Silicon steel strip alkali washing quality online analysis method, device and equipment and storage medium

Abstract

The invention relates to the technical field of silicon steel production, and particularly discloses a silicon steel strip alkali washing quality online analysis method, device and equipment and a storage medium, and the method comprises the following steps: S1, performing real-time detection through a detection head to obtain linear quality distribution information; s2, analyzing whether the linear quality distribution information is abnormal or not based on a first preset quality threshold value; s3, when abnormity exists, regional alkali washing quality distribution information is detected and obtained through a detection head; s4, obtaining all abnormal position points of the regional alkali washing quality distribution information based on a second preset quality threshold value; s5, according to the distribution condition of all abnormal position points and the corresponding quality information, inferring an abnormal type; according to the method, automatic detection and analysis of the alkali washing quality are realized, the control level of the production process is improved, and the limitations of low efficiency and dependence on experience of traditional manual analysis are overcome.

Description

Technical Field

[0001] The present application relates to the technical field of silicon steel production. Specifically, it relates to an on-line analysis method, device, equipment and storage medium for the quality of alkaline cleaning of silicon steel strips. Background Art

[0002] In the field of silicon steel production, the process treatment flow plays a decisive role in the quality and performance of products. The core steps such as normalizing pickling, cold rolling, alkaline cleaning, decarburizing annealing, coating and high-temperature annealing are closely linked. Among them, the alkaline cleaning link is particularly crucial, aiming to remove residues such as rolling oil stains and iron powder on the surface of the silicon steel strip, providing a good foundation for subsequent processes.

[0003] The traditional alkaline cleaning process usually consists of four steps: First, the alkaline solution is sprayed through a nozzle to wash the surface of the silicon steel strip, initially removing the rolling oil stains; then, the alkaline solution nozzle and the brush roller work together to deeply brush the surface of the silicon steel strip to thoroughly remove the remaining oil stains; subsequently, the surface of the silicon steel strip is cleaned by hot water spraying and the combination of hot water and the brush roller; finally, the surface moisture of the silicon steel strip is dried by hot air.

[0004] However, in the actual production process, the situation of insufficient alkaline cleaning often occurs. In the face of this problem, the traditional approach is to rely on manual analysis of the quality of alkaline cleaning on the surface of the silicon steel strip to determine the problem link and make adjustments or repairs. This method is not only time-consuming and laborious, but also highly dependent on the experience and technical level of workers.

[0005] In view of the above problems, there is currently no effective technical solution. Summary of the Invention

[0006] The purpose of the present application is to provide an on-line analysis method, device, equipment and storage medium for the quality of alkaline cleaning of silicon steel strips, so as to realize the automatic detection and analysis of the quality of alkaline cleaning, and overcome the limitations of low efficiency and dependence on experience of traditional manual analysis.

[0007] In a first aspect, the present application provides an on-line analysis method for the quality of alkaline cleaning of silicon steel strips, which is used for quality monitoring of silicon steel strip alkaline cleaning equipment. A quality detection component is provided at the output end of the silicon steel strip alkaline cleaning equipment. The quality detection component includes a plurality of detection heads arranged linearly. The detection heads are used to collect quality information at corresponding positions. The method includes the following steps: S1. Real-time detection is carried out through the detection heads to obtain linear quality distribution information, where the linear quality distribution information includes the quality information corresponding to each position point linearly distributed perpendicular to the length direction of the silicon steel strip; S2. Analyze whether the linear quality distribution information is abnormal based on a first preset quality threshold; S3. When there is an abnormality, use a detection head to detect and obtain the quality distribution information of the alkaline cleaning in the area. The quality distribution information of the alkaline cleaning in the area includes the quality information of each position point in a preset rectangular window area; S4. Obtain all abnormal position points of the quality distribution information of the alkaline cleaning in the area based on a second preset quality threshold; S5. Infer the type of abnormality based on the distribution of all abnormal position points and the corresponding quality information.

[0008] The on-line analysis method for the alkaline cleaning quality of silicon steel strips in this application realizes the on-line detection of alkaline cleaning quality based on the method of using a detection head for linear scanning to obtain linear quality distribution information. When it is initially determined that the alkaline cleaning quality is abnormal, the detection head is used for area scanning to obtain the quality distribution information of the alkaline cleaning in the area, and the type of abnormality causing the alkaline cleaning quality problem is inferred based on the distribution of abnormal position points in the quality distribution information of the alkaline cleaning in the area and the corresponding quality information, realizing the automatic detection and analysis of alkaline cleaning quality, improving the control level of the production process, and overcoming the limitations of low efficiency and dependence on experience in traditional manual analysis.

[0009] In the on-line analysis method for the alkaline cleaning quality of silicon steel strips, step S5 includes: S51. Extract the quantity, position coordinates, shape, and direction of all abnormal position points to obtain distribution parameters, and construct a feature vector to be recognized according to the distribution parameters and the quality information; S52. Calculate the similarity between the feature vector to be recognized and the feature vectors corresponding to each preset abnormality type in a pre-constructed abnormality type knowledge base. The abnormality type knowledge base includes multiple preset abnormality types, and each preset abnormality type corresponds to at least one feature vector; S53. Use the preset abnormality type with the highest similarity value among the similarity values as the inferred abnormality type.

[0010] This series of steps work together to transform the original abnormal position distribution and quality information into specific abnormality type identifications, thus solving the problem of how to accurately, efficiently, and objectively infer the specific abnormality type based on this information. Compared with manual judgment, this solution avoids subjectivity and dependence on experience through standardized feature extraction and quantitative similarity calculation, improves the accuracy and efficiency of inference, and reduces the dependence on manual experience.

[0011] In the on-line analysis method for the alkaline cleaning quality of silicon steel strips, the quality information includes oil stain residue amount information and alkali residue amount information.

[0012] This clarification of the content of the quality information enables the on-line analysis method for the alkaline cleaning quality of silicon steel strips in this application to more comprehensively and accurately evaluate the alkaline cleaning quality.

[0013] The online analysis method for the quality of the silicon steel strip after alkaline cleaning, wherein the second preset quality threshold is less than the first preset quality threshold.

[0014] The online analysis method for the quality of the silicon steel strip after alkaline cleaning, wherein the abnormal type is one or more of insufficient concentration of the alkaline cleaning solution, wear of the alkaline cleaning brush roll, and wear of the clean water brush roll.

[0015] The online analysis method for the quality of the silicon steel strip after alkaline cleaning, wherein when the abnormal type only includes insufficient concentration of the alkaline cleaning solution, the alkaline supplement amount information is generated according to the quality information of all abnormal position points, and when the abnormal type includes wear of the alkaline cleaning brush roll or wear of the clean water brush roll, a warning prompt information is generated.

[0016] The online analysis method for the quality of the silicon steel strip after alkaline cleaning, wherein the distribution density of the detection heads in the middle of the quality detection component is less than that on both sides.

[0017] In a second aspect, the present application further provides an online analysis device for the quality of the silicon steel strip after alkaline cleaning, which is used for quality monitoring of the silicon steel strip alkaline cleaning equipment. A quality detection component is provided at the output end of the silicon steel strip alkaline cleaning equipment. The quality detection component includes a plurality of detection heads arranged linearly. The detection heads are used to collect the quality information of the corresponding positions. The device includes: A first acquisition module, which is used to detect and acquire the linear quality distribution information in real time through the detection heads. The linear quality distribution information includes the quality information corresponding to each position point linearly distributed perpendicular to the length direction of the silicon steel strip; An abnormal detection module, which is used to analyze whether there is an abnormality in the linear quality distribution information based on the first preset quality threshold; A second acquisition module, which is used to detect and acquire the regional alkaline cleaning quality distribution information through the detection heads when there is an abnormality. The regional alkaline cleaning quality distribution information includes the quality information of each position point in a preset rectangular window area; An abnormal positioning module, which is used to obtain all abnormal position points of the regional alkaline cleaning quality distribution information based on the second preset quality threshold; An abnormal inference module, which is used to infer the abnormal type according to the distribution situation of all abnormal position points and the corresponding quality information.

[0018] The on-line analysis device for the quality of the alkali-washed silicon steel strip of the present application realizes the on-line detection of the alkali-washing quality based on the method of obtaining the linear quality distribution information by linear scanning of the detection head. When it is initially determined that the alkali-washing quality is abnormal, the detection head is used for area scanning to obtain the area alkali-washing quality distribution information, and the abnormal type causing the alkali-washing quality problem is inferred based on the distribution of the abnormal position points and the corresponding quality information in the area alkali-washing quality distribution information, realizing the automatic detection and analysis of the alkali-washing quality, improving the control level of the production process, and overcoming the limitations of low efficiency and dependence on experience in traditional manual analysis.

[0019] In a third aspect, the present application further provides an electronic device, including a processor and a memory, where the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps in the method provided in the first aspect above are run.

[0020] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps in the method provided in the first aspect above are run.

[0021] As can be seen from the above, the present application provides a method, device, equipment and storage medium for on-line analysis of the quality of alkali-washed silicon steel strip. Among them, the on-line analysis method for the quality of alkali-washed silicon steel strip of the present application realizes the on-line detection of the alkali-washing quality based on the method of obtaining the linear quality distribution information by linear scanning of the detection head. When it is initially determined that the alkali-washing quality is abnormal, the detection head is used for area scanning to obtain the area alkali-washing quality distribution information, and the abnormal type causing the alkali-washing quality problem is inferred based on the distribution of the abnormal position points and the corresponding quality information in the area alkali-washing quality distribution information, realizing the automatic detection and analysis of the alkali-washing quality, improving the control level of the production process, and overcoming the limitations of low efficiency and dependence on experience in traditional manual analysis. Description of the Drawings

[0022] Figure 1 It is a flowchart of the on-line analysis method for the quality of alkali-washed silicon steel strip provided by the embodiment of the present application.

[0023] Figure 2 It is a schematic structural diagram of the output end of the alkali-washing equipment for silicon steel strip.

[0024] Figure 3 It is a schematic structural diagram of the on-line analysis device for the quality of alkali-washed silicon steel strip provided by the embodiment of the present application.

[0025] Figure 4 It is a schematic structural diagram of the electronic device provided by the embodiment of the present application.

[0026] Reference numerals: 101, alkaline cleaning equipment for silicon steel strip; 102, quality detection component; 201, first acquisition module; 202, anomaly detection module; 203, second acquisition module; 204, anomaly location module; 205, anomaly inference module; 301, processor; 302, memory; 303, communication bus. Detailed implementation manners

[0027] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and illustrated herein can be arranged and designed in various different configurations. Therefore, the detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application to be protected, but only represents the selected embodiments of the present application. All other embodiments obtained by those skilled in the art based on the embodiments of the present application without creative efforts belong to the scope of protection of the present application.

[0028] It should be noted that similar reference numerals and letters denote similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of the present application, terms such as "first" and "second" are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0029] In a first aspect, please refer to Figure 1 and Figure 2 , some embodiments of the present application provide an on-line analysis method for the quality of alkaline cleaning of silicon steel strips, which is used for quality monitoring of the alkaline cleaning equipment 101 for silicon steel strips. A quality detection component 102 is provided at the output end of the alkaline cleaning equipment 101 for silicon steel strips. The quality detection component 102 includes a plurality of detection heads arranged linearly. The detection heads are used to collect quality information at corresponding positions. The method includes the following steps: S1. Real-time detection is performed by the detection heads to obtain linear quality distribution information, where the linear quality distribution information includes the quality information corresponding to each position point linearly distributed perpendicular to the length direction of the silicon steel strip. S2. Analyze whether there is an anomaly in the linear quality distribution information based on a first preset quality threshold. S3. When there is an anomaly, the detection heads are used to detect and obtain regional alkaline cleaning quality distribution information, where the regional alkaline cleaning quality distribution information includes the quality information of each position point in a preset rectangular window area. S4. Obtain all anomaly position points of the regional alkaline cleaning quality distribution information based on a second preset quality threshold. S5. Infer the anomaly type according to the distribution of all anomaly position points and the corresponding quality information.

[0030] Specifically, the quality detection component 102 is arranged at the output end of the silicon steel strip caustic washing device 101. The component includes a plurality of detection heads, which are arranged in a straight line parallel to the width direction of the silicon steel strip and are used to collect the quality information of multiple position points in the width direction of the silicon steel strip surface in parallel.

[0031] More specifically, in the actual production process, steps S1 and S2 are processes of online collecting and analyzing linear quality distribution information based on a preset sampling interval, which are used to preliminarily judge whether there is an abnormality in the previous caustic washing treatment to determine whether to trigger step S3 to determine the abnormality. Among them, step S1 realizes a rapid scan of the quality in the width direction of the silicon steel strip, and the obtained linear quality distribution information provides the quality profile of the current surface of the silicon steel strip and can be used for a rapid preliminary evaluation of the caustic washing effect.

[0032] More specifically, step S2 provides a preliminary abnormal screening mechanism, which judges whether there is a quality abnormality in the current scan line by comparing the magnitude relationship between the first preset quality threshold and the quality information of each position point in the linear quality distribution information.

[0033] More specifically, step S3 is triggered and executed only when step S2 judges that there is an abnormality. It uses the detection head and obtains the quality distribution information within a set rectangular area, which contains the quality information of each position point within the rectangular area. In the specific execution process, step S3 can collect multiple linear quality distribution information by continuously triggering the detection head during the conveying process of the silicon steel strip to form the quality distribution information, thereby realizing the scan of the two-dimensional area when there is an abnormality.

[0034] More specifically, in step S4, the second preset quality threshold can be the same as or different from the first preset quality threshold, and both are set according to the quality detection requirements. The goal of step S4 is to identify and obtain all the position points that do not meet the requirements of the second preset quality threshold within the rectangular window area by comparing the second preset quality threshold with the quality information, so as to determine the abnormal position points and the corresponding quality information.

[0035] More specifically, step S5 is used to analyze and infer the specific cause type leading to the quality abnormality according to the spatial distribution characteristics of all the abnormal position points identified in step S4 and the quality information corresponding to these position points.

[0036] More specifically, the on-line analysis method for the caustic washing quality of silicon steel strips in the embodiments of the present application realizes the automatic and on-line monitoring of the caustic washing quality of silicon steel strips by setting a quality detection component 102 at the output end of the caustic washing equipment. It uses step S1 to obtain the linear quality distribution information in the width direction of the silicon steel strip in real time, and then compares the first preset quality threshold with the linear quality distribution information to quickly and preliminarily evaluate the caustic washing effect, so as to quickly identify whether the current caustic washing quality is abnormal, and trigger a more detailed scan when it is abnormal to obtain two-dimensional quality data more detailed than the linear scan, providing richer information for subsequent anomaly analysis. Subsequently, step S4 compares the quality information of all position points in the rectangular window area by using the second preset quality threshold to identify and screen out all the specific position points with unqualified quality as abnormal position points. Finally, step S5 analyzes the spatial arrangement mode of these abnormal position points and the corresponding quality information to infer the specific cause type leading to the caustic washing quality problem. This inference process converts the detection result into actionable diagnostic information, which helps to take corrective measures in a timely manner, improves the control level of the production process, and overcomes the limitations of low efficiency and reliance on experience in traditional manual analysis.

[0037] The on-line analysis method for the caustic washing quality of silicon steel strips in the embodiments of the present application realizes the on-line detection of the caustic washing quality based on the way of obtaining the linear quality distribution information by linear scanning of the detection head. When it is initially judged that the caustic washing quality is abnormal, it performs area scanning based on the detection head to obtain the area caustic washing quality distribution information, and infers the abnormal type leading to the caustic washing quality problem based on the distribution of abnormal position points and the corresponding quality information in the area caustic washing quality distribution information, realizing the automatic detection and analysis of the caustic washing quality, improving the control level of the production process, and overcoming the limitations of low efficiency and reliance on experience in traditional manual analysis.

[0038] In some preferred embodiments, step S5 includes: S51. Extract the quantity, position coordinates, shape and direction of all abnormal position points to obtain distribution parameters, and construct a feature vector to be recognized according to the distribution parameters and quality information; S52. Calculate the similarity between the feature vector to be recognized and the feature vectors corresponding to each preset abnormal type in the pre-constructed abnormal type knowledge base to obtain multiple similarity values. The abnormal type knowledge base includes multiple preset abnormal types, and each preset abnormal type corresponds to at least one feature vector; S53. Take the preset abnormal type with the highest similarity value among the similarity values as the inferred abnormal type.

[0039] Specifically, step S51 refers to extracting the quantity, position coordinates, shape, and orientation of all abnormal position points to obtain distribution parameters, and constructing a feature vector to be recognized based on the distribution parameters and quality information. This can be specifically achieved by using image processing techniques or spatial analysis algorithms. For example, the shape and size of the abnormal area can be obtained through connected component analysis, the position coordinates can be obtained by calculating the centroid, the orientation information can be obtained through principal component analysis, and the quantity can be obtained by counting the number of pixel points. The distribution parameters can include the area, perimeter, aspect ratio, orientation angle, centroid coordinates, dispersion degree, etc. of the abnormal area. These parameters and quality information are integrated into a multi-dimensional vector as the feature vector to be recognized. This step transforms the original and discrete abnormal position point data into a structured and computable feature representation, laying a foundation for subsequent automated recognition.

[0040] More specifically, step S52 refers to calculating the similarity between the feature vector to be recognized and the feature vectors corresponding to each preset abnormal type in the pre-constructed abnormal type knowledge base, obtaining multiple similarity values. This can be specifically achieved by using various vector similarity calculation methods. For example, metrics such as Euclidean distance, cosine similarity, and Manhattan distance can be used to calculate the similarity or distance between two feature vectors. The abnormal type knowledge base stores in advance the typical feature vectors of different caustic washing abnormal types (such as strip-shaped abnormalities, block-shaped abnormalities, dot-shaped abnormalities, edge abnormalities, etc.). These typical feature vectors can be constructed by analyzing, clustering, or expert annotation of historical abnormal data. This step measures the matching degree between the currently detected abnormal features and the typical features of known abnormal types through quantitative comparison.

[0041] More specifically, step S53 refers to taking the preset abnormal type with the highest similarity in the similarity values as the inferred abnormal type. This can be specifically achieved by using a comparison algorithm. For example, after calculating the similarity values between the feature vector to be recognized and the feature vectors of all preset abnormal types in the knowledge base, select the preset abnormal type with the largest similarity value as the final inferred result.

[0042] More specifically, steps S51, S52, and S53 together constitute an abnormal type inference process based on feature matching. These steps work together to transform the original abnormal position distribution and quality information into specific abnormal type identifications, thus solving the problem of how to accurately, efficiently, and objectively infer specific abnormal types based on this information. Compared with manual judgment, this solution avoids subjectivity and experience dependence through standardized feature extraction and quantitative similarity calculation, improves the accuracy and efficiency of inference, and reduces the dependence on manual experience.

[0043] In some preferred embodiments, the quality information includes oil stain residue amount information and caustic residue amount information.

[0044] Specifically, the quality information refers to the data used to evaluate the effect of alkaline cleaning of silicon steel strips. Based on the foregoing, it can be known that the alkaline cleaning process of the silicon steel strip alkaline cleaning device 101 actually includes the alkaline cleaning liquid flushing, hot water flushing and drying processes. Therefore, the abnormal alkaline cleaning quality can be manifested as oil residue or alkaline substance residue. If the collected quality information only contains the information of one of the residues, it cannot comprehensively reflect the alkaline cleaning effect. For example, only detecting the oil residue amount may not be able to find the problem of excessive alkaline substance residue; vice versa. Therefore, the quality information obtained by the on-line analysis method for the alkaline cleaning quality of silicon steel strips in the embodiments of the present application includes the oil residue amount information and the alkaline substance residue amount information to simultaneously monitor the two main residues on the surface of the silicon steel strip, and it is also beneficial for step S5 to refer to more types of data to infer the abnormal type, that is, when step S5 infers the abnormal type according to the distribution of all abnormal position points and the corresponding oil residue amount information and alkaline substance residue amount information, different types of alkaline cleaning problems can be more accurately distinguished. This clarification of the content of the quality information enables the on-line analysis method for the alkaline cleaning quality of silicon steel strips in the embodiments of the present application to more comprehensively and accurately evaluate the alkaline cleaning quality.

[0045] More specifically, in the process of step S2 analyzing the abnormality based on the first preset quality threshold and step S4 screening the abnormal position points based on the second preset quality threshold, the oil residue threshold and the alkaline substance residue threshold need to be considered simultaneously.

[0046] In some preferred embodiments, the second preset quality threshold is less than the first preset quality threshold.

[0047] Specifically, the first preset quality threshold is used to quickly judge whether there is a preliminary abnormality in the linear scanning stage. When a preliminary abnormality is detected, the system performs a more detailed area scan. The second preset quality threshold is used to identify abnormal position points in the area scan stage. Since the quality information includes the oil residue amount information and the alkaline substance residue amount information, that is, the larger the quality information, the worse the corresponding alkaline cleaning quality. By setting the second preset quality threshold smaller than the first preset quality threshold in the method of the present application, more position points with quality deviating from the normal range can be identified within the area scan range, even if the degree of quality deviation of these position points is not sufficient to trigger an alarm in the linear scanning stage. Although the additional identified abnormal position points may have a relatively small degree of deviation, their distribution, quantity, shape and corresponding quality information in the area are crucial for subsequent inference of the abnormal type. Obtaining more data of abnormal position points can provide richer sample information, making the analysis based on the distribution of abnormal position points and quality information more accurate and reliable, thereby improving the accuracy of abnormal type inference.

[0048] More specifically, the second preset quality threshold is preferably set to 80-90% of the first preset quality threshold.

[0049] In some preferred embodiments, the abnormal types are one or more of insufficient concentration of the alkaline cleaning solution, wear of the alkaline cleaning brush roll, and wear of the pure water cleaning brush roll.

[0050] Specifically, insufficient concentration of the alkaline cleaning solution will result in a reduction in the oil removal ability of the alkaline cleaning solution, causing blocky, flaky, or large-area oil stains to remain on the surface of the silicon steel strip output from the output end of the silicon steel strip alkaline cleaning device 101, thereby increasing the oil stain residue information in the quality information of adjacent position points in the regional alkaline cleaning quality distribution information; wear of the alkaline cleaning brush roll and wear of the pure water cleaning brush roll are generally manifested as circumferential bristle wear, thereby increasing the oil stain residue information or alkali residue information of multiple position points arranged along the length direction of the silicon steel strip in the regional alkaline cleaning quality distribution information.

[0051] More specifically, the above-mentioned abnormal types are the most common causes of the gap quality abnormality of the silicon steel strip alkaline cleaning device 101, and will generate regional alkaline cleaning quality distribution information with relatively obvious differences. By defining the specific scope of the abnormal types, the inference result has clear technological significance and can directly guide subsequent fault diagnosis and treatment, enabling step S5 to infer the abnormal type based on the distribution of these abnormal position points and the corresponding quality information. For example, if the abnormal points are mainly manifested as a generally high alkali residue in the blocky area of the silicon steel strip, step S5 may infer that the abnormal type is insufficient concentration of the alkaline cleaning solution. If the abnormal points are manifested as strip-shaped oil stains along the length direction of the silicon steel strip and are located at a specific lateral position of the silicon steel strip, the system may infer that the abnormal type is wear of the alkaline cleaning brush roll. If the abnormal points are manifested as strip-shaped alkali residues along the length direction of the silicon steel strip, the system may infer that the abnormal type is wear of the pure water cleaning brush roll. This clear inference of the abnormal type provides a basis for subsequent targeted measures and improves the efficiency and accuracy of fault diagnosis.

[0052] It should be noted that the abnormal types are one or more of insufficient concentration of the alkaline cleaning solution, wear of the alkaline cleaning brush roll, and wear of the pure water cleaning brush roll, that is, the preset abnormal types in the abnormal type knowledge base in step S52 can be one or more of insufficient concentration of the alkaline cleaning solution, wear of the alkaline cleaning brush roll, and wear of the pure water cleaning brush roll. For example, the abnormal type corresponding to a certain feature vector is a composite abnormality of insufficient concentration of the alkaline cleaning solution and wear of the alkaline cleaning brush roll.

[0053] In some preferred embodiments, when the abnormal type only includes insufficient concentration of the alkaline cleaning solution, alkali supplement amount information is generated based on the quality information of all abnormal position points. When the abnormal type includes wear of the alkaline cleaning brush roll or wear of the pure water cleaning brush roll, a warning prompt message is generated.

[0054] Specifically, in actual production, when the abnormal type only includes insufficient concentration of the alkali cleaning solution, the operator can supplement the alkali substances online to adjust the concentration of the alkali cleaning solution, ensuring the continuity of production. If the abnormal type includes wear of the alkali scrubbing roller or wear of the water scrubbing roller, then it is necessary to stop the machine for replacement. Therefore, the above-mentioned processing method provides two different response mechanisms based on the inferred abnormal type. When the inferred abnormal type only includes insufficient concentration of the alkali cleaning solution, it indicates that there is no need to stop the machine for maintenance at present. Therefore, the solution uses the quality information of all abnormal position points to calculate the amount of alkali substances to be supplemented and gives a reminder to generate the alkali substance supplement amount information. The quality information reflects the alkali cleaning effect, and the quality information of the abnormal position points indicates the degree of insufficient alkali cleaning. By processing this information, the degree of alkali solution shortage can be quantified, and then the alkali substance supplement amount information can be generated. This information can be directly used to control the automated system to add alkali substances to the alkali solution pool or give a prompt to the operator to add alkali substances, so as to quickly adjust the concentration of the alkali solution and restore the normal alkali cleaning effect. When the inferred abnormal type includes wear of the alkali scrubbing roller or wear of the water scrubbing roller, it indicates that it is necessary to stop the machine for maintenance to solve the alkali cleaning quality problem. Therefore, the solution generates a warning prompt information in this case. This information directly warns the operator, indicating that it is necessary to stop the machine and replace the corresponding scrubbing roller. This response mechanism avoids continuing to produce unqualified products in the case of wear of the scrubbing roller and fundamentally solves the problem by replacing the parts in time.

[0055] More specifically, the online analysis method for the alkali cleaning quality of silicon steel strips in the embodiments of the present application can specifically solve common problems in the alkali cleaning process by distinguishing different abnormal types and taking corresponding automated or prompt measures, improving the efficiency and accuracy of fault handling, reducing the need for manual intervention, and ensuring the alkali cleaning quality of silicon steel strips.

[0056] In some preferred embodiments, the step of generating the alkali substance supplement amount information according to the quality information of all abnormal position points includes: A1. According to the quality information of each abnormal position point, estimate the alkali solution shortage amount corresponding to each abnormal position point. The alkali solution shortage amount is the amount of alkali solution required to make the position point reach the preset alkali cleaning quality standard; A2. Accumulate the alkali solution shortage amounts corresponding to all abnormal position points to obtain the total alkali solution shortage amount; A3. Calculate the alkali substance supplement amount information according to the total alkali solution shortage amount and the alkali solution supplement coefficient.

[0057] Specifically, in step A1, according to the quality information collected at each abnormal position point, such as the amount of oil residue or alkali residue, it is compared with the preset alkali washing quality standard. The degree of deviation between the quality information and the standard is used to estimate the amount of alkali solution to be supplemented at that position point to meet the cleaning standard. This estimation process can be based on a pre-established relationship model or lookup table between the quality information and the required amount of alkali solution.

[0058] More specifically, in step A2, the estimated alkali solution shortage amounts at all position points identified as abnormal within the preset rectangular window area are summed up to obtain a total amount representing the overall cleaning deficiency degree of this area.

[0059] More specifically, in step A3, calculate the amount of alkali substance that finally needs to be supplemented into the alkali solution pool. When calculating, multiply the total alkali solution shortage amount by an alkali solution supplementation coefficient. The alkali solution supplementation coefficient can be dynamically adjusted based on historical alkali washing data and real-time alkali washing parameters, and is used to compensate for losses or errors during the alkali washing process; the value of this alkali solution supplementation coefficient will be adjusted in real time according to historical production data and current process parameters, such as the speed of the silicon steel strip, the temperature of the alkali solution, the current concentration of the alkali solution, the volume of the alkali solution in the alkali solution pool, etc. The purpose of the adjustment coefficient is to more accurately reflect the possible alkali solution losses, reaction consumptions or measurement errors in actual production, and ensure that the calculated supplementation amount can effectively improve the alkali washing quality.

[0060] In some preferred embodiments, the detection head acquires quality information based on infrared spectroscopy detection method, laser scattering method, laser Raman spectroscopy or laser-induced breakdown spectroscopy method.

[0061] Specifically, these above methods are non-contact optical detection technologies that can analyze the substance composition or distribution on the surface of the silicon steel strip.

[0062] More specifically, the infrared spectroscopy detection method identifies and quantifies the chemical bond information of organic and inorganic substances. The laser scattering method detects surface particles or roughness. The laser Raman spectroscopy provides molecular structure information of substances. Laser-induced breakdown spectroscopy (LIBS) generates plasma through laser ablation and analyzes its emission spectrum for elemental analysis, detects alkali metal elements remaining on the surface of the silicon steel strip or carbon and hydrogen elements in the oil stain, and quantifies the amount of alkali residue and oil residue. In the embodiments of the present application, the detection head is preferably based on the laser-induced breakdown spectroscopy method to acquire quality information, which can ensure the accuracy and timeliness of quality information acquisition. In this embodiment, the detection head is preferably equipped with a pulsed laser, cooperating with the corresponding spectral instrument to collect spectral line intensity data, and through a pre-established calibration curve, convert the spectral line intensity data into specific values of the oil residue amount and the alkali residue amount. These values are output as quality information for subsequent online analysis steps.

[0063] In some preferred embodiments, the number of position points corresponding to the detection in the preset rectangular window area is a preset number, the two side edges are adjusted in real time based on the edge position of the silicon steel strip, and its length is adjusted and set based on the distance between the two side edges and the preset number.

[0064] More specifically, the two side edges of the preset rectangular window area are adjusted in real time based on the edge position of the silicon steel strip, which means that the side position of the window will be dynamically adjusted following the change of the actual edge position of the silicon steel strip. Thus, it is ensured that the window area always covers the actual width range of the silicon steel strip, including the edge area. The length of the preset rectangular window area is adjusted and set based on the distance between the two side edges and the preset number, determining the size of the window area in the width direction of the silicon steel strip and associating this size with the number of data points to be collected.

[0065] More specifically, the on-line analysis method for the alkali cleaning quality of the silicon steel strip in the embodiment of the present application adjusts the side position of the window in real time, so that the window always covers the effective range of the silicon steel strip, avoiding collecting invalid data outside the silicon steel strip or missing key data at the edges of the silicon steel strip. This improves the pertinence and effectiveness of the collection of regional quality distribution information, supports the acquisition and analysis of subsequent abnormal position points, and provides a reliable data basis for obtaining all abnormal position points based on the second preset quality threshold.

[0066] In some preferred embodiments, the distribution density of the detection heads in the middle of the quality detection component 102 is less than that on both sides.

[0067] Specifically, the distribution density of the detection heads in the width direction of the silicon steel strip affects the fineness of data collection. In actual production, since the alkali cleaning solution and hot water are both sprayed on the surface of the silicon steel strip through nozzles, both the alkali cleaning solution and the clear water flow to both sides in the width direction of the silicon steel strip. At the same time, burrs are more likely to appear at the edges of the silicon steel strip, and the positions with abnormal alkali cleaning quality are generally concentrated at both side edges of the silicon steel strip. Therefore, in the on-line analysis method for the alkali cleaning quality of the silicon steel strip in the embodiment of the present application, the distribution density of the detection heads in the middle is set to be less than that on both sides, so that the system can collect the quality information of the edge area of the silicon steel strip more densely, obtain more detailed quality data for the edges, and improve the detection ability and positioning accuracy of quality problems in the edge area. At the same time, reducing the detection density in the middle area can optimize the data collection volume while ensuring the coverage of the main area and reduce the data processing burden. This distribution method adjusts the allocation of data collection resources according to the probability difference of quality problems in different areas of the silicon steel strip, improving the effectiveness of the entire on-line quality analysis method.

[0068] In the second aspect, please refer to Figure 3, some embodiments of the present application further provide an on-line analysis device for the alkali cleaning quality of silicon steel strips, which is used for quality monitoring of the silicon steel strip alkali cleaning equipment 101. A quality detection component 102 is provided at the output end of the silicon steel strip alkali cleaning equipment 101. The quality detection component 102 includes a plurality of detection heads arranged linearly. The detection heads are used to collect quality information at corresponding positions. The device includes: A first acquisition module 201, configured to detect and acquire linear quality distribution information in real time through the detection heads. The linear quality distribution information includes quality information corresponding to each position point linearly distributed perpendicular to the length direction of the silicon steel strip; An anomaly detection module 202, configured to analyze whether there is an anomaly in the linear quality distribution information based on a first preset quality threshold; A second acquisition module 203, configured to, when an anomaly exists, detect and acquire regional alkali cleaning quality distribution information through the detection heads. The regional alkali cleaning quality distribution information includes quality information of each position point in a preset rectangular window area; An anomaly location module 204, configured to obtain all anomaly position points of the regional alkali cleaning quality distribution information based on a second preset quality threshold; An anomaly inference module 205, configured to infer the type of anomaly according to the distribution of all anomaly position points and the corresponding quality information.

[0069] The on-line analysis device for the alkali cleaning quality of silicon steel strips according to the embodiments of the present application realizes on-line detection of alkali cleaning quality based on the method of linearly scanning the detection heads to obtain linear quality distribution information. When it is initially determined that the alkali cleaning quality is abnormal, it scans the area based on the detection heads to obtain regional alkali cleaning quality distribution information, and infers the type of anomaly that causes the alkali cleaning quality problem according to the distribution of the anomaly position points in the regional alkali cleaning quality distribution information and the corresponding quality information, realizing automatic detection and analysis of alkali cleaning quality, improving the control level of the production process, and overcoming the limitations of low efficiency and dependence on experience of traditional manual analysis.

[0070] In some preferred embodiments, the on-line analysis device for the alkali cleaning quality of silicon steel strips according to the embodiments of the present application is used to execute the on-line analysis method for the alkali cleaning quality of silicon steel strips provided in the first aspect above.

[0071] In a third aspect, please refer to Figure 4 , some embodiments of the present application further provide a schematic structural diagram of an electronic device. The present application provides an electronic device, including: a processor 301 and a memory 302. The processor 301 and the memory 302 are interconnected and communicate with each other through a communication bus 303 and / or other forms of connection mechanisms (not marked). The memory 302 stores computer-readable instructions executable by the processor 301. When the electronic device runs, the processor 301 executes the computer-readable instructions to execute the methods in any optional implementation manner of the above embodiments.

[0072] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method in any optional implementation manner of the foregoing embodiments is executed. Among them, the computer-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM for short), Electrically Erasable Programmable Read-Only Memory (EEPROM for short), Erasable Programmable Read Only Memory (EPROM for short), Programmable Red-Only Memory (PROM for short), Read-Only Memory (ROM for short), magnetic memory, flash memory, a magnetic disk, or an optical disc.

[0073] In the embodiments provided in the present application, it should be understood that the disclosed device and method can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For another example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some communication interfaces. The indirect coupling or communication connection of the device or unit can be in an electrical, mechanical, or other form.

[0074] In addition, the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0075] Furthermore, in each embodiment of the present application, the various functional modules can be integrated together to form an independent part, or each module can exist alone, or two or more modules can be integrated to form an independent part.

[0076] In this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations.

[0077] The above are only embodiments of the present application and are not intended to limit the protection scope of the present application. For those skilled in the art, various modifications and changes can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the protection scope of the present application.

Claims

1. An on-line analysis method for the quality of silicon steel strip in alkaline cleaning, which is used for quality monitoring of silicon steel strip alkaline cleaning equipment, is characterized in that A quality detection component is provided at the output end of the silicon steel strip alkali cleaning equipment. The quality detection component includes a plurality of detection heads arranged linearly. The detection heads are used to collect quality information at corresponding positions. The method includes the following steps: S1. Real-time detection is performed by the detection heads to obtain linear quality distribution information, where the linear quality distribution information includes quality information corresponding to each position point linearly distributed perpendicular to the length direction of the silicon steel strip; S2. Analyze whether there is an abnormality in the linear quality distribution information based on a first preset quality threshold; S3. When there is an abnormality, the detection heads are used to detect and obtain regional alkali cleaning quality distribution information, where the regional alkali cleaning quality distribution information includes quality information of each position point in a preset rectangular window area; S4. Based on a second preset quality threshold, obtain all abnormal position points of the regional alkali cleaning quality distribution information; S5. Infer the type of abnormality according to the distribution of all abnormal position points and the corresponding quality information.

2. The online analysis method for the quality of the caustic washing of silicon steel strips according to claim 1, wherein, Step S5 includes: S51. Extract the quantity, position coordinates, shape, and direction of all abnormal position points to obtain distribution parameters. According to the distribution parameters and the quality information, construct a feature vector to be recognized; S52. Calculate the similarity between the feature vector to be recognized and the feature vectors corresponding to each preset abnormality type in a pre-constructed abnormality type knowledge base. Obtain a plurality of similarity values. The abnormality type knowledge base includes multiple preset abnormality types, and each preset abnormality type corresponds to at least one feature vector; S53. Use the preset abnormality type with the highest similarity value among the similarity values as the inferred abnormality type.

3. The online analysis method for the quality of the caustic washing of silicon steel strips according to claim 1, characterized in that The quality information includes oil stain residue amount information and alkali residue amount information.

4. The online analysis method for the quality of the caustic washing of silicon steel strips according to claim 3, wherein The second preset quality threshold is less than the first preset quality threshold.

5. The on-line analysis method for the quality of the caustic washing of the silicon steel strip according to claim 1, characterized in that, The abnormality type is one or more of insufficient alkali cleaning solution concentration, wear of the alkali scrubbing roller, and wear of the clean water scrubbing roller.

6. The online analysis method for the quality of the caustic washing of silicon steel strips according to claim 5, characterized in that, When the abnormality type only includes insufficient alkali cleaning solution concentration, alkali supplement amount information is generated according to the quality information of all abnormal position points. When the abnormality type includes wear of the alkali scrubbing roller or wear of the clean water scrubbing roller, a warning prompt information is generated.

7. The online analysis method for the quality of the caustic washing of silicon steel strips according to claim 1, characterized in that, The distribution density of the detection heads in the middle of the quality detection component is less than that on both sides.

8. An on-line analysis device for the quality of alkaline washing of silicon steel strips, which is used for quality monitoring of silicon steel strip alkaline washing equipment, is characterized in that, A quality detection component is provided at the output end of the silicon steel strip alkali cleaning equipment. The quality detection component includes a plurality of detection heads arranged linearly. The detection heads are used to collect quality information at corresponding positions. The device includes: A first acquisition module, configured to perform real-time detection by the detection heads to obtain linear quality distribution information, where the linear quality distribution information includes quality information corresponding to each position point linearly distributed perpendicular to the length direction of the silicon steel strip; An abnormality detection module, configured to analyze whether there is an abnormality in the linear quality distribution information based on a first preset quality threshold; A second acquisition module, configured to, when there is an abnormality, detect and obtain regional alkali cleaning quality distribution information by the detection heads, where the regional alkali cleaning quality distribution information includes quality information of each position point in a preset rectangular window area; An abnormality positioning module, configured to obtain all abnormal position points of the regional alkali cleaning quality distribution information based on a second preset quality threshold; Anomaly inference module, configured to infer the anomaly type according to the distribution of all anomaly location points and the corresponding quality information.

9. An electronic device, characterized in that, It includes a processor and a memory, and the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the steps in the method according to any one of claims 1-7 are run.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps in the method according to any one of claims 1-7 are run.

Images