Rare earth extraction production process simulation system and method

Abstract

The invention is applicable to the field of rare earth extraction, and provides a rare earth extraction production process simulation system and method, and the system comprises a spectral imaging analysis module, a production control decision module, an environment simulation module and an early warning support module. According to the scheme, the time and the cost required by an experiment are reduced, the process is completely carried out in a virtual simulation environment, and the optimal process parameters can be obtained without consuming actual materials, so that rapid iteration and optimization are allowed, the improvement process is accelerated, and the experiment efficiency is improved. The optimal production details are directly applied to the actual process, complex and various condition phase simulation can be constructed for a production scene, the performance of rare earth elements under different operation conditions can be predicted, then the production efficiency and the theoretical design of products are improved, the intelligent level and flexibility of the whole rare earth extraction production are improved, and the production cost is reduced. And the production decision-making process of an enterprise is greatly optimized.

Description

Technical Field

[0001] The invention belongs to the field of rare earth extraction, and in particular relates to a rare earth extraction production process simulation system and method. Background Art

[0002] Rare earth resources are known as "industrial vitamins". As an indispensable supply material for the development of high-tech industries such as intelligent equipment manufacturing and new energy, their importance is self-evident. Faced with the requirements for intelligent transformation in the rare earth extraction production process, there is an urgent need for stable, efficient, intelligent and flexible extraction process simulation methods to assist production decisions, so as to reduce the waste of raw materials in the extraction process and improve product purity. In view of the actual production process of rare earth extraction, a digital twin framework suitable for the entire life cycle of the process is studied, and Unity, 3DMaxs software and python development software are used to build a digital twin platform for the rare earth extraction process. Through this system, the process status, process parameters, equipment operation status, etc. in the rare earth extraction production process can be viewed.

[0003] Combined with the actual situation of rare earth extraction production, the digital twin framework applicable to the entire life cycle of the process is studied. Unity, 3DMaxs software and python development software are used to preliminarily build a digital twin platform for the rare earth extraction process, and realize real-time mapping and interactive control between the digital twin system and the extraction plant. At the same time, the automatic collection and online detection of rare earth extraction and separation production process data are realized. Secondly, a closed-loop control system for key links of equipment and processes in the rare earth extraction and separation production process is developed. Then, a control system for dissolution, extraction and separation, precipitation, calcination and other processes based on DCS is established. Finally, an interlocking and optimization control system for each workshop of the enterprise is established. It enables it to quickly explore and analyze the actual situation of the extraction plant production, and through simulation experiments, it can predict the production status in advance and make relevant control optimization, and guide related production operations and production planning.

[0004] At present, complex chemical processes traditionally require a large amount of experimental materials and time to test different extraction conditions. The impact of various operating conditions (such as pressure, temperature and concentration) on the extraction process may be very complex and difficult to predict. When the actual conditions change, timely adjustment of process parameters is crucial to maintaining production efficiency and product quality. Summary of the invention

[0005] The purpose of the present invention is to provide a rare earth extraction production process simulation system and method, aiming to solve the technical problems existing in the prior art identified in the background technology.

[0006] The present invention is implemented in this way: a rare earth extraction production process simulation system, the system comprising: Spectral imaging analysis module, used to identify the color characteristics of system elements through spectral imaging, and establish a rare earth element prediction model to obtain the element component content based on the element color characteristics analysis; The production control decision module is used to monitor and dynamically collect production parameters in real time, and generate optimized and adjusted production parameters based on the obtained element component content; The environmental simulation module is used to build a virtual environment for rare earth element extraction based on the real-time production parameters obtained, and substitute the optimized and adjusted production parameters into the virtual environment, simulate the production process and results, analyze the process quality of the simulation results, and establish a parameter library. The simulation results and the substituted production parameters are retained in the parameter library, and when the process quality is qualified, the substituted production parameters are synchronized to the production line; The early warning support module is used to identify the current process quality in real time, and when the process quality is abnormal, it will issue a warning message, analyze the abnormal state, and determine the abnormal process flow.

[0007] As a further solution of the present invention, the spectral imaging analysis module includes: Spectral imaging acquisition unit, used to capture spectral image data of raw materials and products in the production process, formulate and execute data acquisition and transmission protocols, transmit the captured spectral image data, and pre-process the data; The model building training unit is used to identify and quantify the spectral characteristics of rare earths, based on which a rare earth element prediction model is established. The element component content is analyzed through the color characteristics of each element in the obtained spectral image data.

[0008] As a further solution of the present invention, the production control decision module includes: Real-time parameter collection unit, used to collect all production parameters related to production from the production line; The data optimization unit is used to identify and screen out relevant parameters that affect production quality and production efficiency, and use the optimization algorithm to analyze each relevant parameter to determine whether the relevant parameters need to be optimized and adjusted, and obtain several complete parameter groups after optimization and adjustment.

[0009] As a further solution of the present invention, the environment simulation module includes: The virtual environment building unit is used to create a virtual model of all production-related physical and chemical parameters required for rare earth element extraction, and simulate the current actual production status using real-time collected production parameters and spectral imaging analysis results; A dynamic simulation evaluation unit, used to substitute the several complete parameter groups after optimization and adjustment into the virtual model respectively, simulate each complete parameter group respectively through the virtual model, and analyze the quality of the product generated by the simulation; The quality assessment and analysis unit is used to analyze the product quality simulated by each set of complete parameters, set the quality error, obtain a set of complete parameters with the best product quality, and substitute it into the production line; The parameter library creation unit is used to establish a parameter library, store the obtained optimal product quality and the complete parameter group used for the product quality in the parameter library, and the two are bound to each other during storage.

[0010] As a further solution of the present invention, the early warning support module includes: Real-time monitoring unit, used to continuously detect all operating parameters on the production line and identify production trends under these parameters; The early warning trigger unit is used to analyze the production trend, and when a production trend deviates from the production target, it issues a warning message and marks the parameters that cause the production trend.

[0011] Another object of the present invention is to provide a rare earth extraction production process simulation method, the method comprising: Identify the color characteristics of system elements through spectral imaging, establish a rare earth element prediction model, and derive the element component content based on the color characteristics of the elements; Real-time monitoring and dynamic collection of production parameters, and generation of optimized and adjusted production parameters based on the obtained element component content; According to the real-time production parameters obtained, a virtual environment for rare earth element extraction is built, and the optimized and adjusted production parameters are substituted into the virtual environment, the production process and results are simulated, and the process quality of the simulation results is analyzed, and a parameter library is established. The simulation results and the substituted production parameters are retained in the parameter library, and when the process quality is qualified, the substituted production parameters are synchronized to the production line; Identify the current process quality in real time, and when the process quality is abnormal, issue a warning message, analyze the abnormal state, and determine the abnormal process flow.

[0012] As a further solution of the present invention, the establishment of a rare earth element prediction model and obtaining the element component content according to the element color characteristic analysis specifically includes: Capture the spectral image data of raw materials and products in the production process, formulate and implement data acquisition and transmission protocols, transmit the captured spectral image data, and pre-process the data; The spectral characteristics of rare earths are identified and quantified, and a rare earth element prediction model is established based on this. The element component content is analyzed through the color characteristics of each element in the obtained spectral image data.

[0013] As a further solution of the present invention, the real-time monitoring and dynamic collection of production parameters, and the generation of optimized and adjusted production parameters according to the obtained element component contents, specifically include: Collect all production parameters related to production from the production line; Identify and screen out the relevant parameters that affect production quality and production efficiency, and use the optimization algorithm to analyze each relevant parameter to determine whether the relevant parameters need to be optimized and adjusted, and obtain several complete parameter groups after optimization and adjustment.

[0014] As a further solution of the present invention, the virtual environment for rare earth element extraction is constructed, and the optimized and adjusted production parameters are substituted into the virtual environment to simulate the production process and results, specifically including: Create a virtual model of all production-related physical and chemical parameters required for rare earth element extraction, and use real-time collected production parameters and spectral imaging analysis results to simulate the current actual production status; Substituting the several complete parameter groups after optimization and adjustment into the virtual model respectively, simulating each complete parameter group respectively through the virtual model, and analyzing the quality of the products generated by the simulation; Analyze the product quality simulated by each set of complete parameters, set the quality error, obtain a set of complete parameters with the best product quality, and substitute it into the production line; A parameter library is established, and the obtained optimal product quality and the complete parameter group used for the product quality are stored in the parameter library, and the two are bound to each other during storage.

[0015] As a further solution of the present invention, the real-time identification of the current process quality and issuing of warning information when the process quality is abnormal specifically includes: Continuously detect all operating parameters on the production line and identify production trends under these parameters; Analyze the production trend, and when there is a production trend that deviates from the production target, issue a warning message and mark the parameters that cause the production trend.

[0016] The beneficial effects of the present invention are: This solution reduces the time and cost required for experiments, because the process is completely carried out in a virtual simulation environment, and the optimal process parameters can be obtained without consuming actual materials, allowing rapid iteration and optimization, accelerating the improvement process, and directly applying the best production details to the actual process. Complex, conditional phase simulations can be constructed for production scenarios, allowing us to predict the performance of rare earth elements under different operating conditions, thereby improving production efficiency and theoretical design of products, enhancing the intelligence and flexibility of the entire rare earth extraction production, and greatly optimizing the company's production decision-making process. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A structural block diagram of a rare earth extraction production process simulation system provided by an embodiment of the present invention; Figure 2 A structural block diagram of a spectral imaging analysis module provided in an embodiment of the present invention; Figure 3 A structural block diagram of a production control decision module provided in an embodiment of the present invention; Figure 4 A structural block diagram of an environment simulation module provided by an embodiment of the present invention; Figure 5 A structural block diagram of an early warning support module provided by an embodiment of the present invention; Figure 6 A flow chart of a method for simulating a rare earth extraction production process provided by an embodiment of the present invention; Figure 7 A flowchart for establishing a rare earth element prediction model provided by an embodiment of the present invention, and obtaining the element component content based on element color feature analysis; Figure 8 A flowchart for real-time monitoring and dynamic collection of production parameters provided by an embodiment of the present invention, and generating optimized and adjusted production parameters based on the obtained element component contents; Fig. 9 A flowchart of building a virtual environment for rare earth element extraction provided by an embodiment of the present invention, substituting optimized and adjusted production parameters into the virtual environment, and simulating the production process and results; Fig.10 A flowchart of an embodiment of the present invention for real-time identification of current process quality and issuing warning information when process quality is abnormal. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0019] It is understood that the terms "first", "second", etc. used in this application may be used herein to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, without departing from the scope of this application, a first xx script may be referred to as a second xx script, and similarly, a second xx script may be referred to as a first xx script.

[0020] Figure 1The structural block diagram of the rare earth extraction production process simulation system provided by the embodiment of the present invention is as follows: Figure 1 As shown, a rare earth extraction production process simulation system, the system comprises: Spectral imaging analysis module 100, used to identify the color characteristics of system elements through spectral imaging, and establish a rare earth element prediction model, and obtain the element component content according to the element color characteristic analysis; This module is responsible for capturing the spectral data of raw materials and products in the production process through advanced spectral imaging technology, providing accurate identification of the color characteristics of system elements. With its high-resolution imaging capabilities and real-time data capture, this module significantly improves the accuracy and efficiency of rare earth element component content analysis in the production process. Through customized data acquisition and transmission protocols, the captured spectral image data can be processed in a timely and efficient manner to ensure data integrity and provide stable input for the analysis model.

[0021] As a large amount of data is collected and input, this module not only gradually enhances its ability to identify and quantify the spectral characteristics of rare earths, but also evolves itself by using advanced statistical and deep learning methods, thereby continuously improving accuracy and response speed. This self-optimization of capabilities ensures that the model predictions become more and more accurate over time and as data accumulates, greatly improving the reliance on real-time monitoring and regulation of rare earth element content.

[0022] The spectral imaging analysis module 100 not only effectively reduces the analysis and prediction deviation in the entire rare earth extraction production process, but also strengthens the processing automation, ultimately promoting the intelligence and sustainable development of the entire production process. This progress plays an indispensable role in improving the quality and efficiency of production management in the rare earth extraction industry.

[0023] The production control decision module 200 is used to monitor and dynamically collect production parameters in real time, and generate optimized and adjusted production parameters according to the obtained element component contents; This module has the complex task of real-time parameter collection from the production line and performing data optimization. Its main function is to capture comprehensive production parameters from the production line in real time. These parameters cover the entire production process from start to finish, including but not limited to material temperature, pressure, flow, density and many more different physical and chemical indicators. These data are crucial for subsequent analysis and decision making.

[0024] Furthermore, it is not only important to collect data, but also to use advanced optimization algorithms to identify which parameters are the key factors affecting production quality and efficiency. This can not only identify existing problems, but also predict potential risks. This module is like the brain of a production process. Compared with traditional methods, it can detect anomalies in the production process faster and take preventive measures to avoid potential quality problems.

[0025] For parameters determined to affect production performance, this unit will apply mathematical and statistical models to optimize and adjust them, scraping analysis data to predict the possible impact of various settings on production. Therefore, after careful analysis, these parameters will be transformed into a series of optimized parameter combinations to achieve the purpose of improving production efficiency and quality. These optimized parameter combinations play a very important role in the extraction of rare earths.

[0026] The significant progress of this module lies in its high degree of automation and decision support capabilities. In the more traditional manual monitoring and parameter adjustment process, the response time is slow and it is easy to be inefficient due to human errors. The implementation of the production control decision module has greatly improved the level of intelligent production line management, implemented data-driven decision-making, improved the accuracy of production plans, reduced consumables and waste, and reduced the impact on the environment.

[0027] This module can adjust parameters in time to respond to dynamic changes in the production process, and can appropriately predict and adapt to the impact of complex interactions that may occur in biological and chemical reactions. In this way, resource utilization is greatly optimized, the optimal state of the production line is dynamically guaranteed, and the sustainability and high efficiency of rare earth extraction operations are maintained. This is a revolutionary technological advancement in the traditional rare earth extraction process.

[0028] The environmental simulation module 300 is used to build a virtual environment for rare earth element extraction according to the real-time production parameters obtained, and substitute the optimized and adjusted production parameters into the virtual environment, simulate the production process and results, analyze the process quality of the simulation results, and establish a parameter library, and store the simulation results and the substituted production parameters in the parameter library. When the process quality is qualified, the substituted production parameters are synchronized to the production line; This module bridges theory and practical operations in parallel, working collaboratively to virtually map the production process and perform quality optimization control.

[0029] First, a detailed virtual model of the physical and chemical parameters of the production process is created. This model can receive elemental color feature data from the spectral imaging analysis module and dynamic production parameters collected by the real-time parameter acquisition unit. It ensures the accuracy of reflecting the current production process and achieves a high degree of synchronization with the actual production status.

[0030] Then, the virtual environment is used to test multiple optimized parameter combinations, which is equivalent to multiple trial and error production in a risk-free environment. The module evaluates the impact of each parameter adjustment on product quality, thus providing the best process parameter setting basis for real production.

[0031] At the same time, by carefully analyzing the simulated rare earth element product quality and setting the error threshold, we can trace back and determine the parameter combination that optimizes the production quality. After obtaining the optimal parameters, we pass the instructions to the production line to adjust the actual process in order to achieve the results predicted by the simulation.

[0032] Finally, not only is the determined optimal production information stored in the database, but a parameter library with learning capabilities is also established. By synchronously storing product quality data and corresponding parameter combinations, this unit provides rich historical data for future optimization decisions and process error analysis.

[0033] The environmental simulation module reduces the time and cost required for experiments, because the process is completely carried out in a virtual simulation environment, and the optimal process parameters can be obtained without consuming actual materials. The module allows designers to quickly iterate and optimize, accelerate the improvement process, and directly apply the best production details to the actual process. And it can build complex, various conditional phase simulations for production scenarios, so that we can predict the performance of rare earth elements under different operating conditions, thereby improving production efficiency and theoretical design of products. This module substantially improves the intelligence level and flexibility of the entire rare earth extraction production, greatly optimizes the company's production decision-making process, and proves the important influence of technology in promoting the upgrading of traditional industries.

[0034] The early warning support module 400 is used to identify the current process quality in real time, and when the process quality is abnormal, issue a warning message, analyze the abnormal state, and determine the abnormal process flow.

[0035] Figure 2 The structural block diagram of the spectral imaging analysis module provided by the embodiment of the present invention is as follows: Figure 2 As shown, the spectral imaging analysis module includes: The spectral imaging acquisition unit 110 is used to capture the spectral image data of the raw materials and products in the production process, formulate and execute the data acquisition and transmission protocol, transmit the captured spectral image data, and pre-process the data; The model building training unit 120 is used to identify and quantify the spectral characteristics of rare earths, based on which a rare earth element prediction model is established, and the element component content is analyzed through the color characteristics of each element in the obtained spectral image data.

[0036] Figure 3 The structural block diagram of the production control decision module provided by the embodiment of the present invention is as follows: Figure 3 As shown, the production control decision module includes: A real-time parameter collection unit 210 is used to collect all production parameters related to production from the production line; The data optimization unit 220 is used to identify and screen out relevant parameters that affect production quality and production efficiency, and use an optimization algorithm to analyze each relevant parameter to determine whether the relevant parameters need to be optimized and adjusted, and obtain several complete parameter groups after optimization and adjustment.

[0037] Figure 4 The structural block diagram of the environment simulation module provided by the embodiment of the present invention is as follows: Figure 4 As shown, the environment simulation module includes: The virtual environment building unit 310 is used to create a virtual model of all production-related physical and chemical parameters required for rare earth element extraction, and simulate the current actual production status using the real-time collected production parameters and spectral imaging analysis results; The dynamic simulation evaluation unit 320 is used to substitute the several complete parameter groups after optimization and adjustment into the virtual model respectively, simulate each complete parameter group respectively through the virtual model, and analyze the quality of the product generated by the simulation; The quality evaluation and analysis unit 330 is used to analyze the product quality simulated by each set of complete parameters, set the quality error, obtain a set of complete parameters with the best product quality, and substitute it into the production line; The parameter library creation unit 340 is used to establish a parameter library, store the obtained optimal product quality and the complete parameter group used for the product quality in the parameter library, and the two are bound to each other during storage.

[0038] Figure 5 The structural block diagram of the early warning support module provided by the embodiment of the present invention is as follows: Figure 5 As shown, the early warning support module includes: A real-time monitoring unit 410 is used to continuously detect all operating parameters on the production line and identify production trends under the parameters; The early warning trigger unit 420 is used to analyze the production trend, and when a production trend deviates from the production target, issue a warning message and mark the parameters causing the production trend.

[0039] Figure 6 A flowchart of a method for simulating a rare earth extraction production process provided by an embodiment of the present invention is shown in FIG. Figure 6 As shown, a rare earth extraction production process simulation method, the method comprises: S100, identifies the color characteristics of system elements through spectral imaging, and establishes a rare earth element prediction model to derive the element component content based on the element color characteristics analysis; This step is responsible for capturing the spectral data of raw materials and products in the production process through advanced spectral imaging technology, providing accurate identification of the color characteristics of system elements. This step significantly improves the accuracy and efficiency of rare earth element component content analysis in the production process with its high-resolution imaging capabilities and real-time data capture. Through customized data acquisition and transmission protocols, the captured spectral image data can be processed in a timely and efficient manner to ensure data integrity and provide stable input for the analysis model.

[0040] As large amounts of data are collected and input, this step not only gradually increases its ability to identify and quantify the spectral characteristics of rare earths, but also evolves itself through the use of advanced statistical and deep learning methods, thereby continuously improving accuracy and response speed. This self-optimization of capabilities ensures that the model predictions become more and more accurate over time and as data accumulates, greatly improving the reliance on real-time monitoring and regulation of rare earth element content.

[0041] This step not only effectively reduces the analysis and prediction deviation in the entire rare earth extraction production process, but also strengthens the processing automation, ultimately promoting the intelligence and sustainable development of the entire production process. This progress plays an indispensable role in improving the quality and efficiency of production management in the rare earth extraction industry.

[0042] S200, real-time monitoring and dynamic collection of production parameters, and generating optimized and adjusted production parameters based on the acquired element component contents; This step has the complex task of real-time parameter collection from the production line and performing data optimization. The main function is to capture comprehensive production parameters from the production line in real time. These parameters cover the entire production process from start to finish, including but not limited to the temperature, pressure, flow, density and many more physical and chemical indicators of the material. These data are crucial for subsequent analysis and decision making.

[0043] Furthermore, it is not only important to collect data, but also to use advanced optimization algorithms to identify which parameters are the key factors affecting production quality and efficiency. This can not only identify existing problems, but also predict potential risks. This step is like the brain of a production process. Compared with traditional methods, it can detect anomalies in the production process faster and take preventive measures to avoid potential quality problems.

[0044] For parameters determined to affect production performance, this unit will apply mathematical and statistical models to optimize and adjust them, scraping analysis data to predict the possible impact of various settings on production. Therefore, after careful analysis, these parameters will be transformed into a series of optimized parameter combinations to achieve the purpose of improving production efficiency and quality. These optimized parameter combinations play a very important role in the extraction of rare earths.

[0045] The significant progress of this step is its high degree of automation and decision support capabilities. In the more traditional manual monitoring and parameter adjustment process, the response time is slow and it is easy to be inefficient due to human errors. The implementation of this step greatly improves the level of intelligent production line management, implements data-driven decision-making, improves the accuracy of production plans, reduces consumables and waste, and reduces the impact on the environment.

[0046] This step can adjust parameters in time to respond to dynamic changes in the production process, and can appropriately predict and adapt to the impact of complex interactions that may occur in biological and chemical reactions. In this way, resource utilization is greatly optimized, the optimal state of the production line is dynamically guaranteed, and the sustainability and high efficiency of rare earth extraction operations are maintained. This is a revolutionary technological advancement in the traditional rare earth extraction process.

[0047] S300, based on the real-time production parameters obtained, a virtual environment for rare earth element extraction is built, and the optimized and adjusted production parameters are substituted into the virtual environment, the production process and results are simulated, and the process quality of the simulation results is analyzed, and a parameter library is established, and the simulation results and the substituted production parameters are retained in the parameter library. When the process quality is qualified, the substituted production parameters are synchronized to the production line; This step bridges theory and practical operation in parallel, working collaboratively to virtually map the production process and perform quality optimization control.

[0048] First, a detailed virtual model of the physical and chemical parameters of the production process is created. This model is able to receive elemental color characteristic data, as well as dynamic production parameters. It ensures that the current production process is accurately reflected and highly synchronized with the actual production status.

[0049] Then, the virtual environment is used to test the application of multiple optimized parameter combinations, which is equivalent to multiple trial and error production in a risk-free environment. The step evaluates the impact of each parameter adjustment on product quality, thus providing the best process parameter setting basis for actual production.

[0050] At the same time, by carefully analyzing the simulated rare earth element product quality and setting the error threshold, we can trace back and determine the parameter combination that optimizes the production quality. After obtaining the optimal parameters, we pass the instructions to the production line to adjust the actual process in order to achieve the results predicted by the simulation.

[0051] Finally, not only is the determined optimal production information stored in the database, but a parameter library with learning capabilities is also established. By synchronously storing product quality data and corresponding parameter combinations, this unit provides rich historical data for future optimization decisions and process error analysis.

[0052] This step reduces the time and cost required for experiments, because the process is completely carried out in a virtual simulation environment and the optimal process parameters can be obtained without consuming actual materials. This step allows designers to quickly iterate and optimize, accelerate the improvement process, and directly apply the best production details to the actual process. And it can build complex, various conditional phase simulations for production scenarios, so that we can predict the performance of rare earth elements under different operating conditions, thereby improving production efficiency and theoretical design of products. This step substantially improves the intelligence level and flexibility of the entire rare earth extraction production, greatly optimizes the company's production decision-making process, and proves the important influence of technology in promoting the upgrading of traditional industries.

[0053] S400, real-time identification of the current process quality, and when the process quality is abnormal, a warning message is issued, and the abnormal state is analyzed to determine the abnormal process flow.

[0054] Figure 7 The embodiment of the present invention provides a flow chart for establishing a rare earth element prediction model and obtaining the element component content according to the element color feature analysis, such as Figure 7 As shown, the rare earth element prediction model is established, and the element component content is obtained according to the element color characteristic analysis, which specifically includes: S110, capturing spectral image data of raw materials and products in the production process, formulating and executing data acquisition and transmission protocols, transmitting the captured spectral image data, and preprocessing the data; S120, identifying and quantifying the spectral characteristics of rare earths, establishing a rare earth element prediction model based on the spectral characteristics, and analyzing and obtaining the element component content through the color characteristics of each element in the obtained spectral image data; Specifically, the spectral characteristics of rare earths are identified and quantified, and a rare earth element prediction model is established based on this. The element component content is analyzed through the color characteristics of each element in the obtained spectral image data. The specific steps are as follows: Based on the spectral image data of raw materials and products, the electronic transition database of rare earth elements is calculated and constructed based on the density functional mechanism; Based on the rare earth element electronic transition database, the characteristic wavelength interval is adaptively extracted through the attention mechanism, and the characteristic wavelength selection is optimized using the quantum annealing algorithm to obtain the characteristic wavelength range and spectral intensity value of the element; Based on the characteristic wavelength range and spectral intensity value of the element, the filtering technology is used to obtain the spectral intensity value after noise removal, and the spectral intensity value after noise removal is normalized to obtain the processed spectral intensity value. In the denoising process, the spectral domain attention discrimination mechanism is used to verify the feature preservation of the spectral intensity value after noise removal. Based on the processed spectral intensity values, the spectral response function of the element is constructed by polynomial fitting method; Within the characteristic wavelength range of the element, the product of the spectral intensity value and the spectral response function is calculated wavelength by wavelength to obtain a weighted spectral intensity value; The weighted spectral intensity value is integrated using the Simpson integration method to obtain the integration result of the spectral intensity value; The integral results of the spectral intensity values ​​were converted through the calibration curve to obtain the elemental component content.

[0055] Figure 8 The embodiment of the present invention provides a flow chart for real-time monitoring and dynamic collection of production parameters, and generating optimized and adjusted production parameters according to the obtained element component content, such as Figure 8 As shown, the real-time monitoring and dynamic collection of production parameters, and the generation of optimized and adjusted production parameters based on the obtained element component contents, specifically include: S210, collecting all production parameters related to production from the production line; S220, identifying and screening out relevant parameters that affect production quality and production efficiency, and using an optimization algorithm to analyze each relevant parameter, determine whether the relevant parameter needs to be optimized and adjusted, and obtain several complete parameter groups after optimization and adjustment; Specifically, identify and screen out the relevant parameters that affect production quality and production efficiency, and use the optimization algorithm to analyze each relevant parameter to determine whether the relevant parameters need to be optimized and adjusted, and obtain several complete parameter groups after optimization and adjustment. The specific steps are as follows: By identifying and screening out the relevant parameters that affect production quality and production efficiency, we can obtain production quality scores, quality indicators, production efficiency, production costs, quality weights, and production efficiency weights; Extract all production quality scores in the current production cycle from the production quality score values ​​and sort them according to the production batch numbers; Classify and label the quality indicators of each batch, generate a multidimensional quality indicator matrix and obtain a structured quality data set; Based on the quality index, a dynamic weight is assigned to each indicator, and an indicator dynamic weight vector is obtained; Based on the structured quality data set and the indicator dynamic weight vector, a batch weighted quality sequence is obtained; The quality deviation value is calculated by the total number of batches and the batch weighted quality sequence; The mass deviation value is squared to obtain a mass deviation square sequence; Based on the mass deviation square sequence, the mass variance is obtained by using an unbiased estimation method; The quality variance is multiplied by the quality weight to obtain the adjusted quality variance, the production efficiency is multiplied by the production efficiency weight to obtain the adjusted production efficiency, and the production cost is multiplied by the cost weight to obtain the adjusted production cost; A comprehensive optimization function is constructed using the adjusted quality variance, the adjusted production efficiency and the adjusted production cost; By means of iterative training, the parameters of the comprehensive optimization function are optimized, and the optimized comprehensive optimization function is obtained; Using the optimized comprehensive optimization function as a basis, the relevant parameters are judged and screened to obtain the screened relevant parameters; The selected related parameters are optimized through the optimized comprehensive optimization function to obtain the optimized and adjusted parameters; The optimized and adjusted parameters are integrated to obtain a complete optimized and adjusted parameter set.

[0056] Fig. 9 A flowchart of building a virtual environment for rare earth element extraction provided by an embodiment of the present invention, substituting the optimized and adjusted production parameters into the virtual environment, and simulating the production process and results, such as Fig. 9 As shown, the virtual environment for rare earth element extraction is constructed, and the optimized and adjusted production parameters are substituted into the virtual environment to simulate the production process and results, specifically including: S310, creating a virtual model of all production-related physical and chemical parameters required for rare earth element extraction, and using real-time collected production parameters and spectral imaging analysis results to simulate the current actual production status; S320, respectively substituting the plurality of optimized and adjusted complete parameter groups into the virtual model, simulating each complete parameter group through the virtual model, and analyzing the quality of the simulated product; S330, analyzing the product quality simulated by each set of complete parameters, setting the quality error, obtaining a set of complete parameters with the best product quality, and substituting it into the production line; S340, establishing a parameter library, storing the obtained optimal product quality and the complete parameter set used for the product quality in the parameter library, and the two are bound to each other during storage; Specifically, a virtual model of all production-related physical and chemical parameters required for rare earth element extraction is created, and the actual current production status is simulated using the real-time collected production parameters and spectral imaging analysis results. The specific steps are as follows: Determine total production time; Determine the critical production status and critical production time in the production process based on the production-related physical and chemical parameters required for rare earth element extraction; Based on the production-related physical and chemical parameters required for rare earth element extraction, the activation energy difference and real-time temperature value are determined; Combining the activation energy difference and the real-time temperature value, and amplifying the temperature sensitivity through an exponential function, we can obtain a preliminary energy level weight factor and generate an activation energy weight sequence. Based on the production-related physical and chemical parameters required for rare earth element extraction, a real-time spectral feature vector, a target spectral feature vector and a spectral adjustment coefficient are determined; Determine a spectrum offset according to the real-time spectrum feature vector and the target spectrum feature vector; The spectral offset is input into a hyperbolic tangent function for nonlinear compression to obtain a compressed offset; The spectral adjustment coefficient is used to scale the compressed offset to obtain a normalized spectral offset impact factor; Extract the activation energy weight of each reaction stage from the activation energy weight sequence, and multiply the activation energy weight of each reaction stage by the normalized spectral shift influence factor to obtain a preliminary coincidence contribution value; Perform weighted sum processing on all preliminary contribution values ​​to generate a contribution coefficient set; Construct a bell-shaped distribution function centered on the critical production time; Substituting the real time timestamp into the bell-shaped distribution function to obtain a time diffusion parameter; Based on the contribution coefficient set, the event diffusion parameters are coupled and verified, and after the verification is completed, the event coupling parameter group is output; Calculate and obtain the production status based on the contribution coefficient of the key production status, the key production time and the time diffusion parameter; Construct a virtual model by accumulating all production states within the total production time; Input the current time into the virtual model to obtain the current actual production status.

[0057] Fig.10 A flowchart of an embodiment of the present invention for real-time identification of the current process quality and issuing a warning message when the process quality is abnormal is provided, such as Fig.10 As shown, the real-time identification of the current process quality and the issuance of warning information when the process quality is abnormal include: S410, continuously detecting all operating parameters on the production line and identifying production trends under the parameters; S420, analyzing the production trend, and when a production trend deviates from the production target, issuing a warning message, and marking the parameters causing the production trend; Analyze the production trend, and when there is a production trend that deviates from the production target, issue a warning message and mark the parameters that cause the production trend. The specific steps are as follows: By analyzing the production trend, the current value fluctuation and dynamic reference value of the operating parameters are obtained; Divide the current value fluctuation of each operating parameter by the dynamic reference benchmark value to obtain a normalized fluctuation; The normalized fluctuation is smoothed by using the S-curve function to obtain the smoothed fluctuation; Normalize the smoothed volatility to generate a preliminary weight distribution of volatility; By analyzing the production trend, the real-time characteristics of the parameters are obtained, and the ideal state characteristics and deviation compression adjustment factors are set; Calculate the Euclidean distance between the real-time characteristics of the parameters and the ideal state characteristics in the multidimensional space to obtain the original deviation; Substitute the original deviation into the hyperbolic tangent function, and use the deviation compression adjustment factor to control the sensitivity of the deviation estimation to generate the parameter state deviation coefficient; The parameter weight function is constructed using the preliminary weight distribution of the fluctuation amount and the parameter state deviation coefficient; deriving the operating parameters based on the parameter weight function, and calculating and obtaining the second-order derivatives of the operating parameters; For each pair of operating parameters, the second-order derivatives of the two operating parameters are multiplied to obtain a preliminary synergy value, and the filtered synergy value is amplitude compressed to obtain a synergy strength index; The filtered synergy value is amplitude compressed to obtain the synergy strength index; Through the analysis of production trends, the position coordinates and spatial influence coefficients of the parameter control unit are further obtained; Based on the position coordinates of the parameter control units, a geometric distance between each pair of parameter control units is calculated; The geometric distance between each pair of parameter control units is introduced into the exponential attenuation function, and optimized through the spatial influence coefficient to obtain the spatial influence attenuation coefficient; An interaction function is constructed based on the synergy intensity index and the spatial attenuation coefficient, and based on the operating parameters, the interaction value between the parameters is calculated and obtained through the interaction function; Combining the second-order derivative of the parameter and the interaction value between the parameters, the deviation from the production target value is obtained, and all the deviations from the production target values ​​are accumulated to obtain the deviation threshold value; Based on the deviation threshold, the production trend is analyzed, and when the production trend deviates from the production target, a warning message is issued, and the parameters that cause the production trend operation are marked.

[0058] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0059] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0060] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described 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 this specification.

[0061] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

[0062] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A rare earth extraction production process simulation method, characterized in that: The method comprises the following steps: Identify the color characteristics of system elements through spectral imaging, establish a rare earth element prediction model, and derive the element component content based on the color characteristics of the elements; Real-time monitoring and dynamic collection of production parameters, and generation of optimized and adjusted production parameters based on the obtained element component content; According to the real-time production parameters obtained, a virtual environment for rare earth element extraction is built, and the optimized and adjusted production parameters are substituted into the virtual environment, the production process and results are simulated, and the process quality of the simulation results is analyzed, and a parameter library is established. The simulation results and the substituted production parameters are retained in the parameter library, and when the process quality is qualified, the substituted production parameters are synchronized to the production line; Identify the current process quality in real time, and when the process quality is abnormal, issue a warning message, analyze the abnormal state, and determine the abnormal process flow; The method of establishing a rare earth element prediction model and analyzing the element component content based on the element color characteristics specifically includes: Capture the spectral image data of raw materials and products in the production process, formulate and implement data acquisition and transmission protocols, transmit the captured spectral image data, and pre-process the data; The spectral characteristics of rare earths are identified and quantified, and a rare earth element prediction model is established based on this. The element component content is analyzed through the color characteristics of each element in the obtained spectral image data.

2. The rare earth extraction production process simulation method according to claim 1, characterized in that: Identify and quantify the spectral characteristics of rare earths, and establish a rare earth element prediction model based on this. The color characteristics of each element in the obtained spectral image data are analyzed to obtain the element component content. The specific steps are as follows: Based on the spectral image data of raw materials and products, the electronic transition database of rare earth elements is calculated and constructed based on the density functional mechanism; Based on the rare earth element electronic transition database, the characteristic wavelength interval is adaptively extracted through the attention mechanism, and the characteristic wavelength selection is optimized using the quantum annealing algorithm to obtain the characteristic wavelength range and spectral intensity value of the element; Based on the characteristic wavelength range and spectral intensity value of the element, the filtering technology is used to obtain the spectral intensity value after noise removal, and the spectral intensity value after noise removal is normalized to obtain the processed spectral intensity value. In the denoising process, the spectral domain attention discrimination mechanism is used to verify the feature preservation of the spectral intensity value after noise removal. Based on the processed spectral intensity values, the spectral response function of the element is constructed by polynomial fitting method; Within the characteristic wavelength range of the element, the product of the spectral intensity value and the spectral response function is calculated wavelength by wavelength to obtain a weighted spectral intensity value; The weighted spectral intensity value is integrated using the Simpson integration method to obtain the integration result of the spectral intensity value; The integral results of the spectral intensity values ​​were converted through the calibration curve to obtain the elemental component content.

3. The rare earth extraction production process simulation method according to claim 2, characterized in that: The real-time monitoring and dynamic collection of production parameters, and the generation of optimized and adjusted production parameters based on the obtained element component contents, specifically include: Collect all production parameters related to production from the production line; Identify and screen out the relevant parameters that affect production quality and production efficiency, and use the optimization algorithm to analyze each relevant parameter to determine whether the relevant parameters need to be optimized and adjusted, and obtain several complete parameter groups after optimization and adjustment.

4. The rare earth extraction production process simulation method according to claim 3, characterized in that: Identify and screen out the relevant parameters that affect production quality and production efficiency, and use the optimization algorithm to analyze each relevant parameter to determine whether the relevant parameters need to be optimized and adjusted, and obtain several complete parameter groups after optimization and adjustment. The specific steps are as follows: By identifying and screening out the relevant parameters that affect production quality and production efficiency, we can obtain production quality scores, quality indicators, production efficiency, production costs, quality weights, and production efficiency weights; Extract all production quality scores in the current production cycle from the production quality score values ​​and sort them according to the production batch numbers; Classify and label the quality indicators of each batch, generate a multidimensional quality indicator matrix and obtain a structured quality data set; Based on the quality index, a dynamic weight is assigned to each indicator, and an indicator dynamic weight vector is obtained; Based on the structured quality data set and the indicator dynamic weight vector, a batch weighted quality sequence is obtained; The quality deviation value is calculated by the total number of batches and the batch weighted quality sequence; The mass deviation value is squared to obtain a mass deviation square sequence; Based on the mass deviation square sequence, the mass variance is obtained by using an unbiased estimation method; The quality variance is multiplied by the quality weight to obtain the adjusted quality variance, the production efficiency is multiplied by the production efficiency weight to obtain the adjusted production efficiency, and the production cost is multiplied by the cost weight to obtain the adjusted production cost; A comprehensive optimization function is constructed using the adjusted quality variance, the adjusted production efficiency and the adjusted production cost; By means of iterative training, the parameters of the comprehensive optimization function are optimized, and the optimized comprehensive optimization function is obtained; Using the optimized comprehensive optimization function as a basis, the relevant parameters are judged and screened to obtain the screened relevant parameters; The selected related parameters are optimized through the optimized comprehensive optimization function to obtain the optimized and adjusted parameters; The optimized and adjusted parameters are integrated to obtain a complete optimized and adjusted parameter set.

5. The rare earth extraction production process simulation method according to claim 4, characterized in that: The virtual environment for rare earth element extraction is constructed, and the optimized and adjusted production parameters are substituted into the virtual environment to simulate the production process and results, specifically including: Create a virtual model of all production-related physical and chemical parameters required for rare earth element extraction, and use real-time collected production parameters and spectral imaging analysis results to simulate the current actual production status; Substituting the several complete parameter groups after optimization and adjustment into the virtual model respectively, simulating each complete parameter group respectively through the virtual model, and analyzing the quality of the products generated by the simulation; Analyze the product quality simulated by each set of complete parameters, set the quality error, obtain a set of complete parameters with the best product quality, and substitute it into the production line; A parameter library is established, and the obtained optimal product quality and the complete parameter group used for the product quality are stored in the parameter library, and the two are bound to each other during storage.

6. The rare earth extraction production process simulation method according to claim 5, characterized in that: Create a virtual model of all production-related physical and chemical parameters required for rare earth element extraction, and use the real-time collected production parameters and spectral imaging analysis results to simulate the current actual production status. The specific steps are as follows: Determine total production time; Determine the critical production status and critical production time in the production process based on the production-related physical and chemical parameters required for rare earth element extraction; Based on the production-related physical and chemical parameters required for rare earth element extraction, the activation energy difference and real-time temperature value are determined; Combining the activation energy difference and the real-time temperature value, and amplifying the temperature sensitivity through an exponential function, we can obtain a preliminary energy level weight factor and generate an activation energy weight sequence. Based on the production-related physical and chemical parameters required for rare earth element extraction, a real-time spectral feature vector, a target spectral feature vector and a spectral adjustment coefficient are determined; Determine a spectrum offset according to the real-time spectrum feature vector and the target spectrum feature vector; The spectral offset is input into a hyperbolic tangent function for nonlinear compression to obtain a compressed offset; The spectral adjustment coefficient is used to scale the compressed offset to obtain a normalized spectral offset impact factor; Extract the activation energy weight of each reaction stage from the activation energy weight sequence, and multiply the activation energy weight of each reaction stage by the normalized spectral shift influence factor to obtain a preliminary coincidence contribution value; Perform weighted sum processing on all preliminary contribution values ​​to generate a contribution coefficient set; Construct a bell-shaped distribution function centered on the critical production time; Substituting the real time timestamp into the bell-shaped distribution function to obtain a time diffusion parameter; Based on the contribution coefficient set, the event diffusion parameters are coupled and verified, and after the verification is completed, the event coupling parameter group is output; Calculate and obtain the production status based on the contribution coefficient of the key production status, the key production time and the time diffusion parameter; Construct a virtual model by accumulating all production states within the total production time; Input the current time into the virtual model to obtain the current actual production status.

7. The rare earth extraction production process simulation method according to claim 6, characterized in that: The real-time identification of the current process quality and the issuance of warning information when the process quality is abnormal include: Continuously detect all operating parameters on the production line and identify production trends under these parameters; Analyze the production trend, and when there is a production trend that deviates from the production target, issue a warning message and mark the parameters that cause the production trend.

8. The rare earth extraction production process simulation method according to claim 7, characterized in that: Analyze the production trend, and when there is a production trend that deviates from the production target, issue a warning message and mark the parameters that cause the production trend. The specific steps are as follows: By analyzing the production trend, the current value fluctuation and dynamic reference value of the operating parameters are obtained; Divide the current value fluctuation of each operating parameter by the dynamic reference benchmark value to obtain a normalized fluctuation; The normalized fluctuation is smoothed by using the S-curve function to obtain the smoothed fluctuation; Normalize the smoothed volatility to generate a preliminary weight distribution of volatility; By analyzing the production trend, the real-time characteristics of the parameters are obtained, and the ideal state characteristics and deviation compression adjustment factors are set; Calculate the Euclidean distance between the real-time characteristics of the parameters and the ideal state characteristics in the multidimensional space to obtain the original deviation; Substitute the original deviation into the hyperbolic tangent function, and use the deviation compression adjustment factor to control the sensitivity of the deviation estimation to generate the parameter state deviation coefficient; The parameter weight function is constructed using the preliminary weight distribution of the fluctuation amount and the parameter state deviation coefficient; deriving the operating parameters based on the parameter weight function, and calculating and obtaining the second-order derivatives of the operating parameters; For each pair of operating parameters, the second-order derivatives of the two operating parameters are multiplied to obtain a preliminary synergy value; The product of the second-order derivatives is filtered using an activation function to obtain a filtered synergy value, and the filtered synergy value is amplitude compressed to obtain a synergy strength index; Through the analysis of production trends, the position coordinates and spatial influence coefficients of the parameter control unit are further obtained; Based on the position coordinates of the parameter control units, a geometric distance between each pair of parameter control units is calculated; The geometric distance between each pair of parameter control units is introduced into the exponential attenuation function, and optimized through the spatial influence coefficient to obtain the spatial influence attenuation coefficient; An interaction function is constructed based on the synergy intensity index and the spatial attenuation coefficient, and based on the operating parameters, the interaction value between the parameters is calculated and obtained through the interaction function; Combining the second-order derivative of the parameter and the interaction value between the parameters, the deviation from the production target value is obtained, and all the deviations from the production target values ​​are accumulated to obtain the deviation threshold value; Based on the deviation threshold, the production trend is analyzed, and when the production trend deviates from the production target, a warning message is issued, and the parameters that cause the production trend operation are marked.

9. A rare earth extraction production process simulation system, characterized in that: The system applies the rare earth extraction production process simulation method as described in any one of claims 1 to 8 above, and the system comprises: Spectral imaging analysis module, used to identify the color characteristics of system elements through spectral imaging, and establish a rare earth element prediction model to obtain the element component content based on the element color characteristics analysis; The production control decision module is used to monitor and dynamically collect production parameters in real time, and generate optimized and adjusted production parameters based on the obtained element component content; The environmental simulation module is used to build a virtual environment for rare earth element extraction based on the real-time production parameters obtained, and substitute the optimized and adjusted production parameters into the virtual environment, simulate the production process and results, analyze the process quality of the simulation results, and establish a parameter library. The simulation results and the substituted production parameters are retained in the parameter library, and when the process quality is qualified, the substituted production parameters are synchronized to the production line; The early warning support module is used to identify the current process quality in real time, and when the process quality is abnormal, it will issue a warning message, analyze the abnormal state, and determine the abnormal process flow.

Images