Sorting Strategy Determination Method and Device

Abstract

This application relates to a method and device for determining a sorting strategy. The method includes: obtaining target condition parameters corresponding to a target sorting task; the target condition parameters include sorting action parameters of a sorting device, coal quality characteristics of coal to be sorted, and real-time sorting data; the real-time sorting data includes the coal flow rate and particle size distribution of the coal to be sorted; determining a target sorting strategy according to the target condition parameters so that the sorting efficiency and product quality corresponding to the target sorting task reach the optimal state; the target sorting strategy at least includes adjusting the screening particle size and changing the dense medium density. This application can dynamically adjust the sorting strategy, ensure that the sorting process always remains in the optimal state, thereby improving the sorting efficiency, reducing the time of ineffective sorting and repeated processing, enhancing the adaptability of the sorting process, and solving the technical problem that the coal sorting process faces complex sorting conditions and it is difficult to achieve the best sorting effect.

Description

Technical Field

[0001] The present application relates to the technical field of coal, and particularly to a method and device for determining a separation strategy. Background Art

[0002] Coal separation refers to the process of processing coal to remove impurities, reduce ash content and sulfur content, thereby improving the quality of coal. This is the application of mineral processing technology in the coal industry. The main basis for coal separation is the differences in various physical properties, surface physicochemical properties and chemical properties of minerals.

[0003] Currently, due to the diversity of coal quality characteristics (such as ash content, moisture content, sulfur content, particle size distribution, etc.) of coal and the separation action parameters of separation equipment (such as the sieve hole size and vibration frequency of a screening machine, the medium density and flow rate of a heavy medium separator, etc.), the existing coal separation process faces complex separation conditions and it is difficult to achieve the best separation effect. Therefore, there is an urgent need for improvement. Summary of the Invention

[0004] Based on this, in view of the above technical problems, it is necessary to provide a method and device for determining a separation strategy that can optimize the separation process.

[0005] In a first aspect, the present application provides a method for determining a separation strategy, the method comprising:

[0006] Obtain target condition parameters corresponding to a target separation task; the target condition parameters include separation action parameters of separation equipment, coal quality characteristics of coal to be separated, and real-time separation data; the real-time separation data includes the coal flow rate and particle size distribution of the coal to be separated;

[0007] Determine a target separation strategy according to the target condition parameters, so that the separation efficiency and product quality corresponding to the target separation task reach the optimum; the target separation strategy at least includes adjusting the screening particle size and changing the heavy medium density.

[0008] In one embodiment, determining the target separation strategy according to the target condition parameters includes:

[0009] Match the target condition parameters with each simulation condition parameter in a simulation experiment;

[0010] Determine the simulation separation strategy corresponding to the successfully matched simulation condition parameter as the target separation strategy.

[0011] In one embodiment, the simulation separation strategy corresponding to each simulation condition parameter is determined in the following manner:

[0012] Construct a Markov model for the sorting process; wherein, the state space of the Markov model includes the simulation condition parameters corresponding to the simulation sorting tasks, the action space of the Markov model includes adjusting the screening particle size and changing the heavy medium density, and the reward function of the Markov model is determined according to the sorting efficiency and product quality;

[0013] For each simulation condition parameter, adjust the action space in the Markov model to obtain the simulation sorting strategy corresponding to the simulation condition parameter, so that the sorting efficiency and product quality corresponding to the simulation sorting strategy of the simulation condition parameter reach the optimum.

[0014] In one embodiment, constructing a Markov model for the sorting process includes:

[0015] Construct a three-dimensional model of the sorting equipment;

[0016] In the state space of the Markov model, add the state parameters of the three-dimensional model;

[0017] In the action space of the Markov model, add the control parameters of the moving parts in the three-dimensional model.

[0018] In one embodiment, the state parameters of the three-dimensional model include geometric shape parameters, texture coordinate parameters, material property parameters, structural property parameters, and physical property parameters;

[0019] Correspondingly, in the state space of the Markov model, adding the state parameters of the three-dimensional model includes:

[0020] In the state space of the Markov model, add the state representation corresponding to the state parameters of the three-dimensional model and the state transition matrix corresponding to the three-dimensional model; the state representation is used to describe the position, speed, and shape of the sorting equipment at different times;

[0021] In one embodiment, the control parameters of the moving parts in the three-dimensional model include position parameters, rotation parameters, speed parameters, acceleration parameters, and switch parameters of the moving parts;

[0022] In the action space of the Markov model, adding the control parameters of the moving parts in the three-dimensional model includes:

[0023] In the action space of the Markov model, add the control actions corresponding to the control parameters of the moving parts in the three-dimensional model.

[0024] In one embodiment, adjusting the action space in the Markov model to obtain the simulation sorting strategy corresponding to the simulation condition parameter includes:

[0025] Adjust the action space in the Markov model to obtain the candidate sorting strategies corresponding to the simulation condition parameters, so that the sorting efficiency and product quality corresponding to the candidate sorting strategies corresponding to the simulation condition parameters reach the optimum;

[0026] Simulate the sorting process corresponding to the candidate sorting strategy based on the three-dimensional model to obtain the sorting result;

[0027] If the result after verification by the expert review model of the sorting result passes the verification, then use the candidate sorting strategy corresponding to the simulation condition parameters as the simulation sorting strategy corresponding to the simulation condition parameters.

[0028] In one embodiment, obtain the coal quality characteristics of the coal to be sorted, including:

[0029] According to the coal image of the coal to be sorted, and determine the associated equipment corresponding to the coal to be sorted; the associated equipment corresponding to the coal to be sorted includes at least one of a conveyor belt, a crusher, a screening machine, a heavy medium separator, and a flotation machine;

[0030] Obtain the equipment operation characteristics of the associated equipment; the equipment operation characteristics of the associated equipment include the equipment sound characteristics and equipment vibration characteristics of the associated equipment;

[0031] Determine the coal quality characteristics of the coal to be sorted according to the coal image and the equipment operation characteristics.

[0032] In one embodiment, determine the coal quality characteristics of the coal to be sorted according to the coal image and the equipment operation characteristics, including:

[0033] Construct a three-dimensional coal pile model corresponding to the coal to be sorted;

[0034] Determine the coal quality characteristics of the coal to be sorted according to the three-dimensional coal pile model, the coal image and the equipment operation characteristics.

[0035] In a second aspect, the present application also provides a sorting strategy determination device, including:

[0036] An acquisition module, configured to acquire target condition parameters corresponding to a target sorting task; the target condition parameters include sorting action parameters of a sorting device, coal quality characteristics of coal to be sorted, and real-time sorting data; the real-time sorting data includes the coal flow rate and particle size distribution of the coal to be sorted;

[0037] A strategy determination module, configured to determine a target sorting strategy according to the target condition parameters, so that the sorting efficiency and product quality corresponding to the target sorting task reach the optimum; the target sorting strategy at least includes adjusting the screening particle size and changing the heavy medium density.

[0038] In a third aspect, the present application further provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0039] Obtain target condition parameters corresponding to a target sorting task; the target condition parameters include sorting action parameters of a sorting device, coal quality characteristics of coal to be sorted, and real-time sorting data; the real-time sorting data includes the coal flow rate and particle size distribution of the coal to be sorted;

[0040] Determine a target sorting strategy according to the target condition parameters so that the sorting efficiency and product quality corresponding to the target sorting task reach the optimum; the target sorting strategy at least includes adjusting the screening particle size and changing the heavy medium density.

[0041] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0042] Obtain target condition parameters corresponding to a target sorting task; the target condition parameters include sorting action parameters of a sorting device, coal quality characteristics of coal to be sorted, and real-time sorting data; the real-time sorting data includes the coal flow rate and particle size distribution of the coal to be sorted;

[0043] Determine a target sorting strategy according to the target condition parameters so that the sorting efficiency and product quality corresponding to the target sorting task reach the optimum; the target sorting strategy at least includes adjusting the screening particle size and changing the heavy medium density.

[0044] In a fifth aspect, the present application further provides a computer program product, including a computer program. When the computer program is executed by a processor, the following steps are implemented:

[0045] Obtain target condition parameters corresponding to a target sorting task; the target condition parameters include sorting action parameters of a sorting device, coal quality characteristics of coal to be sorted, and real-time sorting data; the real-time sorting data includes the coal flow rate and particle size distribution of the coal to be sorted;

[0046] Determine a target sorting strategy according to the target condition parameters so that the sorting efficiency and product quality corresponding to the target sorting task reach the optimum; the target sorting strategy at least includes adjusting the screening particle size and changing the heavy medium density.

[0047] The above sorting strategy determination method and device can dynamically adjust the sorting strategy by obtaining the coal quality characteristics and sorting data of the coal to be sorted in real time, as well as the parameter status of the sorting equipment. This dynamic adjustment can ensure that the sorting process always remains in the optimal state, thereby improving the sorting efficiency and reducing the time of ineffective sorting and repeated processing. Due to the diversity of the coal quality characteristics and sorting action parameters of coal, this method can enhance the adaptability of the sorting process through real-time data monitoring and strategy adjustment. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for the description of the embodiments of the present application or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0049] Figure 1 It is a schematic flowchart of the sorting strategy determination method in an embodiment;

[0050] Figure 2 It is a schematic flowchart of the step of determining the coal quality characteristics of the coal to be sorted in an embodiment;

[0051] Figure 3 It is a schematic flowchart of the step of constructing a Markov model of the sorting process in an embodiment;

[0052] Figure 4 It is a schematic flowchart of the step of adjusting the action space in the Markov model to obtain a simulation sorting strategy corresponding to the simulation condition parameters in an embodiment;

[0053] Figure 5 It is a structural block diagram of a sorting strategy determination device in an embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0054] In order to make the objectives, technical solutions and advantages of the present application clearer, the following further details the present application in conjunction with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0055] In an exemplary embodiment, a sorting strategy determination method is provided, as Figure 1 shown, the method includes:

[0056] S101, obtaining target condition parameters corresponding to a target sorting task.

[0057] Among them, the target condition parameters include the sorting action parameters of the sorting equipment, the coal quality characteristics of the coal to be sorted, and the real-time sorting data.

[0058] Specifically, establish a communication connection with the sorting equipment, send a parameter query request to the sorting equipment, and obtain the sorting action parameters of the equipment. The sorting action parameters may include the operating speed, vibration frequency, sorting accuracy, screen size, etc. of the equipment. Verify the obtained equipment parameters to ensure that the parameter values are within a reasonable range and match the current task requirements.

[0059] Optionally, the coal quality characteristics of the coal to be sorted may include ash content, moisture content, sulfur content, calorific value, etc. of the coal.

[0060] Among them, the real-time sorting data includes the coal flow rate and particle size distribution of the coal to be sorted.

[0061] Specifically, start the data monitoring system, and collect key data during the sorting process in real time, such as the operating status of the equipment, sorting efficiency, coal flow rate, etc. Analyze the real-time sorting data to understand the influence of different coal quality characteristics on the sorting effect.

[0062] S102, determine the target sorting strategy according to the target condition parameters, so that the sorting efficiency and product quality corresponding to the target sorting task reach the optimal.

[0063] Among them, the target sorting strategy at least includes adjusting the screening particle size and changing the heavy medium density.

[0064] In an implementable manner, the target sorting strategy can be determined based on a rule-based method: select or generate a sorting strategy according to preset rules and thresholds. For example, if the coal ash content exceeds a certain threshold, increase the screening particle size or adjust the heavy medium density.

[0065] In another implementable manner, the target sorting strategy can also be determined based on a machine learning method: use algorithms such as supervised learning and reinforcement learning to train a model to predict the optimal sorting strategy according to historical sorting data and target condition parameters. If the historical data contains condition parameters and corresponding optimal strategies, a classification or regression model can be used to predict the target strategy.

[0066] Then, send the determined sorting strategy to the control system of the sorting equipment to perform corresponding adjustment operations.

[0067] For the above sorting strategy determination method, the present application can dynamically adjust the sorting strategy by obtaining in real time the coal quality characteristics and sorting data of the coal to be sorted, as well as the parameter status of the sorting equipment. This dynamic adjustment can ensure that the sorting process always remains in the optimal state, thereby improving the sorting efficiency and reducing the time for ineffective sorting and repeated processing. Due to the diversity of the coal quality characteristics and sorting action parameters of coal, this method can enhance the adaptability of the sorting process through real-time data monitoring and strategy adjustment.

[0068] In an exemplary embodiment, determining the target sorting strategy according to the target condition parameters includes: matching the target condition parameters with each simulation condition parameter in the simulation experiment; and determining the simulation sorting strategy corresponding to the successfully matched simulation condition parameter as the target sorting strategy.

[0069] Among them, the simulation condition parameters are the tests actually carried out in history, and each simulation condition parameter should cover different coal quality characteristics, real-time sorting data (such as coal flow rate, particle size distribution), and sorting action parameters of the sorting equipment.

[0070] Specifically, for each combination of condition parameters, the actual sorting process is simulated through a simulation model, and the corresponding optimal sorting strategy and its effects (such as sorting efficiency, product quality, etc.) are recorded. These data and strategies are sorted into a database for subsequent matching use.

[0071] Exemplarily, the obtained target condition parameters are compared one by one with each simulation condition parameter in the simulation experiment database, or a more advanced matching algorithm (such as the nearest neighbor algorithm, fuzzy matching, etc.) is used for matching. The goal is to find the simulation condition parameter combination that is most similar or closest to the target condition. Once a successfully matched simulation condition parameter combination is found, its corresponding simulation sorting strategy is directly used as the target sorting strategy.

[0072] In an exemplary embodiment, as Figure 2 shown, the simulation sorting strategy corresponding to each simulation condition parameter is determined in the following manner:

[0073] S201, construct a Markov model of the sorting process.

[0074] Among them, the state space of the Markov model includes the coal quality characteristics of the coal to be sorted and the sorting action parameters of the sorting equipment, the action space of the Markov model includes adjusting the screening particle size and changing the heavy medium density, and the reward function of the Markov model is determined according to the sorting efficiency and product quality.

[0075] It can be understood that the construction process of the Markov model is:

[0076] Define the state space: The state space should include the coal quality characteristics of the coal to be sorted (such as ash content, moisture content, sulfur content, particle size distribution, etc.) and the sorting action parameters of the sorting equipment (such as the screen hole size and vibration frequency of the screening machine, the medium density and flow rate of the heavy medium separator, etc.).

[0077] Define the action space: The action space includes adjustable operation parameters, such as adjusting the screening particle size and changing the heavy medium density.

[0078] Define the reward function: The reward function should be defined according to the sorting efficiency and product quality. For example, it can be set as a positive reward for the improvement of sorting efficiency and product quality, and a negative penalty for the decrease of sorting efficiency and product quality.

[0079] S202. For each set of simulation condition parameters, adjust the action space in the Markov model to obtain the simulation sorting strategy corresponding to the simulation condition parameters, so that the sorting efficiency and product quality corresponding to the simulation sorting strategy corresponding to the simulation condition parameters reach the optimal.

[0080] Optionally, for each set of simulation condition parameters, initialize the state of the Markov model. Use the deep reinforcement learning algorithm to train a policy network, which can select the optimal action according to the target state. During the training process, the algorithm will simulate the sorting process, evaluate the quality of each action according to the reward function, and adjust the parameters of the policy network through the backpropagation algorithm to maximize the long-term reward. After the training is completed, the obtained policy network is the simulation sorting strategy under the simulation condition parameters.

[0081] Furthermore, on the basis of deep reinforcement learning, the dynamic programming algorithm can be further combined to optimize the long-term policy. The dynamic programming algorithm can consider the rewards of multiple future time steps, so as to make a more globally optimal decision. At the same time, using the historical sorting strategies and historical sorting conditions of historical sorting tasks, transfer learning can be carried out to accelerate the learning process of new strategies and improve the generalization ability of the strategies.

[0082] Exemplarily, taking Deep Q-Network (DQN) as an example, the specific implementation steps are as follows:

[0083] Initialize the Q network (a deep neural network) to estimate the Q value (i.e., the expected future reward) of each state-action pair. Initialize the experience replay buffer to store the state transition samples during the training process. For each set of simulation condition parameters, reset the state of the Markov model. At each time step, select an action (such as adjusting the screening particle size or changing the heavy medium density) according to the target state and the Q network. Execute the action, observe the new state and reward, and store this state transition sample in the experience replay buffer.

[0084] Randomly sample a batch of samples from the experience replay buffer. For each sample, calculate the target Q-value (based on the target Q-network and the reward function). Calculate the loss using the target Q-value and the predicted value of the target Q-network, and update the parameters of the Q-network through the backpropagation algorithm. Repeat the simulation sorting process and train the Q-network until the Q-network converges or reaches the preset number of training epochs. The converged Q-network is the simulation sorting strategy under the simulation condition parameters and can select the optimal action according to the target state. During the training process, the dynamic programming algorithm can be used to optimize the long-term strategy, considering the rewards of multiple future time steps. At the same time, the data of historical sorting tasks can be used for transfer learning to accelerate the learning process of the Q-network.

[0085] In an exemplary embodiment, as Figure 3 shown, construct a Markov model of the sorting process, including:

[0086] S301, construct a three-dimensional model of the sorting device.

[0087] Optionally, use 3D modeling software (such as Blender, 3ds Max, SolidWorks, etc.) to design the three-dimensional model of the sorting device. Create an accurate geometric model according to the actual size, shape and structure of the device. Add necessary details to the model, such as textures, colors, materials, etc., to improve the authenticity of the simulation.

[0088] S302, in the state space of the Markov model, add the state parameters of the three-dimensional model.

[0089] Among them, the state parameters of the three-dimensional model include geometric shape parameters, texture coordinate parameters, material property parameters, structural property parameters and physical property parameters.

[0090] Exemplarily, the geometric shape parameters include: Vertex position: The three-dimensional coordinates of each vertex in the three-dimensional model. Edge length or area: The length or area of the edges or faces in the model, which can reflect the size and shape changes of the model. Normal direction: The normal direction of the vertex or face, which is used to describe the orientation of the surface.

[0091] The texture and material parameters include: Texture coordinates: Describe the mapping position of the texture image on the model surface. Material properties: Such as color, glossiness, reflectivity, transparency, etc., these properties can affect the appearance of the model during rendering.

[0092] The structural property parameters are deformation and animation parameters, specifically including: Joint angles and positions in skeletal animation: Used to describe the skeletal animation state of the model. Vertex weights: In skeletal animation, each vertex may be affected by multiple bones, and vertex weights describe the degree of this influence. Deformation parameters: Such as parameters for deformation operations such as stretching, bending, and twisting.

[0093] The physical property parameters are physical and kinetic parameters, specifically including: mass, center of gravity, and inertia tensor: used for physical simulation and collision detection. Velocity and acceleration: describe the motion state of the model in physical space. Torque and force: the forces and torques acting on the model, which can affect the motion and deformation of the model.

[0094] Specifically, in the state space of the Markov model, add the state parameters of the 3D model, including:

[0095] In the state space of the Markov model, add the state representations corresponding to the state parameters of the 3D model and the state transition matrix corresponding to the 3D model.

[0096] Among them, the state representation is used to describe the position, velocity, and shape of the sorting device at different times.

[0097] Exemplarily, determine the state space of the Markov model, which should be able to represent all possible states of the sorting device. The states can include the position, velocity, shape of the device, and any other parameters related to the sorting process. Map the state parameters (geometric shape parameters, texture coordinate parameters, material property parameters, structural property parameters, physical property parameters) of the 3D model into the state space of the Markov model. Define corresponding state representations for each state parameter, and these representations should be able to clearly describe the state of the sorting device at different times.

[0098] According to the operation logic and possible state transitions of the sorting device, construct the state transition matrix. Each element in the matrix represents the probability of transitioning from one state to another. Ensure that the state transition matrix conforms to the properties of the Markov chain, that is, the current state is only related to the previous state.

[0099] S303, in the action space of the Markov model, add the control parameters of the moving parts in the 3D model.

[0100] The control parameters of the moving parts in the 3D model include the position parameters, rotation parameters, velocity parameters, acceleration parameters, and switch parameters of the moving parts.

[0101] Specifically, in the action space of the Markov model, add the control parameters of the moving parts in the 3D model, including: in the action space of the Markov model, add the control actions corresponding to the control parameters of the moving parts in the 3D model.

[0102] Exemplarily, determine the action space of the Markov model, which should include all possible control actions. The control actions should be able to change the state of the sorting device, such as moving, rotating, accelerating, decelerating, switching on and off, etc. Map the control parameters (position parameters, rotation parameters, speed parameters, acceleration parameters, switching parameters) of the moving parts in the three-dimensional model to the action space of the Markov model. Define corresponding control actions for each control parameter, and these actions should be able to be directly applied to the moving parts in the three-dimensional model.

[0103] Write the control logic to calculate and apply the necessary control parameters according to the state of the Markov model and the selected actions. Ensure that the control logic can respond to state changes in real time and accurately control the movement of the moving parts.

[0104] Exemplarily, the position parameter describes the position of the moving part in the three-dimensional space, such as the X, Y, and Z coordinates. The rotation parameter is used to describe the rotation state of the moving part, such as the rotation angles around the X, Y, and Z axes. The speed parameter is used to describe the translational or rotational speed of the moving part. The acceleration parameter is used to describe the rate of change of the speed of the moving part. The switching parameter is used for moving parts that can be switched (such as the joints of a robotic arm), and it is necessary to control their switching states.

[0105] The move action is used to specify that the moving part moves a certain distance in a certain direction. The rotate action is used to specify that the moving part rotates a certain angle around a certain axis. The speed adjustment action is used to increase or decrease the translational or rotational speed of the moving part. The acceleration adjustment action is used to change the acceleration of the moving part. The switch action is used to switch the switching state of the moving part.

[0106] In this embodiment, by constructing a three-dimensional model of the sorting device and combining it with the Markov model, accurate simulation and optimization of the sorting process can be achieved.

[0107] In an exemplary embodiment, as Figure 4 shown, adjust the action space in the Markov model to obtain the simulation sorting strategy corresponding to the simulation condition parameters, including:

[0108] S401, adjust the action space in the Markov model to obtain the candidate sorting strategy corresponding to the simulation condition parameters, so that the sorting efficiency and product quality corresponding to the candidate sorting strategy corresponding to the simulation condition parameters reach the optimal.

[0109] Optionally, based on the simulation condition parameters, adjust the action space in the Markov model. This may involve modifying some actions in the action space or adjusting the transition probabilities between actions to optimize the sorting efficiency and product quality under the given simulation conditions. Optimization algorithms (such as genetic algorithms, particle swarm optimization algorithms, etc.) can be used to search for the optimal action space configuration. Based on the adjusted action space, generate a set of candidate sorting strategies. Each strategy corresponds to a specific action space configuration, that is, a specific set of control actions and decision rules.

[0110] S402. Simulate the sorting process corresponding to the candidate sorting strategy based on the three-dimensional model to obtain the sorting result.

[0111] Optionally, load the previously constructed three-dimensional model of the sorting equipment into the simulation environment. According to the candidate sorting strategy, set the relevant parameters in the simulation environment, including the operating parameters of the sorting equipment, the physical property parameters of the coal, etc. Based on the three-dimensional model and the set simulation parameters, perform the simulation of the sorting process. This usually involves simulating the processes of coal flow, screening, and discharging in the sorting equipment. After the simulation is completed, obtain the sorting results from the simulation environment, including indicators such as sorting efficiency, product quality, and energy consumption.

[0112] S403. If the result after verification by the expert review model of the sorting result is verified to pass, then use the candidate sorting strategy corresponding to the simulation condition parameters as the simulation sorting strategy corresponding to the simulation condition parameters.

[0113] Optionally, establish an expert review model that can objectively and comprehensively evaluate the candidate sorting strategies based on the sorting results and preset evaluation criteria. Input the sorting results obtained from the simulation into the expert review model for verification. The verification process may include comparing the simulation results with experimental data, evaluating the improvement degree of sorting efficiency and product quality, analyzing the reduction of energy consumption and cost, etc.

[0114] If the result after verification by the expert review model is verified to pass, that is, the candidate sorting strategy performs well under the simulation conditions and meets the expected sorting efficiency and product quality requirements, then determine the candidate sorting strategy as the simulation sorting strategy corresponding to the simulation condition parameters. If the verification fails, it is necessary to return to step S401, continue to adjust the action space in the Markov model, and generate new candidate sorting strategies for simulation and verification until a satisfactory simulation sorting strategy is found.

[0115] In an exemplary embodiment, obtain the coal quality characteristics of the coal to be sorted, including: based on the coal image of the coal to be sorted, determine the associated equipment corresponding to the coal to be sorted; obtain the equipment operation characteristics of the associated equipment; based on the coal image and the equipment operation characteristics, determine the coal quality characteristics of the coal to be sorted.

[0116] Among them, the associated devices corresponding to the coal to be sorted include at least one of a conveyor belt, a crusher, a screening machine, a heavy medium separator, and a flotation machine.

[0117] Among them, the equipment operation characteristics of the associated devices include the equipment sound characteristics and equipment vibration characteristics of the associated devices.

[0118] Specifically, a camera or image sensor is used to photograph the coal to be sorted to obtain a clear coal image. The image should contain the appearance characteristics of the coal, such as color, texture, shape, etc., and these characteristics may have a certain correlation with the coal quality characteristics of the coal (such as ash content, moisture content, sulfur content, etc.). According to the coal sorting process, determine the devices directly related to the coal to be sorted, such as conveyor belts, crushers, screening machines, heavy medium separators, and flotation machines. These devices will perform different treatments on the coal during the coal sorting process, so their operating parameters can contain information about the coal quality characteristics of the coal. For each associated device, install corresponding sensors to monitor its operating parameters. In particular, pay attention to the device sound parameters (such as noise level, sound frequency, etc.) and device vibration parameters (such as vibration amplitude, vibration frequency, etc.). These parameters can reflect the flow state, collision situation, or sorting effect of the coal inside the device, thereby indirectly reflecting the coal quality characteristics of the coal.

[0119] Then, input the obtained coal image and equipment operation characteristics into a pre-trained machine learning model. The model should be able to infer the coal quality characteristics of the coal to be sorted based on these input data, combined with the prior knowledge of coal sorting. Possible models include a convolutional neural network (CNN) for image processing, and a regression model or classification model for the correlation analysis between equipment operation characteristics and coal quality characteristics. The output result should include key coal quality indicators such as ash content, moisture content, sulfur content, calorific value, etc. of the coal. Ensure that the acquisition of the coal image and equipment operation characteristics is synchronized to accurately associate them. The machine learning model needs to be trained using a large amount of labeled data, and these data should include coal images with different coal quality characteristics and corresponding equipment operation characteristics. During the model training process, carefully select the image characteristics and equipment operation characteristics that are most helpful for predicting coal quality characteristics. As the coal sorting process changes and new data accumulates, the machine learning model should be updated regularly to improve the prediction accuracy.

[0120] Furthermore, based on the coal image and equipment operation characteristics, determine the coal quality characteristics of the coal to be sorted, including: constructing a three-dimensional coal pile model corresponding to the coal to be sorted; determining the coal quality characteristics of the coal to be sorted according to the three-dimensional coal pile model, coal image, and equipment operation characteristics.

[0121] Exemplarily, a three-dimensional scanning technology or a stereoscopic vision technology is used to perform an all-round scan on the coal pile to be sorted, and three-dimensional point cloud data on its surface is obtained. Based on the obtained three-dimensional point cloud data, a three-dimensional coal pile model of the coal to be sorted is constructed using three-dimensional modeling software.

[0122] Specifically, image processing technologies (such as edge detection, texture analysis, etc.) are used to extract key features in the coal image, such as the particle size distribution, color, luster, etc. of the coal. The operating characteristics of the sorting equipment are analyzed, including the vibration frequency of the equipment, the inclination angle of the sieve mesh, the feeding speed, etc.

[0123] The three-dimensional coal pile model, the coal image features, and the equipment operating characteristics are comprehensively analyzed. The three-dimensional coal pile model is used to understand the overall structure and distribution of the coal pile. Combining the coal image features to analyze the surface characteristics of the coal such as particle size, color, luster, etc.; considering the influence of the equipment operating characteristics on coal sorting, for example, the vibration frequency may affect the stratification effect of the coal, and the inclination angle of the sieve mesh may affect the passing rate of coals with different particle sizes, etc.

[0124] Based on the above comprehensive analysis, the coal quality characteristics of the coal to be sorted are determined, including key indicators such as the particle size distribution, ash content, sulfur content, calorific value, etc. of the coal.

[0125] It can be understood that although the steps in the flowcharts involved in the above embodiments are shown in sequence according to the indication of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same moment, but can be executed at different moments, and the execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0126] Based on the same inventive concept, an embodiment of the present application also provides a sorting strategy determination device for implementing the sorting strategy determination method involved above. The solution provided by this device to solve the problem is similar to the solution recorded in the above method. Therefore, the specific limitations in one or more embodiments of the sorting strategy determination device provided below can refer to the limitations on the sorting strategy determination method in the above text, and will not be repeated here.

[0127] In an exemplary embodiment, as Figure 5 shown, a sorting strategy determination device is provided, including:

[0128] An acquisition module 11, configured to acquire target condition parameters corresponding to a target sorting task; the target condition parameters include sorting action parameters of a sorting device, coal quality characteristics of coal to be sorted, and real-time sorting data; the real-time sorting data includes coal flow rate and particle size distribution of the coal to be sorted.

[0129] A strategy determination module 12, configured to determine a target sorting strategy according to the target condition parameters, so that the sorting efficiency and product quality corresponding to the target sorting task reach the optimal; the target sorting strategy at least includes adjusting the screening particle size and changing the dense medium density.

[0130] Each module in the above sorting strategy determination device can be implemented in whole or in part by software, hardware and their combination. Each of the above modules can be embedded in or independent of a processor in a computer device in the form of hardware, or stored in a memory in the computer device in the form of software, so as to facilitate the processor to call and execute the operations corresponding to each of the above modules.

[0131] In an exemplary embodiment, a computer device is provided, including a memory and a processor, and a computer program is stored in the memory. When the processor executes the computer program, the following steps are implemented:

[0132] Acquire target condition parameters corresponding to a target sorting task; the target condition parameters include sorting action parameters of a sorting device, coal quality characteristics of coal to be sorted, and real-time sorting data; the real-time sorting data includes coal flow rate and particle size distribution of the coal to be sorted.

[0133] Determine a target sorting strategy according to the target condition parameters, so that the sorting efficiency and product quality corresponding to the target sorting task reach the optimal; the target sorting strategy at least includes adjusting the screening particle size and changing the dense medium density.

[0134] In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0135] Acquire target condition parameters corresponding to a target sorting task; the target condition parameters include sorting action parameters of a sorting device, coal quality characteristics of coal to be sorted, and real-time sorting data; the real-time sorting data includes coal flow rate and particle size distribution of the coal to be sorted.

[0136] Determine a target sorting strategy according to the target condition parameters, so that the sorting efficiency and product quality corresponding to the target sorting task reach the optimal; the target sorting strategy at least includes adjusting the screening particle size and changing the dense medium density.

[0137] In an embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the following steps are implemented:

[0138] Obtain the target condition parameters corresponding to the target sorting task; the target condition parameters include the sorting action parameters of the sorting equipment, the coal quality characteristics of the coal to be sorted, and the real-time sorting data; the real-time sorting data includes the coal flow rate and particle size distribution of the coal to be sorted.

[0139] Determine the target sorting strategy according to the target condition parameters so that the sorting efficiency and product quality corresponding to the target sorting task reach the optimum; the target sorting strategy at least includes adjusting the screening particle size and changing the dense medium density.

[0140] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the various embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include Read-Only Memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, Resistive Random Access Memory (ReRAM), Magnetoresistive Random Access Memory (MRAM), Ferroelectric Random Access Memory (FRAM), Phase Change Memory (PCM), graphene memory, etc. Volatile memory can include Random Access Memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), etc. The databases involved in the various embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the various embodiments provided in this application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, Artificial Intelligence (AI) processors, etc., without limitation.

[0141] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this application.

[0142] The above-described embodiments merely represent several implementation manners of this application. The description is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of this application. It should be noted that for those of ordinary skill in the art, without departing from the concept of this application, several modifications and improvements can still be made, and these all belong to the protection scope of this application. Therefore, the protection scope of this application shall be subject to the appended claims.

Claims

1. A method for determining a sorting strategy, characterized in that, The method includes: Obtaining target condition parameters corresponding to a target sorting task; the target condition parameters include sorting action parameters of a sorting device, coal quality characteristics of coal to be sorted, and real-time sorting data; the real-time sorting data includes the coal flow rate and particle size distribution of the coal to be sorted; Determining a simulation sorting strategy corresponding to simulation condition parameters that match the target condition parameters as the target sorting strategy, and the target sorting strategy optimizes the sorting efficiency and product quality corresponding to the target sorting task; the target sorting strategy at least includes adjusting the screening particle size and changing the heavy medium density; Among them, the simulation sorting strategy corresponding to the simulation condition parameters that match the target condition parameters is determined in the following manner: For the simulation condition parameters that match the target condition parameters, adjusting the action space in the Markov model of the sorting process to obtain a candidate sorting strategy corresponding to the simulation condition parameters, so that the sorting efficiency and product quality corresponding to the candidate sorting strategy corresponding to the simulation condition parameters reach the optimal; Simulating the sorting process corresponding to the candidate sorting strategy based on the three-dimensional model of the sorting device to obtain the simulation sorting strategy corresponding to the simulation condition parameters; Among them, the state space of the Markov model includes the simulation condition parameters corresponding to the simulation sorting task and the state parameters of the three-dimensional model; The action space of the Markov model includes adjusting the screening particle size, changing the heavy medium density, and control parameters of the moving parts in the three-dimensional model.

2. The method according to claim 1, characterized in that, Determining the simulation condition parameters that match the target condition parameters includes: Matching the target condition parameters with each simulation condition parameter in the simulation experiment; Obtaining the simulation condition parameters that match the target condition parameters.

3. The method according to claim 2, characterized in that, Constructing the Markov model includes: In the state space of the Markov model, adding a state representation corresponding to the state parameters of the three-dimensional model and a state transition matrix corresponding to the three-dimensional model; Among them, the state representation is used to describe the position, speed, and shape of the sorting device at different times.

4. The method according to claim 2, wherein Constructing the Markov model includes: In the action space of the Markov model, adding control actions corresponding to the control parameters of the moving parts in the three-dimensional model.

5. The method according to claim 2, wherein The simulating the sorting process corresponding to the candidate sorting strategy based on the three-dimensional model of the sorting device to obtain the simulation sorting strategy corresponding to the simulation condition parameters includes: Based on the three-dimensional model of the sorting device, simulating the sorting process corresponding to the candidate sorting strategy to obtain a sorting result; If the result after verification by the expert review model of the sorting result passes the verification, then taking the candidate sorting strategy corresponding to the simulation condition parameters as the simulation sorting strategy corresponding to the simulation condition parameters.

6. The method according to claim 1, characterized in that If the sorting device is a screening machine, the sorting action parameters of the sorting device include the screen hole size and vibration frequency of the screening machine; If the sorting device is a heavy medium sorting machine, the sorting action parameters of the sorting device include the medium density and flow rate of the screening machine.

7. The method according to claim 1, wherein The state parameters of the three-dimensional model include geometric shape parameters, texture coordinate parameters, material property parameters, structural property parameters, and physical property parameters; The geometric shape parameters include the three-dimensional coordinates of each vertex in the three-dimensional model, the lengths or areas of the edges or faces in the model, and the normal directions of the vertices or faces; The material property parameters include color, gloss, reflectivity, and transparency; The structural property parameters include deformation and animation parameters; The physical property parameters include physical and kinetic parameters.

8. The method according to claim 1, wherein Obtaining the coal quality characteristics of the coal to be sorted includes: Based on the coal image of the coal to be sorted and determining the associated equipment corresponding to the coal to be sorted; the associated equipment corresponding to the coal to be sorted includes at least one of a conveyor belt, a crusher, a screening machine, a heavy medium separator, and a flotation machine; Obtaining the equipment operation characteristics of the associated equipment; the equipment operation characteristics of the associated equipment include the equipment sound characteristics and equipment vibration characteristics of the associated equipment; Based on the coal image and the equipment operation characteristics, determining the coal quality characteristics of the coal to be sorted.

9. The method according to claim 8, wherein The determining the coal quality characteristics of the coal to be sorted based on the coal image and the equipment operation characteristics includes: Constructing a three-dimensional coal pile model corresponding to the coal to be sorted; Based on the three-dimensional coal pile model, the coal image, and the equipment operation characteristics, determining the coal quality characteristics of the coal to be sorted.

10. A sorting strategy determination device, characterized in that, The device includes: An acquisition module, configured to acquire target condition parameters corresponding to a target sorting task; the target condition parameters include sorting action parameters of a sorting device, coal quality characteristics of the coal to be sorted, and real-time sorting data; the real-time sorting data includes the coal flow rate and particle size distribution of the coal to be sorted; A strategy determination module, configured to determine a simulation sorting strategy corresponding to the simulation condition parameters that match the target condition parameters as a target sorting strategy, and the target sorting strategy optimizes the sorting efficiency and product quality corresponding to the target sorting task; the target sorting strategy at least includes adjusting the screening particle size and changing the heavy medium density; The simulation sorting strategy corresponding to the simulation condition parameters that match the target condition parameters is determined in the following manner: For the simulation condition parameters that match the target condition parameters, adjusting the action space in the Markov model of the sorting process to obtain a candidate sorting strategy corresponding to the simulation condition parameters, so that the sorting efficiency and product quality corresponding to the candidate sorting strategy corresponding to the simulation condition parameters reach the optimal; Simulating the sorting process corresponding to the candidate sorting strategy based on the three-dimensional model of the sorting device to obtain a simulation sorting strategy corresponding to the simulation condition parameters; Wherein, the state space of the Markov model includes the simulation condition parameters corresponding to the simulation sorting task and the state parameters of the three-dimensional model; The action space of the Markov model includes adjusting the screening particle size, changing the heavy medium density, and control parameters of the moving parts in the three-dimensional model.

Images