Intelligent mineral processing system and method based on digital brain

Abstract

The present invention belongs to the technical field of mineral processing technology and discloses an intelligent mineral processing system and method based on a digital brain; the method comprises: collecting raw ore property data, brain-like auditory data and brain-like sensory data; cleaning and verifying the collected data, and evaluating the data, and when the evaluation is in an abnormal state, issuing a corresponding warning; when the evaluation is in a normal state, constructing a grinding process MPC model, a flotation process MPC model, a classification process MPC model and a dehydration process MPC model based on the MPC model, for dynamic prediction of the mineral processing process; based on the digital brain in combination with each MPC model, outputting an intelligent adjustment strategy for the mineral processing equipment, and intelligently adjusting the mineral processing equipment according to the intelligent adjustment strategy through the brain-like motion device; the present invention continuously optimizes the adjustment strategy of the mineral processing equipment based on the digital brain in combination with multiple MPC models, so that the mineral processing process can always be maintained in the optimal state.

Description

Technical Field

[0001] The present invention relates to the field of mineral processing technology, and more specifically, to an intelligent mineral processing system and method based on a digital brain. Background Art

[0002] Traditional mineral processing lacks effective coordination between various processes. Real-time data exchange and coordinated adjustments are rarely implemented across grinding, flotation, classification, and dewatering. For example, changes in the particle size of the ground ore product make it difficult for the flotation process to detect and adjust accordingly. This results in parameters such as flotation reagent dosage and aeration volume being incompatible with the new grinding product, impacting the stability of the entire mineral processing process and product quality.

[0003] The Chinese patent application with publication number CN115718464A discloses a visual mineral processing production full-process process indicator optimization decision-making system, including a server, and the server is communicatively connected with a data acquisition unit, a mineral processing pre-analysis unit, an equipment process analysis unit, a process process analysis unit, an indicator comprehensive judgment unit, a process optimization verification unit and a display terminal; the invention comprehensively analyzes the status of the mineral processing production process of the visual mineral processing full process through data calibration, union analysis and signal output, and realizes the optimization control of the mineral processing full process by triggering different optimization decision operations, and after completing the optimization operation, uses the data calibration and normalization analysis method to verify and analyze the effect of the optimization operation of the visual mineral processing full-process production process, thereby realizing the optimization control of the process indicators of the mineral processing production full process while saving the economic benefits of visual mineral processing.

[0004] Although the above methods can meet most scenarios, research and practical application of the above methods and existing technologies have revealed that the above methods and existing technologies have at least the following defects:

[0005] There is a lack of a detailed prediction mechanism for the dynamic changes in the mineral processing process; there is a lack of comprehensive consideration of changes in equipment status, fluctuations in the properties of the raw ore, and the complex interactions between various process links; and the monitoring and early warning of potential failures and abnormal conditions during equipment operation are not comprehensive enough.

[0006] In view of this, the present invention proposes an intelligent mineral processing system and method based on a digital brain to solve the above problems. Summary of the Invention

[0007] In order to overcome the above-mentioned defects of the prior art and achieve the above-mentioned purpose, the present invention provides the following technical solution: an intelligent mineral processing method based on a digital brain, comprising the following steps:

[0008] Collecting raw ore property data, brain-like auditory data, and brain-like sensory data; the raw ore property data includes the content of useful minerals in the raw ore, the content of impurity minerals, and the hardness of the raw ore; the brain-like auditory data includes the equipment decibel and vibration frequency; the brain-like sensory data includes the equipment operating temperature, equipment energy consumption, and process parameter data;

[0009] Clean and verify the collected data, and evaluate brain-like auditory data, equipment operating temperature, and equipment energy consumption. When the evaluation is in an abnormal state, issue a corresponding warning;

[0010] When the assessment is in a normal state, the grinding process MPC model, flotation process MPC model, classification process MPC model and dehydration process MPC model are built based on the MPC model to dynamically predict the mineral processing process;

[0011] Based on the digital brain combined with the MPC model of the grinding process, the MPC model of the flotation process, the MPC model of the classification process and the MPC model of the dehydration process, the intelligent adjustment strategy of the mineral processing equipment is output, and the mineral processing equipment is intelligently adjusted according to the intelligent adjustment strategy through the brain-like motion equipment.

[0012] Furthermore, based on the MPC model, an MPC model of the grinding process is established according to the ball mill power, the ball mill reference power, the slurry concentration, the reference slurry concentration, the particle size and the reference particle size;

[0013] Set the prediction time domain and control time domain ,in, ; In each control cycle , according to the current state , using the established grinding process MPC model to predict future In a moment, in a moment Grinding product grade at , ;Construct the grinding process optimization objective function ;

[0014] Solve the objective function through the nature-inspired optimization algorithm to obtain the current grinding control sequence ,in, For control cycle The grinding control quantity at the current moment; so that the objective function minimum, take As the grinding control input at the current moment, it acts on the grinding process and repeats the above process in the next control cycle;

[0015] An MPC model for the flotation process is established based on the flotation agent addition amount, benchmark agent addition amount, flotation machine aeration amount, benchmark aeration amount, grinding product grade and benchmark grinding product grade; an MPC model for the classification process is established based on the benchmark processing capacity; for the dehydration process, an MPC model for the dehydration process is established, and the MPC model for the dehydration process includes a dynamic model for the concentrator process and a dynamic model for the filter process.

[0016] Furthermore, the method for outputting the intelligent adjustment strategy of the mineral processing equipment includes:

[0017] Step 1: Define the state information in the mineral processing process as the state space ;

[0018] Step 2: Define the adjustment action of MPC control parameters as space ,The adjustment actions include the adjustment coefficients of the prediction time domain, the control time domain and the weight matrix;

[0019] Step 3: Preset the prediction time step , initialize various sensors and initialize the state vector is 0;

[0020] Step 4: For each time step , according to the current state vector , iteratively update the state value function through the value iteration algorithm;

[0021] Step 5: Based on the updated state value function, select the state value function The largest action set , as the selected action for the current time step;

[0022] Step 6. Perform the selected action , each beneficiation process updates its state synchronously to obtain the state vector at the next moment ;

[0023] Step 7: Repeat steps 3 to 6 to continuously optimize the intelligent adjustment strategy until the mineral processing process is completed.

[0024] Furthermore, the state space Including the content of useful minerals , impurity mineral content , ore hardness , ball mill power , ball mill temperature , Flotation machine inflation volume ,granularity , slurry concentration , Flotation reagent addition amount , grinding product grade , processing capacity , the current grinding control input , flotation control input at the current moment , the hierarchical control input at the current moment and the current dehydration control input Based on the state space Get the corresponding state vector.

[0025] Furthermore, the action space Motion vectors included Prediction time domain of different mineral processing processes corresponding to grinding process, flotation process, classification process and dewatering process The control time domain and the corresponding adjustment coefficient of the mineral processing process are obtained.

[0026] Furthermore, the state value function is updated according to the reward function value and the maximum state value under the next state vector after the action is performed, which is predicted by the value iteration algorithm.

[0027] Furthermore, the reward function is obtained The methods include:

[0028] Step 4.1: Calculate the concentrate grade improvement bonus based on the target concentrate grade and the current concentrate grade;

[0029] Step 4.2: Calculate the recycling rate improvement reward based on the target recycling rate and the current recycling rate;

[0030] Step 4.3: Calculate the energy consumption reduction reward based on the initial energy consumption and the current energy consumption;

[0031] Step 4.4: Calculate the equipment wear reduction reward based on the initial wear level and current wear level of the equipment;

[0032] Step 4.5: Calculate the reward function based on the sum of the concentrate grade improvement reward, recovery rate improvement reward, energy consumption reduction reward, and equipment wear reduction reward. .

[0033] Furthermore, the method for predicting the maximum state value under the next state vector after executing the action by the value iteration algorithm includes:

[0034] Future output of the grinding process predicted by the grinding process MPC model , the future output of the flotation process predicted by the flotation process MPC model , the future output of the classification process predicted by the classification process MPC model and the future output of the dehydration process predicted by the dehydration process MPC model Get the next state vector, calculate the reward function value corresponding to the next state vector, calculate the corresponding state value function value for each action, and select the largest value among the state value function values ​​as the predicted maximum state value under the next state vector after executing the action.

[0035] Furthermore, the method for verifying the collected data includes:

[0036] Compare the collected data with the preset range threshold. If the collected data is within the preset range threshold, the data is valid. Otherwise, it is marked as abnormal data and re-collected.

[0037] Methods for assessing equipment operating temperature and issuing corresponding warnings include:

[0038] Calculate the rate of change of the device's operating temperature based on the ratio of the device's temperature change value at different time nodes to the time interval;

[0039] The rate of change of the device operating temperature is compared with a preset rate of change threshold. When the rate of change of the device operating temperature exceeds the preset rate of change threshold, a corresponding device operating temperature abnormality warning is issued.

[0040] Furthermore, the method for evaluating the vibration frequency and issuing a corresponding warning includes:

[0041] Compare the device decibel level with the preset device decibel threshold. When the device decibel level exceeds the preset device decibel threshold, the device is judged to be operating abnormally and a corresponding decibel abnormality warning is issued.

[0042] Compare the vibration frequency with the preset vibration frequency threshold. When the vibration frequency is higher than the preset vibration frequency threshold, the device is judged to be operating abnormally and a corresponding vibration frequency abnormality warning is issued;

[0043] Methods for evaluating equipment energy consumption and issuing corresponding warnings include:

[0044] The actual energy consumption value is obtained by accumulating the real-time power of the device within the preset time, and the actual energy consumption value is compared with the preset energy consumption threshold. When the actual energy consumption value is higher than the preset energy consumption threshold, the device energy consumption is judged to be abnormal and an abnormal energy consumption warning is issued; otherwise, the device is judged to be operating normally.

[0045] The intelligent mineral processing system based on digital brain implements the intelligent mineral processing method based on digital brain, including:

[0046] Data acquisition module: collects raw ore property data, brain-like auditory data, and brain-like sensory data; the raw ore property data includes the content of useful minerals in the raw ore, the content of impurity minerals, and the hardness of the raw ore; the brain-like auditory data includes the equipment decibel and vibration frequency; the brain-like sensory data includes equipment operating temperature, equipment energy consumption, and process parameter data;

[0047] Data evaluation module: Cleans and verifies the collected data, and evaluates brain-like auditory data, equipment operating temperature, and equipment energy consumption. When the evaluation is in an abnormal state, it issues a corresponding warning;

[0048] Dynamic prediction module: When the evaluation is in a normal state, the grinding process MPC model, flotation process MPC model, classification process MPC model and dehydration process MPC model are built based on the MPC model to dynamically predict the mineral processing process;

[0049] Intelligent mineral processing module: Based on the digital brain combined with the MPC model of the grinding process, the MPC model of the flotation process, the MPC model of the classification process and the MPC model of the dehydration process, it outputs the intelligent adjustment strategy of the mineral processing equipment, and uses the brain-like motion equipment to intelligently adjust the mineral processing equipment according to the intelligent adjustment strategy.

[0050] The technical effects and advantages of the intelligent mineral processing system and method based on digital brain of the present invention are as follows:

[0051] The present invention collects data on the properties of the raw ore and can formulate accurate mineral processing strategies based on the specific characteristics of the raw ore, which helps to improve the grade and recovery rate of the concentrate and enhance the quality of mineral processing products. It collects brain-like auditory data and brain-like sensory data, and performs corresponding processing and evaluation and early warning, providing comprehensive guarantees for the reliable operation of the equipment. It also uses the MPC model of the grinding, flotation, classification and dehydration processes for dynamic prediction, realizing the coordinated optimization of all links in mineral processing. It can effectively reduce the mismatch between the various links and improve the quality of mineral processing products. Based on the digital brain combined with multiple MPC models, it continuously optimizes the adjustment strategy of mineral processing equipment, so that the mineral processing process can always operate in a near-optimal state, stabilizing and improving the quality of mineral processing products. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 This is a flow chart of the intelligent mineral processing method based on digital brain of the present invention;

[0053] Figure 2 This is a schematic diagram of the method flow of the intelligent adjustment strategy of the output mineral processing equipment of the present invention;

[0054] Figure 3 Schematic diagram of the method for obtaining a reward function according to the present invention;

[0055] Figure 4This is a structural diagram of the intelligent mineral processing system based on digital brain of the present invention. DETAILED DESCRIPTION

[0056] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0057] Example 1

[0058] See also Figure 1 As shown, the intelligent mineral processing method based on the digital brain provided in this embodiment includes the following steps:

[0059] Collect raw ore property data, brain-like auditory data, and brain-like sensory data;

[0060] The raw ore property data includes the content of useful minerals in the raw ore, the content of impurity minerals and the hardness of the raw ore; it is obtained by testing the collected raw ore. The collected raw ore property data can provide a reference standard for the equipment to automatically adjust the operating status, so that the equipment can operate in the best state and improve the mineral processing efficiency and quality.

[0061] Brain-like auditory data includes equipment decibels and vibration frequencies, which are collected through brain-like auditory devices; brain-like auditory devices include shock wave detection equipment and vibration detection equipment, etc.; collecting brain-like auditory data can provide real-time feedback on the equipment's operating status, improve the optimization efficiency of subsequent mineral processing equipment, and ensure the stability of the mineral processing process, thereby improving the quality of mineral processing products.

[0062] Brain-like sensory data include equipment operating temperature, equipment energy consumption and process parameter data; process parameter data include ball mill benchmark power, ball mill power, benchmark slurry concentration, slurry concentration, benchmark particle size, particle size, benchmark reagent addition amount, flotation reagent addition amount, benchmark aeration amount, flotation machine aeration amount, benchmark grinding product grade, grinding product grade (indicating the useful components in the grinding product, that is, the content of target minerals), benchmark processing volume and processing volume; equipment operating temperature data can monitor the working status of the equipment, ensure the efficient operation of the equipment, and improve mineral processing efficiency; equipment energy consumption can intuitively reflect the energy utilization of the equipment, so that when the equipment is optimized and adjusted in the later stage, it can not only ensure the mineral processing effect, but also reduce energy consumption and improve energy utilization efficiency; thereby reducing mineral processing costs and improving mineral processing benefits; process parameter data directly affects the operating effect of mineral processing equipment, and the equipment operating parameters can be accurately adjusted according to the process parameters in the later stage; ultimately improving the overall quality of mineral processing products.

[0063] The collected data is cleaned and verified, and the brain-like auditory data and equipment operating temperature are evaluated. When the evaluation is in an abnormal state, a corresponding warning is issued. Data cleaning can remove outliers and erroneous data. Data verification can ensure that the data conforms to the physical laws and actual conditions of the mineral processing process. The cleaned and verified data can serve as the basis for the intelligent mineral processing system to make accurate decisions and ensure that the ideal mineral processing requirements are met. Equipment operating temperature is one of the key indicators reflecting the equipment's operating status. Calculating the rate of change of the equipment's operating temperature can detect potential equipment failures in advance, prevent the equipment from operating at excessive temperatures, extend the equipment's service life, and ensure the stability of the mineral processing process. Different equipment operating states and parameter settings will result in different sound characteristics. Evaluating brain-like auditory data can help optimize equipment performance and reduce the impact of equipment failures on mineral processing production.

[0064] By evaluating the energy consumption of the equipment, the energy consumption of the equipment can be monitored in real time, so that the mineral processing cost can be reduced through manual adjustment.

[0065] Methods for verifying the collected data include:

[0066] The collected data is compared with the preset range threshold. If the collected data is within the preset range threshold, the data is valid. Otherwise, it is marked as abnormal data and re-collected.

[0067] Methods for assessing equipment operating temperature and issuing corresponding warnings include:

[0068] The rate of change of the device's operating temperature is calculated based on the ratio of the device's temperature change value at different time nodes to the time interval. The specific calculation formula is:

[0069] ;

[0070] in, is the rate of change of the equipment operating temperature; Time node The operating temperature of the equipment; Time node The operating temperature of the equipment; Time node and time nodes time interval;

[0071] The rate of change of the device operating temperature is compared with a preset rate of change threshold. When the rate of change of the device operating temperature exceeds the preset rate of change threshold, a corresponding device operating temperature abnormality warning is issued.

[0072] Methods for assessing vibration frequency and issuing corresponding warnings include:

[0073] Compare the device decibel level with the preset device decibel threshold. When the device decibel level exceeds the preset device decibel threshold, the device is judged to be operating abnormally and a corresponding decibel abnormality warning is issued.

[0074] The vibration frequency is compared with the preset vibration frequency threshold. When the vibration frequency is higher than the preset vibration frequency threshold, the equipment is judged to be operating abnormally and a corresponding vibration frequency abnormality warning is issued.

[0075] Methods for evaluating equipment energy consumption and issuing corresponding warnings include:

[0076] The actual energy consumption value is obtained by accumulating the real-time power of the device within the preset time, and the actual energy consumption value is compared with the preset energy consumption threshold. When the actual energy consumption value is higher than the preset energy consumption threshold, the device energy consumption is judged to be abnormal and an abnormal energy consumption warning is issued; otherwise, the device is judged to be operating normally.

[0077] When the assessment is in a normal state, the grinding process MPC model, flotation process MPC model, classification process MPC model and dehydration process MPC model are built based on the MPC model to dynamically predict the mineral processing process;

[0078] The MPC model of the grinding process is established based on the MPC model as follows:

[0079] ;

[0080] in, The grade of the grinding product; is the grinding rate constant; is the ball mill power; is the base power of the ball mill; is the slurry concentration; is the baseline slurry concentration; is the particle size; is the benchmark particle size;

[0081] Set the prediction time domain and control time domain ,in, ; In each control cycle , according to the current state , using the established grinding process MPC model to predict future In a moment, in a moment Grinding product grade at ;

[0082] Constructing the grinding process optimization objective function :

[0083] ;

[0084] in, For the moment Reference trajectory of grinding product grade at the time of and is the weight matrix used to weigh the tracking error and control action changes, The amount of change in the grinding control input; is the norm;

[0085] Solve the objective function through the nature-inspired optimization algorithm to obtain the current grinding control sequence ,in, For control cycle The grinding control quantity at the current moment; so that the objective function minimum, take As the grinding control input at the current moment, it acts on the grinding process and repeats the above process in the next control cycle;

[0086] An MPC model for the flotation process is established based on the flotation agent addition amount, benchmark agent addition amount, flotation machine aeration amount, benchmark aeration amount, grinding product grade and benchmark grinding product grade; an MPC model for the classification process is established based on the benchmark processing capacity; for the dehydration process, an MPC model for the dehydration process is established, and the MPC model for the dehydration process includes a dynamic model for the concentrator process and a dynamic model for the filter process.

[0087] Based on the digital brain combined with the MPC model of the grinding process, the MPC model of the flotation process, the MPC model of the classification process and the MPC model of the dehydration process, the intelligent adjustment strategy of the mineral processing equipment is output, and the mineral processing equipment is intelligently adjusted according to the intelligent adjustment strategy through the brain-like motion equipment.

[0088] Methods for solving the objective function through nature-inspired optimization algorithms include:

[0089] The nature-inspired optimization algorithm can use optimization algorithms such as particle swarm optimization algorithm or genetic algorithm. Taking particle swarm optimization algorithm as an example:

[0090] Initialize particle swarm parameters: population size , particle dimensions , maximum number of iterations , termination threshold , inertia weight, learning factor;

[0091] Initialize the initial state:

[0092] Current control cycle , current status ( The power of ball mill, is the slurry concentration, is the particle size); particles The particle position ,in, For particles In the control cycle The grinding control quantity at the current moment; For particles In the control cycle The grinding control amount at the current moment; randomly generated within the allowed control range; particles Particle speed Initialize to 0 or a random smaller value;

[0093] For each particle , input control sequence To the grinding process MPC model, predict the future Grinding product grade at each moment ; Substitute into the objective function to calculate the fitness value ; Taking minimizing fitness value as the objective function;

[0094] Record the position corresponding to the particle's own historical best fitness and the position corresponding to the current best fitness of all particles; update the particle speed and position according to the iterative formula of position and speed of the particle swarm optimization algorithm;

[0095] If the number of iterations reaches Or the change in fitness value is less than the termination threshold , terminate the iteration; otherwise return to the step of calculating the fitness value; select the first element of the global optimal position As the control input at the current moment, it acts on the grinding equipment (such as adjusting the power of the ball mill).

[0096] Reference Figure 2 , the method for outputting the intelligent adjustment strategy of the mineral processing equipment includes:

[0097] Step 1: Define the state information in the mineral processing process as the state space ; State space Including the content of useful minerals , impurity mineral content , ore hardness , ball mill power , ball mill temperature , Flotation machine inflation volume ,granularity , slurry concentration , Flotation agent addition amount , grinding product grade , processing capacity , the current grinding control input , flotation control input at the current moment , the hierarchical control input at the current moment and the current dehydration control input ; Get the state vector included in the state space as follows:

[0098] .

[0099] Step 2: Define the adjustment action of MPC control parameters as space , the adjustment action includes the adjustment coefficients of the prediction time domain, the control time domain and the weight matrix; the action space Motion vectors included The details are as follows:

[0100] ;

[0101] in, For the Prediction time domain of a mineral processing process; For the Control time domain of each mineral processing process; For the The first adjustment coefficient of the weight matrix of each beneficiation process; For the The second adjustment coefficient of the weight matrix of each beneficiation process; Index for the mineral processing process, They correspond to the grinding process, flotation process, classification process and dehydration process respectively.

[0102] Step 3: Preset the prediction time step , initialize various sensors and initialize the state vector is 0;

[0103] Step 4: For each time step , according to the current state vector , iteratively update the state value function through the value iteration algorithm;

[0104] The state value function is updated based on the reward function value and the maximum state value under the next state vector after the action is executed, as predicted by the value iteration algorithm. The update formula of the state value function is as follows:

[0105] ;

[0106] in, is the time step The state value of is the time step The reward function value of is the discount factor, which indicates the importance of future rewards; For the next time step The predicted state vector of It is the maximum state value under the next state vector after executing the action predicted by the value iteration algorithm.

[0107] Reference Figure 3 , obtain the reward function The methods include:

[0108] Step 4.1: Calculate the Concentrate Grade Improvement Reward , assuming the target concentrate grade is The current concentrate grade is ,but: ;in, is the concentrate grade bonus coefficient, when hour, ,otherwise ;

[0109] Step 4.2: Calculate the reward for improving the recovery rate , the target recovery rate is The current recovery rate is ,but: ;in, is the recovery rate bonus coefficient, when hour, ,otherwise ;

[0110] Step 4.3: Calculate the energy consumption reduction reward , assuming the initial energy consumption , the current energy consumption is ,but: ;in, is the energy consumption bonus coefficient, when hour, ,otherwise ;

[0111] Step 4.4: Calculate Equipment Wear Reduction Rewards , equipment wear degree and equipment running time and equipment load The wear degree function is: ;in, The current wear level of the equipment; is the wear coefficient. By adjusting the action, the wear of the equipment is reduced; the equipment wear reduction reward is obtained. : ;in, is the equipment wear bonus coefficient; is the initial wear degree;

[0112] Step 4.5: Rewards based on concentrate grade , rewards for increased recovery rates , Energy consumption reduction rewards and equipment wear reduction bonus Calculating the reward function ;

[0113] Calculating the reward function The methods include: .

[0114] Methods for predicting the maximum state value under the next state vector after executing an action through value iteration algorithms include:

[0115] Future output of the grinding process predicted by the grinding process MPC model , the future output of the flotation process predicted by the flotation process MPC model , the future output of the classification process predicted by the classification process MPC model and the future output of the dehydration process predicted by the dehydration process MPC model Get the next state vector, calculate the reward function value corresponding to the next state vector, calculate the corresponding state value function value for each action, and select the largest value among the state value function values ​​corresponding to all actions as the predicted maximum state value under the next state vector after executing the action.

[0116] Step 5: Based on the updated state value function, select the state value function The largest action set , as the selected action for the current time step;

[0117] Step 6. Perform the selected action , each beneficiation process updates its state synchronously to obtain the state vector at the next moment ;

[0118] Step 7: Repeat steps 3 to 6 to continuously optimize the intelligent adjustment strategy until the mineral processing process is completed.

[0119] By continuously repeating the above process, the optimal decision-making strategy can be gradually learned, enabling the digital brain to make the optimal action decisions based on the real-time status of the mineral processing process and control brain-like motion equipment to perform actions; brain-like motion equipment includes electric valves, frequency converters, intelligent equipment, cloud robots and production equipment, etc.

[0120] Example 2

[0121] See also Figure 4 As shown, the intelligent mineral processing system based on the digital brain provided in this embodiment includes:

[0122] Data acquisition module: collects raw ore property data, brain-like auditory data, and brain-like sensory data; the raw ore property data includes the content of useful minerals in the raw ore, the content of impurity minerals, and the hardness of the raw ore; the brain-like auditory data includes the equipment decibel and vibration frequency; the brain-like sensory data includes equipment operating temperature, equipment energy consumption, and process parameter data;

[0123] Data evaluation module: Cleans and verifies the collected data, and evaluates brain-like auditory data, equipment operating temperature, and equipment energy consumption. When the evaluation is in an abnormal state, it issues a corresponding warning;

[0124] Dynamic prediction module: When the evaluation is in a normal state, the grinding process MPC model, flotation process MPC model, classification process MPC model and dehydration process MPC model are built based on the MPC model to dynamically predict the mineral processing process;

[0125] Intelligent mineral processing module: Based on the digital brain combined with the MPC model of the grinding process, the MPC model of the flotation process, the MPC model of the classification process and the MPC model of the dehydration process, it outputs the intelligent adjustment strategy of the mineral processing equipment, and uses the brain-like motion equipment to intelligently adjust the mineral processing equipment according to the intelligent adjustment strategy.

[0126] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

[0127] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. An intelligent mineral processing method based on digital brain, characterized in that: The steps include: Collecting raw ore property data, brain-like auditory data, and brain-like sensory data; the raw ore property data includes the content of useful minerals in the raw ore, the content of impurity minerals, and the hardness of the raw ore; the brain-like auditory data includes the equipment decibel and vibration frequency; the brain-like sensory data includes the equipment operating temperature, equipment energy consumption, and process parameter data; Clean and verify the collected data, and evaluate brain-like auditory data, equipment operating temperature, and equipment energy consumption. When the evaluation is in an abnormal state, issue a corresponding warning; When the assessment is in a normal state, the grinding process MPC model, the flotation process MPC model, the classification process MPC model and the dehydration process MPC model are constructed based on the MPC model to dynamically predict the mineral processing process; wherein, the grinding process MPC model is established according to the ball mill power, the ball mill benchmark power, the pulp concentration, the benchmark pulp concentration, the particle size and the benchmark particle size; the flotation process MPC model is established based on the flotation reagent addition amount, the benchmark reagent addition amount, the flotation machine aeration amount, the benchmark aeration amount, the grinding product grade and the benchmark grinding product grade; the classification process MPC model is established based on the benchmark processing amount; for the dehydration process, the dehydration process MPC model is established, and the dehydration process MPC model includes a concentration process dynamic model for the concentrator and a filtration process dynamic model for the filter; Based on the digital brain, combined with the MPC models of the grinding process, flotation process, classification process, and dehydration process, the intelligent adjustment strategy of the mineral processing equipment is output, and the selected action, that is, the adjustment action of the MPC control parameters, is obtained. The mineral processing equipment is intelligently adjusted according to the intelligent adjustment strategy through the brain-like motion device; The method for outputting the intelligent adjustment strategy of the mineral processing equipment includes: Step 1: Define the state information in the mineral processing process as the state space The state space Including the content of useful minerals , impurity mineral content , ore hardness , ball mill power , ball mill temperature , Flotation machine inflation volume ,granularity , slurry concentration , Flotation reagent addition amount , grinding product grade , processing capacity , the current grinding control input , flotation control input at the current moment , the hierarchical control input at the current moment and the current dehydration control input Based on the state space Get the corresponding state vector ; Step 2: Define the adjustment action of MPC control parameters as space ,The adjustment actions include the adjustment coefficients of the prediction time domain, the control time domain and the weight matrix; Step 3: Preset the prediction time step , initialize various sensors and initialize the state vector is 0; Step 4: For each time step , according to the current state vector , iteratively update the state value function through the value iteration algorithm; Step 5: Based on the updated state value function, select the state value function The largest action set , as the selected action for the current time step; Step 6. Perform the selected action , each beneficiation process updates its state synchronously to obtain the state vector at the next moment ; Step 7: Repeat steps 3 to 6 to continuously optimize the intelligent adjustment strategy until the mineral processing process is completed.

2. The intelligent mineral processing method based on digital brain according to claim 1 is characterized in that: Based on the MPC model; Set the prediction time domain and control time domain in, ; In each control cycle , according to the current state , using the established grinding process MPC model to predict future In a moment, in a moment Grinding product grade at ;Construct the grinding process optimization objective function ; Solve the objective function through the nature-inspired optimization algorithm to obtain the current grinding control sequence ,in, For control cycle The grinding control quantity at the current moment; so that the objective function minimum, take As the grinding control input at the current moment, it acts on the grinding process and repeats the above process in the next control cycle.

3. The intelligent mineral processing method based on digital brain according to claim 1 is characterized in that: The action space Motion vectors included It is obtained according to the prediction time domain, control time domain and adjustment coefficient corresponding to different mineral processing processes of grinding process, flotation process, classification process and dehydration process.

4. The intelligent mineral processing method based on digital brain according to claim 1 is characterized in that: The state-value function is updated according to the reward function value and the maximum state value under the next state vector after the action is performed, which is predicted by the value iteration algorithm.

5. The intelligent mineral processing method based on digital brain according to claim 4 is characterized in that: Get the reward function The methods include: Step 4.1: Calculate the concentrate grade improvement bonus based on the target concentrate grade and the current concentrate grade; Step 4.2: Calculate the recycling rate improvement reward based on the target recycling rate and the current recycling rate; Step 4.3: Calculate the energy consumption reduction reward based on the initial energy consumption and the current energy consumption; Step 4.4: Calculate the equipment wear reduction reward based on the initial wear level and current wear level of the equipment; Step 4.5: Calculate the reward function based on the sum of the concentrate grade improvement reward, recovery rate improvement reward, energy consumption reduction reward, and equipment wear reduction reward. .

6. The intelligent mineral processing method based on digital brain according to claim 5 is characterized in that: The method for predicting the maximum state value under the next state vector after executing the action by the value iteration algorithm includes: Future output of the grinding process predicted by the grinding process MPC model , the future output of the flotation process predicted by the flotation process MPC model , the future output of the classification process predicted by the classification process MPC model and the future output of the dehydration process predicted by the dehydration process MPC model Get the next state vector, calculate the reward function value corresponding to the next state vector, calculate the corresponding state value function value for each action, and select the largest value among the state value function values ​​as the predicted maximum state value under the next state vector after executing the action.

7. The intelligent mineral processing method based on digital brain according to claim 1 is characterized in that: The method for verifying the collected data includes: Compare the collected data with the preset range threshold. If the collected data is within the preset range threshold, the data is valid. Otherwise, it is marked as abnormal data and re-collected. Methods for assessing equipment operating temperature and issuing corresponding warnings include: Calculate the rate of change of the device's operating temperature based on the ratio of the device's temperature change value at different time nodes to the time interval; The rate of change of the device operating temperature is compared with a preset rate of change threshold. When the rate of change of the device operating temperature exceeds the preset rate of change threshold, a corresponding device operating temperature abnormality warning is issued.

8. The intelligent mineral processing method based on digital brain according to claim 1 is characterized in that: Methods for evaluating the vibration frequency and issuing corresponding warnings include: Compare the device decibel level with the preset device decibel threshold. When the device decibel level exceeds the preset device decibel threshold, the device is judged to be operating abnormally and a corresponding decibel abnormality warning is issued. Compare the vibration frequency with the preset vibration frequency threshold. When the vibration frequency is higher than the preset vibration frequency threshold, the device is judged to be operating abnormally and a corresponding vibration frequency abnormality warning is issued; Methods for evaluating equipment energy consumption and issuing corresponding warnings include: The actual energy consumption value is obtained by accumulating the real-time power of the device within the preset time, and the actual energy consumption value is compared with the preset energy consumption threshold. When the actual energy consumption value is higher than the preset energy consumption threshold, the device energy consumption is judged to be abnormal and an abnormal energy consumption warning is issued; otherwise, the device is judged to be operating normally.

9. An intelligent mineral processing system based on a digital brain, implementing the intelligent mineral processing method based on a digital brain according to any one of claims 1 to 8, characterized in that: include: Data acquisition module: collects raw ore property data, brain-like auditory data, and brain-like sensory data; the raw ore property data includes the content of useful minerals in the raw ore, the content of impurity minerals, and the hardness of the raw ore; the brain-like auditory data includes the equipment decibel and vibration frequency; the brain-like sensory data includes equipment operating temperature, equipment energy consumption, and process parameter data; Data evaluation module: Cleans and verifies the collected data, and evaluates brain-like auditory data, equipment operating temperature, and equipment energy consumption. When the evaluation is in an abnormal state, it issues a corresponding warning; Dynamic prediction module: When the assessment is in a normal state, the grinding process MPC model, flotation process MPC model, classification process MPC model and dehydration process MPC model are built based on the MPC model to dynamically predict the mineral processing process; among them, the flotation process MPC model is established based on the flotation reagent addition amount, the benchmark reagent addition amount, the flotation machine aeration volume, the benchmark aeration volume, the grinding product grade and the benchmark grinding product grade; the classification process MPC model is established based on the benchmark processing volume; For the dehydration process, a dehydration process MPC model is established. The dehydration process MPC model includes a concentration process dynamic model for the concentrator and a filtration process dynamic model for the filter. Intelligent mineral processing module: Based on the digital brain and combined with the MPC model of the grinding process, the MPC model of the flotation process, the MPC model of the classification process and the MPC model of the dehydration process, it outputs the intelligent adjustment strategy of the mineral processing equipment, obtains the selected action, that is, the adjustment action of the MPC control parameters, and uses the brain-like motion device to intelligently adjust the mineral processing equipment according to the intelligent adjustment strategy.

Images