In-furnace melt component detection method and system, storage medium and electronic equipment

Abstract

The invention belongs to the technical field of laser spectrum analysis, and provides an in-furnace melt component detection method and system, a storage medium and electronic equipment.The method comprises the steps that an original multi-furnace-number, multi-furnace-period and multi-point-location spectrum data set is obtained, and the original multi-furnace-number, multi-furnace-period and multi-point-location spectrum data set is preprocessed to obtain a multi-furnace-number, multi-furnace-period and multi-point-location spectrum data set; a preprocessed multi-furnace-number, multi-furnace-period and multi-point-location spectrum data set is obtained; constructing a plurality of quantitative detection models on the basis of the preprocessed multi-furnace-time multi-furnace-period multi-point-location spectral data set; and selecting an applicable quantitative detection model from the plurality of quantitative detection models, and detecting the melt components in the furnace by using the applicable quantitative detection model to obtain a detection result. According to the method, the defect of representativeness of single-point sampling of a sampling rod is overcome, the influence of factors such as physical characteristics and texture of melts in different furnace periods in the smelting process on a detection result is reduced, and the detection precision and the accuracy of the detection result are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of laser spectrum analysis, and in particular relates to a method, system, storage medium and electronic equipment for detecting the composition of a melt in a furnace. Background Art

[0002] During the smelting process, it is necessary to pay real-time attention to the composition of the materials in the reactor and promptly adjust core smelting parameters such as material ratio and input amount.

[0003] Currently, fluorescence analysis is mainly used to conduct periodic and high-frequency testing of materials. However, fluorescence analysis requires manual sampling, sample preparation, and testing processes, and the test results have a certain lag.

[0004] Laser-induced breakdown spectroscopy (LIBS) is an emerging atomic emission spectroscopic analysis technique with advantages such as no sample preparation and online, in-situ detection. It enables real-time online material detection and real-time control of auxiliary processes. However, it can be affected by on-site flue gas, large liquid level fluctuations, and surface scum. Sampling with a sampling rod can reduce the impact of on-site working conditions, but the sampling rod passes through a layer of surface scum, causing the scum to adhere to the outermost layer of the probe. Furthermore, the surface morphology and texture of the material on the sampling rod vary significantly during different stages of a single smelting process in a reactor. Direct detection and modeling will affect the quantitative analysis accuracy of LIBS. Summary of the Invention

[0005] The present invention provides a method, system, storage medium and electronic equipment for detecting the composition of a melt in a furnace.

[0006] A method for detecting melt composition in a furnace according to the present invention comprises:

[0007] Acquire an original multi-heat, multi-furnace, multi-point spectral dataset, and preprocess the original multi-heat, multi-furnace, multi-point spectral dataset to obtain a preprocessed multi-heat, multi-furnace, multi-point spectral dataset;

[0008] Dividing all the furnace periods of each heat into a plurality of segments, and dividing the pre-processed multi-heat, multi-furnace, multi-point spectral dataset according to the segmentation time to obtain a multi-heat, multi-segment spectral dataset;

[0009] Combining the multi-heat multi-segment spectral data sets according to the segment sequence numbers to obtain a plurality of segmented combined spectral data sets;

[0010] constructing a quantitative detection model based on the segmented combined spectral data set to obtain a plurality of the quantitative detection models;

[0011] An applicable quantitative detection model is selected from the plurality of quantitative detection models, and the composition of the melt in the furnace is detected using the applicable quantitative detection model to obtain a detection result.

[0012] Furthermore,

[0013] The original multi-heat, multi-heat period, multi-point spectral data set is specifically expressed as:

[0014] {(S1,S2,……,S i )1,(S1,S2,……,S i )2,……,(S1,S2,……,S i ) j},

[0015] Among them, i is the furnace period; j is the furnace number; S i is the original single furnace period multi-point spectral data set; (S1, S2, ..., S i ) j It is the original single-furnace, multi-furnace period, and multi-point spectral dataset.

[0016] Furthermore,

[0017] The original single furnace period multi-point spectral data set is specifically expressed as:

[0018] {(S 11 ,S 12 ,……,S 1n ),(S 21 ,S 22 ,……,S 2n ),……,(S m1 ,S m2 ,……,S mn )},

[0019] Where m is the point position; n is the height of the sampling rod; S mn is the original single-point spectral data; (S m1 ,S m2 ,……,S mn ) is the original single-point spectral dataset.

[0020] Furthermore,

[0021] Preprocessing the original multi-heat, multi-furnace, multi-point spectral dataset to obtain the preprocessed multi-heat, multi-furnace, multi-point spectral dataset includes:

[0022] The original multi-heat multi-furnace period multi-point spectral data set is processed by removing abnormal points and slag spectrum to obtain the pre-processed multi-heat multi-furnace period multi-point spectral data set {(S e1 ,Se2 ,……,S ei )1,(S e1 ,S e2 ,……,S ei )2,……,(S e1 ,S e2 ,……,S ei ) j}, where i is the furnace period; j is the furnace number; S ei is the preprocessed single furnace period multi-point spectral dataset; (S e1 ,S e2 ,……,S ei ) j It is a preprocessed single-furnace, multi-furnace period, and multi-point spectral dataset.

[0023] Furthermore,

[0024] According to the shape and texture of the material in the furnace, all the furnace periods of each furnace are divided into K segments, K≤I, where I is the number of all furnace periods of a single furnace.

[0025] Furthermore,

[0026] The multiple segmented combined spectral data sets are specifically represented as:

[0027] (data1,data2,……,data k ),

[0028] Among them, k is the segment; data k Combine spectral datasets for a certain segment.

[0029] Furthermore,

[0030] The multiple quantitative detection models are specifically expressed as:

[0031] {y=f1(x),y=f2(x),……,y=f l (x)},

[0032] Where x is the spectral feature extracted from the spectral data; y is the melt composition detection result in the furnace; l is the serial number of the quantitative detection model; y = f l (x) is a quantitative detection model.

[0033] A furnace melt composition detection system of the present invention is used to implement the above-mentioned furnace melt composition detection method, and the system includes:

[0034] A preprocessing module is used to obtain an original multi-heat multi-furnace period multi-point spectral data set, and preprocess the original multi-heat multi-furnace period multi-point spectral data set to obtain a preprocessed multi-heat multi-furnace period multi-point spectral data set;

[0035] a partitioning module, configured to divide all furnace periods of each heat into a plurality of segments, and to partition the pre-processed multi-heat, multi-furnace, multi-point spectral dataset according to segmentation time to obtain a multi-heat, multi-segment spectral dataset;

[0036] a combining module, configured to combine the multi-heat multi-segment spectral data sets according to segment sequence numbers to obtain a plurality of segmented combined spectral data sets;

[0037] A construction module, configured to construct a quantitative detection model based on the segmented combined spectral data set to obtain a plurality of the quantitative detection models;

[0038] The detection module is used to select an applicable quantitative detection model from the multiple quantitative detection models, use the applicable quantitative detection model to detect the composition of the melt in the furnace and obtain the detection results.

[0039] A computer-readable storage medium of the present invention stores a program or instruction. When the program or instruction is run on a computer, the computer executes the above-mentioned method for detecting the composition of the melt in the furnace.

[0040] An electronic device of the present invention includes a processor coupled to a memory; the processor is used to read and execute a computer program stored in the memory to implement the aforementioned method for detecting the composition of a melt in a furnace.

[0041] Compared with the prior art, the present invention has the following beneficial effects:

[0042] The present invention makes up for the lack of representativeness of single-point sampling by the sampling rod by sampling at multiple points; by collecting data from the same segment of multiple furnaces and multiple furnace periods to establish a quantitative detection model, and combining the actual working conditions to select the most suitable quantitative detection model to detect the melt composition, the influence of factors such as the physical properties and texture of the melt in different furnace periods during the smelting process on the detection results is reduced, and the detection precision and accuracy of the detection results are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0044] Figure 1 This is a schematic diagram of the fully automatic sampling method of the present invention;

[0045] Figure 2 This is a flow chart of the method for detecting melt composition in a furnace according to the present invention;

[0046] Figure 3 Schematic diagram comparing the Sn element detection results of tin-rich slag before the implementation of the furnace melt composition detection method of the present invention;

[0047] Figure 4 Schematic diagram comparing the Sn element detection results of tin-rich slag after the implementation of the furnace melt composition detection method of the present invention;

[0048] Figure 5 Schematic diagram of the structure of the melt composition detection system in the furnace of the present invention;

[0049] Figure 6 Schematic diagram of the structure of the electronic device of the present invention.

[0050] Description of reference numerals:

[0051] 1-sampling rod, 2-sampling rod system, 3-optical detection system, 201-preprocessing module, 202-division module, 203-combination module, 204-construction module, 205-detection module, 301-processor, 302-memory. DETAILED DESCRIPTION

[0052] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0053] In addition, in order to have a deeper understanding of the present invention, some of the terms are explained as follows:

[0054] A heat refers to the entire process of smelting in a reactor, from the beginning of smelting to discharge.

[0055] A furnace period refers to different stages or time periods within the same furnace. A furnace is divided into multiple furnace periods based on the degree of smelting and reduction.

[0056] Before executing the furnace melt composition detection method provided by the embodiment of the present invention, it is necessary to use a fully automatic sampling rod (hereinafter referred to as the "sampling rod") to collect spectral data within the reaction furnace (hereinafter referred to as the "furnace"). The following is the process for collecting spectral data from multiple furnace periods of multiple heats:

[0057] Before collecting spectral data, select a certain furnace period of a certain furnace and set the point position and sampling rod movement trajectory.

[0058] first step:

[0059] like Figure 1 As shown, a sampling rod is used to penetrate a point in the furnace, dip the material in the furnace, and then the sampling rod is pulled to a specified height. The LIBS device (LIBS device refers to laser induced breakdown spectroscopy device) on the sampling rod is used to collect spectral data at the specified height to obtain a piece of spectral data. The spectral data obtained at a point is defined as single-point spectral data.

[0060] By extracting the sampling rod to different heights and collecting spectral data at different heights, multiple spectral data can be obtained at one point. The multiple spectral data obtained at one point are defined as a single-point spectral data set.

[0061] By collecting the spectral data generated by the reactor in a certain furnace period of a certain furnace, a set of single-furnace, single-furnace period, single-point spectral data sets is obtained.

[0062] Step 2:

[0063] The sampling rod is moved to the next point along the sampling rod movement trajectory. Spectral data collection continues at the next point using the aforementioned method, resulting in another single-point spectral dataset. This method continues until spectral data collection for all points along the sampling rod movement trajectory is complete, resulting in multiple single-point spectral datasets. The multiple spectral data obtained at all points is defined as a multi-point spectral dataset. A multi-point spectral dataset includes multiple single-point spectral datasets.

[0064] In summary, the spectral data generated by the reactor during a certain furnace period of a certain heat are collected multiple times at multiple points according to the method described in the first and second steps to obtain multiple groups of single-heat, single-furnace, multi-point spectral data sets. For example, if a furnace period of a certain heat is from 12:00 to 13:00, the spectral data generated by the reactor during a certain furnace period of the certain heat are collected five times at multiple points to obtain five groups of single-heat, single-furnace, multi-point spectral data sets.

[0065] Step 3:

[0066] For all the heat periods of a single heat, spectral data were collected according to the methods described in the first and second steps, and finally a single heat, multi-heat period, multi-point spectral data set was obtained.

[0067] Step 4:

[0068] For all furnace periods of all heats, spectral data are collected according to the methods described in the first, second, and third steps, and finally a multi-heat, multi-period, and multi-point spectral data set is obtained.

[0069] The single-heat-period single-point spectral dataset, the single-heat-period multi-point spectral dataset, the single-heat-period multi-point spectral dataset, and the multi-heat-period multi-point spectral dataset all have corresponding collection times.

[0070] In addition, when selecting a sampling rod, a sampling rod with a circular, rectangular or square cross section can be selected. Preferably, the sampling rod has a square cross section because the square shape can ensure the flatness and usability of each surface of the sampling rod.

[0071] Figure 2 1 is a flow chart of a method for detecting melt composition in a furnace provided by an embodiment of the present invention. In one embodiment, the method specifically includes the following steps:

[0072] S101: obtaining an original multi-heat, multi-furnace period, multi-point spectral dataset, and preprocessing the original multi-heat, multi-furnace period, multi-point spectral dataset to obtain a preprocessed multi-heat, multi-furnace period, multi-point spectral dataset.

[0073] S101-1: Obtain the original multi-heat, multi-heat period, multi-point spectral dataset {(S1, S2, ..., S i )1,(S1,S2,……,S i )2,……,(S1,S2,……,S i ) j}, where i is the furnace period; j is the furnace number; S i is the original single furnace period multi-point spectral data set; (S1, S2, ..., S i ) j The original single-heat, multi-heat period, multi-point spectral dataset is the unprocessed raw dataset directly collected by the sampling rod.

[0074] Specifically, S i ={(S 11 ,S 12 ,……,S 1n ),(S 21 ,S 22 ,……,S 2n ),……,(S n1 ,Sn2 ,……,S nb )}, where m is the point; n is the height of the sampling rod; S mn is the original single-point spectral data, that is, the original spectral data at a certain height collected at a single point; (S m1 ,S m2 ,……,S mn ) is the original single-point spectral dataset.

[0075] S101-2: Preprocessing the original multi-heat, multi-furnace period, multi-point spectral dataset to obtain a preprocessed multi-heat, multi-furnace period, multi-point spectral dataset.

[0076] The pre-processing methods include scum spectrum removal and abnormal point removal.

[0077] Scum spectrum removal refers to removing anomalous spectral data from all single-point spectral datasets. The processing method for a specific set of single-point spectral datasets is to perform feature extraction on the dataset and perform data cleaning using outlier removal methods such as correlation and 3 sigma to remove scum spectra and obtain a valid single-point spectral dataset.

[0078] Outlier point removal refers to the removal of outliers from all multi-point spectral datasets. The processing method for a specific multi-point spectral dataset is to extract features from the dataset and perform data cleaning using outlier removal methods such as correlation and 3 sigma, as well as smelting mechanism analysis, to remove outliers and obtain a valid multi-point spectral dataset. Smelting mechanism analysis refers to the fact that during the smelting process, certain process parameters may deviate from the normal range due to equipment failure, raw material changes, or improper operation, resulting in outlier data. By comparing the data range and trend under normal smelting mechanisms, these outliers can be more easily identified.

[0079] By performing slag spectrum removal processing on all single-point spectral datasets in the original multi-heat multi-furnace period multi-point spectral dataset, and performing abnormal point removal processing on all multi-point spectral datasets in the original multi-heat multi-furnace period multi-point spectral dataset, an effective multi-heat multi-furnace period multi-point spectral dataset is obtained. The effective multi-heat multi-furnace period multi-point spectral dataset is also called the preprocessed multi-heat multi-furnace period multi-point spectral dataset. The preprocessed multi-heat multi-furnace period multi-point spectral dataset is defined as {(S e1 ,S e2 ,……,S ei )1,(S e1 ,S e2 ,……,S ei )2,……,(S e1 ,S e2,……,S ei ) j}, where i is the furnace period; j is the furnace number; S ei is the preprocessed single furnace period multi-point spectral dataset; (S e1 ,S e2 ,……,S ei ) j It is a preprocessed single-furnace, multi-furnace period, and multi-point spectral dataset.

[0080] S102: Divide all the furnace periods of each heat into multiple segments, and divide the pre-processed multi-heat, multi-furnace, multi-point spectral dataset according to the segmentation time to obtain a multi-heat, multi-segment spectral dataset.

[0081] Based on the material morphology and texture within the furnace, all heat cycles of a single heat are divided into multiple continuous and non-overlapping segments. The number of segments is defined as K, where K ≤ I, where I is the number of all heat cycles within a single heat. All heat cycles of each heat are divided according to the method described in step S102-1, and all heat cycles of each heat are divided into K segments.

[0082] Each segment has its corresponding time and sequence number. The time corresponding to each segment is defined as the segment time, and the sequence number corresponding to each segment is defined as the segment sequence number.

[0083] Obtain the acquisition time of the preprocessed multi-heat, multi-cycle, multi-point spectral dataset, align the segmentation time with the acquisition time, and divide the preprocessed multi-heat, multi-cycle, multi-point spectral dataset according to the segmentation time to obtain all segmented spectral datasets of all heats. The all segmented spectral datasets of all heats are referred to as "multi-heat, multi-segmented spectral datasets."

[0084] S103: Combining the multi-segment spectral data sets of multiple heats according to the segment sequence numbers to obtain multiple segmented combined spectral data sets.

[0085] Multiple segmented combined spectral datasets are defined as (data1, ata2, ..., ata k ), where k is the segment; data k Combine spectral datasets for a certain segment.

[0086] For example, the first segmented spectral dataset of the first heat, the first segmented spectral dataset of the second heat, and the first segmented spectral dataset of the third heat are combined to obtain three segmented combined spectral datasets (data1, ata2, ata3).

[0087] S104: Constructing a quantitative detection model based on the segmented combined spectral data set to obtain multiple quantitative detection models.

[0088] Multiple quantitative detection models are defined as {y=f1(x),=f2(x),……,=f l (x)}, where x is the spectral feature extracted from the spectral data; y is the melt composition detection result in the furnace; l is the serial number of the quantitative detection model; y = f l (x) is a quantitative detection model. The composition test results of the melt in the furnace are specifically expressed as element concentrations.

[0089] It is worth noting that the number of quantitative detection models is equal to the number of segments.

[0090] S105: selecting an applicable quantitative detection model from a plurality of quantitative detection models, detecting the composition of the melt in the furnace using the applicable quantitative detection model and obtaining a detection result.

[0091] A single-furnace-period multi-point spectral dataset to be tested is obtained, spectral features are extracted from the single-furnace-period multi-point spectral dataset, the specific position of the single-furnace-period multi-point spectral dataset to be tested in the furnace period setting is determined based on the furnace period setting and the process time (the process time refers to the time difference between furnace periods), a quantitative detection model applicable to the single-furnace-period multi-point spectral dataset to be tested is selected in combination with the previous detection result, the spectral features are input into the applicable quantitative detection model, and the melt composition in the furnace is detected using the applicable quantitative detection model to obtain the detection results, that is, the element concentration.

[0092] Obtain a multi-point spectral dataset of a single heat and a single furnace period to be tested, extract spectral features from the multi-point spectral dataset of a single heat and a single furnace period, and manually select an applicable quantitative detection model, input the spectral features into the applicable quantitative detection model, and use the applicable quantitative detection model to detect the melt composition in the furnace and obtain the test results, that is, the element concentration.

[0093] Verification Example

[0094] Verification was carried out at a tin smelter:

[0095] like Figure 3 As shown in the figure, the horizontal axis represents heats, each consisting of multiple heat cycles; the vertical axis represents the concentration of melt components within the furnace; the blue curve represents the reference value for Sn concentration; and the orange curve represents the actual measured Sn concentration. Using the model before implementing this method to detect Sn, the detection results were poor, prone to abnormalities, and the actual measured values ​​deviated significantly from the reference values.

[0096] like Figure 4As shown in the figure, the horizontal axis represents heats, each consisting of multiple heat cycles; the vertical axis represents the concentration of melt components within the furnace; the blue curve represents the reference value for Sn concentration; and the orange curve represents the actual measured Sn concentration. Using this quantitative detection model, the Sn detection method employed after implementation rarely yields abnormal results, with actual measured values ​​generally consistent with reference values. This significantly improves detection effectiveness and better aligns with the smelting mechanism, which states that during the reduction of tin-rich slag, the Sn content gradually decreases while the contents of elements such as Fe, Si, and Ca gradually increase.

[0097] It can be seen that the method for detecting the composition of the melt in the furnace of the present invention improves the detection accuracy of the composition of the melt in the furnace.

[0098] The embodiment of the present invention also provides a system for detecting the composition of the melt in the furnace, such as Figure 5 Shown, including:

[0099] The preprocessing module 201 is used to obtain an original multi-heat, multi-cycle, multi-point spectral dataset, and preprocess the original multi-heat, multi-cycle, multi-point spectral dataset to obtain a preprocessed multi-heat, multi-cycle, multi-point spectral dataset.

[0100] The division module 202 is used to divide all the furnace periods of each heat into multiple segments, and divide the preprocessed multi-heat, multi-furnace, multi-point spectral dataset according to the segmentation time to obtain a multi-heat, multi-segment spectral dataset.

[0101] The combining module 203 is configured to combine the multi-heat multi-segment spectral data sets according to the segment sequence numbers to obtain a plurality of segment combined spectral data sets.

[0102] The construction module 204 is used to construct a quantitative detection model based on the segmented combined spectral data set to obtain multiple quantitative detection models.

[0103] The detection module 205 is used to select an applicable quantitative detection model from multiple quantitative detection models, use the applicable quantitative detection model to detect the composition of the melt in the furnace and obtain the detection results.

[0104] It should be noted here that the above-mentioned preprocessing module 201, division module 202, combination module 203, construction module 204 and detection module 205 correspond to steps S101 to S105 in the embodiment of the method for detecting the composition of the melt in the furnace. The examples and application scenarios implemented by the above-mentioned modules and corresponding steps are the same, but are not limited to the contents disclosed in the above-mentioned embodiments.

[0105] An embodiment of the present invention further provides a computer-readable storage medium storing a program or instruction. When the program or instruction is executed on a computer, the computer executes the method for detecting the composition of the melt in the furnace as described in the above method embodiment.

[0106] like Figure 6 As shown, an embodiment of the present invention further provides an electronic device, including: a processor 301, the processor 301 is coupled to a memory 302, and the processor 301 is used to read and execute a computer program stored in the memory 302 to implement the method for detecting the composition of the melt in the furnace as described in the above method embodiment.

[0107] Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for detecting melt composition in a furnace, characterized in that: include: Acquire an original multi-heat-multi-furnace-period multi-point spectral data set, and preprocess the original multi-heat-multi-furnace-period multi-point spectral data set to obtain a preprocessed multi-heat-multi-furnace-period multi-point spectral data set; Dividing all furnace periods of each furnace into a plurality of segments, dividing the pre-processed multi-furnace multi-furnace multi-point spectral data set according to the segmentation time, to obtain a multi-furnace multi-segment spectral data set; Combining the multi-furnace multi-segment spectral data sets according to the segment sequence numbers to obtain a plurality of segment combined spectral data sets; Building a quantitative detection model based on the segmented combined spectral data set to obtain a plurality of the quantitative detection models; An applicable quantitative detection model is selected from the plurality of quantitative detection models, and the applicable quantitative detection model is used to detect the composition of the melt in the furnace and obtain the detection result.

2. The method according to claim 1, characterized in that The original multi-heat, multi-heat period, multi-point spectral data set is specifically expressed as: {(S1,S2,……,S i )1,(S1,S2,……,S i )2,……,(S1,S2,……,S i ) j }, Among them, i is the furnace period; j is the furnace number; S i is the original single furnace period multi-point spectral data set; (S1, S2, ..., S i ) j It is the original single-furnace, multi-furnace period and multi-point spectral dataset.

3. The method according to claim 2, characterized in that The original single furnace period multi-point spectral data set is specifically expressed as: {(S 11 ,S 12 ,……,S 1n ),(S 21 ,S 22 ,……,S 2n ),……,(S m1 ,S m2 ,……,S mn )}, Where m is the point position; n is the height of the sampling rod; S mn is the original single-point spectral data; (S m1 , S m2 , ..., S mn ) is the original single-point spectral dataset.

4. The method according to claim 3, characterized in that Preprocessing the original multi-heat, multi-furnace, multi-point spectral data set to obtain the preprocessed multi-heat, multi-furnace, multi-point spectral data set, including: The original multi-heat multi-furnace period multi-point spectral data set is processed by removing abnormal points and slag spectra to obtain the pre-processed multi-heat multi-furnace period multi-point spectral data set {(S e1 , S e2 , ..., S ei )1,(S e1 , S e2 , ..., S ei )2,……,(S e1 , S e2 , ..., S ei ) j }, where i is the furnace period; j is the furnace number; S ei is the preprocessed single furnace period multi-point spectral data set; (S e1 , S e2 , ..., S ei ) j It is a single-furnace, multi-furnace period, and multi-point spectral dataset after preprocessing.

5. The method according to claim 1, characterized in that According to the shape and texture of the material in the furnace, all the furnace periods of each furnace are divided into K segments, K≤I, where I is the number of all furnace periods of a single furnace.

6. The method according to claim 1 or 5, characterized in that: The multiple segmented combined spectral data sets are specifically expressed as: (data1,data2,……,data k ), Among them, k is the segment; data k Combine spectral datasets for a certain segment.

7. The method according to claim 1 or 5, characterized in that: The multiple quantitative detection models are specifically expressed as: {y=f1(x),y=f2(x),……,y=f l (x)}, Where x is the spectral feature extracted from the spectral data; y is the melt composition detection result in the furnace; l is the serial number of the quantitative detection model; y = f l (x) is a quantitative detection model.

8. A furnace melt composition detection system, characterized in that: include: A preprocessing module is used to obtain an original multi-heat multi-furnace period multi-point spectral data set, and preprocess the original multi-heat multi-furnace period multi-point spectral data set to obtain a preprocessed multi-heat multi-furnace period multi-point spectral data set; A division module is used to divide all the furnace periods of each furnace into a plurality of segments, and divide the pre-processed multi-furnace multi-furnace multi-point spectral data set according to the segmentation time to obtain a multi-furnace multi-segment spectral data set; A combining module, used for combining the multi-heat multi-segment spectral data sets according to the segment sequence numbers to obtain a plurality of segment combined spectral data sets; A construction module, used to construct a quantitative detection model based on the segmented combined spectral data set to obtain a plurality of the quantitative detection models; The detection module is used to select an applicable quantitative detection model from the multiple quantitative detection models, and use the applicable quantitative detection model to detect the composition of the melt in the furnace and obtain the detection result.

9. A computer-readable storage medium, characterized in that: A program or instruction is stored, and when the program or instruction is run on a computer, the computer is enabled to execute the method for detecting the composition of the melt in the furnace as described in any one of claims 1 to 7.

10. An electronic device, characterized in that: comprising a processor coupled to a memory; The processor is used to read and execute the computer program stored in the memory to implement the method for detecting the composition of the melt in the furnace according to any one of claims 1 to 7.

Images