Stamping production control method based on big data monitoring

Abstract

The invention provides a stamping production control method based on big data monitoring, and relates to the technical field of stamping control, and the method comprises the steps: obtaining a stamping production control instruction through a stamping production management module; setting a stamping production loss factor; performing loss prediction on the stamping production control scheme according to the stamping production loss factor to obtain a stamping loss prediction result; the prediction result is input into a stamping loss verification module, and a stamping loss verification result is generated; when the verification result is not passed, a stamping loss optimization module is activated, the production control scheme is optimized in combination with product requirements, and a stamping production control optimization result is obtained; and based on the punching production monitoring regulation and control module, punching control is performed according to the control optimization result, the technical problems of insufficient data utilization, slow response speed and insufficient optimization capability in punching production in the prior art are solved, and the purposes of improving the punching production efficiency and the product quality through big data monitoring and optimization control and improving the product quality are achieved. And the production cost is reduced.

Description

Technical Field

[0001] The present invention relates to the field of stamping control technology, and in particular to a stamping production control method based on big data monitoring. Background Art

[0002] With the rapid development of intelligent manufacturing, stamping production, as an important link in the manufacturing industry, has a direct impact on the competitiveness and profitability of enterprises due to its production efficiency, quality and resource utilization. Traditional stamping production management often relies on manual experience and fixed production processes, which makes it difficult to cope with complex and changing market demands and production environments, and cannot make full use of the massive data generated in the production process, resulting in insufficient decision-making basis and difficulty in making accurate production control decisions. In addition, in the face of rapid changes in market demand and sudden problems in the production process, traditional methods often lag in response and make it difficult to adjust production plans and control strategies in a timely manner. And simply relying on manual experience and fixed rules makes it difficult to achieve global optimization and continuous improvement. The rise of big data technology has made it possible for intelligent and refined management of stamping production. By collecting, processing and analyzing massive data in the production process, enterprises can more accurately grasp the production status, discover problems in a timely manner and make optimization adjustments, thereby improving production efficiency and product quality and reducing production costs.

[0003] In summary, the existing technologies often have technical problems such as insufficient data utilization, slow response speed and insufficient optimization capability in stamping production. Summary of the invention

[0004] The present application provides a stamping production control method based on big data monitoring, which is used to solve the technical problems of insufficient data utilization, slow response speed and insufficient optimization capability in stamping production existing in the prior art.

[0005] The present application provides a stamping production control method based on big data monitoring, the method comprising:

[0006] According to the stamping production management module, a stamping production control instruction is obtained, wherein the stamping production control instruction includes the stamping product demand and the stamping production control plan; a stamping production loss factor is set, wherein the stamping production loss factor includes the stamping production resource utilization loss, the stamping production efficiency loss and the stamping production quality loss; a loss prediction is performed on the stamping production control plan according to the stamping production loss factor to obtain a stamping loss prediction result; the stamping loss prediction result is input into the stamping loss verification module to generate a stamping loss verification result; when the stamping loss verification result is not passed, the stamping loss optimization module is activated, and the stamping production control plan is optimized in combination with the stamping product demand to obtain a stamping production control optimization result; based on the stamping production monitoring and control module, stamping control is performed according to the stamping production control optimization result.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] The stamping production control method based on big data monitoring provided in the present application obtains stamping production control instructions according to the stamping production management module, wherein the stamping production control instructions include stamping product requirements and stamping production control plans; sets stamping production loss factors, wherein the stamping production loss factors include stamping production resource utilization loss, stamping production efficiency loss and stamping production quality loss; performs loss prediction on the stamping production control plan according to the stamping production loss factor to obtain a stamping loss prediction result; inputs the stamping loss prediction result into a stamping loss verification module to generate a stamping loss verification result; when the stamping loss verification result is not passed, activates the stamping loss optimization module, optimizes the stamping production control plan in combination with the stamping product requirements, and obtains a stamping production control optimization result; performs stamping control based on the stamping production monitoring and control module according to the stamping production control optimization result, thereby solving the technical problems of insufficient data utilization, slow response speed and insufficient optimization capability in stamping production in the prior art, and achieving the technical effect of improving stamping production efficiency, product quality and reducing production costs through big data monitoring and optimization control. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 A flow chart of a stamping production control method based on big data monitoring is provided for this application.

[0010] Figure 2 A flow chart of obtaining stamping loss prediction results in a stamping production control method based on big data monitoring is provided for this application. DETAILED DESCRIPTION

[0011] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0012] Examples, such as Figure 1 As shown, the present application provides a stamping production control method based on big data monitoring, the method comprising:

[0013] Step S100: obtaining a stamping production control instruction according to a stamping production management module, wherein the stamping production control instruction includes a stamping product requirement and a stamping production control plan.

[0014] In the whole process of stamping production management, a crucial link is to obtain and parse stamping production control instructions according to the stamping production management module. This step is not only the key to start the entire production process, but also the basis for ensuring that subsequent production activities can be carried out accurately and efficiently. As the core brain of the entire production system, the stamping production management module is responsible for integrating data information from various production links, including inventory status, equipment status, personnel configuration, and past production records. This information is processed by the intelligent algorithm inside the module to form a series of instructions that are instructive for production activities.

[0015] As the output of the stamping production management module, the stamping production control instructions include two core elements: stamping product demand and stamping production control plan. The stamping product demand refers to the specific market demand information for stamping products in the current or future period, including but not limited to product type, specification, quantity, delivery date, etc. This information is the direct basis for formulating production plans and an important reference for evaluating production capacity and resource allocation. For example, if the market demand is for metal stamping parts of a certain size and material, then this demand will be clearly reflected in the demand for stamping products. The stamping production control plan is a detailed production guidance plan formulated on the basis of a full understanding of the demand for stamping products and combined with current production conditions (such as equipment capacity, raw material supply, personnel skills, etc.). The plan not only includes the specific arrangement of the production process (such as the processing order of the process and the specific operation requirements of each process, etc.), but also involves the scheduling of production resources (such as equipment allocation, material flow, personnel scheduling, etc.) and quality control standards and measures. Through this plan, production managers can clearly understand how to organize production activities to meet market demand.

[0016] In actual operation, the process of obtaining stamping production control instructions is usually implemented through the user interface of the production management system. The production manager first logs into the system to enter the stamping production management module. By querying or entering relevant parameters (such as market demand information, inventory levels, etc.), the system can automatically calculate the demand for stamping products and generate stamping production control plans based on preset algorithms and rules. This process not only reflects the intelligence and automation of the system, but also requires production managers to have high professional quality and judgment ability so that they can adjust and optimize the plans generated by the system when necessary.

[0017] The step of obtaining stamping production control instructions according to the stamping production management module is an indispensable part of the stamping production process. It not only provides a clear guiding direction for subsequent production activities, but also is an important guarantee for achieving production efficiency, product quality and cost control goals.

[0018] Step S200: setting a stamping production loss factor, wherein the stamping production loss factor includes stamping production resource utilization loss, stamping production efficiency loss and stamping production quality loss.

[0019] Specifically, in order to comprehensively and meticulously evaluate the various losses that may be encountered in the stamping production process, so as to provide a solid basis for subsequent loss prediction and optimization control, it is necessary to set the stamping production loss factor. The main loss dimensions involved in the stamping production process include stamping production resource utilization loss, stamping production efficiency loss and stamping production quality loss. Among them, the stamping production resource utilization loss refers to the loss of resource value that cannot be fully utilized due to improper resource allocation, waste or idleness in the production process. For example, long-term idling of equipment and excessive accumulation of raw materials without timely treatment all belong to the category of resource utilization loss; the stamping production efficiency loss reflects the slowdown of production speed or extension of production cycle caused by various reasons in the production process, which in turn affects the loss of overall production efficiency. This may be caused by factors such as equipment failure, unreasonable process, and unskilled operation of personnel; the stamping production quality loss refers to the economic loss and reputation loss caused by the stamping products produced not meeting the quality standards and needing to be reworked, scrapped or reduced in price. Quality loss may be caused by raw material problems, insufficient equipment precision, and lax production process control. After identifying the loss dimension, each loss factor can be quantified, and on the basis of quantifying each loss factor, these factors need to be integrated into a unified system for subsequent loss prediction and optimization control. At the same time, it is necessary to ensure that the above system should be able to clearly reflect the relationship between the various loss factors and their impact on the overall production performance.

[0020] Suppose that in a certain stamping production process, it is found that the equipment idle time accounts for 10% of the total production time, the raw material inventory turnover rate is 20% lower than the industry average, and the defective product rate reaches 5%. Based on these data, the quantitative values ​​of resource utilization loss, production efficiency loss and quality loss can be calculated respectively, and they can be included in the loss factor system for analysis and comparison. In this way, the problems and deficiencies in the production process can be more intuitively understood, providing a clear direction and goal for subsequent optimization control.

[0021] Step S300: performing loss prediction on the stamping production control scheme according to the stamping production loss factor to obtain a stamping loss prediction result.

[0022] Optionally, a prediction framework based on stamping production loss factors is established. This framework should clearly include which loss factors (such as resource utilization loss, production efficiency loss, and production quality loss) will be included in the prediction scope, and determine how these factors are associated with the stamping production control scheme. In order to make accurate loss predictions, historical data related to stamping production is collected, such as past production records, resource consumption, efficiency statistics, quality inspection results, etc. At the same time, it is also necessary to obtain the specific content of the current production control scheme, including production plans, equipment configuration, personnel arrangements, etc. Further, the relationship between loss factors and control schemes is analyzed, and each loss factor is analyzed in depth to clarify how they are affected by the stamping production control scheme. For example, production efficiency loss may be affected by multiple factors such as the rationality of production plans, equipment failure rate, and personnel skill level; while production quality loss may be closely related to raw material quality, process control accuracy, quality inspection standards, etc. Based on the above analysis, a loss prediction model is constructed using statistics, machine learning, or other prediction techniques. This model will comprehensively consider the impact of each loss factor and make predictions based on the characteristics of the current production control scheme, and the model should be able to output the loss prediction results of the stamping production control scheme under different scenarios. Furthermore, the specific parameters of the current stamping production control scheme can be input into the prediction model, the model can be run and the stamping loss prediction results can be obtained. This result will include the specific values ​​of each loss factor and the overall loss assessment. Finally, the prediction results are interpreted in detail, the changing trends and causes of each loss factor are analyzed, and the risks and problems that may be caused by the current production control scheme are evaluated. The pros and cons of different schemes can also be evaluated by comparing the prediction results under different schemes. By predicting the loss of the production control scheme, it is helpful to identify potential risks and problems in advance, so that appropriate measures can be taken to reduce losses.

[0023] For example, suppose that a linear regression-based prediction model for stamping production loss has been established, which takes resource utilization loss, production efficiency loss and production quality loss as dependent variables, and production plan rationality, equipment failure rate, personnel skill level, raw material quality, process control accuracy, etc. as independent variables. Now, there is a new stamping production control plan A, whose production plan is relatively compact but may face the risk of equipment overload, and the personnel skill level is high but the raw material quality is uncertain. Therefore, the specific parameters of plan A can be input into the prediction model, and the following prediction results are obtained after running the model: resource utilization loss is expected to be 5%, production efficiency loss is expected to be 3%, and production quality loss is expected to be 2%. By interpreting these results, it can be found that although plan A can improve production efficiency (relatively low efficiency loss), it may lead to higher resource utilization loss due to equipment overload operation; at the same time, the uncertainty of raw material quality may also bring certain quality loss risks. Therefore, it is necessary to further evaluate whether these risks are within an acceptable range and consider whether plan A needs to be adjusted or optimized.

[0024] Step S400: inputting the stamping loss prediction result into a stamping loss verification module to generate a stamping loss verification result.

[0025] Step S500: When the stamping loss verification result is failed, the stamping loss optimization module is activated, and the stamping production control scheme is optimized in combination with the stamping product requirements to obtain a stamping production control optimization result.

[0026] Furthermore, the obtained stamping loss prediction results (including specific values ​​of resource utilization loss, production efficiency loss, and production quality loss) are input into the stamping loss verification module for standard evaluation. The stamping loss verification module is specially designed to evaluate whether the prediction results meet the preset loss standards or thresholds. Furthermore, the stamping loss verification module conducts a comparative analysis based on the input prediction results and the preset standards or thresholds. If all loss factors in the prediction results do not exceed the corresponding thresholds, the current stamping production control plan is considered acceptable, and the verification result is "passed". On the contrary, if any one or more loss factors exceed the threshold, it is considered that the current plan has a greater risk of loss, and the verification result is "failed".

[0027] When the stamping loss verification result is "failed", the system will automatically activate the stamping loss optimization module. The function of this module is to propose targeted optimization suggestions or solutions based on the stamping product demand and the shortcomings of the current production control plan. In the stamping loss optimization module, the stamping product demand will be reviewed first, including key factors such as product type, specification, quantity, and delivery time. Then, combined with the shortcomings of the current production control plan (such as improper resource utilization, low production efficiency, lax quality control, etc.), a series of optimization measures are formulated. These measures may include adjusting production plans, optimizing equipment configuration, improving personnel skills, and improving process flows. After the implementation and adjustment of a series of optimization measures, the optimization result of stamping production control is finally obtained. This result not only considers how to reduce the risk of loss, but also takes into account the improvement of production efficiency and product quality. The optimized production control plan will be more in line with actual needs and market changes.

[0028] Suppose that the prediction result of a stamping production loss shows that both the production efficiency loss and the quality loss exceed the preset threshold. At this time, the stamping loss verification result is "failed", and the system automatically activates the stamping loss optimization module. In the optimization module, it is first confirmed that the stamping product demand is a certain model of automotive parts, with large demand and tight delivery time. In response to the problem of production efficiency loss, the optimization module recommends increasing the night production shift and using non-peak hours to improve equipment utilization; at the same time, the production line is automated to reduce manual operation links to improve efficiency. In response to the quality loss problem, the optimization module proposes to strengthen the quality inspection of raw materials to ensure that each batch of raw materials meets the production standards; at the same time, the production equipment is regularly maintained and calibrated to ensure the accuracy and stability of process control. After the implementation of the above optimization measures, the optimization results of stamping production control are finally obtained, the production efficiency and quality are significantly improved, and the loss risk is effectively controlled.

[0029] Step S600: Based on the stamping production monitoring and control module, stamping control is performed according to the stamping production control optimization result.

[0030] Specifically, the stamping production control optimization results (including production plan adjustment, equipment configuration optimization, process flow improvement and other specific solutions) are integrated into the stamping production monitoring and control module. The stamping production monitoring and control module is the core control system of the stamping production line, which is responsible for real-time monitoring of the production status and regulation as needed. In the stamping production monitoring and control module, various monitoring parameters and thresholds are reconfigured according to the optimization results. These parameters may include equipment operation status, production efficiency, product quality indicators, etc., and the threshold is used to judge whether the current production status is normal. For example, the minimum threshold of production efficiency can be set to 90%, and the threshold of quality qualification rate can be set to 98%. After the configuration is completed, the stamping production monitoring and control module is started to monitor the production process in real time. The module will continuously collect production data, including equipment operation status data, production efficiency data, product quality data, etc., and compare and analyze with the preset threshold. During the monitoring process, if a certain production data deviates from the preset threshold, the monitoring and control module will immediately perform real-time analysis to determine the cause of the deviation, and automatically or prompt the operator to take corresponding control measures. For example, if the production efficiency is found to be lower than the threshold, the module may analyze that the downtime is too long due to equipment failure. At this time, an alarm message will be automatically sent to the maintenance personnel, and the production plan will be prompted to adjust to make up for the loss.

[0031] Since stamping production is a dynamic process, the original optimization plan may need to be further adjusted as production conditions change (such as fluctuations in raw material quality, equipment aging, etc.). Therefore, the stamping production monitoring and control module can also include the function of continuous optimization and adjustment. The module will continuously evaluate the effectiveness of the optimization plan based on real-time production data and feedback results, and put forward new optimization suggestions or automatically adjust production parameters when necessary.

[0032] By performing stamping control based on the stamping production monitoring and control module and the stamping production control optimization results, it is ensured that the production process is smoothly executed according to the optimization plan, thereby achieving the optimization goals of improving production efficiency, optimizing quality and reducing losses.

[0033] Furthermore, if Figure 2 As shown, according to the stamping production loss factor, the stamping production control scheme is predicted to obtain a stamping loss prediction result. Step S300 of the present application also includes:

[0034] Step S310: Based on the stamping production loss factor, a stamping production multi-feature loss prediction channel is established, wherein the stamping production multi-feature loss prediction channel includes a stamping production resource utilization loss prediction channel, a stamping production efficiency loss prediction channel and a stamping production quality loss prediction channel.

[0035] Step S320: Based on the stamping production control solution and according to the stamping production resource utilization loss prediction channel, a predicted stamping production resource utilization loss coefficient is generated.

[0036] Step S330: Based on the stamping production control solution and according to the stamping production efficiency loss prediction channel, a predicted stamping production efficiency loss coefficient is obtained.

[0037] Step S340: Based on the stamping production control scheme and according to the stamping production quality loss prediction channel, a predicted stamping production quality loss coefficient is obtained.

[0038] Step S350: adding the predicted stamping production resource utilization loss coefficient, the predicted stamping production efficiency loss coefficient and the predicted stamping production quality loss coefficient to the stamping loss prediction result.

[0039] Exemplarily, there are many factors that may cause losses in the stamping production process, and these factors are collectively referred to as stamping production loss factors. In this embodiment, in order to comprehensively predict these losses, a stamping production multi-feature loss prediction channel can be built based on these loss factors. This channel is a comprehensive prediction model. Since the three main loss dimensions in the stamping process are analyzed here, three main sub-channels are set for the comprehensive prediction model, namely, the stamping production resource utilization loss prediction channel, the stamping production efficiency loss prediction channel, and the stamping production quality loss prediction channel. Among them, the stamping production resource utilization loss prediction channel focuses on predicting the losses caused by the underutilization or waste of resources (such as raw materials, energy, manpower, etc.). Improper resource utilization may directly increase production costs; the stamping production efficiency loss prediction channel aims to predict the losses caused by low production efficiency due to equipment failure, downtime maintenance, improper operation, etc. Low efficiency means reduced output per unit time, which directly affects the profitability of the enterprise; and the stamping production quality loss prediction channel focuses on predicting the losses caused by product quality problems (such as defects, unqualified products). Quality problems not only affect customer satisfaction, but may also cause additional costs such as returns and compensation.

[0040] Furthermore, based on the stamping production control scheme, the stamping production resource utilization loss prediction channel is used to generate the predicted stamping production resource utilization loss coefficient, which is a quantitative indicator used to represent the expected degree of resource utilization loss under a given control scheme. For example, if the control scheme includes strict monitoring and optimization of raw material use, the predicted resource utilization loss coefficient may be relatively low. Similarly, the stamping production efficiency loss prediction channel is used to obtain the predicted stamping production efficiency loss coefficient according to the stamping production control scheme, which reflects the degree of loss of production efficiency under a given control scheme. For example, if the control scheme includes enhanced measures for regular maintenance and upkeep of equipment, the predicted production efficiency loss coefficient may be reduced because equipment failures and downtime will be reduced. And, the stamping production quality loss prediction channel is used to obtain the predicted stamping production quality loss coefficient according to the stamping production control scheme, which measures the expected degree of product quality loss under a given control scheme. If the control scheme includes strict quality control and inspection measures for the production process, the predicted quality loss coefficient may be low because the number of defective products will be reduced. Finally, the predicted stamping production resource utilization loss coefficient, predicted stamping production efficiency loss coefficient and predicted stamping production quality loss coefficient are summarized into the stamping loss prediction result. The prediction result is a comprehensive evaluation report that provides the overall loss situation that may be faced under a given control scheme.

[0041] Furthermore, based on the stamping production loss factor, a stamping production multi-feature loss prediction channel is established. Step S310 of the present application also includes:

[0042] Step S311: Load the stamping production control plan record set.

[0043] Step S312: Based on the stamping production loss factor, loss record retrieval is performed according to the stamping production control scheme record set to obtain a stamping production resource utilization loss coefficient record set, a stamping production efficiency loss coefficient record set and a stamping production quality loss coefficient record set.

[0044] Step S313: constructing the stamping production resource utilization loss prediction channel according to the stamping production control scheme record set and the stamping production resource utilization loss coefficient record set.

[0045] Step S314: constructing the stamping production efficiency loss prediction channel according to the stamping production control scheme record set and the stamping production efficiency loss coefficient record set.

[0046] Step S315: constructing the stamping production quality loss prediction channel according to the stamping production control scheme record set and the stamping production quality loss coefficient record set.

[0047] Step S316: connecting the stamping production resource utilization loss prediction channel, the stamping production efficiency loss prediction channel and the stamping production quality loss prediction channel to generate the stamping production multi-feature loss prediction channel.

[0048] Specifically, the stamping production control plan record set is loaded. The detailed record set of the historical stamping production control plan is retrieved from the database or directly loaded from the file system. These record sets contain key data such as control parameters, process settings, equipment status, raw material information, etc. in each production process, which is an important basis for subsequent analysis and prediction. For example, the record set involves the control plan of a certain stamping production, which may include mold temperature setting value, stamping speed, stamping times, material thickness, etc.

[0049] After obtaining the control scheme record set, the next step is to retrieve the corresponding loss records based on the pre-defined stamping production loss factors (such as resource utilization, production efficiency, production quality, etc.). The purpose is to associate the control scheme with the specific loss situation and provide data support for the subsequent construction of the prediction model. For example, through retrieval, it is possible to obtain the downtime caused by equipment failure in a certain production (resource utilization loss) and the defective rate of the batch of products (quality loss).

[0050] Then, based on the control scheme record set and the resource utilization loss coefficient record set, a model that can predict future resource utilization loss is constructed by using statistical learning, machine learning or deep learning methods. The model will take into account the complex relationship between various parameters in the control scheme and resource utilization loss. For example, through regression analysis, it can be found that there is a certain correlation between mold temperature and equipment downtime, and then this correlation is used to predict the downtime that may occur under a given mold temperature. Similarly, using the control scheme record set and the production efficiency loss coefficient record set, a production efficiency loss prediction model is constructed. The model will focus on identifying the key factors affecting production efficiency and predicting the efficiency loss that may occur under a given control scheme. Based on the control scheme record set and the quality loss coefficient record set, a quality loss prediction model is constructed. The model will focus on analyzing how the control scheme affects product quality and predicting the defective rate or other quality losses that may occur under given conditions. Finally, the three prediction channels are connected in an appropriate way to form a comprehensive multi-feature loss prediction channel, which will be able to simultaneously predict and display the various loss situations that stamping production may face under different control schemes. For example, the outputs of the three prediction models can be integrated into a unified interface through ensemble learning or joint modeling technology to provide a comprehensive loss prediction report for subsequent decision-making, optimize production control plans, reduce losses, and improve overall production efficiency.

[0051] Furthermore, the punching loss prediction result is input into a punching loss verification module to generate a punching loss verification result. Step S400 of the present application further includes:

[0052] Step S410: the stamping loss verification module includes multi-dimensional stamping production loss constraints, and the multi-dimensional stamping production loss constraints include stamping production resource utilization loss constraints, stamping production efficiency loss constraints and stamping production quality loss constraints.

[0053] Step S420: inputting the stamping loss prediction result into the stamping loss verification module to determine whether the stamping loss prediction result satisfies the multi-dimensional stamping production loss constraint.

[0054] Step S430: If the stamping loss prediction result does not satisfy the multi-dimensional stamping production loss constraint, the stamping loss verification result obtained is failure.

[0055] Optionally, the stamping loss verification module is specially designed to evaluate whether the prediction results of stamping production losses meet the preset standards and expectations of the enterprise. These standards are embodied in the form of multidimensional loss constraints, including resource utilization loss constraints, production efficiency loss constraints and quality loss constraints. The multidimensional stamping production loss constraints refer to the restrictions or expected goals set for resource utilization, production efficiency and product quality in the production process, which are used to ensure the economy and effectiveness of production activities. Among them, the stamping production resource utilization loss constraint is a condition used to limit the losses caused by unreasonable resource utilization (such as equipment idleness, material waste, etc.) in the production process within a certain range; the stamping production efficiency loss constraint refers to the minimum standard that the production efficiency should reach, so as to reduce the efficiency decline caused by equipment failure, improper operation and other reasons; the stamping production quality loss constraint refers to setting product quality standards to limit quality losses such as defective rate and rework rate to below a certain level.

[0056] The predicted resource utilization loss, production efficiency loss and quality loss results of stamping production are imported as input data into the stamping loss verification module, and the predicted results are compared with the actual production constraints. Assuming that the predicted results show that the resource utilization loss rate of a stamping production is 5%, the production efficiency loss rate is 3%, and the quality loss rate is 2%, these data will be input into the verification module for subsequent processing. Inside the verification module, the input prediction results are compared with the multi-dimensional stamping production loss constraints through the preset algorithm logic. This step aims to determine whether the prediction results meet the production standards and expectations set by the enterprise. For example, resource utilization loss verification refers to checking whether the predicted resource utilization loss rate (5%) is lower than the preset resource utilization loss constraint value (such as 6%). Similarly, production efficiency loss verification and production quality loss verification are performed. Finally, the stamping loss verification conclusion is generated based on the comparison results. If the predicted results meet all multi-dimensional loss constraints, the verification result is passed; otherwise, if any of the predicted results exceeds the constraint range, the verification result is failed.

[0057] By verifying the stamping loss prediction and multi-dimensional production loss constraints, the economy, efficiency and quality of stamping production activities are ensured to meet the company's preset standards and expectations.

[0058] Furthermore, when the stamping loss verification result is not passed, the stamping loss optimization module is activated, and the stamping production control scheme is optimized in combination with the stamping product requirements to obtain the stamping production control optimization result. Step S500 of this application also includes:

[0059] Step S510: The stamping loss optimization module includes a stamping control record library and a stamping loss weight condition.

[0060] Step S520: Based on the stamping product requirements, the stamping production control solution is optimized and constrained in combination with the stamping control record library to generate stamping control optimization constraint conditions.

[0061] Step S530: Based on the stamping control optimization constraint condition, the stamping production control scheme is optimized in combination with the stamping loss verification module and the stamping production loss factor to obtain a stamping production control optimization space.

[0062] Step S540: Optimizing the stamping loss minimization in the stamping production control optimization space according to the stamping loss weight condition to generate the stamping production control optimization result.

[0063] Furthermore, once the stamping loss verification result is displayed as "failed", the stamping loss optimization module is activated. This module is pre-built and integrated into the production management system. It is specifically used to analyze and optimize various factors that lead to stamping losses. This module contains two core components: the stamping control record library and the stamping loss weight condition. The stamping control record library is a database that stores detailed records of control parameters, production conditions, result feedback, and loss conditions for all stamping production batches in history. These data are important references for the optimization process and help identify key factors affecting stamping losses. The stamping loss weight condition defines the importance of different stamping loss factors in the optimization process, that is, the weight. For example, factors such as mold wear, material quality, and stamping speed may have different effects on the loss. By setting weights, it can be ensured that the optimization process focuses more accurately on the main contradictions.

[0064] Next, based on the current stamping product requirements (such as product size, shape, precision requirements, etc.), combined with the historical data in the stamping control record library, the existing stamping production control scheme is deeply analyzed. Through analysis, we can identify which control parameters or production conditions need to be adjusted to meet product requirements, and generate corresponding stamping control optimization constraints, which will become the guiding principles for the subsequent optimization process. Furthermore, based on the optimization constraints, we further combine the real-time feedback of the stamping loss verification module and the comprehensive analysis of stamping production loss factors (such as equipment failure rate, material scrap rate, etc.), and make a preliminary optimization attempt on the stamping production control scheme. This process aims to explore a series of possible control parameter combinations, namely the stamping production control optimization space. Each point in this space represents a potential optimization scheme, and its goal is to reduce stamping losses.

[0065] Finally, using the stamping loss weight condition as a guide, the optimization is performed in the stamping production control optimization space. This step is similar to the process of finding the optimal solution in a complex mathematical space. Through continuous iteration and adjustment of control parameters, the production control scheme with the minimum loss is gradually approached. According to the weight condition, the system will prioritize the factors that have the greatest impact on the loss until the optimization result that satisfies all constraints and has the minimum loss is found. Suppose that in a stamping production, the product qualification rate decreases due to severe die wear, and the loss check fails. After activating the optimization module, the system first finds that the die wear is closely related to the stamping speed and lubrication conditions through the stamping control record library. Subsequently, optimization constraints are generated according to product requirements, such as reducing the stamping speed and increasing the lubrication frequency. In the optimization space, different parameter combinations are tried and the loss changes are monitored in real time through the stamping loss check module. Finally, according to the set loss weight condition, a stamping production control optimization scheme that can both ensure product quality and significantly reduce losses is found. The above steps reduce losses by fine-tuning the production control scheme, thereby improving production efficiency and product quality.

[0066] Furthermore, based on the stamping product requirements, the stamping production control scheme is optimized and constrained in combination with the stamping control record library to generate stamping control optimization constraint conditions. Step S520 of the present application also includes:

[0067] Step S521: the stamping control record library includes multiple groups of stamping control records, each group of stamping control records includes sample stamping product requirements and sample stamping production control solutions.

[0068] Step S522: Based on the stamping product requirements, feature association analysis is performed on the stamping control record library to obtain a feature sample stamping production control solution set that meets predetermined feature association constraints.

[0069] Step S523: performing multiple control feature triggering interval identification according to the feature sample stamping production control solution set to obtain multiple stamping control feature triggering intervals.

[0070] Step S524: performing difference analysis based on the multiple stamping control feature triggering intervals and the stamping production control scheme to obtain the stamping control optimization constraint conditions.

[0071] Specifically, the stamping control record library is a comprehensive database that stores multiple groups of control records of historical stamping production. Each group of records contains two core parts, namely, sample stamping product requirements and sample stamping production control schemes. The sample stamping product requirements describe the various specifications and standards that need to be achieved when producing this batch of products; and the sample stamping production control scheme records in detail the control parameters and process conditions used in the production process. Then, based on the current proposed stamping product requirements, the stamping control record library is subjected to feature association analysis. The purpose of this step is to find historical production records that are similar or related to the current product requirements. By comparing the various features of the product requirements (such as size, shape, material, precision, etc.), a set of feature sample stamping production control schemes that meet the predetermined feature association constraints can be screened out. These scheme sets provide valuable reference for subsequent optimization.

[0072] Next, the system conducts an in-depth analysis of the characteristic sample stamping production control scheme set and identifies the trigger intervals of multiple control features. This process involves a detailed examination of multiple key control features in the control scheme (such as stamping speed, pressure, temperature, lubrication conditions, etc.). Through statistical analysis and data mining technology, it is possible to identify the influence of these control features on product quality and production efficiency within different value ranges, and then determine multiple stamping control feature trigger intervals, which represent the reasonable ranges that control features should maintain under different production conditions.

[0073] Finally, difference analysis is performed based on multiple stamping control feature trigger intervals and the current stamping production control scheme. Difference analysis is a method of comparing the differences between two sets to find the gap between the current control scheme and the optimal control feature trigger interval. Through analysis, the parts of the current control scheme that need to be adjusted or optimized are identified, and stamping control optimization constraints are generated based on this. These constraints specify how the control features should be adjusted to meet product requirements and optimization goals.

[0074] For example, the current stamping product demand is to produce a batch of high-precision, low-deformation metal parts. Through feature association analysis, several groups of similar historical production records were found in the stamping control record library. Furthermore, multi-control feature trigger interval identification shows that when the stamping speed is controlled within a certain range and the temperature and lubrication conditions also meet certain conditions, the product's precision and deformation can be optimized. However, in the current stamping production control scheme, the stamping speed is set too high, resulting in a large amount of product deformation. Therefore, one of the generated stamping control optimization constraints is to adjust the stamping speed to the above-mentioned specific range, and adjust the temperature and lubrication conditions accordingly to ensure that the product quality meets the requirements.

[0075] Through the above steps, not only the production efficiency and product quality are improved, but also the production losses are reduced, and the production flexibility and continuous improvement capabilities are enhanced.

[0076] Furthermore, based on the stamping control optimization constraint condition, the stamping production control scheme is optimized in combination with the stamping loss verification module and the stamping production loss factor to obtain the stamping production control optimization space. Step S530 of this application also includes:

[0077] Step S531: randomly adjusting the stamping production control scheme according to the stamping control optimization constraint condition to obtain a first adjusted stamping production control scheme.

[0078] Step S532: performing loss prediction on the first adjusted stamping production control scheme according to the stamping production loss factor to obtain a stamping loss prediction result of the first adjustment scheme.

[0079] Step S533: inputting the stamping loss prediction result of the first adjustment scheme into the stamping loss verification module to generate the stamping loss verification result of the first adjustment scheme.

[0080] Step S534: When the stamping loss verification result of the first adjustment scheme is passed, the first adjustment stamping production control scheme is set as the first optimized stamping production control scheme, and the first optimized stamping production control scheme is added to the stamping production control optimization space.

[0081] Step S535: Continue to optimize the stamping production control scheme according to the stamping control optimization constraint conditions, the stamping loss verification module and the stamping production loss factor until the stamping production control optimization space that meets the optimization space construction constraint conditions is obtained.

[0082] The optimization space construction constraint condition is that the number of optimization schemes in the stamping production control optimization space satisfies a predetermined number of optimization schemes.

[0083] Exemplarily, according to the optimization constraints of stamping control, the parameters in the current stamping production control scheme, such as stamping speed, pressure, temperature, etc., are randomly adjusted to generate the first adjusted stamping production control scheme. This random adjustment ensures the extensiveness of exploration and helps to discover potential optimization space. Subsequently, the stamping production loss factor is used to predict the loss of the first adjusted stamping production control scheme, and the stamping loss prediction result under the scheme is calculated by a mathematical model, that is, the stamping loss prediction result of the first adjustment scheme. Then, the stamping loss prediction result of the first adjustment scheme is input into the stamping loss verification module, which verifies the prediction result based on historical data, expert experience and industry standards to judge its rationality and feasibility. The verification process may include steps such as data comparison, trend analysis, and risk assessment, and finally generates the stamping loss verification result of the first adjustment scheme. When the stamping loss verification result of the first adjustment scheme is passed, it indicates that the scheme performs well in loss control and has implementation value. At this time, the first adjusted stamping production control scheme is set as the first optimized stamping production control scheme and added to the stamping production control optimization space.

[0084] Furthermore, according to the stamping control optimization constraints, stamping loss verification module and stamping production loss factor, the stamping production control scheme is randomly adjusted, loss prediction and loss verification are repeated. Each cycle may generate new optimization schemes. After verification, the schemes that meet the conditions will be added to the stamping production control optimization space. This process continues until the optimization space construction constraints are met. This constraint is usually set as the number of optimization schemes in the stamping production control optimization space reaches the predetermined number of optimization schemes, which means that when the optimization space contains enough and high-quality optimization schemes, the construction process will terminate.

[0085] For example, suppose that during the optimization process, the system first randomly adjusts the stamping speed and finds that when the speed is reduced to a certain range, the predicted scrap rate and material loss rate both decrease. After verification by the stamping loss verification module, it is confirmed that the adjustment scheme is effective in reducing production losses. Therefore, this scheme was selected as the first optimized stamping production control scheme and added to the optimization space. Subsequently, other control parameters such as temperature and lubrication conditions are adjusted. Through multiple cycles of optimization, a stamping production control optimization space containing multiple optimization schemes is finally constructed. These schemes have performed well in reducing production losses, improving product quality and production efficiency, and provide valuable production guidance for subsequent processing.

[0086] Furthermore, based on the stamping production monitoring and control module, stamping control is performed according to the stamping production control optimization result. Step S600 of the present application also includes:

[0087] Step S610: Obtain stamping control monitoring data.

[0088] Step S620: performing an offset analysis according to the stamping production control optimization result and the stamping control monitoring data to obtain a stamping control offset analysis result.

[0089] Step S630: Based on the stamping production monitoring and control module, stamping offset compensation control is performed according to the stamping control offset analysis result.

[0090] Specifically, the stamping production monitoring and control module will continuously and in real time collect various key data in the stamping production process. These data constitute the stamping control monitoring data, including but not limited to the operating status of the stamping machine (such as speed, pressure), the working status of the mold (such as temperature, wear), the properties of the raw materials (such as thickness, hardness) and the parameters of the production environment (such as temperature, humidity), etc. The acquisition of these data is the basis for subsequent analysis and control, ensuring the comprehensiveness and accuracy of the information. Next, the stamping production control optimization results (that is, the best control parameter combination determined by the optimization process before) are compared and analyzed with the stamping control monitoring data obtained in real time. This process is called offset analysis, and its purpose is to identify the deviation between the current production state and the ideal optimization state. Offset analysis may involve complex algorithms and models, such as statistical methods, machine learning algorithms, etc., to accurately calculate the results of stamping control offset analysis. For example, if the optimization results show that the scrap rate should be kept at a low level at a specific stamping speed, but the monitoring data shows that the current scrap rate is high, then the system will identify that there is an offset in the speed control and calculate the specific offset.

[0091] Based on the results of the stamping control offset analysis, the stamping production monitoring and control module will automatically trigger the stamping offset compensation control mechanism, which aims to correct the offset by adjusting the control parameters in the stamping production process, so that the production status returns to the optimal state indicated by the optimization results. The specific operations of compensation control may include adjusting the speed and pressure settings of the stamping machine, optimizing the cooling or lubrication system of the mold, adjusting the supply method of raw materials, etc. These adjustments are based on the precise calculation of the offset analysis results to ensure the accuracy and effectiveness of the compensation. For example, if there is an offset in the speed control, the system may automatically reduce the speed of the stamping machine until the scrap rate drops to the level indicated by the optimization results. At the same time, the system will continue to monitor the production status and adjust the compensation strategy according to the new monitoring data to achieve dynamic optimization.

[0092] The stamping control process based on the stamping production monitoring and control module is a closed-loop, dynamically optimized system. It first obtains real-time production data through the monitoring module, then uses offset analysis technology to identify the deviation between the production status and the optimization result, and automatically triggers the compensation control mechanism based on these analysis results. This process is continuously iterated to ensure efficient, stable and continuous optimization of stamping production.

[0093] Through the technical solutions of the above-mentioned embodiments, the stamping production control method based on big data monitoring provided by the present application solves the technical problems of insufficient data utilization, slow response speed and insufficient optimization capability in stamping production existing in the prior art, and achieves the technical effect of improving stamping production efficiency, product quality and reducing production costs through big data monitoring and optimization control.

[0094] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0095] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application.

Claims

1. The stamping production control method based on big data monitoring is characterized by: The method comprises: According to the stamping production management module, a stamping production control instruction is obtained, wherein the stamping production control instruction includes a stamping product demand and a stamping production control plan; Setting a stamping production loss factor, wherein the stamping production loss factor includes stamping production resource utilization loss, stamping production efficiency loss and stamping production quality loss; Perform loss prediction on the stamping production control scheme according to the stamping production loss factor to obtain a stamping loss prediction result; Inputting the punching loss prediction result into a punching loss verification module to generate a punching loss verification result; When the stamping loss verification result is not passed, the stamping loss optimization module is activated, and the stamping production control scheme is optimized in combination with the stamping product requirements to obtain a stamping production control optimization result; Based on the stamping production monitoring and control module, stamping control is performed according to the stamping production control optimization result.

2. The stamping production control method based on big data monitoring according to claim 1, characterized in that: The stamping production control scheme is subjected to loss prediction according to the stamping production loss factor to obtain a stamping loss prediction result, including: Based on the stamping production loss factor, a stamping production multi-feature loss prediction channel is established, wherein the stamping production multi-feature loss prediction channel includes a stamping production resource utilization loss prediction channel, a stamping production efficiency loss prediction channel and a stamping production quality loss prediction channel; Based on the stamping production control scheme, and according to the stamping production resource utilization loss prediction channel, a predicted stamping production resource utilization loss coefficient is generated; Based on the stamping production control scheme, and according to the stamping production efficiency loss prediction channel, a predicted stamping production efficiency loss coefficient is obtained; Based on the stamping production control scheme, and according to the stamping production quality loss prediction channel, a predicted stamping production quality loss coefficient is obtained; The predicted stamping production resource utilization loss coefficient, the predicted stamping production efficiency loss coefficient and the predicted stamping production quality loss coefficient are added to the stamping loss prediction result.

3. The stamping production control method based on big data monitoring according to claim 2 is characterized in that: Based on the stamping production loss factor, a stamping production multi-feature loss prediction channel is built, including: Load stamping production control scheme record set; Based on the stamping production loss factor, loss record retrieval is performed according to the stamping production control scheme record set to obtain a stamping production resource utilization loss coefficient record set, a stamping production efficiency loss coefficient record set and a stamping production quality loss coefficient record set; Constructing the stamping production resource utilization loss prediction channel according to the stamping production control scheme record set and the stamping production resource utilization loss coefficient record set; Constructing the stamping production efficiency loss prediction channel according to the stamping production control scheme record set and the stamping production efficiency loss coefficient record set; Constructing the stamping production quality loss prediction channel according to the stamping production control scheme record set and the stamping production quality loss coefficient record set; The stamping production resource utilization loss prediction channel, the stamping production efficiency loss prediction channel and the stamping production quality loss prediction channel are connected to generate the stamping production multi-feature loss prediction channel.

4. The stamping production control method based on big data monitoring according to claim 1, characterized in that: The punching loss prediction result is input into the punching loss verification module to generate a punching loss verification result, including: The stamping loss verification module includes multi-dimensional stamping production loss constraints, and the multi-dimensional stamping production loss constraints include stamping production resource utilization loss constraints, stamping production efficiency loss constraints and stamping production quality loss constraints; Inputting the stamping loss prediction result into the stamping loss verification module to determine whether the stamping loss prediction result meets the multi-dimensional stamping production loss constraint; If the stamping loss prediction result does not satisfy the multi-dimensional stamping production loss constraint, the stamping loss verification result obtained is failure.

5. The stamping production control method based on big data monitoring according to claim 1, characterized in that: When the stamping loss verification result is not passed, the stamping loss optimization module is activated, and the stamping production control scheme is optimized in combination with the stamping product requirements to obtain the stamping production control optimization result, including: The punching loss optimization module includes a punching control record library and a punching loss weight condition; Based on the stamping product requirements, the stamping production control scheme is optimized and constrained in combination with the stamping control record library to generate stamping control optimization constraint conditions; Based on the stamping control optimization constraint condition, the stamping production control scheme is optimized in combination with the stamping loss verification module and the stamping production loss factor to obtain the stamping production control optimization space; The stamping loss minimization is performed on the stamping production control optimization space according to the stamping loss weight condition to generate the stamping production control optimization result.

6. The stamping production control method based on big data monitoring according to claim 5 is characterized in that: Based on the stamping product requirements, the stamping production control scheme is optimized and constrained in combination with the stamping control record library to generate stamping control optimization constraint conditions, including: The stamping control record library includes multiple groups of stamping control records, each group of stamping control records includes sample stamping product requirements and sample stamping production control plans; Based on the stamping product requirements, feature association analysis is performed on the stamping control record library to obtain a feature sample stamping production control solution set that meets predetermined feature association constraints; Performing multiple control feature trigger interval identification according to the feature sample stamping production control solution set to obtain multiple stamping control feature trigger intervals; The stamping control optimization constraint condition is obtained by performing difference analysis based on the multiple stamping control feature triggering intervals and the stamping production control scheme.

7. The stamping production control method based on big data monitoring according to claim 5 is characterized in that: Based on the stamping control optimization constraint condition, the stamping production control scheme is optimized in combination with the stamping loss verification module and the stamping production loss factor to obtain the stamping production control optimization space, including: Randomly adjust the stamping production control scheme according to the stamping control optimization constraint condition to obtain a first adjusted stamping production control scheme; Perform loss prediction on the first adjusted stamping production control scheme according to the stamping production loss factor to obtain a stamping loss prediction result of the first adjustment scheme; Inputting the prediction result of the stamping loss of the first adjustment scheme into the stamping loss verification module to generate a stamping loss verification result of the first adjustment scheme; When the stamping loss verification result of the first adjustment scheme is passed, the first adjustment stamping production control scheme is set as the first optimized stamping production control scheme, and the first optimized stamping production control scheme is added to the stamping production control optimization space; Continue to optimize the stamping production control scheme according to the stamping control optimization constraint condition, the stamping loss verification module and the stamping production loss factor until the stamping production control optimization space that satisfies the optimization space construction constraint condition is obtained; The optimization space construction constraint condition is that the number of optimization schemes in the stamping production control optimization space satisfies a predetermined number of optimization schemes.

8. The stamping production control method based on big data monitoring according to claim 1, characterized in that: Based on the stamping production monitoring and control module, stamping control is performed according to the stamping production control optimization result, including: Obtain stamping control monitoring data; Performing a deviation analysis according to the stamping production control optimization result and the stamping control monitoring data to obtain a stamping control deviation analysis result; Based on the stamping production monitoring and control module, stamping offset compensation control is performed according to the stamping control offset analysis result.

Images