A large model-based grinding optimization processing system

Abstract

The application discloses a kind of based on big model's grinding optimization processing system, the system includes: semi-autogenous mill optimization algorithm processing module, for semi-autogenous mill optimization algorithm utilizes optimization algorithm to process, obtains optimization node;Semi-autogenous mill pretreatment module is used to realize man-machine interaction front end semi-autogenous mill parameter, variable iteration, remote semi-autogenous mill automatic monitoring, semi-autogenous mill input variable pretreatment and normal running semi-autogenous mill connection;Big model fuzzy expert system module is used to provide the experience rule of depth learning optimization algorithm and semi-autogenous mill fuzzy logic to carry out data processing;Semi-autogenous mill parameter configuration selection module is used to carry out the configuration of the working mode of semi-autogenous mill optimization algorithm under different parameters, the present application meets the urgent needs of high-efficiency, intelligent grinding technology for mining industry, also lays a solid foundation for the development of future grinding optimization technology.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of semi-autogenous grinding mill optimization, and in particular to a large model-based grinding optimization processing system. BACKGROUND

[0002] In recent years, due to the gradual decrease of mineral resources and the continuous reduction of ore grade, improving ore processing efficiency and reducing energy consumption has become a key issue in the mining industry. SAG (Semi-Autogenous Grinding) semi-autogenous grinding mill has received widespread attention due to its high ore processing capacity. However, the grinding process is affected by various factors such as ore hardness, mill load, ball filling rate, etc., making its running state highly complex, thus increasing the difficulty of grinding optimization.

[0003] To address this challenge, the industry has developed a series of grinding optimization technologies based on fuzzy control and expert systems. At the current technical level, these technologies have been able to effectively simulate the decision-making process of human experts and use fuzzy logic to fuzz the real-time monitored grinding data, then adjust the control parameters to optimize the grinding effect. However, the performance of existing technologies is still limited by the limitations of fuzzy logic and fixed experience rules. For example, fuzzy logic may not be accurate enough when facing complex grinding processes. When the characteristics of the ore or the state of the grinding equipment change, these systems based on fixed experience rules may not be able to adaptively adjust. In addition, a large amount of data is collected in the modern mining environment, but traditional fuzzy logic and expert systems may not be efficient enough in processing, analyzing, and utilizing these data, resulting in their inability to fully exploit the information in big data. The grinding efficiency is not high enough to meet the current industrial needs, therefore, the present application proposes a large model-based grinding optimization processing system SUMMARY

[0004] In order to overcome the shortcomings and deficiencies of the prior art, the present application provides a large model-based grinding optimization processing system. The technical scheme adopted by the present application is as follows:

[0005] A large model-based grinding optimization processing system is provided, which includes:

[0006] A semi-autogenous grinding mill optimization algorithm processing module is used to process the semi-autogenous grinding mill optimization algorithm using an optimization algorithm to obtain an optimization node.

[0007] A semi-autogenous grinding mill preprocessing module is used to realize human-computer interaction front-end semi-autogenous grinding mill parameter, variable iteration, remote semi-autogenous grinding mill automatic monitoring, semi-autogenous grinding mill input variable preprocessing, and normal running semi-autogenous grinding mill connection.

[0008] The big model fuzzy expert system module is configured to provide a deep learning optimization algorithm and an empirical rule of semi-autogenous mill fuzzy logic for data processing.

[0009] The semi-autogenous mill update optimization module is configured to apply and monitor the semi-autogenous mill optimization algorithm under different models, the big model fuzzy expert system module, and the semi-autogenous mill scheduling optimization algorithm library in the whole process.

[0010] The semi-autogenous mill parameter configuration selection module is configured to configure the working mode of the semi-autogenous mill optimization algorithm under different parameters.

[0011] In an alternative embodiment, the semi-autogenous mill optimization algorithm processing module comprises:

[0012] The optimization algorithm integration module is configured to provide transceiving, control server, optimization algorithm saving, optimization algorithm clustering, optimization algorithm calculation, and optimization algorithm coding.

[0013] The optimization algorithm processing module is configured to process a mass of semi-autogenous mill optimization algorithms under different models and provide an optimization algorithm running environment.

[0014] The optimization algorithm evaluation module comprises an optimization algorithm screening, a redundant algorithm adjustment component, and an optimization algorithm evaluation.

[0015] The grinding efficiency per unit time optimization module is configured to optimize the working efficiency per unit time in the semi-autogenous mill application process.

[0016] The grinding fault influence module is configured to statistically analyze and predict the influence of grinding faults.

[0017] In an alternative embodiment, the semi-autogenous mill optimization algorithm processing module comprises

[0018] The basic optimization algorithm library is configured to store remote semi-autogenous mill field basic optimization algorithms.

[0019] The semi-autogenous mill big model clustering component is configured to cluster, encrypt, and package remote semi-autogenous mill field basic optimization algorithms.

[0020] The redundant algorithm adjustment component is configured to adjust redundant algorithms according to existing semi-autogenous mill industry optimization algorithm standards and self-defined standards.

[0021] The optimization algorithm code management component is configured to directly extract optimization algorithms in the basic optimization algorithm library and periodically regulate and control grinding efficiency, so that the system can quickly call optimization algorithms in the basic optimization algorithm library according to requirements.

[0022] In an alternative embodiment, the semi-autogenous mill preprocessing module comprises:

[0023] The semi-autogenous mill initial automated monitoring AI module is used to realize the automated monitoring of the semi-autogenous mill, the transmission of useful power data of the semi-autogenous mill, the configuration of operating parameters, the preprocessing of input variables of the semi-autogenous mill, and the integrated AI hazard warning.

[0024] The semi-autogenous mill automated monitoring module is used by grinding engineers and safety monitoring personnel to master the unit time optimization algorithm of the semi-autogenous mill under different loads, and to provide manual instructions for the operation of the semi-autogenous mill.

[0025] The semi-autogenous mill decision-making section input variable preprocessing module is used to transmit the useful power data of the semi-autogenous mill based on the semi-autogenous mill equipment management, ore hardness, ore type, and grinding fault impact of the semi-autogenous mill decision-making section, so as to achieve the accuracy of semi-autogenous mill parameter and variable iteration;

[0026] The system management module is used to maintain the normal operation of all parameters in the system and to maintain the stability of the system.

[0027] In one optional embodiment, the large model fuzzy expert system module includes:

[0028] A library of artificial fusion optimization algorithms, consisting of fuzzy expert system network optimization algorithms and hypergraph neural network optimization algorithms.

[0029] A fusion optimization algorithm library based on the configuration matching of semi-autogenous mill scheduling parameters.

[0030] In one optional embodiment, the semi-autogenous mill update and optimization module includes:

[0031] System original parameter settings, system optimization parameter settings, system account login, system scheduled maintenance, system link matching, system front-end expansion, system interface composition, system back-end changes and system front-end changes.

[0032] In one optional embodiment, the semi-autogenous mill initial automated monitoring AI module includes: a semi-autogenous mill management parameter optimization module, a new semi-autogenous mill target AI module, a system energy supply module, a system front-end module, a system parameter setting module, a semi-autogenous mill power transmission module, a semi-autogenous mill parameter intelligent calibration module, and a semi-autogenous mill conversion efficiency module.

[0033] In one optional embodiment, the semi-autogenous mill automated monitoring module includes: an automated monitoring efficiency module, a semi-autogenous mill pretreatment module, a remote management module, and a semi-autogenous mill power module.

[0034] In an optional embodiment, the semi-autogenous mill decision section input variable preprocessing module comprises a semi-autogenous mill equipment intelligent management module, a grinding task index analysis module, an ore type semi-autogenous mill useful power data transmission module, a semi-autogenous mill grinding speed benchmark setting module, a semi-autogenous mill distribution module, and a semi-autogenous mill de-muzzling management module.

[0035] The beneficial effects of the above technical solutions provided by the embodiments of the present application are as follows:

[0036] The system provided by the embodiments of the present application establishes an integrated framework of pipeline convergence, integration, processing and fusion of semi-autogenous mill optimization algorithm bodies under different models through the semi-autogenous mill optimization algorithm processing module, realizing integrated management of semi-autogenous mill field optimization algorithms with multiple optimization algorithm types and complex structures; the semi-autogenous mill preprocessing module realizes semi-autogenous mill parameter iteration before human-computer interaction, remote semi-autogenous mill automatic monitoring, semi-autogenous mill input variable preprocessing and normal operation semi-autogenous mill connection, and enhances the close connection of industry knowledge; the large model fuzzy expert system module fuses multi-parameter configuration automatic monitoring and control prediction technology based on large models and artificial intelligence, and forms a model end-to-end no-code custom development mode for semi-autogenous mill field use and different parameter configurations, providing deep learning optimization algorithms and semi-autogenous mill fuzzy logic experience rules for data processing; the semi-autogenous mill update optimization module applies and monitors the semi-autogenous mill optimization algorithm, the large model fuzzy expert system module and the semi-autogenous mill scheduling optimization algorithm library under different models; the semi-autogenous mill parameter configuration selection module configures the working mode of the semi-autogenous mill optimization algorithm under different parameters, solves the problem of few automatic optimization parameter configuration associations in semi-autogenous mill industry automatic monitoring, and realizes AI automatic monitoring of the semi-autogenous mill field through the cooperation of the above modules. The system provided by the embodiments of the present application plays an important role in the development of semi-autogenous mill industry automation and intelligence, and realizes effective optimization of the semi-autogenous mill. The present application provides a more advanced and reliable solution for the grinding industry. This not only meets the urgent needs of the mining industry for efficient and intelligent grinding technology, but also lays a solid foundation for the future development of grinding optimization technology. BRIEF DESCRIPTION OF DRAWINGS

[0037] Figure 1 The system structure diagram of the present application is shown in Figure 1.

[0038] Figure 2 The system use flowchart of the present application is shown in Figure 2. DETAILED DESCRIPTION

[0039] It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict, and the present application will be further described in detail below with reference to the drawings and specific embodiments.

[0040] The present application focuses on the grinding optimization process based on fuzzy logic and trusted large models. In the implementation process, it is essential to optimize and adjust the grinding operation in depth to ensure its efficient, safe and stable operation.

[0041] Please refer to Figure 1 The embodiment of the application provides a large model-based grinding optimization processing system, which comprises:

[0042] The semi-autogenous mill optimization algorithm processing module is used for processing the semi-autogenous mill optimization algorithm by using the optimization algorithm to obtain an optimized node.

[0043] The semi-autogenous mill preprocessing module is used for realizing the man-machine interaction front-end semi-autogenous mill parameter, variable iteration, remote semi-autogenous mill automatic monitoring, semi-autogenous mill input variable preprocessing and normal running semi-autogenous mill connection.

[0044] The large model fuzzy expert system module is used for providing data processing of the deep learning optimization algorithm and the experience rule of the semi-autogenous mill fuzzy logic.

[0045] The semi-autogenous mill update optimization module is used for applying and monitoring the semi-autogenous mill optimization algorithm, the large model fuzzy expert system module and the semi-autogenous mill scheduling optimization algorithm library in the whole process.

[0046] The semi-autogenous mill parameter configuration selection module is used for configuring the working mode of the semi-autogenous mill optimization algorithm under different parameters.

[0047] The above technical solutions provided by the embodiment of the application have the following beneficial effects:

[0048] The system provided by the embodiment of the application establishes an integrated framework of pipeline convergence, integration, processing and fusion of semi-autogenous mill optimization algorithm bodies under different models through the semi-autogenous mill optimization algorithm processing module, realizes integrated management of semi-autogenous mill field optimization algorithms with multiple types and complex structures, and enhances the close connection of industry knowledge through the semi-autogenous mill preprocessing module to realize human-machine interaction front-end semi-autogenous mill parameters, variable iteration, remote semi-autogenous mill automatic monitoring, semi-autogenous mill input variable preprocessing and normal operation semi-autogenous mill connection. The big model fuzzy expert system module fuses multi-parameter configuration automatic monitoring and control prediction technology based on a big model and artificial intelligence, forms an end-to-end no-code custom development mode for semi-autogenous mill field use and different parameter configurations, and provides deep learning optimization algorithm and semi-autogenous mill fuzzy logic experience rules for data processing. The semi-autogenous mill update optimization module applies and monitors the semi-autogenous mill optimization algorithm, the big model fuzzy expert system module and the semi-autogenous mill scheduling optimization algorithm library under different models. The semi-autogenous mill parameter configuration selection module configures the working mode of the semi-autogenous mill optimization algorithm under different parameters, solves the problem of few automatic optimization parameter configuration associations in semi-autogenous mill industry automatic monitoring, and realizes AI comprehensive management of semi-autogenous mill field automatic monitoring through cooperation of the above modules. The system provided by the embodiment of the application plays an important role in the development of semi-autogenous mill industry automation and intelligence, and achieves the purpose of effective optimization of the semi-autogenous mill.

[0049] The system provided by the embodiment of the application is further explained and described below through optional embodiments.

[0050] In an optional embodiment, the semi-autogenous mill optimization algorithm module comprises:

[0051] The optimization algorithm integration module provides multiple grinding speed resource grinding efficiency including transceiving of instructions, control server, optimization algorithm saving, optimization algorithm clustering, optimization algorithm calculation, artificial intelligence calculation and optimization algorithm grinding efficiency.

[0052] The optimization algorithm processing module is used for processing massive semi-autogenous mill optimization algorithm bodies under different models and providing an optimization algorithm running environment.

[0053] The optimization algorithm evaluation module comprises optimization algorithm screening, redundant algorithm adjustment components and optimization algorithm evaluation.

[0054] It should be noted that the optimization algorithm evaluation module is a core of a grinding optimization processing system based on a big model, and comprises optimization algorithm screening, redundant algorithm adjustment components and optimization algorithm evaluation.

[0055] Further, the optimization algorithm screening collected optimization algorithms are open knowledge optimization algorithms, including optimization algorithms through semi-autogenous mill professional field optimization algorithm library, semi-autogenous mill numerical simulation software and semi-autogenous mill Internet of Things, monitoring experimental optimization algorithms, including structured optimization algorithms such as dynamic automatic monitoring optimization algorithms and seismic inversion optimization algorithms; unstructured optimization algorithms form semi-autogenous mill large model clustering components, numerical simulation optimization algorithms, etc.

[0056] The redundant algorithm adjustment component mainly optimizes and fuses semi-autogenous mill optimization algorithms under different models, optimizes missing and redundant algorithms by using local optimization, global optimization and statistical methods, and correlates and fuses the optimized optimization algorithms by establishing professional use conditions for the semi-autogenous mill field, to form a core research optimization algorithm library, method library, achievement library and expert database.

[0057] The grinding efficiency unit time optimization module is used for unit time optimization of the working efficiency reduction in the semi-autogenous mill application process.

[0058] The grinding efficiency unit time optimization module is a unit time optimization module for the working efficiency reduction in the semi-autogenous mill application process.

[0059] In an optional embodiment, the grinding efficiency unit time optimization module includes a semi-autogenous mill upstream automatic monitoring development module, a semi-autogenous mill automatic monitoring module, a semi-autogenous mill decision section wisdom supervision module and a management module.

[0060] The grinding fault influence module is used for engineers and safety background monitoring personnel to realize the use of platform grinding efficiency functions and semi-autogenous mill optimization algorithms by different personnel.

[0061] The grinding fault influence module is used for statistics and prediction of grinding fault influence conditions.

[0062] In an optional embodiment, the semi-autogenous mill optimization algorithm processing module includes a basic optimization algorithm library for remote semi-autogenous mill field basic optimization algorithms.

[0063] The semi-autogenous mill large model clustering component is used for clustering and encrypting and packaging remote semi-autogenous mill field basic optimization algorithms.

[0064] The redundant algorithm adjustment component is used for adjusting redundant algorithms according to existing optimization algorithm standards and self-defined standards in the semi-autogenous mill industry.

[0065] The redundancy algorithm adjusting component adjusts the redundancy algorithm according to the existing optimization algorithm standard in the semi-autogenous mill industry and self-defined standard, searches for missing and abnormal problems in the optimization algorithm by using global optimization optimization algorithm, and performs completion and denoising of the optimization algorithm. The optimized optimization algorithm is evaluated through the respective quality evaluation system. The optimization algorithm that fails to pass the evaluation needs to be optimized again according to its field and optimization algorithm characteristics until it passes the optimization algorithm evaluation, so as to improve the quality of the optimization algorithm. Then, the optimized optimization algorithm entity is taken as a node, and the relationship between entities is taken as an edge. The use case of the semi-autogenous mill field is constructed through the experience knowledge of experts, and the optimization algorithm library of the semi-autogenous mill field is established.

[0066] The optimization algorithm code management component is used for directly extracting the optimization algorithm in the basic optimization algorithm library and periodically regulating the grinding efficiency, so that the system can quickly call the optimization algorithm in the basic optimization algorithm library according to the demand.

[0067] The optimization algorithm code management component can directly extract the optimization algorithm in the basic optimization algorithm library and periodically regulate the grinding efficiency. Each module in the application layer can quickly call the basic optimization algorithm interface according to its own demand. Finally, the application layer includes the grinding efficiency application, the optimization algorithm calling, the visual grinding efficiency, and the external grinding efficiency, which can directly call the core optimization algorithm that passes the optimization algorithm quality evaluation, the optimization algorithm library constructed by the semi-autogenous mill use case, and the semi-autogenous mill large model clustering component. The semi-autogenous mill optimization algorithm processing module realizes the integrated optimization algorithm management system of optimization algorithm integration-optimization-extraction-fusion.

[0068] In an optional embodiment, the semi-autogenous mill preprocessing module includes:

[0069] The semi-autogenous mill initial automatic monitoring AI module is used for realizing the semi-autogenous mill automatic monitoring, the semi-autogenous mill useful power data transmission, the operation parameter configuration, the semi-autogenous mill input variable preprocessing, and the AI integrated danger early warning.

[0070] In an optional embodiment, the semi-autogenous mill initial automatic monitoring AI module includes a semi-autogenous mill management parameter optimization module, a new semi-autogenous mill target AI module, a system energy consumption supply module, a system front-end module, a system parameter setting module, a semi-autogenous mill power transmission module, a semi-autogenous mill parameter intelligent calibration module, and a semi-autogenous mill conversion efficiency module.

[0071] The initial automatic monitoring AI module of the semi-autogenous mill mainly includes eight integrated optimization algorithm modules. Each functional module includes screening optimization algorithms and application examples corresponding to different parameter configurations, forming an integrated danger warning system from semi-autogenous mill automatic monitoring, semi-autogenous mill useful power data transmission, operation parameter configuration, AI integrated danger warning system.

[0072] The semi-autogenous mill automatic monitoring module is used by grinding engineers and safety background monitoring personnel to master the unit time optimization algorithm of the semi-autogenous mill under different loads, and to provide manual instructions for the operation of the semi-autogenous mill.

[0073] In an alternative embodiment, the semi-autogenous mill automatic monitoring module includes an automatic monitoring efficiency module, a semi-autogenous mill preprocessing module, a remote management module, and a semi-autogenous mill power module. The semi-autogenous mill automatic monitoring module is used by grinding engineers and safety background monitoring personnel to master the unit time optimization algorithm of the semi-autogenous mill from collection, transmission, and reception, and to provide manual instructions for the operation of the semi-autogenous mill.

[0074] The semi-autogenous mill decision segment input variable preprocessing module is used to transmit semi-autogenous mill useful power data based on semi-autogenous mill equipment management, ore hardness, ore type, and grinding fault influence quantity of the semi-autogenous mill decision segment, to realize the accuracy of semi-autogenous mill parameter and variable iteration.

[0075] In an alternative embodiment, the semi-autogenous mill decision segment input variable preprocessing module includes a semi-autogenous mill equipment intelligent management module, a grinding task index analysis module, an ore type semi-autogenous mill useful power data transmission module, a semi-autogenous mill grinding speed benchmark setting module, a semi-autogenous mill distribution module, and a semi-autogenous mill de-fuzzification management module.

[0076] The semi-autogenous mill decision segment input variable preprocessing module can understand detailed optimization algorithms of the semi-autogenous mill based on semi-autogenous mill equipment management, and is used for intelligent analysis and ore type semi-autogenous mill useful power data transmission based on the basic optimization algorithm, to realize semi-autogenous mill intelligent specification.

[0077] The system comprehensive management module is used to optimize the operation permissions of each module in the system facing different semi-autogenous mills.

[0078] In an alternative embodiment, the large model fuzzy expert system module includes:

[0079] The artificial fusion optimization algorithm library is composed of fuzzy expert system network optimization algorithms and hypergraph neural network algorithm optimization algorithms.

[0080] The large model fuzzy expert system module is composed of two parts. One part is an artificial fusion optimization algorithm library composed of fuzzy expert system network optimization algorithm and hypergraph neural network algorithm optimization algorithm. The fuzzy expert system network optimization algorithm library is based on different code running environments.

[0081] The fusion optimization algorithm library based on semi-autogenous mill scheduling parameter configuration matching.

[0082] The screening optimization algorithm based on semi-autogenous mill scheduling parameter configuration matching. The core idea is to take the fuzzy expert system network optimization algorithm as the basis, and take the optimization equation, boundary condition and initial condition in the hypergraph neural network algorithm optimization algorithm as the constraint to construct a new loss function and integrate it into the fuzzy expert system network optimization algorithm. Based on the development mode of the above optimization algorithm, the reservoir physical property semi-autogenous mill useful power data transmission, semi-autogenous mill parameter intelligent calibration, and fracturing effect intelligent evaluation are established. In addition, considering the programming ability of semi-autogenous mill personnel, an end-to-end no-code operation platform is established. The deep learning optimization algorithm and customized optimization algorithm are integrated and packaged into a structured optimization algorithm module, which is called through a drag-and-drop way. The front end triggers the optimization algorithm event by clicking the drag-and-drop icon, and the back end automatically builds the model according to the front-end response to realize the rapid assembly and pipeline calling mode of the optimization algorithm.

[0083] In an optional embodiment, the semi-autogenous mill parameter configuration selection module is used to configure the working mode of the semi-autogenous mill optimization algorithm under different parameters.

[0084] After logging in to the semi-autogenous mill platform, the required optimization algorithm set can be obtained through three ways of local uploading, online importing and network crawling. The uploaded optimization algorithm is temporarily saved in the background optimization algorithm library and is assigned a specific tag code. A large model grinding optimization processing system considers the complexity of semi-autogenous mill optimization algorithms and optimization algorithms in various industries, and constructs a model editor. The required optimization algorithm is imported on the editor, the corresponding optimization algorithm optimization algorithm is selected to improve the optimization algorithm quality, and the encapsulated optimization algorithm component library is configured under different parameters to configure the working mode of the semi-autogenous mill optimization algorithm. The graphical method better helps the semi-autogenous mill to establish a complex self-learning model, and the output result and application effect of the model can be seen through the visualization technology.

[0085] To ensure the quality and integrity of the data, the historical production data and real-time production data of this method come from the mining and metallurgical industry data collection management system. This system has been widely used in many mining and metallurgical industries and has been proven to be reliable and effective. Through this system, we can ensure the real-time collection of a large amount of raw data from the grinding equipment. These data cover various key parameters in the grinding process, such as ore hardness, mill power, etc.

[0086] The trusted large model is an important part of the grinding optimization link. Through the analysis of data components, it is found that the data structure is time series data (i.e. data arranged and processed in chronological order), which conforms to the training and prediction of the Transformer model (self-attention mechanism model). The outstanding performance of Transformer in time series data (such as its application in GPT base model, BERT model, etc., whose paper has been cited more than 20,000 times on Google Scholar) has proven the reliability of its structure. We designed a trusted large model structure suitable for grinding production data based on the Transformer model, and through model training on the collected data, we can ensure the credibility of the prediction results after the model verification stage.

[0087] As shown in Figure 2 , a large model-based grinding optimization processing system is provided, and the optimization process of the system is as follows:

[0088] A1, data preprocessing; the program performs data cleaning, standardization and normalization, etc. in this stage to ensure the integrity and accuracy of the data. The goal of this step is to remove noise and inconsistencies in the data, making it more suitable for subsequent processing.

[0089] A2, fuzzy processing; in this stage, the computer program performs fuzzy processing on the preprocessed data. The goal of this step is to convert specific numerical data into fuzzy sets, which can better handle the uncertainty and fuzziness in the grinding process. Fuzzy processing involves defining fuzzy sets and membership functions to convert the original data.

[0090] A3, real-time data stream inspection; to ensure the safe operation of the grinding equipment, a specially designed data stream protection module is used to perform real-time inspection of the data stream. This module can detect any potential anomalies or errors and terminate the processing flow if necessary. This not only ensures the safety of the equipment, but also avoids potential production losses.

[0091] A4, the optimization processing of data; the program first uses the fuzzy expert system to carry out the preliminary optimization processing to the data, to capture and process the fuzzy factor in the grinding process. Subsequently, a deep learning method based on the reliable large model is used to carry out the deep optimization processing to the data. This method can effectively capture the complex mode in the data, and provide more accurate optimization suggestions for the grinding operation.

[0092] A5, the output results are fused and defuzzified. The obtained output data can be directly used to guide the operation of the grinding equipment, to ensure the best running state thereof.

[0093] The optimization process of the system provided by the embodiment of the application comprises the upstream automatic monitoring development of the semi-autogenous mill, the full-load operation gathering and transportation, and the automatic monitoring and supervision of the lower stage, the semi-autogenous mill optimization algorithm under different models is processed in a process automation manner, and the working efficiency of the management personnel and the grinding efficiency personnel is improved.

[0094] In the description of the application, it should be noted that, unless otherwise explicitly specified and limited, the terms "arrangement", "installation", "connection", "connection", "fixing" should be understood in a broad sense, for example, it can be fixedly connected, or it can be detachably connected, or integrally connected, it can be mechanically connected, or it can be electrically connected, it can be directly connected, or it can be indirectly connected through an intermediate medium, it can be the communication inside two elements. For ordinary skilled in the art, the specific meaning of the above terms in the application can be understood according to the specific circumstances.

[0095] Although the embodiments of the application have been shown and described, it can be understood by those skilled in the art that various equivalent changes, modifications, replacements and variations can be made to the embodiments without departing from the principles and spirits of the application, the scope of the application is defined by the appended claims and their equivalent scope.

Claims

1. A large model-based grinding optimization processing system, characterized in that, The system comprises: A semi-autogenous mill preprocessing module for realizing human-computer interaction front-end semi-autogenous mill parameters, variable iteration, remote semi-autogenous mill automatic monitoring, semi-autogenous mill input variable preprocessing, and normal running semi-autogenous mill connection; A semi-autogenous mill optimization algorithm processing module for processing semi-autogenous mill optimization algorithms by using optimization algorithms to obtain optimization nodes; A large model fuzzy expert system module for providing deep learning optimization algorithms and semi-autogenous mill fuzzy logic experience rules for data processing; A semi-autogenous mill update optimization module for applying and monitoring the semi-autogenous mill optimization algorithms, the large model fuzzy expert system module, and the semi-autogenous mill scheduling optimization algorithm library in the whole process under different models; A semi-autogenous mill parameter configuration selection module for configuring the working mode of the semi-autogenous mill optimization algorithm under different parameters; The semi-autogenous mill optimization algorithm processing module comprises a basic optimization algorithm library for remote semi-autogenous mill field basic optimization algorithms, a semi-autogenous mill large model clustering component for clustering and encrypting and packaging the remote semi-autogenous mill field basic optimization algorithms, a redundant algorithm adjustment component for adjusting redundant algorithms according to existing semi-autogenous mill industry optimization algorithm standards and self-defined standards, and an optimization algorithm code management component for directly extracting optimization algorithms in the basic optimization algorithm library and periodically regulating and controlling the grinding efficiency, so that the system can quickly call the optimization algorithms in the basic optimization algorithm library according to the requirements; The semi-autogenous mill preprocessing module further comprises: A semi-autogenous mill decision section input variable preprocessing module for performing semi-autogenous mill useful power data transmission according to semi-autogenous mill equipment management, ore hardness, ore type, and grinding fault influence quantity in the semi-autogenous mill decision section; A system comprehensive management module for maintaining the normal operation of all parameters in the system and maintaining the stability of the system.

2. The large model-based grinding optimization processing system according to claim 1, wherein, The semi-autogenous mill optimization algorithm processing module comprises an optimization algorithm integration module for providing transceiving, control servers, optimization algorithm saving, optimization algorithm clustering, optimization algorithm calculation, and optimization algorithm coding, an optimization algorithm processing module for processing massive semi-autogenous mill optimization algorithms under different models and providing an optimization algorithm running environment, an optimization algorithm evaluation module comprising optimization algorithm screening, a redundant algorithm adjustment component, and optimization algorithm evaluation, a grinding efficiency per unit time optimization module for optimizing the working efficiency per unit time in the semi-autogenous mill application process, and a grinding fault influence module for statistically and predictively analyzing grinding fault influences.

3. The large model-based grinding optimization processing system according to claim 1, wherein, The semi-autogenous mill preprocessing module comprises: A semi-autogenous mill initial automatic monitoring AI module for realizing semi-autogenous mill automatic monitoring, semi-autogenous mill useful power data transmission, running parameter configuration, semi-autogenous mill input variable preprocessing, and AI integrated danger early warning; A semi-autogenous mill automatic monitoring module for enabling grinding engineers and safety background monitoring personnel to master the semi-autogenous mill unit time optimization algorithm under different loads and provide semi-autogenous mill running manual instructions.

4. The large model-based grinding optimization processing system according to claim 1, wherein, The large model fuzzy expert system module comprises an artificial fusion optimization algorithm library composed of a fuzzy expert system network optimization algorithm and a hypergraph neural network algorithm optimization algorithm, and the fusion optimization algorithm library is matched based on semi-autogenous mill scheduling parameter configuration.

5. The large model-based grinding optimization processing system according to claim 3, wherein, The semi-autogenous mill initial automatic monitoring AI module comprises a semi-autogenous mill management parameter optimization module, a new semi-autogenous mill target AI module, a system energy consumption supply module, a system front-end module, a system parameter setting module, a semi-autogenous mill power transmission module, a semi-autogenous mill parameter intelligent calibration module and a semi-autogenous mill conversion efficiency module.

6. The large model-based grinding optimization processing system according to claim 3, wherein, The semi-autogenous mill automatic monitoring module comprises an automatic monitoring efficiency module, a semi-autogenous mill preprocessing module, a remote management module and a semi-autogenous mill power module.

7. The large model-based grinding optimization processing system of claim 1, wherein, The semi-autogenous mill decision section input variable preprocessing module comprises a semi-autogenous mill equipment intelligent management module, a grinding task index analysis module, an ore type semi-autogenous mill useful power data transmission module, a semi-autogenous mill grinding speed benchmark setting module, a semi-autogenous mill distribution module and a semi-autogenous mill de-buzzing management module.

Images