CLS data management method and system

Abstract

The invention relates to a CLS data management method and system, and the method comprises the steps: uploading equipment operation data to an integrated data management platform through a plurality of communication protocols, and carrying out the encryption storage of the equipment operation data according to the priority of equipment; the equipment operation data is integrated into a big data processing framework, the equipment operation data is analyzed to obtain an analysis result, a dynamic production task report is generated based on the analysis result, and the production task report comprises a production progress, an equipment health state, real-time fault early warning information and optimization suggestions; calculating a risk value of each production device in the real-time fault early warning information, and performing priority classification on fault early warning signals in the real-time fault early warning information; if the risk value exceeds a preset fault risk threshold value, an alarm signal is triggered, and a fault processing scheme is generated according to the fault priority; and correspondingly adjusting the production equipment according to the user feedback information and the production task report. The method has the effect of improving the fault prediction precision.

Description

Technical Field

[0001] This application relates to the technical field of data management, and in particular, to a CLS data management method and system. Background Art

[0002] Currently, with the rapid development of industrial Internet and intelligent manufacturing, enterprises are facing the problem of how to effectively manage a large amount of production equipment data. Equipment operation data includes equipment status, production task progress, and sensor data, etc. The real-time collection, storage, and analysis of these data are crucial for equipment management, fault prediction, and production optimization. Traditional equipment data management methods usually rely on manual monitoring or simple rule-based algorithms, lacking the ability of intelligence and self-adaptation. Many systems also fail to effectively integrate various types of equipment data to generate comprehensive production task reports in real time for accurate equipment fault warning and intelligent equipment management.

[0003] The above-mentioned existing technical solutions have the following defects: Traditional systems mostly rely on fixed thresholds and manual intervention, and cannot adapt to changes in equipment status or the influence of environmental factors, resulting in untimely or overly lagged fault warnings, so there is room for improvement. Summary of the Invention

[0004] In order to improve the accuracy of fault prediction, this application provides a CLS data management method and system.

[0005] The first invention object of this application is achieved through the following technical solutions: A CLS data management method, the CLS data management method includes: Obtain the real-time equipment operation data of each production equipment, and the equipment operation data includes equipment status, production task progress, and sensor data; Upload the equipment operation data to the integrated data management platform through multiple communication protocols, and encrypt and store the equipment operation data according to the equipment priority; Integrate the equipment operation data into a big data processing framework, analyze the equipment operation data through big data analysis tools to obtain an analysis result, and generate a dynamic production task report based on the analysis result. The production task report includes production progress, equipment health status, real-time fault warning information, and optimization suggestions; Calculate the risk values of each production equipment in the real-time fault warning information, and classify the fault warning signals in the real-time fault warning information by priority; If the risk value exceeds the preset fault risk threshold, trigger an alarm signal, and generate a fault handling plan according to the fault priority; Make corresponding adjustments to the production equipment according to the user feedback information and the production task report.

[0006] By adopting the above technical solutions, by obtaining the real-time device operation data of each production device, it is possible to grasp the health status of the device, the progress of production tasks, and sensor data in real time, thereby providing data support for device fault warning; by uploading the device data to the integrated data management platform through multiple communication protocols and encrypting and storing it, the security and integrity of the data can be ensured, and at the same time, the flexibility of data transmission can be improved; by integrating the device data into the big data processing framework and analyzing it, it is possible to accurately predict device faults, generate real-time and dynamic production task reports, thereby helping production managers adjust production strategies in a timely manner and take preventive measures; by calculating the risk value and classifying the warning signals by priority, it is possible to trigger alarms in a timely manner and formulate fault handling plans, thereby improving the efficiency of device management, reducing the fault downtime, and enhancing the reliability and production efficiency of production devices; by adjusting the operation parameters of the production device according to the user feedback information, the adjustment of the production device can be made more in line with the actual needs, thereby enhancing the working efficiency and production quality of the device.

[0007] In one example, the present application can be further configured as follows: uploading the device operation data to the integrated data management platform through multiple communication protocols and encrypting and storing the device operation data according to the device priority includes: selecting a corresponding communication protocol according to the operating environment, data transmission requirements, and network conditions of each production device, and the communication protocols include Wi-Fi, Bluetooth, LoRa, 5G, and Ethernet; Assign a priority level to each production device according to the importance of each production device and the requirements for key data, and encrypt and store the data transmitted by each production device using a corresponding encryption algorithm according to the priority level.

[0008] By adopting the above technical solutions, by selecting a corresponding communication protocol and encrypting and storing the device operation data according to the device priority, it is possible to optimize the data transmission method according to the requirements of different devices and the network environment, ensure the security and stability of the data, reduce the risk of data loss or leakage caused by network fluctuations, and thus guarantee the information security in the production process.

[0009] In one example, the present application can be further configured as follows: integrating the device operation data into the big data processing framework and analyzing the device operation data through big data analysis tools to obtain analysis results includes: Preprocessing the device operation data to obtain preprocessed data, and the preprocessing includes data cleaning, data formatting, and outlier detection; Feature extraction is performed on the preprocessed data using a decision tree algorithm to obtain a feature dataset of the device operation data; a pre-trained fault prediction model is used to perform prediction analysis on the feature dataset to obtain the analysis result.

[0010] By adopting the above technical solution, through preprocessing the device operation data and using a decision tree algorithm for feature extraction, the device data can be cleaned and standardized, providing a more accurate and consistent data source for subsequent analysis; by using a pre-trained fault prediction model for prediction analysis, potential faults can be detected in advance, thereby reducing unexpected downtime in production, ensuring the efficient operation of production equipment and extending the service life of the equipment.

[0011] In one example, the present application can be further configured as: before using the pre-trained fault prediction model to perform prediction analysis on the feature dataset to obtain the analysis result, the method for managing CLS data further includes: obtaining the historical operation datasets of the production devices, where the historical operation datasets include sensor data, fault records, device status, and production task progress of the devices; Preprocess the collected historical operation datasets, and through feature engineering, select key features related to fault prediction to construct a feature dataset; Associate the key feature data in the feature dataset with the corresponding fault types to obtain a validation set; Use the feature dataset to train a deep neural network, and after training, use the validation set to verify and adjust the model to obtain the pre-trained fault prediction model.

[0012] By adopting the above technical solution, by obtaining historical operation datasets and preprocessing them, a feature dataset including device health status and fault types can be constructed, thereby providing more comprehensive data support; by selecting key features related to fault prediction through feature engineering and training the model through a deep neural network, the accuracy and robustness of the fault prediction model can be improved, thereby enhancing the intelligent level and prediction accuracy of production equipment management, detecting device faults in advance and reducing the risk of downtime.

[0013] In one example, the present application can be further configured as: calculating the risk values of the production devices in the real-time fault warning information includes: Determine the device status score, production task progress score, and sensor data score according to the device operation data; Through the formula: risk value = ω1·S status +ω2·S progress +ω3·S sensor , calculate to obtain the risk value, where S statusFor device status scoring, S progress For production task progress scoring, S sensor For sensor data scoring, ω1, ω2, ω3 are the weight coefficients of device status, task progress, and sensor data.

[0014] By adopting the above technical solution, by determining the device status score, production task progress score, and sensor data score according to the device operation data, the quantitative evaluation of the comprehensive health status of the device can be realized; by calculating the risk value and classifying the device failure risks according to the preset weight coefficients, high-risk devices can be identified more accurately, high-risk devices with faults can be processed preferentially, and unexpected faults during the production process can be avoided, thereby improving the reliability and production efficiency of the device.

[0015] In one example of the present application, it can be further configured as follows: Before triggering an alarm signal when the risk value exceeds the preset failure risk threshold and generating a fault handling plan according to the fault priority, the above-mentioned CLS data management method further includes: Setting corresponding risk thresholds according to the fault data and fault frequencies of different types of production equipment during historical operation; Dynamically adjusting the risk threshold according to the fault history and health status of different types of production equipment within a preset time period to obtain the preset failure risk threshold.

[0016] By adopting the above technical solution, by setting risk thresholds for different types of production equipment and dynamically adjusting the risk thresholds according to the health status and fault history of the equipment, more accurate fault early warning can be realized; the dynamic adjustment of the risk threshold changes according to the actual operation situation of the equipment, ensuring that the risk assessment is more flexible and accurate, reducing the possibility of false alarms or missed alarms, thereby improving the stability and safety of the production line.

[0017] In one example of the present application, it can be further configured as follows: The corresponding adjustment of the production equipment according to the user feedback information and the production task report includes: Obtaining user feedback information from the user side, where the feedback information includes user satisfaction, equipment adjustment suggestions, and fault handling effect evaluations; Performing semantic analysis on the user feedback information through natural language processing technology, extracting key adjustment suggestions and optimization requirements, and generating a semantic analysis result; According to the semantic analysis result, optimizing and adjusting the operation parameters of each production equipment and allocating adjustment production tasks.

[0018] By adopting the above technical solution, by obtaining user feedback information from the user side and using natural language processing technology for semantic analysis, it is possible to accurately extract the user's optimization suggestions and adjustment requirements, and optimize the operating parameters of production equipment through the analysis results; automatically adjusting the parameters of production equipment and allocating production tasks based on user feedback can make equipment management more personalized and refined, ensure the best operating state of the equipment in different production environments, and improve production efficiency and product quality.

[0019] The second invention object of the present application is achieved through the following technical solutions: A CLS data management system, the CLS data management system includes: An operating data acquisition module, configured to acquire real-time device operating data of each production device, where the device operating data includes device status, production task progress, and sensor data; A data upload module, configured to upload the device operating data to an integrated data management platform through multiple communication protocols, and encrypt and store the device operating data according to device priority; An analysis module, configured to integrate the device operating data into a big data processing framework, analyze the device operating data through big data analysis tools to obtain an analysis result, and generate a dynamic production task report based on the analysis result, where the production task report includes production progress, device health status, real-time fault warning information, and optimization suggestions; A calculation module, configured to calculate the risk values of the respective production devices in the real-time fault warning information, and classify the fault warning signals in the real-time fault warning information according to priority; An alarm module, configured to trigger an alarm signal if the risk value exceeds a preset fault risk threshold, and generate a fault handling solution according to the fault priority; An adjustment module, configured to make corresponding adjustments to the production equipment according to user feedback information and the production task report.

[0020] By adopting the above technical solutions, by obtaining the real-time device operation data of each production device, it is possible to grasp the health status of the device, the progress of production tasks, and sensor data in real time, thereby providing data support for device fault warning; by uploading device data to the integrated data management platform through multiple communication protocols and encrypting and storing it, the security and integrity of the data can be ensured, and at the same time, the flexibility of data transmission can be improved; by integrating device data into the big data processing framework and analyzing it, it is possible to accurately predict device faults, generate real-time and dynamic production task reports, thereby helping production managers adjust production strategies in a timely manner and take preventive measures; by calculating risk values and classifying the priority of warning signals, it is possible to trigger alarms in a timely manner and formulate fault handling plans, thereby improving device management efficiency, reducing fault downtime, and enhancing the reliability and production efficiency of production devices; by adjusting the operation parameters of production devices according to user feedback information, the adjustment of production devices can be made more in line with actual needs, thereby enhancing the working efficiency and production quality of the devices.

[0021] In summary, the present application includes the following beneficial technical effects: 1. By obtaining the real-time device operation data of each production device, it is possible to grasp the health status of the device, the progress of production tasks, and sensor data in real time, thereby providing data support for device fault warning; by uploading device data to the integrated data management platform through multiple communication protocols and encrypting and storing it, the security and integrity of the data can be ensured, and at the same time, the flexibility of data transmission can be improved; 2. By integrating device data into the big data processing framework and analyzing it, it is possible to accurately predict device faults, generate real-time and dynamic production task reports, thereby helping production managers adjust production strategies in a timely manner and take preventive measures; by calculating risk values and classifying the priority of warning signals, it is possible to trigger alarms in a timely manner and formulate fault handling plans, thereby improving device management efficiency, reducing fault downtime, and enhancing the reliability and production efficiency of production devices; by adjusting the operation parameters of production devices according to user feedback information, the adjustment of production devices can be made more in line with actual needs, thereby enhancing the working efficiency and production quality of the devices. Description of the Drawings

[0022] Figure 1 is a flowchart of a CLS data management method in an embodiment of the present application; Figure 2 is an implementation flowchart of step S20 in a CLS data management method in an embodiment of the present application; Figure 3 is an implementation flowchart of step S30 in a CLS data management method in an embodiment of the present application; Figure 4It is a flowchart of an implementation of a CLS data management method in an embodiment of the present application; Figure 5 It is a flowchart of the implementation of step S40 in a CLS data management method in an embodiment of the present application; Figure 6 It is a flowchart of an implementation of a CLS data management method in an embodiment of the present application; Figure 7 It is a flowchart of the implementation of step S60 in a CLS data management method in an embodiment of the present application; Figure 8 It is a schematic block diagram of a CLS data management system in an embodiment of the present application. Detailed implementation manners

[0023] The present application will be further described in detail below with reference to the accompanying drawings.

[0024] In one embodiment, as Figure 1 shown, the present application discloses a CLS data management method, which specifically includes the following steps: S10: Obtain the real-time device operation data of each production device, where the device operation data includes device status, production task progress, and sensor data.

[0025] Specifically, through sensors and control modules, the operation status data of the device is collected in real time, including physical parameters such as temperature, pressure, and rotation speed. These data can be monitored in real time through embedded sensors to ensure the real-time and accuracy of the data. At the same time, the production task progress information is regularly obtained from the device management software, and the working status and production progress of each device are recorded for subsequent analysis and processing. For example, when the user enters the RFID tag production module, selects an order that needs to generate EPC data in the system, and selects the encoding rule or template, the system automatically generates EPC data that meets the requirements based on the order and the encoding rule. The generated EPC data will be automatically distributed to the pre-authorized machines. The authorized machines perform the coding operation according to the received EPC data. After the coding operation is completed, the machines will send back the complete information of the written EPC data to the CLS system, including the EPC code of each tag, the coding time, the operator, etc. Through the back-transmitted data, the system can automatically generate a production log to record the production information of each batch and each tag for future query and tracking. In addition, the sensor data may include information such as device vibration, temperature fluctuation, and power consumption. These data provide a dynamic view of the device health and help to identify potential problems in a timely manner.

[0026] S20: Upload the device operation data to the integrated data management platform through multiple communication protocols, and encrypt and store the device operation data according to the device priority.

[0027] Specifically, the device operation data is uploaded to the integrated data management platform through communication protocols such as Wi-Fi, Bluetooth, LoRa, 5G or Ethernet, and a suitable communication protocol is selected according to different device priorities to achieve data transmission. For example, for critical devices that require real-time response, 5G or Ethernet with low latency may be used for data transmission; for low-power devices, the LoRa protocol is preferably used. The uploaded data will be encrypted and stored, and encryption algorithms such as AES are used to encrypt sensitive data to ensure data security, prevent data leakage or loss during transmission, and ensure the secure storage and subsequent use of the data of each device in the platform.

[0028] S30: Integrate the device operation data into the big data processing framework, analyze the device operation data through big data analysis tools to obtain analysis results, and generate a dynamic production task report based on the analysis results. The production task report includes production progress, device health status, real-time fault warning information and optimization suggestions.

[0029] Specifically, after uploading the device operation data to the big data processing framework, the uploaded data is integrated and parallel computed through big data processing platforms such as Hadoop or Spark. First, data cleaning and preprocessing are performed to remove redundant data and abnormal data, and then machine learning or deep learning algorithms are used to analyze the processed data, and a dynamic production task report is generated through methods such as pattern recognition and trend analysis. The content in the report includes real-time production progress, evaluation of the device health status, fault warning information, probability of occurrence of potential faults, and optimization suggestions based on the current device status. The report can be displayed through visual charts to help operators and management understand the device status more intuitively and take actions. For example, during RFID tag decoding detection, the read tag EPC data is compared with the generated original EPC data. If a mismatch is found, the system will automatically mark it as an error and generate a corresponding report; if a coding error is detected, the system will prompt the user and provide the option to rewrite the code. The user can choose to rewrite the RFID tag or manually adjust the error data, and all relevant data can be exported in EXCEL, CSV or TXT formats for convenient archiving and transmission.

[0030] S40: Calculate the risk values of each production device in the real-time fault warning information, and classify the fault warning signals in the real-time fault warning information by priority.

[0031] Specifically, the risk value is calculated based on the real-time operation data of the equipment. First, the risk value of each equipment is obtained by methods such as weighted average according to factors such as the working load of the equipment, the equipment status score, and the sensor data score. For example, when the temperature of a certain equipment exceeds the standard or the vibration is abnormal, it will affect its health status score, thus increasing the overall risk value of the equipment. Then, the fault warning signals are classified according to the size of the risk value, and multiple risk thresholds (such as high risk, medium risk, low risk) are set for classification, so as to take corresponding actions according to different levels of risks. For example, high-risk equipment will immediately alarm and stop operation, while low-risk equipment will be monitored and subsequently detected.

[0032] S50: If the risk value exceeds the preset fault risk threshold, trigger an alarm signal and generate a fault handling plan according to the fault priority.

[0033] Specifically, when the risk value of the equipment exceeds the set warning threshold, the system will immediately trigger an alarm signal to notify the operator or manager to handle it. For example, it will timely remind the relevant personnel by means of email, text message, or APP push. According to the risk priority of the equipment, the system will generate a corresponding fault handling plan according to the severity of the fault. For example, for high-risk equipment, a plan of immediately stopping operation and conducting troubleshooting and repair may be triggered; for low-risk equipment, only regular monitoring and updating of the fault log may be required.

[0034] S60: Make corresponding adjustments to the production equipment according to the user feedback information and the production task report.

[0035] Specifically, feedback information is collected from the user side, including data such as the actual effect of equipment operation, the satisfaction of fault handling, and the performance after equipment adjustment. The user feedback is analyzed through natural language processing technology to extract key information such as "the equipment temperature is too high" and "frequent faults", and then the equipment adjustment requirements are automatically generated. According to these feedbacks, the system adjusts the equipment operation parameters, such as adjusting the load of the equipment, adjusting the priority of the production task, or changing the operation state of the equipment, so as to improve the equipment operation efficiency, extend the equipment life, and reduce the probability of faults.

[0036] By adopting the above technical solutions, by obtaining the real-time device operation data of each production device, the health status of the device, the progress of production tasks, and sensor data can be grasped in real time, thus providing data support for device fault warning; by uploading device data to the integrated data management platform through multiple communication protocols and encrypting and storing it, the security and integrity of the data can be ensured, and at the same time, the flexibility of data transmission can be improved; by integrating device data into the big data processing framework and analyzing it, device faults can be accurately predicted, and real-time and dynamic production task reports can be generated, thus helping production managers adjust production strategies in a timely manner and take preventive measures; by calculating risk values and classifying the priority of warning signals, alarms can be triggered in a timely manner and fault handling solutions can be formulated, thus improving device management efficiency, reducing fault downtime, and enhancing the reliability and production efficiency of production devices; by adjusting the operation parameters of production devices according to user feedback information, the adjustment of production devices can be made more in line with actual needs, thus enhancing the working efficiency and production quality of the devices.

[0037] In one embodiment, as Figure 2 shown, in step S20, that is, the device operation data is uploaded to the integrated data management platform through multiple communication protocols, and the device operation data is encrypted and stored according to the device priority. Specifically, it includes: S21: According to the operating environment, data transmission requirements, and network conditions of each production device, select the corresponding communication protocol. The communication protocols include Wi-Fi, Bluetooth, LoRa, 5G, and Ethernet.

[0038] Specifically, in the encoding and decoding process of RFID tags, the data transmission requirements and the actual situation of the device directly determine which communication protocol to adopt to ensure the efficient and stable transmission of RFID data. According to the usage scenarios and requirements of different devices, the most suitable communication protocol is selected. For example, for low-power sensor devices, the LoRa communication protocol is used, which supports long-distance and low-power transmission; for devices with high real-time requirements, such as robotic arms or conveyor belts, the system preferably uses 5G or Ethernet to ensure high-speed data transmission and low latency; for production lines with complex working environments and a large number of devices, the system uses Wi-Fi or Bluetooth for data exchange between local devices to ensure that the data of each device can be uploaded to the integrated platform in a timely manner.

[0039] S22: According to the importance of each production device and the requirements for key data, assign a priority level to each production device, and use the corresponding encryption algorithm to encrypt and store the data transmitted by each production device according to the priority level.

[0040] Specifically, according to the working environment of the production equipment, the fault history records, and the importance of the equipment to the production line, the system assigns a priority level to each device. For critical equipment, the system will use a high-strength encryption algorithm, such as AES-256, to encrypt and store the data; while for relatively ordinary equipment, a lower-strength encryption algorithm, such as AES-128, may be used to ensure a balance between the efficiency and cost of data transmission while ensuring security. For example, during the encoding process of RFID tags, for critical equipment (such as the coding machine station), the EPC data it processes involves the uniqueness of products and the tracking of the supply chain, so a higher security level is required. For ordinary equipment (such as auxiliary tools or sensors), a lower priority level can be assigned, and the data transmitted may have a smaller impact on the system.

[0041] In one embodiment, as Figure 3 shown, in step S30, the device operation data is integrated into the big data processing framework, and the device operation data is analyzed through big data analysis tools to obtain analysis results, specifically including: S31: Preprocess the device operation data to obtain preprocessed data. The preprocessing includes data cleaning, data formatting, and outlier detection.

[0042] Specifically, first, clean the device operation data to remove invalid, duplicate data, and null values, and then format it to standardize different data formats of the device. For example, convert different data types of sensors into a numerical format uniformly, which is convenient for subsequent processing and analysis. In addition, the system will also perform outlier detection by setting thresholds to identify and remove obviously illogical abnormal data to ensure that subsequent analysis is based on accurate data.

[0043] S32: Use the decision tree algorithm to extract features from the preprocessed data to obtain a feature dataset of the device operation data.

[0044] Specifically, in the preprocessed device data, the system uses the decision tree algorithm to extract features from the data. By constructing a decision tree model, it automatically identifies features related to device faults, such as temperature, pressure, operating duration, etc., to obtain a feature dataset of a device. These feature datasets can better describe the operating state of the device and provide effective support for subsequent fault prediction analysis. For example, in RFID tag encoding and decoding, by extracting the EPC data in the tag memory, it is judged whether the written data is consistent with the expected data according to the read tag EPC data.

[0045] S33: Use a pre-trained fault prediction model to perform predictive analysis on the feature dataset to obtain analysis results.

[0046] Specifically, the feature dataset is input into a pre-trained fault prediction model. The model makes predictions based on the historical data of the device and known fault patterns, analyzes the possible future fault types and times of the device, and gives the probability of the occurrence of a fault. Based on these prediction results, the operator can perform maintenance or replace components in advance to avoid unforeseen faults of the device.

[0047] In one embodiment, as Figure 4 shown, before step S33, that is, before using the pre-trained fault prediction model to perform predictive analysis on the feature dataset and obtain the analysis result, this CLS data management method further includes: S331: Obtain the historical operation datasets of each production device. The historical operation datasets include the sensor data, fault records, device status, and production task progress of the device.

[0048] Specifically, obtain the historical operation datasets from the device management platform or on-site devices, including information such as the sensor data of the device at different time periods, historical fault records, the health status of the device, and the completion status of production tasks. These data can provide data support for subsequent fault prediction and device optimization.

[0049] S332: Preprocess the collected historical operation datasets, and through feature engineering, select the key features related to fault prediction to construct a feature dataset.

[0050] Specifically, clean the collected historical data, remove noise and irrelevant data to ensure data quality, and then perform feature engineering to select features that have a significant impact on fault prediction, such as the workload of the device, ambient temperature, operation duration, etc. Through these key features, construct a feature dataset for fault prediction.

[0051] S333: Associate the key feature data in the feature dataset with the corresponding fault types to obtain a validation set.

[0052] Specifically, associate the key features extracted from the feature dataset with the fault records of the device, and label each piece of data with the corresponding fault type or status to obtain a validation set containing fault types and feature data for subsequent training and validation.

[0053] S334: Use the feature dataset to train a deep neural network. After training, use the validation set to verify and adjust the model to obtain a pre-trained fault prediction model.

[0054] Specifically, a deep neural network is trained using a feature dataset. Through training, the model learns to identify potential fault patterns of the device. Then, the model is verified using a validation set to check its prediction accuracy, and the model is adjusted according to the verification results to optimize the model parameters. Finally, a verified and optimized fault prediction model is obtained.

[0055] In one embodiment, as Figure 5 shown, in step S40, that is, calculating the risk values of each production device in the real-time fault warning information, specifically including: S41: Determine the device status score, production task progress score, and sensor data score according to the device operation data.

[0056] Specifically, according to the real-time data collected from the device sensors, first evaluate the health status of the device. For example, calculate the device status score through sensor data such as temperature, vibration, and pressure. The device status score is obtained by weighted summation or comprehensive calculation of each sensor data. For example, factors such as the degree of temperature deviation from the set standard and vibration intensity are weighted proportionally to obtain the current health score of the device; for the production task progress score, evaluate the completion degree of the device's production task. The task progress score can be calculated by the proportional relationship between the current production volume and the target production volume. When the task progress lags, the score will be relatively low; the sensor data score is based on the accuracy and stability of the sensor data. For example, if a certain sensor frequently generates abnormal data or has large fluctuations, the sensor data score will be correspondingly reduced. Through these scores, the operation status of the device can be comprehensively reflected. Suppose during the encoding process of an RFID tag, the device is operating well, the temperature and vibration are within the normal range, and the score is 90; the encoding operation is completed, but some tags fail to be successfully written, and the score is 75; there are minor errors during the decoding process, and the score is 60; the device environment temperature is moderate, without moisture interference, and the score is 80.

[0057] S42: Calculate the risk value through the formula: Risk value = ω1·S status +ω2·S progress +ω3·S sensor , where S status is the device status score, S progress is the production task progress score, S sensor is the sensor data score, and ω1, ω2, ω3 are the weight coefficients of the device status, task progress, and sensor data.

[0058] Specifically, the overall risk value of the device is calculated by combining the device status score, production task progress score, and sensor data score through the weighted average method. The weight coefficients ω1, ω2, ω3 are set according to the importance of each score. For example, if the device status is a key factor affecting the overall operation of the device, ω1 can be set to a relatively high value; while the production task progress score may have a relatively small impact on the long-term reliability of the device, and the weight of ω2 can be set relatively low; the sensor data score comprehensively affects the accuracy and fault prediction of the device, so ω3 will be determined according to the specific type and function of the sensor. The calculation method of the formula can be to accumulate the weighted score values to obtain a comprehensive risk value, which can effectively reflect the overall risk level of the device and provide a basis for subsequent fault warning and decision-making.

[0059] In one embodiment, as Figure 6 shown, before step S50, that is, calculating the risk values of each production device in the real-time fault warning information, specifically including: S501: Set corresponding risk thresholds according to the fault data and fault frequencies of different types of production devices during historical operation.

[0060] Specifically, due to differences in the technologies used, working environments, and loads of different types of production devices, the risk levels of faults are also different. By analyzing information such as fault records, fault frequencies, and device service lives in the device historical operation data, a benchmark risk threshold can be set for each device type. For example, for some devices such as high-pressure boilers or robotic arms, once a fault occurs, it will cause relatively large safety hazards, so their risk thresholds will be set relatively low to ensure timely warning; while for some devices such as conveyor belts, although there is a risk of faults, the impact on production after the faults occur is relatively small, so their risk thresholds can be set relatively high. This setting process is completed through statistical analysis of historical data to ensure that the risk thresholds can reasonably reflect the actual fault risks of different devices.

[0061] S502: Dynamically adjust the risk threshold according to the fault history and health status of different types of production devices within a preset time period to obtain a preset fault risk threshold.

[0062] Specifically, as the device is used, the health status of the device changes, and the failure risk also fluctuates. Therefore, the risk threshold needs to be dynamically adjusted. For example, if a device has not had any major failures for a period of time and its status remains good, its risk threshold can be appropriately increased to reduce unnecessary warnings. On the contrary, if the device has experienced several minor failures or its status has been continuously declining, the system will automatically lower its risk threshold to enhance the sensitivity of failure warnings and prevent larger-scale failures caused by delayed warnings. The process of dynamic adjustment is based on the device operation data collected in real time. Through real-time calculation and adjustment, it ensures that the risk threshold of the device can adapt to the actual status and historical data of the device, improving the accuracy and flexibility of warnings.

[0063] In one embodiment, as Figure 7 shown, in step S60, that is, according to the user feedback information and the production task report, corresponding adjustments are made to the production equipment, specifically including: S61: Obtain user feedback information from the user side. The feedback information includes user satisfaction, equipment adjustment suggestions, and evaluation of the effect of fault handling.

[0064] Specifically, the collection of user feedback information is carried out through various channels. For example, through the questionnaire function of the device operation panel or the device management application, the user's satisfaction with the device, feedback on the fault handling process, and evaluation of the operation effect after equipment adjustment are collected. Users can provide opinions on aspects such as the operation stability of the device, the timeliness of fault handling, and the overall performance of the device. These feedbacks will help evaluate the performance of the device in actual use and provide directions for improvement in device management. By collecting this feedback information, device managers can more comprehensively understand the actual situation of device operation and make corresponding adjustments based on the user's feedback.

[0065] S62: Perform semantic analysis on the user feedback information through natural language processing technology, extract key adjustment suggestions and optimization requirements, and generate the semantic analysis result.

[0066] Specifically, after collecting the user's feedback information, natural language processing (NLP) technology is used to perform semantic analysis on the feedback content. Through techniques such as word frequency analysis and sentiment analysis, the key information and adjustment suggestions involved in the feedback are extracted. For example, if the user feedback mentions "the device stopped due to high temperature" or "the device is more stable after adjusting the load", these key information will be automatically extracted and converted into structured data. The semantic analysis result can clearly show the main needs and problems of the user, providing a basis for subsequent equipment adjustment and optimization.

[0067] S63: According to the semantic analysis result, optimize and adjust the operation parameters of each production equipment, and allocate adjusted production tasks.

[0068] Specifically, based on the understanding of user feedback and semantic analysis results, the system will optimize and adjust the operating parameters of the device, such as increasing the cooling time, adjusting the device load, modifying the operating speed of the device, etc., to improve the overall operating effect of the device; at the same time, the system will also reallocate production tasks according to the needs of optimization and adjustment, such as adjusting the working order or task priority of the device, so as to ensure that the device can work in the best state and avoid the decline of production efficiency or the occurrence of failures caused by unstable operation or overload of the device. This adjustment process is optimized individually according to the specific feedback of the user, so as to improve the overall production capacity and reliability of the device.

[0069] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution, and the execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0070] In one embodiment, a CLS data management system is provided, and this CLS data management system corresponds one-to-one with the CLS data management method in the above embodiment. As Figure 8 shown, this CLS data management system includes an operating data acquisition module, a data upload module, an analysis module, a calculation module, and an alarm module. The detailed description of each functional module is as follows: The operating data acquisition module is used to acquire the real-time device operating data of each production device, and the device operating data includes device status, production task progress, and sensor data; The data upload module is used to upload the device operating data to the integrated data management platform through multiple communication protocols, and encrypt and store the device operating data according to the device priority; The analysis module is used to integrate the device operating data into the big data processing framework, analyze the device operating data through big data analysis tools, obtain the analysis results, and generate a dynamic production task report based on the analysis results. The production task report includes production progress, device health status, real-time fault warning information, and optimization suggestions; The calculation module is used to calculate the risk values of each production device in the real-time fault warning information, and classify the fault warning signals in the real-time fault warning information by priority; The alarm module is used to trigger an alarm signal if the risk value exceeds the preset fault risk threshold, and generate a fault handling plan according to the fault priority; The adjustment module is used to make corresponding adjustments to the production device according to the user feedback information and the production task report.

[0071] Optionally, the data upload module includes: A protocol selection sub-module, which is used to select a corresponding communication protocol according to the operating environment, data transmission requirements, and network conditions of each production device. The communication protocols include Wi-Fi, Bluetooth, LoRa, 5G, and Ethernet; An encryption sub-module, which is used to assign a priority level to each production device according to the importance of each production device and the requirements of critical data, and encrypt and store the data transmitted by each production device using the corresponding encryption algorithm according to the priority level.

[0072] Optionally, the analysis module includes: A preprocessing sub-module, which is used to preprocess the device operation data to obtain preprocessed data. The preprocessing includes data cleaning, data formatting, and outlier detection; A feature extraction sub-module, which is used to extract features from the preprocessed data using a decision tree algorithm to obtain a feature dataset of the device operation data; A model analysis sub-module, which is used to perform predictive analysis on the feature dataset using a pre-trained fault prediction model to obtain an analysis result.

[0073] Optionally, the calculation module includes: A scoring sub-module, which is used to determine the device status score, production task progress score, and sensor data score according to the device operation data; A formula calculation sub-module, which is used to calculate the risk value through the formula: Risk value = ω1·S status +ω2·S progress +ω3·S sensor , where S status is the device status score, S progress is the production task progress score, S sensor is the sensor data score, and ω1, ω2, ω3 are the weight coefficients of the device status, task progress, and sensor data.

[0074] Optionally, the CLS data management system further includes: A historical data acquisition module, which is used to acquire the historical operation datasets of each production device. The historical operation datasets include the sensor data, fault records, device status, and production task progress of the device; A feature set construction module, which is used to preprocess the collected historical operation datasets and select key features related to fault prediction through feature engineering to construct a feature dataset; An association module, which is used to associate the key feature data in the feature dataset with the corresponding fault types to obtain a validation set; A model training module, which is used to train a deep neural network using the feature dataset, and after training, use the validation set to verify and adjust the model to obtain a pre-trained fault prediction model.

[0075] A threshold setting module, configured to set corresponding risk thresholds according to the fault data and fault frequencies of different types of production equipment during historical operation; A threshold adjustment module, configured to dynamically adjust the risk thresholds according to the fault histories and health states of different types of production equipment within a preset time period, so as to obtain preset fault risk thresholds.

[0076] Optionally, the adjustment module includes: A feedback acquisition sub-module, configured to acquire user feedback information from a user terminal, where the feedback information includes user satisfaction, equipment adjustment suggestions, and fault handling effect evaluations; A semantic analysis sub-module, configured to perform semantic analysis on the user feedback information through natural language processing technology, extract key adjustment suggestions and optimization requirements, and generate semantic analysis results; An optimization adjustment sub-module, configured to optimize and adjust the operating parameters of each production equipment according to the semantic analysis results, and allocate adjustment production tasks.

[0077] For the specific limitations of a CLS data management system, reference can be made to the limitations of a CLS data management method in the foregoing text, which will not be elaborated herein. Each module in the above-mentioned CLS data management system can be implemented in whole or in part by software, hardware, and their combinations. The above-mentioned modules can be embedded in the processor of a computer device in hardware form or be independent of it, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above-mentioned modules.

[0078] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is used as an example. In practical applications, the above-mentioned functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above.

[0079] The above-mentioned embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A CLS data management method, characterized in that: The CLS data management method comprises: Acquire real-time equipment operation data of each production equipment, wherein the equipment operation data includes equipment status, production task progress and sensor data; Uploading the device operation data to the integrated data management platform through multiple communication protocols, and encrypting and storing the device operation data according to device priority; Integrate the equipment operation data into the big data processing framework, analyze the equipment operation data through big data analysis tools, obtain analysis results, and generate a dynamic production task report based on the analysis results, the production task report includes production progress, equipment health status, real-time fault warning information and optimization suggestions; Calculating the risk value of each production equipment in the real-time fault warning information, and classifying the fault warning signals in the real-time fault warning information by priority; If the risk value exceeds the preset fault risk threshold, an alarm signal is triggered and a fault handling plan is generated according to the fault priority; According to the user feedback information and the production task report, the production equipment is adjusted accordingly.

2. A CLS data management method according to claim 1, characterized in that: The uploading of the device operation data to the integrated data management platform through multiple communication protocols and encrypting and storing the device operation data according to the device priority includes: Select corresponding communication protocols according to the operating environment, data transmission requirements and network conditions of each production equipment, including Wi-Fi, Bluetooth, LoRa, 5G and Ethernet; According to the importance of each production device and the demand for key data, a priority level is assigned to each production device, and according to the priority level, the data transmitted by each production device is encrypted and stored using a corresponding encryption algorithm.

3. A CLS data management method according to claim 1, characterized in that: The device operation data is integrated into the big data processing framework, and the device operation data is analyzed by a big data analysis tool to obtain analysis results including: Preprocessing the device operation data to obtain preprocessed data, wherein the preprocessing includes data cleaning, data formatting and outlier detection; A decision tree algorithm is used to extract features from the preprocessed data to obtain a feature data set of the equipment operation data; a pre-trained fault prediction model is used to perform predictive analysis on the feature data set to obtain the analysis result.

4. A CLS data management method according to claim 3, characterized in that: Before performing predictive analysis on the feature data set using the pre-trained fault prediction model to obtain the analysis result, the CLS data management method further includes: Acquire a historical operation data set of each production device, wherein the historical operation data set includes sensor data, fault records, device status, and production task progress of the device; Preprocessing the collected historical operation data set, and selecting key features related to fault prediction through feature engineering to construct a feature data set; Associating the key feature data in the feature data set with the corresponding fault type to obtain a verification set; The deep neural network is trained using the feature data set, and after the training, the model is verified and adjusted using the verification set to obtain the pre-trained fault prediction model.

5. A CLS data management method according to claim 1, characterized in that: The calculating of the risk value of each production equipment in the real-time fault warning information comprises: Determine the equipment status score, the production task progress score and the sensor data score according to the equipment operation data; By formula: Risk value = ω1·S status +ω2·S progress +ω3·S sensor , calculate the risk value, where S status Score the device status, S progress Score the production task progress, S sensor is the sensor data score, ω1, ω2, ω3 are the weight coefficients of device status, task progress and sensor data.

6. A CLS data management method according to claim 1, characterized in that: Before triggering an alarm signal if the risk value exceeds a preset fault risk threshold and generating a fault handling solution according to the fault priority, the CLS data management method further includes: Set corresponding risk thresholds based on the failure data and failure frequency of different types of production equipment in historical operation; According to the failure history and health status of the different types of production equipment within a preset time period, the risk threshold is dynamically adjusted to obtain the preset failure risk threshold.

7. A CLS data management method according to claim 1, characterized in that: The adjusting the production equipment accordingly according to the user feedback information and the production task report includes: Obtain user feedback information from the user end, the feedback information including user satisfaction, equipment adjustment suggestions and fault handling effect evaluation; Performing semantic analysis on the user feedback information through natural language processing technology, extracting key adjustment suggestions and optimization requirements, and generating semantic analysis results; According to the semantic analysis results, the operating parameters of each production equipment are optimized and adjusted, and the production tasks are allocated and adjusted.

8. A CLS data management system, characterized in that: The CLS data management system comprises: An operation data acquisition module is used to acquire real-time equipment operation data of each production equipment, wherein the equipment operation data includes equipment status, production task progress and sensor data; A data uploading module, used to upload the device operation data to the integrated data management platform through multiple communication protocols, and encrypt and store the device operation data according to the device priority; An analysis module is used to integrate the equipment operation data into a big data processing framework, analyze the equipment operation data through a big data analysis tool, obtain analysis results, and generate a dynamic production task report based on the analysis results, wherein the production task report includes production progress, equipment health status, real-time fault warning information and optimization suggestions; A calculation module, used to calculate the risk value of each production equipment in the real-time fault warning information, and to prioritize the fault warning signals in the real-time fault warning information; An alarm module is used to trigger an alarm signal if the risk value exceeds a preset fault risk threshold, and generate a fault handling solution according to the fault priority; The adjustment module is used to make corresponding adjustments to the production equipment according to the user feedback information and the production task report.

Images