Submerged arc furnace temperature measuring point generation method and device and storage medium

Abstract

The invention relates to a submerged arc furnace temperature measuring point generation method and device and a storage medium. The method comprises the steps that key parameters of a target submerged arc furnace are obtained; generating feature vectors of the target submerged arc furnace based on the key parameters of the target submerged arc furnace; respectively calculating a first distance between the feature vector of the target submerged arc furnace and the feature vector of each first submerged arc furnace; the first submerged arc furnace with the minimum first distance from the feature vector of the target submerged arc furnace is selected as a reference submerged arc furnace; acquiring all measuring points of the reference submerged arc furnace as first measuring points, and acquiring feature information and a temperature data sequence of each first measuring point; and calculating the comprehensive value of each first measuring point based on the obtained feature information and temperature data sequence of the first measuring points, sorting all the first measuring points according to the descending order of the comprehensive values, and selecting the first measuring points in the front as the measuring points of the target submerged arc furnace. Compared with the prior art, the method has the advantages that the measuring point distribution scheme of the submerged arc furnace of a novel model is automatically generated by utilizing the similarity between the submerged arc furnaces of different models, so that the design is aided by combining actual data, and the method is more scientific.

Description

Technical Field

[0001] The invention relates to the field of design of temperature measurement point layout schemes for submerged arc furnaces, and in particular to a method, a device and a storage medium for generating temperature measurement points for submerged arc furnaces. Background Art

[0002] In order to realize the intelligent control of the ore-heating furnace, it is necessary to arrange sensors in the ore-heating furnace. However, in the prior art, there is no standard and unified approach to the location of buried points in the ore-heating furnace. The industry's approach is often based on the experience of veterans or the mechanism of ore-heating furnace smelting. During the construction stage of a single ore-heating furnace or an ore-heating furnace of a single project, sensors are arranged in positions such as the furnace lining and furnace bottom, combined with the design drawings of a single ore-heating furnace. After implementation, the measurement effect is often poor, or the data is inaccurate and invalid, which affects the operator's judgment on the internal operating status of the furnace.

[0003] In order to improve the effect, some existing technologies will conduct feedback verification and repeated experiments to find the best burial point solution. However, due to the variable models of submerged arc furnaces, a new model of submerged arc furnace still needs to be redesigned for the burial point solution. At this time, the new solution still faces the problem of poor effect. Summary of the invention

[0004] The purpose of the present invention is to provide a method, device and storage medium for generating temperature measurement points of an electric arc furnace.

[0005] The purpose of the present invention can be achieved by the following technical solutions:

[0006] A method for generating temperature measurement points of an electric arc furnace, comprising:

[0007] Obtain key parameters of the target submerged arc furnace;

[0008] Based on the key parameters of the target ore-fired furnace, a feature vector of the target ore-fired furnace is generated;

[0009] respectively calculating first distances between a characteristic vector of a target ore-forming furnace and a characteristic vector of each first ore-forming furnace, wherein the first ore-forming furnace is an ore-forming furnace with a known arrangement of temperature measurement points;

[0010] Selecting a first submerged arc furnace with the smallest first distance to the characteristic vector of the target submerged arc furnace as a reference submerged arc furnace;

[0011] Acquire all measuring points of the reference ore-fired furnace as first measuring points, and acquire characteristic information and temperature data sequence of each first measuring point;

[0012] Based on the characteristic information and temperature data sequence of the first measuring points, the comprehensive value of each first measuring point is calculated, and all the first measuring points are sorted from large to small according to the comprehensive value, and the front part of the first measuring points are selected as the measuring points of the target ore furnace.

[0013] The key parameters of the target ore-forming furnace include a furnace identification, a furnace type and a plurality of furnace design parameters.

[0014] The furnace types include closed furnaces and non-closed furnaces.

[0015] The design parameters of the furnace include furnace lining thickness, furnace bottom thickness, furnace lining material and furnace lining thermal conductivity.

[0016] The first distance is the Euclidean distance.

[0017] The characteristic information includes the measuring point representation, the measuring point model and the measuring point location.

[0018] The step of calculating the comprehensive value of each first measuring point based on acquiring the characteristic information of the first measuring point and the temperature data sequence includes:

[0019] Obtaining the data validity value of each first measuring point according to the continuity of the temperature data sequence of each first measuring point itself;

[0020] Acquire multiple adjacent first measuring points according to the measuring point position of the first measuring point, and obtain the data rationality value of each first measuring point based on the temperature data of each first measuring point and the temperature data of the adjacent first measuring points at the same time;

[0021] The layout economic value of the first measuring point is obtained according to the ratio of the total price of the laid sensors to the volume of the first ore-bearing furnace;

[0022] Get the equipment life value based on the price of the sensor;

[0023] The comprehensive value is obtained based on the data validity value and data rationality value of each first measuring point combined with the layout economy value and equipment life value.

[0024] The step of obtaining the data validity value of each first measuring point according to the continuity of the temperature data sequence of each first measuring point itself includes:

[0025] Calculating the curvature of the temperature data of the first measuring point as a function of time;

[0026] Calculating a difference between the curvature and a curvature threshold;

[0027] The data validity value of each first measuring point is obtained by normalizing the difference values ​​of all first measuring points.

[0028] A device for generating temperature measurement points of an electric arc furnace comprises a memory, a processor, and a program stored in the memory. When the processor executes the program, the method described above is implemented.

[0029] A storage medium stores a program, which implements the above method when executed.

[0030] Compared with the prior art, the present invention has the following beneficial effects:

[0031] 1. By comparing the characteristics of the submerged arc furnace and utilizing the similarities between different types of submerged arc furnaces, the measurement point distribution plan for the new type of submerged arc furnace is automatically generated, thereby combining the actual data to assist in the design, which is more scientific.

[0032] 2. Before the new model of ore-fired furnace is put into operation, the design can be carried out by referring to the measurement point data performance of similar furnaces, which reduces the risk of poor measurement results and inability to reinstall after commissioning.

[0033] 3. As more and more submerged arc furnaces are put into operation, the more data is accumulated, the better the measurement point layout plan for new models of submerged arc furnaces will be, and the scale effect will be achieved.

[0034] 4. Consider the closed furnace and the non-closed furnace separately, so that the closed characteristics can be extracted and the convergence speed can be improved.

[0035] 5. According to the data validity value and data rationality value of each first measuring point, combined with the layout economy value and equipment life value, the comprehensive value can be obtained to improve accuracy.

[0036] 6. Use curvature analysis to calculate data validity values, thereby solving the problem of data drift and avoiding overall inaccuracy caused by local information. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 The figure is a schematic flow chart of the main steps of the method of the present invention. DETAILED DESCRIPTION

[0038] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. This embodiment is implemented based on the technical solution of the present invention, and provides a detailed implementation method and specific operation process, but the protection scope of the present invention is not limited to the following embodiments.

[0039] A method for generating temperature measurement points of an electric arc furnace, such as Figure 1 As shown, including:

[0040] (1) Obtaining key parameters of the target submerged arc furnace;

[0041] Specifically, in this embodiment, the submerged arc furnace data table structure is shown in Table 1:

[0042] Table 1

[0043]

[0044]

[0045] Table 1 specifically consists of the relationship between furnace-measurement point and measurement result of the measurement point, where the furnace identification is the field that identifies the uniqueness of the ore-fired furnace, and the furnace type, furnace design parameters, etc. are descriptions of other information of the ore-fired furnace. For the i-th ore-fired furnace, there may be Mi measurement points, and the measurement point identification is the field that identifies the uniqueness of the measurement point.

[0046] The set of furnaces is {S}, with S_1...S_I, corresponding to I submerged arc furnaces respectively. For the data structure S_i of the i-th submerged arc furnace, stove_type_i represents the furnace type, stove_tag_i represents the furnace identifier, and stove_para_1_i...stove_para_K_i are furnace design parameters 1 to K. Therefore, the data structure of a submerged arc furnace is: S_i = [stove_tag_i, stove_type_i, stove_para_1_i,..., stove_para_K_i].

[0047] For one measuring point, corresponding to one measuring point position, the physical entity of the measuring point is often a thermocouple, which is a device, that is, a temperature sensor installed in the furnace body, furnace lining or furnace bottom of the ore-fired furnace. Therefore, there are also fields for describing other information related to the measuring point, such as the measuring point model and the time the equipment has been put into use.

[0048] The set of measuring points is {D}, with D_1...D_Mi; for measuring point D_j, there are D_j parameters, device_stove_j is the identifier of the furnace installed at the measuring point, that is, Stove_tag, device_tag_j represents the measuring point identifier, device_type_j is the measuring point model and device_location_j is the measuring point location, and device_his_j is the time when the equipment has been put into use. Therefore, the data structure of a submerged arc furnace is: D_j = [device_stove_i, device_tag_j, device_type_j, device_location_j, device_his_j].

[0049] For one measuring point, at different time points, the temperature performance will be different due to different furnaces, different furnace conditions at different times, and different locations of the electric arc furnace.

[0050] The temperature of different measuring points at a certain time is indicated by T_t, where capital T represents temperature and lowercase t represents time.

[0051] When designing a measurement point layout for a new type of electric arc furnace, first of all, it is necessary to obtain the key parameters of the new type of electric arc furnace, including: furnace identification, furnace type, furnace design parameters, etc.

[0052] The target ore-fired furnace is S_new, that is, S_new = [stove_tag_new, stove_type_new, stove_para_1_new, ..., stove_para_K_new].

[0053] The specific key parameters can be obtained from Table 2.

[0054] Table 2

[0055]

[0056] Among them, Stove_type: 1 represents a closed stove, and 0 represents a non-closed stove.

[0057] Stove_para_n: represents n design parameters of the electric furnace, including but not limited to furnace lining thickness, furnace bottom thickness, furnace lining material, furnace lining thermal conductivity, etc.

[0058] (2) generating a characteristic vector of the target ore-fired furnace based on key parameters of the target ore-fired furnace;

[0059] The specific method is to encode the data

[0060] (3) respectively calculating a first distance between a characteristic vector of the target ore-forming furnace and a characteristic vector of each first ore-forming furnace, wherein the first ore-forming furnace is an ore-forming furnace with a known temperature measurement point arrangement scheme;

[0061] First, since different parameters have different dimensions, they need to be standardized.

[0062] Then calculate the Euclidean distance as the first distance, the formula is:

[0063]

[0064] Where: d(new,i) is the first distance between the target ore furnace and the i-th ore furnace, H is the length of the feature vector, new h is the hth element in the characteristic vector of the target ore-fired furnace, i h is the hth element in the characteristic vector of the i-th ore-arc furnace.

[0065] (iv) selecting the first submerged arc furnace with the smallest first distance from the characteristic vector of the target submerged arc furnace as the reference submerged arc furnace;

[0066] In this embodiment, only one reference ore-arcing furnace is selected as a similar furnace.

[0067] (V) Obtaining all measuring points of the reference ore-fired furnace as first measuring points, and obtaining characteristic information and temperature data sequences of each first measuring point;

[0068] (6) Calculating the comprehensive value of each first measuring point based on the characteristic information and temperature data sequence of the first measuring point, sorting all the first measuring points from large to small according to the comprehensive value, and selecting the front part of the first measuring points as the measuring points of the target ore furnace.

[0069] The characteristic information includes the measuring point representation, measuring point model and measuring point location.

[0070] The comprehensive value of each first measuring point is calculated based on the characteristic information of the first measuring point and the temperature data sequence, including:

[0071] Obtaining the data validity value of each first measuring point according to the continuity of the temperature data sequence of each first measuring point itself;

[0072] Acquire multiple adjacent first measuring points according to the measuring point position of the first measuring point, and obtain the data rationality value of each first measuring point based on the temperature data of each first measuring point and the temperature data of the adjacent first measuring points at the same time;

[0073] The layout economic value price_j of the first measuring point is obtained according to the ratio of the total price of the deployed sensors to the volume of the first ore-fired furnace;

[0074] Get the device life span value lifespan_j according to the price of the sensor;

[0075] According to the data validity value and data rationality value of each first measuring point, combined with the layout economy value and equipment life value, the comprehensive value Z_j is obtained:

[0076] Z_j=x*effectiveness_j+y*rationality_j+z*price_j+w*lifespan_j

[0077] x+y+z+w=1

[0078] Among them, x, y, z and w are weights.

[0079] In this embodiment, the data validity value of each first measuring point is obtained according to the continuity of the temperature data sequence of each first measuring point itself, including:

[0080] Calculating the curvature of the temperature data of the first measuring point as a function of time;

[0081] Calculate the difference between the curvature and the curvature threshold;

[0082] The data effectiveness value of each first measuring point is obtained by normalizing the differences of all first measuring points, which is specifically defined as effectiveness_j.

[0083] And, in this embodiment, for the data rationality value, the data standard deviation s_r_j of the measuring point D_j and its four adjacent measuring points at the same time is calculated, a suitable threshold s_r_base is selected, the difference between s_r_j and s_r_base is calculated, and the difference is standardized to a score of 0-100%, which is defined as rationality_j.

[0084] In addition, in this embodiment, the comprehensive values ​​of all measuring points are ranked, and the first 75% of the measuring points are selected and retained as the measuring point positions of the target ore-fired furnace.

[0085] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several 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, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program code.

Claims

1. A method for generating temperature measurement points of an electric arc furnace, characterized in that: include: Obtain key parameters of the target submerged arc furnace; Based on the key parameters of the target ore-fired furnace, a feature vector of the target ore-fired furnace is generated; respectively calculating first distances between a characteristic vector of a target ore-forming furnace and a characteristic vector of each first ore-forming furnace, wherein the first ore-forming furnace is an ore-forming furnace with a known arrangement of temperature measurement points; Selecting a first submerged arc furnace with the smallest first distance to the characteristic vector of the target submerged arc furnace as a reference submerged arc furnace; Acquire all measuring points of the reference ore-fired furnace as first measuring points, and acquire characteristic information and temperature data sequence of each first measuring point; Based on the characteristic information and temperature data sequence of the first measuring points, the comprehensive value of each first measuring point is calculated, and all the first measuring points are sorted from large to small according to the comprehensive value, and the front part of the first measuring points are selected as the measuring points of the target ore furnace.

2. A method for generating temperature measurement points of a submerged arc furnace according to claim 1, characterized in that: The key parameters of the target ore-forming furnace include a furnace identification, a furnace type and a plurality of furnace design parameters.

3. A method for generating temperature measurement points of a submerged arc furnace according to claim 2, characterized in that: The furnace types include closed furnaces and non-closed furnaces.

4. A method for generating temperature measurement points of a submerged arc furnace according to claim 2, characterized in that: The design parameters of the furnace include furnace lining thickness, furnace bottom thickness, furnace lining material and furnace lining thermal conductivity.

5. The method for generating temperature measurement points of a submerged arc furnace according to claim 1, characterized in that: The first distance is the Euclidean distance.

6. A method for generating temperature measurement points of a submerged arc furnace according to claim 1, characterized in that: The characteristic information includes the measuring point representation, the measuring point model and the measuring point location.

7. A method for generating temperature measurement points of a submerged arc furnace according to claim 6, characterized in that: The step of calculating the comprehensive value of each first measuring point based on acquiring the characteristic information of the first measuring point and the temperature data sequence includes: Obtaining the data validity value of each first measuring point according to the continuity of the temperature data sequence of each first measuring point itself; Acquire multiple adjacent first measuring points according to the measuring point position of the first measuring point, and obtain the data rationality value of each first measuring point based on the temperature data of each first measuring point and the temperature data of the adjacent first measuring points at the same time; The layout economic value of the first measuring point is obtained according to the ratio of the total price of the laid sensors to the volume of the first ore-bearing furnace; Get the equipment life value based on the price of the sensor; The comprehensive value is obtained based on the data validity value and data rationality value of each first measuring point combined with the layout economy value and equipment life value.

8. A method for generating temperature measurement points of a submerged arc furnace according to claim 6, characterized in that: The step of obtaining the data validity value of each first measuring point according to the continuity of the temperature data sequence of each first measuring point itself includes: Calculating the curvature of the temperature data of the first measuring point as a function of time; Calculating a difference between the curvature and a curvature threshold; The data validity value of each first measuring point is obtained by normalizing the difference values ​​of all first measuring points.

9. A device for generating temperature measurement points of an electric arc furnace, comprising a memory, a processor, and a program stored in the memory, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 8 is implemented.

10. A storage medium having a program stored thereon, characterized in that: When the program is executed, the method according to any one of claims 1 to 8 is implemented.

Images