Ceramic card production data state control method and system

Abstract

The invention provides a ceramic card production data state control method and system. The method comprises the following steps: obtaining production data in a ceramic card production process; by adopting the data acquisition module with a distributed architecture, sensor self-diagnosis and self-adaptive adjustment functions and dynamic self-adaptive time interval data acquisition, and combining with the preprocessing and standard storage mode of the data processing and storage module, the problems of inaccurate production data recording and transmission delay errors are solved; the data state updating module monitors in real time, updates the state based on a machine learning model, and realizes data state real-time tracking and anomaly discovery by matching with a visual platform of the data state monitoring and early warning module, dynamic threshold early warning and multi-mode early warning; a multi-dimensional analysis result is generated through a data analysis module by applying a professional tool and an algorithm, and an intelligent decision-making module constructs an intelligent decision-making model and provides an effective data state control mechanism, so that reasonable production scheduling and decision-making are performed according to a production data state.

Description

Technical Field

[0001] The present invention relates to the technical field of ceramic card production, and particularly to a method and system for controlling the production data status of ceramic cards. Background Art

[0002] Due to its unique material properties, ceramic cards excel in terms of aesthetics and durability, and thus have been widely used in many fields. In terms of appearance, ceramic cards have a delicate and warm texture, with a soft and uniform surface gloss, and can present rich and vivid colors. Whether it is a simple solid color design or a delicate and complex pattern printing, they can all show high-quality visual effects. In terms of durability, ceramic materials have excellent hardness and wear resistance, making ceramic cards not easily scratched or worn, and can withstand frequent daily use and a certain degree of external force impact; at the same time, it also has good chemical stability, can resist the erosion of chemical substances such as acids and alkalis, and effectively extends the service life of the cards. Given these significant advantages, ceramic cards are widely used in many fields such as financial payment, identity recognition, access control systems, and transportation. The production process of ceramic cards involves many complex links and a large amount of data interaction, but there are still certain problems: First, the recording of production data is inaccurate, and there are delays and errors in data transmission between different production links; Second, the status of production data cannot be updated and tracked in real time, and abnormal situations in the production process cannot be detected in a timely manner; Third, there is a lack of an effective data status control mechanism, and it is difficult to carry out reasonable production scheduling and decision-making based on the status of production data; Therefore, a method and system for controlling the production data status of ceramic cards are proposed. Summary of the Invention

[0003] In view of this, embodiments of the present invention hope to provide a method and system for controlling the production data status of ceramic cards to solve or alleviate the technical problems existing in the prior art, and at least provide a beneficial option.

[0004] To solve the above technical problems, a technical solution adopted in this application is: a method for controlling the production data status of ceramic cards, including the following steps: Step 1. Obtain the production data in the ceramic card production process; Step 2. Preprocess the obtained production data, store it in a preset format, and at the same time, set an initial status for the production data of each ceramic card production batch; Step 3. During the ceramic card production process, monitor the changes in production data in real time, update the data status of the corresponding production batch according to the pre-established status update rules, and at the same time transmit the updated data status to the production management center; Step 4: Build a data status monitoring platform in the production management center to display the data status of all ceramic card production batches in real time, and set thresholds and warning rules for the data status to monitor and warn about the data status; Step 5: Use data analysis tools and algorithms to analyze historical production data and the current real-time data status, and generate analysis results; Step 6: Based on the analysis results, by constructing an intelligent decision-making model, provide a scientific basis and decision-making support for production scheduling, process optimization, and quality control; Step 7: Build a data status traceability system to record the historical changes in the data status of each ceramic card production batch, and through the mining and analysis of the historical changes in the data status, continuously optimize the production process.

[0005] Preferably, as a further aspect of this technical solution, in Step 4, the data status monitoring platform adopts a Web-based visual interface to display the data status in the form of charts and tables in real time; the thresholds and warning rules for the data status are dynamically generated by combining fuzzy logic reasoning and real-time data analysis, and are adjusted according to the statistical analysis results of historical production data, industry standards, and real-time production environment changes. When the data status approaches or exceeds the threshold, a warning is issued through a multimodal warning method, and the multimodal warning method includes audible and visual alarms, SMS notifications, system pop-up prompts, and vibration reminders on smart wearable devices.

[0006] Preferably, as a further aspect of this technical solution, in Step 5, the data analysis tools include the Pandas and Numpy libraries in Python, as well as professional data analysis software SAS and SPSS; the algorithms include an association analysis algorithm based on deep learning and a trend prediction algorithm based on reinforcement learning; the analysis results include production efficiency trend analysis, quality fluctuation cause analysis, and equipment failure warning probability analysis.

[0007] Preferably, as a further aspect of this technical solution, in Step 2, the preprocessing includes cleaning the production data and filling in missing values; the preset format conforms to the format of a relational database table structure, and the data of each production batch is associated and stored with a unique identifier; the initial states include to be produced, in production, in quality inspection, completed, and discarded.

[0008] Preferably, as a further aspect of this technical solution, in Step 1, the production data is collected at a dynamically adaptive time interval through sensors and equipment interfaces distributed on production equipment, and the dynamically adaptive time interval is adjusted in real time according to the operating state and production stage of the production equipment; the production data includes raw material information, process parameters, and equipment operating status.

[0009] As a further preference of this technical solution, in step three, the change of the real-time monitored production data is realized by collecting data at a dynamically adaptive time interval through a real-time data acquisition module installed on the production equipment; the status update rule is adjusted in real time based on a machine learning model, and the machine learning model uses historical production data, real-time production data, and quality feedback data as the training set and is trained according to production process standards and quality requirements. The machine learning model is trained using a convolutional neural network or a recurrent neural network; the updated data status is transmitted to the production management center through an industrial Ethernet or a wireless communication protocol.

[0010] As a further preference of this technical solution, in step seven, the data status traceability system is implemented using blockchain technology; the history of data status changes includes the time of data status change, the operator, equipment information, production process parameters, and the execution records of smart contracts based on blockchain. The execution records of smart contracts based on blockchain include the execution status of raw material procurement contracts, the execution status of production task assignments, and the verification status of quality inspection results.

[0011] To solve the above technical problems, another technical solution adopted by this application is: a ceramic card production data status control system, which includes: a data acquisition module, a data processing and storage module, a data status update module, a data status monitoring and warning module, a data analysis module, an intelligent decision-making module, and a data traceability module; The data acquisition module is configured to obtain production data during the production process of ceramic cards; The data processing and storage module is configured to preprocess the obtained production data, store it in a preset format, and at the same time, set an initial status for the production data of each ceramic card production batch; The data status update module is configured to, during the production process of ceramic cards, monitor the change of production data in real time, update the data status of the corresponding production batch according to the pre-established status update rule, and at the same time transmit the updated data status to the production management center; The data status monitoring and warning module is configured to build a data status monitoring platform in the production management center, display the data status of all ceramic card production batches in real time, and set thresholds and warning rules for the data status to monitor and warn the data status; The data analysis module is configured to analyze historical production data and the current real-time data status using data analysis tools and algorithms, and generate analysis results; The intelligent decision-making module is configured to, based on the analysis results, provide a scientific basis and decision support for production scheduling, process optimization, and quality control by constructing an intelligent decision-making model; The data traceability module is configured to build a data status traceability system, record the historical changes of the data status of each production batch of ceramic cards, and continuously optimize the production process through the mining and analysis of the historical changes of the data status.

[0012] Preferably, as a further aspect of the present technical solution, the data acquisition module adopts a distributed architecture, and the sensors distributed on the production equipment and the equipment interfaces work independently and cooperatively, and the sensors have self-diagnosis and adaptive adjustment functions.

[0013] Preferably, as a further aspect of the present technical solution, the data traceability module uses the timestamp technology of the blockchain to accurately record the time of data status changes, and realizes the access right management of the historical changes of the data status through smart contracts.

[0014] Due to the above technical solutions adopted in the embodiments of the present invention, the following advantages are achieved: 1. By adopting a data acquisition module with a distributed architecture, the self-diagnosis and adaptive adjustment functions of the sensors, and collecting data at a dynamically adaptive time interval, and combining the preprocessing and standardized storage methods of the data processing and storage module, the present invention solves the problems of inaccurate production data recording and transmission delay errors. 2. By the data status update module, the data changes are monitored in real time and the status is updated based on the machine learning model. With the visualization platform, dynamic threshold warning rules and multi-modal warning methods of the data status monitoring and warning module, the real-time update and tracking of the production data status are realized, and abnormal situations can be detected in time. 3. By the data analysis module using professional tools and advanced algorithms to generate multi-dimensional analysis results, and the intelligent decision-making module constructing an intelligent decision-making model that synthesizes multiple objectives and dynamically adjusts weights, an effective data status control mechanism is provided, so as to perform reasonable production scheduling and decision-making according to the production data status.

[0015] The above summary is only for the purpose of the specification and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments and features described above, further aspects, embodiments and features of the present invention will be readily apparent by reference to the drawings and the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present application, and those of ordinary skill in the art can obtain other drawings without creative efforts.

[0017] Figure 1Schematic flowchart of a method for controlling the production data status of a ceramic card according to the present invention; Figure 2 Schematic diagram of the functional modules of a system for controlling the production data status of a ceramic card according to the present invention. Detailed implementation manners

[0018] The following describes the embodiments of the present disclosure in detail with reference to the accompanying drawings.

[0019] It should be clear that the following illustrates the implementation manners of the present disclosure through specific specific examples. Those skilled in the art can easily understand other advantages and effects of the present disclosure from the content disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all the embodiments. The present disclosure can also be implemented or applied through other different specific implementation manners. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present disclosure. It should be noted that, without conflict, the following embodiments and the features in the embodiments can be combined with each other. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present disclosure without making creative efforts belong to the scope of protection of the present disclosure.

[0020] It should also be noted that the following describes various aspects of the embodiments within the scope of the appended claims. It should be obvious that the aspects described herein can be embodied in a wide variety of forms, and any specific structure and / or function described herein is illustrative only. Based on the present disclosure, those skilled in the art should understand that one aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number of aspects described herein can be used to implement the device and / or practice the method. In addition, this device and / or this method can be implemented using other structures and / or functions in addition to one or more of the aspects described herein.

[0021] It also needs to be noted that the drawings provided in the following embodiments only illustrate the basic concept of the present disclosure schematically. The drawings only show the components related to the present disclosure, rather than being drawn according to the number, shape and size of the components in actual implementation. The type, quantity and proportion of each component in its actual implementation can be an arbitrary change, and the component layout type may also be more complex.

[0022] In addition, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, those skilled in the art will understand that the described aspects can be practiced without these specific details.

[0023] Figure 1It is a schematic flow diagram of a method for controlling the production data status of a ceramic card according to an embodiment of the present invention. It should be noted that if there are substantially the same results, the method of the present application is not limited to Figure 1 the flow order shown. For example Figure 1 as shown: A method for controlling the production data status of a ceramic card includes the following steps: Step 1, obtain production data during the ceramic card production process; Specifically, in the actual ceramic card production scenario, various sensors are installed on the production equipment, such as temperature sensors, pressure sensors, flow sensors, etc. These sensors are connected to the data acquisition module through device interfaces; the data acquisition module adopts a distributed architecture, and the sensors have self-diagnosis and adaptive adjustment functions; for example, the temperature sensor on the kiln equipment will monitor its own working status in real time. When environmental interference affects the measurement accuracy, the sensor automatically adjusts its internal parameters to ensure accurate measurement; if a fault occurs, it will issue a warning in a timely manner; Among them, the acquisition time interval of the production data is not fixed, but is adjusted in real time according to the operating status of the production equipment and the production stage; in the critical stage of green body forming, in order to accurately capture data changes, the acquisition interval is shortened to once per second; in the stable operation stage of the equipment, the acquisition interval can be adjusted to once every 5 seconds; the acquired data covers raw material information (such as the type, batch, supplier, etc. of raw materials), process parameters (such as green body forming pressure, kiln firing temperature, firing time, etc.), and equipment operating status (such as equipment startup time, cumulative operating duration, number of faults, etc.).

[0024] Step 2, preprocess the acquired production data, store it in a preset format, and at the same time, set an initial status for the production data of each ceramic card production batch; Specifically, after obtaining the data from the data acquisition module, the data processing and storage module starts to work. During preprocessing, first perform cleaning processing on the production data, and remove abnormal data by setting reasonable data range thresholds; for example, if the green body forming pressure data exceeds the normal range, it will be regarded as an abnormal value for processing; for missing values, interpolation methods or machine learning-based methods are used for filling; The processed data is stored in a format that conforms to the structure of a relational database table. The data of each production batch is associated and stored with a unique identifier (such as a production batch number); in the database, different types of data are stored in corresponding tables respectively, and associations are established through the batch number; at the same time, according to the production plan and actual situation, set an initial status for the data of each production batch, including to be produced, in production, in quality inspection, completed, and discarded; for example, batches whose production plans have not been started are set to the to be produced status; batches that are in the production operation are in the in production status.

[0025] Step 3: During the production process of ceramic cards, monitor the changes in production data in real time, update the data status of the corresponding production batches according to the pre-established status update rules, and transmit the updated data status to the production management center; Specifically, install a real-time data acquisition module on each production device to collect data at a dynamically adaptive time interval to achieve real-time monitoring of production data; the status update rules are dynamically adjusted based on a machine learning model, which uses historical production data, real-time production data, and quality feedback data as the training set and is trained according to production process standards and quality requirements, using a convolutional neural network or a recurrent neural network; Taking the kiln firing process as an example, when parameters such as kiln temperature and atmosphere change, the machine learning model judges the production status according to the training results; if the temperature exceeds the normal range and lasts for a certain period of time, the model determines that the production is abnormal and updates the data status of the corresponding batch from "in production" to "abnormal"; the updated data status is transmitted to the production management center through industrial Ethernet or a wireless communication protocol to ensure timely data transfer.

[0026] Step 4: Build a data status monitoring platform in the production management center to display the data status of all ceramic card production batches in real time, and set thresholds and warning rules for the data status to monitor and warn about the data status; Specifically, in the production management center, build a Web-based visual data status monitoring platform; this platform displays the data status of all ceramic card production batches in real time in the form of charts (such as line charts showing temperature change trends and bar charts comparing the production efficiency of different batches) and tables (detailed listing of production data for each batch), and managers can access the platform through a computer or mobile device to keep track of the production situation at any time; Among them, the thresholds and warning rules for the data status are dynamically generated by combining fuzzy logic reasoning and real-time data analysis; and the thresholds are adjusted according to the statistical analysis results of historical production data, industry standards, and changes in the real-time production environment; for example, the kiln temperature threshold will change dynamically according to factors such as the historical best production temperature range and the current operating conditions of the equipment; when the data status approaches or exceeds the threshold, warnings are issued through multi-modal warning methods such as audible and visual alarms, SMS notifications, system pop-up prompts, and vibration reminders of smart wearable devices to ensure that relevant personnel are informed of abnormal situations in a timely manner.

[0027] Step 5: Use data analysis tools and algorithms to analyze historical production data and the current real-time data status and generate analysis results; Specifically, the data analysis module uses the Pandas and Numpy libraries in Python, as well as professional data analysis software SAS and SPSS, to conduct data analysis. It employs an association analysis algorithm based on deep learning to mine the potential associations between production data, such as analyzing the relationship between raw material quality and product quality. It also uses a trend prediction algorithm based on reinforcement learning to predict production efficiency trends, the causes of quality fluctuations, and the probability of equipment failure warnings. For example, through analysis, it is found that there is an association between the specific component content of a certain raw material and the hardness of ceramic cards. The probability of a certain piece of equipment malfunctioning within the next week is predicted, providing a basis for equipment maintenance. The analysis results are presented in an intuitive form to help production managers understand the production situation and make scientific decisions.

[0028] Step 6: Based on the analysis results, by constructing an intelligent decision-making model, provide scientific basis and decision support for production scheduling, process optimization, and quality control. Specifically, first, clarify the decision-making objectives for production scheduling, process optimization, and quality control, as follows: Production scheduling: The goal is to reasonably allocate resources such as manpower, equipment, and raw materials to improve production efficiency, shorten the production cycle, and reduce costs. For example, ensure that production tasks are completed within the order delivery period while avoiding equipment idleness and excessive fatigue of personnel. Process optimization: Aims to improve product quality, reduce production costs, and increase production efficiency. For example, by adjusting process parameters, reduce the defective rate and improve the utilization rate of raw materials. Quality control: The goal is to ensure that products meet quality standards and reduce the production of defective and waste products. For example, promptly detect quality problems in the production process and take measures to correct them. Then, conduct data integration and feature extraction as follows: Integrate the analysis results obtained in Step 5, including data such as production efficiency trend analysis, quality fluctuation cause analysis, and equipment failure warning probability analysis, with other relevant data (such as order information, inventory data, equipment maintenance records, etc.). Extract features related to the decision-making objectives from the integrated data. For example, for production scheduling decisions, extract features such as order priority, equipment available time, and personnel skill level. For process optimization decisions, extract features such as process parameters and product quality indicators. Next, construct an intelligent decision-making model, including a rule-based decision-making model, a machine learning-based decision-making model, and a machine learning-based decision-making model. The specific construction process of the rule-based decision-making model is as follows: Based on production experience and domain knowledge, a series of decision rules are formulated; for example, if the equipment failure warning probability exceeds 80%, arrange equipment maintenance; if the product quality fluctuation is caused by an abnormal process parameter, adjust the process parameter; Input the integrated data into the rule engine, make decisions according to the rules, and the rule engine will automatically match the data with the rules and output the corresponding decision results; The specific construction process of the decision-making model based on machine learning is as follows: According to the characteristics of the decision-making problem and the data type, select an appropriate machine learning algorithm; for example, for classification problems (such as judging whether a product is qualified), algorithms such as decision trees and support vector machines can be selected; for regression problems (such as predicting production efficiency), algorithms such as linear regression and neural networks can be selected; Use historical data to train the machine learning model and adjust the model parameters to enable the model to make accurate decisions; Use test data to evaluate the trained model, and the evaluation metrics include accuracy, recall rate, mean square error, etc.; if the model performance does not meet the requirements, the model parameters need to be adjusted or other algorithms need to be selected; The specific construction process of the decision-making model based on optimization algorithms is as follows: According to the decision-making goal, define an objective function; for example, for production scheduling problems, the objective function can be defined as minimizing the production cycle or maximizing production efficiency; for process optimization problems, the objective function can be defined as minimizing production costs or maximizing product quality; According to the actual production situation, determine a series of constraint conditions; for example, the production capacity of equipment, the working hours of personnel, the inventory of raw materials, etc.; Use optimization algorithms (such as linear programming, genetic algorithms, etc.) to solve the optimal solution of the objective function under the constraint conditions to obtain the decision result; Finally, conduct decision support and result verification, as follows: Present the decision result to the decision maker in a visual way, such as using charts, reports, etc.; for example, show the Gantt chart of the production scheduling plan, the comparison chart of the process parameter before and after adjustment of the process optimization plan, etc.; and explain the decision result to let the decision maker understand the basis and process of the decision; for example, explain why a certain production scheduling plan or process optimization plan is selected; In actual production, first conduct simulation verification on the decision result to observe the effect of the decision result in the simulation environment; for example, use production simulation software to simulate the production scheduling plan and evaluate the feasibility and effectiveness of the plan; Apply the decision result to actual production and observe the actual production effect; if the actual production effect does not match the expectation, the decision-making model needs to be adjusted and optimized.

[0029] Step 7: Build a data status traceability system to record the historical changes in the data status of each ceramic card production batch. Through the mining and analysis of the historical changes in the data status, continuous optimization of the production process is carried out; Specifically, in an actual ceramic card production enterprise, introduce the distributed ledger technology of blockchain to create an independent blockchain sub-chain for each ceramic card production batch to ensure the independence and security of data. For example, in the enterprise's production network, deploy a consortium chain, and each department participating in the production process (such as procurement, production, quality inspection, etc.) acts as a node to jointly maintain the blockchain; When the status of a production batch changes, such as from "in production" to "in quality inspection", the system automatically records the change time, accurate to the second level; at the same time, record the information of the personnel operating the batch, which can be associated with specific personnel through the employee's work number or identity authentication system; equipment information includes equipment number, model, operating status, etc.; production process parameters such as pressure and temperature during green body forming, temperature curve and time of kiln firing, etc.; in terms of the execution of raw material procurement contracts, record contract number, supplier information, raw material arrival time, quality inspection results, etc. For example, when raw materials arrive, the smart contract automatically records the arrival time and calls the quality inspection system to record the inspection results. In the execution of production task allocation, record the task allocation time, allocated equipment, operating personnel, and actual production time; the verification situation of quality inspection results records information such as inspection time, inspection personnel, and inspection result judgment; Then, use the query function of blockchain to extract the historical data of the data status changes of a specific batch according to the production batch number or other relevant indexes, and organize these data into a structured format for subsequent analysis. For example, extract all the data of a certain batch from raw material procurement to finished product completion and arrange them in chronological order; Next, use data analysis tools (such as pandas and numpy libraries in Python, as well as professional data analysis software SAS, SPSS, etc.) to establish a data analysis model. For example, use the clustering analysis algorithm to cluster the production data of different batches to find similar patterns in the production process; use the association rule mining algorithm to analyze the association relationship between raw material quality, process parameters and product quality; Through the analysis of the data, potential problems in the production process are found. For example, by comparing the production data of different batches, it is found that the defective rate of ceramic cards produced by a certain piece of equipment is relatively high during a specific period. Further analysis reveals that the equipment was not maintained in a timely manner during this period, resulting in wear of key components and affecting product quality; Adjust the production strategy according to the analysis results; if it is found that the quality of a certain raw material is unstable and affects the product quality, consider replacing the raw material supplier or strengthening the raw material inspection link; for example, for the raw materials used in batches with a high defective rate, increase the inspection frequency or replace the supplier with more reliable quality. Optimize the production process parameters based on the analysis of the relationship between process parameters and product quality; for example, after data analysis, it is found that when the firing temperature of the kiln is within a certain range, the qualified rate of the product is relatively high, and this temperature range can be used as the optimized process parameter and applied to subsequent production. Formulate a more reasonable equipment maintenance plan for equipment failures or performance degradation; for example, for equipment that often has problems, increase the maintenance frequency, regularly check and replace key components to ensure the stable operation of the equipment. Conduct targeted training for relevant operators based on the correlation analysis between operators and product quality; for example, if it is found that a certain operator's operation is not standardized in a specific process and causes product quality problems, provide skill training for this operator to improve their operation level. After implementing the optimization measures, continuously collect and analyze production data, and re-evaluate each link of the production process; for example, after optimizing the process parameters, observe whether the product quality has been improved and whether the production efficiency has increased. Feed back the optimized effect to the data status traceability system to further improve the data analysis model and optimization strategy; if new problems or potential optimization points are found, conduct data mining and analysis again, continuously improve the production process, and form a virtuous cycle to continuously improve the production quality and efficiency of ceramic cards.

[0030] In one embodiment, specifically, in step four, the data status monitoring platform adopts a Web-based visual interface to display the data status in real time in the form of charts and tables. Specifically, in the production management center, use Web development technology to build a data status monitoring platform. The front end uses HTML, CSS, and JavaScript frameworks (such as Vue.js or React.js) to build an interactive interface, and the back end uses Python's Flask or Django framework to provide data interfaces; the platform displays the data status in intuitive charts and tables; for example, use a line chart to show the change trend of the kiln temperature over time, with the abscissa being time and the ordinate being the temperature value; use a bar chart to compare the production efficiency of different production batches, and the height of the bars represents the production efficiency values of each batch; the table details the key data of each production batch, such as raw material information, process parameters, current production status, etc.

[0031] The thresholds and warning rules for data status are dynamically generated by combining fuzzy logic inference and real-time data analysis, and are adjusted according to the statistical analysis results of historical production data, industry standards, and changes in the real-time production environment. When the data status approaches or exceeds the threshold, a warning is issued through multi-modal warning methods, including audible and visual alarms, SMS notifications, system pop-up prompts, and vibration reminders on smart wearable devices; Specifically, first, collect historical production data, including process parameters, equipment operation status, product quality data, etc. of each production batch, and store them in a relational database (such as MySQL or Oracle). Use the Pandas library in Python to clean and preprocess the data to remove outliers and missing values; Then, establish a fuzzy logic model with the statistical analysis results of historical production data, industry standards, and changes in the real-time production environment as inputs; for example, for the threshold of furnace temperature, take the historical best temperature range and the safe temperature range specified by the industry as the boundaries of the fuzzy set; according to the real-time production environment (such as the degree of equipment aging and the temperature requirements of product types), use a fuzzy inference algorithm (such as the Mamdani algorithm) to dynamically adjust the threshold; Finally, collect production data in real time, and transmit the data to the monitoring platform through sensors and device interfaces; use real-time data analysis tools (such as Apache Flink) to process the data in real time and extract key features; combine the real-time data with historical data to analyze the change trends and patterns of the data, providing a basis for the dynamic adjustment of thresholds and warning rules; Among them, the implementation methods of multi-modal warning methods are as follows: Audible and visual alarms: Install audible and visual alarms in the production management center and connect them to the monitoring platform. When the data status approaches or exceeds the threshold, the platform sends an instruction to trigger the audible and visual alarms, emitting a loud alarm sound and flashing lights to attract the attention of on-site personnel; SMS notifications: Configure an SMS gateway and enter the mobile phone numbers of relevant personnel into the system. When a warning is triggered, the platform sends an SMS containing warning information (such as warning batch, abnormal data, reasons) to relevant personnel through the SMS gateway; for example, when the firing temperature of a certain batch of ceramic cards exceeds the threshold, the system sends SMS notifications to the furnace operator and production supervisor; System pop-up prompts: On the operation interface of the monitoring platform, when the data is abnormal, a system pop-up window will automatically appear, showing detailed warning information in the pop-up window, including production batch, specific values of abnormal data, normal range, impacts, etc. Operators can view the information in the pop-up window and perform corresponding processing operations; Vibration reminder of smart wearable devices: Bluetooth connection with smart wearable devices (such as smart bracelets) or data interaction through specific mobile applications; when an early warning occurs, the monitoring platform sends a reminder message to the smart wearable device, and the device reminds relevant personnel through vibration; for example, inspection personnel wear smart bracelets and can receive early warning information in a timely manner even when they are far away from production equipment.

[0032] In one embodiment, specifically, in step five, the data analysis tools include Pandas and Numpy libraries in Python, as well as professional data analysis software SAS and SPSS; Among them, the specific usage method of the data analysis tool is as follows: First, use the Pandas library to clean, transform, and preprocess the data. For example, remove duplicate data, error data, and incomplete data records through data cleaning; use the pivot table function of Pandas to summarize and analyze production data, and quickly obtain key data statistics for different production batches and different time periods; use the Numpy library for efficient numerical calculations, such as calculating statistics such as the mean and standard deviation of production data, providing basic data for subsequent analysis; Then, import the sorted data into SAS and SPSS software; in SAS, use its powerful statistical analysis function to perform complex statistical tests, such as analysis of variance, correlation analysis, etc., to deeply explore the relationships between production data; SPSS, with its convenient operation interface and rich analysis methods, performs classification analysis, regression analysis, etc. on the data to help analysts understand the characteristics and laws of production data from different perspectives.

[0033] The algorithms include an association analysis algorithm based on deep learning and a trend prediction algorithm based on reinforcement learning; Association analysis algorithm based on deep learning: Build a deep learning model with historical production data and current real-time data as inputs; the model can adopt a neural network architecture, such as a multi-layer perceptron (MLP) or a convolutional neural network (CNN); for ceramic card production data, use raw material information, process parameters, equipment operating status, etc. as input features, and learn the complex association relationships between these features through model training; for example, analyze the association between the specific component content of a certain raw material and the final hardness, wear resistance and other quality indicators of the ceramic card; study the impact of different process parameter combinations on production efficiency; during the training process, continuously adjust the model parameters to enable the model to accurately capture the internal connections between the data, thereby providing a basis for production decisions; Reinforcement Learning-based Trend Prediction Algorithm: Consider the ceramic card production process as a dynamic environment, take production data as the state, and operations such as adjusting production parameters and equipment maintenance strategies as actions; use the reinforcement learning algorithm to let the intelligent agent continuously try different actions in this environment and learn the optimal strategy according to the reward signal feedback from the environment; for example, predict the probability of equipment failure in the future period based on the current operating state and production data of the equipment, and through continuous learning and optimization, enable the intelligent agent to more accurately predict equipment failures, arrange maintenance in advance, and reduce the risk of production interruption; at the same time, predict the change trend of production efficiency and provide a reference for production scheduling, such as reasonably arranging production tasks according to the prediction results to improve the overall production efficiency.

[0034] The analysis results include the analysis of production efficiency trends, the analysis of the reasons for quality fluctuations, and the analysis of the probability of equipment failure early warning. Analysis of production efficiency trends: Combine the statistical results of the reinforcement learning-based trend prediction algorithm and data analysis tools to draw a curve of the change of production efficiency over time, analyze the trend of the curve, and judge whether the production efficiency is on the rise, decline or stable; for example, through the analysis of production data in the past month, it is found that the production efficiency of a certain production line shows a downward trend during a specific period of each week, and further analysis reveals that it is due to the excessive load of the equipment during this period; based on this, the enterprise can adjust the production plan, reasonably allocate the equipment load, and improve the overall production efficiency. Analysis of the reasons for quality fluctuations: Use the correlation analysis algorithm based on deep learning to find out the key factors affecting the quality fluctuations of ceramic cards; for example, through analysis, it is found that the defective rate of a certain batch of ceramic cards is relatively high, and through correlation analysis, it is found that it is jointly caused by the large fluctuations in a certain quality index of the raw materials and the instability of a certain process parameter during the firing process; in response to these reasons, the enterprise can strengthen the management of raw material suppliers and optimize the firing process parameters, thereby reducing the defective rate and improving product quality. Analysis of the probability of equipment failure early warning: According to the learning and analysis of the equipment operation data by the reinforcement learning model, calculate the probability of the equipment failing at different future time points; set a reasonable early warning threshold, and when the predicted failure probability exceeds the threshold, send an early warning signal in a timely manner; for example, predict that the probability of a certain key equipment failing within the next week is 30%, which exceeds the set early warning threshold of 20%, and the system immediately issues an early warning to remind the enterprise to prepare the spare parts and technical personnel required for equipment maintenance in advance, and reduce the impact of equipment failure on production.

[0035] In one embodiment, specifically, in step two, the preprocessing includes cleaning the production data and filling in the missing values. Among them, cleaning the production data includes processing noise data, error data, and duplicate data, specifically as follows: Noise data processing: Apply filtering algorithms such as Kalman filtering or median filtering to remove noise generated by sensor measurement errors or external interferences. For example, when collecting the temperature data of a kiln, due to electromagnetic interference, some temperature data show minor fluctuations. By using the median filtering algorithm to process the continuous temperature data and replacing the abnormally fluctuating data with the median value, the temperature data becomes smoother and more accurate. Error data processing: Identify and correct error data based on production process knowledge and data logic rules. For instance, if the forming pressure data of ceramic blank bodies exceeds the normal pressure range of the equipment, it is determined as error data. By communicating with the equipment manufacturer, the correct pressure range can be obtained, and the data outside the range can be corrected or marked. Duplicate data processing: Use data duplicate checking algorithms such as the hash algorithm to find and delete duplicate production data records. When the volume of production data is large, there may be duplicate records, which will affect the accuracy and efficiency of data analysis. By generating a unique hash value for each data record through the hash algorithm, duplicate records with the same hash value can be quickly identified and deleted.

[0036] Among them, the processing of missing values includes filling based on statistical methods and filling based on model prediction, as follows: Filling based on statistical methods: For numerical data such as temperature and pressure, calculate the mean, median, or mode of the data column and fill the missing values with the calculated values. For example, if some temperature data are missing during the firing process of a certain batch of ceramic cards, calculate the mean of the other normal temperature data of this batch and fill the missing values with the mean. Filling based on model prediction: Apply machine learning algorithms such as linear regression and decision trees to predict the missing values based on other relevant data. Taking the kiln temperature data as an example, use time, equipment operating status, raw material type, etc. as features to train a linear regression model and use the model to predict the missing temperature values.

[0037] The preset format conforms to the format of the relational database table structure, and the data of each production batch is associated and stored with a unique identifier. Specifically, according to the characteristics of ceramic card production data, design multiple data tables, such as raw material table, process parameter table, equipment operation table, production batch table, etc. In the raw material table, store information such as the type, batch, and supplier of raw materials; the process parameter table records the process parameters of processes such as blank body forming and firing; the equipment operation table includes the operating status and fault records of the equipment; the production batch table associates with other data tables and uses the production batch number as the unique identifier to record the production-related information of each batch of ceramic cards. By means of foreign key association, the data of each production batch is associated with the relevant data tables. For example, in the process parameter table, it is associated with the production batch table through the production batch number to ensure that the process parameter data of each production batch corresponds one-to-one with other information of this batch, facilitating query and management.

[0038] The initial states include to-be-produced, in-production, in-quality-inspection, completed, and discarded, which are specifically as follows: To-be-produced state: When the production plan is issued but the actual production has not yet started, the data status of this batch is set to "to-be-produced". At this time, the production time recorded in the production batch table is empty, and the relevant process parameters and equipment operation data have not started to be recorded. In-production state: After production starts, the data status of this batch is updated to "in-production". During the production process, information such as equipment operation data and process parameters is recorded in real time, such as the pressure and temperature of the green body forming equipment, and the firing temperature curve of the kiln. In-quality-inspection state: After the ceramic card production is completed, it enters the quality inspection link, and the data status becomes "in-quality-inspection". During the quality inspection, information such as the quality inspector, inspection time, and inspection result is recorded. Completed state: For batches that have passed the inspection and completed packaging, the data status is set to "completed". At this time, all production processes recorded in the production batch table have ended, and the products can enter the market circulation link. Discarded state: If the product quality is unqualified or production cannot continue for other reasons, the data status is marked as "discarded". Information such as the reason for discarding and the discarding time is recorded for subsequent analysis and improvement of the production process.

[0039] In one embodiment, specifically, in step one, the production data is collected at a dynamically adaptive time interval through sensors and equipment interfaces distributed on the production equipment, and the dynamically adaptive time interval is adjusted in real time according to the operating state and production stage of the production equipment. Among them, the production data collection process is specifically as follows: On the green body forming equipment, pressure sensors are installed to monitor the pressure on the green body during forming, and temperature sensors are installed to measure the mold temperature. These sensors can accurately obtain data closely related to the forming process. In the kiln equipment, multiple temperature sensors are arranged at different positions along the kiln to monitor the temperature distribution in different areas inside the kiln. At the same time, gas composition sensors are set to detect the concentrations of gases such as oxygen and carbon dioxide in the kiln to master the atmosphere environment of the kiln. The equipment interface selects an appropriate industrial standard interface, such as RS-485, CAN, etc., to ensure that the data collected by the sensors can be stably and quickly transmitted to the data collection system. The application of the dynamic adaptive time interval collection mechanism is as follows: to achieve dynamic adaptive collection of production data, an intelligent time interval adjustment system is established; in the equipment startup phase, since the production process is not yet stable, the system sets a shorter collection time interval, such as collecting data once per second, so as to timely capture parameter changes when the equipment is started and ensure normal startup of the equipment; when the equipment enters a stable operating state, the collection interval is appropriately extended, such as adjusting it to collect data every 5 seconds, while ensuring data accuracy, reducing data transmission and storage pressure; if the equipment operating state is abnormal, such as large fluctuations in parameters such as temperature and pressure, the system automatically shortens the collection interval to multiple times per second, monitors the equipment status in real time, and provides sufficient data support for fault diagnosis; taking the kiln as an example, in the heating stage, the temperature changes rapidly, and the collection interval is set to 1 second; in the constant temperature firing stage, the interval is adjusted to 5 seconds; if the temperature fluctuates abnormally, the interval is immediately shortened to 0.5 seconds.

[0040] Production data includes raw material information, process parameters and equipment operating status; the details are as follows: Raw material information collection: Before the raw materials are put into production, detailed information of the raw materials is collected through sensors and equipment interfaces; the weight of the raw materials is measured by weight sensors to determine the amount of raw materials put into production each time; the batch number, production date, supplier and other information of the raw materials are read through code scanning equipment to ensure the traceability of the raw materials; for the ceramic powder commonly used in the production of ceramic cards, the chemical composition of the powder can also be tested by a component analyzer to ensure that the quality of the raw materials meets the production requirements; Process parameter collection: collect corresponding process parameters for different production stages; collect pressure, temperature, molding time and other parameters in the green body molding stage. The pressure sensor monitors the pressure changes in the green body molding process in real time, the temperature sensor records the temperature of the mold and the green body, and the timer records the molding time; in the firing stage, collect the temperature curve, firing time, atmosphere composition and other parameters of the kiln; the temperature sensor records the temperature changes at different positions in the kiln to form a temperature curve; the timer records the total firing time; the gas composition sensor monitors the atmosphere composition in the kiln, such as oxygen and carbon dioxide concentrations; Equipment operation status collection: Collect equipment operation status data for equipment maintenance and production management; obtain equipment startup time, cumulative operation time, rotation speed, vibration and other information through the equipment's own sensors or external sensors; for example, monitor the equipment's operating speed through a rotation speed sensor, and detect the equipment's vibration amplitude through a vibration sensor. Once the vibration amplitude exceeds the normal range, an alarm is issued in time to indicate that the equipment has potential faults, so that equipment maintenance can be arranged in a timely manner to ensure production continuity.

[0041] In one embodiment, specifically, in step three, the real-time monitoring of the changes in production data is achieved by installing a real-time data acquisition module on the production equipment and collecting data at dynamically adaptive time intervals. Specifically, for example, install data acquisition modules on key production equipment such as green body forming equipment, kilns, and grinding equipment. These modules should have high precision, high stability, and anti-interference capabilities to adapt to the complex industrial environment of the ceramic card production workshop. Continue the dynamically adaptive time interval acquisition mechanism in step one, and adjust the acquisition time interval in real time according to the operating status and production stage of the production equipment. When the equipment starts up, adjusts parameters, or experiences abnormal fluctuations, shorten the acquisition interval, such as setting it to collect data once per second, in order to promptly capture the subtle changes in production data. When the equipment is running stably, appropriately extend the acquisition interval, such as collecting data once every 5 - 10 seconds, to reduce the pressure of data transmission and storage.

[0042] The state update rule is adjusted in real time and dynamically based on a machine learning model. The machine learning model uses historical production data, real-time production data, and quality feedback data as the training set and is trained according to production process standards and quality requirements. The machine learning model is trained using a convolutional neural network or a recurrent neural network. Specifically, collect historical production data, including raw material information, process parameters, equipment operating status, etc. for each production batch over a period of time. Real-time collect the current production data, and at the same time collect quality feedback data, such as the defective rate of products, defect types, etc. Clean and preprocess this data to remove noise and incorrect data, and organize the data into a format suitable for training the machine learning model. Optionally, a convolutional neural network (CNN) or a recurrent neural network (RNN) can be used for training. If the data has spatial features, such as the temperature distribution at different positions in the kiln, a CNN model can be used for training because CNN has advantages in processing spatial data. If the data has time series features, such as the change in the operating status of the equipment over time, an RNN model is more suitable, especially the long short-term memory network (LSTM), which can effectively handle the dependencies in long sequence data. Use the organized historical production data, real-time production data, and quality feedback data as the training set, and set the goals of the model according to production process standards and quality requirements. For example, set the qualified standard of the product as the output goal of the model, and by continuously adjusting the parameters of the model, enable the model to accurately predict the product quality status corresponding to the production data. During the training process, use methods such as cross-validation to evaluate the performance of the model and continuously optimize the model. Integrate the trained machine learning model into the data status monitoring system. The model analyzes the newly collected production data in real time and dynamically adjusts the status update rules according to the prediction results of the model. For example, if the model predicts that a change in a certain production parameter leads to a decline in product quality, the system will promptly adjust the status update threshold corresponding to this parameter and strengthen the monitoring of this parameter.

[0043] The updated data status is transmitted to the production management center through industrial Ethernet or wireless communication protocols. Among them, industrial Ethernet has the characteristics of fast transmission speed and high reliability, and can ensure that data is transmitted to the production management center in a timely and accurate manner. If the production equipment is relatively dispersed or there are mobile devices, wireless communication protocols such as Wi-Fi and ZigBee can be adopted. Wireless communication protocols have the advantages of flexible deployment and low cost, and can meet the data transmission requirements in different scenarios.

[0044] In one embodiment, specifically, in step seven, the data status traceability system is implemented using blockchain technology. The specific implementation method is as follows: The enterprise selects a suitable blockchain platform, such as Ethereum or Hyperledger, to build a data status traceability system. In the blockchain network, each department participating in the production process (such as the procurement department, production workshop, quality inspection department, etc.) joins as a node. Nodes are connected through encrypted networks and jointly maintain the distributed ledger of the blockchain. Use the smart contract function of the blockchain to write code logic for recording data status changes. Among them, a smart contract is an automatically executed contract clause deployed on the blockchain in the form of code to ensure the accuracy and immutability of data records.

[0045] The history of data status changes includes the time of data status change, the operator, equipment information, production process parameters, and the execution records of smart contracts based on the blockchain. The execution records of smart contracts based on the blockchain include the execution status of raw material procurement contracts, the execution status of production task assignments, and the verification status of quality inspection results. Among them, the history of data status changes specifically includes: Time of data status change: When the data status changes during the production process, such as the ceramic card changing from "in production" to "in quality inspection", the system automatically obtains the current accurate timestamp and records it on the blockchain. The accuracy of the timestamp can be accurate to seconds or even milliseconds, providing an accurate time basis for subsequent traceability. Operator: Obtain the information of the person performing the operation through the internal enterprise identity authentication system. For example, in the ceramic blank forming process, when the operator logs in to the production equipment, the system automatically records their employee number or identification information, which is associated with the production data of this batch of ceramic cards and recorded on the blockchain. This can clarify the responsible person for each operation step, facilitating subsequent problem tracing and liability determination. Equipment information: Record the detailed information of the equipment used in the production process, including equipment number, model, manufacturer, etc. When the equipment performs a certain operation, such as when the kiln starts firing ceramic cards, the system records the relevant information of the equipment on the blockchain and binds it to the production data of this batch of products. This helps to trace the impact of the equipment on product quality, as well as the usage and maintenance requirements of the equipment. Production process parameters: In each link of ceramic card production, collect and record production process parameters in real time. For example, the pressure, temperature, and forming time during ceramic blank forming; parameters such as the heating curve, constant temperature time, and cooling rate during kiln firing. These parameters are crucial for ensuring product quality. Recorded on the blockchain, they can be used to analyze the impact of the production process on product quality and provide data support for process optimization.

[0046] The execution records of the smart contract based on the blockchain specifically include: Implementation status of raw material procurement contracts: In the raw material procurement process, after the procurement contract is signed, the key information of the contract (such as contract number, supplier information, raw material specifications, quantity, price, delivery time, etc.) is recorded on the blockchain. As the procurement process progresses, the smart contract automatically records information such as the arrival time of raw materials, actual delivered quantity, and quality inspection results. If the quality of the raw materials does not meet the contract requirements, the smart contract can automatically trigger corresponding processing procedures, such as returns and claims, and record these operations on the blockchain to ensure the transparency and traceability of the execution of the procurement contract. Implementation status of production task allocation: After the production task is issued, the allocation information of the production task (such as task number, which production workshop, production line is assigned to, estimated start time and completion time, etc.) is recorded on the blockchain. During the production process, the smart contract records in real time information such as the actual start time, completion time, and production progress of the task. If there are delays or changes in the production task, the smart contract automatically records the relevant information and notifies the relevant departments for adjustment. This helps the production management department to promptly grasp the production progress, rationally allocate resources, and ensure the smooth execution of the production plan. Verification of quality inspection results: In each quality inspection link of ceramic card production (such as green body inspection, post-firing inspection, finished product inspection, etc.), the inspection results (such as qualified, unqualified, defect type, inspector, etc.) are recorded on the blockchain; the smart contract verifies the inspection results. If the inspection results are unqualified, the processing process for unqualified products is automatically triggered, such as rework, scrapping, etc., and the processing process is recorded. At the same time, the quality inspection results can be associated and analyzed with raw material information, production process parameters, etc. to help the enterprise find the root cause of quality problems and take targeted improvement measures.

[0047] In summary, a method for controlling the state of ceramic card production data provided by an embodiment of the present invention collects data through sensors deployed on production equipment, stores it after preprocessing and sets an initial state; uses a machine learning model to monitor and update the data state and transmit it; builds a visualization platform for monitoring and early warning; uses a variety of tool algorithms to analyze data; constructs an intelligent decision-making model to assist production; and uses blockchain technology to trace data to optimize production, solving the problem of ceramic card production data management and improving production management level, product quality and production efficiency.

[0048] Figure 2 It is a schematic diagram of the functional modules of a ceramic card production data state control system according to an embodiment of the present application. As Figure 2 shown, a ceramic card production data state control system includes: a data acquisition module, a data processing and storage module, a data state update module, a data state monitoring and early warning module, a data analysis module, an intelligent decision-making module, and a data traceability module; The data acquisition module is configured to obtain production data during the ceramic card production process; this module collects data at a dynamically adaptive time interval through sensors and device interfaces distributed on production equipment, and has sensor self-diagnosis and adaptive adjustment functions to ensure the accuracy and reliability of the collected data; The data processing and storage module is configured to preprocess the obtained production data and store it in a preset format. At the same time, an initial state is set for the production data of each ceramic card production batch; this module completes preprocessing tasks such as data cleaning and missing value filling, stores the data in a storage medium that conforms to the relational database table structure, and sets the initial state of the data according to the actual production situation; The data state update module is configured to monitor the changes in production data in real time during the ceramic card production process, update the data state of the corresponding production batch according to the pre-established state update rules, and transmit the updated data state to the production management center; this module obtains production data change information through the real-time data acquisition module, updates the data state with the help of state update rules based on a machine learning model, and is responsible for transmitting the updated data to the production management center; The data status monitoring and warning module is configured to build a data status monitoring platform in the production management center, display the data status of all ceramic card production batches in real time, set the thresholds and warning rules for the data status, and monitor and warn the data status; the visual monitoring platform built by this module combines fuzzy logic reasoning and real-time data analysis to dynamically generate thresholds and warning rules, and timely discovers and processes production anomalies through multi-modal warning methods; The data analysis module is configured to use data analysis tools and algorithms to analyze historical production data and current real-time data status, and generate analysis results; this module uses professional tools and advanced algorithms to deeply explore the value of production data and provide a scientific basis for subsequent decision-making; The intelligent decision-making module is configured to provide a scientific basis and decision-making support for production scheduling, process optimization, and quality control based on the analysis results by building an intelligent decision-making model; this module constructs an intelligent decision-making model by comprehensively considering multiple objectives according to the data analysis results to optimize production management.

[0049] The data traceability module is configured to build a data status traceability system, record the historical changes of the data status of each ceramic card production batch, and continuously optimize the production process through the mining and analysis of the historical changes of the data status; this module uses blockchain technology to record the historical changes of the data status and provides data support for the optimization of the production process.

[0050] In one embodiment, specifically, the data acquisition module adopts a distributed architecture, and the sensors distributed on the production equipment and the equipment interfaces work independently and collaboratively. The sensors have self-diagnosis and adaptive adjustment functions; when the sensors detect a decline in their own performance or environmental changes affecting the detection accuracy, they automatically adjust parameters or issue a fault warning to ensure the accuracy and reliability of the collected production data; the data acquisition module supports multiple data transmission protocols and can be seamlessly docked with different types of production equipment.

[0051] In one embodiment, specifically, the data traceability module uses the timestamp technology of blockchain to accurately record the time of data status changes, and realizes the access right management of the historical changes of the data status through smart contracts; the access rights to the historical changes of the data status are managed through smart contracts, so that only authorized personnel and system modules can view specific traceability information, ensuring the security and privacy of the data.

[0052] Regarding other details of the implementation technical solutions of each module in the above-mentioned ceramic card production data status control system in the above embodiment, reference can be made to the description in a ceramic card production data status control method in the above embodiment, which will not be elaborated here.

[0053] It should be noted that the embodiments in this specification are all described in a progressive manner. Each embodiment focuses on the differences from other embodiments. For the same or similar parts among the embodiments, reference can be made to each other. For system embodiments, since they are basically similar to method embodiments, the description is relatively simple. For the relevant parts, reference can be made to the description in the method embodiments.

[0054] The basic principles of the present disclosure have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, benefits, effects, etc. mentioned in the present disclosure are only examples and not limitations. It cannot be considered that these advantages, benefits, effects, etc. are essential for each embodiment of the present disclosure. In addition, the above-mentioned specific details are only for illustrative and easy-to-understand purposes, rather than limitations. The above details do not limit the present disclosure to necessarily adopt the above specific details to be implemented.

[0055] In the present disclosure, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The block diagrams of devices, apparatuses, equipment, and systems involved in the present disclosure are only illustrative examples and do not intend to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any way. Words such as "including", "comprising", "having", etc. are open-ended words, meaning "including but not limited to", and can be used interchangeably with each other. The words "or" and "and" used herein refer to the word "and / or" and can be used interchangeably with each other, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to" and can be used interchangeably with each other.

[0056] In addition, as used herein, the "or" used in the listing of items starting with "at least one" indicates a disjunctive listing. For example, the listing of "at least one of A, B, or C" means A or B or C, or AB or AC or BC, or ABC (i.e., A and B and C). Furthermore, the term "exemplary" does not mean that the examples described are preferred or better than other examples.

[0057] It should also be noted that in the systems and methods of the present disclosure, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent solutions of the present disclosure.

[0058] Various changes, substitutions, and alterations to the technology described herein may be made without departing from the teachings defined by the appended claims. In addition, the scope of the claims of this disclosure is not limited to the specific aspects of the processes, machines, manufactures, compositions of events, means, methods, and acts described above. Current or later-developed processes, machines, manufactures, compositions of events, means, methods, or acts that perform substantially the same function or achieve substantially the same result as the corresponding aspects described herein may be utilized. Accordingly, the appended claims include such processes, machines, manufactures, compositions of events, means, methods, or acts within their scope.

[0059] The foregoing description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present disclosure. Thus, the present disclosure is not intended to be limited to the aspects shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0060] The foregoing description has been presented for purposes of illustration and description. In addition, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although numerous example aspects and embodiments have been discussed above, those skilled in the art will recognize some of their variations, modifications, alterations, additions, and subcombinations.

Claims

1. A method for controlling the production data status of a ceramic card, characterized in that, It includes the following steps: Obtain the production data during the ceramic card production process; Preprocess the obtained production data, store it in a preset format, and at the same time, set the initial state for the production data of each ceramic card production batch; During the ceramic card production process, monitor the changes in production data in real time, update the data status of the corresponding production batch according to the pre-established status update rules, and transmit the updated data status to the production management center; Build a data status monitoring platform in the production management center to display the data status of all ceramic card production batches in real time, set the thresholds and warning rules for the data status, and monitor and warn the data status; Use data analysis tools and algorithms to analyze the historical production data and the current real-time data status, and generate analysis results; Based on the analysis results, by constructing an intelligent decision-making model, provide scientific basis and decision-making support for production scheduling, process optimization and quality control; Build a data status traceability system to record the historical changes in the data status of each ceramic card production batch, and through the mining and analysis of the historical changes in the data status, continuously optimize the production process.

2. The method for controlling the production data status of a ceramic card according to claim 1, wherein: The data status monitoring platform adopts a Web-based visual interface to display the data status in the form of charts and tables in real time; the thresholds and warning rules for the data status are dynamically generated by combining fuzzy logic reasoning and real-time data analysis, and are adjusted according to the statistical analysis results of historical production data, industry standards and real-time production environment changes. When the data status approaches or exceeds the threshold, a warning is issued through multi-modal warning methods, and the multi-modal warning methods include audible and visual alarms, SMS notifications, system pop-up prompts and vibration reminders of intelligent wearable devices.

3. A method for controlling the production data status of a ceramic card according to claim 1, characterized in that: The data analysis tools include the Pandas and Numpy libraries in Python, as well as professional data analysis software SAS and SPSS; the algorithms include an association analysis algorithm based on deep learning and a trend prediction algorithm based on reinforcement learning; the analysis results include production efficiency trend analysis, quality fluctuation cause analysis and equipment failure warning probability analysis.

4. A method for controlling the production data status of a ceramic card according to claim 1, characterized in that: The preprocessing includes cleaning the production data and filling in the missing values; the preset format is a format that conforms to the relational database table structure, and the data of each production batch is associated and stored with a unique identifier; the initial state includes to be produced, in production, in quality inspection, completed and discarded.

5. A method for controlling the production data status of a ceramic card according to claim 1, characterized in that: The production data is collected at a dynamically adaptive time interval through sensors and device interfaces distributed on the production equipment, and the dynamically adaptive time interval is adjusted in real time according to the operating status and production stage of the production equipment; the production data includes raw material information, process parameters and equipment operating status.

6. A method for controlling the production data status of a ceramic card according to claim 1, characterized in that: The change of the real-time monitored production data is realized by collecting data at a dynamically adaptive time interval through a real-time data acquisition module installed on the production equipment; the status update rule is adjusted in real time based on a machine learning model, and the machine learning model uses historical production data, real-time production data, and quality feedback data as the training set, and is trained according to production process standards and quality requirements. The machine learning model is trained using a convolutional neural network or a recurrent neural network; the updated data status is transmitted to the production management center through an industrial Ethernet or a wireless communication protocol.

7. A method for controlling the production data status of a ceramic card according to claim 1, characterized in that: The data status tracing system is implemented using blockchain technology; the history of data status changes includes the time of data status change, the operator, equipment information, production process parameters, and the execution records of smart contracts based on blockchain. The execution records of smart contracts based on blockchain include the execution status of raw material procurement contracts, the execution status of production task assignments, and the verification status of quality inspection results.

8. A ceramic card production data status control system, which is applied to the ceramic card production data status control method according to any one of claims 1-7, characterized in that, The system includes: a data acquisition module, a data processing and storage module, a data status update module, a data status monitoring and warning module, a data analysis module, an intelligent decision-making module, and a data tracing module; The data acquisition module is configured to obtain production data during the production process of ceramic cards; The data processing and storage module is configured to preprocess the obtained production data and store it in a preset format. At the same time, an initial status is set for the production data of each production batch of ceramic cards; The data status update module is configured to, during the production process of ceramic cards, monitor the change of production data in real time, update the data status of the corresponding production batch according to the pre-established status update rule, and transmit the updated data status to the production management center at the same time; The data status monitoring and warning module is configured to build a data status monitoring platform in the production management center, display the data status of all production batches of ceramic cards in real time, and set the threshold and warning rules for the data status to monitor and warn the data status; The data analysis module is configured to analyze historical production data and the current real-time data status using data analysis tools and algorithms, and generate analysis results; The intelligent decision-making module is configured to, based on the analysis results, provide scientific basis and decision support for production scheduling, process optimization, and quality control by constructing an intelligent decision-making model; The data tracing module is configured to build a data status tracing system, record the history of data status changes for each production batch of ceramic cards, and continuously optimize the production process through the mining and analysis of the history of data status changes.

9. The ceramic card production data status control system according to claim 8, characterized in that: The data acquisition module adopts a distributed architecture, and the sensors distributed on the production equipment and the equipment interfaces work independently and collaboratively. The sensors have self-diagnosis and adaptive adjustment functions.

10. A ceramic card production data status control system according to claim 8, characterized in that: The data tracing module uses the timestamp technology of blockchain to accurately record the time of data status change, and realizes the access right management of the history of data status change through smart contracts.

Images