Method and device for determining process parameters of substance extraction system and electronic equipment

By constructing simulation models and optimizing process parameters, the problem of low extraction efficiency caused by fixed parameters in the substance extraction system is solved, and a more efficient and accurate material extraction process is achieved.

CN118981955APending Publication Date: 2024-11-19QINGHAI SALT LAKE FUZHAO LANKE LITHIUM IND CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411059074.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-02
Publication Date
2024-11-19

AI Technical Summary

Technical Problem

Fixed parameters are usually used in existing substance extraction systems, which makes it difficult to effectively extract substances, and information collection is time-consuming, lagging and error-prone, and lacks effective solutions.

Method used

By obtaining multiple process points of the material extraction system, building simulation models, using simulation data to run multiple sets of point parameter settings, determining target point parameters, and optimizing the extraction system to improve product extraction efficiency and quality.

Benefits of technology

It realizes more effective material extraction, improves production efficiency, reduces the time-consuming and error rate of information collection, and provides more accurate process parameter settings.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118981955A_ABST
    Figure CN118981955A_ABST
Patent Text Reader

Abstract

The invention discloses a method and a device for determining process parameters of a substance extraction system and electronic equipment. The method comprises the following steps: acquiring a plurality of process point locations of a substance extraction system; according to the to-be-extracted substance and the process point location data corresponding to the plurality of process point locations, determining a target point location which affects the substance extraction system to extract the product; constructing a simulation model corresponding to the substance extraction system based on the target point location; the simulation data serve as input, the simulation models under the multiple sets of point location parameters are operated respectively, multiple sets of operation results are obtained, and the multiple sets of point location parameters correspond to the multiple sets of operation results one to one; and determining target point location parameters corresponding to the target point location according to the multiple groups of operation results. The technical problem that in a substance extraction system in the related technology, due to the fact that fixed parameters are usually adopted at corresponding process point positions, substance extraction is difficult to conduct effectively is solved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of process settings, and in particular to a method, device and electronic equipment for determining process parameters of a material extraction system. Background Art

[0002] In recent years, with the development of information technology and automation, driven by both external and internal demands, the automation level of production lines has been further improved, and new enterprise-level management information systems have been introduced, thereby greatly improving the production management level and market competitiveness of enterprises.

[0003] However, this cannot effectively improve the production efficiency of the enterprise. The reason for this problem is that the enterprise usually adopts a fixed parameter extraction process in the production process, which makes the collection of information cumbersome, delayed, and prone to errors.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present invention provide a method, device and electronic device for determining process parameters of a material extraction system, so as to at least solve the technical problem that in the material extraction system in the related art, fixed parameters are usually used at corresponding process points, resulting in difficulty in effectively extracting the material.

[0006] According to one aspect of an embodiment of the present invention, there is provided a method for determining process parameters of a material extraction system, comprising: acquiring multiple process points of the material extraction system; determining target points that affect the extraction products of the material extraction system based on the material to be extracted and the process point data corresponding to the multiple process points; constructing a simulation model corresponding to the material extraction system based on the target points; using simulation data as input, respectively running the simulation model under multiple groups of point parameter settings to obtain multiple groups of operation results, wherein the multiple groups of point parameters correspond one-to-one to the multiple groups of operation results; and determining the target point parameters corresponding to the target point based on the multiple groups of operation results.

[0007] Optionally, after determining the target point parameters corresponding to the target point based on the multiple groups of operation results, it also includes: receiving a material extraction instruction, wherein the material extraction instruction carries the material to be extracted; controlling the point parameters corresponding to the target point in the material extraction system to be the target point parameters; and running the material extraction system to extract the material to be extracted when the point parameters corresponding to the target point are set to the target point parameters.

[0008] Optionally, based on the substance to be extracted and the process point data corresponding to the multiple process points, target points that affect the output product of the substance extraction system are determined, including: when the substance to be extracted can be extracted through multiple combinations, based on the substance to be extracted and the process point data corresponding to the multiple process points, multiple groups of target points are determined.

[0009] Optionally, based on the material to be extracted and the process point data corresponding to the multiple process points, the target points that affect the output products of the material extraction system are determined, including: determining an extraction target, wherein the extraction target includes at least one of the following: a minimum cost target, a fastest speed target; based on the extraction target, determining target indexes corresponding to the multiple groups of target points, wherein the target indexes are determined by the operation results corresponding to the multiple groups of target points; based on the corresponding target indexes, selecting the highest priority point group from the multiple groups of target points.

[0010] Optionally, taking simulation data as input, the simulation model is run under multiple sets of point parameter settings respectively to obtain multiple sets of running results, including: when the multiple sets of running results all include the extracted material mass index, determining the steady-state parameter setting interval corresponding to the target point based on the extracted material mass index corresponding to the multiple sets of point parameters respectively.

[0011] Optionally, taking simulation data as input and running the simulation model under multiple sets of point parameter settings respectively, before obtaining multiple sets of running results, it also includes: when there are multiple target points, determining the correlation relationship between the multiple target points; determining the multiple sets of point parameters based on the correlation relationship and the material to be extracted.

[0012] Optionally, taking simulation data as input and running the simulation model under multiple sets of point parameter settings respectively, before obtaining multiple sets of running results, it also includes: using sample data to train the simulation model until a simulation model with a predetermined index greater than or equal to a predetermined threshold is obtained, wherein the predetermined index includes at least one of the following: accuracy index, determination coefficient index.

[0013] According to one aspect of an embodiment of the present invention, there is provided a device for determining process parameters of a material extraction system, comprising: an acquisition module for acquiring multiple process points of the material extraction system; a first determination module for determining target points that affect the output product of the material extraction system based on a material to be extracted and process point data corresponding to the multiple process points; a construction module for constructing a simulation model corresponding to the material extraction system based on the target points; an operation module for taking simulation data as input and respectively operating the simulation model under multiple groups of point parameter settings to obtain multiple groups of operation results, wherein the multiple groups of point parameters correspond one-to-one to the multiple groups of operation results; and a second determination module for determining target point parameters corresponding to the target points based on the multiple groups of operation results.

[0014] According to one aspect of an embodiment of the present invention, there is provided an electronic device, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement the method for determining process parameters of a material extraction system as described in any one of the above.

[0015] According to one aspect of an embodiment of the present invention, a computer-readable storage medium is provided. When instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device can execute any of the above-mentioned methods for determining process parameters of a material extraction system.

[0016] In an embodiment of the present invention, multiple process points of a material extraction system are obtained. Based on the material to be extracted and the process point data corresponding to the multiple process points, the target points that affect the extraction of the product by the material extraction system are determined. Based on the target points, a simulation model corresponding to the material extraction system is constructed. With the simulation data as input, the simulation models are respectively run under multiple groups of point parameter settings to obtain multiple groups of operation results, wherein the multiple groups of point parameters correspond one to one to the multiple groups of operation results. Based on the multiple groups of operation results, the target point parameters corresponding to the target point are determined. The parameters corresponding to the process points in the material extraction system are set as the target point parameters, so that the product can be better extracted. This solves the technical problem that in the material extraction system in the related art, fixed parameters are usually used at the corresponding process points, which makes it difficult to effectively extract the material. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0018] Figure 1 is a flow chart of a method for determining process parameters of a material extraction system according to an embodiment of the present invention;

[0019] Figure 2 is a simulation model establishment flow chart provided by an optional implementation mode of the present invention;

[0020] Figure 3 4 is a structural block diagram of a device for determining process parameters of a material extraction system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0022] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0023] Example 1

[0024] According to an embodiment of the present invention, an embodiment of a method for determining process parameters of a material extraction system is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0025] Figure 1 is a flow chart of a method for determining process parameters of a material extraction system according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0026] Step S102, obtaining multiple process points of the material extraction system;

[0027] In step S102 provided in the present application, a material extraction system is involved. There may be multiple material extraction systems, for example, a lithium extraction system. There are also multiple process points involved, for example, in a lithium extraction system, there may be ore crushing points, ore grinding points, leaching liquid treatment points, lithium precipitation points, lithium refining points, and the like.

[0028] Step S104, determining a target point that affects the extraction product of the material extraction system according to the material to be extracted and the process point data corresponding to the plurality of process points;

[0029] In step S104 provided in the present application, the substance to be extracted is involved, such as lithium in a lithium extraction system. According to the specific substance to be extracted, the specific process point, and the parameters and historical data of the process point, the target point that will affect the extraction product of the substance extraction system can be accurately determined.

[0030] Step S106, constructing a simulation model corresponding to the material extraction system based on the target point;

[0031] In step S106 provided in the present application, a simulation model corresponding to the material extraction system is constructed based on the target point.

[0032] For example, when the object extraction system is a multi-substance extraction system, if the substance to be extracted this time is lithium, only the points related to lithium extraction need to be affected. In addition, for the points used in the lithium extraction process but not having much impact, simulation modeling can be omitted to reduce resource consumption.

[0033] Without affecting resource consumption, the process parameters for efficient extraction of substances can still be effectively estimated, thereby achieving the effect of more efficient extraction of the substances to be extracted.

[0034] Step S108, using the simulation data as input, respectively running the simulation model under the multiple sets of point parameter settings to obtain multiple sets of operation results, wherein the multiple sets of point parameters correspond to the multiple sets of operation results one by one;

[0035] In step S108 provided in the present application, simulation data is used as input, and simulation models are respectively run under multiple groups of point parameter settings to obtain multiple groups of operation results, wherein the multiple groups of point parameters correspond one to one to the multiple groups of operation results. That is, in order to determine the corresponding operation results under different point parameters, for example, the extraction weight, extraction rate, extraction concentration, etc. of the substance to be extracted can be evaluated under different point parameters. It is not limited here and can be set according to the set target. Among them, the simulation data can be the raw material composition required to extract the substance to be extracted, so as to simulate the extraction of the substance to be extracted, and then select the appropriate point parameters.

[0036] Step S110, determining target point parameters corresponding to the target points according to the multiple sets of operation results.

[0037] In step S110 provided in the present application, the target point parameters corresponding to the target point are determined based on multiple groups of operation results. It should be noted that when determining the target point parameters corresponding to the target point, it can be determined based on certain goals, such as extraction weight, extraction rate, extraction concentration, etc. Custom settings can be made according to actual applications and scenarios. In order to set the point parameters of the system in a targeted manner.

[0038] Through the above steps S102-S110, multiple process points of the material extraction system are obtained. According to the material to be extracted and the process point data corresponding to the multiple process points, the target point that affects the extraction of the product by the material extraction system is determined. Based on the target point, a simulation model corresponding to the material extraction system is constructed. With the simulation data as input, the simulation models are respectively run under multiple groups of point parameter settings to obtain multiple groups of operation results, wherein the multiple groups of point parameters correspond to the multiple groups of operation results one by one. According to the multiple groups of operation results, the target point parameters corresponding to the target point are determined. The parameters corresponding to the process points in the material extraction system are set as the target point parameters, so that the product can be better extracted. This solves the technical problem that in the material extraction system in the related art, fixed parameters are usually used at the corresponding process points, which makes it difficult to effectively extract the material.

[0039] As an optional embodiment, after determining the target point parameters corresponding to the target point based on multiple groups of operation results, it also includes: receiving a material extraction instruction, wherein the material extraction instruction carries the material to be extracted; controlling the point parameters corresponding to the target point in the material extraction system to be the target point parameters; and running the material extraction system to extract the material to be extracted when the point parameters corresponding to the target point are set to the target point parameters.

[0040] In this embodiment, a substance extraction instruction is received, and the substance extraction instruction carries the substance to be extracted. The point parameters corresponding to the target point in the material extraction system are controlled to be the target point parameters, so that the corresponding substance can be efficiently extracted. When the point parameters corresponding to the target point are set to the target point parameters, the material extraction system is operated to extract the substance to be extracted. For example, if it is a lithium extraction system, the corresponding parameters of the corresponding points can be set to the target point parameters so that the lithium substance can be efficiently extracted. It should be noted that after setting the point parameters of multiple points, the points involved can also be connected by physical relationships or communication methods to ensure that they can smoothly extract the substance.

[0041] As an optional embodiment, based on the material to be extracted and the process point data corresponding to multiple process points, target points that affect the output products of the material extraction system are determined, including: when the material to be extracted can be extracted through multiple combinations, based on the material to be extracted and the process point data corresponding to multiple process points, multiple groups of target points are determined.

[0042] In this embodiment, the process of determining the target points that affect the output product of the material extraction system based on the material to be extracted and the process point data corresponding to the multiple process points is described. First, it is determined whether the material to be extracted can be extracted through multiple combinations. If it can be extracted through multiple combinations, multiple groups of target points are determined based on the material to be extracted and the process point data corresponding to the multiple process points. In order to select appropriate target points from multiple groups of target points according to the corresponding operation results. When determining a specific group from multiple groups of target points, it can also be considered according to different aspects of the operation results, such as cost, efficiency, etc. In order to be able to extract the material in a more targeted manner.

[0043] As an optional embodiment, based on the material to be extracted and the process point data corresponding to multiple process points, the target points that affect the output products of the material extraction system are determined, including: determining the extraction target, wherein the extraction target includes at least one of the following: minimum cost target, fastest speed target; based on the extraction target, determining the target indexes corresponding to multiple groups of target points, wherein the target indexes are determined by the operation results corresponding to the multiple groups of target points; based on the corresponding target indexes, selecting the highest priority point group from the multiple groups of target points.

[0044] In this embodiment, a process of determining a target point that affects the output product of a material extraction system based on a material to be extracted and process point data corresponding to a plurality of process points is described. In this process, an extraction target can be determined so that the most suitable point group can be determined according to the target.

[0045] These include the minimum cost target, the fastest speed target, and other targets that can be set, which can be customized based on actual applications and scenarios.

[0046] When the target is the minimum cost target, the target indexes corresponding to the multiple groups of target points can be the target indexes determined according to the cost amount. When the target is the fastest speed target, the target indexes corresponding to the multiple groups of target points can be the target indexes determined according to the time to produce the predetermined amount. Etc., no limitation is made here. In this way, the point group with the highest priority is determined so that the point group can be used for subsequent implementation.

[0047] As an optional embodiment, simulation data is used as input, and simulation models are respectively run under multiple sets of point parameter settings to obtain multiple sets of running results, including: when the multiple sets of running results all include the extracted material mass index, the steady-state parameter setting interval corresponding to the target point is determined based on the extracted material mass index corresponding to the multiple sets of point parameters.

[0048] In this embodiment, the process of taking simulation data as input, running the simulation model under multiple groups of point parameter settings, and obtaining multiple groups of operation results is described. That is, when the multiple groups of operation results include the extracted material quality index, the steady-state parameter setting interval corresponding to the target point is determined according to the extracted material quality index corresponding to the multiple groups of point parameters. That is, under different point parameter settings, the quality of the extracted material is also different. Under this consideration, the interval in which the material quality meets the requirements will be determined to avoid the subsequent impact caused by the unqualified material quality. When the subsequent points produce the material, the point parameters corresponding to the target point must be within the steady-state parameter interval to avoid the generation of quality problems when blindly pursuing speed or weight.

[0049] As an optional embodiment, taking simulation data as input, respectively running the simulation model under multiple sets of point parameter settings, before obtaining multiple sets of running results, it also includes: when there are multiple target points, determining the correlation between the multiple target points; determining multiple sets of point parameters based on the correlation and the substances to be extracted.

[0050] In this embodiment, the process of determining multiple sets of point parameters is described. When there are multiple target points, the correlation relationship between the multiple target points is determined, for example, the product of point A is the raw material of point B, etc. Based on the correlation relationship and the material to be extracted, multiple sets of point parameters are determined. That is, if the product of point A is the raw material of point B, then the point parameter setting of B is actually related to point A and the output of point A. Therefore, by making appropriate settings in this way, it can be ensured that multiple sets of point parameters are not randomly selected, avoiding the waste of computing resources caused by random selection.

[0051] As an optional embodiment, taking simulation data as input, and running the simulation model under multiple sets of point parameter settings respectively, before obtaining multiple sets of running results, it also includes: using sample data to train the simulation model until a simulation model with a predetermined index greater than or equal to a predetermined threshold is obtained, wherein the predetermined index includes at least one of the following: accuracy index, determination coefficient index.

[0052] In this embodiment, the process of training a simulation model using sample data is described, and the model is trained until a simulation model with a predetermined index greater than or equal to a predetermined threshold is obtained, and the predetermined index includes at least one of the following: accuracy index, determination coefficient index. That is, the model after training can achieve a certain accuracy rate. Or meet a certain determination coefficient, where the determination coefficient is also called goodness of fit, which reflects the degree to which the independent variable explains the change of the dependent variable. The closer it is to 1, the better the model fits, and the closer it is to 0, the worse the model effect. Ensure that the model application can provide effective decision support for the business.

[0053] Based on the above embodiments and optional embodiments, an optional implementation is provided, which is described in detail below.

[0054] An optional embodiment of the present invention provides a method for determining process parameters of a lithium material extraction system, which is described below. Figure 2 This is a flow chart of establishing a simulation model provided by an optional embodiment of the present invention. Figure 2 Introduce it.

[0055] The optional implementation mode of the present invention performs modeling analysis based on big data and artificial intelligence technology to achieve the following goals:

[0056] Optimization of process parameters for lithium extraction process:

[0057] 1) Through the historical data of weather, raw materials, adsorbents, cumulative values ​​of tower area control variables, flow values, temperature, etc. and the content of lithium chloride and magnesium chloride measured in the analysis room, the important points affecting lithium chloride and magnesium chloride and their time lag intervals are analyzed.

[0058] 2) Use historical data to build a simulation prediction model during the process production.

[0059] 3) Through methods such as operations optimization, find the optimal parameter combination for achieving the quality standards of process components, and push it to production technology engineers to provide a basis for their parameter adjustments.

[0060] Product quality control in lithium deposition process:

[0061] 1) Analyze the process points that affect the quality of product components and screen qualified samples.

[0062] 2) Find the steady-state range of product components and construct a steady-state differentiation model.

[0063] 3) When product components do not meet the standards, identify the variables that affect product quality, provide the points of non-compliance and their reasonable ranges, and provide data support for proposing solutions.

[0064] For the above:

[0065] Process parameter tuning:

[0066] The purpose of production process parameter tuning is to return the data of the analysis room. Combined with the production equipment requirements and process flow, the algorithm model is generated with the help of machine learning tools in artificial intelligence. The algorithm dynamically optimizes and gives suggestions for equipment parameter adjustment to achieve equipment parameter adjustment.

[0067] Feature Engineering:

[0068] The raw data will be automatically extracted from the platform data, and after cleaning and processing, business features with business significance will be obtained. Data extraction will be carried out in a daily incremental extraction manner. Table 1 is a list of features of the 56-tower area, Table 2 is a list of adjustable parameters for the 56-tower area, Table 1 is a list of features of the 24-tower area, and Table 2 is a list of adjustable parameters for the 24-tower area. As shown in Tables 1, 2, 3, and 4, the corresponding point parameters can be adjusted.

[0069] Table 1

[0070]

[0071]

[0072]

[0073] Table 2

[0074] Serial number Point 1 Cumulative adsorption 2 One lithium wash accumulation 3 Second stage lithium washing accumulation 4 Three-stage lithium washing accumulation 5 Four-stage lithium washing accumulation 6 Five-stage lithium washing accumulation 7 Six-stage lithium washing accumulation 8 1 / 1 Desorption accumulation 9 2 / 1 Desorption accumulation 10 1 / Secondary desorption accumulation 11 2 / Secondary desorption accumulation 12 1 / Three desorption accumulation 13 2 / Three desorption accumulation 14 Top liquid accumulation

[0075] Table 3

[0076]

[0077]

[0078]

[0079] Table 4

[0080] Serial number Point 1 Adsorption set flow 2 One stage lithium washing set flow 3 Second stage lithium washing setting flow 4 Three-stage lithium washing setting flow 5 Four-stage lithium washing flow setting 6 Set flow rate for stage 1 separation 7 1st stage desorption 2 set flow 8 Second stage separation 1 set flow rate 9 Second stage separation 2 set flow rate 10 Three-stage separation 1 set flow 11 Three-stage separation 2 set flow 12 Top liquid set flow 13 Backwash set flow

[0081] Build the simulation model:

[0082] In the process of production, a prediction simulation model is constructed based on the collected historical process point data. This stage mainly includes model establishment and model tuning.

[0083] Data preprocessing mainly includes data outlier analysis and missing value filling.

[0084] The purpose of feature engineering is to extract features from raw data to the maximum extent possible for use by algorithms and models, and the models built using features can achieve optimal performance on unknown data.

[0085] The three main approaches used to build models are statistical algorithms, machine learning, and deep learning models. Targeted selection and optimization are carried out based on the specific circumstances of the business.

[0086] Simulation model tuning:

[0087] 1) Introduce new process control and monitoring data as needed to tune the model;

[0088] 2) Analyze the correlation between data from a business perspective, build features as needed, and optimize the model;

[0089] 3) Select different types of machine learning and deep learning models based on data distribution, and optimize the model selection;

[0090] 4) Build multidimensional models as needed, integrate models, and optimize model results;

[0091] 5) Use the latest data to verify and tune the model before it goes online.

[0092] Process parameter optimization:

[0093] Based on the establishment of the simulation model, the optimal parameter combination for achieving the quality standards of the process components is found and pushed to the production technical engineers, providing a basis for them to adjust the parameters.

[0094] Through genetic algorithms, taboo search, naive Bayesian optimization, etc., taboo search is performed on process point parameters to find the parameter combination that makes the target value reach the optimal value. The main steps include the following:

[0095] S1, obtain the normal range of each point data according to the process principle requirements and historical data;

[0096] S2, based on different parameter combinations, generates parameter combinations of variables that have a great influence on a certain component;

[0097] S3, based on the Gaussian probability proxy model;

[0098] S4, extract the initial N observation points;

[0099] S5, calculate the optimization objective function distribution;

[0100] S6, generate the next observation point;

[0101] S7, calculate the upper bound of the expected incremental confidence;

[0102] S8, according to the optimization improvement results or iteration termination conditions;

[0103] S9, find the optimal parameter combination of the point;

[0104] S10, recommends the combined parameter operation to the finished product quality management personnel, production operators, production technical engineers and digital factory management personnel;

[0105] S11, on-site operators adjust equipment operating parameters according to operational suggestions to achieve the expected improved quality indicators.

[0106] Product quality control:

[0107] Collect product quality-related data, identify different process steady states by establishing an algorithm model related to product quality, analyze factors that restrict product quality, and when product quality exceeds the standard range, find the cause of the problem, providing a data basis for proposing solutions.

[0108] According to the characteristics of the project, the quality management process of lithium precipitation technology is divided into three stages: sample classification stage, steady-state division & point analysis stage, and product quality review stage.

[0109] Sample classification stage: According to the sampling quality, the samples are divided into qualified and unqualified categories.

[0110] In the steady-state division and point analysis phase, based on qualified samples, multiple steady-state processes are identified by clustering the data. The thresholds of process points are set by combining data analysis with process requirements. The main process is as follows:

[0111] S1, screen out data samples with qualified quality;

[0112] S2, data normalized and unified;

[0113] S3, analyzing and handling outlier data;

[0114] S4, determine how many clusters are needed and randomly initialize a cluster centroid point for each of them;

[0115] S5, calculate the distance from each sample to the centroid and assign each sample point to the nearest class centroid;

[0116] S6, based on these sample points that have been preliminarily classified, recalculate the average value of all vectors in each cluster to determine a new centroid;

[0117] S7, performing a certain number of iterations until the position of the center of mass no longer changes significantly, and obtaining data sets of different steady states;

[0118] S8, through the combination of mathematical statistics and machine learning models, the process point threshold is determined from the data perspective;

[0119] S9, refer to the actual process requirements and adjust the point threshold based on business experience.

[0120] S10, product quality review stage, analyzes the process point data of unqualified samples and gives the specific points that affect product quality.

[0121] The main process is as follows:

[0122] S10.1, after data preprocessing, use the above model to determine which type of steady state the unqualified sample is closest to;

[0123] S10.2, analyzing the point data to obtain the abnormal process points exceeding the set threshold and their degree of dispersion from the threshold;

[0124] S10.3, calculate the correlation between the process points and the target points;

[0125] S10.4, based on the correlation between the points and the degree of dispersion between the abnormal points and their thresholds, the process points that affect the product quality are given in order after comprehensive evaluation.

[0126] Through the above optional implementation, at least the following beneficial effects can be achieved:

[0127] Since the establishment of algorithms for production process parameter tuning and product quality control, the optimal parameter combination for the process components in the production process is pushed to the production technical engineer to provide a basis for the production technical engineer to adjust the parameters. Collect product quality-related data, and identify different process steady states by establishing an algorithm model related to product quality. Analyze the factors that restrict product quality. When the product quality exceeds the standard range, find the cause of the problem and provide a data basis for proposing solutions.

[0128] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0129] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods of various embodiments of the present invention.

[0130] Example 2

[0131] According to an embodiment of the present invention, there is also provided a device for implementing the method for determining process parameters of the substance extraction system. Figure 3 is a structural block diagram of a process parameter determination device of a material extraction system according to an embodiment of the present invention. Figure 3 As shown, the device includes: an acquisition module 302, a first determination module 304, a construction module 306, an operation module 308 and a second determination module 310. The device is described in detail below.

[0132] An acquisition module 302 is used to acquire multiple process points of a material extraction system; a first determination module 304 is connected to the acquisition module 302, and is used to determine the target points that affect the output products of the material extraction system based on the material to be extracted and the process point data corresponding to the multiple process points; a construction module 306 is connected to the first determination module 304, and is used to construct a simulation model corresponding to the material extraction system based on the target points; an operation module 308 is connected to the construction module 306, and is used to use the simulation data as input to respectively operate the simulation model under multiple groups of point parameter settings to obtain multiple groups of operation results, wherein the multiple groups of point parameters correspond one to one to the multiple groups of operation results; a second determination module 310 is connected to the operation module 308, and is used to determine the target point parameters corresponding to the target point based on the multiple groups of operation results.

[0133] It should be noted here that the above-mentioned acquisition module 302, first determination module 304, construction module 306, operation module 308 and second determination module 310 correspond to steps S102 to S110 in the method for determining process parameters of a material extraction system, and the instances and application scenarios implemented by the multiple modules and corresponding steps are the same, but are not limited to the contents disclosed in the above-mentioned embodiment 1.

[0134] Example 3

[0135] According to another aspect of an embodiment of the present invention, there is also provided an electronic device, comprising: a processor; and a memory for storing instructions executable by the processor, wherein the processor is configured to execute instructions to implement any of the above-mentioned methods for determining process parameters of a material extraction system.

[0136] Example 4

[0137] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided. When instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device can execute any of the above-mentioned methods for determining process parameters of a material extraction system.

[0138] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0139] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0140] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0141] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0142] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0143] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0144] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for determining process parameters of a material extraction system, characterized in that: include: Obtain multiple process points of the material extraction system; Determining a target point that affects the extraction product of the substance extraction system according to the substance to be extracted and the process point data corresponding to the plurality of process points; Based on the target point, construct a simulation model corresponding to the material extraction system; Taking the simulation data as input, respectively running the simulation model under multiple sets of point parameter settings to obtain multiple sets of operation results, wherein the multiple sets of point parameters correspond to the multiple sets of operation results one by one; According to the multiple groups of operation results, target point parameters corresponding to the target points are determined.

2. The method according to claim 1, characterized in that After determining the target point parameters corresponding to the target point according to the multiple groups of operation results, the method further includes: receiving a substance extraction instruction, wherein the substance extraction instruction carries the substance to be extracted; Controlling the point parameter corresponding to the target point in the material extraction system to be the target point parameter; When the point parameter corresponding to the target point is set as the target point parameter, the substance extraction system is operated to extract the substance to be extracted.

3. The method according to claim 1, characterized in that According to the substance to be extracted and the process point data corresponding to the plurality of process points, a target point affecting the output product of the substance extraction system is determined, including: In the case that the substance to be extracted can be extracted by a plurality of combined methods, a plurality of groups of target points are determined according to the substance to be extracted and the process point data corresponding to the plurality of process points.

4. The method according to claim 3, characterized in that According to the substance to be extracted and the process point data corresponding to the plurality of process points, a target point affecting the output product of the substance extraction system is determined, including: Determine an extraction target, wherein the extraction target includes at least one of the following: a minimum cost target, a maximum speed target; According to the extracted target, target indexes corresponding to the multiple groups of target points are determined, wherein the target indexes are determined by operation results corresponding to the multiple groups of target points; According to the respectively corresponding target indexes, a point group with the highest priority is selected from the multiple groups of target points.

5. The method according to claim 1, characterized in that Taking the simulation data as input, the simulation model is run under multiple sets of point parameter settings to obtain multiple sets of operation results, including: In the case that the plurality of groups of operation results all include the extracted material quality index, the steady-state parameter setting interval corresponding to the target point is determined according to the extracted material quality indexes respectively corresponding to the plurality of groups of point parameters.

6. The method according to claim 1, characterized in that Taking the simulation data as input, respectively running the simulation model under multiple sets of point parameter settings, and obtaining multiple sets of operation results, the method further includes: In the case where the target point includes multiple ones, determining the association relationship between the multiple target points; The multiple groups of point parameters are determined according to the association relationship and the substance to be extracted.

7. The method according to any one of claims 1 to 6, characterized in that: Taking the simulation data as input, respectively running the simulation model under multiple sets of point parameter settings, and obtaining multiple sets of operation results, the method further includes: The simulation model is trained using sample data until a simulation model having a predetermined index greater than or equal to a predetermined threshold is obtained, wherein the predetermined index includes at least one of the following: an accuracy index and a determination coefficient index.

8. A device for determining process parameters of a material extraction system, characterized in that: include: An acquisition module, used to acquire multiple process points of a material extraction system; A first determination module is used to determine a target point that affects the output product of the substance extraction system according to the substance to be extracted and the process point data corresponding to the multiple process points; A construction module, used to construct a simulation model corresponding to the material extraction system based on the target point; An operation module, used for taking simulation data as input, respectively operating the simulation model under multiple sets of point parameter settings, and obtaining multiple sets of operation results, wherein the multiple sets of point parameters correspond to the multiple sets of operation results one by one; The second determination module is used to determine the target point parameters corresponding to the target point according to the multiple groups of operation results.

9. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the method for determining process parameters of a material extraction system according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the method for determining process parameters of a substance extraction system according to any one of claims 1 to 7.