A production monitoring system and method based on big data

Through the production monitoring method based on big data, the abnormal situations in the production process of epoxy plate heating plates and PTC heating plates are monitored and warned in real time, and the problems of monitoring lag and production interruption risks in the existing technology are solved, achieving efficient and accurate production control.

CN118689157BActive Publication Date: 2024-11-29厦门宝益科技有限公司
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
CN202411180312.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-27
Publication Date
2024-11-29
Estimated Expiration
2044-08-27

AI Technical Summary

Technical Problem

The existing epoxy plate heating sheet and PTC heating sheet production monitoring systems have lag in abnormal detection, making it difficult to achieve real-time monitoring and early warning, which increases the risk of production interruption and affects production efficiency and product quality.

Method used

Using a production monitoring method based on big data, by obtaining raw material data sets and equipment operation information, performing data preprocessing and abnormal detection, generating raw material quality data and equipment operation abnormal data, combining process parameter information for intelligent production control, and building production regulation strategies Model to realize real-time monitoring and early warning of the production process.

Benefits of technology

Real-time monitoring and early warning of the production process of epoxy plate heating sheets and PTC heating sheets is realized, reducing the risk of production interruption, improving production efficiency and product quality, and enhancing the flexibility and adaptability of the production process.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118689157B_ABST
    Figure CN118689157B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of big data monitoring technology, and in particular to a production monitoring system and method based on big data. The method comprises the following steps: obtaining a raw material data set; performing data preprocessing on the raw material data set to obtain a standard raw material data set; extracting quality data of the standard raw material data set to generate raw material quality data; performing parameter compliance analysis on the raw material quality data to obtain quality parameter analysis data; marking the quality parameter analysis data using a preset standard quality parameter threshold to generate raw material quality exceeding standard data. The present invention realizes real-time monitoring and early warning of the production process of epoxy plate heaters and PTC heaters through Internet of Things technology, machine learning technology, intelligent control technology and visualization technology, thereby reducing the risk of production interruption; and performs intelligent production control on the production process to enhance flexibility and adaptability.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

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

[0002] As key components widely used in electronic equipment, medical equipment, automotive parts and other fields, the monitoring and control of the production process of epoxy plate heaters and PTC heaters is crucial to ensure product quality and production efficiency. From the early reliance on manual inspection and simple mechanical measurement to modern automation and digital monitoring, production monitoring technology has undergone significant changes. Initially, production monitoring mainly relied on direct observation by operators and basic measurement tools, which was not only inefficient, but also difficult to ensure accuracy and consistency. With the development of sensor technology, data acquisition technology and computer technology, production monitoring has begun to transform towards automation and digitalization, improving the efficiency and accuracy of monitoring. In recent years, the rise of big data and artificial intelligence technology has further promoted the intelligence and precision of production monitoring systems. However, the existing production monitoring systems for epoxy plate heaters and PTC heaters have lags in abnormal detection, making it difficult to achieve real-time monitoring and early warning, thereby increasing the risk of production interruptions and affecting production efficiency and product quality; and traditional production control strategies are based on fixed rules and experience, lack flexibility and adaptability, and are difficult to achieve effective intelligent control in the face of complex and changing production environments. Summary of the invention

[0003] Based on this, it is necessary to provide a production monitoring system and method based on big data to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a production monitoring method based on big data is provided, the method comprising the following steps:

[0005] Step S1: obtaining a raw material data set; performing data preprocessing on the raw material data set to obtain a standard raw material data set; extracting quality data of the standard raw material data set to generate raw material quality data;

[0006] Step S2: Perform parameter compliance analysis on the raw material quality data to obtain quality parameter analysis data; mark the quality parameter analysis data using a preset standard quality parameter threshold to generate raw material quality exceeding standard data;

[0007] Step S3: Acquire equipment operation information on the production line; perform abnormality detection on the equipment operation information to generate equipment operation abnormality data; perform abnormal situation integration on the equipment operation abnormality data and raw material quality exceeding standard data to generate abnormal exceeding standard data;

[0008] Step S4: Acquire process parameter information; perform process adjustment analysis on the process parameter information to obtain process analysis data; perform intelligent production control on the process analysis data and abnormal exceeding standard data to generate production control data; construct a production control strategy model based on the production control data to obtain a production regulation strategy model;

[0009] Step S5: According to the production control strategy model, the raw material quality data, equipment operation information and process parameter information are used to perform real-time monitoring of the production process of epoxy plate heaters and PTC heaters, and a real-time production monitoring report is generated; early warning analysis is performed on the real-time production monitoring report to obtain early warning information; normal production data of the real-time production monitoring report is extracted to obtain normal production information;

[0010] Step S6: construct a visualization platform based on the real-time production monitoring report to obtain a real-time production monitoring visualization platform; send warning information and normal production information to the designated equipment of the production team based on the real-time production monitoring visualization platform to perform production monitoring operations for epoxy plate heaters and PTC heaters.

[0011] The present invention ensures that the production monitoring system can fully cover all key raw material properties by acquiring raw material data sets, providing a solid data foundation for subsequent quality control and process optimization, and performing data preprocessing on raw material data sets, which can significantly improve the accuracy and consistency of raw material quality data, reduce the deviation caused by different data sources and measurement methods, obtain standard raw material data sets, eliminate the need for repeated testing of raw material quality, improve production efficiency, extract quality data of standard raw material data sets, generate raw material quality data, and accurate raw material quality data provide intuitive decision support for production management personnel, which helps to timely discover and solve quality problems. Parameter compliance analysis is performed through raw material quality data to ensure high standards and consistency of raw material quality data, and marking is performed using preset quality parameter thresholds, which can timely discover and mark raw materials that do not meet the standards, thereby avoiding inferior materials from entering the production process, reducing production risks and costs, and the generated raw material quality exceeding standard data provides a direct reference for subsequent quality control and material selection, enhancing the transparency and predictability of the production process. By acquiring the equipment operation information on the production line, the real-time monitoring of the equipment status is realized, the abnormality detection of the equipment operation information is performed, and the abnormal operation data of the equipment is generated. It can timely discover and mark the abnormal conditions in the equipment operation, which helps to prevent production interruptions and equipment failures, reduce downtime and maintenance costs, and integrate the abnormal conditions of equipment operation abnormal data and raw material quality exceeding standard data to generate abnormal exceeding standard data, which provides abnormal exceeding standard data for the production process. By acquiring process parameter information, the accuracy of the process of the production process can be mastered, which provides a data basis for subsequent process optimization. The process parameter information is analyzed for process adjustment to obtain process analysis data to ensure that the production process can be dynamically adjusted according to real-time feedback, thereby improving production efficiency and product quality. Combined with process analysis data and abnormal exceeding standard data for intelligent production control, it can respond to various changes in production in a timely manner, generate production control data, and construct a production control strategy model based on the production control data to obtain a production control strategy model, which provides scientific and systematic decision support for the production process, making production control more accurate and efficient. By applying the production control strategy model, the raw material quality data, equipment operation information and process parameter information are used to monitor the production process of epoxy plate heaters and PTC heaters in real time, ensuring the continuity of production activities. The real-time production monitoring report is generated to provide the production team with instant feedback on the production status, so that production problems can be quickly identified and responded to. The real-time production monitoring report is analyzed for early warning to obtain early warning information. The early warning information can inform the production team of production risks so that measures can be taken to reduce production interruptions and quality accidents. At the same time, the normal production data of the real-time production monitoring report is extracted to obtain normal production information, which helps the production team to know the current production information, thereby optimizing the production process and improving efficiency.By building a real-time production monitoring visualization platform, the intuitiveness and convenience of production monitoring can be significantly improved, so that the production team can intuitively understand complex production data and status through a graphical interface, so as to make decisions more quickly. Based on the real-time production monitoring visualization platform, early warning information and normal production information are sent to the designated equipment of the production team, ensuring the timeliness and accuracy of information transmission, and enhancing the production team's ability to control the production process. Therefore, the present invention realizes real-time monitoring and early warning of the production process of epoxy plate heating plates and PTC heating plates through Internet of Things technology, machine learning technology, intelligent control technology and visualization technology, reducing the risk of production interruption; and intelligent production control of the production process is performed to enhance flexibility and adaptability.

[0012] Preferably, step S1 comprises the following steps:

[0013] Step S11: using sensors to obtain a raw material data set;

[0014] Step S12: performing data preprocessing on the raw material data set to obtain a standard raw material data set, wherein the data preprocessing includes data decryption, data cleaning, data denoising and data standardization;

[0015] Step S13: performing quality feature identification on the standard raw material data set to obtain quality feature information; performing quality data screening on the standard raw material data set according to the quality feature information to generate raw material quality data.

[0016] The present invention obtains raw material data sets through sensors, thereby ensuring the timeliness and accuracy of the data, providing original and comprehensive information for subsequent analysis, performing data preprocessing on the raw material data sets to obtain a standard raw material data set, ensuring the quality and consistency of the data, laying a solid foundation for accurate analysis, and ensuring the validity of the data results. The present invention performs quality feature identification on the standard raw material data sets to obtain quality feature information, which can capture the key quality attributes of the raw materials, performs quality data screening on the standard raw material data sets according to the quality feature information, generates raw material quality data, and further ensures that only high-quality raw materials that meet the standards are used for production, thereby improving the utilization rate and production efficiency of the raw materials, and reducing the production risks and costs caused by material quality problems.

[0017] Preferably, step S2 comprises the following steps:

[0018] Step S21: extracting characteristic values ​​of raw material quality data to obtain quality characteristic values, wherein the quality characteristic values ​​include chemical composition data, physical property data and mechanical property data of the raw material;

[0019] Step S22: performing weighted average calculation on the raw material chemical composition data, physical property data and mechanical property data to generate weighted average quality data;

[0020] Step S23: performing parameter compliance analysis on the weighted average quality data to obtain quality parameter analysis data;

[0021] Step S24: Compare the quality parameter analysis data with the preset standard quality parameter threshold. When the quality parameter analysis data is less than or equal to the preset standard quality parameter threshold, the quality parameter analysis data is recorded normally; when the quality parameter analysis data is greater than the preset standard quality parameter threshold, the quality parameter analysis data is marked as abnormal and raw material quality exceeding standard data is generated.

[0022] The present invention obtains quality characteristic values ​​by extracting raw material chemical composition data, physical property data and mechanical property data of raw material quality data, thereby providing comprehensive characteristic values ​​for subsequent quality evaluation; weighted average calculation is performed on the raw material chemical composition data, physical property data and mechanical property data to generate weighted average quality data, which can comprehensively reflect the overall quality level of the raw materials; parameter compliance analysis is performed on the weighted average quality data to obtain quality parameter analysis data, thereby further ensuring that the quality of the raw materials meets the established standards; the quality parameter analysis data is compared with the preset standard quality parameter threshold value, thereby achieving precise control of the quality of the raw materials; when the quality parameter value obtained by analysis is less than or equal to the set threshold value, these data are recorded normally, indicating that the raw materials meet the production requirements and can smoothly enter the next production stage; on the contrary, when the quality parameter analysis data exceeds the preset threshold value, an abnormal mark will be performed to generate raw material quality exceeding standard data, thereby improving the speed and accuracy of problem identification, and also providing an important basis for subsequent quality control.

[0023] Preferably, step S3 comprises the following steps:

[0024] Step S31: using sensors to obtain equipment operation information on the production line;

[0025] Step S32: extracting the working characteristics of the equipment operation information and generating a working characteristic vector of the equipment operation;

[0026] Step S33: performing abnormality detection on the equipment operation feature vector to generate equipment operation abnormality data;

[0027] Step S34: abnormal situation integration is performed on the equipment operation abnormality data and the raw material quality exceeding standard data to generate abnormal situation exceeding standard data, wherein the abnormal situation integration includes the type of equipment operation abnormality, the type of raw material quality exceeding standard and the duration of the abnormality.

[0028] The present invention obtains the equipment operation information on the production line through sensors, provides real-time data support for subsequent analysis, extracts the working characteristics of the equipment operation information, generates the equipment operation working characteristic vector, so that the equipment operation status can be evaluated in a quantitative manner, and the equipment operation working characteristic vector is subjected to abnormal detection, so that the abnormal situation in the equipment operation can be discovered in time, and the equipment operation abnormal data is generated, and the equipment operation abnormal data and the raw material quality exceeding standard data are integrated for abnormal situation, so as to generate abnormal exceeding standard data, which not only includes the abnormal type of the equipment and the quality exceeding standard type of the raw material, but also takes into account the duration of the abnormality, thereby providing a more comprehensive abnormal situation perspective, and helping the production team to quickly respond to equipment failures and raw material quality problems, and reduce the occurrence of production interruptions and quality accidents. At the same time, an in-depth understanding of abnormal situations can optimize maintenance strategies and improve production processes, thereby improving the stability and production efficiency of the production line.

[0029] Preferably, step S4 comprises the following steps:

[0030] Step S41: using sensors to obtain process parameter information;

[0031] Step S42: performing temperature uniformity analysis of the epoxy plate heater and the PTC heater on the process parameter information to generate temperature uniformity data; using the temperature uniformity data to perform heating uniformity impact assessment on the process parameter information to generate heating uniformity impact data;

[0032] Step S43: Analyze the processing time of the epoxy plate heater and the PTC heater according to the process parameter information to generate processing time data; evaluate the impact of the process parameter information on production efficiency using the processing time data to generate production efficiency impact data;

[0033] Step S44: performing surface treatment process control analysis on the epoxy plate heater and the PTC heater based on the process parameter information to generate surface treatment data; using the surface treatment data to evaluate the impact of the process parameter information on surface finish to generate surface finish impact data;

[0034] Step S45: performing process adjustment analysis on the heating uniformity influence data, the production efficiency influence data and the surface finish influence data to obtain process analysis data;

[0035] Step S46: Perform intelligent production control on the process analysis data and abnormal exceeding standard data to generate production control data;

[0036] Step S47: construct a production control strategy model according to the production control data to obtain a production control strategy pre-model; and use the production control data to train the production control strategy pre-model to obtain a production control strategy training model; perform model cross-validation evaluation on the production control strategy training model to obtain production control strategy model evaluation data; adjust model parameters of the production control strategy training model using the production control strategy model evaluation data to obtain a production control strategy model.

[0037] The present invention ensures the real-time acquisition of process parameter information through the application of sensor technology, provides an accurate data basis for subsequent analysis, generates impact assessment data through in-depth analysis of key process parameters such as temperature uniformity, processing time and surface treatment, and is directly related to the heating uniformity, production efficiency and surface finish of the product. Process adjustment analysis requires comprehensive impact data, provides scientific process optimization suggestions for the production process, performs intelligent production control on process analysis data and abnormal exceeding standard data, generates production control data, and makes production control more accurate and dynamic. The generated production control data provides real-time guidance for production decision-making, and constructs a production control strategy model based on the production control data to obtain a production control strategy pre-model, which can be implemented. Now the production process is controlled, and the production control data is used to train the production control strategy pre-model to obtain the production control strategy training model, so that the production control strategy training model can more accurately identify the production control data. The production control strategy training model is cross-validated and evaluated to obtain the production control strategy model evaluation data, which reflects the performance indicators of the production control strategy model and ensures the accuracy and applicability of the strategy model. The model parameters of the production control strategy training model are adjusted through the production control strategy model evaluation data to obtain the production control strategy model, which improves the automation and intelligence level of the production process, and also enhances the flexibility and adaptability of the production system, ultimately achieving the improvement of product quality and the maximization of production efficiency.

[0038] Preferably, step S46 includes the following steps:

[0039] Step S461: Perform periodic analysis on the process analysis data to obtain a process analysis time series trend chart;

[0040] Step S462: Calculate the peak-to-valley difference of the process analysis time series trend chart to obtain process peak-to-valley difference data;

[0041] Step S463: Compare the process peak-to-valley difference data with the preset process parameter standard threshold. When the process peak-to-valley difference data is greater than the preset process parameter standard threshold, adjust the control parameters of the process parameter information to generate a process parameter control adjustment strategy; when the process peak-to-valley difference data is less than or equal to the preset process parameter standard threshold, optimize the process flow of the process parameter information to generate a process flow optimization strategy; integrate the process parameter control adjustment strategy and the process flow optimization strategy to generate a process control rule;

[0042] Step S464: label the abnormal data exceeding the standard to obtain abnormal label data;

[0043] Step S465: performing label classification processing on the abnormal label data to obtain label classification data;

[0044] Step S466: Analyze the production abnormality through label classification data to obtain abnormality cause analysis data; perform abnormal processing and rapid response to the production process according to the abnormality cause analysis data, and generate abnormality control rules;

[0045] Step S467: Intelligently execute control measures for process control rules and abnormal situation control rules to generate production control data.

[0046] The present invention performs periodic analysis on process analysis data, and can accurately capture the periodic change law of the production process of epoxy plate heaters and PTC heaters, and obtain a process analysis time series trend chart. The process analysis time series trend chart helps the production team understand the reasons for process parameter fluctuations. The peak-to-valley difference calculation is performed on the process analysis time series trend chart to obtain process peak-to-valley difference data, which can accurately measure the amplitude and frequency of process fluctuations, determine the intensity and period of process fluctuations, and implement intelligent process control rules by comparing the process peak-to-valley difference data with a preset process parameter standard threshold. When the process peak-to-valley difference data exceeds the preset process parameter standard threshold, the process parameter information is controlled and adjusted to stabilize the process parameters; when the process peak-to-valley difference data is within the expected range, the process flow is optimized to improve efficiency, and the process parameter control adjustment strategy and the process flow optimization strategy are rule-integrated to generate a process control rule. The process control rule integrates the process parameter control adjustment strategy. The dual means of and process flow optimization strategy can quickly adapt to different production conditions and demand changes, effectively improve the production efficiency of epoxy plate heaters and PTC heaters, label the abnormal exceeding data to obtain abnormal label data, classify and mark different types of abnormalities, improve the readability and analysis efficiency of abnormal label data, label the abnormal label data to obtain label classification data, and the label classification data enables the production team to quickly identify common abnormal patterns and provide an important reference for abnormal handling. The production abnormalities are analyzed through the label classification data to obtain abnormal cause analysis data. The abnormal cause analysis data shows the causes of abnormal events in the production process, which is helpful to formulate targeted abnormal handling measures, and the control measures for process control rules and abnormal situation control rules are intelligently executed. It can quickly respond to various changes and challenges in the production process, generate production control data, and can adjust and optimize the production process in real time and respond to abnormal situations.

[0047] Preferably, step S51 includes the following steps:

[0048] Step S51: Real-time physical and chemical property monitoring of raw material quality data is performed through the production control strategy model to obtain real-time monitoring data of raw material quality;

[0049] Step S52: monitoring the equipment operation status in real time through the production control strategy model to obtain real-time monitoring data of the equipment operation;

[0050] Step S53: Real-time processing condition monitoring of process parameter information is performed through the production control strategy model to obtain real-time process monitoring data;

[0051] Step S54: Integrate the real-time monitoring data of raw material quality, the real-time monitoring data of equipment operation and the real-time monitoring data of process to generate a real-time production monitoring report;

[0052] Step S55: Perform early warning analysis on the real-time production monitoring report to obtain early warning information; extract normal production data from the real-time production monitoring report to obtain normal production information.

[0053] The present invention uses a production control strategy model to monitor the physical and chemical properties of raw material quality data in real time to obtain real-time monitoring data of raw material quality, continuously monitors the quality of raw materials to ensure that they meet production needs, thereby avoiding production interruptions caused by material problems, uses a production control strategy model to monitor the real-time operation status of equipment operation information to obtain real-time monitoring data of equipment operation, promptly discovers and handles equipment abnormalities, and reduces the impact of equipment failures on production, uses a production control strategy model to monitor real-time processing conditions of process parameter information to obtain real-time process monitoring data, and ensures the stability of the processing process and product consistency, generates a real-time production monitoring report through real-time monitoring data of raw material quality, real-time monitoring data of equipment operation, and real-time monitoring data of process, provides comprehensive and accurate information support for production decisions, performs early warning analysis on the real-time production monitoring report, obtains early warning information, and enables the production team to identify potential risks in advance, take preventive measures, and reduce production losses; extracts normal production data from the real-time production monitoring report to obtain normal production information, which helps to optimize the production process and improve production efficiency.

[0054] Preferably, step S55 comprises the following steps:

[0055] Step S551: Perform multi-dimensional abnormality analysis on the real-time production monitoring report to obtain real-time multi-dimensional abnormality data;

[0056] Step S552: Performing stage analysis on real-time multi-dimensional abnormal data to obtain real-time abnormal stage data;

[0057] Step S553: ​​performing weight division processing on the real-time abnormal stage data to obtain abnormal stage weight data; performing priority feature extraction on the abnormal stage weight data to generate abnormal stage priority data;

[0058] Step S554: Performing grade scoring according to the abnormal stage priority data to obtain grade scoring data; performing early warning analysis according to the grade scoring data to obtain early warning information;

[0059] Step S555: Identify the normal production status of the real-time production monitoring report to obtain normal production status data; extract production data from the normal production status data to obtain normal production information.

[0060] The present invention performs multi-dimensional abnormal analysis through real-time production monitoring reports, can comprehensively capture abnormal situations in the production process, obtain real-time multi-dimensional abnormal data, perform stage analysis through real-time multi-dimensional abnormal data, and further refine the various stages of abnormal occurrence, so that the problem location is more accurate, and real-time abnormal stage data is obtained. The real-time abnormal stage data is weighted and processed to obtain abnormal stage weight data; priority feature extraction is performed on the abnormal stage weight data to generate abnormal stage priority data. The weight division and priority feature extraction not only highlight the urgency of abnormal processing, but also provide a clear processing order for the production team. Grade scoring is performed according to the abnormal stage priority data to obtain grade scoring data; early warning analysis is performed according to the grade scoring data to obtain early warning information. Through grade scoring and early warning analysis, abnormal situations can be quantitatively evaluated, and early warning information with practical guiding significance is generated, so as to take measures in advance, reduce production interruptions and quality defects, identify the normal production status of the real-time production monitoring report, and obtain normal production status data; extract production data of the normal production status data to ensure the continuity and stability of the production process, obtain normal production information, and provide a reliable reference for production optimization.

[0061] Preferably, step S6 comprises the following steps:

[0062] Step S61: constructing a visualization platform according to the real-time production monitoring report to obtain a real-time production monitoring visualization platform, wherein the real-time production monitoring visualization platform construction includes the construction of a real-time monitoring interface for raw material quality, a real-time monitoring interface for equipment operation, and a real-time monitoring interface for process;

[0063] Step S62: partitioning the data stream based on the real-time production monitoring visualization platform to obtain data stream partitioning information;

[0064] Step S63: Distinguish the warning information and normal production information according to the data stream partition information, and send the warning information and normal production information to the equipment designated by the production team to perform production monitoring operations for epoxy board heaters and PTC heaters.

[0065] The present invention constructs a visualization platform through real-time production monitoring reports to obtain a real-time production monitoring visualization platform, wherein the real-time production monitoring visualization platform construction includes the construction of a real-time monitoring interface for raw material quality, a real-time monitoring interface for equipment operation, and a real-time monitoring interface for process, providing a centralized and intuitive monitoring environment for the production team, making the monitoring data easy to understand and operate, and enhancing the control capability over the production process, performing data stream partitioning based on the real-time production monitoring visualization platform to obtain data stream partitioning information, so that different types of information such as early warning information and normal production information can be clearly distinguished and managed, optimizing the information processing flow, distinguishing early warning information from normal production information through data stream partitioning information, and sending the early warning information and normal production information to the designated equipment of the production team, ensuring the timeliness and accuracy of information transmission, enabling the production team to quickly respond to various situations in production and adjust production strategies in a timely manner to perform production monitoring operations for epoxy plate heaters and PTC heaters.

[0066] In this specification, a production monitoring system based on big data is provided, which is used to execute the above-mentioned production monitoring method based on big data. The production monitoring system based on big data includes:

[0067] The raw material quality data module is used to obtain a raw material data set; perform data preprocessing on the raw material data set to obtain a standard raw material data set; extract quality data of the standard raw material data set to generate raw material quality data;

[0068] The quality status assessment module is used to perform parameter compliance analysis on raw material quality data to obtain quality parameter analysis data; the quality parameter analysis data is marked using the preset standard quality parameter threshold to generate raw material quality exceeding standard data;

[0069] The abnormality and excess data module is used to obtain the equipment operation information on the production line; perform abnormality detection on the equipment operation information to generate equipment operation abnormality data; perform abnormal situation integration on the equipment operation abnormality data and the raw material quality excess data to generate abnormality and excess data;

[0070] The control strategy model module is used to obtain process parameter information; perform process adjustment analysis on the process parameter information to obtain process analysis data; perform intelligent production control on the process analysis data and abnormal exceeding standard data to generate production control data; construct a production control strategy model based on the production control data to obtain a production control strategy model;

[0071] The real-time monitoring module is used to monitor the production process of epoxy plate heaters and PTC heaters in real time based on the raw material quality data, equipment operation information and process parameter information according to the production control strategy model, and generate a real-time production monitoring report; perform early warning analysis on the real-time production monitoring report to obtain early warning information; extract normal production data from the real-time production monitoring report to obtain normal production information;

[0072] The visualization module is used to construct a visualization platform based on the real-time production monitoring report to obtain a real-time production monitoring visualization platform; based on the real-time production monitoring visualization platform, the early warning information and normal production information are sent to the designated equipment of the production team to perform production monitoring operations for epoxy plate heaters and PTC heaters.

[0073] The present invention constructs a production monitoring system based on big data. The raw material quality data module obtains the raw material data set, ensures that the production monitoring system can fully cover all key raw material properties, provides a solid data foundation for subsequent quality control and process optimization, performs data preprocessing on the raw material data set, can significantly improve the accuracy and consistency of the raw material quality data, reduces the deviation caused by different data sources and measurement methods, obtains a standard raw material data set, makes it unnecessary to repeatedly detect the quality of raw materials, improves production efficiency, extracts the quality data of the standard raw material data set, generates raw material quality data, and accurate raw material quality data provides intuitive decision support for production management personnel, which helps to timely discover and solve quality problems. The quality status assessment module performs parameter compliance analysis through the raw material quality data to ensure the high standards and consistency of the raw material quality data, and uses the preset quality parameter threshold for marking, which can timely discover and mark the raw materials that do not meet the standards, thereby avoiding inferior materials from entering the production process, reducing production risks and costs, and the generated raw material quality exceeding standard data provides a direct reference for subsequent quality control and material selection, and enhances the transparency and predictability of the production process. The abnormal exceeding standard data module can realize real-time monitoring of equipment status by acquiring equipment operation information on the production line, detect abnormalities in equipment operation information, generate abnormal equipment operation data, and timely discover and mark abnormal conditions in equipment operation, which helps to prevent production interruptions and equipment failures, reduce downtime and maintenance costs, integrate abnormal equipment operation data and raw material quality exceeding standard data, generate abnormal exceeding standard data, and provide abnormal exceeding standard data for the production process. The control strategy model module can grasp the accuracy of the production process by acquiring process parameter information, providing a data basis for subsequent process optimization, and perform process adjustment analysis on process parameter information to obtain process analysis data to ensure that the production process can be dynamically adjusted according to real-time feedback, thereby improving production efficiency and product quality. It combines process analysis data and abnormal exceeding standard data for intelligent production control, which can respond to various changes in production in a timely manner, generate production control data, and construct a production control strategy model based on production control data to obtain a production control strategy model, which provides scientific and systematic decision support for the production process, making production control more accurate and efficient.The real-time monitoring module monitors the production process of epoxy plate heaters and PTC heaters in real time by applying the production control strategy model to the raw material quality data, equipment operation information and process parameter information, ensuring the continuity of production activities. The real-time production monitoring report is generated to provide the production team with immediate production status feedback, so that production problems can be quickly identified and responded to. The real-time production monitoring report is analyzed for early warning to obtain early warning information, which can inform the production team of production risks and take measures to reduce production interruptions and quality accidents. At the same time, the normal production data of the real-time production monitoring report is extracted to obtain normal production information, which helps the production team to know the current production information, so as to optimize the production process and improve efficiency. The visualization module can significantly improve the intuitiveness and convenience of production monitoring by building a real-time production monitoring visualization platform, so that the production team can intuitively understand complex production data and status through a graphical interface, so as to make decisions more quickly. Based on the real-time production monitoring visualization platform, the early warning information and normal production information are sent to the designated equipment of the production team, ensuring the timeliness and accuracy of information transmission and enhancing the production team's control over the production process. Therefore, the present invention realizes real-time monitoring and early warning of the production process of epoxy board heaters and PTC heaters through Internet of Things technology, machine learning technology, intelligent control technology and visualization technology, thereby reducing the risk of production interruption; and performs intelligent production control on the production process to enhance flexibility and adaptability. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 A schematic diagram of the steps of a production monitoring method based on big data;

[0075] Figure 2 for Figure 1 Detailed implementation steps of step S4 in FIG.

[0076] Figure 3 for Figure 2 Detailed implementation steps of step S46;

[0077] Figure 4 for Figure 1 Detailed implementation steps of step S5;

[0078] Figure 5 for Figure 4 Detailed implementation steps of step S55 are shown in the flowchart.

[0079] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0080] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0081] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0082] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0083] To achieve this, please refer to Figures 1 to 5 , a production monitoring method based on big data, comprising the following steps:

[0084] Step S1: obtaining a raw material data set; performing data preprocessing on the raw material data set to obtain a standard raw material data set; extracting quality data of the standard raw material data set to generate raw material quality data;

[0085] Step S2: Perform parameter compliance analysis on the raw material quality data to obtain quality parameter analysis data; mark the quality parameter analysis data using a preset standard quality parameter threshold to generate raw material quality exceeding standard data;

[0086] Step S3: Acquire equipment operation information on the production line; perform abnormality detection on the equipment operation information to generate equipment operation abnormality data; perform abnormal situation integration on the equipment operation abnormality data and raw material quality exceeding standard data to generate abnormal exceeding standard data;

[0087] Step S4: Acquire process parameter information; perform process adjustment analysis on the process parameter information to obtain process analysis data; perform intelligent production control on the process analysis data and abnormal exceeding standard data to generate production control data; construct a production control strategy model based on the production control data to obtain a production regulation strategy model;

[0088] Step S5: According to the production control strategy model, the raw material quality data, equipment operation information and process parameter information are used to perform real-time monitoring of the production process of epoxy plate heaters and PTC heaters, and a real-time production monitoring report is generated; early warning analysis is performed on the real-time production monitoring report to obtain early warning information; normal production data of the real-time production monitoring report is extracted to obtain normal production information;

[0089] Step S6: construct a visualization platform based on the real-time production monitoring report to obtain a real-time production monitoring visualization platform; send warning information and normal production information to the designated equipment of the production team based on the real-time production monitoring visualization platform to perform production monitoring operations for epoxy plate heaters and PTC heaters.

[0090] The present invention ensures that the production monitoring system can fully cover all key raw material properties by acquiring raw material data sets, providing a solid data foundation for subsequent quality control and process optimization, and performing data preprocessing on raw material data sets, which can significantly improve the accuracy and consistency of raw material quality data, reduce the deviation caused by different data sources and measurement methods, obtain standard raw material data sets, eliminate the need for repeated testing of raw material quality, improve production efficiency, extract quality data of standard raw material data sets, generate raw material quality data, and accurate raw material quality data provide intuitive decision support for production management personnel, which helps to timely discover and solve quality problems. Parameter compliance analysis is performed through raw material quality data to ensure high standards and consistency of raw material quality data, and marking is performed using preset quality parameter thresholds, which can timely discover and mark raw materials that do not meet the standards, thereby avoiding inferior materials from entering the production process, reducing production risks and costs, and the generated raw material quality exceeding standard data provides a direct reference for subsequent quality control and material selection, enhancing the transparency and predictability of the production process. By acquiring the equipment operation information on the production line, the real-time monitoring of the equipment status is realized, the abnormality detection of the equipment operation information is performed, and the abnormal operation data of the equipment is generated. It can timely discover and mark the abnormal conditions in the equipment operation, which helps to prevent production interruptions and equipment failures, reduce downtime and maintenance costs, and integrate the abnormal conditions of equipment operation abnormal data and raw material quality exceeding standard data to generate abnormal exceeding standard data, which provides abnormal exceeding standard data for the production process. By acquiring process parameter information, the accuracy of the process of the production process can be mastered, which provides a data basis for subsequent process optimization. The process parameter information is analyzed for process adjustment to obtain process analysis data to ensure that the production process can be dynamically adjusted according to real-time feedback, thereby improving production efficiency and product quality. Combined with process analysis data and abnormal exceeding standard data for intelligent production control, it can respond to various changes in production in a timely manner, generate production control data, and construct a production control strategy model based on the production control data to obtain a production control strategy model, which provides scientific and systematic decision support for the production process, making production control more accurate and efficient. By applying the production control strategy model, the raw material quality data, equipment operation information and process parameter information are used to monitor the production process of epoxy plate heaters and PTC heaters in real time, ensuring the continuity of production activities. The real-time production monitoring report is generated to provide the production team with instant feedback on the production status, so that production problems can be quickly identified and responded to. The real-time production monitoring report is analyzed for early warning to obtain early warning information. The early warning information can inform the production team of production risks so that measures can be taken to reduce production interruptions and quality accidents. At the same time, the normal production data of the real-time production monitoring report is extracted to obtain normal production information, which helps the production team to know the current production information, thereby optimizing the production process and improving efficiency.By building a real-time production monitoring visualization platform, the intuitiveness and convenience of production monitoring can be significantly improved, so that the production team can intuitively understand complex production data and status through a graphical interface, so as to make decisions more quickly. Based on the real-time production monitoring visualization platform, early warning information and normal production information are sent to the designated equipment of the production team, ensuring the timeliness and accuracy of information transmission, and enhancing the production team's ability to control the production process. Therefore, the present invention realizes real-time monitoring and early warning of the production process of epoxy plate heating plates and PTC heating plates through Internet of Things technology, machine learning technology, intelligent control technology and visualization technology, reducing the risk of production interruption; and intelligent production control of the production process is performed to enhance flexibility and adaptability.

[0091] In the embodiment of the present invention, reference Figure 1 The above is a schematic diagram of the steps of a production monitoring method based on big data of the present invention. In this example, the production monitoring method based on big data includes the following steps:

[0092] Step S1: obtaining a raw material data set; performing data preprocessing on the raw material data set to obtain a standard raw material data set; extracting quality data of the standard raw material data set to generate raw material quality data;

[0093] In an embodiment of the present invention, sensors are used to monitor and record the physical and chemical properties of raw materials in real time, wherein the physical and chemical properties include resistivity, thermal conductivity and density data, to form an original data set, and data preprocessing is performed on the raw material data set, wherein the data preprocessing includes data cleaning to remove invalid or erroneous data, data denoising to reduce measurement errors, and data standardization to unify the formats and units of data from different sources to obtain a standard raw material data set, and key quality-related data are extracted from the preprocessed data set, wherein the quality-related data include chemical composition, physical properties and mechanical properties data, to generate raw material quality data, which provides a basis for subsequent quality control and process optimization.

[0094] Step S2: Perform parameter compliance analysis on the raw material quality data to obtain quality parameter analysis data; mark the quality parameter analysis data using a preset standard quality parameter threshold to generate raw material quality exceeding standard data;

[0095] In an embodiment of the present invention, parameter compliance analysis is performed on raw material quality data, and by comparing the physical and chemical properties of the raw materials with the expected performance indicators, it is determined whether they meet the production requirements. Statistical tools and methods, including variance analysis and hypothesis testing, are used to evaluate whether the mean, distribution and consistency of the raw materials are within an acceptable range. The quality parameter analysis data obtained are judged and marked according to a preset quality parameter threshold. If the quality parameter analysis data exceeds the preset quality parameter threshold, raw material quality exceeding standard data is generated. The raw material quality exceeding standard data lists in detail the unqualified parameters and the degree of deviation, providing a basis for subsequent decision-making and corrective measures.

[0096] Step S3: Acquire equipment operation information on the production line; perform abnormality detection on the equipment operation information to generate equipment operation abnormality data; perform abnormal situation integration on the equipment operation abnormality data and raw material quality exceeding standard data to generate abnormal exceeding standard data;

[0097] In an embodiment of the present invention, sensors are installed at key parts of the equipment to monitor and record equipment operation information, wherein the equipment operation information includes temperature, vibration, current and voltage parameters. Data analysis technologies including machine learning algorithms, deep learning algorithms and rule engine methods are used to perform abnormality detection on the equipment operation information, identify abnormal patterns or deviations in the data, and compare them with baseline data during normal operation to determine whether there is an abnormality. Once an abnormality is detected, equipment operation abnormality data will be generated, and the nature, time and location information of the abnormality will be recorded in detail. The equipment operation abnormality data will be integrated with the raw material quality exceeding standard data. Through data association and analysis technology, the abnormal conditions in the two data sources are compared and associated to identify equipment abnormalities caused by raw material quality problems or raw material processing problems caused by equipment failures. Finally, the generated abnormal exceeding standard data will contain all relevant abnormal information.

[0098] Step S4: Acquire process parameter information; perform process adjustment analysis on the process parameter information to obtain process analysis data; perform intelligent production control on the process analysis data and abnormal exceeding standard data to generate production control data; construct a production control strategy model based on the production control data to obtain a production regulation strategy model;

[0099] In an embodiment of the present invention, process parameter information is obtained through sensors in a production system, wherein the process parameter information includes material ratio, rheological properties and heating rate, and the process parameter information is a key factor in product quality. After obtaining the process parameter information, a process adjustment analysis is performed, and the impact of the current process parameter settings on the production process is evaluated through statistical methods and machine learning algorithms, and process adjustment improvement points are identified, wherein the process adjustment improvement points include adjusting the heating temperature to optimize the curing process and changing the pressure to improve the molding quality, and process analysis data is obtained. Through integrated control algorithms, such as fuzzy logic and neural networks, the process analysis data is combined with previously generated abnormal exceeding standard data to perform intelligent production control, dynamically adjust production equipment and process flow to respond to monitored abnormal conditions, and generate production control data, wherein the intelligent production control includes, if it is detected that the quality of raw materials exceeds the standard, automatically adjusting the processing parameters to compensate for quality problems and adjusting the production speed to ensure that the final product meets the specifications. Finally, based on the generated production control data, a production control strategy model is constructed, so that the production process can achieve higher flexibility and adaptability, ensuring that optimal performance can be maintained under various conditions.

[0100] Step S5: According to the production control strategy model, the raw material quality data, equipment operation information and process parameter information are used to perform real-time monitoring of the production process of epoxy plate heaters and PTC heaters, and a real-time production monitoring report is generated; early warning analysis is performed on the real-time production monitoring report to obtain early warning information; normal production data of the real-time production monitoring report is extracted to obtain normal production information;

[0101] In an embodiment of the present invention, the key elements of the production process of epoxy plate heaters and PTC heaters are monitored in real time through a production control strategy model to generate a real-time production monitoring report, wherein the real-time production monitoring report records in detail the real-time data of raw material quality data, equipment operation information and process parameter information, and the real-time production monitoring report is subjected to in-depth early warning analysis through pattern recognition technology to identify potential risks and problems, obtain early warning information, and classify the early warning information according to severity and urgency, extract normal production data from the real-time production monitoring report to obtain normal production information, and the normal production information is used to confirm when the production process is within the control range to ensure production stability and product quality.

[0102] Step S6: construct a visualization platform based on the real-time production monitoring report to obtain a real-time production monitoring visualization platform; send warning information and normal production information to the designated equipment of the production team based on the real-time production monitoring visualization platform to perform production monitoring operations for epoxy plate heaters and PTC heaters.

[0103] In an embodiment of the present invention, a visualization platform is constructed based on the real-time production monitoring report, and data visualization tools and techniques, including charts, dashboards, and real-time data streams, are used to convert the data in the real-time production monitoring report into a graphical interface to obtain a real-time production monitoring visualization platform. Based on the real-time production monitoring visualization platform, early warning information and normal production information can be transmitted to the designated equipment of the production team via a wired or wireless network, wherein the designated equipment of the production team includes mobile devices and personal computers, thereby ensuring that the production team can receive the latest production status in real time to perform production monitoring operations of epoxy board heaters and PTC heaters.

[0104] Preferably, step S1 comprises the following steps:

[0105] Step S11: using sensors to obtain a raw material data set;

[0106] Step S12: performing data preprocessing on the raw material data set to obtain a standard raw material data set, wherein the data preprocessing includes data decryption, data cleaning, data denoising and data standardization;

[0107] Step S13: performing quality feature identification on the standard raw material data set to obtain quality feature information; performing quality data screening on the standard raw material data set according to the quality feature information to generate raw material quality data.

[0108] In an embodiment of the present invention, sensors are deployed in raw material storage or processing areas to monitor and record key physical and chemical properties of raw materials in real time, such as resistivity, thermal conductivity and density data. The collected raw data is preprocessed. First, data decryption is performed to ensure the security of data during transmission and storage. Next, data cleaning is performed to remove invalid or erroneous data, such as missing values ​​or outliers. Then, data denoising is performed to reduce the noise generated during the measurement process and improve the accuracy of the data. Finally, data standardization is performed to convert data in different formats and units into a unified format to obtain a standard raw material data set. Data analysis tools such as statistical analysis and machine learning algorithms are used to identify quality features of the standard raw material data set, extract key quality features from the standard raw material data set, and obtain quality feature information, wherein the quality feature information includes chemical composition, physical properties and mechanical properties. According to these quality feature information, the data set is further screened for quality data, raw materials that meet production requirements are identified, and raw material quality data is generated.

[0109] Preferably, step S2 comprises the following steps:

[0110] Step S21: extracting characteristic values ​​of raw material quality data to obtain quality characteristic values, wherein the quality characteristic values ​​include chemical composition data, physical property data and mechanical property data of the raw material;

[0111] Step S22: performing weighted average calculation on the raw material chemical composition data, physical property data and mechanical property data to generate weighted average quality data;

[0112] Step S23: performing parameter compliance analysis on the weighted average quality data to obtain quality parameter analysis data;

[0113] Step S24: Compare the quality parameter analysis data with the preset standard quality parameter threshold. When the quality parameter analysis data is less than or equal to the preset standard quality parameter threshold, the quality parameter analysis data is recorded normally; when the quality parameter analysis data is greater than the preset standard quality parameter threshold, the quality parameter analysis data is marked as abnormal and raw material quality exceeding standard data is generated.

[0114] In an embodiment of the present invention, by extracting key quality characteristic values ​​from raw material quality data, wherein the quality characteristic values ​​include raw material chemical composition data, physical property data and mechanical property data, more specifically element content, specific gravity, melting point, hardness and tensile strength, the raw material chemical composition data, physical property data and mechanical property data are weighted averaged to generate weighted average quality data, the weighting process considers the importance of different characteristics on the quality of the final product, and calculates the comprehensive influence of each characteristic by assigning different weights, including for epoxy board heater, more attention is paid to thermal stability and resistivity, and for PTC heater, more attention is paid to the characteristics of resistance changing with temperature, the generated weighted average quality data is subjected to parameter compliance analysis through variance analysis and hypothesis testing, and by comparing the weighted average value with the standard specified in the material specification, it is determined whether the raw materials meet the production requirements, so as to evaluate the consistency and compliance of the data, and obtain quality parameter analysis data, and compare the quality parameter analysis data with the preset standard quality parameter threshold, if the quality parameter analysis data is within the threshold range, it indicates that the raw material quality is qualified, and these data are recorded normally. On the contrary, if the quality parameter analysis data exceeds the threshold, it will be marked as abnormal and raw material quality exceeding standard data will be generated.

[0115] Preferably, step S3 comprises the following steps:

[0116] Step S31: using sensors to obtain equipment operation information on the production line;

[0117] Step S32: extracting the working characteristics of the equipment operation information and generating a working characteristic vector of the equipment operation;

[0118] Step S33: performing abnormality detection on the equipment operation feature vector to generate equipment operation abnormality data;

[0119] Step S34: abnormal situation integration is performed on the equipment operation abnormality data and the raw material quality exceeding standard data to generate abnormal situation exceeding standard data, wherein the abnormal situation integration includes the type of equipment operation abnormality, the type of raw material quality exceeding standard and the duration of the abnormality.

[0120] In an embodiment of the present invention, by deploying sensors at key parts of the motor, bearing and heating element of the equipment, the equipment operation information is obtained in real time, wherein the equipment operation information includes temperature, vibration, current and voltage, and the working characteristics of the equipment operation information are extracted, wherein the working characteristics include the working cycle of the equipment, load change and energy consumption mode. By using signal processing technology, such as Fourier transform and wavelet transform, the equipment operation information is converted into a working characteristic vector, and the working characteristic vector can represent the typical mode of equipment operation. Through anomaly detection algorithms, such as machine learning models or statistical threshold methods, these equipment operation working characteristic vectors are subjected to anomaly detection. By comparing the current characteristic vector with the characteristic vector under the normal operating state, the deviation from the normal mode is identified, thereby generating equipment operation abnormality data, integrating, correlating and analyzing the equipment operation abnormality data with the raw material quality exceeding standard data, and recording the types of equipment operation abnormalities, the types of raw material quality exceeding standard, and the duration of these abnormalities. Through this integration, the generated abnormal exceeding standard data provides a comprehensive and integrated abnormal situation data for the production team, which is convenient for fault diagnosis and production adjustment.

[0121] As an example of the present invention, refer to Figure 2 As shown, in this example, step S4 includes:

[0122] Step S41: using sensors to obtain process parameter information;

[0123] Step S42: performing temperature uniformity analysis of the epoxy plate heater and the PTC heater on the process parameter information to generate temperature uniformity data; using the temperature uniformity data to perform heating uniformity impact assessment on the process parameter information to generate heating uniformity impact data;

[0124] Step S43: Analyze the processing time of the epoxy plate heater and the PTC heater according to the process parameter information to generate processing time data; evaluate the impact of the process parameter information on production efficiency using the processing time data to generate production efficiency impact data;

[0125] Step S44: performing surface treatment process control analysis on the epoxy plate heater and the PTC heater based on the process parameter information to generate surface treatment data; using the surface treatment data to evaluate the impact of the process parameter information on surface finish to generate surface finish impact data;

[0126] Step S45: performing process adjustment analysis on the heating uniformity influence data, the production efficiency influence data and the surface finish influence data to obtain process analysis data;

[0127] Step S46: Perform intelligent production control on the process analysis data and abnormal exceeding standard data to generate production control data;

[0128] Step S47: construct a production control strategy model according to the production control data to obtain a production control strategy pre-model; and use the production control data to train the production control strategy pre-model to obtain a production control strategy training model; perform model cross-validation evaluation on the production control strategy training model to obtain production control strategy model evaluation data; adjust model parameters of the production control strategy training model using the production control strategy model evaluation data to obtain a production control strategy model.

[0129] In the embodiment of the present invention, sensor technology is used to capture the process parameters in the production process of epoxy plate heating sheet and PTC heating sheet, wherein the process parameter information includes material ratio, rheological properties and heating rate, and the process parameter information is subjected to temperature uniformity analysis, and temperature uniformity data is generated by comparing the measured values ​​at different positions or time periods, and the temperature uniformity data is used to evaluate the influence of heating uniformity on product quality, and heating uniformity influence data is generated, and processing time data is generated by recording and analyzing the time required to produce each component, and the processing time data is used to evaluate production efficiency and generate production efficiency influence data, and surface treatment data is generated by monitoring and analyzing process parameters related to surface treatment. Surface finish is evaluated by surface treatment data, and surface finish influence data is generated, and heating uniformity influence data, production efficiency influence data and surface finish influence data are combined to perform process adjustment analysis, help the production team determine how to adjust process parameters to optimize the production process, and generate process analysis data, and by combining process analysis data with abnormal exceeding standard data, intelligent production control is performed to generate production control data. Production control strategy model is constructed according to production control data, and first, a pre-model is generated according to production control data. Then, the pre-model is trained using production control data. During the training process, the parameters of the model are continuously optimized through the back propagation algorithm to minimize the error between the predicted output and the actual output. The model contains multiple hidden layers, each with several neurons. Each neuron processes the input signal through an activation function, such as ReLU (Rectified Linear Unit) or Sigmoid function. After the training is completed, the model is cross-validated and evaluated. The model is trained using the training set and the model performance is evaluated on the validation set. The evaluation indicators include accuracy, recall, F1 score and mean square error (MSE). According to the evaluation data, the parameters of the training model are adjusted, and the adjustment operation includes adjusting the learning rate; increasing or decreasing the number of neurons in the hidden layer, changing the activation function and optimization algorithm, so as to improve the generalization ability of the model. The adjusted model is trained and evaluated again until it reaches a satisfactory performance standard. Finally, the obtained production control strategy model can dynamically adjust the production process according to real-time input data, generate production control data, and guide the automatic adjustment of production equipment and process parameters.

[0130] As an example of the present invention, refer to Figure 3 As shown, in this example, step S46 includes:

[0131] Step S461: Perform periodic analysis on the process analysis data to obtain a process analysis time series trend chart;

[0132] Step S462: Calculate the peak-to-valley difference of the process analysis time series trend chart to obtain process peak-to-valley difference data;

[0133] Step S463: Compare the process peak-to-valley difference data with the preset process parameter standard threshold. When the process peak-to-valley difference data is greater than the preset process parameter standard threshold, adjust the control parameters of the process parameter information to generate a process parameter control adjustment strategy; when the process peak-to-valley difference data is less than or equal to the preset process parameter standard threshold, optimize the process flow of the process parameter information to generate a process flow optimization strategy; integrate the process parameter control adjustment strategy and the process flow optimization strategy to generate a process control rule;

[0134] Step S464: label the abnormal data exceeding the standard to obtain abnormal label data;

[0135] Step S465: performing label classification processing on the abnormal label data to obtain label classification data;

[0136] Step S466: Analyze the production abnormality through label classification data to obtain abnormality cause analysis data; perform abnormal processing and rapid response to the production process according to the abnormality cause analysis data, and generate abnormality control rules;

[0137] Step S467: Intelligently execute control measures for process control rules and abnormal situation control rules to generate production control data.

[0138] In an embodiment of the present invention, a periodic analysis is performed on the process analysis data through a time series analysis method, such as moving average or exponential smoothing, to generate a process analysis time series trend chart. The process analysis time series trend chart can show the changes in process parameters over time and provide a visual reference for further analysis. It is usually completed by identifying the highest point (peak) and the lowest point (valley) in the trend chart, performing peak-to-valley difference calculation on the generated process analysis time series trend chart, and calculating the difference between them to obtain process peak-to-valley difference data. The process peak-to-valley difference data is compared with a preset process parameter standard threshold. If the peak-to-valley difference is greater than the threshold, it indicates that the process parameter fluctuation exceeds an acceptable range and the control parameter needs to be adjusted. At this time, a process parameter control adjustment strategy is generated, wherein the process parameter control adjustment strategy includes changing the heating rate and adjusting the pressure setting. If the peak-to-valley difference is less than or equal to the threshold, a process flow optimization strategy is generated. The process flow optimization strategy includes improving material ratios and optimizing equipment operation sequence. The process parameter control adjustment strategy and the process flow optimization strategy are rule-integrated to generate process control rules. The abnormal data exceeding the standard are labeled to generate abnormal label data, where the abnormal label data includes "temperature exceeding the standard" and "pressure abnormality", which are used to quickly identify and classify the abnormal types. The abnormal label data are classified to generate label classification data, which helps to classify similar abnormal situations into one category, facilitate pattern recognition and cause analysis, and conduct in-depth analysis of production abnormalities through label classification data to obtain abnormal cause analysis data. The abnormal cause analysis data helps to identify the root causes of the abnormalities, such as equipment failure, operating errors and material defects. According to the process control rules and abnormal situation control rules, control measures are intelligently executed, where the intelligent execution of control measures includes automatically adjusting equipment parameters or reminding operators to intervene manually, generating production control data, and ensuring the stability of the production process and product quality.

[0139] As an example of the present invention, refer to Figure 4 As shown, in this example, step S5 includes:

[0140] Step S51: Real-time physical and chemical property monitoring of raw material quality data is performed through the production control strategy model to obtain real-time monitoring data of raw material quality;

[0141] Step S52: monitoring the equipment operation status in real time through the production control strategy model to obtain real-time monitoring data of the equipment operation;

[0142] Step S53: Real-time processing condition monitoring of process parameter information is performed through the production control strategy model to obtain real-time process monitoring data;

[0143] Step S54: Integrate the real-time monitoring data of raw material quality, the real-time monitoring data of equipment operation and the real-time monitoring data of process to generate a real-time production monitoring report;

[0144] Step S55: Perform early warning analysis on the real-time production monitoring report to obtain early warning information; extract normal production data from the real-time production monitoring report to obtain normal production information.

[0145] In an embodiment of the present invention, the physical and chemical properties of raw material quality data are monitored in real time through the production control strategy model, wherein the physical and chemical properties of the raw material quality data include key parameters such as resistivity, thermal conductivity and density, which are captured by sensors and input into the model to generate real-time monitoring data of raw material quality. The equipment operation information is monitored in real time through the production control strategy model, wherein the equipment operation status data includes temperature, vibration and speed, which are captured by sensors and input into the model to obtain real-time monitoring data of equipment operation. The process parameter information is monitored in real time through the production control strategy model, wherein the process processing conditions include material ratio, rheological properties and heating rate, which are captured by sensors and input into the model to obtain real-time monitoring data of the process. Through data fusion algorithm technology, the real-time monitoring data of raw material quality, the real-time monitoring data of equipment operation and the real-time monitoring data of process are integrated to generate a comprehensive real-time production monitoring report. Through the analysis algorithm, the real-time production monitoring report is analyzed for early warning to identify abnormalities or risks and generate early warning information. At the same time, the production data within the normal range of the report is extracted to form normal production information, wherein the normal production information includes raw material parameters, equipment operation status and process conditions that meet the standards, providing a real-time production status reference for the production team.

[0146] As an example of the present invention, refer to Figure 5 As shown, in this example, step S55 includes:

[0147] Step S551: Perform multi-dimensional abnormality analysis on the real-time production monitoring report to obtain real-time multi-dimensional abnormality data;

[0148] Step S552: Performing stage analysis on real-time multi-dimensional abnormal data to obtain real-time abnormal stage data;

[0149] Step S553: ​​performing weight division processing on the real-time abnormal stage data to obtain abnormal stage weight data; performing priority feature extraction on the abnormal stage weight data to generate abnormal stage priority data;

[0150] Step S554: Performing grade scoring according to the abnormal stage priority data to obtain grade scoring data; performing early warning analysis according to the grade scoring data to obtain early warning information;

[0151] Step S555: Identify the normal production status of the real-time production monitoring report to obtain normal production status data; extract production data from the normal production status data to obtain normal production information.

[0152] In the embodiment of the present invention, a machine learning algorithm and a deep learning algorithm are used to perform multi-dimensional anomaly analysis on the real-time production monitoring report, identify abnormal values ​​that deviate from the normal mode from the monitoring data, and generate real-time multi-dimensional abnormal data, wherein the multi-dimensional anomaly analysis takes into account multiple dimensions such as raw material properties, equipment performance, and process parameters. Through time series analysis, the real-time multi-dimensional abnormal data is used to identify abnormal patterns at specific stages in the production process, and real-time abnormal stage data is generated. According to the severity of the impact of the abnormality on production, the real-time abnormal stage data is weighted and processed, and a weight value is assigned to each abnormal event. The determination of the weight value can be achieved by the production team, historical data analysis, or preset rules, and the abnormal stage data is obtained. The abnormal stage weight data is used to extract priority features from the abnormal stage weight data to generate abnormal stage priority data, and grade scoring is performed based on the abnormal stage priority data. By setting scoring rules, such as the frequency, duration, and impact range of the abnormality, a grade score is assigned to each abnormality to obtain grade scoring data. Using the grade scoring data, early warning analysis is performed to generate early warning information. By setting the standards and thresholds for normal production, the normal production status in the real-time production monitoring report is identified to obtain normal production status data, and detailed information in the normal production status data, including production speed, output, and quality indicators, is further extracted to obtain normal production information, providing the production team with positive feedback and confirmation of the production process.

[0153] Preferably, step S6 comprises the following steps:

[0154] Step S61: constructing a visualization platform according to the real-time production monitoring report to obtain a real-time production monitoring visualization platform, wherein the real-time production monitoring visualization platform construction includes the construction of a real-time monitoring interface for raw material quality, a real-time monitoring interface for equipment operation, and a real-time monitoring interface for process;

[0155] Step S62: partitioning the data stream based on the real-time production monitoring visualization platform to obtain data stream partitioning information;

[0156] Step S63: Distinguish the warning information and normal production information according to the data stream partition information, and send the warning information and normal production information to the equipment designated by the production team to perform production monitoring operations for epoxy board heaters and PTC heaters.

[0157] In an embodiment of the present invention, a visualization platform is constructed through real-time production monitoring reports, and data visualization tools and techniques are used to obtain a real-time production monitoring visualization platform, wherein the construction of the real-time production monitoring visualization platform includes the construction of a real-time monitoring interface for raw material quality, a real-time monitoring interface for equipment operation, and a real-time monitoring interface for process. Based on the real-time production monitoring visualization platform, the data of the real-time production monitoring report is classified according to different types, sources, and importance, and the data stream partition information is obtained, and logical grouping is performed in the visualization interface. The data stream partition information guides how the data is displayed in different interfaces and modules to ensure that the organization and presentation of information meet the needs of the production team. According to the data stream partition information, the warning information and normal production information generated in the monitoring report are distinguished and processed, wherein the warning information includes raw material quality problems, equipment operation abnormalities, and process parameter deviation information. The warning information is highlighted in the interface through highlighting or specific icons, while the normal production information reflects the conventional data and status in the production process, the parameters that meet the standards, and the equipment status that runs smoothly. Finally, the warning information and normal production information are sent to the designated equipment of the production team via wireless or wired networks, where the designated equipment includes mobile devices and personal computers, to ensure that the production team can receive key production monitoring information in a timely manner and perform corresponding epoxy board heater and PTC heater production monitoring operations accordingly.

[0158] In this specification, a production monitoring system based on big data is provided, which is used to execute the above-mentioned production monitoring method based on big data. The production monitoring system based on big data includes:

[0159] The raw material quality data module is used to obtain a raw material data set; perform data preprocessing on the raw material data set to obtain a standard raw material data set; extract quality data of the standard raw material data set to generate raw material quality data;

[0160] The quality status assessment module is used to perform parameter compliance analysis on raw material quality data to obtain quality parameter analysis data; the quality parameter analysis data is marked using the preset standard quality parameter threshold to generate raw material quality exceeding standard data;

[0161] The abnormality and excess data module is used to obtain the equipment operation information on the production line; perform abnormality detection on the equipment operation information to generate equipment operation abnormality data; perform abnormal situation integration on the equipment operation abnormality data and the raw material quality excess data to generate abnormality and excess data;

[0162] The control strategy model module is used to obtain process parameter information; perform process adjustment analysis on the process parameter information to obtain process analysis data; perform intelligent production control on the process analysis data and abnormal exceeding standard data to generate production control data; construct a production control strategy model based on the production control data to obtain a production control strategy model;

[0163] The real-time monitoring module is used to monitor the production process of epoxy plate heaters and PTC heaters in real time based on the raw material quality data, equipment operation information and process parameter information according to the production control strategy model, and generate a real-time production monitoring report; perform early warning analysis on the real-time production monitoring report to obtain early warning information; extract normal production data from the real-time production monitoring report to obtain normal production information;

[0164] The visualization module is used to construct a visualization platform based on the real-time production monitoring report to obtain a real-time production monitoring visualization platform; based on the real-time production monitoring visualization platform, the early warning information and normal production information are sent to the designated equipment of the production team to perform production monitoring operations for epoxy plate heaters and PTC heaters.

[0165] The present invention constructs a production monitoring system based on big data. The raw material quality data module obtains the raw material data set, ensures that the production monitoring system can fully cover all key raw material properties, provides a solid data foundation for subsequent quality control and process optimization, performs data preprocessing on the raw material data set, can significantly improve the accuracy and consistency of the raw material quality data, reduces the deviation caused by different data sources and measurement methods, obtains a standard raw material data set, makes it unnecessary to repeatedly detect the quality of raw materials, improves production efficiency, extracts the quality data of the standard raw material data set, generates raw material quality data, and accurate raw material quality data provides intuitive decision support for production management personnel, which helps to timely discover and solve quality problems. The quality status assessment module performs parameter compliance analysis through the raw material quality data to ensure the high standards and consistency of the raw material quality data, and uses the preset quality parameter threshold for marking, which can timely discover and mark the raw materials that do not meet the standards, thereby avoiding inferior materials from entering the production process, reducing production risks and costs, and the generated raw material quality exceeding standard data provides a direct reference for subsequent quality control and material selection, and enhances the transparency and predictability of the production process. The abnormal exceeding standard data module can realize real-time monitoring of equipment status by acquiring equipment operation information on the production line, detect abnormalities in equipment operation information, generate abnormal equipment operation data, and timely discover and mark abnormal conditions in equipment operation, which helps to prevent production interruptions and equipment failures, reduce downtime and maintenance costs, integrate abnormal equipment operation data and raw material quality exceeding standard data, generate abnormal exceeding standard data, and provide abnormal exceeding standard data for the production process. The control strategy model module can grasp the accuracy of the production process by acquiring process parameter information, providing a data basis for subsequent process optimization, and perform process adjustment analysis on process parameter information to obtain process analysis data to ensure that the production process can be dynamically adjusted according to real-time feedback, thereby improving production efficiency and product quality. It combines process analysis data and abnormal exceeding standard data for intelligent production control, which can respond to various changes in production in a timely manner, generate production control data, and construct a production control strategy model based on production control data to obtain a production control strategy model, which provides scientific and systematic decision support for the production process, making production control more accurate and efficient.The real-time monitoring module monitors the production process of epoxy plate heaters and PTC heaters in real time by applying the production control strategy model to the raw material quality data, equipment operation information and process parameter information, ensuring the continuity of production activities. The real-time production monitoring report is generated to provide the production team with immediate production status feedback, so that production problems can be quickly identified and responded to. The real-time production monitoring report is analyzed for early warning to obtain early warning information, which can inform the production team of production risks and take measures to reduce production interruptions and quality accidents. At the same time, the normal production data of the real-time production monitoring report is extracted to obtain normal production information, which helps the production team to know the current production information, so as to optimize the production process and improve efficiency. The visualization module can significantly improve the intuitiveness and convenience of production monitoring by building a real-time production monitoring visualization platform, so that the production team can intuitively understand complex production data and status through a graphical interface, so as to make decisions more quickly. Based on the real-time production monitoring visualization platform, the early warning information and normal production information are sent to the designated equipment of the production team, ensuring the timeliness and accuracy of information transmission and enhancing the production team's control over the production process. Therefore, the present invention realizes real-time monitoring and early warning of the production process of epoxy board heaters and PTC heaters through Internet of Things technology, machine learning technology, intelligent control technology and visualization technology, thereby reducing the risk of production interruption; and performs intelligent production control on the production process to enhance flexibility and adaptability.

[0166] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0167] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A production monitoring method based on big data, characterized in that: The following steps are involved: Step S1: Obtain raw material data set; Preprocessing the raw material data set to obtain a standard raw material data set; extracting quality data of the standard raw material data set to generate raw material quality data; Step S2: Perform parameter compliance analysis on the raw material quality data to obtain quality parameter analysis data; mark the quality parameter analysis data using a preset standard quality parameter threshold to generate raw material quality exceeding standard data; Step S3: Obtaining equipment operation information on the production line; Perform abnormal detection on equipment operation information and generate equipment operation abnormality data; Integrate abnormal data on equipment operation and data on raw material quality exceeding standards to generate abnormal exceeding standards data; Step S4: obtaining process parameter information; Conduct process adjustment analysis on process parameter information to obtain process analysis data; Conduct intelligent production control on process analysis data and abnormal exceeding standard data to generate production control data; The production control strategy model is constructed according to the production control data to obtain the production regulation strategy model; step S4 includes the following steps: Step S41: using sensors to obtain process parameter information; Step S42: performing temperature uniformity analysis of the epoxy plate heater and the PTC heater on the process parameter information to generate temperature uniformity data; using the temperature uniformity data to perform heating uniformity impact assessment on the process parameter information to generate heating uniformity impact data; Step S43: Analyze the processing time of the epoxy plate heater and the PTC heater according to the process parameter information to generate processing time data; evaluate the impact of the process parameter information on production efficiency using the processing time data to generate production efficiency impact data; Step S44: performing surface treatment process control analysis on the epoxy plate heater and the PTC heater based on the process parameter information to generate surface treatment data; using the surface treatment data to evaluate the impact of the process parameter information on surface finish to generate surface finish impact data; Step S45: performing process adjustment analysis on the heating uniformity influence data, the production efficiency influence data and the surface finish influence data to obtain process analysis data; Step S46: Perform intelligent production control on the process analysis data and the abnormal exceeding standard data to generate production control data; wherein step S46 includes: Step S461: Perform periodic analysis on the process analysis data to obtain a process analysis time series trend chart; Step S462: Calculate the peak-to-valley difference of the process analysis time series trend chart to obtain process peak-to-valley difference data; Step S463: Compare the process peak-to-valley difference data with the preset process parameter standard threshold. When the process peak-to-valley difference data is greater than the preset process parameter standard threshold, adjust the control parameters of the process parameter information to generate a process parameter control adjustment strategy; when the process peak-to-valley difference data is less than or equal to the preset process parameter standard threshold, optimize the process flow of the process parameter information to generate a process flow optimization strategy; integrate the process parameter control adjustment strategy and the process flow optimization strategy to generate a process control rule; Step S464: label the abnormal data exceeding the standard to obtain abnormal label data; Step S465: performing label classification processing on the abnormal label data to obtain label classification data; Step S466: Analyze the production abnormality through label classification data to obtain abnormality cause analysis data; perform abnormal processing and rapid response to the production process according to the abnormality cause analysis data, and generate abnormality control rules; Step S467: intelligently executing control measures for process control rules and abnormal situation control rules to generate production control data; Step S47: constructing a production control strategy model according to the production control data to obtain a production control strategy pre-model; and using the production control data to perform model training on the production control strategy pre-model to obtain a production control strategy training model; performing model cross-validation evaluation on the production control strategy training model to obtain production control strategy model evaluation data; adjusting model parameters of the production control strategy training model using the production control strategy model evaluation data to obtain a production control strategy model; Step S5: According to the production control strategy model, the raw material quality data, equipment operation information and process parameter information are used to perform real-time monitoring of the production process of epoxy plate heaters and PTC heaters, and a real-time production monitoring report is generated; the real-time production monitoring report is used for early warning analysis to obtain early warning information; the normal production data of the real-time production monitoring report is extracted to obtain normal production information; wherein, step S5 includes: Step S51: Real-time physical and chemical property monitoring of raw material quality data is performed through the production control strategy model to obtain real-time monitoring data of raw material quality; Step S52: monitoring the equipment operation status in real time through the production control strategy model to obtain real-time monitoring data of the equipment operation; Step S53: Real-time processing condition monitoring of process parameter information is performed through the production control strategy model to obtain real-time process monitoring data; Step S54: Integrate the real-time monitoring data of raw material quality, the real-time monitoring data of equipment operation and the real-time monitoring data of process to generate a real-time production monitoring report; Step S55: Perform early warning analysis on the real-time production monitoring report to obtain early warning information; extract normal production data from the real-time production monitoring report to obtain normal production information; wherein step S55 includes: Step S551: Perform multi-dimensional abnormality analysis on the real-time production monitoring report to obtain real-time multi-dimensional abnormality data; Step S552: Performing stage analysis on real-time multi-dimensional abnormal data to obtain real-time abnormal stage data; Step S553: ​​performing weight division processing on the real-time abnormal stage data to obtain abnormal stage weight data; performing priority feature extraction on the abnormal stage weight data to generate abnormal stage priority data; Step S554: Performing grade scoring according to the abnormal stage priority data to obtain grade scoring data; performing early warning analysis according to the grade scoring data to obtain early warning information; Step S555: identifying the normal production status of the real-time production monitoring report to obtain normal production status data; extracting production data of the normal production status data to obtain normal production information; Step S6: construct a visualization platform based on the real-time production monitoring report to obtain a real-time production monitoring visualization platform; send warning information and normal production information to the designated equipment of the production team based on the real-time production monitoring visualization platform to perform production monitoring operations for epoxy plate heaters and PTC heaters.

2. The production monitoring method based on big data according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: using sensors to obtain a raw material data set; Step S12: performing data preprocessing on the raw material data set to obtain a standard raw material data set, wherein the data preprocessing includes data decryption, data cleaning, data denoising and data standardization; Step S13: performing quality feature identification on the standard raw material data set to obtain quality feature information; performing quality data screening on the standard raw material data set according to the quality feature information to generate raw material quality data.

3. The production monitoring method based on big data according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: extracting characteristic values ​​of raw material quality data to obtain quality characteristic values, wherein the quality characteristic values ​​include chemical composition data, physical property data and mechanical property data of the raw material; Step S22: performing weighted average calculation on the raw material chemical composition data, physical property data and mechanical property data to generate weighted average quality data; Step S23: performing parameter compliance analysis on the weighted average quality data to obtain quality parameter analysis data; Step S24: Compare the quality parameter analysis data with the preset standard quality parameter threshold. When the quality parameter analysis data is less than or equal to the preset standard quality parameter threshold, the quality parameter analysis data is recorded normally; when the quality parameter analysis data is greater than the preset standard quality parameter threshold, the quality parameter analysis data is marked as abnormal and raw material quality exceeding standard data is generated.

4. The production monitoring method based on big data according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: using sensors to obtain equipment operation information on the production line; Step S32: extracting the working characteristics of the equipment operation information and generating a working characteristic vector of the equipment operation; Step S33: performing abnormality detection on the equipment operation feature vector to generate equipment operation abnormality data; Step S34: abnormal situation integration is performed on the equipment operation abnormality data and the raw material quality exceeding standard data to generate abnormal situation exceeding standard data, wherein the abnormal situation integration includes the type of equipment operation abnormality, the type of raw material quality exceeding standard and the duration of the abnormality.

5. The production monitoring method based on big data according to claim 1, characterized in that: Step S6 includes the following steps: Step S61: constructing a visualization platform according to the real-time production monitoring report to obtain a real-time production monitoring visualization platform, wherein the real-time production monitoring visualization platform construction includes the construction of a real-time monitoring interface for raw material quality, a real-time monitoring interface for equipment operation, and a real-time monitoring interface for process; Step S62: partitioning the data stream based on the real-time production monitoring visualization platform to obtain data stream partitioning information; Step S63: Distinguish the warning information and normal production information according to the data stream partition information, and send the warning information and normal production information to the equipment designated by the production team to perform production monitoring operations for epoxy board heaters and PTC heaters.

6. A production monitoring system based on big data, characterized in that: Used to execute the production monitoring method based on big data as claimed in claim 1, the production monitoring system based on big data comprises: The raw material quality data module is used to obtain a raw material data set; perform data preprocessing on the raw material data set to obtain a standard raw material data set; extract quality data of the standard raw material data set to generate raw material quality data; The quality status assessment module is used to perform parameter compliance analysis on raw material quality data to obtain quality parameter analysis data; the quality parameter analysis data is marked using the preset standard quality parameter threshold to generate raw material quality exceeding standard data; The abnormality and excess data module is used to obtain the equipment operation information on the production line; perform abnormality detection on the equipment operation information to generate equipment operation abnormality data; perform abnormal situation integration on the equipment operation abnormality data and the raw material quality excess data to generate abnormality and excess data; The control strategy model module is used to obtain process parameter information; perform process adjustment analysis on the process parameter information to obtain process analysis data; perform intelligent production control on the process analysis data and abnormal exceeding standard data to generate production control data; construct a production control strategy model based on the production control data to obtain a production control strategy model; The real-time monitoring module is used to monitor the production process of epoxy plate heaters and PTC heaters in real time based on the raw material quality data, equipment operation information and process parameter information according to the production control strategy model, and generate a real-time production monitoring report; perform early warning analysis on the real-time production monitoring report to obtain early warning information; extract normal production data from the real-time production monitoring report to obtain normal production information; The visualization module is used to construct a visualization platform based on the real-time production monitoring report to obtain a real-time production monitoring visualization platform; based on the real-time production monitoring visualization platform, the early warning information and normal production information are sent to the designated equipment of the production team to perform production monitoring operations for epoxy plate heaters and PTC heaters.

Citation Information

Patent Citations

  • Methods and systems for detection in industrial internet of things data collection environment with large data sets

    CN110073301A