A copper concentrate smelting process prediction method and system based on orthogonal data weights

Abstract

The present application relates to the technical field of metal smelting process simulation, in particular to a copper concentrate smelting process prediction method and system based on orthogonal data weight.A copper concentrate smelting process prediction method based on orthogonal data weight comprises the following steps: collecting smelting furnace data to obtain a working condition list data set; constructing a database according to the working condition list data set to obtain a field information database; performing orthogonal weight analysis on the field information data according to the field information database to obtain a process weight data set; inputting target smelting furnace data, and performing twin data fitting according to the working condition list data set, the field information database and the process weight data set to obtain target smelting process twin data; and performing visual display on a display according to the target smelting process twin data.The present application is a high-efficiency and instant copper concentrate smelting process prediction method.

Description

Technical Field

[0001] The present invention relates to the technical field of metal smelting process simulation, and in particular to a method and system for predicting a copper concentrate smelting process based on orthogonal data weights. Background Art

[0002] Bath smelting has no specific requirements for the particle size or moisture content of the copper concentrate. During production, the copper concentrate is dropped directly from the furnace top into a turbulent, swirling bath, where it undergoes oxidation smelting under the stirring action of oxygen-enriched air. Its key advantage is its adaptability to raw materials, enabling it to process complex copper-bearing materials and low-grade copper concentrates. It also allows for wet pelletizing to reduce dust content in the flue gas. As rich ore resources decrease, the grade of copper ore used in production gradually decreases, and the proportion of difficult-to-process, multi-metallic, complex copper ores continues to increase, the advantages of bath smelting will gradually become apparent.

[0003] As raw materials, working conditions, spray gun structure, etc. change, the multiphase flow field movement in the furnace will also change accordingly, which will have a significant impact on the entire smelting process and indicators. However, in a high-temperature smelting environment, it is difficult to conduct online real-time monitoring of the actual conditions in the furnace. Simulation research using experimental and simulation methods often takes weeks or even months, making it impossible to immediately control the smelting process and achieve the goal of stable production.

[0004] For the high-temperature system of copper concentrate bath smelting, CFD technology can quantitatively establish the relationships between the velocity field within the furnace, the distribution of matte-slag, and other operating conditions, such as slag properties, injection conditions, and lance layout, and achieve visual three-dimensional analysis. However, due to the complex multiphase motion of matte-slag within top-blown, side-blown, and bottom-blown bath smelting furnaces, steady-state simulations cannot accurately describe the field distribution within the furnace. Transient simulations require iterative solutions with very small time steps, significantly increasing the CFD modeling and computational load. Simulating the multiphase flow field of matte-slag within the smelting furnace requires approximately 1,000 core hours for a single condition. Simulating all possible conditions would be prohibitively expensive. Simulating a single condition in real time would be time-consuming and inefficient, making it difficult to meet the real-time requirements of production control. Currently, smelting process control still relies heavily on control systems based on simple material balance calculations or manual experience.

[0005] In the existing technology, there is a lack of an efficient and timely method for predicting the copper concentrate smelting process. Summary of the Invention

[0006] The present invention provides a method and system for predicting the copper concentrate smelting process based on orthogonal data weights. The technical solution is as follows:

[0007] In one aspect, a method for predicting a copper concentrate smelting process based on orthogonal data weights is provided. The method is implemented by an electronic device and includes:

[0008] Collect smelting furnace data and obtain working condition list data set;

[0009] Building a database based on the working condition list data set to obtain a field information database;

[0010] performing an orthogonal weight analysis on the field information data according to the field information database to obtain a process weight data set;

[0011] Inputting target smelting furnace data, performing twin data fitting based on the operating condition list data set, the field information database, and the process weight data set to obtain target smelting process twin data;

[0012] The target smelting process twin data is visualized through a display.

[0013] Optionally, collecting smelting furnace data to obtain a working condition list data set includes:

[0014] Collect smelting furnace data and obtain smelting process conditions;

[0015] Calculate according to the process conditions of the smelting process to obtain a working condition list data set;

[0016] The smelting process conditions include top-blowing furnace process conditions, side-blowing furnace process conditions and bottom-blowing furnace process conditions.

[0017] Optionally, constructing a database based on the operating condition list data set to obtain a field information database includes:

[0018] Obtaining modeling data and simulation data according to the operating condition list data set;

[0019] constructing a model according to the modeling data to obtain a model database;

[0020] Perform simulation calculations based on the simulation data to obtain a simulation database;

[0021] A field information database is obtained according to the model database and the simulation database.

[0022] Optionally, performing orthogonal weight analysis on the field information data according to the field information database to obtain a process weight data set includes:

[0023] Based on the field information database, a matrix analysis method is used to analyze and obtain a multi-layer structure model;

[0024] Calculate according to the multi-layer structure model to obtain the structure matrix of each layer;

[0025] The weights of the layers are calculated based on the structure matrix to obtain a process weight data set.

[0026] Optionally, the input target smelting furnace data, performing twin data fitting according to the operating condition list data set, the field information database, and the process weight data set to obtain target smelting process twin data, includes:

[0027] Obtaining a target operating condition data set according to the target smelting furnace data and the operating condition list data set;

[0028] Obtaining target field information according to the target operating condition data set and the field information database;

[0029] Obtaining target weight data according to the target operating condition data set and the process weight data set;

[0030] An interpolation operation is performed based on the target field information and the target weight data to obtain target smelting process twin data.

[0031] On the other hand, a copper concentrate smelting process prediction system based on orthogonal data weights is provided. The system is applied to a copper concentrate smelting process prediction method based on orthogonal data weights. The system includes an electronic device and a display, wherein:

[0032] The electronic device is used to collect smelting furnace data to obtain a working condition list data set; construct a database based on the working condition list data set to obtain a field information database; perform orthogonal weight analysis on the field information data based on the field information database to obtain a process weight data set; input target smelting furnace data, perform twin data fitting based on the working condition list data set, the field information database, and the process weight data set to obtain target smelting process twin data;

[0033] The display is used for visual display based on the target smelting process twin data.

[0034] Optionally, the electronic device is further configured to:

[0035] Collect smelting furnace data and obtain smelting process conditions;

[0036] Calculate according to the process conditions of the smelting process to obtain a working condition list data set;

[0037] The smelting process conditions include top-blowing furnace process conditions, side-blowing furnace process conditions and bottom-blowing furnace process conditions.

[0038] Optionally, the electronic device is further configured to:

[0039] Obtaining modeling data and simulation data according to the operating condition list data set;

[0040] constructing a model according to the modeling data to obtain a model database;

[0041] Perform simulation calculations based on the simulation data to obtain a simulation database;

[0042] A field information database is obtained according to the model database and the simulation database.

[0043] Optionally, the electronic device is further configured to:

[0044] Based on the field information database, a matrix analysis method is used to analyze and obtain a multi-layer structure model;

[0045] Calculate according to the multi-layer structure model to obtain the structure matrix of each layer;

[0046] The weights of the layers are calculated based on the structure matrix to obtain a process weight data set.

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

[0048] Obtaining a target operating condition data set according to the target smelting furnace data and the operating condition list data set;

[0049] Obtaining target field information according to the target operating condition data set and the field information database;

[0050] Obtaining target weight data according to the target operating condition data set and the process weight data set;

[0051] An interpolation operation is performed based on the target field information and the target weight data to obtain target smelting process twin data.

[0052] On the other hand, an electronic device is provided, comprising a processor and a memory, wherein the memory stores at least one instruction, and the at least one instruction is loaded and executed by the processor to implement the above-mentioned copper concentrate smelting process prediction method based on orthogonal data weights.

[0053] On the other hand, a computer-readable storage medium is provided, wherein at least one instruction is stored in the storage medium, and the at least one instruction is loaded and executed by a processor to implement the above-mentioned copper concentrate smelting process prediction method based on orthogonal data weights.

[0054] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0055] The present invention proposes a method for predicting the copper concentrate smelting process based on orthogonal data weights. Through the designed orthogonal field information data, the amount of calculation data required for the database is greatly reduced; and through the division of watersheds, a process weight data set is established for the influence of different flow field conditions in the furnace. The twin data of the target working condition field information obtained based on the local weight fitting of different watersheds has better accuracy. The present invention solves the problem that the field information in the top-blown smelting furnace is difficult to measure and the working conditions cannot be detected and controlled in real time due to the long calculation cycle of the multiphase flow field simulation. The generation of twin data only takes 10-20 seconds, which greatly improves the immediacy of obtaining furnace condition information. The present invention is an efficient and immediate method for predicting the copper concentrate smelting process. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0057] Figure 1 This is a flow chart of a method for predicting a copper concentrate smelting process based on orthogonal data weights provided by an embodiment of the present invention;

[0058] Figure 2 This is a block diagram of a copper concentrate smelting process prediction system based on orthogonal data weights provided by an embodiment of the present invention;

[0059] Figure 3 It is a structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0060] In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0061] The embodiment of the present invention provides a method for predicting the copper concentrate smelting process based on orthogonal data weights, which can be implemented by an electronic device, which can be a terminal or a server. Figure 1 The flowchart of a method for predicting the copper concentrate smelting process based on orthogonal data weights is shown. The processing flow of the method may include the following steps:

[0062] S1. Collect smelting furnace data and obtain a working condition list data set.

[0063] Optionally, collect smelting furnace data to obtain a working condition list data set, including:

[0064] Collect smelting furnace data and obtain smelting process conditions;

[0065] According to the calculation of the smelting process conditions, a working condition list data set is obtained;

[0066] The smelting process conditions include top blowing furnace process conditions, side blowing furnace process conditions and bottom blowing furnace process conditions.

[0067] In a feasible implementation, in the present application, the smelting process conditions for which the orthogonal data is to be established are determined according to different smelting furnaces.

[0068] The top blowing furnace process conditions include lance diameter, lance immersion depth, air pressure and air volume, lance bending angle, liquid level height, slag- matte ratio, etc.

[0069] The side blowing furnace process conditions include air eye diameter, air eye horizontal position, air eye vertical position, air eye spacing, air pressure and air volume, liquid level height, slag-matte ratio, etc.

[0070] The bottom blowing furnace process conditions include lance diameter, lance arrangement angle, lance spacing, air pressure and air volume, liquid level height, slag-matte ratio, etc.

[0071] According to the smelting process conditions, the quantities to be calculated for each process condition are determined, the orthogonal data working condition list of N factors and N levels is determined, and the minimum value and the maximum value of the process conditions that can be predicted under different working conditions are given.

[0072] S2, according to the working condition list data set, a database is constructed to obtain a field information database.

[0073] Optionally, according to the working condition list data set, a database is constructed to obtain a field information database, which includes:

[0074] According to the working condition list data set, modeling data and simulation data are obtained;

[0075] According to the modeling data, a model is constructed to obtain a model database;

[0076] According to the simulation data, simulation calculation is performed to obtain a simulation simulation database;

[0077] According to the model database and the simulation simulation database, a field information database is obtained.

[0078] In a feasible implementation, in the present application, the working condition list of orthogonal data established is subjected to modeling and simulation calculation, and field information data such as instantaneous and average velocity field, phase distribution field and turbulent kinetic energy field under different working conditions are calculated and output in accordance with a specific name and data information arrangement format.

[0079] The data name should show the calculation conditions of the calculated working condition, and the format can be "Condition 1_Condition 2_Condition 3_Condition 4"; the arrangement format of data information can be "x coordinate, y coordinate, z coordinate, x-direction speed, y-direction speed, z-direction speed, gas phase volume fraction, slag phase volume fraction, matte phase volume fraction, turbulent kinetic energy, turbulent dissipation rate".

[0080] S3. Based on the field information database, perform orthogonal weight analysis on the field information data to obtain a process weight data set.

[0081] Optionally, an orthogonal weight analysis is performed on the field information data according to the field information database to obtain a process weight data set, including:

[0082] Based on the field information database, a matrix analysis method is used to obtain a multi-layer structure model;

[0083] Calculate according to the multi-layer structure model to obtain the structure matrix of each layer;

[0084] The weights are calculated according to the structure matrix of each layer to obtain the process weight data set.

[0085] In a feasible implementation manner, the present invention divides the flow field area of ​​the smelting furnace into several flow field areas based on the smelting furnace data and combined with the flow field characteristics in the smelting furnace, such as: blowing area, circulation area, splashing area, sedimentation area, and dead area. Each flow field area can be further divided into multiple parts, and the flow field in the furnace is divided into 10-30 flow basins.

[0086] Within each watershed, an orthogonal weight analysis is performed on the data in the field information database. Matrix analysis is used to establish a multi-layered structural model reflecting the data characteristics. The structural matrix for each layer is calculated, and the weight matrix for the entire watershed is calculated from each layer's matrix. Ultimately, the weights of the impact of different process conditions on the flow field are determined within each watershed. By combining the weights of all process conditions, a process weight dataset is generated.

[0087] S4. Input the target smelting furnace data, perform twin data fitting based on the working condition list data set, the field information database, and the process weight data set to obtain the target smelting process twin data.

[0088] Optionally, the target smelting furnace data is input, and twin data fitting is performed based on the operating condition list data set, the field information database, and the process weight data set to obtain the target smelting process twin data, including:

[0089] Obtaining a target operating condition data set according to target smelting furnace data and an operating condition list data set;

[0090] Obtain target field information based on the target working condition data set and the field information database;

[0091] Obtain target weight data according to the target working condition data set and the process weight data set;

[0092] Interpolation operation is performed based on the target field information and target weight data to obtain the target smelting process twin data.

[0093] In a feasible implementation manner, target smelting furnace data is matched with smelting furnace data in the operating condition list data set, and the operating condition with unknown flow field data is obtained, which is called the target operating condition.

[0094] Based on the query and matching of the target working condition in the field information database, the field information of the target smelting furnace is obtained. Then, based on the process weight data set, the weight matrix in different flow domains or the weight matrix w of different grids of the working condition flow field under all the set factor level combinations is obtained. Then, the absolute distance matrix D between the working conditions is calculated, and the weight distance W between the target working condition and a certain working condition is calculated according to formula (1). Formula (1) is shown as follows:

[0095] W=wθD T (1)

[0096] Where 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 Indicates the level value corresponding to the Nth factor.

[0097] θ N represents the adjustment factor of the Nth factor.

[0098] From this, the weighted distance W between the target working condition and all working conditions can be calculated d =(W1, W2, ..., W N ).

[0099] Based on the weighted distance, k reasonable known working conditions are selected. The value of k is generally 3 to 5. It can be considered that the process conditions of these k working conditions are close to the target working conditions. The value X of the target working condition can be fitted from the value x of the working conditions of k known flow field data according to formula (2). Formula (2) is shown as follows:

[0100]

[0101] Among them, w d，i It is the ratio of the weighted distance of a known working condition to the sum of the weighted distances of all working conditions. When i = 1, that is, k = 1, its calculation formula is as follows (3):

[0102]

[0103] The data values of all flow fields or grid points of the target working condition are calculated through the above steps, and the flow field data under any factor level combination are obtained, and any position (point) or flow field in the target working condition flow field can be fitted through interpolation operation.

[0104] The nearest neighbor algorithm is used to find the K known points closest to the target point in the three-dimensional space in terms of the Euclidean distance, and the corresponding Euclidean distances (d1, d2,..., dk) are obtained. K The value of the target point is predicted through formula (4) as follows:

[0105]

[0106] Wherein, w K，i is the ratio of the reciprocal of the Euclidean distance between the target point and a known point to the sum of the reciprocals of the distances between the target point and all K known points, and when i = 1, the calculation formula is as follows (5):

[0107]

[0108] Since Value known，i is the value of the i-th known point, the smelting process twin data of different flow field information in the target working condition flow field range can be obtained according to the interpolation method.

[0109] S5, according to the target smelting process twin data, visual display is performed through the display.

[0110] In a feasible implementation, in the present application, the smelting process twin data obtained in the above steps are converted into smelting process demonstration animation, and the smelting process demonstration animation is displayed by the display. At the same time, the visual field information display can be performed according to actual needs, such as the flow field cross-section position, image resolution, etc. The process of converting the smelting process twin data into demonstration animation adopts the existing technology, and will not be described here.

[0111] The present application provides a copper concentrate smelting process prediction method based on orthogonal data weight, which greatly reduces the number of calculation data required by the database through the designed orthogonal field information data; and the process weight data set of the conditions affecting the different flow fields in the furnace is established through flow field division, and the twin data of the target working condition field information fitted based on the local weight of different flow fields has better accuracy. The present application solves the problems of difficult measurement of field information in top-blown smelting furnace, long simulation calculation period of multiphase flow field, and inability to detect and control the working condition in time. The generation of twin data only needs 10-20s, which greatly improves the immediacy of obtaining furnace condition information. The present application is a high-efficiency and instant copper concentrate smelting process prediction method.

[0112] Figure 2 This is a block diagram of a copper concentrate smelting process prediction system based on orthogonal data weights according to an exemplary embodiment. The system is applied to a copper concentrate smelting process prediction method based on orthogonal data weights. Figure 2 , the system includes an electronic device and a display, wherein:

[0113] Electronic device 210 is used to collect smelting furnace data and obtain a working condition list data set; construct a database based on the working condition list data set to obtain a field information database; perform orthogonal weight analysis on the field information data based on the field information database to obtain a process weight data set; input target smelting furnace data, perform twin data fitting based on the working condition list data set, the field information database, and the process weight data set to obtain target smelting process twin data;

[0114] The display 220 is used for visual display based on the target smelting process twin data.

[0115] Optionally, the electronic device 210 is further configured to:

[0116] Collect smelting furnace data and obtain smelting process conditions;

[0117] Calculate according to the process conditions of the smelting process to obtain the working condition list data set;

[0118] The process conditions of the smelting process include top-blowing furnace process conditions, side-blowing furnace process conditions and bottom-blowing furnace process conditions.

[0119] Optionally, the electronic device 210 is further configured to:

[0120] Obtain modeling data and simulation data based on the working condition list data set;

[0121] Construct a model based on the modeling data to obtain a model database;

[0122] Perform simulation calculations based on the simulation data to obtain a simulation database;

[0123] A field information database is obtained based on the model database and the simulation database.

[0124] Optionally, the electronic device 210 is further configured to:

[0125] Based on the field information database, a matrix analysis method is used to obtain a multi-layer structure model;

[0126] Calculate according to the multi-layer structure model to obtain the structure matrix of each layer;

[0127] The weights are calculated according to the structure matrix of each layer to obtain the process weight data set.

[0128] Optionally, the electronic device 210 is further configured to:

[0129] Obtaining a target operating condition data set according to target smelting furnace data and an operating condition list data set;

[0130] Obtain target field information based on the target working condition data set and the field information database;

[0131] Obtain target weight data according to the target working condition data set and the process weight data set;

[0132] Interpolation operation is performed based on the target field information and target weight data to obtain the target smelting process twin data.

[0133] The present invention proposes a method for predicting the copper concentrate smelting process based on orthogonal data weights. Through the designed orthogonal field information data, the amount of calculation data required for the database is greatly reduced; and through the division of watersheds, a process weight data set is established for the influence of different flow field conditions in the furnace. The twin data of the target working condition field information obtained based on the local weight fitting of different watersheds has better accuracy. The present invention solves the problem that the field information in the top-blown smelting furnace is difficult to measure and the working conditions cannot be detected and controlled in real time due to the long calculation cycle of the multiphase flow field simulation. The generation of twin data only takes 10-20 seconds, which greatly improves the immediacy of obtaining furnace condition information. The present invention is an efficient and immediate method for predicting the copper concentrate smelting process.

[0134] Figure 3 It is a structural diagram of an electronic device 300 provided in an embodiment of the present invention. The electronic device 300 may have relatively large differences due to different configurations or performances, and may 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, and the at least one instruction is loaded and executed by the processor 301 to implement the steps of the above-mentioned copper concentrate smelting process prediction method based on orthogonal data weights.

[0135] In an exemplary embodiment, a computer-readable storage medium is also provided, such as a memory including instructions. The instructions are executable by a processor in a terminal to implement the above-described method for predicting a copper concentrate smelting process based on orthogonal data weights. For example, the computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, or optical data storage device.

[0136] Those skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware, or by a program to instruct the relevant hardware, and the program may be stored in a computer-readable storage medium, which may be a read-only memory, a disk, or an optical disk, etc.

[0137] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for predicting copper concentrate smelting process based on orthogonal data weights, characterized in that: The method comprises: Collect smelting furnace data and obtain working condition list data set; Building a database based on the working condition list data set to obtain a field information database; performing an orthogonal weight analysis on the field information data according to the field information database to obtain a process weight data set; Inputting target smelting furnace data, performing twin data fitting based on the operating condition list data set, the field information database, and the process weight data set to obtain target smelting process twin data; The target smelting furnace data is input, and twin data fitting is performed according to the operating condition list data set, the field information database, and the process weight data set to obtain target smelting process twin data, including: Obtaining a target operating condition data set according to the target smelting furnace data and the operating condition list data set; Obtaining target field information according to the target operating condition data set and the field information database; Obtaining target weight data according to the target operating condition data set and the process weight data set; Performing an interpolation operation based on the target field information and the target weight data to obtain target smelting process twin data; The target smelting furnace data is matched with the smelting furnace data in the working condition list data set to obtain the working condition with unknown flow field data, which is called the target working condition; based on the target working condition, a query and match is performed in the field information database to obtain the target field information of the target smelting furnace; According to the process weight data set, the weight matrix w under all the set factor level combinations is obtained, and then the absolute distance matrix D between the working conditions is calculated. The weight distance W is calculated according to formula (1). Formula (1) is shown as follows: W=wθD T (1); Where w=(w1, w2, ..., w n ), n represents the total number of factor levels under each factor; D = (|p1-p0|, |p2-p0|, ..., |p N -p0|), p N Indicates the factor level value corresponding to the Nth factor; θ N represents the adjustment factor of the Nth factor; From this, the weighted distance W between the target working condition and all working conditions can be calculated d =(W1, W2, ..., W N ); Based on the target working condition data set, k working condition data are selected according to the weighted distance; the value X of the target working condition is fitted from the value x of the k working condition data according to formula (2), which is shown as follows: Among them, w d，i It is the ratio of the weighted distance of a known single working condition to the sum of the weighted distances of all working conditions. When i = 1, that is, k = 1, its calculation formula is as follows (3): Through the above steps, the data values ​​of all the watersheds or grid points of the target working condition are calculated, and then the flow field data under any factor level combination are obtained. Then, the interpolation operation can be used to fit any position or watershed in the flow field of the target working condition. The target smelting process twin data of different flow field information within the target working condition flow field range are obtained according to the interpolation method; The target smelting process twin data is visualized through a display.

2. The method for predicting the copper concentrate smelting process based on orthogonal data weights according to claim 1, characterized in that: The collecting of smelting furnace data to obtain a working condition list data set includes: Collect smelting furnace data and obtain smelting process conditions; Calculate according to the process conditions of the smelting process to obtain a working condition list data set; The smelting process conditions include top-blowing furnace process conditions, side-blowing furnace process conditions and bottom-blowing furnace process conditions.

3. The method for predicting the copper concentrate smelting process based on orthogonal data weights according to claim 1, characterized in that: The step of constructing a database based on the working condition list data set to obtain a field information database includes: Obtaining modeling data and simulation data according to the operating condition list data set; constructing a model according to the modeling data to obtain a model database; Perform simulation calculations based on the simulation data to obtain a simulation database; A field information database is obtained according to the model database and the simulation database.

4. A copper concentrate smelting process prediction system based on orthogonal data weights, characterized in that: The system is used to implement a copper concentrate smelting process prediction method based on orthogonal data weights. The copper concentrate smelting process prediction system based on orthogonal data weights includes an electronic device and a display, wherein: The electronic device is used to collect smelting furnace data to obtain a working condition list data set; construct a database based on the working condition list data set to obtain a field information database; perform orthogonal weight analysis on the field information data based on the field information database to obtain a process weight data set; input target smelting furnace data, perform twin data fitting based on the working condition list data set, the field information database, and the process weight data set to obtain target smelting process twin data; Wherein, the electronic device is further used for: Obtaining a target operating condition data set according to the target smelting furnace data and the operating condition list data set; Obtaining target field information according to the target operating condition data set and the field information database; Obtaining target weight data according to the target operating condition data set and the process weight data set; Performing an interpolation operation based on the target field information and the target weight data to obtain target smelting process twin data; The target smelting furnace data is matched with the smelting furnace data in the working condition list data set to obtain the working condition with unknown flow field data, which is called the target working condition; based on the target working condition, a query and match is performed in the field information database to obtain the target field information of the target smelting furnace; According to the process weight data set, the weight matrix w under all the set factor level combinations is obtained, and then the absolute distance matrix D between the working conditions is calculated. The weight distance W is calculated according to formula (1). Formula (1) is shown as follows: W=wθD T (1); Where w=(w1, w2, ..., w n ), n represents the total number of factor levels under each factor; D = (|p1-p0|, |p2-p0|, ..., |p N -p0|), p N Indicates the factor level value corresponding to the Nth factor; θ N represents the adjustment factor of the Nth factor; From this, the weighted distance W between the target working condition and all working conditions can be calculated d =(W1, W2, ..., W N ); Based on the target working condition data set, k working condition data are selected according to the weighted distance; the value X of the target working condition is fitted from the value x of the k working condition data according to formula (2), which is shown as follows: Among them, w d，i It is the ratio of the weighted distance of a known single working condition to the sum of the weighted distances of all working conditions. When i = 1, that is, k = 1, its calculation formula is as follows (3): Through the above steps, the data values ​​of all the watersheds or grid points of the target working condition are calculated, and then the flow field data under any factor level combination are obtained. Then, the interpolation operation can be used to fit any position or watershed in the flow field of the target working condition. The target smelting process twin data of different flow field information within the target working condition flow field range are obtained according to the interpolation method; The display is used for visual display based on the target smelting process twin data.

5. A copper concentrate smelting process prediction system based on orthogonal data weights according to claim 4, characterized in that: The electronic device is further used for: Collect smelting furnace data and obtain smelting process conditions; Calculate according to the process conditions of the smelting process to obtain a working condition list data set; The smelting process conditions include top-blowing furnace process conditions, side-blowing furnace process conditions and bottom-blowing furnace process conditions.

6. A copper concentrate smelting process prediction system based on orthogonal data weights according to claim 4, characterized in that: The electronic device is further used for: Obtaining modeling data and simulation data according to the operating condition list data set; constructing a model according to the modeling data to obtain a model database; Perform simulation calculations based on the simulation data to obtain a simulation database; A field information database is obtained according to the model database and the simulation database.

Images