described in reference to the flowchart illustrations and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams. Figure 1 means for performing each of the one or more functions specified in the flowchart illustrations and / or block diagrams.

[0082] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams. Figure 1 means for performing each of the one or more functions specified in the flowchart illustrations and / or block diagrams.

[0083] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams. Figure 1 means for performing each of the one or more functions specified in the flowchart illustrations and / or block diagrams.

[0084] While the preferred embodiments of the application have been described, additional variations and modifications can be made to these embodiments by those skilled in the art once they have the benefit of the present disclosure without departing from the spirit and scope of the application. Accordingly, it is intended that the appended claims include all such modifications and variations as fall within the scope of the present application.

[0085] It is apparent that those skilled in the art can make various changes and modifications to the application without departing from the spirit and scope of the application. It is therefore intended that the present application cover all such changes and modifications that are within its scope.

Claims

1. A method of material loading control, characterized by, Comprise: S101, collect the volume data of the loading material in the time period, calculate the volume according to the collected volume data, and calculate the mapping relationship between the target time and the volume of the loading material by using the fitting algorithm; The mapping relationship between the target time and the volume of the loading material is: V=f(t; θ)=at+b, wherein V is the volume of the loading material, indicating the volume size occupied by the loading material at a certain time t; t is the target time, indicating the time interval from the start of loading to a certain sampling time, used to represent the time progress in the loading process; a is the slope parameter, indicating the rate of change of the volume of the loading material with time, determining the speed of the volume increasing with time, if a is positive, indicating that the volume increases with time; if a is negative, the volume decreases with time; b is the intercept parameter, indicating the initial volume of the loading material when the time t=0; θ is a parameter set, containing all parameters for describing the mapping relationship, θ={a, b}; S102, install a camera device, capture the material flow image in real time according to the camera device, identify the state change of the material in the flow process, and calculate the flowability parameter in the flow velocity vector field by using the algorithm; The flow parameters include an average flow rate and a standard deviation of the flow rate, the average flow rate is calculated by the formula: wherein, represents the average flow rate, represents a module of the i-th flow rate vector, i.e., a size of the vector, and N represents a total number of vectors in the flow rate vector field; the standard deviation of the flow rate is calculated by the formula: wherein, represents the standard deviation of the flow rate, represents a difference between the module of the i-th flow rate vector and the average flow rate, represents a module of the i-th flow rate vector, i.e., a size of the vector, and N represents a total number of vectors in the flow rate vector field; S103, substituting the calculated flowability parameter into the mapping relationship in step S101, correcting the mapping relationship, and establishing a corrected volume mapping relationship model; The flowability parameter is substituted into the mapping relationship between the target time and the loading material volume to obtain: a' = a + b + + + wherein a' is a slope parameter corrected according to the flowability parameter, and is a correction coefficient, indicating the influence degree of the average flow rate and the standard deviation of the flow rate distribution on the parameter a, the correction coefficient is determined through experiment or data fitting, the corrected slope parameter is substituted into the mapping relationship to obtain the formula: V = f(t; ') = a' t + b, wherein ' indicates a corrected parameter set, ' = {a', b}. S104, comparing the prediction result of the corrected volume mapping relationship model with the volume of the material monitored in real time, and dynamically adjusting the control parameter according to the comparison result.

2. The method of claim 1, wherein, The specific steps of identifying the state change of the material in the flow process are: S201, setting a plurality of static recognition units on the conveying belt according to the width, length and material flow speed of the conveying belt; S202, identifying the change state of the material according to the set static recognition unit, judging whether the material is adhered, if the material particles are connected together, and the area of the connected part exceeds 15% of the total area of the particles, that is, the material is in the adhered state, otherwise, the material is not adhered.

3. A method of material loading according to claim 2, wherein, The conveying belt is divided into an entrance pre-check area, a dynamic balance area and a loading positioning area, the entrance pre-check area is located at the silo, the dynamic balance area is located at the geometric center of the longest horizontal section of the conveying belt, and the loading positioning area is located at the material unloading place.

4. The method of claim 3, wherein, The method for identifying the change state of the material further comprises: S301, collecting the data of the material, and constructing a material motion trajectory prediction model according to the collected material data; S302, when there is undetected material contour in the identification result according to the image identified by the static recognition unit, inputting the image into the material motion trajectory prediction model to predict the undetected material contour; S303, integrating the constructed material motion trajectory prediction model with the loading control system.

5. A method of material loading according to claim 4, wherein, The method for constructing the material motion trajectory prediction model further comprises: S401, setting a dynamic recognition unit on the conveying belt according to the sensing data of the material; S402, a physical model is established according to the collected sensing data, information of a historical collision event is identified according to a dynamic identification unit and the physical model, a collision event library is established, and a rule of collision event occurrence is extracted according to the established collision event library; S403, the bounce mode is classified according to the data in the collision event library, and a material flow prediction system is established according to the bounce mode and the rule of collision event occurrence.

6. A method of material loading according to claim 5, wherein, The bounce mode includes straight-line bounce and rotary bounce, the straight-line bounce is that the material bounces along a straight-line track after collision, and the rotary bounce is that the material rotates simultaneously after collision.

Images