Online Monitoring System and Method for Organic Coated Color Steel Plate Production Line

Abstract

The present application provides an online monitoring system and method for an organic coated color steel plate production line. It includes: an online monitoring module, which is used to collect production-related data on the organic coated color steel plate production line according to a data monitoring instruction, and determine whether the production-related data is normal data. If it is, the production-related data is sent to the prediction and analysis module; otherwise, a first-level warning prompt is generated according to the production-related data, where the production-related data includes equipment operation parameters, product process parameters, energy consumption parameters, production environment parameters, and product performance parameters; a prediction and analysis module, which is used to construct a prediction and analysis model, and input the received production-related data into the prediction and analysis model to obtain a prediction result output by the prediction and analysis model. When the prediction result is a prediction anomaly, a second-level warning prompt is generated according to the production-related data. Through the monitoring, analysis, and prediction of the production line data, online monitoring of the production process can be realized, and production efficiency can be improved.

Description

Technical Field

[0001] The present invention relates to the field of production control, and particularly to an online monitoring system and method for an organic coated color steel plate production line. Background Art

[0002] With the continuous development of industrial technology, organic coated color steel plates have been widely used in fields such as construction, household appliances, and automobiles. An organic coated color steel plate production line is a production line that coats an organic coating on the surface of a steel plate and makes a color steel plate through processes such as baking and curing. However, during the production process, due to the influence of various factors, such as raw material quality, equipment status, process parameters, etc., the product quality may fluctuate, and even unqualified products may appear.

[0003] In order to ensure the stable quality of organic coated color steel plates, improve production efficiency, and reduce production costs, it is necessary to monitor the production line in real time. Traditional monitoring methods mainly rely on manual inspections and off-line detections, which have problems such as untimely monitoring, inaccuracy, and low efficiency. Summary of the Invention

[0004] The purpose of the present invention is to overcome the problems of untimely monitoring and low efficiency in the prior art solutions, and provide an online monitoring system and method for an organic coated color steel plate production line. Through online monitoring and predictive analysis of the production line, information-based management of the production process can be achieved, and the efficiency and level of production management can be improved.

[0005] In a first aspect, an embodiment of the present disclosure provides an online monitoring system for an organic coated color steel plate production line, the system includes: an online monitoring module, and a predictive analysis module connected to the online monitoring module;

[0006] The online monitoring module is configured to collect production-related data on the organic coated color steel plate production line according to a data monitoring instruction, determine whether the production-related data is normal data, and if so, send the production-related data to the predictive analysis module; otherwise, generate a first-level warning prompt according to the production-related data, where the production-related data includes equipment operation parameters, product process parameters, energy consumption parameters, production environment parameters, and product performance parameters;

[0007] The predictive analysis module is configured to build a predictive analysis model, input the received production-related data into the predictive analysis model to obtain a prediction result output by the predictive analysis model, and when the prediction result is a prediction anomaly, generate a second-level warning prompt according to the production-related data.

[0008] Optionally, the online monitoring module specifically includes: a device status monitoring unit, a production process monitoring unit, an energy consumption monitoring unit, an environmental monitoring unit, and a product performance monitoring unit; the device status monitoring unit is used to obtain the device operation parameters of each target device on the production line through sensors, and determine whether the device operation parameters conform to the corresponding device parameter threshold range. If so, determine the device operation parameters as normal data; otherwise, determine the device operation parameters as abnormal data. Among them, the device operation parameters include device temperature, device pressure, and device rotation speed; the production process monitoring unit is used to obtain the product process parameters of the current color steel plate on the production line through a detector, and determine whether the product process parameters conform to the corresponding product process parameter threshold range. If so, determine the product process parameters as normal data; otherwise, determine the product process parameters as abnormal data. Among them, the product process parameters include substrate mechanical properties, organic coating thickness, production line speed, coating viscosity, curing temperature, and drying time; the energy consumption monitoring unit is used to obtain the energy consumption parameters on the production line, and determine whether the energy consumption parameters conform to the corresponding energy consumption parameter threshold range. If so, determine the energy consumption parameters as normal data; otherwise, determine the energy consumption parameters as abnormal data. Among them, the energy consumption parameters include water energy utilization rate, electric energy utilization rate, and gas energy utilization rate; the environmental monitoring unit is used to obtain the production environment parameters on the production line through sensors, and determine whether the production environment parameters conform to the corresponding production environment parameter threshold range. If so, determine the production environment parameters as normal data; otherwise, determine the production environment parameters as abnormal data. Among them, the production environment parameters include environmental temperature and environmental humidity; the product performance monitoring unit is used to obtain the product performance parameters of the current color steel plate on the production line through a detector, and determine whether the product performance parameters conform to the corresponding product performance parameter threshold range. If so, determine the product performance parameters as normal data; otherwise, determine the product performance parameters as abnormal data. Among them, the product performance parameters include color difference value, glossiness, and color uniformity.

[0009] Optionally, the online monitoring module is further used to determine the performance difference between the product performance parameters and the corresponding standard performance parameters when the product performance parameters are normal data. When the performance difference is greater than the preset performance difference threshold, determine the adjustment parameters according to the product performance parameters, and perform feedback adjustment on the product process parameters according to the adjustment parameters.

[0010] Optionally, the predictive analysis module specifically includes: a test group generation unit and a model construction unit; the test group generation unit is configured to obtain historical production data, determine the collection time of each piece of historical production data, sort each piece of historical production data in ascending order according to the collection time to generate a sample sequence, generate test groups according to the sample sequence, and determine the target time corresponding to the test groups, where each test group includes a specified number of adjacent historical production data; the model construction unit is configured to build a time series neural network structure, determine the initial parameters of the neural network structure, input the test groups into the neural network structure to obtain the production data sample values corresponding to the target time, and determine the true values of the production data at the target time, determine the mean square error between the production data sample values and the true values of the production data, determine the final parameters according to the mean square error and the initial parameters, and generate a predictive analysis model according to the final parameters; where the forward process of the time series neural network structure is:

[0011] ; where, and represent moments, represents the input test group, represents the memory of the sample at time , represents the input weight, represents the weight of the input test group at this moment, represents the output test group weight.

[0012] Optionally, the system further includes: a surface defect detection module connected to the online monitoring module; the surface defect detection module is configured to collect a grayscale image of the original steel plate on the production line according to a specified time, perform grayscale projection on the grayscale image to determine the grayscale average value, and determine the grayscale difference between each pixel point in the grayscale image and the grayscale average value, determine whether the grayscale difference is greater than a preset grayscale difference threshold, if so, generate a third-level warning prompt, otherwise, generate a data monitoring instruction according to a preset time, and send the data monitoring instruction to the online monitoring module.

[0013] Optionally, the system further includes: a product positioning module connected to the surface defect detection module; the surface defect detection module is further configured to send the data monitoring instruction to the product positioning module; the product positioning module is configured to obtain a production line image through a camera device, and detect the production line image based on a steel plate recognition model to identify the target color-coated steel plate therein, position the target color-coated steel plate through a target tracking algorithm, and generate a fourth-level warning prompt when it is detected that the target color-coated steel plate exceeds the preset area range, where the positioning includes position positioning and angle positioning; where the angle positioning formula is:

[0014] ; where, N1 represents the production line reference plane, N2 represents the upper surface of the target color steel plate, N1⋅N2 = A1A2 + B1B2 + C1C2, , , A1, B1, and C1 represent the coordinates of the normal vector of the production line reference plane, and A2, B2, and C2 represent the coordinates of the normal vector of the upper surface of the target color steel plate, represents the angle between the production line reference plane and the upper surface of the target color steel plate.

[0015] Optionally, the system further includes: a production efficiency determination module connected to the product positioning module; the product positioning module is further configured to obtain each preset positioning point, determine the timestamps when the target color steel plate reaches each preset positioning point, and send each timestamp to the production efficiency determination module; the production efficiency determination module is configured to determine the number of timestamps received within a specified period, and determine the production efficiency of the production line based on the number of timestamps and the timestamps.

[0016] Optionally, the system further includes: a user terminal connected to the online monitoring module, the prediction analysis module, the surface defect detection module, and the product positioning module; the user terminal is configured to receive warning prompts and alarm in a specified manner according to the warning prompts, where the warning prompts include first-level warning prompts, second-level warning prompts, third-level warning prompts, and fourth-level warning prompts.

[0017] Optionally, the system further includes: a storage module connected to the user terminal and the online monitoring module; the online monitoring module is further configured to send production-related data to the storage module; the storage module is configured to receive and store the production-related data; the user terminal is further configured to obtain a data query instruction input by the user and send the data query instruction to the storage module; the storage module is configured to filter the production-related data based on the data query instruction to obtain target query data, and feedback the target query data to the user terminal.

[0018] In a second aspect, an online monitoring method for an organic coated color steel plate production line provided by an embodiment of the present disclosure includes:

[0019] Collect production-related data on the organic coated color steel plate production line by the online monitoring module according to a data monitoring instruction, and determine whether the production-related data is normal data. If so, send the production-related data to the prediction analysis module; otherwise, generate a first-level warning prompt according to the production-related data, where the production-related data includes equipment operation parameters, product process parameters, energy consumption parameters, production environment parameters, and product performance parameters;

[0020] Construct a prediction analysis model by the prediction analysis module, and input the received production-related data into the prediction analysis model to obtain a prediction result output by the prediction analysis model. When the prediction result is a prediction anomaly, generate a second-level warning prompt according to the production-related data.

[0021] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understandable through the following description.

[0022] Therefore, the present invention has the following beneficial effects:

[0023] 1. Detect production-related data through the online monitoring module and give early warnings for anomalies, providing a basis for production optimization.

[0024] 2. Conduct predictive analysis on production-related data through the predictive analysis module to achieve early monitoring and warning and eliminate potential production safety hazards.

[0025] 3. By positioning the color steel plate, equipment failures can be reduced, and production efficiency analysis can be carried out, enabling users to more intuitively master the production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0027] Figure 1 is a schematic structural diagram of an online monitoring system for an organic-coated color steel plate production line according to Embodiment 1 of the present invention;

[0028] Figure 2 is another schematic structural diagram of an online monitoring system for an organic-coated color steel plate production line according to Embodiment 1 of the present invention;

[0029] Figure 3 is another schematic structural diagram of an online monitoring system for an organic-coated color steel plate production line according to Embodiment 2 of the present invention;

[0030] Figure 4 is a flowchart of an online monitoring method for an organic-coated color steel plate production line according to Embodiment 3 of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0031] To enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0032] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present invention described here can be implemented in an order other than those illustrated or described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0033] Embodiment 1: Figure 1 A structural schematic diagram of an online monitoring system for an organic coated color steel plate production line is provided for Embodiment 1 of the present invention. The system includes: an online monitoring module and a prediction analysis module connected to the online monitoring module.

[0034] Optionally, the online monitoring module is used to collect production-related data on the organic coated color steel plate production line according to a data monitoring instruction, determine whether the production-related data is normal data, and if so, send the production-related data to the prediction analysis module; otherwise, generate a first-level warning prompt according to the production-related data, where the production-related data includes equipment operation parameters, product process parameters, energy consumption parameters, production environment parameters, and product performance parameters; the prediction analysis module is used to construct a prediction analysis model and input the received production-related data into the prediction analysis model to obtain a prediction result output by the prediction analysis model. When the prediction result is a prediction anomaly, a second-level warning prompt is generated according to the production-related data.

[0035] Among them, organic coated color steel plate refers to a kind of plate with an organic coating on the surface of the steel plate, which has good corrosion resistance, decorative properties, etc., and is commonly used in the construction and industrial fields. The online monitoring module is a system part that can monitor and control the production process in real time to ensure the continuous production and timely acquisition of data. The data monitoring instruction refers to the instruction information used to guide the online monitoring module on which specific data to collect and the collection time. The equipment operation parameters refer to the various index data shown by the production equipment during operation, reflecting the working state of the equipment. The product process parameters refer to the specific parameter settings related to the product manufacturing process, which have a direct impact on the product quality. The energy consumption parameters refer to the parameters describing the energy usage situation during the production process. The production environment parameters refer to the parameters related to the production site environment conditions. The product performance parameters refer to the specific numerical values indicating the various performances of the product. The prediction analysis model refers to a model constructed based on data analysis and algorithms that can predict and analyze the future production situation. The first-level warning prompt refers to the warning used to prompt the abnormality of production-related data. The second-level warning prompt refers to a warning that is more forward-looking and important than the first-level warning prompt and is issued based on the prediction analysis results.

[0036] Specifically, according to the data monitoring instruction, the online monitoring module can comprehensively collect production-related data in all aspects of the organic coated color steel plate production line. And it will use specific judgment logics and standards to judge the collected production-related data. If the data is judged to be normal data, these data will be sent to the prediction analysis module for further analysis and processing. Once it is found that the production-related data is not normal data, a first-level warning prompt will be generated based on these abnormal data, enabling relevant personnel to detect possible problems in the production process in a timely manner.

[0037] Furthermore, after receiving the production-related data sent by the online monitoring module, the prediction analysis module will input the production-related data into the constructed prediction analysis model. The prediction analysis model will output the corresponding prediction results. When the prediction result is a prediction abnormality, it means that problems may occur in the future based on the existing data. At this time, a second-level warning prompt will be generated based on the corresponding production-related data. The second-level warning prompt can remind relevant personnel to take corresponding countermeasures in advance to avoid the further deterioration and expansion of the problems.

[0038] Figure 2 FIG. 10 is a schematic structural diagram of an online monitoring system for an organic coated color steel plate production line according to Embodiment 1 of the present invention. Figure 2Among them, the online monitoring module specifically includes: a device status monitoring unit, a production process monitoring unit, an energy consumption monitoring unit, an environmental monitoring unit, and a product performance monitoring unit; the prediction and analysis module specifically includes: a test grouping generation unit and a model construction unit; the system further includes: a surface defect detection module connected to the online monitoring module, a product positioning module connected to the surface defect detection module, and a production efficiency determination module connected to the product positioning module.

[0039] Optionally, the online monitoring module specifically includes: a device status monitoring unit, a production process monitoring unit, an energy consumption monitoring unit, an environmental monitoring unit, and a product performance monitoring unit; the device status monitoring unit is configured to obtain the device operation parameters of each target device on the production line through sensors, and determine whether the device operation parameters meet the corresponding device parameter threshold range. If so, determine the device operation parameters as normal data; otherwise, determine the device operation parameters as abnormal data. Among them, the device operation parameters include device temperature, device pressure, and device rotation speed; the production process monitoring unit is configured to obtain the product process parameters of the current color steel plate on the production line through a detector, and determine whether the product process parameters meet the corresponding product process parameter threshold range. If so, determine the product process parameters as normal data; otherwise, determine the product process parameters as abnormal data. Among them, the product process parameters include substrate mechanical properties, organic coating thickness, production line speed, coating viscosity, curing temperature, and drying time; the energy consumption monitoring unit is configured to obtain the energy consumption parameters on the production line and determine whether the energy consumption parameters meet the corresponding energy consumption parameter threshold range. If so, determine the energy consumption parameters as normal data; otherwise, determine the energy consumption parameters as abnormal data. Among them, the energy consumption parameters include water energy utilization rate, electric energy utilization rate, and gas energy utilization rate; the environmental monitoring unit is configured to obtain the production environment parameters on the production line through sensors and determine whether the production environment parameters meet the corresponding production environment parameter threshold range. If so, determine the production environment parameters as normal data; otherwise, determine the production environment parameters as abnormal data. Among them, the production environment parameters include environmental temperature and environmental humidity; the product performance monitoring unit is configured to obtain the product performance parameters of the current color steel plate on the production line through a detector and determine whether the product performance parameters meet the corresponding product performance parameter threshold range. If so, determine the product performance parameters as normal data; otherwise, determine the product performance parameters as abnormal data. Among them, the product performance parameters include color difference value, glossiness, and color uniformity.

[0040] In a specific embodiment, the device status monitoring unit closely monitors the operating conditions of each target device on the production line by means of various sensors. The sensors collect device operation parameters. For example, the device temperature can reflect the heat generation situation of the device, the device pressure can reflect the pressure borne by the device during operation, and the device rotation speed indicates the operating speed of the device. Then, the collected device operation parameters are compared with the corresponding pre-set device parameter threshold ranges. If the device operation parameters are within the corresponding device parameter threshold ranges, it indicates that the device is operating well, and the device operation parameters are determined as normal data. If they exceed the device parameter threshold ranges, it indicates that the device may have problems or abnormalities, and at this time, these parameters are identified as abnormal data. It should be noted that there is a one-to-one correspondence between the parameters and the threshold ranges. For example, there is a corresponding threshold range for the device temperature, and there is also a corresponding threshold range for the device pressure. When making an abnormality judgment, the corresponding threshold range should be selected for judgment.

[0041] In a specific embodiment, the production process monitoring unit is used to obtain the product process parameters of the current color steel plate during the production process through a dedicated detector. For example, the mechanical properties of the substrate affect the basic properties of the product, the thickness of the organic coating is related to the quality and effect of the coating, the production line speed determines the production efficiency, the coating viscosity affects the uniformity of the coating, etc., and the curing temperature and drying time determine the curing and drying effects of the coating. Similarly, the production process monitoring unit judges these product process parameters against the corresponding threshold ranges. Those that meet the range are determined as normal data, and those that do not are abnormal data.

[0042] In a specific embodiment, the energy consumption monitoring unit is responsible for obtaining the energy consumption parameters on the production line. For example, the water energy utilization rate, the electric energy utilization rate, and the gas energy utilization rate can reflect the utilization situations of different energies. The energy consumption monitoring unit also determines the nature of the energy consumption parameters by comparing them with the set energy consumption parameter threshold ranges. Those that meet the threshold range are normal data, otherwise they are abnormal data.

[0043] In a specific embodiment, the environment monitoring unit uses sensors to collect the production environment parameters on the production line. For example, the environmental temperature and humidity, and the production environment parameters may have a certain impact on the production process and product quality. By comparing the production environment parameters with the corresponding threshold ranges. Those that meet are normal data, and those that do not are abnormal data.

[0044] In a specific embodiment, the product performance monitoring unit can obtain the product performance parameters of the current color steel plate with the help of a detector. For example, the color difference reflects the consistency of the product color, the glossiness reflects the appearance gloss condition of the product, and the color uniformity concerns the overall color uniformity of the product. The product performance monitoring unit also determines the status of the product performance parameters based on the comparison result with the set threshold range of the product performance parameters. The data that conforms is normal data, and the data that does not conform is abnormal data.

[0045] In summary, through the collaborative work of these monitoring units, all aspects of the organic coated color steel plate production line can be comprehensively and meticulously grasped, problems can be discovered in a timely manner, and corresponding measures can be taken to ensure the smooth progress of production and the quality of products.

[0046] Optionally, the online monitoring module is further configured to determine the performance difference between the product performance parameters and the corresponding standard performance parameters when the product performance parameters are normal data. When the performance difference is greater than the preset performance difference threshold, adjustment parameters are determined based on the product performance parameters, and the product process parameters are feedback-adjusted according to the adjustment parameters.

[0047] Specifically, the online monitoring module further makes a detailed comparison between the normal product performance parameters and the corresponding standard performance parameters, so as to calculate the performance difference between them. The standard performance parameters are reference values set according to the ideal state or established standards of the product. Then, the calculated performance difference is compared with the preset performance difference threshold. If the performance difference exceeds this preset performance difference threshold, it means that although the product performance parameters themselves are normal, there is still a certain deviation compared with the standard, and adjustment is needed. The online monitoring module can determine specific adjustment parameters based on the current product performance parameters, and feedback-adjust the production process parameters according to the determined adjustment parameters. In this way, the production process can be improved to be closer to the standard performance parameters, continuously improving the performance and quality of the product, minimizing the gap between the actual product performance and the standard performance, so as to ensure that the produced products can better meet the expected requirements and standards.

[0048] Furthermore, the online monitoring module will adjust the production quality according to the adjustment parameters and then transmit these adjustment instructions to the relevant equipment or systems responsible for the product process. After receiving the instructions, these equipment or systems will change and adjust the production process parameters in real time as required, such as changing the running speed of the production line, adjusting the pressure during the processing, controlling the reaction time, etc. In addition, during the adjustment process, the online monitoring module will continuously monitor the changes in the product performance parameters to ensure that the effect of the feedback adjustment meets the expectations. If it is found that the adjustment effect is not ideal, it may further analyze and re-determine the adjustment parameters, and perform the feedback adjustment again, forming a continuous optimization and improvement cycle process until the gap between the product performance parameters and the standard performance parameters reaches an ideal state, thereby ensuring that the quality and performance of the product are stable at a relatively high level.

[0049] It should be noted that the adjustment parameters can be determined in the following ways: First, based on historical experience data. By analyzing the effective adjustment parameters used in similar situations in the past when performance differences occurred, these can be used as a reference to initially determine the current adjustment parameters. Second, using data analysis and model calculation. Establish relevant data analysis models, input the product performance parameters, standard performance parameters, and other relevant factors into the model, and obtain possible adjustment parameters through the operation and reasoning of the model. Third, conducting experiments and tests. Some tentative process parameter adjustment experiments can be carried out in a small range or under specific conditions, observing the impact of different adjustment parameter combinations on the product performance, so as to screen out more suitable adjustment parameters. Fourth, expert evaluation. Invite experts in the relevant field to analyze the product performance parameters based on their professional knowledge and experience and give reasonable suggestions for adjustment parameters.

[0050] Optionally, the prediction analysis module specifically includes: a test group generation unit and a model construction unit; the test group generation unit is used to obtain historical production data, determine the collection time of each historical production data, sort each historical production data in ascending order according to the collection time to generate a sample sequence, generate test groups according to the sample sequence, and determine the target time corresponding to the test groups, where each test group includes a specified number of adjacent historical production data; the model construction unit is used to build a time series neural network structure, determine the initial parameters of the neural network structure, input the test groups into the neural network structure to obtain the production data sample values corresponding to the target time, and determine the true values of the production data at the target time, determine the squared error between the production data sample values and the true values of the production data, determine the final parameters according to the squared error and the initial parameters, and generate a prediction analysis model according to the final parameters. The forward process of the time series neural network structure is as follows:

[0051] ;

[0052] Among them, and Represents a moment, Represents the input test group, Represents the memory of the sample at time Here, Represents the input weight, Represents the weight of the input test group at this moment, Represents the output test group weight.

[0053] Specifically, the test group generation unit will obtain a large amount of historical production data, which records various information in the previous production process. Then it will determine the collection time of each piece of historical production data and sort all the historical production data in ascending order from the earliest to the latest according to the order of collection time, thus generating a sample sequence. And test groups will be generated based on the sample sequence. When generating test groups, a specified number of adjacent historical production data will be selected. At the same time, a corresponding target time will be determined for each test group. Exemplarily, the test group with a collection time of the 1st - 5th second can correspond to the target time of 6 seconds, and the test group with a collection time of the 6th - 10th second can correspond to the target time of 11 seconds, and so on.

[0054] Specifically, the model construction unit will first construct a time - series neural network structure, which is the basic framework for data analysis and prediction. Then the generated test groups will be input into the neural network structure. Through calculation and analysis, the production data sample value corresponding to the target time will be obtained. This sample value is the prediction result calculated by the model based on the input data. At the same time, the true value of the actual production data at the target time also needs to be determined. Then the square error between the production data sample value and the true value of the production data will be calculated. The square error reflects the deviation degree between the prediction result and the actual result.

[0055] In a specific implementation, the forward process of the time - series neural network structure is represented by the following formula (1):

[0056]

[0057] Where, And Represents a moment, Represents the input test group, Represents the memory of the sample at time Here, Represents the input weight, Represents the weight of the input test group at this moment, Represents the output test group weight. Further, at moment, generally initialize Randomly initialize , , , and then calculate using the following formula:

[0058]

[0059] Among them, and represent activation functions, represents the output at time represents an intermediate variable, represents the set of test groups input at time represents the memory of the sample at time ; represents the initial memory, , represents the input weight, represents the weight of the test group input at this moment, represents the weight of the output test group. When time advances, the current state serves as the memory state at time and participates in the prediction activity at the next moment, that is:

[0060]

[0061] Among them, and represent activation functions, represents the output at time represents an intermediate variable, represents the set of test groups input at time represents the memory of the test group at time ; represents the memory of the test group at time ; represents the input weight, represents the weight of the test group input at this moment, represents the weight of the output test group.

[0062] The model construction unit can continuously adjust and optimize the initial parameters based on the calculated mean squared error, so as to determine the final parameters to generate a predictive analysis model. Using this predictive analysis model, the future production situation of the production line can be estimated and judged more accurately, so as to better guide production decisions and process optimization.

[0063] Optionally, the system further includes: a surface defect detection module connected to the online monitoring module; the surface defect detection module is configured to collect a grayscale image of the original steel plate on the production line at a specified time, perform grayscale projection on the grayscale image to determine the grayscale average value, and determine the grayscale difference between each pixel point in the grayscale image and the grayscale average value, and determine whether the grayscale difference is greater than a preset grayscale difference threshold. If so, generate a third-level warning prompt. Otherwise, generate a data monitoring instruction according to a preset time and send the data monitoring instruction to the online monitoring module.

[0064] Specifically, the surface defect detection module obtains the grayscale image of the original steel plate at a specified time point through an image acquisition device. After the image is collected, using the grayscale projection technology, the two-dimensional grayscale image can be converted into one-dimensional grayscale value distribution information, which is convenient for calculating and analyzing the grayscale average value. After calculating the grayscale average value, compare the grayscale value of each pixel point with the average value one by one, which can keenly detect the minute changes in grayscale. The preset grayscale difference threshold is a judgment criterion. When the grayscale difference exceeds it, it indicates that there may be defects because this exceeds the normal grayscale fluctuation range. At this time, a third-level warning prompt is issued. If it is within the threshold range, it means the surface is relatively normal, and then a data monitoring instruction is generated according to the preset time, allowing the online monitoring module to further participate in the subsequent monitoring work. The whole process realizes the effective detection and monitoring of the surface defects of the original steel plate through continuous comparison, analysis and feedback.

[0065] Optionally, the system further includes: a product positioning module connected to the surface defect detection module; the surface defect detection module is further configured to send the data monitoring instruction to the product positioning module; the product positioning module is configured to obtain a production line image through a camera device and detect the production line image based on a steel plate recognition model to identify the target color-coated steel plate therein, and position the target color-coated steel plate through a target tracking algorithm. When it is detected that the target color-coated steel plate exceeds the preset area range, generate a fourth-level warning prompt, where the positioning includes position positioning and angle positioning; among them, the angle positioning formula is:

[0066] ;

[0067] where N1 represents the production line reference plane, N2 represents the upper surface of the target color-coated steel plate, N1⋅N2 = A1A2 + B1B2 + C1C2, , , A1, B1 and C1 represent the normal vector coordinates of the production line reference plane, and A2, B2 and C2 represent the normal vector coordinates of the upper surface of the target color-coated steel plate, represents the angle between the production line reference plane and the upper surface of the target color-coated steel plate.

[0068] Specifically, the surface defect detection module also sends the generated data monitoring instructions to the product positioning module. After receiving the instructions, the product positioning module uses the camera device to obtain real-time images on the production line. Then, based on the pre-trained steel plate recognition model, these production line images are deeply detected and analyzed to identify the target color-coated steel plate from the images. Next, the product positioning module uses the target tracking algorithm to continuously and accurately position and track the identified target color-coated steel plate. In this way, the position information of the target color-coated steel plate on the production line can be grasped in real time. When the product positioning module detects that the target color-coated steel plate exceeds the preset area range, it indicates that there may be an abnormality in the production process. At this time, a level 4 warning prompt will be generated. Through the level 4 warning prompt, relevant personnel can be reminded in time to ensure the smooth progress of the production process and the accurate position of the product.

[0069] Specifically, the angle positioning is expressed by the following formula:

[0070]

[0071] Among them, N1 represents the production line reference plane, N2 represents the upper surface of the target color-coated steel plate, N1⋅N2 = A1A2 + B1B2 + C1C2, , , A1, B1, and C1 represent the normal vector coordinates of the production line reference plane, and A2, B2, and C2 represent the normal vector coordinates of the upper surface of the target color-coated steel plate, represents the angle between the production line reference plane and the upper surface of the target color-coated steel plate. The angle can be obtained through the inverse cosine calculation . When the angle is greater than the preset threshold, such as 5°, it means that the target color-coated steel plate has an angle deviation, and at this time, a level 4 warning prompt will also be generated.

[0072] Optionally, the system further includes: a production efficiency determination module connected to the product positioning module; the product positioning module is further configured to obtain each preset positioning point, determine the timestamp when the target color-coated steel plate reaches each preset positioning point, and send each timestamp to the production efficiency determination module; the production efficiency determination module is configured to determine the number of timestamps received within a specified period, and determine the production efficiency of the production line according to the number of timestamps and the timestamps.

[0073] Specifically, the product positioning module will obtain each preset positioning point set in advance. The preset positioning points are usually position points with specific meanings on the production line. When the target color-coated steel plate moves on the production line and reaches these preset positioning points, the product positioning module will accurately record the corresponding timestamps, that is, the specific time point information when reaching each preset positioning point. Then the product positioning module will send these recorded timestamps to the production efficiency determination module.

[0074] Furthermore, after receiving these timestamps, the production efficiency determination module will also determine the number of timestamps received within a specified period. The production efficiency determination module will comprehensively determine the production efficiency of the production line based on the number of timestamps and the specific time information represented by each timestamp through specific algorithms and calculation methods, so as to provide an important basis for production management and decision-making, in order to timely detect problems in production efficiency, take corresponding measures to optimize the production process, improve production efficiency, and ensure that the production line can operate efficiently and stably.

[0075] Exemplarily, when the production efficiency determination module performs calculations, it will first count the number of received timestamps. Assume that N timestamps are received within the specified period. Then the production efficiency determination module can analyze the time intervals between these timestamps. By calculating the differences between adjacent timestamps, the time spent in each production process stage can be obtained, and then by summing up these times, the total production time T can be obtained.

[0076] In a specific embodiment, the production efficiency can be determined in various ways. For example, the number of products produced within this period can be divided by the total production time to obtain the production quantity per unit time, which is used to represent the production efficiency. Or divide the total production time by the number of products to obtain the average time required to produce a single product, which reflects the production efficiency from another perspective. For example, if M target color steel plates are produced within this period, then the production efficiency can be expressed as M / T (the number of products produced per unit time), or T / M (the average time to produce a single product). In actual calculations, some other factors may also be considered, such as the weights of different stages, time losses caused by abnormal situations, etc. The actual production efficiency of the production line can be determined more accurately through comprehensive consideration and complex calculation models, so as to more comprehensively and objectively evaluate the working status and performance of the production line.

[0077] Optionally, the system may further include a supplier collaboration module. After calculating the production efficiency, the production efficiency determination module can further send the production efficiency to the supplier collaboration module so that the supplier can timely grasp the production efficiency of the current production line. It can also enable the supplier to more clearly understand the utilization efficiency of the raw material steel plates they provide in actual production, which helps the supplier better grasp the impact of the quality and performance of their products or services on the customer's production line, and thus make targeted improvements and optimizations to enhance the supply quality. Secondly, the supplier can reasonably adjust its production plan and delivery arrangement according to the production efficiency information. If the production efficiency is high, the supplier can appropriately increase the supply quantity to meet the demand; on the contrary, if the production efficiency is low, the supplier can make timely adjustments to avoid waste of resources caused by over-supply. In addition, the supplier can optimize its resource allocation based on the production efficiency data. For example, for products or services closely related to high-efficiency production, the supplier can increase investment and resource allocation to better support the customer's production. In summary, information sharing helps the collaborative operation of the entire supply chain. It enables the supplier to better adapt to the production rhythm and demand changes, thereby enhancing the stability and competitiveness of the entire supply chain.

[0078] The technical solution of the embodiment of the present invention detects production-related data through the online monitoring module and issues an abnormal warning, providing a basis for production optimization. Through the prediction analysis module, the production-related data is predicted and analyzed to achieve early monitoring and warning and eliminate potential production safety hazards. By positioning the color steel plate, equipment failures can be reduced, and production efficiency analysis can be carried out, enabling users to more intuitively master the production process.

[0079] Embodiment 2: Figure 3 FIG. is a schematic structural diagram of an online monitoring system for an organic-coated color steel plate production line provided in Embodiment 1 of the present invention. Figure 3 On the basis of Embodiment 1, a user terminal and a storage module are added.

[0080] Optionally, the system further includes: a user terminal connected to the online monitoring module, the prediction analysis module, the surface defect detection module, and the product positioning module; the user terminal is used to receive warning prompts and alarm in a specified manner according to the warning prompts, where the warning prompts include first-level warning prompts, second-level warning prompts, third-level warning prompts, and fourth-level warning prompts.

[0081] Specifically, the user terminal has the function of receiving warning prompts. The warning prompts include first-level warning prompts, second-level warning prompts, third-level warning prompts, and fourth-level warning prompts. Among them, the first-level warning prompts are issued by the online monitoring module, indicating that there are abnormalities in the current production-related data. The second-level warning prompts are issued by the prediction analysis module, indicating that abnormalities will occur in the production-related data in the future. The third-level warning prompts are issued by the surface defect detection module, indicating that there are surface defects in the original steel plate. The fourth-level warning prompts are issued by the product positioning module, indicating that there are abnormalities in the position of the target steel plate. The user terminal will alarm in a specified manner according to the warning prompts, which may be continuous sound prompts or warning signals of specific colors, etc., to remind relevant personnel that they need to take corresponding measures as soon as possible. In addition, the user terminal can alarm in different ways according to the different levels of warning prompts, so that users can distinguish the specific abnormal situations in time.

[0082] Optionally, the system further includes: a storage module connected to the user terminal and the online monitoring module; the online monitoring module is further configured to send production-related data to the storage module; the storage module is configured to receive and store the production-related data; the user terminal is further configured to obtain a data query instruction input by the user and send the data query instruction to the storage module; the storage module is configured to screen the production-related data based on the data query instruction to obtain target query data and feed back the target query data to the user terminal.

[0083] Specifically, the online monitoring module will also send the production-related data to the storage module. The storage module will store the production-related data for subsequent call and analysis at any time. The user terminal can obtain the instruction related to data query input by the user. When the user wants to query specific production-related data, the corresponding data query instruction can be input by operating the user terminal, and then the user terminal will send this instruction to the storage module. After receiving the data query instruction, the storage module will screen and process the stored production-related data according to the requirements of the instruction, so as to accurately find the target query data that meets the requirements of the query instruction from a large amount of data. Finally, the storage module will feed back the found target query data to the user terminal. In this way, the user can obtain the production-related data he needs through the user terminal, so as to more conveniently and quickly understand and master the specific situation in the production process, providing strong support for decision-making and management.

[0084] The technical solution of the embodiment of the present invention detects and issues abnormal warnings for production-related data through the online monitoring module, providing a basis for production optimization. Through the prediction analysis module, the production-related data is predicted and analyzed to achieve early monitoring and warning and eliminate potential production safety hazards. By positioning the color steel plate, equipment failures can be reduced, and production efficiency analysis can be carried out, enabling users to more intuitively master the production process.

[0085] Embodiment 3: Figure 4 The figure is a flowchart of an online monitoring method for an organic coated color steel plate production line provided by Embodiment 3 of the present invention. This embodiment is applicable to the scenario of real-time monitoring of an organic coated color steel plate production line. As Figure 4 shown, the method includes:

[0086] S310. The online monitoring module collects production-related data on the organic coated color steel plate production line according to the data monitoring instruction, and determines whether the production-related data is normal data. If so, the production-related data is sent to the prediction analysis module; otherwise, a first-level warning prompt is generated according to the production-related data, where the production-related data includes equipment operation parameters, product process parameters, energy consumption parameters, production environment parameters, and product performance parameters.

[0087] Specifically, the online monitoring module can comprehensively collect production-related data in all aspects of the organic coated color steel plate production line according to the data monitoring instruction. And it will use specific judgment logics and standards to judge the collected production-related data. If the judgment is normal data, these data will be sent to the prediction analysis module for further analysis and processing. Once it is found that the production-related data is not normal data, a first-level warning prompt will be generated according to these abnormal data. So that relevant personnel can be aware of possible problems in the production process in a timely manner.

[0088] S320. The prediction analysis module constructs a prediction analysis model, and inputs the received production-related data into the prediction analysis model to obtain the prediction result output by the prediction analysis model. When the prediction result is a prediction anomaly, a second-level warning prompt is generated according to the production-related data.

[0089] Specifically, after receiving the production-related data sent from the online monitoring module, the prediction analysis module inputs the production-related data into the constructed prediction analysis model. The prediction analysis model will output the corresponding prediction result. When the prediction result is a prediction anomaly, it means that problems may occur in the future based on the existing data. At this time, a second-level warning prompt will be generated according to the corresponding production-related data. The second-level warning prompt can remind relevant personnel to take corresponding measures in advance to avoid the further deterioration and expansion of the problems.

[0090] The technical solution of the embodiment of the present invention detects production-related data through the online monitoring module and gives an anomaly warning, providing a basis for production optimization. Through the prediction analysis module, the production-related data is predicted and analyzed to achieve early monitoring and warning and eliminate potential production safety hazards. By positioning the color steel plate, equipment failures can be reduced, and production efficiency analysis can be carried out, enabling users to more intuitively master the production process.

[0091] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in the present invention can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is imposed herein.

[0092] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub - combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. The online monitoring system of the organic coating color steel plate production line is characterized by: include: An online monitoring module, and a prediction analysis module connected to the online monitoring module; The online monitoring module is used to collect production-related data on the organic coated color steel plate production line according to the data monitoring instruction, and determine whether the production-related data is normal data. If so, the production-related data is sent to the prediction analysis module; otherwise, a first-level early warning prompt is generated according to the production-related data, wherein the production-related data includes equipment operation parameters, product process parameters, energy consumption parameters, production environment parameters and product performance parameters; The prediction analysis module is used to build a prediction analysis model and input the received production-related data into the prediction analysis model to obtain a prediction result output by the prediction analysis model, and when the prediction result is a prediction abnormality, generate a secondary warning prompt according to the production-related data; The prediction and analysis module specifically includes: a test group generation unit and a model building unit; The test group generating unit is used to obtain historical production data, determine the collection time of each historical production data, sort each historical production data in ascending order according to the collection time to generate a sample sequence, generate a test group according to the sample sequence, and determine the target time corresponding to the test group, wherein the test group includes a specified number of adjacent historical production data; The model building unit is used to build a time series neural network structure, determine the initial parameters of the neural network structure, input the test group into the neural network structure to obtain the corresponding production data sample value of the target time, determine the true value of the production data at the target time, determine the square error between the production data sample value and the true value of the production data, determine the final parameters according to the square error and the initial parameters, and generate the prediction analysis model according to the final parameters; Among them, the forward process of the temporal neural network structure is: ;in, and Indicates the time, Indicates the input test group, Indicates at time Input test group, Indicates that the sample is at time The memory of Indicates that the sample is at time The memory of represents the input weight, Indicates the weight of the test group entered at this moment, Represents the temporal neural network structure function; Wherein, the system further comprises: a surface defect detection module connected to the online monitoring module; The surface defect detection module is used to collect the grayscale image of the original steel plate on the production line according to the specified time, perform grayscale projection on the grayscale image to determine the grayscale average value, and determine the grayscale difference between each pixel in the grayscale image and the grayscale average value, and judge whether the grayscale difference is greater than a preset grayscale difference threshold. If so, generate a three-level early warning prompt, otherwise, generate a data monitoring instruction according to the preset time, and send the data monitoring instruction to the online monitoring module; Wherein, the system further comprises: a product positioning module connected to the surface defect detection module; The surface defect detection module is further used to send the data monitoring instruction to the product positioning module; The product positioning module is used to obtain the production line image through the camera device, and detect the production line image based on the steel plate recognition model to identify the target color steel plate therein, and locate the target color steel plate through the target tracking algorithm. When the target color steel plate is detected to be beyond the preset area, a four-level warning prompt is generated, wherein the positioning includes position positioning and angle positioning; Wherein, the angle positioning formula is: ; Among them, N1 represents the production line reference surface, N2 represents the target color steel plate surface, , , , A1, B1 and C1 represent the normal vector coordinates of the production line reference plane, A2, B2 and C2 represent the normal vector coordinates of the target color steel plate surface, It indicates the angle between the production line reference plane and the upper surface of the target color steel plate.

2. The online monitoring system for the organic coated color steel plate production line according to claim 1 is characterized in that: The online monitoring module specifically includes: an equipment status monitoring unit, a production process monitoring unit, an energy consumption monitoring unit, an environment monitoring unit and a product performance monitoring unit; The equipment status monitoring unit is used to obtain equipment operating parameters of each target equipment on the production line through sensors, and determine whether the equipment operating parameters meet the corresponding equipment parameter threshold range. If so, the equipment operating parameters are determined to be normal data, otherwise, the equipment operating parameters are determined to be abnormal data, wherein the equipment operating parameters include equipment temperature, equipment pressure and equipment speed; The production process monitoring unit is used to obtain the product process parameters of the current color steel plate on the production line through the detector, and determine whether the product process parameters meet the corresponding product process parameter threshold range. If so, the product process parameters are determined to be normal data, otherwise, the product process parameters are determined to be abnormal data, wherein the product process parameters include mechanical properties of the substrate, thickness of the organic coating, production line speed, coating viscosity, curing temperature and drying time; The energy consumption monitoring unit is used to obtain energy consumption parameters on the production line, determine whether the energy consumption parameters meet the corresponding energy consumption parameter threshold range, and if so, determine that the energy consumption parameters are normal data; otherwise, determine that the energy consumption parameters are abnormal data, wherein the energy consumption parameters include water energy usage rate, electricity energy usage rate and gas energy usage rate; The environmental monitoring unit is used to obtain the production environment parameters on the production line through sensors, and determine whether the production environment parameters meet the corresponding production environment parameter threshold range. If so, determine that the production environment parameters are normal data; otherwise, determine that the production environment parameters are abnormal data, wherein the production environment parameters include ambient temperature and ambient humidity; The product performance monitoring unit is used to obtain the product performance parameters of the current color steel plate on the production line through a detector, and determine whether the product performance parameters meet the corresponding product performance parameter threshold range. If so, the product performance parameters are determined to be normal data; otherwise, the product performance parameters are determined to be abnormal data, wherein the product performance parameters include color difference value, glossiness and color uniformity.

3. The online monitoring system for the organic coated color steel plate production line according to claim 2 is characterized in that: The online monitoring module is also used to determine the performance difference between the product performance parameter and the corresponding standard performance parameter when the product performance parameter is normal data, and when the performance difference is greater than a preset performance difference threshold, determine the adjustment parameter according to the product performance parameter, and feedback-adjust the product process parameter according to the adjustment parameter.

4. The online monitoring system for the organic coated color steel plate production line according to claim 1 is characterized in that: The system further comprises: a production efficiency determination module connected to the product positioning module; The product positioning module is also used to obtain each preset positioning point, determine the time stamp when the target color steel plate reaches each preset positioning point, and send each time stamp to the production efficiency determination module; The production efficiency determination module is used to determine the number of timestamps received within a specified period, and determine the production efficiency of the production line according to the number of timestamps and the timestamps.

5. The online monitoring system for the organic coated color steel plate production line according to claim 1 is characterized in that: The system further includes: a user terminal connected to the online monitoring module, the prediction and analysis module, the surface defect detection module and the product positioning module; The user terminal is used to receive early warning prompts and issue an alarm in a specified manner according to the early warning prompts, wherein the early warning prompts include level one early warning prompts, level two early warning prompts, level three early warning prompts and level four early warning prompts.

6. The online monitoring system for the organic coating color steel plate production line according to claim 5 is characterized in that: The system further comprises: a storage module connected to the user terminal and the online monitoring module; The online monitoring module is also used to send the production-related data to the storage module; The storage module is used to receive and store the production-related data; The user terminal is further used to obtain a data query instruction input by a user and send the data query instruction to the storage module; The storage module is used to screen the production-related data based on the data query instruction to obtain target query data, and feed back the target query data to the user terminal.

7. An online monitoring method for an organic coated color steel plate production line, characterized in that: A system for online monitoring of an organic coated color steel plate production line according to any one of claims 1 to 6, comprising: The online monitoring module collects production-related data on the organic coated color steel plate production line according to the data monitoring instruction, and determines whether the production-related data is normal data. If so, the production-related data is sent to the prediction analysis module. Otherwise, a first-level early warning prompt is generated according to the production-related data, wherein the production-related data includes equipment operation parameters, product process parameters, energy consumption parameters, production environment parameters and product performance parameters; A prediction analysis model is constructed through the prediction analysis module, and the received production-related data is input into the prediction analysis model to obtain a prediction result output by the prediction analysis model. When the prediction result is a prediction abnormality, a secondary warning prompt is generated based on the production-related data.

Images