A method and system for predicting a mineral pulp electrolysis process based on orthogonal analysis

Abstract

The present application relates to the technical field of ore pulp electrolysis process simulation, in particular to an ore pulp electrolysis process prediction method and system based on orthogonal analysis. The ore pulp electrolysis process prediction method based on orthogonal analysis comprises the following steps: collecting ore pulp electrolysis process data to obtain an influence factor dataset and an evaluation index dataset in the ore pulp electrolysis process; calculating according to the influence factor database and the evaluation index dataset to obtain an influence factor-evaluation index weight dataset; constructing a model according to the influence factor database and the influence factor-evaluation index weight dataset to obtain a data twin prediction model; inputting the ore pulp process data to be predicted into the data twin prediction model to obtain an ore pulp electrolysis process prediction result; and visually displaying the ore pulp electrolysis process prediction result on a display. The present application is an instant, efficient and visual ore pulp electrolysis process prediction method.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of simulation of ore pulp electrolysis process, in particular to an ore pulp electrolysis process prediction method and system based on orthogonal analysis. BACKGROUND

[0002] As a new technology of hydrometallurgy, ore pulp electrolysis integrates ore leaching, solution purification and electrolytic deposition in a stirring device to realize one-step preparation of metal. Valuable metal elements in the ore are leached by anodic oxidation reaction and chemical dissolution in the electrolytic deposition process, and metal ions are deposited on the cathode plate under the action of an electric field. With the advantages of green, high efficiency, controllable ion separation and low resource consumption, ore pulp electrolysis is increasingly obvious in the preparation of metal from complex multi-metal ores. However, the one-step preparation process results in a complex tank structure, including a stirring device, electrode plates and diaphragm bags for purification, and the process control is difficult.

[0003] Currently, research on ore pulp electrolysis mainly focuses on reaction mechanism, including feasibility analysis of the reaction and optimization of process parameters at the laboratory scale. There is a lack of flow research at the industrial scale. Traditional empirical methods cannot predict the complex flow in the tank of ore pulp electrolysis, and industrial tests for process parameter and structure optimization have problems such as high cost and low efficiency. However, numerical simulation can effectively simulate the characteristics of key fields such as flow field, concentration field and stress-strain field in the complex tank, establish a three-dimensional visual analysis of the whole tank, identify the stirring dead zone and improve the stirring efficiency. However, general numerical simulation takes a long time from model establishment to calculation and solving, and cannot provide real-time prediction for industrial production.

[0004] In the prior art, there is a lack of an instant, efficient and visual ore pulp electrolysis process prediction method. SUMMARY

[0005] The embodiments of the present application provide an ore pulp electrolysis process prediction method and system based on orthogonal analysis. The technical solution is as follows:

[0006] In one aspect, an ore pulp electrolysis process prediction method based on orthogonal analysis is provided, which is realized by an electronic device. The method comprises the following steps:

[0007] Collecting ore pulp electrolysis process data to obtain an influence factor data set and an evaluation index data set in the ore pulp electrolysis process;

[0008] Performing data orthogonal analysis according to the influence factor data set to obtain an influence factor database;

[0009] According to the influence factor database and the evaluation index data set, the influence factor- evaluation index weight data set is obtained.

[0010] According to the influence factor database and the influence factor-evaluation index weight dataset, a model is constructed to obtain a data twin prediction model;

[0011] Input the process data of the slurry to be predicted, and obtain a prediction result of the slurry electrolysis process through the data twin prediction model; and display the prediction result of the slurry electrolysis process through a display.

[0012] The influence factor dataset is a factor set influencing the result in the actual production process of the slurry electrolysis.

[0013] The influence factor dataset includes stirring speed, solid content, particle size and particle density.

[0014] The evaluation index dataset is an index set evaluating the result in the actual production process of the slurry electrolysis.

[0015] The evaluation index dataset includes suspension uniformity, particle concentration between the plates and power consumption.

[0016] Optionally, the orthogonal analysis according to the influence factor dataset to obtain the influence factor database comprises:

[0017] According to the influence factor dataset, single-factor orthogonal dataset is obtained through data orthogonal analysis.

[0018] Geometric modeling and simulation calculation are performed on the single-factor orthogonal dataset to obtain a single-factor orthogonal model example.

[0019] The single-factor orthogonal model example is solved to obtain a velocity field single-factor orthogonal database and a concentration field single-factor orthogonal database.

[0020] According to the velocity field single-factor orthogonal database and the concentration field single-factor orthogonal database, an influence factor database is obtained.

[0021] Optionally, the calculation according to the influence factor database and the evaluation index dataset to obtain the influence factor-evaluation index weight dataset comprises:

[0022] According to the evaluation index dataset, each evaluation index is obtained.

[0023] According to the influence factor database and each evaluation index, matrix analysis is performed to obtain each index weight matrix.

[0024] Each index weight matrix is processed to obtain a processed each index weight matrix.

[0025] Based on the processed individual index weight matrix, an arithmetic average is calculated according to the influence factors to obtain an influence factor-evaluation index weight data set.

[0026] Optionally, the model is constructed according to the influence factor database and the influence factor-evaluation index weight data set to obtain a data twin prediction model, which includes:

[0027] According to the influence factor database, a single-factor orthogonal database of a velocity field and a single-factor orthogonal database of a concentration field are obtained.

[0028] The single-factor orthogonal database of the velocity field and the single-factor orthogonal database of the concentration field are mathematically associated to obtain an associated orthogonal database.

[0029] The model is constructed according to the associated orthogonal database and the influence factor-evaluation index weight data set to obtain the data twin prediction model.

[0030] In another aspect, a mineral slurry electrolysis process prediction system based on orthogonal analysis is provided, which is applied to a mineral slurry electrolysis process prediction method based on orthogonal analysis, and the system includes an electronic device and a display, wherein:

[0031] The electronic device is used to collect mineral slurry electrolysis process data to obtain an influence factor data set and an evaluation index data set in a mineral slurry electrolysis process, perform data orthogonal analysis according to the influence factor data set to obtain an influence factor database, perform calculation according to the influence factor database and the evaluation index data set to obtain an influence factor-evaluation index weight data set, construct a model according to the influence factor database and the influence factor-evaluation index weight data set to obtain a data twin prediction model, input to-be-predicted mineral slurry process data, and obtain a mineral slurry electrolysis process prediction result through the data twin prediction model.

[0032] The display is used to visually display the mineral slurry electrolysis process prediction result through the display.

[0033] The influence factor data set is a factor set that affects the result in the actual production process of the mineral slurry electrolysis.

[0034] The influence factor data set includes stirring speed, solid content, particle size, and particle density.

[0035] The evaluation index data set is an index set that evaluates the result in the actual production process of the mineral slurry electrolysis.

[0036] The evaluation index data set includes suspension uniformity, particle concentration between the plates, and power consumption.

[0037] Optionally, the electronic device is further configured to:

[0038] perform data orthogonal analysis according to the influence factor dataset to obtain a single-factor orthogonal dataset;

[0039] perform geometric modeling and simulation calculation on the single-factor orthogonal dataset to obtain a single-factor orthogonal model example;

[0040] solve the single-factor orthogonal model example to obtain a velocity field single-factor orthogonal database and a concentration field single-factor orthogonal database;

[0041] obtain an influence factor database according to the velocity field single-factor orthogonal database and the concentration field single-factor orthogonal database.

[0042] Optionally, the electronic device is further configured to:

[0043] obtain each evaluation index according to the evaluation index dataset;

[0044] perform matrix analysis on the influence factor database and the each evaluation index to obtain each index weight matrix;

[0045] perform data processing on the each index weight matrix to obtain a processed each index weight matrix;

[0046] perform arithmetic average calculation on the processed each index weight matrix according to the influence factor to obtain an influence factor-evaluation index weight dataset.

[0047] Optionally, the electronic device is further configured to:

[0048] obtain a velocity field single-factor orthogonal database and a concentration field single-factor orthogonal database according to the influence factor database;

[0049] perform mathematical correlation on the velocity field single-factor orthogonal database and the concentration field single-factor orthogonal database to obtain a correlated orthogonal database;

[0050] perform model construction on the correlated orthogonal database and the influence factor-evaluation index weight dataset to obtain a data twin prediction model.

[0051] In another aspect, an electronic device is provided, which includes a processor and a memory, the memory storing at least one instruction, the at least one instruction being loaded and executed by the processor to implement the above-mentioned one kind of mineral slurry electrolysis process prediction method based on orthogonal analysis.

[0052] In another aspect, a computer-readable storage medium is provided, the storage medium having stored therein at least one instruction, the at least one instruction being loaded and executed by a processor to implement the above-mentioned method for predicting a mineral slurry electrolysis process based on orthogonal analysis.

[0053] The technical scheme provided by the embodiment of the present application has at least the following beneficial effects:

[0054] The present application provides a method for predicting a mineral slurry electrolysis process based on orthogonal analysis, which simulates the influence factors by orthogonal analysis, reduces the simulation quantity by relying on the orthogonality, and reprocesses the macro data of the simulation calculation by using an interpolation algorithm, thereby establishing a digital twin model of the mineral slurry electrolysis process with respect to the flow field and the concentration field, greatly reducing the model response time, solving the problem of long calculation period of the traditional numerical model, and better applying to real-time prediction of solid-liquid suspension in actual industrial production. The present application is a real-time and efficient, visual method for predicting a mineral slurry electrolysis process. BRIEF DESCRIPTION OF DRAWINGS

[0055] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0056] Figure 1 is a flow chart of a method for predicting a mineral slurry electrolysis process based on orthogonal analysis provided by the embodiment of the present application;

[0057] Figure 2 is a block diagram of a system for predicting a mineral slurry electrolysis process based on orthogonal analysis provided by the embodiment of the present application;

[0058] Figure 3 is a structural schematic diagram of an electronic device provided by the embodiment of the present application. DETAILED DESCRIPTION

[0059] In order to make the technical problems, technical solutions and advantages of the present application more clear, the following will be described in detail with reference to the drawings and specific embodiments.

[0060] The embodiment of the present application provides a method for predicting a mineral slurry electrolysis process based on orthogonal analysis, which can be realized by an electronic device, which can be a terminal or a server. As shown in a flow chart of a method for predicting a mineral slurry electrolysis process based on orthogonal analysis, the processing flow of the method can include the following steps: Figure 1

[0061] ​S1, collect the ore slurry electrolysis process data, obtain the influence factor data set and the evaluation index data set in the ore slurry electrolysis process.

[0062] The influence factor data set is a factor set influencing the result in the actual production process of the ore slurry electrolysis.

[0063] The influence factor data set includes stirring speed, solid content, particle size and particle density.

[0064] The evaluation index data set is an index set evaluating the result in the actual production process of the ore slurry electrolysis.

[0065] The evaluation index data set includes suspension uniformity, particle concentration between the plates and power consumption.

[0066] In a feasible implementation, according to the influence parameters in the actual production process of the ore slurry electrolysis, the test factors are determined, including the variables such as stirring speed, solid content, particle size and particle density, which have greater influence on production efficiency, the fluctuation range of each variable is determined according to actual production, and a 4-factor N-level orthogonal example list is constructed according to needs.

[0067] The suspension effect and the particle concentration between the plates in the ore slurry electrolysis are important indexes for evaluating production efficiency, therefore, the test indexes such as suspension uniformity, particle concentration between the plates and power consumption are selected to judge and measure the good or bad of the test results of each factor.

[0068] S2, perform data orthogonal analysis according to the influence factor data set, and obtain an influence factor database.

[0069] Optionally, the influence factor database is obtained by performing orthogonal analysis according to the influence factor data set, including:

[0070] The single-factor orthogonal data set is obtained by performing data orthogonal analysis according to the influence factor data set;

[0071] The single-factor orthogonal model example is obtained by performing geometric modeling and simulation calculation on the single-factor orthogonal data set;

[0072] The velocity field single-factor orthogonal database and the concentration field single-factor orthogonal database are obtained by solving the single-factor orthogonal model example;

[0073] The influence factor database is obtained according to the velocity field single-factor orthogonal database and the concentration field single-factor orthogonal database.

[0074] In a feasible implementation, the single-factor orthogonal data set is established according to the influence factor data set; geometric modeling and discrete simulation calculation are carried out according to the single-factor orthogonal data set, and the single factors are simulated and solved one by one, and whether the calculation converges is judged by the change of the residual error and the monitored variable with the iteration step number.

[0075] The solved example outputs the liquid phase velocity and solid phase concentration at each grid center to form a database of velocity field and concentration field. Since double-precision calculation is used, the data is uniformly processed to have four decimal places to reduce the storage space of the output data.

[0076] S3. Calculate according to the influence factor database and the evaluation index dataset to obtain the influence factor-evaluation index weight dataset.

[0077] Optionally, the influence factor-evaluation index weight dataset is calculated according to the influence factor database and the evaluation index dataset, comprising:

[0078] According to the evaluation index dataset, obtain each evaluation index;

[0079] According to the influence factor database and each evaluation index, perform matrix analysis to obtain each index weight matrix;

[0080] Data processing is performed on each index weight matrix to obtain a processed each index weight matrix;

[0081] Based on the processed each index weight matrix, arithmetic average calculation is performed according to the influence factors to obtain the influence factor-evaluation index weight dataset.

[0082] In a feasible implementation, the results of the example according to the influence factor database are re-analyzed to extract information such as stirring suspension uniformity, particle concentration between the electrodes, and power consumption of different examples.

[0083] The above evaluation index information is subjected to intuitive analysis of different test indexes, and through matrix analysis, the weight matrix of each test index is obtained. After normalization processing, the weight of each factor affecting a single test index is determined. Through arithmetic average, the comprehensive weight of different factors affecting all test indexes can be determined.

[0084] S4. Model construction is performed according to the influence factor database and the influence factor-evaluation index weight dataset to obtain a data twin prediction model.

[0085] Optionally, the data twin prediction model is obtained by model construction according to the influence factor database and the influence factor-evaluation index weight dataset, comprising:

[0086] According to the influence factor database, obtain a single-factor orthogonal database of the velocity field and a single-factor orthogonal database of the concentration field;

[0087] Mathematical correlation is performed on the single-factor orthogonal database of the velocity field and the single-factor orthogonal database of the concentration field to obtain a correlated orthogonal database;

[0088] According to the correlation after the orthogonal database and the influence factor-evaluation index weight dataset, a model is constructed, and a data twin prediction model is obtained.

[0089] In a feasible implementation, according to the data of the influence factor database as a reference, data visualization processing is realized on the flow field and concentration field at different positions through an interpolation algorithm, and through processing of the macro data, mathematical correlations are established between different example models.

[0090] At the same time, the influence factor-evaluation index weight dataset is combined to accurately predict the flow field and concentration field information of the model that is not calculated by the computational fluid dynamics calculation model, and a data twin prediction model is formed.

[0091] S5, input the to-be-predicted ore pulp process data, obtain the ore pulp electrolysis process prediction result through the data twin prediction model, and visually display the ore pulp electrolysis process prediction result through a display.

[0092] In a feasible implementation, based on the to-be-predicted ore pulp process data, field information of the to-be-predicted ore pulp process data is obtained by querying and matching in the orthogonal field information database.

[0093] Then, according to the field information of the to-be-predicted ore pulp process data, a weight matrix w is calculated, and an absolute distance matrix D of the to-be-predicted ore pulp process data is calculated, and the weight distance W between the to-be-predicted ore pulp electrolysis process and a certain working condition is calculated according to formula (1), and formula (1) is as follows:

[0094] W=w θ D T (1)

[0095] Wherein, w=(w1,w2,...,w n ), n represents the total number of levels under each factor; D=(|p1-p0|,|p2-p0|,...,|p N -p0|), p N represents the level value corresponding to the Nth factor.

[0096] θ N represents the adjustment factor of the Nth factor.

[0097] Therefore, the weight distance W between the to-be-predicted ore pulp electrolysis process and all working conditions can be calculated d =(W1,W2,...,W N ).

[0098] According to the weight distance, k reasonable known working conditions are selected, and the value of k is generally 3-5. According to formula (2), the value X of the target working condition can be fitted from the values x of the k known flow field data working conditions, and formula (2) is as follows:

[0099]

[0100] wherein, w d，i is the ratio of the weight distance of the known to be predicted ore pulp electrolysis process to the sum of the distances of all to be predicted ore pulp electrolysis processes, when i = 1, i.e. k = 1, the calculation formula is as follows formula (3):

[0101]

[0102] Through the above steps, the data values of all grid points of the to-be-predicted ore pulp electrolysis process are calculated, and then the fitting data under any factor level combination is obtained, and the to-be-predicted ore pulp electrolysis process can be fitted through interpolation operation.

[0103] The nearest neighbor algorithm is used to find the K known points closest to the target point in the three-dimensional space and the corresponding Euclidean distances (d1, d2,..., dk) of the target point to the K known points. K The value of the target point is predicted through formula (4), and formula (4) is as follows:

[0104]

[0105] wherein, w K，i is the ratio of the reciprocal of the Euclidean distance of the target point to a known point to the sum of the reciprocals of the distances of the target point to all K known points, when i = 1, the calculation formula is as follows formula (5):

[0106]

[0107] Since Value known，i is the value of the i-th known point, the twin data of the to-be-predicted ore pulp electrolysis process can be obtained according to the interpolation method.

[0108] The present application provides a kind of ore pulp electrolysis process prediction method based on orthogonal analysis, is simulated by orthogonal analysis to influencing factor value, relies on orthogonality and reduces simulation quantity;Macro data of simulation calculation is reprocessed using interpolation algorithm, to establish the digital twin model of ore pulp electrolysis process about flow field and concentration field, greatly shorten model response time, solve the problem of long calculation period of traditional numerical model, can be better applied to real-time prediction of solid-liquid suspension in actual industrial production.The present application is a kind of ore pulp electrolysis process prediction method of instant efficient, visual.

[0109] Figure 2 is a kind of ore pulp electrolysis process prediction system block diagram based on orthogonal analysis according to an example embodiment.It is shown in reference Figure 2 , the system is applied to a kind of ore pulp electrolysis process prediction method based on orthogonal analysis, the system includes electronic equipment and display, wherein:

[0110] The electronic device 210 is configured to collect ore slurry electrolysis process data, obtain an influence factor dataset and an evaluation index dataset in the ore slurry electrolysis process, perform data orthogonal analysis based on the influence factor dataset to obtain an influence factor database, perform calculation based on the influence factor database and the evaluation index dataset to obtain an influence factor-evaluation index weight dataset, perform model construction based on the influence factor database and the influence factor-evaluation index weight dataset to obtain a data twin prediction model, input ore slurry process data to be predicted, and obtain ore slurry electrolysis process prediction results through the data twin prediction model.

[0111] The display 220 is configured to visually display the ore slurry electrolysis process prediction results through the display.

[0112] The influence factor dataset is a factor set that influences the results in the actual production process of the ore slurry electrolysis.

[0113] The influence factor dataset includes stirring speed, solid content, particle size, and particle density.

[0114] The evaluation index dataset is an index set that evaluates the results in the actual production process of the ore slurry electrolysis.

[0115] The evaluation index dataset includes suspension uniformity, particle concentration between the plates, and power consumption.

[0116] Optionally, the electronic device 210 is further configured to:

[0117] perform data orthogonal analysis based on the influence factor dataset to obtain a single-factor orthogonal dataset;

[0118] perform geometric modeling and simulation calculation based on the single-factor orthogonal dataset to obtain a single-factor orthogonal model example;

[0119] solve the single-factor orthogonal model example to obtain a velocity field single-factor orthogonal database and a concentration field single-factor orthogonal database;

[0120] obtain the influence factor database based on the velocity field single-factor orthogonal database and the concentration field single-factor orthogonal database.

[0121] Optionally, the electronic device 210 is further configured to:

[0122] obtain each evaluation index based on the evaluation index dataset;

[0123] perform matrix analysis based on the influence factor database and each evaluation index to obtain each index weight matrix;

[0124] perform data processing on each index weight matrix to obtain a processed each index weight matrix;

[0125] Based on the processed weight matrix of each index, the influence factors are calculated by arithmetic mean to obtain the influence factor-evaluation index weight data set.

[0126] Optionally, the electronic device 210 is further used for:

[0127] According to the influence factor database, the speed field single factor orthogonal database and the concentration field single factor orthogonal database are obtained.

[0128] The speed field single factor orthogonal database and the concentration field single factor orthogonal database are mathematically associated to obtain an associated orthogonal database.

[0129] According to the associated orthogonal database and the influence factor-evaluation index weight data set, a model is constructed to obtain a data twin prediction model.

[0130] The present application provides a kind of based on orthogonal analysis's ore pulp electrolytic process prediction method, by orthogonal analysis to influence factor numerical simulation, rely on orthogonality reduces the simulation quantity;Interpolation algorithm is used to the macro data of simulation calculation is reprocessed, to establish the digital twin model of ore pulp electrolytic process about flow field and concentration field, greatly reduce the model response time, solve the problem of long calculation period of traditional numerical model, can be better applied to actual industrial production on solid-liquid suspended real-time prediction.This application is a kind of instant efficient, visual ore pulp electrolytic process prediction method.

[0131] Figure 3 It is a kind of structure schematic diagram of electronic device 300 provided by the embodiment of the application, and the electronic device 300 can be greatly different due to configuration or performance, can include one or more processors (central processing units, CPU) 301 and one or more memories 302, wherein the memory 302 stores at least one instruction, the at least one instruction is loaded and executed by the processor 301 to realize the steps of the above-mentioned one kind of based on orthogonal analysis's ore pulp electrolytic process prediction method.

[0132] In exemplary embodiments, a computer readable storage medium, such as a memory including instructions executable by a processor in a terminal to complete the above-mentioned one kind of based on orthogonal analysis's ore pulp electrolytic process prediction method is also provided.For example, the computer readable storage medium can be ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk and optical data storage device, etc.

[0133] Those skilled in the art can understand that all or part of the steps of the above-mentioned embodiments can be completed by hardware, or can be instructed to relevant hardware by program. The program can be stored in a computer readable storage medium, and the storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

[0134] The above description is merely preferred embodiments of the present application, and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for predicting a process of ore electrolysis based on orthogonal analysis, characterized in that, The method comprises: Collecting ore slurry electrolysis process data to obtain an influence factor dataset and an evaluation index dataset in the ore slurry electrolysis process; Performing data orthogonal analysis according to the influence factor dataset to obtain an influence factor database; The orthogonal analysis according to the influence factor dataset to obtain the influence factor database comprises: Performing data orthogonal analysis according to the influence factor dataset to obtain a single-factor orthogonal dataset; Performing geometric modeling and simulation calculation on the single-factor orthogonal dataset to obtain a single-factor orthogonal model example; Solving the single-factor orthogonal model example to obtain a velocity field single-factor orthogonal database and a concentration field single-factor orthogonal database; Obtaining the influence factor database according to the velocity field single-factor orthogonal database and the concentration field single-factor orthogonal database; Performing calculation according to the influence factor database and the evaluation index dataset to obtain an influence factor-evaluation index weight dataset; Performing model construction according to the influence factor database and the influence factor-evaluation index weight dataset to obtain a data twin prediction model; Inputting ore slurry process data to be predicted, obtaining ore slurry electrolysis process prediction results through the data twin prediction model, and visually displaying the ore slurry electrolysis process prediction results through a display.

2. The method of claim 1, wherein the method is based on orthogonal analysis of the process. The influence factor dataset is a factor set influencing the results in the actual production process of ore slurry electrolysis; The influence factor dataset includes stirring speed, solid content, particle size, and particle density.

3. The method of claim 1, wherein the method is based on orthogonal analysis of the process. The evaluation index dataset is an index set evaluating the results in the actual production process of ore slurry electrolysis; The evaluation index dataset includes suspension uniformity, particle concentration between the plates, and power consumption.

4. The method of claim 1, wherein the method is based on orthogonal analysis of the process. The calculation according to the influence factor database and the evaluation index dataset to obtain the influence factor-evaluation index weight dataset comprises: Obtaining each evaluation index according to the evaluation index dataset; Performing matrix analysis according to the influence factor database and each evaluation index to obtain each index weight matrix; Performing data processing on each index weight matrix to obtain processed each index weight matrix; Performing arithmetic average calculation on the influence factors based on the processed each index weight matrix to obtain the influence factor-evaluation index weight dataset.

5. The method of claim 1, wherein the method is based on orthogonal analysis of the process. The model construction according to the influence factor database and the influence factor-evaluation index weight dataset to obtain the data twin prediction model comprises: Obtaining a velocity field single-factor orthogonal database and a concentration field single-factor orthogonal database according to the influence factor database; Performing mathematical correlation on the velocity field single-factor orthogonal database and the concentration field single-factor orthogonal database to obtain a correlated orthogonal database; Performing model construction according to the correlated orthogonal database and the influence factor-evaluation index weight dataset to obtain the data twin prediction model.

6. A system for predicting a mineral pulp electrolysis process based on orthogonal analysis, characterized by The system is used to implement a kind of ore slurry electrolysis process prediction method based on orthogonal analysis, and the system comprises an electronic device and a display, wherein: The electronic device is configured to collect ore pulp electrolysis process data, obtain an influence factor dataset and an evaluation index dataset in an ore pulp electrolysis process, perform data orthogonal analysis based on the influence factor dataset to obtain an influence factor database, perform calculation based on the influence factor database and the evaluation index dataset to obtain an influence factor-evaluation index weight dataset, perform model construction based on the influence factor database and the influence factor-evaluation index weight dataset to obtain a data twin prediction model, input to-be-predicted ore pulp process data, and obtain an ore pulp electrolysis process prediction result through the data twin prediction model. The electronic device is further configured to: perform data orthogonal analysis based on the influence factor dataset to obtain a single-factor orthogonal dataset; perform geometric modeling and simulation calculation on the single-factor orthogonal dataset to obtain a single-factor orthogonal model example; solve the single-factor orthogonal model example to obtain a velocity field single-factor orthogonal database and a concentration field single-factor orthogonal database; obtain the influence factor database based on the velocity field single-factor orthogonal database and the concentration field single-factor orthogonal database; the display is configured to visually display the ore pulp electrolysis process prediction result through the display.

7. A system for predicting a process of electrolysis of ore slurry based on orthogonal analysis according to claim 6, characterized in that, The electronic device is further configured to: obtain each evaluation index based on the evaluation index dataset; perform matrix analysis on the influence factor database and each evaluation index to obtain each index weight matrix; perform data processing on each index weight matrix to obtain a processed each index weight matrix; perform arithmetic average calculation on the influence factors based on the processed each index weight matrix to obtain the influence factor-evaluation index weight dataset.

8. A system for predicting a process of electrolysis of ore slurry based on orthogonal analysis according to claim 6, characterized in that, The electronic device is further configured to: obtain a velocity field single-factor orthogonal database and a concentration field single-factor orthogonal database based on the influence factor database; perform mathematical correlation on the velocity field single-factor orthogonal database and the concentration field single-factor orthogonal database to obtain a correlated orthogonal database; perform model construction based on the correlated orthogonal database and the influence factor-evaluation index weight dataset to obtain the data twin prediction model.

Images