Steel ball supplementing control method, device and equipment of semi-autogenous mill and storage medium

Abstract

The invention provides a steel ball supplementing control method, device and equipment of a semi-autogenous mill and a storage medium, and relates to the technical field of mineral processing, the method comprises the following steps: obtaining production data of the semi-autogenous mill, and constructing a production database according to the production data; constructing a digital platform according to the production database in combination with a beneficiation knowledge base and an expert system; according to the ore parameters, the steel ball parameters and the operation parameters of the semi-autogenous mill, a steel ball abrasion dynamic model is built; calculating steel ball supplementing parameters of the semi-autogenous mill according to the digital platform steel ball wear dynamic model; constructing a digital twinborn prediction system according to the production data, and adjusting steel ball supplementing parameters by using the digital twinborn prediction system to obtain a steel ball supplementing strategy; and according to the steel ball supplementing strategy, the intelligent ball adding machine is controlled to supplement the steel balls to the semi-autogenous mill. Key parameters of the semi-autogenous mill can be obtained in real time, the number and the period of supplemented balls are dynamically adjusted, and it is ensured that equipment is always in the optimal working state.

Description

Technical Field

[0001] The present invention relates to the technical field of mineral processing, and particularly to a steel ball supplementary addition control method, device, equipment and storage medium for a semi-autogenous mill. Background Art

[0002] The semi-autogenous mill crushes ore through the collision and friction between the ore and steel balls. Compared with the traditional ball mill, it reduces the consumption of steel balls, thereby reducing wear and energy consumption. The semi-autogenous mill is widely used in industries such as metallurgy, petrochemical, and coal. Steel balls are used as auxiliary grinding media in the semi-autogenous mill and gradually decrease with the wear of the ore. Supplementary addition of balls can ensure the stability of the quantity and particle size grading of steel balls in the mill, and prevent the mill from losing its crushing ability due to ore accumulation.

[0003] The traditional method for supplementary addition of balls in a semi-autogenous mill mainly relies on empirical formulas (such as the tonnage consumption method) to set the supplementary addition amount. This timed, quantitative, and graded supplementary addition strategy does not consider the dynamic characteristics of steel ball wear and cannot be adjusted in a timely manner according to changes in ore properties. When the ore is soft, the single consumption of steel balls will increase, resulting in waste and over-grinding of the product. When the ore is hard, if the quantity of steel balls is too small, it cannot work effectively, resulting in under-grinding of the product and insufficient monomer dissociation. At the same time, the single-parameter supplementary addition control based on current or power often requires manual monitoring of parameter changes such as current or power, and cannot adjust the working state of the semi-autogenous mill in a timely manner. Therefore, it is urgent to solve the problem that the supplementary addition of balls in the semi-autogenous mill cannot adapt to the fluctuations in ore hardness and the wear characteristics of steel balls in real time, resulting in poor grinding efficiency and stability. Summary of the Invention

[0004] In view of the above deficiencies of the prior art, the present invention provides a steel ball supplementary addition control method, device, equipment and storage medium for a semi-autogenous mill, which effectively solves the problem that the supplementary addition of balls in the current semi-autogenous mill cannot adapt to the fluctuations in ore hardness and the wear characteristics of steel balls in real time, resulting in poor grinding efficiency and stability.

[0005] In a first aspect, the present invention provides a steel ball supplementary addition control method for a semi-autogenous mill, the method comprising:

[0006] Obtain the production data of the semi-autogenous mill, and construct a production database according to the production data;

[0007] Construct a digital platform according to the production database in combination with a mineral processing knowledge base and an expert system, the mineral processing knowledge base is used to provide professional knowledge in the mineral processing process, and the expert system is used to make a decision on steel ball supplementary addition according to the professional knowledge and the production data;

[0008] Construct a steel ball wear kinetics model according to ore parameters, steel ball parameters and the operating parameters of the semi-autogenous mill;

[0009] Calculate the steel ball replenishment parameters of the semi-autogenous mill according to the digital platform and the steel ball wear dynamics model;

[0010] Construct a digital twin prediction system based on the production data, and use the digital twin prediction system to adjust the steel ball replenishment parameters to obtain a steel ball replenishment strategy;

[0011] Control the intelligent ball adding machine to replenish steel balls to the semi-autogenous mill according to the steel ball replenishment strategy.

[0012] In an alternative embodiment, constructing the digital platform by combining the production database with the ore dressing knowledge base and the expert system includes:

[0013] Obtain the production data of the production database, and extract feature data according to the production data;

[0014] Construct a recursive neural network model, and perform predictive analysis on the feature data according to the recursive neural network model to obtain feature parameters;

[0015] Construct an ore dressing knowledge base, and set the parameter matching rules and parameter matching ranges of the ore dressing knowledge base;

[0016] Construct an expert system, and use the expert system to make steel ball replenishment decisions according to the feature parameters, the parameter matching rules, and the parameter matching ranges.

[0017] In an alternative embodiment, the formula of the steel ball wear dynamics model is as follows:

[0018]

[0019] In the above formula, W represents the wear amount of the steel ball, K represents the wear coefficient, D represents the diameter of the steel ball, t represents the running time of the semi-autogenous mill, ρ represents the ore density, H represents the ore hardness, and E represents the impact energy of the semi-autogenous mill.

[0020] In an alternative embodiment, calculating the steel ball replenishment parameters of the semi-autogenous mill according to the digital platform and the steel ball wear dynamics model includes:

[0021] Obtain the real-time production data sequence of the semi-autogenous mill;

[0022] Perform prediction on the real-time production data sequence according to the recursive neural network model and the steel ball wear dynamics model to obtain prediction parameters;

[0023] The expert system determines the steel ball replenishment parameters according to the prediction parameters.

[0024] In an alternative embodiment, constructing the digital twin prediction system based on the production data, and adjusting the steel ball addition parameters by using the digital twin prediction system to obtain a steel ball addition strategy, includes:

[0025] Obtain the production data for data processing and analysis to obtain a production data set;

[0026] Construct a model based on the production data set to obtain the digital twin prediction system, where the digital twin prediction system includes a discrete element prediction model and a long short-term memory network model;

[0027] The discrete element prediction model predicts the working state of the semi-autogenous mill after a first time threshold based on real-time production data to obtain a predicted working state;

[0028] The long short-term memory network model adjusts the steel ball addition parameters according to the predicted working state to obtain the steel ball addition strategy.

[0029] In an alternative embodiment, after controlling the intelligent ball adding machine to add steel balls to the semi-autogenous mill according to the steel ball addition strategy, it further includes:

[0030] After a second time threshold delay after the steel ball addition, obtain the real-time production data of the semi-autogenous mill;

[0031] The digital twin prediction system performs data comparison based on the real-time production data to obtain the operation parameter indicators of the semi-autogenous mill;

[0032] Optimize the digital platform, the steel ball wear kinetics model, and the digital twin prediction system according to the operation parameter indicators.

[0033] In an alternative embodiment, the production data at least includes an operating audio signal, an operating vibration frequency signal, an operating current signal, a temperature field distribution signal of the cylinder body, and a bearing pressure signal of the support point.

[0034] In a second aspect, the present invention provides a steel ball addition control device for a semi-autogenous mill, and the device includes:

[0035] A data acquisition module, configured to acquire the production data of the semi-autogenous mill and construct a production database according to the production data;

[0036] A platform construction module, configured to construct a digital platform according to the production database in combination with a beneficiation knowledge base and an expert system, where the beneficiation knowledge base is used to provide professional knowledge in the beneficiation process, and the expert system is used to make a steel ball addition decision according to the professional knowledge and the production data;

[0037] A model construction module for constructing a steel ball wear dynamics model based on ore parameters, steel ball parameters, and the operating parameters of the semi-autogenous mill;

[0038] A parameter calculation module for calculating the steel ball replenishment parameters of the semi-autogenous mill according to the digital platform and the steel ball wear dynamics model;

[0039] A strategy generation module for constructing a digital twin prediction system based on the production data, adjusting the steel ball replenishment parameters using the digital twin prediction system, and obtaining a steel ball replenishment strategy;

[0040] A steel ball replenishment module for controlling an intelligent ball adding machine to replenish steel balls to the semi-autogenous mill according to the steel ball replenishment strategy.

[0041] In a third aspect, the present invention provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. The processor executes the computer program to implement the steel ball replenishment control method for the semi-autogenous mill as described in the first aspect of the present invention.

[0042] In a fourth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the steel ball replenishment control method for the semi-autogenous mill as described in the first aspect of the present invention.

[0043] The steel ball replenishment control method, device, equipment, and storage medium provided by the present invention can obtain the key parameters of the semi-autogenous mill in real time and dynamically adjust the replenishment ball quantity and cycle, ensuring that the equipment is always in the best working state, thereby significantly improving the throughput, reducing the downtime, and meeting the large-scale production requirements. By precisely controlling the equipment working parameters, the energy consumption is effectively reduced, unnecessary energy waste is avoided. By calculating the optimal replenishment ball quantity in real time, the steel ball consumption is reduced, the service life is extended, and the operation cost is further reduced. At the same time, decisions are made based on real-time production data and algorithm models, reducing manual intervention, improving the decision-making efficiency, and being able to continuously update the algorithm model according to new data, enhancing the robustness and flexibility of the device, providing strong support for the sustainable development and environmental protection production of enterprises. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for use in the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and thus should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0045] Figure 1It is the first schematic diagram of the steel ball supplementary addition control method for the semi-autogenous mill provided by the embodiment of the present invention;

[0046] Figure 2 It is the schematic diagram of the architecture of the steel ball supplementary addition system for the semi-autogenous mill in the embodiment of the present invention;

[0047] Figure 3 It is the second schematic diagram of the steel ball supplementary addition control method for the semi-autogenous mill provided by the embodiment of the present invention;

[0048] Figure 4 It is the third schematic diagram of the steel ball supplementary addition control method for the semi-autogenous mill provided by the embodiment of the present invention;

[0049] Figure 5 It is the fourth schematic diagram of the steel ball supplementary addition control method for the semi-autogenous mill provided by the embodiment of the present invention;

[0050] Figure 6 It is the schematic diagram of the structure of the steel ball supplementary addition control device for the semi-autogenous mill provided by the embodiment of the present invention;

[0051] Figure 7 It is the schematic diagram of the structure of an electronic device provided by the embodiment of the present invention.

[0052] Main element symbol description:

[0053] 600, steel ball supplementary addition control device for the semi-autogenous mill; 610, data acquisition module; 620, platform construction module; 630, model construction module; 640, parameter calculation module; 650, strategy generation module; 660, steel ball supplementary addition module; 700, electronic device; 710, processor; 720, communication interface; 730, memory; 740, communication bus. Detailed implementation manners

[0054] To make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be further described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention. It should be noted that the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0055] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present invention, "a plurality" means two or more unless otherwise specifically defined.

[0056] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this application belongs. The terms used in the specification of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0057] The traditional method of adding balls to semi-autogenous mills mainly relies on empirical formulas (such as tonnage consumption method) to set the addition amount. This timed, quantitative, and graded ball addition strategy does not consider the dynamic characteristics of ball wear and cannot adjust in a timely manner according to changes in ore properties. When the ore is soft, the single consumption of balls will increase, resulting in waste and over-grinding of products. When the ore is hard, if the number of balls is too small, it cannot work effectively, resulting in under-grinding of products and insufficient monomer dissociation. At the same time, the single-parameter addition control based on current or power often requires manual monitoring of changes in parameters such as current or power, and cannot adjust the working state of the semi-autogenous mill in a timely manner. Therefore, it is urgent to solve the problem that the ball addition of semi-autogenous mills cannot adapt to the fluctuations in ore hardness and the characteristics of ball wear in real time, resulting in poor grinding efficiency and stability.

[0058] Example 1

[0059] The embodiment of the present invention provides a method for controlling the addition of balls to a semi-autogenous mill, which effectively solves the problem that the ball addition of the current semi-autogenous mill cannot adapt to the fluctuations in ore hardness and the characteristics of ball wear in real time, resulting in poor grinding efficiency and stability. Figure 1 It is the first schematic diagram of the process of the method for controlling the addition of balls to a semi-autogenous mill provided by the embodiment of the present invention. As Figure 1 shown, the method includes the following steps:

[0060] S100. Obtain the production data of the semi-autogenous mill and construct a production database according to the production data.

[0061] In the embodiment of the present invention, the production data of the semi-autogenous mill is obtained by configuring an array of sensors. Figure 2 It is the schematic diagram of the architecture of the ball addition system for a semi-autogenous mill in the embodiment of the present invention. As Figure 2 shown, the array of sensors includes an acoustic emission sensor, a vibration sensor, a current transformer, an infrared thermal imager, and an axial pressure detector.

[0062] Optionally, an 8-channel acoustic emission sensor is arranged in a circle around the semi-autogenous mill to collect the operating audio signal of the semi-autogenous mill when it is running, a three-dimensional vibration sensor is used to collect the vibration frequency signal caused by the operation of the semi-autogenous mill, a high-precision current transformer is used to collect the operating current signal of the semi-autogenous mill, an infrared thermal imager is used to collect the temperature field distribution signal of the semi-autogenous mill barrel, and an axial pressure detector is used to detect the bearing pressure signal of the semi-autogenous mill support point. In an embodiment of the present invention, the array sensor group automatically collects the production data of the semi-autogenous mill every 5 minutes and stores it in the database to form a production database, which stores a time series of production data sets, and the production data includes but is not limited to data such as operating audio signals, operating vibration frequency signals, operating current signals, temperature field distribution signals of the barrel, and bearing pressure signals of the support points.

[0063] S200, build a digital platform based on the production database combined with the mineral processing knowledge base and expert system. The mineral processing knowledge base is used to provide professional knowledge in the mineral processing process, and the expert system is used to make steel ball replenishment decisions based on professional knowledge and production data.

[0064] In the embodiment of the present invention, the digital platform mainly includes a production database, a mineral processing knowledge base and an expert system, wherein the mineral processing knowledge base contains the professional knowledge in the mineral processing process, and the expert system is a computer system that simulates the decision-making ability of human experts. The expert system needs to extract the required knowledge from the mineral processing knowledge base and apply it to the analysis of production data to make decisions on adding steel balls. Figure 3 2 is a second schematic diagram of the process of the steel ball supplement control method for the semi-autogenous grinding mill provided by the embodiment of the present invention, as shown in FIG. Figure 3 As shown in the figure, the construction of the digital platform includes the following steps:

[0065] S210, obtaining production data from a production database, and extracting feature data based on the production data.

[0066] In an embodiment of the present invention, production data is obtained from a production database, and then feature data is extracted from the production data. The feature data includes but is not limited to audio data, vibration frequency data, current data, temperature data and axial pressure data when the semi-autogenous mill is in operation.

[0067] S220, constructing a recursive neural network model, and performing predictive analysis on the feature data according to the recursive neural network model to obtain feature parameters.

[0068] The recursive neural network model is a neural network model for processing sequence data, which has a loop structure and can capture the time dependency in the sequence. In the embodiment of the present invention, an initial recursive neural network model is first constructed, and then 200 sets of historical feature data are used as training sets and validation sets to train and optimize the initial recursive neural network model to obtain a trained recursive neural network model.

[0069] Predictive analysis is performed on the feature data using the trained recurrent neural network model, mainly for the time series of the consumption of steel balls in the semi-autogenous mill. At the same time, the audio and vibration frequencies of the interaction between steel balls, liners, and ore during the rotation of the semi-autogenous mill are analyzed. Moreover, data such as the temperature field fluctuation of the cylinder body and the change in axial pressure can be tracked and predicted. Various feature data are calibrated and feature-level data fusion is carried out to obtain the characteristic parameters of the semi-autogenous mill.

[0070] S230. Construct a beneficiation knowledge base and set the parameter matching rules and parameter matching ranges of the beneficiation knowledge base.

[0071] The beneficiation knowledge base is used to provide professional knowledge in the beneficiation process. This professional knowledge includes, but is not limited to, parameters such as ore properties, grinding efficiency, and steel ball wear rules. Among them, the ore property parameters include, but are not limited to, parameters such as ore type, hardness, feed particle size of the semi-autogenous mill, and discharge particle size of the semi-autogenous mill. The grinding efficiency parameters include, but are not limited to, parameters such as the throughput of the semi-autogenous mill, grinding concentration, and mill rotation speed. The steel ball wear rule parameters include, but are not limited to, parameters such as steel ball filling rate, specifications, hardness, material of the additional steel balls, additional plan, material and service life of the liner.

[0072] The early-stage beneficiation knowledge base configures parameter matching rules based on multi-dimensional knowledge such as ore physical properties, mill process parameters, and historical cases. This beneficiation knowledge base includes a rule base, a case base, and a model base. The rule base stores relevant control logic and matching logic. For example, when the ore hardness fluctuates by ±15%, the additional ball amount needs to be adjusted by ±X%, or the matching rule between the rotation speed and the filling rate. The case base records historical additional ball events and effect data for the expert system to optimize strategies, such as the additional steel ball efficiency data for ores with different hardnesses. The model base embeds algorithm models such as the hardness-wear correlation model and the mill efficiency calculation model.

[0073] The later-stage beneficiation knowledge base autonomously learns and improves according to the actual parameters detected during the normal production process of the semi-autogenous mill, and configures the parameter matching ranges. For example, normal control parameter ranges such as the normal audio range, vibration frequency range, operating current range, temperature change range, and axial pressure change range are set according to the parameters of the normal operation of the semi-autogenous mill.

[0074] S240. Construct an expert system, and use the expert system to make decisions on steel ball addition according to the characteristic parameters, parameter matching rules, and parameter matching ranges.

[0075] In the embodiments of the present invention, the expert system simulates the decision-making logic of human experts, combines the characteristic parameters output by the recurrent neural network model, and extracts parameter matching rules and parameter matching ranges from the ore dressing knowledge base for dynamic reasoning. The expert system automatically matches the characteristic parameters against these parameter matching rules and parameter matching ranges, and makes decisions on whether to add steel balls and how to add them in combination with the current operating state of the semi-autogenous mill and the equipment working conditions, etc.

[0076] Optionally, when one or more of the parameters such as the axial pressure, operating current, vibration frequency, operating audio, and temperature of the semi-autogenous mill exceed the normal range, steel balls should be added in a timely manner or the ore feeding should be stopped until the abnormal parameters return to normal. For example, when one or more of the following states are reached, it can be determined that steel balls need to be added: the main frequency of acoustic emission drops to 80% of the set value, and the current fluctuation > 8%; the axial pressure rises to 110% of the upper limit value; the vibration frequency rises to 110% of the upper limit; the operating current fluctuation > 10%; the return amount of hard rock rises to 120% of the upper limit.

[0077] In the data platform, the expert system makes decisions using the information in the ore dressing knowledge base and the production database, especially in the specific scenario of adding steel balls. The expert system matches and reasons the rules in the ore dressing knowledge base through an inference engine to decide whether to add steel balls, thereby realizing the intelligence and automation of decision-making.

[0078] S300. Construct a steel ball wear dynamics model based on ore parameters, steel ball parameters, and the operating parameters of the semi-autogenous mill.

[0079] In the embodiments of the present invention, a steel ball wear dynamics model is established based on the parameters related to the ore properties, the parameters related to the steel ball properties, and the operating parameters of the semi-autogenous mill. The formula of the steel ball wear dynamics model is as follows:

[0080]

[0081] In the above formula, W represents the wear amount of the steel ball, K represents the wear coefficient, D represents the diameter of the steel ball, t represents the operating time of the semi-autogenous mill, ρ represents the ore density, H represents the ore hardness, and E represents the impact energy of the semi-autogenous mill.

[0082] S400. Calculate the steel ball addition parameters of the semi-autogenous mill according to the digital platform and the steel ball wear dynamics model.

[0083] Based on the pre-trained recurrent neural network model and the expert system in the data platform, a steel ball addition decision-making method is established, and then a steel ball grading optimization engine is developed in combination with the steel ball wear dynamics model to calculate in real time the steel ball addition parameters such as the optimal number of steel balls to be added and the dynamic addition period. Figure 4 It is the third schematic diagram of the steel ball addition control method flow of the semi-autogenous mill provided by the embodiments of the present invention, asFigure 4 As shown in the figure, the calculation of the steel ball supplementary parameters specifically includes the following steps:

[0084] S410, obtaining a real-time production data sequence of a semi-autogenous mill.

[0085] In the embodiment of the present invention, the real-time production data sequence is a production data time series of steel balls consumed in a semi-autogenous grinding mill.

[0086] S420, predicting the real-time production data sequence according to the recursive neural network model and the steel ball wear dynamics model to obtain prediction parameters.

[0087] The recursive neural network model and the steel ball wear dynamics model are used to predict and analyze the real-time production data series. At the same time, the audio, vibration frequency, fluctuation of the cylinder temperature field, axial pressure changes, etc. of the interaction between the steel balls, liners, and ore when the semi-autogenous mill rotates are tracked and predicted to obtain the prediction parameters.

[0088] S430, the expert system determines the steel ball supplementation parameters according to the predicted parameters.

[0089] In the embodiment of the present invention, the steel ball adding parameters such as the proportion and quantity of additional steel balls, the timing of additional steel balls, etc. are determined by the expert system in combination with the relevant mathematical model for additional steel balls in combination with the mineral processing knowledge base and the data of additional steel balls in the previous normal production database. At the same time, the mineral processing knowledge base and the production database are continuously improved and supplemented by the later production data, so that the mathematical model for additional steel balls is continuously optimized and supplemented.

[0090] S500: construct a digital twin prediction system based on production data, use the digital twin prediction system to adjust steel ball replenishment parameters, and obtain a steel ball replenishment strategy.

[0091] In an embodiment of the present invention, a digital twin prediction system for the operation of a semi-autogenous mill is constructed using 3D technology and a production database, so that managers and technicians can obtain the operating data of the semi-autogenous mill in real time, thereby predicting the working status of the semi-autogenous mill and obtaining a steel ball replenishment strategy. Figure 5 4 is a schematic diagram of the process of the steel ball supplement control method of the semi-autogenous grinding mill provided by the embodiment of the present invention, as shown in Figure 5 As shown in FIG. 1 , the steel ball supplementation strategy specifically includes the following steps:

[0092] S510: Obtain production data for data processing and analysis to obtain a production data set.

[0093] In an embodiment of the present invention, the production data of the semi-autogenous mill can be acquired in real time through an array sensor group, and the production data can be stored using cloud computing services or local servers. Then, big data processing tools can be used to clean the data and analyze the cleaned production data to obtain a production data set.

[0094] S520. Construct a model based on the production data set to obtain a digital twin prediction system, which includes a discrete element prediction model and a long short-term memory network model.

[0095] Optionally, tools such as computer-aided design (CAD), 3D modeling tools, and physical modeling languages can be used to construct a digital twin model of the semi-autogenous mill. In the embodiment of the present invention, after constructing the initial discrete element prediction model and the initial long short-term memory network model, the production data set is used to train and optimize the initial discrete element prediction model and the initial long short-term memory network model, and finally the discrete element prediction model and the long short-term memory network model are obtained.

[0096] Integrate the digital twin model, the discrete element prediction model, and the long short-term memory network model to build a digital twin prediction system, and ensure the matching between the real-time production data and each model to ensure that the digital twin prediction system can accurately simulate the behavior of the semi-autogenous mill in reality. Optionally, a visualization interface of the semi-autogenous mill can also be created, mainly including a schematic diagram of the operation of the semi-autogenous mill, a dashboard and display charts of operation parameters, a tool for generating relevant parameter reports, and a visualization tool, so that technicians or managers can directly obtain real-time information and prediction results.

[0097] The digital twin prediction system realizes the visualization, transparency, and intelligence of the working process of the semi-autogenous mill, thereby improving production efficiency and the safety of the operation of the semi-autogenous mill.

[0098] S530. The discrete element prediction model predicts the working state of the semi-autogenous mill after the first time threshold based on the real-time production data to obtain the predicted working state.

[0099] In the embodiment of the present invention, the discrete element prediction model can simulate the movement form of the load particles inside the semi-autogenous mill, and combine the real-time production data to predict the distribution, velocity, and energy state of the particles inside the semi-autogenous mill after the first time threshold, so as to judge the working state of the semi-autogenous mill in advance. Optionally, the first time threshold is set to 30 minutes.

[0100] S540. The long short-term memory network model adjusts the steel ball addition parameters according to the predicted working state to obtain a steel ball addition strategy.

[0101] In the embodiment of the present invention, the long short-term memory network model can capture the long-term dependence relationship in the time series data of the predicted working state, and can adjust the steel ball addition parameters in advance, including the quantity, specification ratio, and addition time of the added steel balls, and finally obtain a steel ball addition strategy.

[0102] S600. Control the intelligent ball adding machine to add steel balls to the semi-autogenous mill according to the steel ball addition strategy.

[0103] In the embodiment of the present invention, when the operating parameters of the semi-autogenous mill in the digital twin prediction system reach the criterion, a control instruction is sent to the intelligent ball feeder of the semi-autogenous mill through the digital twin system, and steel balls are accurately replenished by controlling the pneumatic conveying system of the intelligent ball feeder.

[0104] As a preferred implementation manner of the embodiment of the present invention, a secondary verification is started after a second time threshold delay after the steel balls are replenished, and the second time threshold can be set to 10 minutes. Specifically, the real-time production data of the semi-autogenous mill is obtained, and the digital twin prediction system compares the real-time production data with the predicted production data to obtain the operating parameter indicators of the semi-autogenous mill. The operating parameter indicators include but are not limited to the processing capacity of the semi-autogenous mill, ore type, ore hardness, feed particle size, discharge particle size, grinding concentration, mill speed, operating audio, vibration frequency, current, power, shaft pressure, shell temperature, steel ball filling rate, replenished steel ball specification, replenished steel ball hardness, replenished steel ball material, replenishment scheme, material and service life of the liner, etc. Finally, the digital platform, the steel ball wear dynamics model, and the digital twin prediction system are optimized according to these operating parameter indicators to optimize the decision-making process of steel ball replenishment.

[0105] To verify the effectiveness of the steel ball replenishment control method for the semi-autogenous mill provided in the embodiment of the present invention, an industrial test was carried out on a semi-autogenous mill with a specification of 8.5×4.3m in a certain copper mine. The traditional tonnage consumption method and the control method in the embodiment of the present invention were respectively used for steel ball replenishment of the semi-autogenous mill. Through parameter comparison and calculation, compared with the traditional tonnage consumption method, the tonnage energy consumption of the control method adopted in the embodiment of the present invention decreased from 6.8kW·h to 5.9kW·h, a decrease of 12%-18%. At the same time, the ore processing capacity increased from 785t / h to 860t / h, an increase of 9.5% in the processing capacity, and the steel ball consumption decreased from 0.8kg / t to 0.62kg / t, a decrease of 22%.

[0106] The steel ball replenishment control method for the semi-autogenous mill provided in the embodiment of the present invention can obtain the key parameters of the semi-autogenous mill in real time and dynamically adjust the replenishment ball quantity and cycle, ensuring that the equipment is always in the best working state, thus significantly improving the processing capacity, reducing the downtime, and meeting the large-scale production requirements. By accurately controlling the working parameters of the equipment, the energy consumption is effectively reduced, unnecessary energy waste is avoided, and by calculating the optimal replenishment ball quantity in real time, the steel ball consumption is reduced, the service life is extended, and the operation cost is further reduced.

[0107] Embodiment 2

[0108] Based on the same technical concept as in Method Embodiment 1 above, the embodiment of the present invention provides a steel ball replenishment control device for a semi-autogenous mill. Figure 6 It is a schematic structural diagram of the steel ball replenishment control device for the semi-autogenous mill provided in the embodiment of the present invention, asFigure 6 As shown, the steel ball replenishment control device 600 of the semi-autogenous mill includes:

[0109] A data acquisition module 610, configured to acquire the production data of the semi-autogenous mill and construct a production database according to the production data.

[0110] A platform construction module 620, configured to construct a digital platform according to the production database in combination with the ore dressing knowledge base and the expert system. The ore dressing knowledge base is used to provide professional knowledge in the ore dressing process, and the expert system is used to make decisions on steel ball replenishment according to the professional knowledge and production data.

[0111] A model construction module 630, configured to construct a steel ball wear dynamics model according to the ore parameters, steel ball parameters, and operating parameters of the semi-autogenous mill.

[0112] A parameter calculation module 640, configured to calculate the steel ball replenishment parameters of the semi-autogenous mill according to the digital platform and the steel ball wear dynamics model.

[0113] A strategy generation module 650, configured to construct a digital twin prediction system according to the production data, adjust the steel ball replenishment parameters by using the digital twin prediction system, and obtain a steel ball replenishment strategy.

[0114] A steel ball replenishment module 660, configured to control an intelligent ball adding machine to replenish steel balls to the semi-autogenous mill according to the steel ball replenishment strategy.

[0115] The steel ball replenishment control device of the semi-autogenous mill provided by the embodiment of the present invention makes decisions based on real-time production data and algorithm models, reduces manual intervention, improves decision-making efficiency, can continuously update the algorithm model according to new data, enhances the robustness and flexibility of the device, and provides strong support for the sustainable development and environmental protection production of enterprises.

[0116] It can be understood that the implementation manners in the steel ball replenishment control method of the semi-autogenous mill described in the above-mentioned Embodiment 1 are equally applicable to this embodiment and can achieve the same technical effects, so they will not be repeated here.

[0117] Embodiment 3

[0118] Based on the same concept, the embodiment of the present invention further provides an electronic device. Figure 7 It is a schematic structural diagram of an electronic device provided by the embodiment of the present invention. As Figure 7 shown, the electronic device 700 may include: a processor 710, a communication interface 720, a memory 730, and a communication bus 740. Among them, the processor 710, the communication interface 720, and the memory 730 communicate with each other through the communication bus 740. The processor 710 may call the logical instructions in the memory 730 to execute the steps of the steel ball replenishment control method of the semi-autogenous mill described in the above-mentioned embodiments. For example, it includes:

[0119] S100. Obtain the production data of the semi-autogenous mill and construct a production database based on the production data;

[0120] S200. Construct a digital platform according to the production database in combination with the ore dressing knowledge base and the expert system. The ore dressing knowledge base is used to provide professional knowledge in the ore dressing process, and the expert system is used to make decisions on steel ball addition according to the professional knowledge and production data;

[0121] S300. Construct a steel ball wear kinetics model based on the ore parameters, steel ball parameters and operating parameters of the semi-autogenous mill;

[0122] S400. Calculate the steel ball addition parameters of the semi-autogenous mill according to the steel ball wear kinetics model of the digital platform;

[0123] S500. Construct a digital twin prediction system according to the production data, and use the digital twin prediction system to adjust the steel ball addition parameters to obtain a steel ball addition strategy;

[0124] S600. Control the intelligent ball adding machine to add steel balls to the semi-autogenous mill according to the steel ball addition strategy.

[0125] Among them, the processor 710 can be a central processing unit (CPU). The processor can also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. chips, or combinations of the above types of chips.

[0126] In addition, when the logical instructions in the above-mentioned memory 730 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0127] The memory 730 may include a program storage area and a data storage area. Among them, the program storage area can store an operating system and application programs required for at least one function; the data storage area can store data created by the processor, etc. In addition, the memory may include high-speed random access memory and may also include non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory optionally includes a memory remotely set relative to the processor, and these remote memories can be connected to the processor through a network. Examples of the above-mentioned network include but are not limited to the Internet, enterprise intranets, local area networks, mobile communication networks, and combinations thereof.

[0128] Embodiment 4

[0129] Based on the same concept, an embodiment of the present invention further provides a computer-readable storage medium. This computer-readable storage medium stores a computer program, and this computer program includes at least one segment of code. This at least one segment of code can be executed by a master control device to control the master control device to implement the steps of the steel ball supplementary addition control method of the semi-autogenous mill as described in the above-mentioned various embodiments. For example, it includes:

[0130] S100. Obtain the production data of the semi-autogenous mill and construct a production database according to the production data;

[0131] S200. Construct a digital platform according to the production database in combination with a beneficiation knowledge base and an expert system. The beneficiation knowledge base is used to provide professional knowledge in the beneficiation process, and the expert system is used to make steel ball supplementary addition decisions based on professional knowledge and production data;

[0132] S300. Construct a steel ball wear kinetics model according to ore parameters, steel ball parameters, and the operating parameters of the semi-autogenous mill;

[0133] S400. Calculate the steel ball replenishment parameters of the semi-autogenous mill according to the digital platform steel ball wear dynamics model;

[0134] S500. Construct a digital twin prediction system based on production data, and use the digital twin prediction system to adjust the steel ball replenishment parameters to obtain a steel ball replenishment strategy;

[0135] S600. Control the intelligent ball adding machine to replenish steel balls to the semi-autogenous mill according to the steel ball replenishment strategy.

[0136] Based on the same technical concept, an embodiment of the present invention also provides a computer program, which, when executed by a main control device, is used to implement the above method embodiment.

[0137] The computer program can be stored in whole or in part on a computer-readable storage medium packaged together with the processor, or can be stored in whole or in part on a memory not packaged together with the processor.

[0138] Based on the same technical concept, an embodiment of the present invention also provides a processor, which is used to implement the above method embodiment. The above processor can be a chip.

[0139] In summary, the steel ball replenishment control method, device, equipment and storage medium of the semi-autogenous mill provided by the present invention can obtain the key parameters of the semi-autogenous mill in real time and dynamically adjust the replenishment ball quantity and cycle, ensuring that the equipment is always in the best working state, thereby significantly increasing the throughput, reducing the downtime, and meeting the large-scale production requirements. By accurately controlling the working parameters of the equipment, the energy consumption is effectively reduced, unnecessary energy waste is avoided, and by calculating the optimal replenishment ball quantity in real time, the steel ball consumption is reduced, the service life is extended, and the operation cost is further reduced. At the same time, decisions are made based on real-time production data and algorithm models, reducing manual intervention, improving decision-making efficiency, and being able to continuously update the algorithm model according to new data, enhancing the robustness and flexibility of the device, and providing strong support for the sustainable development and environmental protection production of enterprises.

[0140] Referring to "embodiment" herein means that a specific feature, structure or characteristic described in connection with the embodiment can be included in at least one embodiment of the present application. The phrase appears in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0141] The above-described embodiments merely represent several implementation manners of the present invention. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the scope of the patent of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the appended claims.

[0142] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for controlling the addition of steel balls in a semi-autogenous mill, characterized in that, The method includes: Obtaining the production data of the semi-autogenous mill and constructing a production database according to the production data; Constructing a digital platform based on the production database in combination with a beneficiation knowledge base and an expert system, where the beneficiation knowledge base is used to provide professional knowledge in the beneficiation process, and the expert system is used to make decisions on steel ball addition according to the professional knowledge and the production data; Constructing a steel ball wear kinetics model according to ore parameters, steel ball parameters and the operating parameters of the semi-autogenous mill; Calculating the steel ball addition parameters of the semi-autogenous mill according to the digital platform and the steel ball wear kinetics model; Constructing a digital twin prediction system according to the production data, and using the digital twin prediction system to adjust the steel ball addition parameters to obtain a steel ball addition strategy; Controlling an intelligent ball adding machine to add steel balls to the semi-autogenous mill according to the steel ball addition strategy.

2. The method for controlling the addition of steel balls in the semi-autogenous mill according to claim 1, characterized in that, The constructing a digital platform based on the production database in combination with a beneficiation knowledge base and an expert system includes: Obtaining the production data of the production database and extracting feature data according to the production data; Constructing a recurrent neural network model, and performing predictive analysis on the feature data according to the recurrent neural network model to obtain feature parameters; Constructing a beneficiation knowledge base and setting parameter matching rules and parameter matching ranges for the beneficiation knowledge base; Constructing an expert system, and using the expert system to make decisions on steel ball addition according to the feature parameters, the parameter matching rules and the parameter matching ranges.

3. The steel ball supplementary addition control method for the semi-autogenous mill according to claim 2, wherein The formula of the steel ball wear kinetics model is as follows: In the above formula, W represents the wear amount of the steel ball, K represents the wear coefficient, D represents the steel ball diameter, t represents the running time of the semi-autogenous mill, ρ represents the ore density, H represents the ore hardness, and E represents the impact energy of the semi-autogenous mill.

4. The steel ball supplementary addition control method of the semi-autogenous mill according to claim 3, characterized in that, The calculating the steel ball addition parameters of the semi-autogenous mill according to the digital platform and the steel ball wear kinetics model includes: Obtaining the real-time production data sequence of the semi-autogenous mill; Performing prediction on the real-time production data sequence according to the recurrent neural network model and the steel ball wear kinetics model to obtain prediction parameters; The expert system determines the steel ball addition parameters according to the prediction parameters.

5. The steel ball supplementary addition control method of the semi-autogenous mill according to claim 1, characterized in that, The constructing a digital twin prediction system according to the production data, and using the digital twin prediction system to adjust the steel ball addition parameters to obtain a steel ball addition strategy includes: Obtaining the production data for data processing and analysis to obtain a production data set; Performing model construction according to the production data set to obtain the digital twin prediction system, where the digital twin prediction system includes a discrete element prediction model and a long short-term memory network model; The discrete element prediction model predicts the working state of the semi-autogenous mill after a first time threshold according to real-time production data to obtain a predicted working state; The long short-term memory network model adjusts the steel ball addition parameters according to the predicted working state to obtain the steel ball addition strategy.

6. The steel ball replenishment control method of the semi-autogenous mill according to claim 1, wherein, After controlling the intelligent ball adding machine to add steel balls to the semi-autogenous mill according to the steel ball addition strategy, it further includes: After a second time threshold delay after the steel ball addition, obtaining the real-time production data of the semi-autogenous mill; The digital twin prediction system compares data based on the real-time production data to obtain the operation parameter indicators of the semi-autogenous mill. Optimize the digital platform, the steel ball wear dynamics model, and the digital twin prediction system according to the operation parameter indicators.

7. The steel ball supplementary addition control method for the semi-autogenous mill according to claim 1, characterized in that, The production data at least includes the operating audio signal, the operating vibration frequency signal, the operating current signal, the temperature field distribution signal of the cylinder body, and the bearing pressure signal of the support point.

8. A steel ball supplementary addition control device for a semi-autogenous mill, characterized in that, The device includes: A data acquisition module, configured to acquire the production data of the semi-autogenous mill and construct a production database according to the production data. A platform construction module, configured to construct a digital platform according to the production database in combination with the ore dressing knowledge base and the expert system. The ore dressing knowledge base is used to provide professional knowledge in the ore dressing process, and the expert system is used to make decisions on steel ball addition according to the professional knowledge and the production data. A model construction module, configured to construct a steel ball wear dynamics model according to the ore parameters, the steel ball parameters, and the operating parameters of the semi-autogenous mill. A parameter calculation module, configured to calculate the steel ball addition parameters of the semi-autogenous mill according to the digital platform and the steel ball wear dynamics model. A strategy generation module, configured to construct a digital twin prediction system according to the production data, and use the digital twin prediction system to adjust the steel ball addition parameters to obtain a steel ball addition strategy. A steel ball addition module, configured to control an intelligent ball adding machine to add steel balls to the semi-autogenous mill according to the steel ball addition strategy.

9. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the steel ball addition control method of the semi-autogenous mill according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steel ball addition control method of the semi-autogenous mill according to any one of claims 1 to 7.

Images