Method and device for optimizing two-phase corundum crushing system based on composite granulation process

Abstract

The embodiment of the invention discloses a two-phase corundum crushing system optimization method and device based on a composite granulation process, and belongs to the technical field of control or regulation systems. The operation data of the two-phase corundum crushing system are collected in real time, the current optimal energy consumption and output ratio is calculated based on a multi-objective optimization algorithm, crushing parameters of the two-phase corundum crushing system are adjusted, and an optimization model of the two-phase corundum crushing system is constructed. And solving the multi-objective optimization problem of the optimization model by adopting a non-dominated sorting genetic algorithm in the optimization model, and adjusting the roller mill pressure of the two-phase corundum crushing system according to an optimization strategy generated by the balance scheme. According to the embodiment of the invention, the operation data of the crushing system is collected in real time, and the multi-objective optimization algorithm is combined to realize dynamic adjustment and optimization of the crushing parameters, so that the overall performance of the two-phase corundum crushing system is improved, the energy consumption is reduced, the product quality is improved, and the service life of equipment is prolonged.

Description

Technical Field

[0001] The embodiments of the present application relate to a method and device for optimizing a dual-phase corundum crushing system based on a composite granulation process, belonging to the technical field of control or regulation systems. Background Art

[0002] Duplex corundum, as an important industrial material, is widely used in a variety of fields, including refractories, abrasives, and electronic ceramics. The crushing system is a key technical link in the production of duplex corundum. The proper operation of the crushing system directly affects the production efficiency and product quality of duplex corundum.

[0003] Limitations of existing dual-phase corundum crushing systems: Traditional duplex corundum crushing systems typically use a single crushing device and fixed crushing parameters, lacking the ability to monitor and dynamically adjust the crushing process in real time. For example, the following problems may occur: 1. High energy consumption: Since it is impossible to adjust the crushing parameters in real time according to the material characteristics and crushing effect, the energy consumption of the crushing process is high and the production cost increases.

[0004] 2. Low crushing efficiency: Crushing equipment with fixed parameters is difficult to adapt to duplex corundum raw materials with different particle size distribution and hardness, resulting in low crushing efficiency and extended production cycle.

[0005] 3. Unstable product quality: The particle size distribution of the output material cannot be accurately controlled, resulting in large fluctuations in product quality and making it difficult to meet the particle size accuracy requirements of high-end applications.

[0006] 4. Severe equipment wear: Due to the lack of monitoring and analysis of key data such as vibration signals during the crushing process, equipment abnormalities cannot be discovered in a timely manner, resulting in increased equipment wear and increased maintenance costs.

[0007] The above problems have not yet been satisfactorily solved, and the existing technology can no longer meet people's requirements and is in urgent need of improvement. Summary of the Invention

[0008] The purpose of the embodiments of the present application is to provide a method and device for optimizing a dual-phase corundum crushing system based on a composite granulation process, using data processing methods and optimization algorithms to improve the performance of the crushing system and address the shortcomings of the prior art.

[0009] The present application provides the following solutions: According to one aspect of an embodiment of the present application, a method for optimizing a duplex corundum crushing system based on a composite granulation process is provided, comprising: real-time collection of operating data of the duplex corundum crushing system, the operating data comprising at least: crusher current, vibration signal, feed particle size distribution, discharge particle size distribution, and equipment temperature, and obtaining ratio data of corundum and β-phase alumina in the duplex corundum; calculating the current optimal energy consumption and output ratio based on a multi-objective optimization algorithm according to the ratio data, and adjusting the crushing parameters of the duplex corundum crushing system accordingly according to the calculation result of the current optimal energy consumption and output ratio; constructing an optimization model for the duplex corundum crushing system, the parameters of the optimization model comprising crushing efficiency, unit energy consumption, and particle size qualified rate, and using a non-dominated sorting genetic algorithm in the optimization model to solve the multi-objective optimization problem of the optimization model, the multi-objective optimization problem specifically comprising providing a balance solution for crushing efficiency, unit energy consumption, and particle size qualified rate through an optimal solution set; updating the parameters of the duplex corundum crushing system at regular intervals according to the optimization strategy generated by the balance solution, and adjusting the roller mill pressure of the duplex corundum crushing system.

[0010] According to at least one specific embodiment of the embodiment of the present application, the real-time collection of operating data of the dual-phase corundum crushing system further includes: collecting the three-phase current signal of the crusher drive motor in real time through a current sensor installed on the crusher main shaft, analyzing the current spectrum characteristics of the three-phase current signal through fast Fourier transform, and extracting the fundamental and harmonic components; collecting the vibration signals of the bearing seat in three directions of the dual-phase corundum crushing system through a vibration acceleration sensor, and the frequency of the sampled vibration signal is greater than or equal to 10kHz; the raw materials of the dual-phase corundum crushing system are scanned online by a laser particle size analyzer to obtain feed particle size distribution data at intervals of a certain time; the three-phase current signal, vibration signal and feed particle size distribution data are transmitted to the host computer via industrial Ethernet, and the host computer is optimally connected to the dual-phase corundum crushing system, and the host computer is used to preprocess the received data.

[0011] According to at least one specific implementation of the embodiments of the present application, during the process of preprocessing the received data by the host computer, a timestamp alignment method is used to ensure the data synchronization of the three-phase current signal, vibration signal and feed particle size distribution data; the crushing parameters of the two-phase corundum crushing system include: crusher current, vibration signal, feed rate, and discharge particle size distribution data.

[0012] According to at least one specific implementation of the embodiments of the present application, the current optimal energy consumption and output ratio is calculated based on the proportion data based on a multi-objective optimization algorithm, and the crushing parameters of the duplex corundum crushing system are adjusted accordingly according to the calculation result of the current optimal energy consumption and output ratio, further including: using the corundum and β-phase alumina in the obtained duplex corundum as input variables of the optimization model, and using a multi-objective optimization algorithm to perform multi-objective optimization solution, and the multi-objective optimization algorithm is specifically an improved NSGA-III algorithm; generating a candidate parameter set in the improved NSGA-III algorithm, and the candidate parameter set contains three decision variables: crusher speed, roller gap, and classifier frequency; dividing the solution set of the candidate parameter set into multiple frontier levels through non-dominated sorting, and performing iterative calculation using a reference point-guided selection mechanism; in the process of iterative calculation, the feasibility of the combination of crushing parameters is checked, and after 80-120 iterations, the Pareto optimal solution set is output.

[0013] According to at least one specific implementation of the embodiments of the present application, during the iterative calculation process, the feasibility of the combination of crushing parameters is checked, and after 80-120 iterations, the Pareto optimal solution set is output, further including: in the improved NSGA-III algorithm, the initial population is randomly generated by the host computer of the two-phase corundum crushing system, and each individual parameter of the initial population includes three decision variables: crusher speed, roller gap and classifier frequency. The speed has a value range of 800-1200 rpm, the roller gap has a value range of 0.1-0.5 mm, and the classifier frequency has a value range of 30-60 Hz.

[0014] According to at least one specific implementation of the embodiments of the present application, the use of a non-dominated sorting genetic algorithm in the optimization model to solve the multi-objective optimization problem of the optimization model further includes: constructing an optimization model containing three objective functions, and using a non-dominated sorting genetic algorithm to solve the multi-objective optimization problem; setting the initialization population size and individual coding in the optimization model, and establishing a crushing system operation prediction sub-model based on the historical operation data of the two-phase corundum crushing system; the upper computer collects the current operation data in real time, performs incremental learning on the crushing system operation prediction sub-model, and updates the model parameters; performs a credibility assessment on the prediction results output by the crushing system operation prediction sub-model, and when the deviation between the predicted value and the actual measured value exceeds 5% for three consecutive times, triggers the model retraining process.

[0015] According to at least one specific implementation of the embodiments of the present application, the construction includes an optimization model of three objective functions, specifically: a first objective function, which is defined as the ratio of the actual processing volume to the rated capacity of the system, and is calculated by the feed rate and effective operating time collected in real time; a second objective function, which is the unit energy consumption, and is calculated by dividing the integral of the current and voltage product of the crusher drive motor by the total mass of the processed material; a third objective function, which is the particle size qualification rate, and is calculated by the degree of conformity of the discharge particle size distribution with the preset standard range.

[0016] According to at least one specific implementation of the embodiments of the present application, the initialization population size and individual code in the setting optimization model are used to establish a crushing system operation prediction sub-model based on the historical operation data of the two-phase corundum crushing system, specifically: the initialization population size is set to 100-150 individuals, and each individual code includes a three-dimensional real number vector composed of crusher speed, roller press pressure and classifier frequency; the crossover probability is set to 0.85 and the mutation probability is set to 0.1 in the prediction sub-model, and a simulated binary crossover operator is used for gene recombination; after completing the gene recombination, a corresponding parameter combination is generated for each individual code in each generation of evolution, and the values ​​of each objective function are predicted by the established digital twin model of the crushing process to obtain a crushing system operation prediction sub-model.

[0017] According to another aspect of the embodiment of the present application, a dual-phase corundum crushing system optimization device based on a composite granulation process is provided, which is used to implement the dual-phase corundum crushing system optimization method, including: a dual-phase corundum crushing system data acquisition module, which is used to collect the operating data of the dual-phase corundum crushing system in real time, and the operating data at least includes: crusher current, vibration signal, feed particle size distribution, discharge particle size distribution, equipment temperature, and obtain the ratio data of corundum and β-phase alumina in the dual-phase corundum; a dual-phase corundum crushing parameter adjustment module, which is used to calculate the current optimal energy consumption and output ratio based on the multi-objective optimization algorithm according to the ratio data, and calculate the current optimal energy consumption and output ratio through the calculation of the current optimal energy consumption and output ratio. The calculation results correspond to the adjustment of the crushing parameters of the dual-phase corundum crushing system; a dual-phase corundum crushing system optimization model construction module is used to construct an optimization model of the dual-phase corundum crushing system, the parameters of the optimization model include crushing efficiency, unit energy consumption and particle size qualified rate, and a non-dominated sorting genetic algorithm is used in the optimization model to solve the multi-objective optimization problem of the optimization model, and the multi-objective optimization problem is specifically to provide a balance solution for crushing efficiency, unit energy consumption and particle size qualified rate through an optimal solution set; a dual-phase corundum crushing system adjustment module is used to update the parameters of the dual-phase corundum crushing system at regular intervals according to the optimization strategy generated by the balance solution, and adjust the roller mill pressure of the dual-phase corundum crushing system.

[0018] According to another aspect of the embodiments of the present application, an electronic device is provided, comprising: a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; a computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the steps of the method.

[0019] Compared with the prior art, the embodiments of the present application have the following advantages: The embodiment of the present application realizes dynamic adjustment and optimization of crushing parameters by real-time collection of operating data of the crushing system and combining it with a multi-objective optimization algorithm, thereby improving the overall performance of the duplex corundum crushing system, reducing energy consumption, improving product quality, and extending equipment life, providing good technical support for the efficient production of duplex corundum. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the specific implementation methods of the embodiments of the present application or the technical solutions in the prior art, the following will briefly introduce the drawings required for use in the specific implementation methods or the description of the prior art. Obviously, the drawings described below are some implementation methods of the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 It is a flow chart of the optimization method of the duplex corundum crushing system based on the composite granulation process.

[0022] Figure 2 It is a flow chart of the optimization technical solution provided in steps S11 and S14.

[0023] Figure 3 It is a flow chart of the optimization technical solution provided by steps S21 to S24.

[0024] Figure 4 It is a flow chart of the optimization technical solution provided by steps S31 to S34.

[0025] Figure 5 It is a flowchart of the optimization technical solution provided by steps S321 to S323.

[0026] Figure 6 This is the architecture diagram of the dual-phase corundum crushing system optimization device based on the composite granulation process.

[0027] Figure 7 It is a structural diagram of an electronic device. DETAILED DESCRIPTION

[0028] The following will clearly and completely describe the technical solutions of the embodiments of the present application in conjunction with the accompanying drawings. Obviously, the embodiments described are only part of the embodiments of the present application, not all of them. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the embodiments of the present application.

[0029] Composite granulation is a process that combines multiple raw materials through specific physical or chemical methods to form granules with specific particle sizes and properties. Composite granulation is widely used in fields such as pharmaceuticals, chemicals, agriculture, and materials science. Depending on the application requirements, composite granulation can be implemented using a variety of methods, such as spray drying, fluidized bed granulation, and wet mixing granulation. In a duplex corundum crushing system, composite granulation is primarily used to further process the crushed duplex corundum granules. This process improves granule strength and uniformity, controls particle size distribution, and enhances chemical stability by adjusting granulation parameters (such as spray rate, drying temperature, and mixing time). Applying composite granulation to a duplex corundum crushing system allows for automated and continuous production, reduces manual intervention, and improves production efficiency.

[0030] In recent years, with the rapid development of industrial automation and intelligent technology, many studies have focused on improving the performance of duplex corundum crushing systems by improving sensor technology, enabling data processing methods, and optimizing algorithms based on host computers. For example, some research results have emerged in the prior art. By installing sensors on the crusher to obtain operating data in real time, and using machine learning algorithms to conduct in-depth analysis of these data, dynamic adjustment of crushing parameters is achieved. However, most of these studies are only carried out for a single type of crusher, and research on the optimization of crushing systems for complex materials such as duplex corundum is relatively scarce. Currently, there are many defects in the existing duplex corundum crushing systems and optimization methods on the market, which are difficult to meet the strict requirements of modern industrial production for high efficiency, energy saving, stability and high quality. Therefore, the embodiment of the present application provides a duplex corundum crushing system optimization method and device based on real-time data acquisition and multi-objective optimization algorithm, which has significant practical significance and broad application prospects. By collecting the operating data of the crushing system in real time and combining it with advanced multi-objective optimization algorithms, dynamic adjustment and optimization of crushing parameters are achieved, thereby comprehensively improving the overall performance of the duplex corundum crushing system, effectively reducing energy consumption, significantly improving product quality, and extending the service life of the equipment.

[0031] like Figure 1 The optimization method of the dual-phase corundum crushing system shown in the figure includes the following steps: In step S1, real-time operational data from the duplex corundum crushing system is collected. This data includes at least crusher current, vibration signal, feed particle size distribution, discharge particle size distribution, and equipment temperature. The ratio of corundum to β-alumina in the duplex corundum is also obtained. In step S1, corundum refers to α-alumina, while β-alumina is also referred to as "β-type alumina" or "β-alumina." The corundum crushing in step S1 involves the phase representation of alumina. Corundum (α-Al2O3) is the name of the naturally occurring mineral α-alumina, the most thermodynamically stable crystal form, commonly found after high-temperature sintering. It is worth noting that β-alumina (β-Al2O3) is not a pure alumina crystal form, but rather an alkali metal-containing aluminate (such as NaAlO2). β-alumina exhibits fast ion conductor properties and differs significantly from α-Al2O3 in structure. β-alumina (β-Al2O3) requires specific components (such as Na2O) to form at high temperatures.

[0032] Step S2, according to the ratio data, calculate the current optimal energy consumption and output ratio based on a multi-objective optimization algorithm, and adjust the crushing parameters of the dual-phase corundum crushing system accordingly according to the calculation result of the current optimal energy consumption and output ratio.

[0033] Step S3, constructing an optimization model of the dual-phase corundum crushing system, the parameters of the optimization model include crushing efficiency, unit energy consumption and particle size qualified rate, and using the non-dominated sorting genetic algorithm NSGA-II in the optimization model to solve the multi-objective optimization problem of the optimization model. The multi-objective optimization problem specifically provides a balance solution for crushing efficiency, unit energy consumption and particle size qualified rate through the optimal solution set.

[0034] Step S4: According to the optimization strategy generated by the balance solution, the parameters of the dual-phase corundum crushing system are updated at regular intervals to adjust the roller mill pressure of the dual-phase corundum crushing system.

[0035] Based on the technical solutions provided in steps S1 to S4, the dual-phase corundum crushing system collects operating data and phase ratio data of dual-phase corundum in real time, and the optimization model can dynamically adjust the crushing parameters to ensure that the crushing process is always in the best state, thereby significantly improving the crushing efficiency. For example, based on the feed particle size distribution and the discharge particle size distribution data, the optimization model can adjust the speed and roller gap of the crusher to make the crushing process more efficient while reducing the unit energy consumption. That is, the optimization model calculates the current optimal energy consumption and output ratio through a multi-objective optimization algorithm, and dynamically adjusts the crushing parameters to ensure that the operating parameter combination with the lowest energy consumption is found while achieving the desired crushing effect, thereby reducing the unit energy consumption. And by monitoring the feed and discharge particle size distribution in real time, the optimization model is used to dynamically adjust the crushing parameters to ensure that the discharge particle size distribution meets the preset standards, thereby significantly improving the particle size qualification rate and ensuring the uniformity and consistency of the discharge particle size distribution.

[0036] It is worth noting that the technical solution provided by steps S1 to S4 can achieve dynamic optimization. Based on the optimization model, a non-dominated sorting genetic algorithm is used to solve the multi-objective optimization problem. The optimal solution set can be dynamically generated to provide a balance between crushing efficiency, unit energy consumption and particle size qualification rate, avoiding the one-sidedness caused by single-objective optimization. By regularly updating the optimization strategy, the crushing parameters are dynamically adjusted according to real-time operation data to ensure that the system always operates in the optimal state.

[0037] In summary, the technical solution provided by steps S1 to S4 achieves dynamic optimization of the duplex corundum crushing system through real-time data acquisition and a multi-objective optimization algorithm, significantly improving crushing efficiency, reducing unit energy consumption, and increasing the particle size qualification rate. This not only improves the overall performance of the duplex corundum crushing system, but also provides efficient, energy-saving, stable, and high-quality technical guarantees and technical support for the industrial production of duplex corundum. For example, during the implementation of a certain refractory project, the intelligent upgrade of the crushing system was successfully achieved, significantly improving production efficiency and product quality, and reducing production costs and equipment maintenance costs. This not only improves the overall performance of the duplex corundum crushing system, but also provides efficient, energy-saving, stable, and high-quality technical guarantees and technical support for the industrial production of modern duplex corundum, which has important practical significance and broad application prospects.

[0038] like Figure 2 As shown, preferably, in step S1, real-time collection of operating data of the dual-phase corundum crushing system further includes: Step S11: The three-phase current signal of the crusher drive motor is collected in real time by a current sensor installed on the crusher main shaft, and the current spectrum characteristics of the three-phase current signal are analyzed by fast Fourier transform to extract the fundamental and harmonic components.

[0039] In step S12, vibration signals from the bearing seat of the dual-phase corundum crushing system are collected in three directions using a vibration acceleration sensor. The frequency of the sampled vibration signals is greater than or equal to 10 kHz. Step S12 is used to calculate the effective value and characteristic frequency amplitude of the vibration signal of the dual-phase corundum crushing system.

[0040] Step S13: Scan the raw materials of the dual-phase corundum crushing system online using a laser particle size analyzer to obtain feed particle size distribution data at regular intervals. For example, the feed particle size distribution data includes characteristic particle sizes such as D10, D50, and D90.

[0041] In step S14, the three-phase current signal, the vibration signal and the feed particle size distribution data are transmitted to a host computer via industrial Ethernet. The host computer is connected to the dual-phase corundum crushing system for optimization. The host computer is used to pre-process the received data.

[0042] The optimization technology solution provided in steps S11 to S14 uses sensors to collect real-time operating data of the dual-phase corundum crushing system, and transmits the above-mentioned sensor data to the host computer via industrial Ethernet for preprocessing, providing comprehensive, accurate, and real-time data support for the subsequent optimization algorithm, ensuring that the optimization model can accurately adjust parameters and make optimization decisions based on the latest system status. During the process of steps S11 to S14, the motor operating status can be accurately monitored. Real-time current monitoring can provide real-time data on motor operation, laying a data foundation for the optimization model to adjust the crushing parameters. Vibration acceleration sensors can also be used to collect vibration signals in three directions of the crushing system bearing seat and calculate their effective value and characteristic frequency amplitude. This can effectively assess the mechanical health of the crushing system and provide the optimization model with health indicator data of the crushing system, which helps to dynamically adjust the crushing parameters and avoid production interruptions due to equipment failure.

[0043] The optimization technology provided in steps S11 through S14 also achieves the goal of precisely controlling the crushing process. A laser particle size analyzer scans the raw materials online to obtain feed particle size distribution data. Based on this feed particle size distribution, the optimization model dynamically adjusts the crushing parameters to ensure that the crushed material particle size meets preset standards, thereby improving the particle size qualification rate and ensuring the stability of product quality. Particle size distribution data is a key indicator of the crushing process. By monitoring this data in real time, the optimization model can dynamically adjust the crushing parameters to ensure the uniformity and consistency of the output particle size distribution, thereby improving product quality.

[0044] During the operations from step S11 to step S14, the host computer, as the control unit of the optimized crushing system, can perform real-time analysis and processing of the received data, provide a computing platform and data support for subsequent optimization algorithms, realize efficient integration and transmission of sensor data and computing data, ensure that the optimization model can make optimization decisions based on the latest system status, avoid optimization deviations caused by data delays or inaccuracies, and improve the overall performance of the system.

[0045] In summary, the optimization technical solution provided by steps S11 to S14 provides comprehensive, accurate, and real-time data support for the optimization model by collecting multi-dimensional operating data in real time and transmitting it to the host computer for preprocessing. It not only improves the operating efficiency and reliability of the crushing system, but also significantly improves the stability of product quality and the service life of the equipment, providing a data basis for the optimization of the duplex corundum crushing system.

[0046] Preferably, in step S14, during the host computer's preprocessing of the received data, timestamp alignment is used to ensure data synchronization among the three-phase current signal, vibration signal, and feed particle size distribution data. The crushing parameters of the dual-phase corundum crushing system include crusher current, vibration signal, feed rate, and discharge particle size distribution data. Step S14 uses timestamp alignment to preprocess the received multi-source data (including the three-phase current signal, vibration signal, and feed particle size distribution data) via the host computer to ensure temporal synchronization among these different types and sources. Furthermore, the crushing parameters of the dual-phase corundum crushing system in step S14 primarily include crusher current, vibration signal, feed rate, and discharge particle size distribution data, providing an accurate and consistent data foundation for subsequent optimization models.

[0047] Step S14 uses timestamp alignment to ensure the temporal synchronization of the three-phase current signal, vibration signal, and feed particle size distribution data, preventing time differences between different data from potentially leading to erroneous associations and analysis results. The two-phase corundum crushing system belongs to a multi-source data fusion scenario, and the time synchronization of data is an important prerequisite for ensuring the accuracy of analysis. Timestamp alignment can ensure that at any given point in time, data such as current, vibration, and particle size distribution can correctly reflect the actual operating status of the crushing system, thereby providing reliable data support for the optimization model. Step S14 can ensure the accuracy and synchronization of the data, and the decision-making quality of the optimization model is guaranteed in step S14. Optimization and adjustment are carried out using high-quality data input, thereby improving crushing efficiency, reducing unit energy consumption, and increasing the particle size qualification rate, ultimately achieving overall system performance improvement.

[0048] like Figure 3 As shown, preferably, in step S2, according to the ratio data, the current optimal energy consumption and output ratio is calculated based on a multi-objective optimization algorithm, and the crushing parameters of the dual-phase corundum crushing system are adjusted accordingly according to the calculation result of the current optimal energy consumption and output ratio, further comprising: In step S21 , the obtained corundum and β-phase alumina in the dual-phase corundum are used as input variables of the optimization model, and a multi-objective optimization algorithm is used to perform multi-objective optimization. Specifically, the multi-objective optimization algorithm is an improved NSGA-III algorithm.

[0049] Step S22: Generate a candidate parameter set in the improved NSGA-III algorithm. The candidate parameter set includes three decision variables: crusher speed, roller gap, and classifier frequency. The initial population size of the candidate parameter set generated by the improved NSGA-III algorithm is 150-200. In step S23, the solution set of the candidate parameter set is divided into multiple frontier levels by non-dominated sorting, and an iterative calculation is performed using a reference point guided selection mechanism to maintain the population diversity in the algorithm.

[0050] Step S24: During the iterative calculation process, the feasibility of the combination of crushing parameters is checked, and after 80-120 iterations, the Pareto optimal solution set is output.

[0051] The optimization technology solution provided in steps S21 to S24 utilizes the improved NSGA-III algorithm to perform multi-objective optimization based on the ratio data of corundum and β-phase alumina in duplex corundum to dynamically adjust the crushing parameters of the crushing system, thereby achieving the optimal balance between crushing efficiency, unit energy consumption and particle size qualification rate. By generating a candidate parameter set, performing non-dominated sorting, adopting a reference point-guided selection mechanism, and performing feasibility verification, the algorithm can efficiently generate a Pareto optimal solution set, providing a scientific basis for the optimization of the crushing system.

[0052] The improved NSGA-III algorithm is a multi-objective optimization genetic algorithm based on a reference point selection strategy. This algorithm improves upon the traditional NSGA-II algorithm and is better suited to multi-objective optimization problems, especially complex ones with a large number of objectives. Based on the principles of a reference point mechanism, non-dominated sorting, population diversity maintenance, and adaptive normalization, the improved NSGA-III algorithm introduces a set of predefined reference points distributed in a normalized objective space to guide the population toward a uniformly distributed Pareto front. The setting of reference points can ensure that the algorithm maintains the diversity of solutions in the high-dimensional target space and avoid the population from converging to the local optimum too early. The improved NSGA-III algorithm uses non-dominated sorting to divide the population into different frontier levels. The population members of each level are assigned to different levels according to their non-dominated relationships, so that the algorithm can dynamically adjust the distribution of the population to ensure that the diversity of the population is maintained during the optimization process. The application of this algorithm can find a more comprehensive set of optimal solutions in complex multi-objective problems. In the middle and late stages of population evolution, the position and number of reference points can be dynamically adjusted according to the distribution characteristics of the population in the target space to adapt to changes in population size and Pareto frontier surface.

[0053] Steps S21 to S24 can realize multi-objective optimization and achieve reliable optimization results through efficient parameter search. By taking the ratio data of corundum and β-phase alumina in duplex corundum as the input variable of the optimization model, the improved NSGA-III algorithm can accurately perform multi-objective optimization solutions, which not only considers the crushing efficiency, but also takes into account the unit energy consumption and particle size qualification rate, avoiding the one-sidedness that may be caused by single-objective optimization. It can optimize multiple objective functions at the same time, ensuring that energy consumption is reduced and the particle size qualification rate is increased while improving the crushing efficiency.

[0054] In some embodiments, the improved NSGA-III algorithm generates a candidate parameter set with an initial population size of 150-200. The solution set is divided into multiple frontier levels through non-dominated sorting, and an iterative calculation is performed using a reference point-guided selection mechanism. This allows for efficient search for the optimal solution set, maintains population diversity, and prevents the algorithm from falling into a local optimum. Different solution spaces are explored in each iteration to find a more comprehensive optimal solution set. During the iterative calculation process, a feasibility check is also performed on the combination of crushing parameters to ensure that the generated solution set is feasible in practical applications. After 80-120 iterations, the Pareto optimal solution set is output, providing a reliable data basis for parameter adjustment of the crushing system. The feasibility check ensures that the optimization result is not only optimal in theory, but also feasible in practical applications. Through multiple iterations, the algorithm can gradually approach the global optimal solution, thereby improving the reliability of the optimization result.

[0055] The Pareto optimal solution set, also called the Pareto frontier or the Pareto set, is a set of solutions in a multi-objective optimization problem. The obtained solutions are non-dominated in all objective functions because there is usually no single optimal solution in a multi-objective optimization problem and there may be conflicts between different objective functions. The Pareto optimal solution set provides a set of solutions that weigh different objective functions. Through steps S21 to S24, a solution can be selected from the set of solutions of different objective functions according to the essence of the technical solution to form an optimal decision. Based on the Pareto optimal solution set, steps S21 to S24 dynamically adjust the crushing parameters of the crushing system so that the crusher speed, roller gap and classifier frequency always operate in the optimal state. Based on the dynamic adjustment mechanism, it can adapt to changes in material properties and operating conditions during the crushing process, ensure the efficient operation of the system, and can dynamically adjust and control the duplex corundum system according to the latest operating data and material properties to ensure that it is in the optimal state, thereby improving production efficiency and product quality.

[0056] For example, in step S24, during the iterative calculation process, the feasibility of the combination of crushing parameters is checked. After 80-120 iterations, the Pareto optimal solution set is output, specifically: In the improved NSGA-III algorithm, the host computer of the two-phase corundum crushing system randomly generates the initial population. Each individual parameter of the initial population includes three decision variables: crusher speed, roller gap, and classifier frequency. The speed ranges from 800 to 1200 rpm, the roller gap ranges from 0.1 to 0.5 mm, and the classifier frequency ranges from 30 to 60 Hz. The initial population contains 150 to 200 individual parameters.

[0057] By randomly generating an initial population containing 150-200 individual parameters, each of which contains three decision variables, the algorithm can start the optimization process from a diverse set of initial solutions. The diverse initial population helps the algorithm explore different solution spaces during the optimization process, avoiding falling into local optimality, and can cover a wider range of solution spaces, providing the algorithm with more exploration directions, thereby increasing the possibility of finding the global optimal solution. By increasing the reasonable range of decision variables, it can avoid generating unrealistic solutions and ensure the feasibility and effectiveness of the optimization results in practical applications.

[0058] like Figure 4 As shown, preferably, in step S3, a non-dominated sorting genetic algorithm NSGA-II is used in the optimization model to solve the multi-objective optimization problem of the optimization model, further comprising: Step S31 : constructing an optimization model including three objective functions, and using a non-dominated sorting genetic algorithm NSGA-II to solve the multi-objective optimization problem.

[0059] Step S32: setting the initial population size and individual codes in the optimization model, and establishing a crushing system operation prediction sub-model based on the historical operation data of the two-phase corundum crushing system.

[0060] In step S33, the host computer collects the current operation data in real time, performs incremental learning on the crushing system operation prediction sub-model, and updates the model parameters.

[0061] Step S34: perform a credibility assessment on the prediction results output by the crushing system operation prediction sub-model. When the deviation between the predicted value and the actual measured value exceeds 5% for three consecutive times, the model retraining process is triggered.

[0062] Steps S31 to S34 achieve intelligent optimization of the dual-phase corundum crushing system by constructing a multi-objective optimization model and solving it using the NSGA-II algorithm, combined with a dynamically updated prediction sub-model and a credibility assessment mechanism. This not only improves the operating efficiency and stability of the system, but also ensures the accuracy and reliability of the optimization decision. The multi-objective optimization algorithm can optimize multiple objective functions simultaneously, ensuring that while improving the crushing efficiency, energy consumption is reduced and the particle size qualification rate is increased. The crushing system operation prediction sub-model established based on historical operation data can perform incremental learning and parameter updates through real-time collected operation data. The incremental learning of real-time data enables the prediction model to continuously adjust its own parameters and reflect the latest operating status of the corundum crushing system. That is, the dynamic update mechanism can effectively respond to uncertainties and changes in system operation, and the credibility assessment mechanism can promptly detect deviations in the prediction model and correct them by retraining the model.

[0063] Exemplarily, the optimization model constructed in step S31 includes three objective functions, specifically: The first objective function is defined as the ratio of the actual processing volume to the rated capacity of the system, which is calculated by the feed rate and effective operation time collected in real time; The second objective function is the unit energy consumption, which is calculated by multiplying the integral of the current and voltage of the crusher drive motor by the total mass of the processed material; The third objective function is the particle size qualification rate, which is obtained by calculating the conformity of the discharge particle size distribution with the preset standard range.

[0064] An optimization model that integrates three objective functions can comprehensively evaluate and optimize the performance of a duplex corundum crushing system. It comprehensively considers multiple key performance indicators across multiple models, ensuring improved production efficiency while reducing energy consumption and enhancing product quality, thereby achieving overall system optimization. For example, the first objective function ensures the system operates efficiently by real-time monitoring of production efficiency, allowing timely adjustments to production parameters to address fluctuations in the production process, thereby improving the system's overall production efficiency. The second objective function calculates the unit energy consumption by multiplying the current and voltage product of the crusher drive motor and dividing it by the total mass of the processed material, enabling precise management of the duplex corundum crushing system's energy consumption. The third objective function calculates the particle size qualification rate by comparing the conformity of the output particle size distribution with the preset standard range. This ensures stable control of product quality and helps ensure that the product's particle size distribution meets the preset standard. By comprehensively evaluating and optimizing the performance of the duplex corundum crushing system, these three objective functions achieve comprehensive optimization of production efficiency, energy consumption, and product quality.

[0065] like Figure 5 As shown, illustratively, in step S32, the initialization population size and individual code in the optimization model are set, and a crushing system operation prediction sub-model is established based on the historical operation data of the two-phase corundum crushing system, specifically: Step S321 : Initialize the population size to 100-150 individuals, and each individual code includes a three-dimensional real number vector consisting of the crusher speed, roller press pressure, and classifier frequency.

[0066] Step S322: Set the crossover probability to 0.85 and the mutation probability to 0.1 in the prediction sub-model, and use the simulated binary crossover operator to perform gene recombination.

[0067] Step S323: After completing the gene recombination, the corresponding parameter combination is generated for each individual code in each generation of evolution. The values ​​of each objective function are predicted through the established digital twin model of the crushing process to obtain the crushing system operation prediction sub-model.

[0068] The optimization technology provided in steps S321 to S323 ensures sufficient diversity in the algorithm at the beginning of optimization by properly initializing the population size and individual encoding method, thereby improving the algorithm's global search capability and laying the foundation for finding a more optimal solution set. Setting the crossover probability to 0.85 and the mutation probability to 0.1 in the prediction submodel and using a simulated binary crossover operator for genetic recombination can effectively simulate the evolution of the population, helping the algorithm to gradually evolve towards a more optimal solution set while maintaining population diversity.

[0069] The prediction sub-model is established based on historical operating data and the system's current operating status data. It is used to predict and optimize the operating status of the duplex corundum crushing system under different parameter settings. During the optimization process, the genetic algorithm NSGA-II is used to optimize the prediction sub-model parameters to find the optimal prediction sub-model operating parameters. This incorporates historical operating data of the duplex corundum crusher and combines it with current operating parameters (such as crusher speed, roller gap, and classifier frequency) to predict the system's operating status (such as crushing efficiency, specific energy consumption, and particle size qualification rate). This allows for rapid evaluation of system performance under different parameter settings, reducing the number of trials in actual operation. The optimization technology provided in steps S321 through S323 is based on the inheritance and mutation theories of genetic algorithms. By simulating genetic recombination and mutation in biological evolution and utilizing reasonable crossover and mutation probability settings, it balances the algorithm's exploration and development capabilities, improving optimization efficiency. The optimization technology solution provided in steps S321 to S323 also establishes a digital twin model, which is used to simulate the crushing process and predict system performance indicators (such as crushing efficiency, unit energy consumption, particle size qualification rate, etc.) under different parameter settings. The digital twin model can predict the system performance indicators in real time based on the current operating parameters, provide rapid feedback, reduce the number of tests in actual operation, and reduce test costs and time.

[0070] The digital twin model can predict system performance indicators based on the parameter combinations generated by the genetic algorithm, and use these performance indicators as feedback to the genetic algorithm, helping the genetic algorithm evaluate system performance under different parameter settings. By establishing a digital twin model of the crushing process and using it to predict the objective function value based on each individual parameter combination, a crushing system operation prediction sub-model was constructed. The prediction sub-model can predict the operating status of the duplex corundum system under different parameter settings based on historical operating data and real-time operating parameters, providing strong support for optimization decisions. The optimization process of the optimized prediction sub-model is based on the operating status of the duplex corundum crushing system, combining current and historical data to make decisions, rather than relying solely on historical data or actual operating results. This can respond more quickly to changes in the system's operating status, improve the foresight and adaptability of optimization decisions, and not only improve the global search capability and optimization efficiency of the optimization model, but also enhance the foresight and adaptability of optimization decisions, thus achieving intelligent optimization of the duplex corundum crushing system.

[0071] For the method steps disclosed in the above embodiments, for the purpose of simple description, the method steps are expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present application are not limited by the order of the actions described, because according to the embodiments of the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present application.

[0072] Any process or method description described in a flowchart or other manner can be understood as: a module, fragment or part of a code that includes one or more executable instructions for implementing a specific logical function or process step, and the scope of the preferred implementation of the embodiments of the present application includes alternative implementations, which may not be in the order shown or discussed, including executing and implementing functions in a substantially simultaneous manner or in the opposite order according to the functions involved, or executing computer instructions and implementing corresponding functions according to program structures such as loops and branches, which can naturally be understood by those skilled in the art when implementing the embodiments of the present application.

[0073] like Figure 6 As shown, the embodiment of the present application further provides a dual-phase corundum crushing system optimization device based on a composite granulation process, which is used to implement the dual-phase corundum crushing system optimization method based on a composite granulation process in any specific embodiment of the embodiment of the present application, including: The duplex corundum crushing system data acquisition module is used to collect the operating data of the duplex corundum crushing system in real time. The operating data includes at least: crusher current, vibration signal, feed particle size distribution, discharge particle size distribution, equipment temperature, and obtain the ratio data of corundum and β-phase alumina in the duplex corundum.

[0074] The dual-phase corundum crushing parameter adjustment module is used to calculate the current optimal energy consumption and output ratio based on the ratio data and a multi-objective optimization algorithm, and adjust the crushing parameters of the dual-phase corundum crushing system accordingly according to the calculation result of the current optimal energy consumption and output ratio.

[0075] The dual-phase corundum crushing system optimization model construction module is used to construct an optimization model for the dual-phase corundum crushing system. The parameters of the optimization model include crushing efficiency, unit energy consumption and particle size qualification rate. In the optimization model, a non-dominated sorting genetic algorithm is used to solve the multi-objective optimization problem of the optimization model. The multi-objective optimization problem specifically provides a balance solution for crushing efficiency, unit energy consumption and particle size qualification rate through an optimal solution set.

[0076] The dual-phase corundum crushing system adjustment module is used to update the parameters of the dual-phase corundum crushing system at regular intervals according to the optimization strategy generated by the balance plan, and adjust the roller mill pressure of the dual-phase corundum crushing system.

[0077] The embodiments of the system described above are merely illustrative. For example, the various functional modules, units, or subsystems in the system may or may not be physically separate, or may or may not be physical units, that is, they may be located in the same place or distributed across multiple different systems and their subsystems or modules. Those skilled in the art may select some or all of the functional modules, units, or subsystems according to actual needs to achieve the purpose of the embodiments of the present application. For the above-mentioned situations, those of ordinary skill in the art can understand and implement them without inventive work.

[0078] like Figure 7 As shown, the embodiment of the present application provides a method and device for optimizing a dual-phase corundum crushing system based on a composite granulation process, and also provides corresponding electronic equipment and storage media: An electronic device comprises: a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of a method for optimizing a dual-phase corundum crushing system based on a composite granulation process.

[0079] A computer-readable storage medium stores a computer program executable by an electronic device. When the computer program runs on the electronic device, the electronic device executes the steps of a method for optimizing a dual-phase corundum crushing system based on a composite granulation process.

[0080] like Figure 7As shown, device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory 602 (ROM) or a computer program loaded from a storage unit 608 into a random access memory 603 (RAM). Various programs and data required for the operation of device 600 can also be stored in the RAM. The computing unit 601, ROM, and RAM are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0081] Multiple components in device 600 are connected to I / O interface 605, including: input unit 606, such as a keyboard, mouse, etc.; output unit 607, such as various types of displays, speakers, etc.; storage unit 608, such as a magnetic disk, optical disk, etc.; and communication unit 609, such as a network card, modem, wireless communication transceiver, etc. Communication unit 609 allows device 600 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0082] The computing unit 601 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 601 executes the various methods described above, such as the method for optimizing a dual-phase corundum crushing system based on a composite granulation process. For example, in some embodiments, the method for optimizing a dual-phase corundum crushing system based on a composite granulation process can be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as a storage unit 608. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the method for optimizing a dual-phase corundum crushing system based on a composite granulation process described above can be performed. Alternatively, in other embodiments, the computing unit 601 may be configured in any other appropriate manner (for example, by means of firmware) to execute the dual-phase corundum crushing system optimization method based on the composite granulation process.

[0083] Various embodiments of the systems and techniques described above can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0084] The program code for implementing the methods of the embodiments of the present application can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other dual-phase corundum crushing system optimization device based on a composite granulation process, so that when the program code is executed by the processor or controller, the functions / operations specified in the flow charts and / or block diagrams are implemented. The program code can be executed entirely on the machine, partially on the machine, as a standalone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0085] In the context of the present application embodiment, machine-readable medium can be a tangible medium that can contain or store a program for use by an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable medium can include but is not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0086] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0087] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0088] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact through a communication network. The client-server relationship arises through computer programs running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, a server in a distributed system, or a server integrated with a blockchain.

[0089] It should be understood that the various forms of processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the embodiments of the present application can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in the embodiments of the present application can be achieved, and this document is not limited here.

[0090] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of the description of the embodiments of this application.

[0091] In the description of the embodiments of the present application, reference to the terms "one embodiment," "example," "specific example," etc., means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the embodiments of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any appropriate manner in any one or more embodiments or examples.

[0092] In addition, the technical solutions between the various implementation methods of the embodiments of the present application can be combined with each other, but it must be based on the fact that ordinary technicians in this field can implement it. When the combination of technical solutions is mutually contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the embodiments of the present application.

[0093] All features disclosed in the embodiments of the present application, or steps in all disclosed methods or processes, except for mutually exclusive features and / or steps, can be combined in any way. Any feature disclosed in the specification of the embodiments of the present application, unless otherwise stated, can be replaced by other alternative features that are equivalent or have similar purposes. That is, unless otherwise stated, each feature is just an example in a series of equivalent or similar features. Throughout the specification, the same reference numerals indicate the same elements.

[0094] Those skilled in the art will appreciate that the modules in the devices of the embodiments can be adaptively modified and installed in one or more devices different from the embodiments. Modules, units, or components in the embodiments can be combined into a single module, unit, or component, and furthermore, they can be divided into multiple sub-modules, sub-units, or sub-components. All features disclosed in the specification of the embodiments of this application (including the corresponding claims, abstract, and drawings), as well as all processes or units of any method or device disclosed therein, can be combined in any combination, except where at least some of such features and / or processes or units are mutually exclusive. Unless expressly stated otherwise, each feature disclosed in the specification of the embodiments of this application (including the corresponding claims, abstract, and drawings) may be replaced by an alternative feature that provides the same, equivalent, or similar purpose.

[0095] Finally, it should be noted that the above embodiments are intended only to illustrate the technical solutions of the embodiments of the present application, and are not intended to limit them. Although the embodiments of the present application have been described in detail with reference to the above embodiments, those skilled in the art should understand that they may still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents, and such modifications or replacements do not deviate from the essence of the corresponding technical solutions within the scope of the specific implementation methods of the embodiments of the present application.

Claims

1. A method for optimizing a dual-phase corundum crushing system based on a composite granulation process, characterized in that: include: Real-time collection of operating data of the duplex corundum crushing system, the operating data including at least: crusher current, vibration signal, feed particle size distribution, discharge particle size distribution, equipment temperature, and obtaining data on the ratio of corundum to β-phase alumina in the duplex corundum; According to the ratio data, the current optimal energy consumption and output ratio is calculated based on a multi-objective optimization algorithm, and the crushing parameters of the dual-phase corundum crushing system are adjusted accordingly according to the calculation result of the current optimal energy consumption and output ratio; An optimization model for a dual-phase corundum crushing system is constructed, wherein the parameters of the optimization model include crushing efficiency, specific energy consumption, and particle size qualification rate. A non-dominated sorting genetic algorithm is used in the optimization model to solve a multi-objective optimization problem of the optimization model. The multi-objective optimization problem specifically provides a balance solution for crushing efficiency, specific energy consumption, and particle size qualification rate through an optimal solution set. According to the optimization strategy generated by the balance scheme, the parameters of the two-phase corundum crushing system are updated at regular intervals, and the roller mill pressure of the two-phase corundum crushing system is adjusted.

2. The method for optimizing a dual-phase corundum crushing system based on a composite granulation process according to claim 1, characterized in that: The real-time collection of operating data of the dual-phase corundum crushing system further includes: The current sensor installed on the main shaft of the crusher collects the three-phase current signal of the crusher drive motor in real time, analyzes the current spectrum characteristics of the three-phase current signal by fast Fourier transform, and extracts the fundamental and harmonic components; The vibration acceleration sensor is used to collect vibration signals in three directions of the bearing seat of the dual-phase corundum crushing system. The frequency of the sampled vibration signals is greater than or equal to 10kHz. The raw materials of the duplex corundum crushing system are scanned online by a laser particle size analyzer to obtain the feed particle size distribution data at certain intervals; The three-phase current signal, vibration signal and feed particle size distribution data are transmitted to a host computer via industrial Ethernet. The host computer is optimally connected to the two-phase corundum crushing system, and the host computer is used to pre-process the received data.

3. The method for optimizing the dual-phase corundum crushing system based on the composite granulation process according to claim 2, characterized in that: During the preprocessing of the received data by the host computer, a timestamp alignment method is used to ensure the data synchronization of the three-phase current signal, the vibration signal and the feed particle size distribution data; The crushing parameters of the dual-phase corundum crushing system include: crusher current, vibration signal, feed rate, and output particle size distribution data.

4. The method for optimizing a dual-phase corundum crushing system based on a composite granulation process according to claim 1, wherein: The method further includes calculating the current optimal energy consumption and output ratio based on the multi-objective optimization algorithm according to the ratio data, and adjusting the crushing parameters of the dual-phase corundum crushing system according to the calculation result of the current optimal energy consumption and output ratio. The obtained corundum and β-phase alumina in the dual-phase corundum are used as input variables of the optimization model, and a multi-objective optimization algorithm is used to perform multi-objective optimization. The multi-objective optimization algorithm is specifically an improved NSGA-III algorithm; Generating a candidate parameter set in the improved NSGA-III algorithm, wherein the candidate parameter set includes three decision variables: crusher speed, roller gap, and classifier frequency; The solution set of candidate parameter sets is divided into multiple frontier levels through non-dominated sorting, and the iterative calculation is performed using a reference point guided selection mechanism; During the iterative calculation process, the feasibility of the combination of crushing parameters is checked, and after 80-120 iterations, the Pareto optimal solution set is output.

5. The method for optimizing a dual-phase corundum crushing system based on a composite granulation process according to claim 4, characterized in that: During the iterative calculation process, the feasibility of the combination of crushing parameters is checked, and after 80-120 iterations, the Pareto optimal solution set is output, which further includes: In the improved NSGA-III algorithm, the host computer of the two-phase corundum crushing system randomly generates an initial population. The parameters of each individual in the initial population include three decision variables: crusher speed, roller gap, and classifier frequency. The speed ranges from 800 to 1200 rpm, the roller gap ranges from 0.1 to 0.5 mm, and the classifier frequency ranges from 30 to 60 Hz.

6. The method for optimizing a dual-phase corundum crushing system based on a composite granulation process according to claim 1, characterized in that: The method of using a non-dominated sorting genetic algorithm in the optimization model to solve the multi-objective optimization problem of the optimization model further includes: An optimization model including three objective functions is constructed, and a non-dominated sorting genetic algorithm is used to solve the multi-objective optimization problem; The initial population size and individual coding in the optimization model are set, and a crushing system operation prediction sub-model is established based on the historical operation data of the two-phase corundum crushing system; The host computer collects the current operating data in real time, performs incremental learning on the crushing system operation prediction sub-model, and updates the model parameters; The credibility of the prediction results output by the crushing system operation prediction sub-model is evaluated. When the deviation between the predicted value and the actual measured value exceeds 5% for three consecutive times, the model retraining process is triggered.

7. The method for optimizing a dual-phase corundum crushing system based on a composite granulation process according to claim 6, wherein: The construction includes an optimization model with three objective functions, specifically: A first objective function, wherein the first objective function is defined as a ratio of actual processing capacity to the rated capacity of the system, and is calculated by using a feed rate and effective operating time collected in real time; A second objective function, which is a specific energy consumption, is calculated by multiplying the integral of the current and voltage of the crusher drive motor by the total mass of the processed material; The third objective function is the particle size qualification rate, which is obtained by calculating the conformity of the discharge particle size distribution with the preset standard range.

8. The method for optimizing a dual-phase corundum crushing system based on a composite granulation process according to claim 6, characterized in that: The initialization population size and individual code in the setting optimization model are set, and a crushing system operation prediction sub-model is established based on the historical operation data of the two-phase corundum crushing system, specifically: The initial population size is set to 100-150 individuals, and the code of each individual includes a three-dimensional real number vector consisting of crusher speed, roller press pressure and classifier frequency; In the prediction sub-model, the crossover probability was set to 0.85 and the mutation probability was set to 0.1, and the simulated binary crossover operator was used for gene recombination; After completing genetic recombination, the corresponding parameter combination is generated for each individual encoding in each generation of evolution. The digital twin model of the crushing process is established to predict the values ​​of each objective function and obtain the crushing system operation prediction sub-model.

9. A dual-phase corundum crushing system optimization device based on a composite granulation process, characterized in that: The method for optimizing a dual-phase corundum crushing system according to any one of claims 1 to 9 comprises: A data acquisition module for the duplex corundum crushing system is used to collect real-time operating data of the duplex corundum crushing system, the operating data including at least: crusher current, vibration signal, feed particle size distribution, discharge particle size distribution, equipment temperature, and obtain the ratio of corundum to β-phase alumina in the duplex corundum; a dual-phase corundum crushing parameter adjustment module, configured to calculate the current optimal energy consumption and output ratio based on the ratio data and a multi-objective optimization algorithm, and adjust the crushing parameters of the dual-phase corundum crushing system accordingly according to the calculation result of the current optimal energy consumption and output ratio; A module for constructing an optimization model for a dual-phase corundum crushing system is used to construct an optimization model for the dual-phase corundum crushing system. The parameters of the optimization model include crushing efficiency, specific energy consumption, and particle size qualification rate. A non-dominated sorting genetic algorithm is used in the optimization model to solve the multi-objective optimization problem of the optimization model. The multi-objective optimization problem specifically provides a balance solution for crushing efficiency, specific energy consumption, and particle size qualification rate through an optimal solution set. The dual-phase corundum crushing system adjustment module is used to update the parameters of the dual-phase corundum crushing system at regular intervals according to the optimization strategy generated by the balance plan, and adjust the roller mill pressure of the dual-phase corundum crushing system.

10. An electronic device, characterized in that: include: A processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the steps of the method according to any one of claims 1 to 8.

Images