Feeding control system for silicon steel sheet production

Abstract

The invention relates to the field of intelligent feeding control, in particular to a feeding control system for silicon steel sheet production, which comprises a conveying unit for conveying materials, a sensing feedback unit, an induction shooting unit, a laser positioning unit and a feeding control unit, the feeding control unit comprises a feeding control unit. The system comprises a communication interaction unit, a data analysis module, an image processing module, a control strategy module, a feeding management module, a fault monitoring module and an execution report module. Intelligent feeding control can be achieved, feeding accuracy is controlled by calculating and analyzing elaboration changes in the feeding process and combining feeding requirements and feature information such as the size, the shape and the surface quality of silicon steel sheets, and feeding control over the silicon steel sheets of different specifications can be adapted by monitoring and adjusting feeding strategies in real time; the overall efficiency of the production line is improved; and human errors and redundant time consumption are reduced, the production cost is reduced, and the production efficiency and the product quality are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent feeding control, in particular to a feeding control system for silicon steel sheet production, and in particular to an automatic feeding control system for intelligent silicon steel sheet production. Background Art

[0002] Silicon is the most basic factor affecting the magnetic and mechanical properties of electrical steel. Adding silicon to electrical steel mainly increases resistivity and reduces eddy current loss, thereby reducing iron loss. Silicon steel is the same as iron. In the production process of silicon steel sheets, the feeding step cannot be ignored. During the feeding process of silicon steel sheet production, the feeding time of the feeding device will increase as the material decreases, thus affecting efficiency. The existing feeding control of silicon steel sheet production mainly relies on manual operation, which is not only time-consuming but also prone to errors.

[0003] After searching, the Chinese patent with announcement number CN1189833C discloses a feeding control system and method, which proposes to use computer software and hardware for data collection and data processing, and inform the operator of the feeding information in advance after analyzing the data by the feeding control system, so as to improve the feeding efficiency. However, there is no mention of a solution for realizing feeding control by judging and monitoring material information;

[0004] The Chinese patent with announcement number CN112988745A discloses a barcode scanning management system for feeding materials. It points out that during the material feeding process, it is easy to mix materials and the materials cannot be traced back. It proposes a solution to obtain material information through a computer management system to obtain the feeding information and confirm the correct feeding. However, it does not mention how to combine the feeding information with the feeding progress to realize the feeding control solution.

[0005] However, in the feeding process of silicon steel sheet production, it is often necessary to determine the position of the silicon steel sheets at all times to ensure that they are correctly placed on the conveying device. It is necessary to specify the feeding demand tasks according to the production needs of the production line to adapt to the speed of the production line while ensuring accuracy. It is also necessary to avoid problems such as feeding failures and feeding path deviations that affect production continuity during the feeding process. How to control feeding to solve the above problems and improve safety protection measures such as automatic emergency stop to improve production efficiency and reduce errors and waste in the feeding process is an urgent problem to be solved.

[0006] To this end, we propose a feeding control system for silicon steel sheet production. Summary of the invention

[0007] A technical problem to be solved by this application is: how to design a feeding control system for silicon steel sheet production.

[0008] In order to solve the above technical problems, the embodiment of the present application provides a feeding control system for silicon steel sheet production, which is used to automatically monitor the feeding anomalies and feeding progress during the feeding process, so as to change and control the operating equipment and perform feeding control processing as planned, including a conveying unit for material conveying, a sensor feedback unit, a sensor shooting unit, and a laser positioning unit;

[0009] It also includes a feeding control unit that is communicatively connected to the conveying unit, the sensor feedback unit, the sensor shooting unit, and the laser positioning unit;

[0010] The feeding control unit includes: a communication interaction unit, a data analysis module, an image processing module, a control strategy module, a feeding management module, a fault monitoring module and an execution report module;

[0011] The feeding control unit also includes a communication processor and a memory;

[0012] In the feeding control unit:

[0013] The communication interaction unit is used to establish communication connections between various equipment components, provide communication connection methods, obtain corresponding data, and at the same time, receive the feeding demand data transmitted by the communication terminal, send feedback data, and perform data interaction; the feeding demand data includes the feeding quantity requirement, silicon steel sheet characteristic data, feeding conveying device data, and time requirements;

[0014] The data analysis module is used to receive the data of each unit component fed back by the communication interaction module, analyze the equipment operation data, RFID data, sensor data and feeding demand data, and also to fuse the image data of different connected sensors to improve the clarity of the image and the integrity of the information;

[0015] The image processing module is used to obtain the feedback data and image data of the sensing and shooting unit and the laser positioning unit, preprocess the image and extract features through the image preprocessing algorithm and feature extraction algorithm, recognize the extracted features through the image recognition algorithm, compare the feature points between different images, and achieve image matching and recognition to obtain the various parameter data of the silicon steel sheet. It should be noted that the image preprocessing module uses the ResNet training model to train the abnormal recognition of silicon steel sheet materials. The abnormal recognition library is recorded and added after each abnormal recognition, and can also be added through manual import;

[0016] A control strategy module, which is used to generate a new feeding strategy or optimize the generated feeding strategy based on the analysis data of the data analysis module, wherein the feeding strategy is converted into a corresponding execution instruction through a communication interaction unit and sent to the corresponding component for feeding control; the feeding strategy is connected to a cloud server and a local storage to store the feeding strategy and establish a strategy rule base, and the feeding strategy is used to generate execution instructions for different devices based on the information parameters related to the silicon steel sheet obtained by analysis and the operating parameters of the feeding equipment components as trigger conditions to complete the feeding control;

[0017] The feeding management module is used to match the corresponding control strategy according to the feeding demand data and the characteristics of the silicon steel sheet, and automatically adjust the control parameters and transmission of the conveying unit;

[0018] The fault monitoring module is used to connect the sensor feedback unit, the sensor shooting unit and the laser positioning unit, analyze the collected data to perform real-time feeding monitoring, and issue an alarm and execute the corresponding feeding strategy when an abnormality is detected;

[0019] An execution report module is used to generate an execution feedback report when the feeding strategy is executed. The execution feedback report includes successfully executed projects, abnormal projects, project data generation time, feeding completion time and feeding speed. When abnormal project data appears, the abnormal project data generation time and the corresponding control instructions are recorded and sent to the corresponding equipment unit;

[0020] The execution feedback report is transmitted to the feeding management module through the sensor feedback module, and the feeding management module calibrates the data. After the data is calibrated correctly, the execution feedback is recorded and exported, including:

[0021] Wherein, the communication interaction unit is connected to the image processing module through the data analysis module, the data analysis module and the image processing module are both connected to the feeding management module through the control strategy module, the feeding management module is respectively connected to the fault monitoring module and the execution reporting module, and the execution reporting module and the fault monitoring module are connected to each other;

[0022] Furthermore, the conveying unit includes a loading preparation area, any suitable loading conveying device for loading and a material storage area, wherein the loading conveying device is connected to the loading control unit via a field bus or industrial Ethernet to receive control instructions and feedback operation data, and transfer the operation data and control authority to the loading control unit;

[0023] The sensing and shooting unit includes an image shooting device for image acquisition and an RFID system for generating and reading RFID information, wherein the RFID system includes an RFID tag and an RFID reader;

[0024] The laser positioning unit comprises a laser emitting device, and the laser emitted by the laser emitting device is captured by the sensing and photographing unit.

[0025] Further, the sensor feedback unit includes a first sensor unit for obtaining material size and shape data, a second sensor unit for obtaining pressure data of the material preparation area and the material storage area, and a third feedback unit for obtaining distance data and surface defects;

[0026] Furthermore, the first sensing unit: adopts a laser scanning sensor, which is installed in the feeding preparation area and the discharging area and can completely scan any position of the silicon steel sheet, adopts high-precision laser scanning to obtain the size and shape data of the silicon steel sheet, and captures the contour information of the silicon steel sheet, and transmits the size and shape data to the feeding control unit;

[0027] The second sensing unit: a pressure sensor is installed in the feeding preparation area and the discharging area to obtain pressure data in the two areas, monitor the pressure data in real time, and transmit the pressure data to the feeding control unit for analysis and calculation, so as to obtain the remaining state of the material and the stress condition of the silicon steel sheet during the transportation process through the pressure change, so as to ensure the stability and safety of the feeding process;

[0028] The third feedback unit: a displacement sensor or an optical sensor (such as a CMOS camera) is installed on one side of the first sensing unit to obtain the feeding speed and feeding length data of the silicon steel sheet during the feeding process, and to capture the surface image of the silicon steel sheet to obtain the surface defect feature information of the material.

[0029] Furthermore, the sensing and photographing unit is connected to the feeding control unit, and is used to obtain the feeding progress data through the RFID system, and perform feeding control based on the feeding progress data;

[0030] Specific steps:

[0031] Obtain feeding demand data and feeding control strategy, attach RFID tags, and treat the materials within a set length before and after the tag as a batch, coded as F0. Change the code once for each additional batch, in the order of F0, F1, F2, and so on;

[0032] At the beginning of loading and conveying, the RFID reader reads and writes the RFID tag information once, and adds the current time node information and corresponding processing information;

[0033] If data anomalies occur, the RFID tag information of the batch will be marked as abnormal and recorded in the feeding control report;

[0034] Sort and count according to the batch code quantity, determine and update the feeding task progress, and optimize and update the feeding control strategy according to the feeding task progress.

[0035] Further, a laser positioning unit is installed above the loading conveying device, and the laser is used to irradiate the surface of the material conveyed by the conveying unit. The laser positioning unit includes a group of two laser emitting devices, and the laser irradiated by the laser emitting device is "L"-shaped and is used as a shooting positioning mark. The "L"-shaped laser marks irradiated by the two laser emitting devices are distributed on the surface of the material along the conveying direction, with a spacing of at least 15 cm, wherein the intersection of the two "L"-shaped laser marks is located on the same horizontal line;

[0036] The "L"-shaped laser mark irradiated by the laser emitting device is irradiated at an angle of 30-60° with the surface of the material as the horizontal plane, and the inclination angle of the camera device is the same as the laser irradiation angle.

[0037] Furthermore, the laser positioning unit and the sensing and shooting unit are both connected to the feeding control unit for analyzing the laser mark, and matching and executing corresponding feeding control instructions according to the analysis results of the laser mark, wherein:

[0038] The sensing and shooting unit captures real-time material images during the feeding and conveying process and sends them to the feeding control unit, where the real-time material images are divided into an image set P1 capturing one of the “L”-shaped laser marks and an image set P2 capturing the other “L”-shaped laser mark, thereby generating two image sets.

[0039] The feeding control unit which is communicatively connected to the conveying unit, the sensor feedback unit, the induction shooting unit and the laser positioning unit is used to capture the laser emitted by the laser device, obtain the image data with the laser mark, analyze the image to obtain the characteristic data of the laser mark, and convert and execute the corresponding feeding control steps through the analysis results.

[0040] Furthermore, the laser positioning unit is connected to the feeding control unit and the sensing and photographing unit, and two "L"-shaped laser marks are used to form marks for image analysis;

[0041] The specific steps are as follows:

[0042] S1: The feeding control unit obtains the collected image data, splits the image frame by frame, analyzes the photo image frame by frame, extracts the characteristic image with "L"-shaped laser mark, aligns the intersection of the image set P1 and the image set P2, and forms an image P0 with two "X"-shaped laser marks, wherein the formed image P0 is a picture frame at two different time points;

[0043] S2: De-noise, grayscale and binarize the image, and use CNN to extract edge features and shape features in the image; where:

[0044] If the detected edge is not smooth, it means that the conveying trajectory of the material has changed, and it is judged as abnormal data. The picture is extracted and recorded, and the corresponding control strategy is executed;

[0045] If the edge is smooth, check the image P0 of the frame to determine whether there is an "X"-shaped laser mark composed of two "L"-shaped laser marks. If there is and the "X"-shaped laser mark is complete, it indicates normal operation. If there is no mark or the "X" shape in the "X"-shaped laser mark is missing or the lines are irregular, it is determined that the material surface has defects, and the frame is extracted and recorded.

[0046] S3: extracting features from the extracted image, and inputting the extracted features into the trained classification model to identify and classify the silicon steel sheet;

[0047] S4: Calculate the position and posture of the silicon steel sheet based on the recognition results, and provide accurate positioning information and accurate feeding judgment.

[0048] In addition, template auxiliary lines are generated based on historical data and feeding demand data. The template auxiliary lines are used to crop the acquired images to reduce computing efficiency. At the same time, the template auxiliary lines are used to determine whether the shape of the "X"-shaped laser mark has changed. If the shape has changed and no abnormality is prompted, all images about 1S before and after the frame are extracted and recorded, and re-analysis and feature extraction are performed. The corresponding control strategy is executed, execution instructions are sent to the equipment components, and the image is fed back to the relevant equipment for further manual confirmation and instruction issuance.

[0049] Furthermore, the execution report module, feeding management module, control strategy module, communication interaction unit and data analysis module are used to analyze the feeding demand data, and generate a feeding strategy for overall control based on the feeding demand data, and implement the monitoring of feeding progress, and adjust and optimize the feeding strategy according to the feeding progress.

[0050] The present invention has at least the following beneficial effects:

[0051] It can realize intelligent feeding control, and control the feeding accuracy by calculating and analyzing the changes in the feeding process, combining the feeding requirements, the size, shape and surface quality of the silicon steel sheet and other characteristic information. It can adapt to the feeding control of silicon steel sheets of different specifications and improve the overall efficiency of the production line through real-time monitoring and adjustment of the feeding strategy.

[0052] In addition, the feeding data and material information during the feeding process are obtained through sensors and RFID systems to determine whether there are any abnormalities in the feeding process, thereby controlling the stability and reliability of the feeding process, improving the feeding efficiency of silicon steel sheets, reducing human errors and unnecessary time consumption, reducing production costs, and improving production efficiency and product quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 It is a schematic diagram of the flow of the feeding control system in an embodiment of the present invention;

[0054] Figure 2 It is a flow chart of the feeding control unit in the embodiment of the present invention. DETAILED DESCRIPTION

[0055] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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 creative work are within the scope of protection of the present invention.

[0056] Embodiment 1

[0057] See also Figure 1-2 , the present invention provides a technical solution:

[0058] A feeding control system for silicon steel sheet production, applied to the feeding and conveying of silicon steel sheets, used to automatically monitor the feeding anomalies and progress during the feeding process, so as to change and control the operating equipment and perform feeding control processing as planned, including a conveying unit for material conveying, a sensor feedback unit, an induction shooting unit, and a laser positioning unit;

[0059] It also includes a feeding control unit that is communicatively connected to the conveying unit, the sensor feedback unit, the sensor shooting unit, and the laser positioning unit;

[0060] The feeding control unit includes: a communication interaction unit, a data analysis module, an image processing module, a control strategy module, a feeding management module, a fault monitoring module and an execution report module, wherein the communication interaction unit is connected to the image processing module via the data analysis module, the data analysis module and the image processing module are both connected to the feeding management module via the control strategy module, the feeding management module is respectively connected to the fault monitoring module and the execution report module, and the execution report module and the fault monitoring module are connected to each other;

[0061] The feeding control unit also includes a communication processor and a memory for executing and storing computer programs between various modules, units, and equipment components to complete the transmission of instructions and the execution of commands of corresponding functions.

[0062] The communication interaction unit is used to establish communication connections between various equipment components, provide communication connection methods, obtain corresponding data, and at the same time, receive the feeding demand data transmitted by the communication terminal, send feedback data, and perform data interaction; the feeding demand data includes the feeding quantity requirement, silicon steel sheet characteristic data, feeding conveying device data, and time requirements;

[0063] The data analysis module is used to receive the data of each unit component fed back by the communication interaction module, analyze the equipment operation data, RFID data, sensor data and feeding demand data, and also to fuse the image data of different connected sensors to improve the clarity of the image and the integrity of the information;

[0064] The image processing module is used to obtain the feedback data and image data of the sensing and shooting unit and the laser positioning unit, preprocess the image and extract features through the image preprocessing algorithm and feature extraction algorithm, recognize the extracted features by using the image recognition algorithm, compare the feature points between different images, and achieve image matching and recognition to obtain various parameter data of silicon steel sheets. It should be noted that the image preprocessing module uses the ResNet training model to train the abnormal recognition of silicon steel sheet materials. The abnormal recognition library is increased by recording after each abnormal recognition, and can also be increased through manual import.

[0065] A control strategy module, which is used to generate a new feeding strategy or optimize the generated feeding strategy based on the analysis data of the data analysis module, wherein the feeding strategy is converted into a corresponding execution instruction through a communication interaction unit and sent to the corresponding component for feeding control; the feeding strategy is connected to a cloud server and a local storage to store the feeding strategy and establish a strategy rule base, and the feeding strategy is used to generate execution instructions for different devices based on the information parameters related to the silicon steel sheet obtained by analysis and the operating parameters of the feeding equipment components as trigger conditions to complete the feeding control;

[0066] The feeding management module is used to match the corresponding control strategy according to the feeding demand data and the characteristics of the silicon steel sheet, and automatically adjust the control parameters and transmission of the conveying unit;

[0067] The fault monitoring module is used to connect the sensor feedback unit, the sensor shooting unit and the laser positioning unit, analyze the collected data to perform real-time feeding monitoring, and issue an alarm and execute the corresponding feeding strategy when an abnormality is detected;

[0068] An execution report module is used to generate an execution feedback report when the feeding strategy is executed. The execution feedback report includes successfully executed projects, abnormal projects, project data generation time, feeding completion time and feeding speed. When abnormal project data appears, the abnormal project data generation time and the corresponding control instructions are recorded and sent to the corresponding equipment unit;

[0069] The execution feedback report is transmitted to the feeding management module through the sensor feedback module, and the feeding management module calibrates the data. After the data is calibrated correctly, the execution feedback is recorded and exported.

[0070] As a preferred embodiment of the present application, the conveying unit includes a loading preparation area, any suitable loading conveying device for loading, and a material storage area, wherein the loading conveying device is connected to the loading control unit via a field bus or industrial Ethernet to receive control instructions and feedback operation data, and transfer the operation data and control authority to the loading control unit;

[0071] The feeding conveying device is used to complete the execution action of feeding control;

[0072] The loading preparation area is a material placement area where the sensor feedback unit is installed for loading preparation;

[0073] The material storage area is divided into a material changing area where a sensor feedback unit is installed for material loading and changing, and a material stacking area where material production is completed after the material loading control is completed;

[0074] The material preparation area and the material storage area both obtain material information through the sensor feedback unit for use in material feeding control, thereby achieving the accuracy of material feeding control and the speed control of material feeding progress.

[0075] In this embodiment, the loading and conveying device is an adapted loading and conveying device, which is connected to the loading control unit through a communication interface or a bus, and is open to control for the loading control unit, including conveyor belts, loaders and other devices that can be communicated and can receive and execute control instructions. It should be noted that the loading control unit can control the start and stop of the loading and conveying device and at least one component that can execute actions, and is used to control the loading through the starting switch and its internal components, control the loading status, and set the component movement trigger conditions by connecting other component units to perform control processing such as screening during the loading process.

[0076] The sensor feedback unit includes a first sensor unit for obtaining material size and shape data, a second sensor unit for obtaining pressure data of the material feeding preparation area and the material storage area, and a third feedback unit (capacitive displacement sensor, optical sensor such as CMOS camera) for obtaining distance data and surface defects;

[0077] The sensing and shooting unit includes an image shooting device (camera) for image acquisition and an RFID system (including RFID tags and RFID readers) for generating and reading RFID information;

[0078] The laser positioning unit includes a laser emitting device, and the laser emitted by the laser emitting device is captured by the sensing and shooting unit; Embodiment 2

[0079] See also Figure 1-2 , based on the first embodiment, the first sensing unit: adopts a laser scanning sensor, which is installed in the feeding preparation area and the discharging area and can completely scan any position of the silicon steel sheet, adopts high-precision laser scanning to obtain the size and shape data of the silicon steel sheet, and captures the contour information of the silicon steel sheet, and transmits the size and shape data to the feeding control unit;

[0080] The second sensing unit: a pressure sensor is installed in the feeding preparation area and the discharging area to obtain pressure data in the two areas, monitor the pressure data in real time, and transmit the pressure data to the feeding control unit for analysis and calculation, so as to obtain the remaining state of the material and the stress condition of the silicon steel sheet during the transportation process through the pressure change, so as to ensure the stability and safety of the feeding process;

[0081] The third feedback unit: a displacement sensor or an optical sensor (such as a CMOS camera) is installed on one side of the first sensing unit to obtain the feeding speed and length data of the silicon steel sheet during the feeding process, and to capture the surface image of the silicon steel sheet to obtain the surface defect feature information of the material;

[0082] The displacement sensor can measure the distance between the silicon steel sheet and the feeding conveyor, while the optical sensor (such as a CMOS camera) can capture the surface image of the silicon steel sheet and analyze surface defects such as scratches, bumps, etc. through image processing technology.

[0083] It should be noted that the displacement sensor includes a laser displacement sensor, an inductive displacement sensor, a photoelectric encoder or any other suitable displacement sensor.

[0084] The sensing and shooting unit is connected to the feeding control unit, and is used to obtain the feeding progress data through the RFID system, and to control the feeding according to the feeding progress data;

[0085] Specific steps:

[0086] Obtain feeding demand data and feeding control strategy, attach RFID tags, and treat the materials within a set length before and after the tag as a batch, coded as F0. Change the code once for each additional batch, in the order of F0, F1, F2, and so on;

[0087] At the beginning of loading and conveying, the RFID reader reads and writes the RFID tag information once, and adds the current time node information and corresponding processing information;

[0088] If data anomalies occur, the RFID tag information of the batch will be marked as abnormal and recorded in the feeding control report; (to facilitate the subsequent retrieval of the RFID tag information of the batch and quickly locate the silicon steel sheet pile that has completed production based on the RFID tag information);

[0089] Sort and count according to the batch code quantity, determine and update the feeding task progress, and optimize and update the feeding control strategy according to the feeding task progress.

[0090] It is not difficult to see from the above design that the RFID system can accurately record the progress of loading, and the material change time can be calculated through the loading information. Taking the consumption of the material change process into consideration in the loading control, the machine's operating time and operating steps can be adjusted, and the loading time, speed and loading sequence can be controlled to achieve stable loading progress.

[0091] Embodiment 3

[0092] See also Figure 1-2 On the basis of the above embodiment, a laser positioning unit is installed above the loading conveying device, and the laser is used to irradiate the surface of the material conveyed by the conveying unit. The laser positioning unit includes a group of two laser emitting devices. The laser irradiated by the laser emitting device is "L"-shaped and is used as a shooting positioning mark. The "L"-shaped laser marks irradiated by the two laser emitting devices are distributed on the surface of the material along the conveying direction with a spacing of at least 15 cm, wherein the intersection of the two "L"-shaped laser marks is located on the same horizontal line;

[0093] The "L"-shaped laser mark irradiated by the laser emitting device is irradiated at an angle of 30-60° with the surface of the material as the horizontal plane. The tilt angle of the camera is the same as the laser irradiation angle. (Shooting at an angle of 30-60°, through tilted shooting, if the surface is uneven, has gullies and other problems, the non-vertical shooting angle can capture the dislocation of the laser on the plane, and the dislocation picture can be analyzed and judged to further calibrate the surface)

[0094] The laser positioning unit and the sensing and shooting unit are both connected to the feeding control unit for analyzing the laser mark, and matching and executing the corresponding feeding control instructions according to the analysis results of the laser mark, wherein:

[0095] The sensing and shooting unit captures real-time material images during the feeding and conveying process and sends them to the feeding control unit, where the real-time material images are divided into an image set P1 capturing one of the “L”-shaped laser marks and an image set P2 capturing the other “L”-shaped laser mark, generating two image sets.

[0096] The feeding control unit, which is communicatively connected to the conveying unit, the sensor feedback unit, the sensor shooting unit and the laser positioning unit, is used to capture the laser emitted by the laser device, obtain the image data with the laser mark, analyze the image to obtain the characteristic data of the laser mark, and convert and execute the corresponding feeding control steps through the analysis results. The specific process is as follows:

[0097] Step 1: Capture the laser emitted by the laser device through a camera device, perform image processing on the laser spot, and obtain the spatial coordinate data of the spot;

[0098] Step 2: Reconstruct the spatial coordinate data of the light spot in three dimensions to construct a distribution model of the laser spot in space;

[0099] Step 3: Based on the spatial distribution model, calculate the distance and relative position relationship between the light spots to obtain the distance matrix between the light spots;

[0100] Step 4: Using the distance matrix, the light spots are divided into several groups through a clustering algorithm, each group represents a spatial area;

[0101] Step 5: Perform statistical analysis on the light spots in each spatial area to obtain the light spot density and distribution characteristics of the area;

[0102] Step 6: According to the light spot density and distribution characteristics, the spatial regions are classified by pattern recognition algorithm to obtain spatial regions of different categories;

[0103] Step 7: Map different categories of spatial regions onto the three-dimensional coordinate axis to obtain a classification map of the spatial region;

[0104] Step 8: According to the classification map of the spatial area, the light spots in the spatial area are interpolated using a spatial interpolation algorithm to obtain a continuous distribution of spatial coordinates;

[0105] Step 9: Fit the spatial coordinates using a surface fitting algorithm through the continuous distribution of the spatial coordinates to obtain a surface model of the spatial coordinates;

[0106] Step 10: According to the surface model of the spatial coordinates, the surface analysis algorithm is used to extract the features of the surface to obtain the characteristic parameters of the surface;

[0107] Step 11: According to the characteristic parameters of the surface, the surface features are mapped to the two-dimensional image through the feature mapping algorithm to obtain the feature map of the spatial coordinates;

[0108] Step 12: According to the feature map of the spatial coordinates, the feature map is matched using a feature matching algorithm to obtain a matching result of the spatial coordinates;

[0109] Step 13: According to the matching result of the spatial coordinates, the spatial coordinates are transformed using a spatial transformation algorithm to obtain the transformation result of the spatial coordinates;

[0110] Step 14: According to the transformation result of the spatial coordinates, the spatial coordinates are analyzed using a spatial analysis algorithm to obtain the analysis result of the spatial coordinates;

[0111] Step 15: According to the analysis results of the spatial coordinates, the spatial coordinates are visualized using a spatial visualization algorithm to obtain a visualization result of the spatial coordinates;

[0112] Step 16: Determine whether the shape of the laser mark, the length of the shape line, and the angle of the shape line are normal based on the visualization results of the spatial coordinates.

[0113] The laser positioning unit is connected to the feeding control unit and the sensing and shooting unit, and forms a new mark for image analysis by using two "L"-shaped laser marks;

[0114] The specific steps are as follows:

[0115] S1: The feeding control unit obtains the collected image data, splits the image frame by frame, analyzes the photo image frame by frame, extracts the characteristic image with "L"-shaped laser mark, aligns the intersection of the image set P1 and the image set P2, and forms an image P0 with two "X"-shaped laser marks, wherein the formed image P0 is a picture frame at two different time points;

[0116] S2: De-noise, grayscale and binarize the image, and use CNN to extract edge features and shape features in the image; where:

[0117] If the detected edge is not smooth, it means that the conveying trajectory of the material has changed, and it is judged as abnormal data. The picture is extracted and recorded, and the corresponding control strategy is executed;

[0118] If the edge is smooth, check the image P0 of the frame to determine whether there is an "X"-shaped laser mark composed of two "L"-shaped laser marks. If there is and the "X"-shaped laser mark is complete, it indicates normal operation. If there is no mark or the "X" shape in the "X"-shaped laser mark is missing or the lines are irregular, it is determined that the material surface has defects, and the frame is extracted and recorded.

[0119] S3: extracting features from the extracted image, and inputting the extracted features into the trained classification model to identify and classify the silicon steel sheet;

[0120] S4: Calculate the position and posture of the silicon steel sheet based on the recognition results, and provide accurate positioning information and accurate feeding judgment.

[0121] In addition, template auxiliary lines are generated based on historical data and feeding demand data. The template auxiliary lines are used to crop the acquired images to reduce computing efficiency. At the same time, the template auxiliary lines are used to determine whether the shape of the "X"-shaped laser mark has changed (such as asymmetric mark shape, one side of the mark line is too long, etc.). If the shape changes and no abnormality is prompted, all images about 1S before and after the frame are extracted and recorded, and re-analysis and feature extraction are performed, and the corresponding control strategy is executed, and execution instructions are sent to the equipment components, and the image is fed back to the relevant equipment for further manual confirmation and instruction.

[0122] As a preferred embodiment of the present application: an execution report module, a feeding management module, a control strategy module, a communication interaction unit and a data analysis module are used to analyze the feeding demand data, and generate a feeding strategy for overall control based on the feeding demand data, and implement monitoring of the feeding progress, and adjust and optimize the feeding strategy according to the feeding progress.

[0123] The specific steps are as follows:

[0124] The communication interaction unit connects to the cloud server or corresponding device (smartphone) to receive the material feeding demand data (list), and transmits the above to the material feeding management module for analysis;

[0125] The feeding management module analyzes the data, obtains the parameter data of the list items, analyzes and obtains the feeding plan tasks, and generates a feeding strategy for adjusting the parameters of the feeding and conveying device, wherein: the feeding strategy is used to control the running speed of the feeding and conveying device in different time periods, generate corresponding control instructions and instruction triggering conditions, and associate the feeding device with the running speed of the feeding and conveying device, and set a floating interval, which is a floating numerical interval of the feeding or conveying speed under geometric proportion;

[0126] The feeding strategies have feeding tasks with execution instructions, which are sent to the corresponding components for execution. The execution status of each task is obtained and monitored. According to the progress of the task, it is determined whether to adjust the feeding strategy, and the subsequent feeding processing is controlled to achieve the initial expected effect.

[0127] In one embodiment, a computer-readable storage medium is also provided, such as a memory including instructions, and the instructions can be executed by a processor to implement a feeding control system for silicon steel sheet production in the above embodiment.

[0128] For example, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, and the like.

[0129] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. This application is intended to cover any modification, use or adaptation of the present invention, which follows the general principles of the present invention and includes common knowledge or customary techniques in the art that are not disclosed by the present invention. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present invention are indicated by the claims. It should be understood that the present invention is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

[0130] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A feeding control system for silicon steel sheet production, applied to the feeding process of silicon steel sheets, used to automatically monitor the feeding anomaly and feeding progress during the feeding process, so as to change and control the operating equipment and perform feeding control processing as planned, characterized in that: It includes a conveying unit for material conveying, a sensor feedback unit, a sensor shooting unit, and a laser positioning unit; It also includes a feeding control unit connected to the conveying unit, the sensor feedback unit, the sensor shooting unit and the laser positioning unit; The feeding control unit includes: a communication interaction unit, a data analysis module, an image processing module, a control strategy module, a feeding management module, a fault monitoring module and an execution report module; In the feeding control unit: The communication interaction unit is used to establish communication connections between various equipment components, provide communication connection methods, obtain corresponding data, and at the same time, receive the feeding demand data transmitted by the communication terminal, send feedback data, and perform data interaction; the feeding demand data includes the feeding quantity requirement, silicon steel sheet characteristic data, feeding conveying device data, and time requirements; The data analysis module is used to receive the data of each unit component fed back by the communication interaction module, analyze the equipment operation data, RFID data, sensor data and feeding demand data, and also to fuse the image data of different connected sensors to improve the clarity of the image and the integrity of the information; The image processing module is used to obtain the feedback data and image data of the sensing and shooting unit and the laser positioning unit, preprocess the image and extract features through the image preprocessing algorithm and feature extraction algorithm, recognize the extracted features using the image recognition algorithm, compare the feature points between different images, and realize image matching and recognition; A control strategy module is used to generate a new feeding strategy or optimize the generated feeding strategy based on the analysis data of the data analysis module, wherein the feeding strategy is converted into a corresponding execution instruction through the communication interaction unit and sent to the corresponding component for feeding control; the feeding strategy is connected to the cloud server and local storage to store the feeding strategy and establish a strategy rule base; The feeding management module is used to match the corresponding control strategy according to the feeding demand data and the characteristics of the silicon steel sheet, and automatically adjust the control parameters and transmission of the conveying unit; The fault monitoring module is used to connect the sensor feedback unit, the sensor shooting unit and the laser positioning unit, analyze the collected data to perform real-time feeding monitoring, and issue an alarm and execute the corresponding feeding strategy when an abnormality is detected; An execution report module is used to generate an execution feedback report when the feeding strategy is executed. The execution feedback report includes successfully executed projects, abnormal projects, project data generation time, feeding completion time and feeding speed. When abnormal project data appears, the abnormal project data generation time and the corresponding control instructions are recorded and sent to the corresponding equipment unit; The execution feedback report is transmitted to the feeding management module through the sensor feedback module, and the feeding management module calibrates the data. After the data is calibrated correctly, the execution feedback is recorded and exported, including: Among them, the communication interaction unit is connected to the image processing module through the data analysis module, the data analysis module and the image processing module are both connected to the feeding management module through the control strategy module, the feeding management module is connected to the fault monitoring module and the execution reporting module respectively, and the execution reporting module and the fault monitoring module are connected to each other.

2. A feeding control system for silicon steel sheet production according to claim 1, characterized in that: The conveying unit includes a loading preparation area, any suitable loading conveying device for loading and a material storage area, wherein the loading conveying device is connected to the loading control unit via a field bus or industrial Ethernet to receive control instructions and feedback operation data, and transfer the operation data and control authority to the loading control unit; The sensing and shooting unit includes an image shooting device for image acquisition and an RFID system for generating and reading RFID information, wherein the RFID system includes an RFID tag and an RFID reader; The laser positioning unit comprises a laser emitting device, and the laser emitted by the laser emitting device is captured by the sensing and photographing unit.

3. A feeding control system for silicon steel sheet production according to claim 2, characterized in that: The sensor feedback unit comprises a first sensor unit for acquiring material size and shape data, a second sensor unit for acquiring pressure data of the material preparation area and the material storage area, and a third feedback unit for acquiring distance data and surface defects.

4. A feeding control system for silicon steel sheet production according to claim 3, characterized in that: The first sensing unit: a laser scanning sensor is installed in the feeding preparation area and the discharging area to completely scan any position of the silicon steel sheet, and uses high-precision laser scanning to obtain the size and shape data of the silicon steel sheet, and captures the contour information of the silicon steel sheet, and transmits the size and shape data to the feeding control unit; The second sensing unit: a pressure sensor is installed in the feeding preparation area and the discharging area to obtain pressure data in the two areas, monitor the pressure data in real time, and transmit the pressure data to the feeding control unit for analysis and calculation, so as to obtain the remaining state of the material and the stress condition of the silicon steel sheet during the transportation process through the pressure change, so as to ensure the stability and safety of the feeding process; The third feedback unit: a displacement sensor or an optical sensor is installed on one side of the first sensing unit to obtain the feeding speed and feeding length data of the silicon steel sheet during the feeding process, and to capture the surface image of the silicon steel sheet to obtain the surface defect feature information of the material.

5. A feeding control system for silicon steel sheet production according to claim 4, characterized in that: The sensing and shooting unit is connected to the feeding control unit, and is used to obtain the feeding progress data through the RFID system, and to control the feeding according to the feeding progress data; Specific steps: Obtain feeding demand data and feeding control strategy, attach RFID tags, and treat the materials within a set length before and after the tag as a batch, coded as F0. Change the code once for each additional batch, in the order of F0, F1, F2, and so on; At the beginning of loading and conveying, the RFID reader reads and writes the RFID tag information once, and adds the current time node information and corresponding processing information; If data anomalies occur, the RFID tag information of the batch will be marked as abnormal and recorded in the feeding control report; Sort and count according to the batch code quantity, determine and update the feeding task progress, and optimize and update the feeding control strategy according to the feeding task progress.

6. A feeding control system for silicon steel sheet production according to claim 5, characterized in that: The laser positioning unit is installed above the loading conveying device. The laser is used to irradiate the surface of the material being conveyed by the conveying unit. The laser positioning unit includes a group of two laser emitting devices. The laser irradiated by the laser emitting device is "L" shaped and is used as a shooting positioning mark. The "L" shaped laser marks irradiated by the two laser emitting devices are distributed on the surface of the material along the conveying direction with a spacing of at least 15 cm, wherein the intersection of the two "L" shaped laser marks is located on the same horizontal line; The "L"-shaped laser mark irradiated by the laser emitting device is irradiated at an angle of 30-60° with the surface of the material as the horizontal plane, and the inclination angle of the camera device is the same as the laser irradiation angle.

7. A feeding control system for silicon steel sheet production according to claim 6, characterized in that: The laser positioning unit and the sensing and shooting unit are both connected to the feeding control unit for analyzing the laser mark, and matching and executing the corresponding feeding control instructions according to the analysis results of the laser mark, wherein: The sensing and shooting unit captures real-time material images during the feeding and conveying process and sends them to the feeding control unit, where the real-time material images are divided into an image set P1 capturing one of the "L"-shaped laser marks and an image set P2 capturing the other "L"-shaped laser mark, thereby generating two image sets. The feeding control unit which is communicatively connected to the conveying unit, the sensor feedback unit, the induction shooting unit and the laser positioning unit is used to capture the laser emitted by the laser device, obtain the image data with the laser mark, analyze the image to obtain the characteristic data of the laser mark, and convert and execute the corresponding feeding control steps through the analysis results.

8. A feeding control system for silicon steel sheet production according to claim 7, characterized in that: The laser positioning unit is connected to the feeding control unit and the sensing and shooting unit, and forms a mark for image analysis by using two "L"-shaped laser marks; The specific steps are as follows: S1: The feeding control unit obtains the collected image data, splits the image frame by frame, analyzes the photo image frame by frame, extracts the characteristic image with "L"-shaped laser mark, aligns the intersection of the image set P1 and the image set P2, and forms an image P0 with two "X"-shaped laser marks, wherein the formed image P0 is a picture frame at two different time points; S2: De-noise, grayscale and binarize the image, and use CNN to extract edge features and shape features in the image; where: If the detected edge is not smooth, it means that the conveying trajectory of the material has changed, and it is judged as abnormal data. The picture is extracted and recorded, and the corresponding control strategy is executed; If the edge is smooth, check the image P0 of the frame to determine whether there is an "X"-shaped laser mark composed of two "L"-shaped laser marks. If there is and the "X"-shaped laser mark is complete, it means normal operation; if there is no mark or the "X" shape in the "X"-shaped laser mark is missing or the lines are irregular, it is determined that the material surface has defects, and the frame is extracted and recorded; S3: extracting features from the extracted image, and inputting the extracted features into the trained classification model to identify and classify the silicon steel sheet; S4: Calculate the position and posture of the silicon steel sheet based on the recognition results, and provide accurate positioning information and accurate feeding judgment.

9. A feeding control system for silicon steel sheet production according to claim 8, characterized in that: The execution report module, feeding management module, control strategy module, communication interaction unit and data analysis module are used to analyze the feeding demand data, generate a feeding strategy for overall control based on the feeding demand data, monitor the feeding progress, and adjust and optimize the feeding strategy according to the feeding progress.

Images