Control Method and System for a Front-End Conveyor Device for Soil Washing and Remediation

Abstract

The present invention relates to the technical field of soil cleaning and remediation, and particularly to a control method and system for a front-end conveying device used for soil washing and remediation. The method includes the following steps: obtaining device monitoring status data and an image of the soil to be remediated by the conveying device; the device monitoring status data includes soil weight parameters, the feeding rate of the feeding machine, and the conveyor belt speed; obtaining a soil remediation boundary area based on the image of the soil to be remediated by the conveying device; performing non-linear correlation mapping learning on the conveyor belt speed according to the soil weight parameters to obtain weight-conveying speed correlation data; performing multi-level collaborative response neural network learning on the conveyor belt speed and the feeding rate of the feeding machine based on the weight-conveying speed correlation data, so as to generate collaborative response data of the conveying device; obtaining a monitoring image of the front-end conveying device; obtaining three-dimensional structure data of components based on the monitoring image of the front-end conveying device. The present invention realizes precise feeding control of the conveying device.

Description

Technical Field

[0001] The present invention relates to the technical field of soil cleaning and remediation, and particularly relates to a control method and system for a front-end conveying device for soil leaching remediation. Background Art

[0002] The chemical leaching technology mainly transfers pollutants from the soil surface to the leaching solution through desorption, reverse complexation, and dissolution, and then realizes the recovery and utilization of heavy metals through the recycling and processing of the leaching solution. This technology can efficiently repair polluted soil with large particle sizes and is suitable for cleaning pollutants in gravel, sand, and soils with low viscosity. In the pretreatment part of chemical leaching, the total amount of polluted soil fed by the feeding machine and transported by the belt is not constant, but the amount of chemical leaching agent used in the subsequent heavy metal ion removal part is determined according to the production capacity. If the transportation volume of polluted soil is too large, the subsequent removal effect will become worse; if the polluted soil is too little, the amount of leaching agent used will be excessive. Traditional soil leaching and remediation devices usually rely on the feeding and conveying speed preset by workers in advance, often resulting in material waste and unable to precisely control the conveying device. Therefore, an intelligent control method for the front-end conveying device is needed. Summary of the Invention

[0003] In order to solve the above technical problems, the present invention proposes a control method and system for a front-end conveying device for soil leaching remediation to solve at least one of the above technical problems.

[0004] To achieve the above object, the present invention provides a control method for a front-end conveying device for soil leaching remediation, including the following steps:

[0005] Step S1: Obtain the device monitoring status data and the image of the soil to be remediated by the conveying device; the device monitoring status data includes soil weight parameters, the feeding rate of the feeding machine, and the conveyor belt speed; obtain the soil remediation boundary area based on the image of the soil to be remediated by the conveying device;

[0006] Step S2: Perform non-linear correlation mapping learning on the conveyor belt speed according to the soil weight parameters to obtain weight-conveying speed correlation data; perform multi-level collaborative response neural network learning on the conveyor belt speed and the feeding rate of the feeding machine based on the weight-conveying speed correlation data, so as to generate the collaborative response data of the conveying device;

[0007] Step S3: Obtain the monitoring image of the front-end conveying device; obtain the three-dimensional structure data of the components based on the monitoring image of the front-end conveying device; perform dynamic parameter rendering on the three-dimensional structure data of the components according to the collaborative response data of the conveying device, so as to construct a dynamic rendering model of the conveying device;

[0008] Step S4: Perform digital dynamic simulation of soil leaching on the dynamic rendering model of the conveyor device to obtain dynamic simulation data of soil leaching; based on the soil remediation boundary area, dynamically adjust the speed parameters of the dynamic simulation data of soil leaching, so as to obtain dynamic speed adjustment data of the conveyor belt;

[0009] Step S5: Optimize the adaptive feeding speed compensation based on the dynamic speed adjustment data of the conveyor belt to obtain the transient feeding compensation speed; adjust the real-time parameters of the front conveyor device according to the transient feeding compensation speed, and obtain the real-time adjustment operation state data;

[0010] Step S6: Identify the error parameters of the real-time adjustment operation state data based on the dynamic simulation data of soil leaching to obtain the control error parameters; optimize the dynamic feeding balance control of the conveyor device according to the control error parameters, and generate dynamic feeding control parameters to execute the soil leaching repair control operation.

[0011] The present invention provides real-time operation information of a conveying device by monitoring status data through a device, including soil weight parameters, the feeding rate of a feeding machine, and the conveyor belt speed. These data are used to analyze the working status and performance of the device. The acquisition of the soil image to be repaired by the conveying device enables the observation of the soil area that needs to be repaired and determines the soil repair boundary area. Through the non-linear correlation mapping learning of the soil weight parameter and the conveyor belt speed, weight-conveyor speed correlation data are established, thereby more accurately controlling the conveyor belt speed. Using the weight-conveyor speed correlation data, multi-level collaborative response neural network learning is performed on the conveyor belt speed and the feeding rate of the feeding machine to obtain the collaborative response data of the conveying device, realizing the collaborative control of the conveyor belt speed and the feeding rate of the feeding machine. The acquisition of the monitoring image of the front-end conveying device provides visual information about the actual situation of the conveying device for further analysis and control. The three-dimensional structure data of the components obtained based on the monitoring image of the front-end conveying device provides the accurate position and shape information of each component of the conveying device. Through the collaborative response data of the conveying device, dynamic parameter rendering is performed on the three-dimensional structure data of the components to construct a dynamic rendering model of the conveying device, which is used to simulate the operating status and behavior of the conveying device. Through the digital dynamic simulation of soil leaching on the dynamic rendering model of the conveying device, the soil leaching process is simulated to obtain the dynamic simulation data of soil leaching. According to the soil repair boundary area, the speed parameters of the dynamic simulation data of soil leaching are dynamically adjusted. According to the requirements of different repair boundaries, the conveyor belt speed is dynamically adjusted to achieve a more precise leaching operation. Based on the dynamic conveyor belt speed adjustment data, adaptive feeding speed compensation optimization is performed. According to the actual speed change of the conveyor belt, the feeding speed is automatically adjusted to maintain an appropriate soil feeding amount. According to the transient feeding compensation speed, real-time parameter adjustment is performed on the front-end conveying device to achieve dynamic and precise control of the conveying device and ensure the accuracy and stability of soil feeding. The acquisition of real-time adjusted operating status data monitors the performance and status of the conveying device during actual operation, providing feedback and reference for subsequent control optimization. Based on the dynamic simulation data of soil leaching, error parameter identification analysis is performed on the real-time adjusted operating status data to identify the control error parameters in actual operation for further control optimization. According to the control error parameters, dynamic feeding balance control optimization is performed on the conveying device. According to the actual error situation, the working status and parameters of the feeding machine are dynamically adjusted to achieve a more precise soil leaching repair control operation.

[0012] Preferably, step S1 includes the following steps:

[0013] Step S11: Conduct real-time working monitoring on the front-end conveying device to obtain device monitoring status data; the device monitoring status data includes soil weight parameters, the feeding rate of the feeding machine, and the conveyor belt speed;

[0014] Step S12: Obtain the soil image to be repaired by the conveying device;

[0015] Step S13: Visually identify the soil boundary of the soil image to be repaired by the conveying device to extract the soil contour line;

[0016] Step S14: Based on the soil contour line, perform boundary segmentation on the soil image to be repaired by the conveying device to obtain the soil repair boundary area;

[0017] Step S15: Identify the soil particle size of the soil repair boundary area to obtain the soil particle size;

[0018] Step S16: Perform quantitative analysis of soil pollution based on the soil particle size to obtain soil pollution degree data.

[0019] Through real-time work monitoring, the present invention obtains the actual working status and performance parameters of the front-end conveying device. The obtained soil weight parameter provides information on the soil delivery volume, which helps control the soil delivery volume. The monitoring data of the feeding rate of the feeding machine and the conveyor belt speed are used to analyze the operating conditions and speed control of the conveying device. By acquiring the soil image to be repaired by the conveying device, the soil area that needs to be repaired is observed. The soil image to be repaired provides visual information on the soil surface condition for further analysis and repair work. Through visual recognition of the soil boundary, the contour line of the soil is extracted from the image. The soil contour line provides geometric information on the soil surface shape for subsequent boundary segmentation and analysis. Through boundary segmentation based on the soil contour line, the soil area in the soil image to be repaired by the conveying device is separated from the background. The obtained soil repair boundary area determines the specific range that needs to be repaired, providing accurate area information for subsequent soil analysis and repair. By identifying the soil particle size of the soil repair boundary area, the size and distribution of particles in the soil are obtained. The obtained soil particle size information helps further analyze the soil properties and formulate repair strategies. Using the soil particle size information for quantitative analysis of soil pollution, evaluating the content and distribution of pollutants in the soil, the obtained soil pollution degree data provides a reference basis for soil repair, helping to formulate reasonable repair plans and control strategies.

[0020] Preferably, step S2 includes the following steps:

[0021] Step S21: Perform weight perturbation analysis on the conveyor belt speed according to the soil weight parameter to obtain the conveyor belt speed perturbation data of the weight;

[0022] Step S22: Perform non-linear correlation mapping learning on the soil weight parameter and the conveyor belt speed according to the conveyor belt speed perturbation data of the weight to obtain the weight-conveyor speed correlation data;

[0023] Step S23: Perform speed fluctuation response analysis on the conveyor belt speed and the feeding rate of the feeding machine to obtain the feeding response data affected by the speed;

[0024] Step S24: Perform multi-level collaborative response neural network learning on the weight-conveyor speed correlation data and the feeding response data affected by speed, so as to generate the collaborative response data of the conveyor device.

[0025] Through weight perturbation analysis, the present invention determines the influence degree of soil weight on the conveyor belt speed, and the obtained conveyor belt speed perturbation data quantifies the relationship between soil weight and conveyor belt speed, providing a basis for subsequent control strategies. Through non-linear correlation mapping learning, a complex relationship model between soil weight parameters and conveyor belt speed is established, and the obtained weight-conveyor speed correlation data provides a reference value for achieving the required conveyor belt speed under given soil weight parameters. Through speed fluctuation response analysis, the mutual influence relationship between conveyor belt speed and the feeding rate of the feeding machine is determined, and the obtained feeding response data provides an adjustment reference value for the feeding rate of the feeding machine under a given conveyor belt speed, thereby achieving the accuracy of speed control. Through multi-level collaborative response neural network learning, the weight-conveyor speed correlation data and the feeding response data affected by speed are comprehensively analyzed and modeled, and the generated collaborative response data of the conveyor device provides guiding information for realizing the dynamic and accurate control of the conveyor device under given soil weight parameters and conveyor belt speed.

[0026] Preferably, the specific steps of step S3 are as follows:

[0027] Step S31: Obtain the monitoring image of the front-end conveyor device;

[0028] Step S32: Perform component space topology analysis on the monitoring image of the front-end conveyor device to obtain component space topology data;

[0029] Step S33: Perform three-dimensional structure analysis based on the component space topology data to obtain component three-dimensional structure data;

[0030] Step S34: Use the component three-dimensional structure data to perform three-dimensional reconstruction of the monitoring image of the front-end conveyor device and construct a three-dimensional structure model of the device;

[0031] Step S35: Perform dynamic parameter rendering on the three-dimensional structure model of the device according to the collaborative response data of the conveyor device, so as to construct a dynamic rendering model of the conveyor device.

[0032] Through weight perturbation analysis, the present invention determines the influence degree of soil weight on the conveyor belt speed. The obtained conveyor belt speed perturbation data quantifies the relationship between soil weight and conveyor belt speed, providing a basis for subsequent control strategies. Through non-linear correlation mapping learning, a complex relationship model between soil weight parameters and conveyor belt speed is established. The obtained weight-conveyor speed correlation data provides a reference value for achieving the required conveyor belt speed under given soil weight parameters. Through speed fluctuation response analysis, the mutual influence relationship between conveyor belt speed and the feeding rate of the feeding machine is determined. The obtained feeding response data provides a reference for adjusting the feeding rate of the feeding machine under a given conveyor belt speed, thereby realizing the accuracy of speed control. Through multi-level collaborative response neural network learning, the weight-conveyor speed correlation data and the feeding response data affected by speed are comprehensively analyzed and modeled. The generated collaborative response data of the conveying device provides guiding information for realizing the dynamic and accurate control of the conveying device under given soil weight parameters and conveyor belt speed.

[0033] Preferably, the specific steps of step S4 are as follows:

[0034] Step S41: Perform digital dynamic simulation of soil leaching on the dynamic rendering model of the conveying device to obtain soil leaching dynamic simulation data;

[0035] Step S42: Based on the weight-conveyor speed correlation data, perform weight-speed proportional control analysis on the soil leaching dynamic simulation data to generate soil weight-conveyor belt speed proportional data;

[0036] Step S43: Based on the soil remediation boundary region, perform dynamic adjustment of speed parameters on the soil weight-conveyor belt speed proportional data to obtain conveyor belt dynamic speed adjustment data; the conveyor belt dynamic speed adjustment data includes dynamic acceleration adjustment data and dynamic deceleration adjustment data;

[0037] Step S44: Calculate the transient feeding speed for the soil leaching dynamic simulation data to obtain the transient feeding speed.

[0038] The present invention provides visual information of the front-end conveying device through monitoring images, which can reflect its current state and working conditions. By obtaining the monitoring images, subsequent component analysis and structural analysis are carried out to provide a necessary data basis for dynamic control. Component spatial topology analysis identifies and extracts each component in the front-end conveying device and the spatial relationship between them. The obtained component spatial topology data describes the component layout and connection mode of the front-end conveying device, providing a basis for subsequent structural analysis and reconstruction. Three-dimensional structural analysis can convert the component spatial topology data into specific three-dimensional geometric information, including the position, size, and shape of the components, etc. The obtained component three-dimensional structure data provides the geometric features of the front-end conveying device, providing a basis for subsequent device reconstruction and dynamic rendering. Device three-dimensional reconstruction fuses the component three-dimensional structure data with the monitoring images to generate a device three-dimensional structure model with spatial geometric information. The constructed device three-dimensional structure model can more intuitively represent the shape and position of the front-end conveying device, providing a basis for subsequent dynamic rendering and control. Dynamic parameter rendering uses the conveying device collaborative response data to associate the device three-dimensional structure model with the actual working parameters to achieve a dynamic visualization effect. The constructed conveying device dynamic rendering model can simulate the operating state of the front-end conveying device under different working conditions, providing a visual reference for dynamic precise control.

[0039] Preferably, the specific steps of step S43 are as follows:

[0040] Perform morphological analysis on the soil remediation boundary area to obtain the morphological data of the remediation area;

[0041] Calculate the area of the soil remediation boundary area based on the morphological data of the remediation area, so as to obtain the area of the boundary area to be remediated;

[0042] Compare the area of the boundary area to be remediated with the preset threshold of the soil remediation boundary area. When the preset threshold of the soil remediation boundary area is greater than the area of the boundary area to be remediated, it is determined that the soil remediation boundary area is a smaller boundary area, and an acceleration adjustment amplitude analysis is performed to obtain the acceleration adjustment amplitude data;

[0043] Perform dynamic acceleration adjustment on the soil weight-conveyor belt speed ratio data based on the conveyor belt acceleration adjustment amplitude data to obtain dynamic acceleration adjustment data;

[0044] When the preset threshold of the soil remediation boundary area is less than or equal to the area of the boundary area to be remediated, it is determined that the soil remediation boundary area is a larger boundary area, and a deceleration adjustment amplitude analysis is performed to obtain the deceleration adjustment amplitude data;

[0045] Perform dynamic deceleration adjustment on the soil weight-conveyor belt speed ratio data based on the deceleration adjustment amplitude data to obtain dynamic deceleration adjustment data.

[0046] The present invention identifies and extracts the morphological features of the soil remediation boundary area through morphological analysis, such as boundary shape, curvature, etc. The obtained morphological data of the remediation area provides a quantitative description of the morphological features of the soil remediation boundary area, providing a basis for subsequent area calculation and adjustment. The area calculation of the region determines the area size of the boundary area to be remediated, reflecting the size and complexity of the remediation scope. The obtained area data of the boundary area to be remediated provides a quantitative description of the remediation scope, providing a basis for subsequent determination and adjustment. Morphological analysis helps to identify and extract the morphological features of the soil remediation boundary area, such as boundary shape, curvature, etc. The obtained morphological data of the remediation area provides a quantitative description of the morphological features of the soil remediation boundary area, which is used for subsequent analysis and control decision-making. The area calculation of the region can determine the area size of the boundary area to be remediated, thereby evaluating the size and complexity of the remediation scope. The obtained area data of the boundary area to be remediated provides a quantitative description of the remediation scope, providing a basis for subsequent control decision-making and resource allocation. By comparing with a preset area threshold, the size of the soil remediation boundary area is judged, and then it is determined whether acceleration adjustment is needed. The analysis of the acceleration adjustment amplitude can determine the degree of acceleration adjustment to achieve precise control and rapid remediation of a smaller boundary area. The dynamic acceleration adjustment can adjust the proportional relationship between the soil weight and the conveyor belt speed in real time according to the conveyor belt acceleration adjustment amplitude data. The obtained dynamic acceleration adjustment data provides an accurate control strategy adapted to the changes in the remediation boundary area to optimize the efficiency and quality of soil remediation. According to the comparison between the preset area threshold and the area of the boundary area to be remediated, it is judged whether the soil remediation boundary area is a large boundary area, and then it is decided whether deceleration adjustment is needed. The analysis of the deceleration adjustment amplitude determines the degree of deceleration adjustment to achieve precise control and appropriate adjustment of a large boundary area.

[0047] Preferably, the specific steps of step S5 are as follows:

[0048] Step S51: Based on the soil pollution degree data and the conveyor belt dynamic speed adjustment data, perform adaptive feeding speed compensation optimization on the transient feeding speed to obtain the transient feeding compensation speed;

[0049] Step S52: Make an optimal cooperative control decision on the conveyor belt dynamic speed adjustment data and the transient feeding compensation speed to obtain the optimal control parameters of the conveying device;

[0050] Step S53: Perform real-time parameter adjustment on the front-end conveying device according to the optimal control parameters of the conveying device, and obtain the real-time adjustment operation state data.

[0051] The present invention adaptively compensates and optimizes the transient feeding speed by combining soil pollution degree data and conveyor belt dynamic speed adjustment data. The adaptive feeding speed compensation and optimization adjusts the feeding speed according to the real-time soil pollution degree and conveyor belt speed changes to meet the requirements of different pollution degrees and conveyor belt speeds. The obtained transient feeding compensation speed provides an optimized adjustment of the feeding speed to achieve a more precise soil remediation process. By combining the conveyor belt dynamic speed adjustment data and the transient feeding compensation speed, an optimal cooperative control decision is made to optimize the control parameters of the conveying device. The optimal cooperative control decision determines the best control parameters of the conveying device by comprehensively considering the influence of the conveyor belt speed and the feeding compensation speed to achieve the efficient operation of the conveying device and the improvement of soil remediation quality. According to the optimal control parameters of the conveying device, real-time parameter adjustment is performed on the front-end conveying device to optimize the operating state of the conveying device. The real-time parameter adjustment adjusts the parameters such as the speed and feeding compensation of the conveying device in real time according to the optimal control parameters to adapt to the actual soil remediation requirements and working conditions. The obtained real-time adjustment operating state data provides real-time monitoring and feedback on the operating state of the conveying device for further adjustment and optimization.

[0052] Preferably, the specific steps of step S51 are as follows:

[0053] Calculate the leaching material demand based on the soil pollution degree data to obtain the current device material demand data;

[0054] Analyze the feeding speed range of the transient feeding speed based on the conveyor belt dynamic speed adjustment data to obtain the feeding speed range data;

[0055] Perform adaptive feeding speed adjustment on the feeding speed range data based on the current device material demand data to obtain the adaptive feeding speed;

[0056] Perform feeding difference compensation and optimization on the transient feeding speed according to the adaptive feeding speed to obtain the transient feeding compensation speed.

[0057] The present invention calculates the material requirements for leaching by using soil pollution degree data, determines the quantity of materials required for the current device according to the soil pollution degree, and provides basic information for material supply with the obtained material requirement data of the current device, which can be used for subsequent adjustment of the feeding speed and control decision-making. By analyzing the dynamic speed adjustment data of the conveyor belt, the range of the transient feeding speed, that is, the reasonable upper and lower limits of the speed, is determined. The obtained feeding speed range data provides an effective control boundary for the feeding speed to ensure that the feeding speed is within the adjustable range. Combining the material requirement data of the current device and the feeding speed range data, an adaptive feeding speed adjustment is carried out to ensure that the feeding speed meets the material requirements of the current device. The adaptive feeding speed adjustment adjusts the feeding speed to the most appropriate range according to the actual requirements, avoiding adverse effects on the working effect caused by too high or too low feeding speed. Based on the adaptive feeding speed, the feeding difference compensation optimization is carried out on the transient feeding speed to further improve the accuracy and stability of feeding. The transient feeding compensation speed optimizes the feeding difference on the basis of considering the adaptive feeding speed, making the feeding speed more accurate and reliable.

[0058] Preferably, the specific steps of step S6 are as follows:

[0059] Step S61: Identify the error parameters of the real-time adjusted operation state data based on the dynamic simulation data of soil leaching, so as to obtain the control error parameters;

[0060] Step S62: Optimize the error control of the optimal control parameters of the conveying device based on the control error parameters to obtain the error optimization parameters;

[0061] Step S63: Optimize the dynamic feeding balance control of the conveying device according to the error optimization parameters to generate the dynamic feeding control parameters;

[0062] Step S64: Execute the soil leaching and remediation control operation based on the dynamic feeding control parameters.

[0063] The present invention identifies error parameters for real-time adjusted operating state data through soil leaching dynamic simulation data, obtains the error conditions in actual operation, and the obtained control error parameters provide a quantitative description of the difference between the operating state of the conveying device and the expected target, which helps optimize subsequent error control. Based on the control error parameters, the optimal control parameters of the conveying device are adjusted and optimized to reduce errors and improve the control accuracy of the device. The error control optimization optimizes and adjusts the control parameters of the conveying device according to the actual error conditions to achieve a more accurate and stable control effect. Based on the error optimization parameters, dynamic feeding balance control optimization is performed on the conveying device to achieve a more balanced and stable feeding process. The dynamic feeding control parameters consider the influence of the error optimization parameters, and by adjusting the parameters in the feeding process, the feeding becomes more uniform and accurate. Based on the dynamic feeding control parameters, the soil leaching repair control operation is executed to achieve effective repair of the soil and removal of pollutants. The dynamic feeding control parameters provide precise control of the feeding process, enabling the leaching operation to adjust the precise material supply and feeding speed according to actual requirements.

[0064] In this specification, a control system for a front-end conveying device for soil leaching repair is provided, which is used to execute the control method for the front-end conveying device for soil leaching repair as described above, and includes:

[0065] A repair boundary module, configured to obtain device monitoring status data and an image of the soil to be repaired by the conveying device; the device monitoring status data includes soil weight parameters, the feeding rate of the feeder, and the conveyor belt speed; and obtain the soil repair boundary area based on the image of the soil to be repaired by the conveying device.

[0066] A collaborative response module, configured to perform non-linear correlation mapping learning on the conveyor belt speed according to the soil weight parameters to obtain weight-conveyor speed correlation data; and perform multi-level collaborative response neural network learning on the conveyor belt speed and the feeding rate of the feeder based on the weight-conveyor speed correlation data, so as to generate conveyor device collaborative response data.

[0067] A dynamic parameter rendering module, configured to obtain a monitoring image of the front-end conveying device; obtain three-dimensional component structure data based on the monitoring image of the front-end conveying device; and perform dynamic parameter rendering on the three-dimensional component structure data according to the conveyor device collaborative response data, so as to construct a dynamic rendering model of the conveyor device.

[0068] A dynamic simulation module, configured to perform digital dynamic simulation of soil leaching on the dynamic rendering model of the conveyor device to obtain soil leaching dynamic simulation data; and perform dynamic adjustment of speed parameters on the soil leaching dynamic simulation data based on the soil repair boundary area, so as to obtain conveyor belt dynamic speed adjustment data.

[0069] A transient feeding compensation module is used to perform adaptive feeding speed compensation optimization based on the dynamic speed adjustment data of the conveyor belt, so as to obtain the transient feeding compensation speed; perform real-time parameter adjustment on the front-end conveyor device according to the transient feeding compensation speed, and obtain the real-time adjustment operation status data;

[0070] A dynamic feeding balance module is used to identify error parameters of the real-time adjustment operation status data based on the dynamic simulation data of soil leaching, so as to obtain control error parameters; perform dynamic feeding balance control optimization on the conveyor device according to the control error parameters, and generate dynamic feeding control parameters to execute the soil leaching repair control operation.

[0071] The present invention obtains key input information by acquiring the device monitoring status data and the image of the soil to be repaired of the conveyor device. The monitoring status data of the soil weight parameter, the feeding rate of the feeder, and the conveyor belt speed provide the real-time situation of the device operation. The specific area to be repaired is determined based on the soil repair boundary area obtained from the image of the soil to be repaired of the conveyor device, providing a basis for precise positioning in subsequent steps. By learning the non-linear correlation mapping between the soil weight parameter and the conveyor belt speed, a weight-conveyor speed relationship is established, providing a reference basis for the conveyor belt speed. Based on the multi-level collaborative response neural network learning of the weight-conveyor speed correlation data, the complex relationship between the conveyor belt speed and the feeding rate of the feeder can be captured, thereby generating the collaborative response data of the conveyor device and realizing the optimal control of the device operation. By acquiring the monitoring image of the front-end conveyor device and extracting the three-dimensional structure data of the components, a dynamic rendering model of the conveyor device is established. This model performs dynamic parameter rendering based on the collaborative response data of the conveyor device, and can reflect the actual state and position of each component of the conveyor device, providing an accurate basis for subsequent control optimization. By performing digital dynamic simulation of soil leaching on the dynamic rendering model of the conveyor device, the process of soil leaching is simulated, and the dynamic simulation data of soil leaching is obtained. Based on the soil repair boundary area, the speed parameters of the simulation data are dynamically adjusted, and the speed of the conveyor belt can be adjusted according to the requirements of the specific repair area, realizing the precise control of soil leaching. By performing adaptive feeding speed compensation optimization based on the dynamic speed adjustment data of the conveyor belt, the optimization adjustment of the feeding speed is realized. The transient feeding compensation speed takes into account the relationship between the conveyor belt speed and the feeding rate of the feeder. Through adaptive compensation, more precise feeding control is realized. The acquisition of the real-time adjustment operation status data reflects the actual operation situation of the device, providing data support for subsequent error parameter identification. By identifying the error parameters of the dynamic simulation data of soil leaching, the control error parameters are determined. Based on the control error parameters, dynamic feeding balance control optimization is performed on the conveyor device, and dynamic feeding control parameters are generated to realize the soil leaching repair control operation. Such a control strategy can precisely adjust the device, improve the repair effect, and minimize errors to the greatest extent. Description of the Drawings

[0072] Figure 1 It is a schematic diagram of the step flow of a control method for a front-end conveying device for soil washing and remediation of the present invention;

[0073] Figure 2 It is a schematic diagram of the detailed implementation steps of step S1;

[0074] Figure 3 It is a schematic diagram of the detailed implementation steps of step S2;

[0075] Figure 4 It is a schematic diagram of the detailed implementation steps of step S3. Detailed implementation manner

[0076] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0077] The embodiments of the present application provide a control method and system for a front-end conveying device for soil washing and remediation. The execution subjects of the control method and system for the front-end conveying device for soil washing and remediation include, but are not limited to, the following general computing nodes that carry this system: mechanical equipment, data processing platforms, cloud server nodes, network uploading devices, etc. The data processing platform includes, but is not limited to, at least one of an audio and image management system, an information management system, and a cloud data management system.

[0078] Please refer to Figures 1 to 4 , the present invention provides a control method for a front-end conveying device for soil washing and remediation, including the following steps:

[0079] Step S1: Obtain the device monitoring status data and the image of the soil to be remediated by the conveying device; the device monitoring status data includes soil weight parameters, the feeding rate of the feeding machine, and the conveyor belt speed; obtain the soil remediation boundary area based on the image of the soil to be remediated by the conveying device;

[0080] Step S2: Perform non-linear correlation mapping learning on the conveyor belt speed according to the soil weight parameters to obtain weight-conveying speed correlation data; perform multi-level collaborative response neural network learning on the conveyor belt speed and the feeding rate of the feeding machine based on the weight-conveying speed correlation data, so as to generate the collaborative response data of the conveying device;

[0081] Step S3: Obtain the monitoring image of the front-end conveying device; obtain the three-dimensional structure data of the components based on the monitoring image of the front-end conveying device; perform dynamic parameter rendering on the three-dimensional structure data of the components according to the collaborative response data of the conveying device, so as to construct a dynamic rendering model of the conveying device;

[0082] Step S4: Perform digital dynamic simulation of soil leaching on the dynamic rendering model of the conveying device to obtain soil leaching dynamic simulation data; dynamically adjust the speed parameters based on the soil remediation boundary area for the soil leaching dynamic simulation data, thereby obtaining the dynamic speed adjustment data of the conveyor belt;

[0083] Step S5: Optimize the adaptive feeding speed compensation based on the dynamic speed adjustment data of the conveyor belt to obtain the transient feeding compensation speed; perform real-time parameter adjustment on the front-end conveying device according to the transient feeding compensation speed, and obtain the real-time adjustment operation state data;

[0084] Step S6: Identify the error parameters of the real-time adjustment operation state data based on the soil leaching dynamic simulation data to obtain the control error parameters; optimize the dynamic feeding balance control of the conveying device according to the control error parameters, generate dynamic feeding control parameters, and execute the soil leaching repair control operation.

[0085] The present invention provides real-time operation information of a conveying device by monitoring status data through a device, including soil weight parameters, the feeding rate of a feeding machine, and the conveyor belt speed. These data are used to analyze the working status and performance of the device. The acquisition of the image of the soil to be repaired by the conveying device enables the observation of the soil area that needs to be repaired and determines the soil repair boundary area. Through the non-linear correlation mapping learning of the soil weight parameters and the conveyor belt speed, weight-conveyor speed correlation data are established, so as to more accurately control the conveyor belt speed. Using the weight-conveyor speed correlation data, multi-level collaborative response neural network learning is carried out on the conveyor belt speed and the feeding rate of the feeding machine to obtain the collaborative response data of the conveying device, realizing the collaborative control of the conveyor belt speed and the feeding rate of the feeding machine. The acquisition of the monitoring image of the front-end conveying device provides visual information about the actual situation of the conveying device for further analysis and control. The three-dimensional structure data of the components obtained based on the monitoring image of the front-end conveying device provides the accurate position and shape information of each component of the conveying device. Through the collaborative response data of the conveying device, dynamic parameter rendering is carried out on the three-dimensional structure data of the components to construct a dynamic rendering model of the conveying device, which is used to simulate the operating status and behavior of the conveying device. Through the digital dynamic simulation of soil leaching on the dynamic rendering model of the conveying device, the soil leaching process is simulated to obtain the dynamic simulation data of soil leaching. According to the soil repair boundary area, the speed parameters of the dynamic simulation data of soil leaching are dynamically adjusted. According to the requirements of different repair boundaries, the conveyor belt speed is dynamically adjusted to achieve a more accurate leaching operation. Based on the dynamic conveyor belt speed adjustment data, adaptive feeding speed compensation optimization is carried out. According to the actual speed change of the conveyor belt, the feeding speed is automatically adjusted to maintain an appropriate soil feeding amount. According to the transient feeding compensation speed, real-time parameter adjustment is carried out on the front-end conveying device to achieve dynamic and accurate control of the conveying device and ensure the accuracy and stability of soil feeding. The acquisition of real-time adjusted operation status data monitors the performance and status of the conveying device during actual operation, providing feedback and reference for subsequent control optimization. Based on the dynamic simulation data of soil leaching, error parameter identification analysis is carried out on the real-time adjusted operation status data to identify the control error parameters in actual operation, which are used for further control optimization. According to the control error parameters, dynamic feeding balance control optimization is carried out on the conveying device. According to the actual error situation, the working status and parameters of the feeding machine are dynamically adjusted to achieve a more accurate soil leaching repair control operation.

[0086] In an embodiment of the present invention, referring to Figure 1 , it is a schematic diagram of the step flow of a control method for a front-end conveying device for soil leaching repair according to the present invention. In this example, the steps of the control method for the front-end conveying device for soil leaching repair include:

[0087] Step S1: Obtain the device monitoring status data and the images of the soil to be repaired by the conveying device; the device monitoring status data includes soil weight parameters, the feeding rate of the feeding machine, and the conveyor belt speed; obtain the soil repair boundary area based on the images of the soil to be repaired by the conveying device;

[0088] In this embodiment, based on the real-time weight data of the soil monitored by the sensor on the conveyor belt, the real-time rotation speed of the feeding machine is monitored, the feeding rate is calculated, and the real-time running speed of the conveyor belt is monitored. A high-definition camera is installed on the conveying device to capture and collect the image data of the soil to be repaired in real time. Ensure that the image resolution is high enough to clearly capture the detailed information on the soil surface. Identify the features such as the texture and color of the soil surface, and distinguish the area to be repaired. According to the distribution of the soil features, determine the boundary position and range of the area to be repaired.

[0089] Step S2: Perform non-linear correlation mapping learning on the conveyor belt speed according to the soil weight parameters to obtain weight-conveyor speed correlation data; perform multi-level collaborative response neural network learning on the conveyor belt speed and the feeding rate of the feeding machine based on the weight-conveyor speed correlation data, so as to generate the collaborative response data of the conveying device;

[0090] In this embodiment, machine learning methods such as regression analysis and neural networks are used to fit the non-linear mapping relationship between the soil weight and the conveyor belt speed to obtain the weight-conveyor speed correlation data, which describes the corresponding changes in the conveyor belt speed when the soil weight changes. Based on the weight-conveyor speed correlation data as the input, and at the same time inputting the conveyor belt speed and the feeding rate data of the feeding machine, a multi-layer perceptron neural network model is constructed to learn the collaborative response relationship between the conveyor belt speed and the feeding rate of the feeding machine. The hidden layer of the network can capture the complex correlation between these two parameters, reflecting the multi-level collaborative response mechanism of the device. The trained network model is the collaborative response data of the conveying device, which describes the linkage changes of the two key parameters.

[0091] Step S3: Obtain the monitoring images of the front-end conveying device; obtain the three-dimensional structure data of the components based on the monitoring images of the front-end conveying device; perform dynamic parameter rendering on the three-dimensional structure data of the components according to the collaborative response data of the conveying device, so as to construct a dynamic rendering model of the conveying device;

[0092] In this embodiment, multiple cameras are installed at the front end of the conveying device to collect image data of each component of the device in real time. Technologies such as structured light scanning and multi-view reconstruction are used to reconstruct the three-dimensional structure of each component using the front-end monitoring image data. These three-dimensional models can accurately describe the geometric shapes and spatial position information of each component of the conveying device. Based on the collaborative response data of the conveying device, such as the conveyor belt speed and the feeding rate of the feeding machine, they are mapped to the corresponding parameters of the three-dimensional model. Using the dynamic rendering technology of computer graphics, according to the real-time collaborative response data, the visualization effects of the conveying device in different working states are generated. The dynamically rendered model constructed in this way can intuitively reflect the motion states of each component of the conveying device under the action of collaborative response.

[0093] Step S4: Perform digital dynamic simulation of soil leaching on the dynamic rendering model of the conveying device to obtain soil leaching dynamic simulation data; based on the soil remediation boundary area, dynamically adjust the speed parameters of the soil leaching dynamic simulation data to obtain conveyor belt dynamic speed adjustment data;

[0094] In this embodiment, based on the dynamic rendering model of the conveying device as a simulation platform, the physical processes of soil leaching, such as liquid flow and solid particle movement, are introduced into the model for digital simulation calculations. During the simulation process, parameter data such as the movement trajectories of each component and the liquid flow velocity are recorded, which are the soil leaching dynamic simulation data. According to the actual situation, soil remediation boundaries are set in certain areas of the conveying device. The obtained soil leaching dynamic simulation data is analyzed to identify the liquid flow and solid particle movement passing through the remediation boundary area. For these flows and movements passing through the remediation boundary, the conveyor belt speed parameters are dynamically adjusted to meet the requirements of soil remediation, and conveyor belt dynamic speed adjustment data is obtained, which describes the conveyor belt speed that needs to be dynamically adjusted to achieve soil remediation.

[0095] Step S5: Perform adaptive feeding speed compensation optimization based on the conveyor belt dynamic speed adjustment data to obtain the transient feeding compensation speed; perform real-time parameter adjustment on the front-end conveying device according to the transient feeding compensation speed, and obtain real-time adjustment operation state data;

[0096] In this embodiment, an adaptive feeding speed compensation algorithm is established. According to the real-time changes in the conveyor belt speed, the feeding speed of the feeding machine is dynamically adjusted to ensure that the materials can enter the remediation area on time and accurately. This algorithm needs to consider the time-delay characteristics of the conveyor belt speed change and adopt advanced strategies such as predictive control to obtain the optimal transient feeding compensation speed. The control system adjusts the actual feeding speed of the feeding machine according to the compensation speed to ensure that the materials can accurately enter the soil remediation area. The control system also collects various operating parameters of the adjusted conveying device, such as the actual conveyor belt speed and the feeding frequency of the feeding machine, to form real-time adjustment operation state data.

[0097] Step S6: Identify the error parameters of the real-time adjusted operation status data based on the dynamic simulation data of soil washing, so as to obtain the control error parameters; optimize the dynamic feeding balance control of the conveying device according to the control error parameters, and generate the dynamic feeding control parameters to execute the soil washing and remediation control operation.

[0098] In this embodiment, the key parameters causing deviations are identified, such as the actual speed of the conveyor belt, the actual feeding frequency of the feeder, etc., to form the control error parameters. These error parameters reflect the differences between the actual system and the simulation model, providing a basis for subsequent control optimization. The operation status of the conveying device is monitored in real time, and adaptive adjustment is made according to the error parameters to ensure that the materials can enter the soil remediation area evenly and accurately. During the algorithm optimization process, factors such as the dynamic characteristics of the feeder and the change of the conveyor belt speed need to be considered to obtain the optimal dynamic feeding control parameters. The optimized dynamic feeding control parameters are sent to the control system of the conveying device in real time through the fieldbus or wireless network. The control system adjusts the actual feeding behavior of the feeder according to these parameters to ensure that the materials can enter the soil remediation area as required. The control system will also monitor the operation status of the adjusted system in real time to provide feedback information for subsequent control optimization.

[0099] In this embodiment, refer to Figure 2 , which is a schematic diagram of the detailed implementation steps of step S1. In this embodiment, the detailed implementation steps of step S1 include:

[0100] Step S11: Monitor the real-time operation of the front-end conveying device to obtain the device monitoring status data; the device monitoring status data includes soil weight parameters, the feeding rate of the feeder, and the conveyor belt speed.

[0101] Step S12: Obtain the image of the soil to be repaired by the conveying device.

[0102] Step S13: Perform visual recognition of the soil boundary on the image of the soil to be repaired by the conveying device to extract the soil contour line.

[0103] Step S14: Perform boundary segmentation on the image of the soil to be repaired by the conveying device based on the soil contour line to obtain the soil remediation boundary area.

[0104] Step S15: Identify the soil particle size of the soil remediation boundary area to obtain the soil particle size.

[0105] Step S16: Perform quantitative analysis of soil pollution based on the soil particle size to obtain the soil pollution degree data.

[0106] In this embodiment, based on the sensors of the front-end conveying device, the soil weight parameter, the feeding rate of the feeding machine, and the conveyor belt speed are obtained. A high-definition camera is deployed on the conveying device to collect images of the soil to be repaired in real time, ensuring that the image resolution is high enough to clearly show the detailed features of the soil. According to the actual situation, multiple cameras are used for stereoscopic shooting to obtain richer soil information. Using image processing algorithms such as edge detection and region segmentation, the boundary contour line of the soil is identified on the soil image. The key to contour line extraction lies in accurately distinguishing the soil from other background elements, which needs to be optimized according to the characteristics of the soil color, texture, etc. Using deep learning-based image segmentation technology to improve the accuracy and stability of contour line recognition, the original soil image is segmented, and after segmentation, the boundary area that needs attention for soil repair is clearly divided. The determination of the boundary area is crucial for subsequent soil particle size recognition and pollution analysis. Using image analysis technology to identify the particle size distribution in the soil, analyzing using the characteristics of the particle shape, texture, etc., and realizing automatic recognition by combining a pre-trained machine learning model. Using chemical analysis, spectral analysis and other means to quantitatively detect the pollutants in the soil, and obtaining the pollution concentration data of the soil for the main pollutant indicators such as heavy metals and organic substances. The soil pollution degree data is the key input for formulating the soil repair plan and provides a basis for the subsequent repair process.

[0107] In this embodiment, refer to Figure 3 , which is a schematic diagram of the detailed implementation steps of step S2. In this embodiment, the detailed implementation steps of the said step S2 include:

[0108] Step S21: Conduct a weight perturbation analysis on the conveyor belt speed according to the soil weight parameter to obtain the conveyor belt speed perturbation data of the weight;

[0109] Step S22: Conduct a non-linear correlation mapping learning on the soil weight parameter and the conveyor belt speed according to the conveyor belt speed perturbation data of the weight to obtain the weight-conveyor speed correlation data;

[0110] Step S23: Conduct a speed fluctuation response analysis on the conveyor belt speed and the feeding rate of the feeding machine to obtain the feeding response data affected by the speed;

[0111] Step S24: Conduct a multi-level collaborative response neural network learning on the weight-conveyor speed correlation data and the feeding response data affected by the speed to generate the collaborative response data of the conveying device.

[0112] In this embodiment, a weighing sensor is installed on the conveying device to monitor the weight change of the soil in real time, record the actual running speed of the conveyor belt under different soil weights, analyze the disturbance of the weight change on the speed, establish a real-time correspondence between weight and speed, obtain detailed weight disturbance data, use a non-linear regression model to model the relationship between the two, and use machine learning algorithms such as neural networks and support vector machines to fit a non-linear correlation function between weight and speed, so as to obtain accurate weight-conveying speed correlation data, which provides a basis for subsequent collaborative response analysis. Synchronously monitor the conveyor belt speed and the feeding rate of the feeding machine, analyze the dynamic response relationship between the two, study the influence of speed fluctuations on the feeding process, obtain detailed speed-feeding response data, use the soil weight, conveyor belt speed and feeding machine feeding rate as input features, construct a multi-layer perceptron (MLP) neural network model, and use the aforementioned weight-conveying speed correlation data and the feeding response data affected by speed to perform end-to-end supervised learning training on the neural network model. During the training process, the network will automatically learn the complex non-linear mapping relationship between the three, and finally obtain an intelligent response model that can collaboratively control the conveyor belt speed and the feeding rate of the feeding machine. Apply the trained neural network model to the actual control of the conveying device to output collaborative response data in real time.

[0113] In this embodiment, referring to Figure 4 as described, it is a schematic diagram of the detailed implementation steps of step S3. In this embodiment, the detailed implementation steps of step S3 include:

[0114] Step S31: Obtain the monitoring image of the front-end conveying device;

[0115] Step S32: Perform component space topology analysis on the monitoring image of the front-end conveying device to obtain component space topology data;

[0116] Step S33: Perform three-dimensional structure analysis based on the component space topology data to obtain component three-dimensional structure data;

[0117] Step S34: Use the component three-dimensional structure data to perform three-dimensional reconstruction of the front-end conveying device monitoring image and construct a three-dimensional structure model of the device;

[0118] Step S35: Perform dynamic parameter rendering on the three-dimensional structure model of the device according to the collaborative response data of the conveying device to construct a dynamic rendering model of the conveying device.

[0119] In this embodiment, multiple high-definition cameras are installed on the front-end conveying device to collect the monitoring images of the device in real time. The collected image data is transmitted to a computing device for subsequent image analysis and processing to ensure that the resolution, clarity, and acquisition frequency of the images can meet the requirements of subsequent analysis. Using computer vision technology, target detection and segmentation are performed on the collected device images to identify each component, analyze the relative positions and connection relationships between the components, establish the spatial topological structure between the components, encode this topological information into structured data, and use it as the basis for subsequent 3D reconstruction. Using computer vision technology, the 3D shapes and sizes of each component are reconstructed from the image data collected from multiple angles. Combining the obtained component topological information, these 3D models are assembled into a complete 3D device structure, and accurate 3D component structure data is output to provide the necessary geometric information for subsequent 3D device reconstruction. According to the topological relationship of the components, each component is assembled into a complete 3D device model. Using the dynamic rendering function of 3D modeling and simulation software, by adjusting relevant parameter values, the 3D model can dynamically reflect the real-time operating state of the conveying device. Through texture mapping, material assignment, etc. to the model, its visual effect is closer to the real device. Finally, a high-fidelity 3D structure model of the conveying device is output. According to the collaborative response data, dynamic simulation and rendering are performed on each component of the 3D model to simulate the motion characteristics and state changes of the device under actual working conditions, construct a dynamic 3D device model, and output the final dynamic rendering model of the conveying device to provide visual support for subsequent simulation analysis.

[0120] In this embodiment, step S4 includes the following steps:

[0121] Step S41: Perform digital dynamic simulation of soil leaching on the dynamic rendering model of the conveying device to obtain soil leaching dynamic simulation data;

[0122] Step S42: Perform weight-speed proportional control analysis on the soil leaching dynamic simulation data based on the weight-conveying speed correlation data to generate soil weight-conveyor belt speed proportional data;

[0123] Step S43: Dynamically adjust the speed parameters of the soil weight-conveyor belt speed proportional data based on the soil remediation boundary region to obtain conveyor belt dynamic speed adjustment data; the conveyor belt dynamic speed adjustment data includes dynamic acceleration adjustment data and dynamic deceleration adjustment data;

[0124] Step S44: Calculate the transient feeding speed of the soil leaching dynamic simulation data to obtain the transient feeding speed.

[0125] In this embodiment, a three-dimensional CAD model of the conveying device is established, and the dynamic leaching process of the soil is simulated in the model. The computational fluid dynamics (CFD) simulation technology is adopted to set the key parameters in the soil leaching process, such as water flow velocity, flow rate, temperature, etc. Based on the CFD simulation, the dynamic changes of the soil during the entire leaching process are obtained, and the dynamic simulation data of soil leaching are formed. Referring to the actual test data, an association model between the operating speed of the conveying device and the soil weight is established. The obtained dynamic simulation data of soil leaching are input into the above association model for analysis. Through analysis, the conveyor belt speed parameters that meet the soil leaching requirements are obtained, and the soil weight-conveyor belt speed ratio data are formed. For the determination and analysis of the repair boundary area, it is determined whether acceleration or deceleration is required. According to the obtained acceleration / deceleration adjustment amplitude data, the weight-speed ratio model is dynamically adjusted. The flow characteristics of the soil on the conveyor belt are analyzed, and the adjusted conveyor belt speed parameters are the required conveyor belt dynamic speed adjustment data, including both acceleration and deceleration cases. For the soil distribution situation at a certain moment on the conveyor belt, the ideal feeding speed is calculated to ensure uniform leaching of the soil.

[0126] In this embodiment, the specific steps of step S43 are as follows:

[0127] Perform morphological analysis on the soil repair boundary area to obtain the repair area morphological data;

[0128] Based on the repair area morphological data, calculate the area of the soil repair boundary area to obtain the area of the boundary area to be repaired;

[0129] Compare the area of the boundary area to be repaired with the preset threshold of the soil repair boundary area. When the preset threshold of the soil repair boundary area is greater than the area of the boundary area to be repaired, it is determined that the soil repair boundary area is a smaller boundary area, and an acceleration adjustment amplitude analysis is performed to obtain the acceleration adjustment amplitude data;

[0130] Based on the conveyor belt acceleration adjustment amplitude data, perform dynamic acceleration adjustment on the soil weight-conveyor belt speed ratio data to obtain the dynamic acceleration adjustment data;

[0131] When the preset threshold of the soil repair boundary area is less than or equal to the area of the boundary area to be repaired, it is determined that the soil repair boundary area is a larger boundary area, and a deceleration adjustment amplitude analysis is performed to obtain the deceleration adjustment amplitude data;

[0132] Based on the deceleration adjustment amplitude data, perform dynamic deceleration adjustment on the soil weight-conveyor belt speed ratio data to obtain the dynamic deceleration adjustment data.

[0133] In this embodiment, the acquired data is processed and analyzed. The geometric shape parameters of the boundary area, such as length and width, are analyzed. Based on the morphological data of the repair area, the total area of the boundary area to be repaired is calculated. Based on the preset area threshold of the soil repair boundary area as the judgment criterion, the area of the boundary area to be repaired is compared with the preset threshold. If the threshold is greater than the area to be repaired, it is determined as a smaller boundary area; otherwise, it is determined as a larger boundary area. For the smaller repair boundary area, the space and range for appropriately increasing the conveyor belt speed are analyzed, and the required acceleration adjustment amplitude parameter in this case is calculated. The dynamic acceleration adjustment parameter in the smaller boundary area is calculated, and these dynamic acceleration adjustment data are output to provide a basis for subsequent intelligent control. For the larger repair boundary area, the space and range for appropriately reducing the conveyor belt speed are analyzed, and the required deceleration adjustment amplitude parameter in this case is calculated. The dynamic deceleration adjustment parameter in the larger boundary area is calculated.

[0134] In this embodiment, the specific steps of step S5 are as follows:

[0135] Step S51: Based on the soil pollution degree data and the conveyor belt dynamic speed adjustment data, an adaptive feeding speed compensation optimization is performed on the transient feeding speed to obtain the transient feeding compensation speed;

[0136] Step S52: An optimal collaborative control decision is made on the conveyor belt dynamic speed adjustment data and the transient feeding compensation speed to obtain the optimal control parameters of the conveying device;

[0137] Step S53: According to the optimal control parameters of the conveying device, real-time parameter adjustment is performed on the front-end conveying device, and real-time adjustment operation state data is obtained.

[0138] In this embodiment, in combination with the conveyor belt dynamic speed adjustment data, the transient feeding speed is correspondingly adjusted. An adaptive algorithm is used to dynamically optimize the feeding speed according to the real-time pollution degree and conveyor belt speed changes to ensure that the soil is fully leached during the conveying process. A multi-objective optimization algorithm is used to find the optimal combination of parameters such as the conveyor belt speed and feeding speed on the premise of meeting the soil repair requirements. Through optimization calculation, the optimal control parameters of the conveying device are obtained, including speed adjustment strategies and feeding compensation strategies, etc. Through sensor monitoring, the operation state data of the conveying device is obtained in real time, including speed, feeding situation, etc. These real-time data are fed back to the aforementioned optimization model to continuously optimize the control parameters and form a closed-loop control.

[0139] In this embodiment, the specific steps of step S51 are as follows:

[0140] Based on the soil pollution degree data, the calculation of the material demand for leaching is performed to obtain the current device material demand data;

[0141] Analyze the feeding speed range of the transient feeding speed based on the dynamic speed adjustment data of the conveyor belt to obtain the feeding speed range data;

[0142] Perform adaptive feeding speed adjustment on the feeding speed range data based on the current device material requirement data to obtain the adaptive feeding speed;

[0143] Perform feeding difference compensation optimization on the transient feeding speed according to the adaptive feeding speed to obtain the transient feeding compensation speed.

[0144] In this embodiment, through soil sampling and analysis, or other soil detection methods, data on the degree of soil pollution are obtained. These data represent the degree of soil pollution in different regions, such as pollutant concentration or pollution level. Using a predefined material requirement model or algorithm, the soil pollution degree data are converted into the corresponding leaching material requirements. The model or algorithm considers factors such as the severity, area, and depth of the soil pollution degree to calculate the material requirements. Combine the calculation results of the leaching material requirements with the operating parameters and real-time status data of the conveying device to obtain the current device material requirement data. These data represent the amount of materials required by the current device during leaching and repair. Combine the conveyor belt speed data and the characteristic parameters of the feeding machine, and use a predefined feeding speed analysis model or algorithm to calculate and determine the adjustable range of the transient feeding speed. This range takes into account the influence of the conveyor belt speed change to ensure that the feeding speed is within a safe and effective range. According to the current device material requirement data, combine the feeding speed range data and the control strategy of the feeding machine to perform adaptive adjustment of the feeding speed. This adjustment involves operations such as increasing, decreasing, or maintaining the feeding speed to meet the material requirements of the current device. According to the adjusted feeding speed, obtain the value of the adaptive feeding speed. This speed can meet the material requirements of the current device and takes into account the limitations of the feeding speed range and the changes in the actual operating status of the device.

[0145] In this embodiment, the specific steps of step S6 are as follows:

[0146] Step S61: Identify the error parameters of the real-time adjusted operating status data based on the dynamic simulation data of soil leaching to obtain the control error parameters;

[0147] Step S62: Perform error control optimization on the optimal control parameters of the conveying device based on the control error parameters to obtain the error optimization parameters;

[0148] Step S63: Perform dynamic feeding balance control optimization on the conveying device according to the error optimization parameters to generate dynamic feeding control parameters;

[0149] Step S64: Execute the soil leaching and repair control operation based on the dynamic feeding control parameters.

[0150] In this embodiment, the deviation between the actual situation and the simulation result under different operating states is analyzed, and statistical analysis is performed on these deviations to identify key error parameters affecting system control, such as conveyor belt speed error, feeding quantity error, etc. An optimization algorithm is used to adjust the key control parameters of the conveying device. The goal is to minimize the deviation of these key parameters and obtain a set of optimized parameters that can effectively suppress control errors. By optimizing parameters such as conveyor belt speed and feeding motor speed, the actual operating state is made as close as possible to the ideal state. The dynamic balance control algorithm is adopted to optimize and adjust the feeding speed, quantity, etc. according to the real-time operating state data. The goal is to ensure that the entire conveying system is in the best feeding balance state with uniform material distribution. After optimization, dynamic feeding control parameters that can meet the actual repair requirements are obtained. According to these control parameters, the conveyor belt speed, feeding motor, etc. are adjusted and controlled in real time to ensure that during the entire repair process, the feeding quantity and distribution of the material can meet the requirements and improve the repair effect. The operating state of the entire system is monitored and optimized to ensure the stability and reliability of the repair operation.

[0151] In this embodiment, a control system for the front-end conveying device for soil washing and remediation is provided, which is used to execute the control method for the front-end conveying device for soil washing and remediation as described above, and includes:

[0152] A repair boundary module, configured to obtain device monitoring status data and the image of the soil to be remediated by the conveying device; the device monitoring status data includes soil weight parameters, the feeding rate of the feeding machine, and the conveyor belt speed; the soil remediation boundary area is obtained based on the image of the soil to be remediated by the conveying device;

[0153] A collaborative response module, configured to perform non-linear correlation mapping learning on the conveyor belt speed according to the soil weight parameters to obtain weight-conveyor speed correlation data; perform multi-level collaborative response neural network learning on the conveyor belt speed and the feeding rate of the feeding machine based on the weight-conveyor speed correlation data, so as to generate collaborative response data of the conveying device;

[0154] A dynamic parameter rendering module, configured to obtain the monitoring image of the front-end conveying device; obtain the three-dimensional structure data of the components based on the monitoring image of the front-end conveying device; perform dynamic parameter rendering on the three-dimensional structure data of the components according to the collaborative response data of the conveying device, so as to construct a dynamic rendering model of the conveying device;

[0155] A dynamic simulation module, configured to perform digital dynamic simulation of soil washing on the dynamic rendering model of the conveying device to obtain soil washing dynamic simulation data; perform dynamic adjustment of speed parameters on the soil washing dynamic simulation data based on the soil remediation boundary area, so as to obtain conveyor belt dynamic speed adjustment data;

[0156] A transient feeding compensation module is used to perform adaptive feeding speed compensation optimization based on the dynamic speed adjustment data of the conveyor belt, so as to obtain the transient feeding compensation speed; perform real-time parameter adjustment on the front-end conveyor device according to the transient feeding compensation speed, and obtain the real-time adjustment operation status data;

[0157] A dynamic feeding balance module is used to identify error parameters of the real-time adjustment operation status data based on the dynamic simulation data of soil washing, so as to obtain control error parameters; perform dynamic feeding balance control optimization on the conveyor device according to the control error parameters, and generate dynamic feeding control parameters to execute the soil washing and remediation control operation.

[0158] The present invention obtains key input information by acquiring the monitoring status data of the device and the image of the soil to be repaired on the conveyor device. The monitoring status data of the soil weight parameter, the feeding rate of the feeder, and the conveyor belt speed provide the real-time situation of the device operation. The specific area to be repaired is determined based on the soil remediation boundary area obtained from the image of the soil to be repaired on the conveyor device, providing a basis for precise positioning in subsequent steps. By learning the non-linear correlation mapping between the soil weight parameter and the conveyor belt speed, a weight-conveyor speed relationship is established to provide a reference basis for the conveyor belt speed. Based on the multi-level collaborative response neural network learning of the weight-conveyor speed correlation data, the complex relationship between the conveyor belt speed and the feeding rate of the feeder can be captured, thereby generating the collaborative response data of the conveyor device to achieve the optimal control of the device operation. By acquiring the monitoring image of the front-end conveyor device and extracting the three-dimensional structure data of the components, a dynamic rendering model of the conveyor device is established. This model performs dynamic parameter rendering based on the collaborative response data of the conveyor device, which can reflect the actual state and position of each component of the conveyor device, providing an accurate basis for subsequent control optimization. By performing digital dynamic simulation of soil washing on the dynamic rendering model of the conveyor device, the process of soil washing is simulated, and the dynamic simulation data of soil washing is obtained. Based on the soil remediation boundary area, the speed parameters of the simulation data are dynamically adjusted, and the speed of the conveyor belt can be adjusted according to the requirements of the specific repair area to achieve precise control of soil washing. By performing adaptive feeding speed compensation optimization based on the dynamic speed adjustment data of the conveyor belt, the optimization adjustment of the feeding speed is realized. The transient feeding compensation speed takes into account the relationship between the conveyor belt speed and the feeding rate of the feeder. Through adaptive compensation, more precise feeding control is achieved. The acquisition of the real-time adjustment operation status data reflects the actual operation situation of the device, providing data support for subsequent error parameter identification. By identifying the error parameters from the dynamic simulation data of soil washing, the control error parameters are determined. Based on the control error parameters, dynamic feeding balance control optimization is performed on the conveyor device to generate dynamic feeding control parameters to achieve the soil washing and remediation control operation. Such a control strategy can precisely adjust the device, improve the repair effect, and minimize errors to the greatest extent.

[0159] Therefore, from any perspective, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the application documents are intended to be encompassed within the present invention.

[0160] As described above, these are merely specific embodiments of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art. The general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but rather will conform to the broadest scope consistent with the principles and novel features invented herein.

Claims

1. A control method for a front-end conveyor device for soil leaching and remediation, characterized in that: The following steps are involved: Step S1: Acquire device monitoring status data and a conveyor device image of the soil to be repaired; the device monitoring status data includes soil weight parameters, material feeding rate of the feeding machine and conveyor belt speed; obtain a soil repair boundary area based on the conveyor device image of the soil to be repaired; Step S2: performing nonlinear correlation mapping learning on the conveyor belt speed according to the soil weight parameter to obtain weight-conveying speed correlation data; performing multi-level coordinated response neural network learning on the conveyor belt speed and the material feeding rate of the feeding machine based on the weight-conveying speed correlation data, thereby generating the coordinated response data of the conveying device; Step S3: Acquire a monitoring image of the front-end conveying device; obtain the three-dimensional structure data of the component based on the monitoring image of the front-end conveying device; Performing dynamic parameter rendering on the three-dimensional structure data of the component according to the coordinated response data of the transmission device, thereby constructing a dynamic rendering model of the transmission device; Step S4: Performing digital dynamic simulation of soil leaching on the dynamic rendering model of the conveyor device to obtain soil leaching dynamic simulation data; dynamically adjusting the speed parameters of the soil leaching dynamic simulation data based on the soil remediation boundary area to obtain conveyor belt dynamic speed adjustment data; the specific steps of step S4 are: Step S41: performing a digital dynamic simulation of soil leaching on the dynamic rendering model of the conveying device to obtain soil leaching dynamic simulation data; Step S42: performing weight-speed ratio control analysis on the soil leaching dynamic simulation data based on the weight-conveyor speed correlation data to generate soil weight-conveyor belt speed ratio data; Step S43: dynamically adjust the speed parameter of the soil weight-conveyor belt speed ratio data based on the soil remediation boundary area, so as to obtain the conveyor belt dynamic speed adjustment data; the conveyor belt dynamic speed adjustment data includes dynamic acceleration adjustment data and dynamic deceleration adjustment data; the specific steps of step S43 are: Conduct morphological analysis on the soil restoration boundary area to obtain restoration area morphological data; The area of ​​the soil restoration boundary area is calculated based on the restoration area morphological data, thereby obtaining the area of ​​the boundary area to be restored; The area of ​​the boundary area to be repaired is compared based on a preset soil remediation boundary area area threshold. When the preset soil remediation boundary area threshold is greater than the area of ​​the boundary area to be repaired, the soil remediation boundary area is determined to be a smaller boundary area, and an accelerated adjustment amplitude analysis is performed to obtain accelerated adjustment amplitude data. Dynamically adjusting the soil weight-conveyor belt speed ratio data based on the conveyor belt acceleration adjustment amplitude data to obtain dynamic acceleration adjustment data; When the preset soil remediation boundary area threshold is less than or equal to the area of ​​the boundary area to be remediated, the soil remediation boundary area is determined to be a larger boundary area, and a deceleration adjustment amplitude analysis is performed to obtain deceleration adjustment amplitude data; Dynamically decelerating and adjusting the soil weight-conveyor belt speed ratio data based on the deceleration adjustment amplitude data to obtain dynamic deceleration adjustment data; Step S44: calculating the transient material shifting speed on the soil leaching dynamic simulation data to obtain the transient material shifting speed; Step S5: Adaptively optimize the material shifting speed compensation based on the dynamic speed adjustment data of the conveyor belt, thereby obtaining a transient material shifting compensation speed; adjust the parameters of the front-end conveying device in real time according to the transient material shifting compensation speed, and obtain real-time adjustment operation status data; Step S6: performing error parameter identification on the real-time adjustment operation status data based on the soil leaching dynamic simulation data, thereby obtaining a control error parameter; The dynamic material shifting balance control of the conveying device is optimized according to the control error parameters, and the dynamic material shifting control parameters are generated to perform the soil leaching and remediation control operation.

2. The control method of the front-end conveyor for soil leaching and remediation according to claim 1, characterized in that: The specific steps of step S1 are: Step S11: Real-time operation monitoring of the front-end conveying device is performed to obtain device monitoring status data; the device monitoring status data includes soil weight parameters, material feeding rate of the feeding machine and conveyor belt speed; Step S12: Acquire the image of the soil to be repaired by the conveying device; Step S13: performing soil boundary visual recognition on the image of the soil to be repaired by the conveyor device to extract the soil contour line; Step S14: performing boundary segmentation on the image of the soil to be repaired of the conveying device based on the soil contour line, thereby obtaining a soil repair boundary area; Step S15: identifying the soil particle size in the soil remediation boundary area to obtain the soil particle size; Step S16: Performing a quantitative analysis of soil pollution based on soil particle size to obtain soil pollution degree data.

3. The control method of the front-end conveyor for soil leaching and remediation according to claim 1, characterized in that: The specific steps of step S2 are: Step S21: performing weight disturbance analysis on the conveyor belt speed according to the soil weight parameter to obtain weight conveyor belt speed disturbance data; Step S22: performing nonlinear correlation mapping learning on soil weight parameters and conveyor belt speed according to the conveyor belt speed disturbance data of weight, so as to obtain weight-conveying speed correlation data; Step S23: performing speed fluctuation response analysis on the conveyor belt speed and the material feeding rate of the material feeding machine, thereby obtaining material feeding response data affected by the speed; Step S24: Perform multi-level coordinated response neural network learning on the weight-transmission speed association data and the speed-influenced material selection response data, thereby generating the transmission device coordinated response data.

4. The control method of the front-end conveyor for soil leaching and remediation according to claim 1, characterized in that: The specific steps of step S3 are: Step S31: Acquire monitoring images of the front-end transmission device; Step S32: performing component space topology analysis on the monitoring image of the front-end transmission device to obtain component space topology data; Step S33: performing a three-dimensional structural analysis based on the component spatial topological data, thereby obtaining the component three-dimensional structural data; Step S34: using the component three-dimensional structure data to perform three-dimensional reconstruction of the monitoring image of the front-end transmission device to construct a three-dimensional structure model of the device; Step S35: dynamically rendering the three-dimensional structure model of the device according to the coordinated response data of the transmission device, thereby constructing a dynamic rendering model of the transmission device.

5. The control method of the front-end conveyor for soil leaching and remediation according to claim 1, characterized in that: The specific steps of step S5 are: Step S51: adaptively optimizing the transient material shifting speed compensation based on the soil pollution degree data and the conveyor belt dynamic speed adjustment data, thereby obtaining the transient material shifting compensation speed; Step S52: making an optimal coordinated control decision on the dynamic speed adjustment data of the conveyor belt and the transient material shifting compensation speed to obtain the optimal control parameters of the conveyor device; Step S53: adjusting the parameters of the front-end transmission device in real time according to the optimal control parameters of the transmission device, and obtaining real-time adjustment operation status data.

6. The control method of the front-end conveyor for soil leaching and remediation according to claim 5, characterized in that: The specific steps of step S51 are: Calculate the leaching material demand based on the soil pollution degree data to obtain the current device material demand data; Based on the dynamic speed adjustment data of the conveyor belt, the material speed range analysis is performed on the transient material speed, so as to obtain the material speed range data; Adaptively adjust the material shifting speed range data based on the current device material demand data to obtain an adaptive material shifting speed; The transient material shifting speed is optimized by performing material shifting difference compensation according to the adaptive material shifting speed, thereby obtaining the transient material shifting compensation speed.

7. The control method of the front-end conveyor for soil leaching and remediation according to claim 1, characterized in that: The specific steps of step S6 are: Step S61: performing error parameter identification on the real-time adjustment operation status data based on the soil leaching dynamic simulation data, thereby obtaining a control error parameter; Step S62: performing error control optimization on the optimal control parameters of the conveying device based on the control error parameters to obtain error optimization parameters; Step S63: Optimizing the dynamic material shifting balance control of the conveying device according to the error optimization parameter to generate a dynamic material shifting control parameter; Step S64: Execute soil leaching and remediation control operations based on dynamic material allocation control parameters.

8. A control system for a front-end conveyor device for soil leaching and remediation, characterized in that: A control method for executing the front-end conveyor for soil washing and remediation according to claim 1, comprising: A restoration boundary module is used to obtain device monitoring status data and a conveyor device image of the soil to be restored; the device monitoring status data includes soil weight parameters, material feeding rate of the feeding machine and conveyor belt speed; and a soil restoration boundary area is obtained based on the conveyor device image of the soil to be restored; The coordinated response module is used to perform nonlinear correlation mapping learning on the conveyor belt speed according to the soil weight parameter to obtain weight-conveying speed correlation data; based on the weight-conveying speed correlation data, a multi-level coordinated response neural network learning is performed on the conveyor belt speed and the material feeding rate of the feeding machine to generate the coordinated response data of the conveying device; A dynamic parameter rendering module is used to obtain a monitoring image of a front-end transmission device; obtain component three-dimensional structure data based on the monitoring image of the front-end transmission device; and dynamically render the component three-dimensional structure data according to the coordinated response data of the transmission device, thereby constructing a dynamic rendering model of the transmission device; The dynamic simulation module is used to perform digital dynamic simulation of soil leaching on the dynamic rendering model of the conveyor device to obtain soil leaching dynamic simulation data; dynamically adjust the speed parameters of the soil leaching dynamic simulation data based on the soil remediation boundary area to obtain the conveyor belt dynamic speed adjustment data; The transient material shifting compensation module is used to perform adaptive material shifting speed compensation optimization based on the dynamic speed adjustment data of the conveyor belt, so as to obtain the transient material shifting compensation speed; perform real-time parameter adjustment on the front-end conveying device according to the transient material shifting compensation speed, and obtain real-time adjustment operation status data; The dynamic material shifting balance module is used to identify the error parameters of the real-time adjustment of the operating status data based on the soil leaching dynamic simulation data, so as to obtain the control error parameters; according to the control error parameters, the dynamic material shifting balance control optimization of the conveying device is performed to generate the dynamic material shifting control parameters to perform the soil leaching remediation control operation.

Images