Production cockpit construction method and production cockpit

Abstract

The invention provides a production cockpit construction method and a production cockpit, and the method comprises the steps: obtaining multi-source data, and determining the attributes of the multi-source data, the multi-source data comprising at least two of production data, quality data, cost data, equipment data, energy data, logistics data, safety data and supply chain data; analyzing the relationship among the multi-source data to obtain a data relationship mode; determining a target analysis model based on the attribute of the multi-source data, the data relation mode and an analysis demand; and based on the target analysis model, analyzing the multi-source data to obtain an analysis result, and applying equipment layout and production logic flow to visually display the analysis result and construct a production cockpit. According to the invention, an efficient and comprehensive production cockpit can be constructed, so that real-time tracking and monitoring of the whole production process can be realized.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a production cockpit construction method and a production cockpit. Background Art

[0002] With the rapid development of technologies such as the Internet of Things, big data, and cloud computing, companies are increasingly aware of the importance of data as a core asset. In order to more effectively manage complex production processes, optimize resource allocation, and improve operational efficiency, building a digital cockpit that integrates data integration, real-time monitoring, intelligent analysis, and decision support has become a common choice for many factories.

[0003] Although some factories have established basic digital cockpits, it is often difficult to collect all necessary data comprehensively and accurately, affecting the integrity of data analysis and decision-making. Moreover, these cockpits only have basic data display and statistical analysis functions, and lack the ability to conduct in-depth analysis and mining for specific business scenarios and needs. Summary of the invention

[0004] The present invention provides a production cockpit construction method and a production cockpit, so as to solve the defects of the existing cockpit, namely, difficulty in integrating data sources and limited data analysis capability.

[0005] The present invention provides a method for constructing a production cockpit, comprising: Acquire multi-source data and determine attributes of the multi-source data, wherein the multi-source data includes at least two of production data, quality data, cost data, equipment data, energy data, logistics data, safety data, and supply chain data; Analyze the relationship between the multi-source data to obtain a data relationship model; Determining a target analysis model based on the attributes of the multi-source data, the data relationship model, and the analysis requirements; Based on the target analysis model, the multi-source data is analyzed to obtain analysis results, and the equipment layout and production logic flow are applied to visualize the analysis results to build a production cockpit.

[0006] According to a production cockpit construction method provided by the present invention, determining a target analysis model based on the attributes of the multi-source data, the data relationship model and the analysis requirements includes: Determining a target analysis model from a set of preset analysis models based on the attributes of the multi-source data, the data relationship model, and the analysis requirements; The preset analysis model set includes at least one of a regression analysis model, a cluster analysis model, a time series analysis model, a classification model, and an anomaly detection model.

[0007] According to a production cockpit construction method provided by the present invention, the attributes of the multi-source data include at least one of data type, data scale, data distribution, and data usage.

[0008] According to a production cockpit construction method provided by the present invention, the analysis result includes a production analysis result, and the multi-source data is analyzed based on the target analysis model to obtain the analysis result, including: Extracting historical production volume and real-time production volume from the multi-source data, and applying the historical production volume and the real-time production volume to perform analysis based on the target analysis model to obtain predicted production volume; Determining production efficiency based on production time and / or production cost, and the historical production volume and the real-time production volume; The production analysis result is obtained based on the real-time production volume, the predicted production volume and the production efficiency.

[0009] According to a production cockpit construction method provided by the present invention, the step of acquiring multi-source data includes: Acquire initial multi-source data, where the initial multi-source data is acquired based on at least one of sensor acquisition, API interface, and third-party data platform; The initial multi-source data is cleaned, standardized and integrated to obtain the multi-source data.

[0010] A method for constructing a production cockpit according to the present invention further includes: Collect various key indicators in the production process in real time and perform anomaly detection based on the key indicators; Based on the key indicators collected historically and in real time, abnormal prediction is performed; When an abnormality is detected or predicted during the production process, an alarm is issued and a solution is pushed.

[0011] The present invention also provides a production cockpit, the production cockpit is obtained based on any of the above production cockpit construction methods, and the production cockpit has a three-level control system; The first-level control system is used to integrate and manage multiple modules, wherein the multiple modules include at least two of a production operation module, a quality inspection module, a cost management module, an equipment management module, a smart energy module, a smart logistics module, a smart safety and environmental protection module, and a smart supply module; The second level control system is used to display the real-time status information of the multiple modules; The third-level control system is used to analyze and display various key indicators in the production process.

[0012] According to a production cockpit provided by the present invention, the production operation module is used to perform linkage management on various production equipment based on production scheduling information and display information on various production tasks; The quality inspection module is used to manage the product quality inspection during the production process and display the quality inspection data of each product; The cost management module is used to manage various costs incurred during the production process and display various cost data; The equipment management module is used to display the real-time operation data of each production equipment, and to perform performance analysis and maintenance management on each production equipment; The smart energy module is used to monitor and display the energy usage in the production process in real time; The smart logistics module is used to track the logistics information of raw materials and finished products in real time and display the inventory of each item; The smart safety and environmental protection module is used to monitor and display the safety indicators and environmental protection indicators in the production process in real time; The smart supply module is used to formulate a procurement plan based on the production plan and inventory status, and to display the inventory status, inventory turnover rate and material backlog.

[0013] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for constructing a production cockpit as described in any one of the above is implemented.

[0014] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the production cockpit construction method as described in any one of the above is implemented.

[0015] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the production cockpit construction method as described in any one of the above is implemented.

[0016] The production cockpit construction method and production cockpit provided by the present invention ensure the comprehensiveness and diversity of data by acquiring data from multiple sources, and by integrating data from these different sources, a more comprehensive and in-depth perspective can be provided to analyze the production operation status. By conducting in-depth analysis of the relationship between multi-source data, a data relationship model is obtained, which helps to reveal the inherent connection and mutual influence between the data, and provides a solid foundation for subsequent data analysis and model building. By determining the target analysis model based on the attributes and relationship patterns of the data, as well as specific analysis needs, it can be ensured that the analysis model can closely fit the actual business scenarios and needs of the factory, and improve the pertinence and effectiveness of the analysis. By analyzing multi-source data with the constructed target analysis model, in-depth analysis results can be obtained, and the analysis results can be combined with the equipment layout and production logic flow for visual display, which is simple and intuitive, so that users can quickly understand the current status and potential problems of production operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present invention or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 It is a schematic diagram of the process of the production cockpit construction method provided by the present invention; Figure 2 It is a structural schematic diagram of a digital cockpit serving production operations provided by the present invention; Figure 3 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] As the "brain" of production operations, the digital cockpit aims to provide managers with a panoramic view of operations by integrating information from multiple data sources such as production systems, equipment monitoring systems, and supply chain management systems. It can not only display key indicators such as production progress, equipment status, and material inventory in real time, but also reveal potential problems in the production process and predict future trends through data analysis and mining, providing managers with accurate decision-making basis.

[0021] However, in actual applications, the construction and application of digital cockpits still have certain defects. First, there are usually multiple data sources in factories, such as production data, equipment data, supply chain data, etc. These data may be distributed in different systems and departments, making it difficult to effectively collect and integrate them. Due to the diversity of data sources and system differences, the collected data may have quality problems, such as inconsistent data formats, data duplication, data missing, etc., which will affect the accuracy and effectiveness of data analysis. Secondly, existing digital cockpits often only have basic data analysis functions and lack in-depth analysis and mining capabilities for specific business scenarios and needs, which limits the role of the cockpit in discovering potential problems, predicting trends, and guiding decision-making. In addition, the interface design of some cockpits is complex, and the information presentation is not intuitive enough, making it difficult for users to quickly obtain key information.

[0022] In this regard, the present invention provides a production cockpit construction method, which integrates data from different sources, including production data, quality data, cost data, equipment data, supply chain data, etc., by adopting key technologies such as automated control equipment, the Internet of Things, cloud computing platforms, big data technology, and digital visualization, so that these data form a complete data chain, providing a basis for subsequent data analysis and display. At the same time, a machine learning algorithm is used to analyze various data obtained from real-time monitoring, and according to the analysis results, the entire production process is displayed in the form of equipment layout and production logic flow, and at the same time, the important data of each process such as production plan, quality, energy, equipment status, inventory, and raw and auxiliary material supply are appropriately displayed, so as to achieve the logic of the production process, the correspondence of process data, and the clarity of the entire production process, thereby overcoming the above-mentioned defects.

[0023] It should be noted that the production cockpit is an information management system designed specifically for the manufacturing industry, based on data visualization and real-time monitoring. It integrates various production-related data sources and displays them in real time on a centralized platform in the form of intuitive and easy-to-understand charts, graphs and indicators, providing manufacturing companies with comprehensive production process monitoring and decision support, helping companies improve production efficiency, optimize resource allocation, improve product quality and reduce production costs.

[0024] Figure 1 It is a flow chart of the production cockpit construction method provided by the present invention, such as Figure 1 As shown, the method includes: Step 110, acquiring multi-source data and determining attributes of the multi-source data, wherein the multi-source data includes at least two of production data, quality data, cost data, equipment data, energy data, logistics data, safety data, and supply chain data; Specifically, multi-source data refers to a collection of data from different sources, different systems or different departments. These data are usually diverse, complex and heterogeneous, and need to be integrated and analyzed through specific methods and tools. Here, multi-source data can include production data, quality data, cost data, equipment data, energy data, logistics data, safety data and supply chain data.

[0025] Among them, production data refers to data directly related to the production process, including the output, production progress, production cycle, production efficiency, etc. on the production line. Quality data refers to data about product quality, including product qualification rate, defective product rate, market complaint rate, etc. Cost data refers to data related to production costs, including raw material costs, labor costs, equipment depreciation, energy consumption, etc. Equipment data refers to data about the status and operation of production equipment, including equipment startup rate, failure rate, maintenance records, service life, etc. Energy data refers to data about energy consumption, including the consumption, consumption rate, energy consumption ratio, etc. of energy such as water, electricity, and gas. Logistics data refers to data related to logistics activities, including data on raw material procurement, inventory management, product sales, logistics distribution, etc. Safety data refers to data about production safety and environmental protection, including the number, type, cause, loss, and environmental protection index data of safety accidents. Supply chain data refers to data about the overall operation of the supply chain, including supplier information, supplier evaluation, supply chain stability, supply chain risks, etc.

[0026] After obtaining multi-source data, you can further analyze and obtain the attribute information of each type of data. Here, the attributes of multi-source data can include data type, data size, data distribution, data usage, etc. Among them, data type refers to the nature and form of data, which determines how the data is stored, processed and displayed. For data type, you can judge and obtain it by checking the format, extension or structure of the data file, or by extracting data samples for analysis.

[0027] Data scale refers to the total amount or size of data, which reflects the complexity and difficulty of data processing. When determining data scale, for data stored in files, you can determine it by looking at the size of the data file, and for data in a database, you can query the database management system to obtain the number of records or rows.

[0028] Data distribution refers to the distribution of data in different dimensions or attributes, which reflects the statistical characteristics and laws of data. In order to determine data distribution, statistical analysis methods, visualization or data mining techniques can be used.

[0029] Data usage refers to the purpose or scenario for which data is used, which determines the value and significance of the data. In order to determine the purpose of each type of data in multi-source data, it can be achieved by analyzing the business scenario and context of the data.

[0030] Furthermore, in step 110, in order to obtain multi-source data, the following steps may be performed: Step 111, obtaining initial multi-source data, wherein the initial multi-source data is obtained based on at least one of sensor acquisition, API interface, and third-party data platform; Step 112, cleaning, standardizing and integrating the initial multi-source data to obtain the multi-source data.

[0031] Specifically, initial multi-source data refers to a collection of unprocessed raw data obtained from different sources or channels. These data can come from a variety of different data sources, including but not limited to sensors, API interfaces, third-party data platforms, etc. Here, through sensors deployed in a specific environment, various types of data such as temperature, humidity, pressure, motion status, etc. can be collected in real time or periodically. API (application programming interface) is a communication bridge between different software applications. By accessing a third-party data platform, the required data set can be obtained.

[0032] For example, data interconnection can be achieved by connecting with APS (Advanced Planning and Scheduling), MES (Manufacturing Execution System), ERM (Enterprise Resource Management), WMS (Warehouse Management System), LIMS (Laboratory Information Management System) and various automation equipment, and initial multi-source data can be obtained from these systems or equipment.

[0033] Subsequently, these initial multi-source data can be preprocessed, such as data cleaning, standardization, and data integration. Here, data cleaning includes removing duplicate data, processing missing values, and correcting erroneous data; data standardization includes data format conversion, encoding conversion, etc., and converting data to the same level through scaling, normalization, etc. for comparison and analysis. Data integration refers to the integration of data from different data sources according to certain logic or rules to form a unified data set. In addition, the preprocessed data can also be verified to ensure the accuracy, completeness, and consistency of the data. Through the above steps, the initial multi-source data can be converted into clean, consistent, and usable multi-source data, providing a solid foundation for subsequent data analysis and application.

[0034] Step 120, analyzing the relationship between the multi-source data to obtain a data relationship model; Specifically, after obtaining multi-source data, the relationship between the multi-source data can also be analyzed to obtain the potential association, dependency or interaction between different data sources, thereby providing a basis for subsequent data integration, analysis model and visualization. Specifically, the association between multi-source data can be identified through statistical methods, data mining technology or machine learning algorithms, and the linear or nonlinear relationship, causal relationship, time series relationship, etc. between data can also be identified through association analysis technology, such as correlation analysis, cluster analysis, association rule mining, etc.

[0035] Furthermore, the identified relationships between data can be verified to ensure their accuracy and reliability, and the verified relationships can be expressed in the form of a model, such as a relationship diagram, a network diagram, an association matrix, etc., to obtain a data relationship pattern. Here, a data relationship pattern refers to a description and definition of the relationship between different data tables or data sets. In an embodiment of the present invention, by analyzing the relationship between multi-source data, it is helpful to select appropriate analysis models and methods, thereby more accurately revealing the laws and trends behind the data.

[0036] Step 130, determining a target analysis model based on the attributes of the multi-source data, the data relationship model, and the analysis requirements; It should be noted that analysis requirements are an important part of the data analysis process, which involves an in-depth understanding and evaluation of user requirements, business requirements or data requirements. For example, analysis requirements can be requirements for analyzing the production operation process, requirements for analyzing the equipment operation status, requirements for analyzing costs, logistics, supply chains, etc., and requirements for prediction, classification, clustering, anomaly detection, etc., which are not specifically limited in the embodiments of the present invention.

[0037] Specifically, according to the attributes of multi-source data, data relationship patterns and specific analysis requirements, a target analysis model can be selected or constructed. Here, the target analysis model refers to a model for guiding data analysis determined according to the attributes of multi-source data, data relationship patterns and analysis requirements.

[0038] Specifically, you can first clarify the specific analysis needs. For example, according to business needs or data-driven goals, clarify the specific problems or goals that need to be analyzed, and determine the granularity, scope, time window and other parameters of the analysis. Then, according to the specific analysis needs and data attributes and relationship patterns, select the appropriate analysis model. If the existing model cannot meet the needs, you can consider customizing the model or combining multiple models for comprehensive analysis. Use historical data or simulation data to verify the model, evaluate the accuracy and stability of the model, and optimize and adjust the model based on the verification results to improve the performance and reliability of the model. Apply the optimized model to actual business scenarios to provide data-driven decision support.

[0039] Step 140: Analyze the multi-source data based on the target analysis model to obtain analysis results, apply equipment layout and production logic flow to visualize the analysis results, and build a production cockpit.

[0040] Specifically, after determining the target analysis model, the multi-source data can be input into the target analysis model, the data can be processed by the model, and the corresponding analysis results can be generated. Here, the analysis results refer to the output information obtained after the multi-source data is processed and analyzed by the target analysis model.

[0041] Subsequently, the analysis results can be visualized according to the equipment layout and production logic flow. Specifically, the following steps can be taken to achieve visualization: First, have an in-depth understanding of the layout of the equipment on the production line, including the location, function, and relationship between the equipment, and master the production logic flow, that is, the entire production process from raw materials to finished products, including various production links, process steps, time nodes, etc. Then, according to the characteristics of the equipment layout and production logic flow, design a reasonable visualization scheme, including selecting appropriate visualization types (such as heat maps, trend maps, flow charts, etc.), color schemes, chart layouts, etc., to ensure that the visualization scheme can clearly display the analysis results and match the equipment layout and production logic flow. Finally, use data visualization tools (such as Tableau, Power BI, etc.) to make visualization charts, sort and layout the analysis results according to the order of equipment layout and production logic flow, ensure that the information in the chart can smoothly display the production process, and add necessary labels, annotations, and interactive elements to the chart so that users can easily understand and use the analysis results.

[0042] The embodiment of the present invention constructs an efficient and comprehensive production cockpit through the steps of multi-source data integration, data relationship analysis, model determination, deep data analysis and visual display, which can not only enhance the management's control over production operations, but also significantly improve decision-making efficiency and accuracy, and promote the development of factories towards intelligence and efficiency.

[0043] The method provided by the embodiment of the present invention ensures the comprehensiveness and diversity of data by acquiring data from multiple sources, and can provide a more comprehensive and in-depth perspective to analyze the production operation status by integrating data from these different sources. By conducting in-depth analysis of the relationship between multi-source data, a data relationship model is obtained, which helps to reveal the inherent connection and mutual influence between the data, and provides a solid foundation for subsequent data analysis and model building. By determining the target analysis model based on the attributes and relationship patterns of the data, as well as specific analysis needs, it can be ensured that the analysis model can closely fit the actual business scenarios and needs of the factory, and improve the pertinence and effectiveness of the analysis. By analyzing multi-source data with the constructed target analysis model, in-depth analysis results can be obtained, and the analysis results can be combined with the equipment layout and production logic flow for visual display, which is simple and intuitive, so that users can quickly understand the current status and potential problems of production operations.

[0044] Based on any of the above embodiments, step 130 specifically includes: Determining a target analysis model from a set of preset analysis models based on the attributes of the multi-source data, the data relationship model, and the analysis requirements; The preset analysis model set includes at least one of a regression analysis model, a cluster analysis model, a time series analysis model, a classification model, and an anomaly detection model.

[0045] Specifically, the preset analysis model set is a predefined analysis model library that contains a variety of analysis models suitable for different scenarios, such as regression analysis models, clustering analysis models, time series analysis models, classification models, and anomaly detection models. According to data attributes, data relationship patterns, and specific analysis requirements, the most appropriate model, namely the target analysis model, can be selected from the preset analysis model set.

[0046] For example, if the goal is to predict a continuous value (such as future output, cost, etc.), you can choose regression analysis models such as linear regression and polynomial regression. If the data has time series characteristics, you can also consider time series regression. If you need to divide the data into several groups or categories, and these groups or categories are unknown in advance, you can choose clustering analysis models such as K-means and hierarchical clustering. For data with time series characteristics (such as time series changes in production volume, time trends in equipment failure rates, etc.), you can choose ARIMA, LSTM (Long Short-Term Memory Network), GRU (Gated Recurrent Unit) and other time series analysis models. When you need to divide the data into several known categories, you can choose classification models such as logistic regression, decision tree, random forest, support vector machine (SVM), neural network, etc. Classification models are often used in quality inspection, equipment failure prediction and other fields. When you need to identify outliers or abnormal patterns in the data, you can choose anomaly detection models.

[0047] Based on any of the above embodiments, the analysis result includes a production analysis result. Accordingly, in step 140, the multi-source data is analyzed based on the target analysis model to obtain the analysis result, including: Step 141, extracting historical production volume and real-time production volume from the multi-source data, and applying the historical production volume and the real-time production volume to perform analysis based on the target analysis model to obtain predicted production volume; Step 142, determining production efficiency based on production time and / or production cost, and the historical production volume and the real-time production volume; Step 143, obtaining the production analysis result based on the real-time production volume, the predicted production volume and the production efficiency.

[0048] It should be noted that the constructed production cockpit can include production operation module, quality inspection module, cost management module, equipment management module, smart energy module, smart logistics module, smart safety and environmental protection module and smart supply module, etc. Each functional module is used to display different information. The following is an introduction to the production operation module. In this module, by integrating and analyzing data from different sources (i.e., multi-source data) and combining it with a specific target analysis model, production volume can be predicted, production efficiency can be evaluated, and finally comprehensive production analysis results can be generated and displayed.

[0049] Specifically, first, historical data and real-time data directly related to production volume are screened from multi-source data, including daily, weekly or monthly production quantities. Historical data provides a record of past production activities, while real-time data reflects the current production status. Then, these data are processed and analyzed using a target analysis model (such as a time series analysis model) to predict future production volume, which takes into account a variety of factors such as historical trends, seasonal changes, market demand, etc. Charts (such as line charts) can be used to intuitively display the changing trend of production volume.

[0050] According to the production order or production plan, specific production tasks can be identified. The progress of each task can be tracked through the MES system or production line sensors, recording the production start time, current production stage, expected completion time, etc. The completion status of production tasks is counted regularly (such as daily and weekly), including the number of completed tasks, the number of ongoing tasks, the number of unstarted tasks, etc. The progress and completion status of production tasks can be displayed using Gantt charts, which is convenient for managers to understand the production progress and coordinate resources.

[0051] It is understandable that production efficiency can be measured by a variety of indicators, such as production volume per unit time, production volume per unit cost, etc. Therefore, production efficiency is calculated based on production volume and production time (or production cost). Capacity utilization refers to the ratio between actual production volume and theoretical maximum production volume, and is calculated by comparing actual production time and production line available time (or capacity). Integrate key indicators such as production efficiency and capacity utilization into the KPI dashboard to display the values ​​and changing trends of production efficiency and capacity utilization in real time.

[0052] Finally, in the production operation module, data visualization tools are used to display the above analysis results in the form of charts, dashboards, etc., which helps companies better understand production conditions, optimize production processes, and improve production efficiency and capacity utilization.

[0053] Based on any of the above embodiments, the method further includes: Collect various key indicators in the production process in real time and perform anomaly detection based on the key indicators; Based on the key indicators collected historically and in real time, abnormal prediction is performed; When an abnormality is detected or predicted during the production process, an alarm is issued and a solution is pushed.

[0054] Specifically, the monitoring system and alarm system can be integrated into the production cockpit to monitor the key indicators in the production process in real time, and the alarm mechanism will be triggered immediately once an abnormality is found. Specifically, sensors, PLC (programmable logic controller), RFID (radio frequency identification) and other technologies can be used to collect key indicator data from the production line in real time, such as temperature, pressure, speed, production volume, equipment operation status, etc. The collected raw data is cleaned to remove noise, outliers and duplicate data, and the data is formatted to ensure data consistency and comparability. The pre-processed data is transmitted to the monitoring system in real time and visualized in the form of charts, dashboards, etc. In the real-time monitoring process, reasonable thresholds and alarm rules are set to detect abnormalities of key indicators. Once abnormal data or exceeding the preset threshold is found, the alarm mechanism is triggered immediately to remind the operator to pay attention and take corresponding measures.

[0055] Furthermore, algorithms such as machine learning and deep learning can be used to conduct in-depth analysis and modeling of historical data and real-time data. Through regression analysis, classification algorithms, time series analysis and other methods, patterns and trends in the data can be discovered and anomaly prediction models can be constructed. The anomaly prediction model can be applied to historical data streams and real-time data streams to predict abnormal situations that may occur in the future. Based on the prediction results, response measures and plans can be formulated in advance to reduce the impact of abnormal events on the production process.

[0056] In addition, the production process and abnormal prediction model can be optimized and improved regularly. Based on the new production data and feedback information collected, the accuracy and reliability of the abnormal prediction model can be continuously improved.

[0057] In the embodiment of the present invention, through the above process, the enterprise can realize real-time monitoring and abnormal prediction of various key indicators in the production process, so as to timely discover and deal with potential problems and risks, and improve production efficiency and product quality.

[0058] Based on any of the above embodiments, an embodiment of the present invention provides a production cockpit, which is obtained based on the production cockpit construction method as described in any of the above embodiments, and has a three-level control system; The first-level control system is used to integrate and manage multiple modules, wherein the multiple modules include at least two of a production operation module, a quality inspection module, a cost management module, an equipment management module, a smart energy module, a smart logistics module, a smart safety and environmental protection module, and a smart supply module; The second level control system is used to display the real-time status information of the multiple modules; The third-level control system is used to analyze and display various key indicators in the production process.

[0059] Specifically, the production cockpit is built with a three-level control system that can manage production factors at all levels in great detail. Each level of the control system is closely integrated with the corresponding related factor analysis model to ensure that every link in the production process can be effectively monitored and managed.

[0060] The first-level control system integrates and manages multiple modules from a macro perspective, including production operation module, quality inspection module, cost management module, equipment management module, smart energy module, smart logistics module, smart safety and environmental protection module, and smart supply module. By integrating these information modules, global real-time linkage and unified management can be achieved, greatly improving the efficiency and coordination of production operations.

[0061] The second-level control system focuses on the real-time status information display of each module, providing operators with key information such as production line status and equipment operation status, helping them to fully understand the current production status.

[0062] The third-level control system displays and analyzes a number of key indicators in detail, providing comprehensive data support to decision-makers and helping them make more scientific and reasonable decisions.

[0063] The interactive switching design between the three-level control systems is simple and efficient. Quick switching between levels can be achieved by just clicking, which improves operational convenience and work efficiency, allowing managers to view information at different levels at any time as needed, while ensuring that data between levels can be shared and updated synchronously in real time.

[0064] Based on any of the above embodiments, Figure 2 is a structural schematic diagram of a digital cockpit for production operations provided by the present invention, such as Figure 2 As shown, the cockpit mainly includes the following functional modules: The production operation module is used to manage various production equipment in a coordinated manner based on production scheduling information and display information on various production tasks; The quality inspection module is used to manage the product quality inspection during the production process and display the quality inspection data of each product; The cost management module is used to manage various costs incurred during the production process and display various cost data; The equipment management module is used to display the real-time operation data of each production equipment, and to perform performance analysis and maintenance management on each production equipment; The smart energy module is used to monitor and display the energy usage in the production process in real time; The smart logistics module is used to track the logistics information of raw materials and finished products in real time and display the inventory of each item; The smart safety and environmental protection module is used to monitor and display the safety indicators and environmental protection indicators in the production process in real time; The smart supply module is used to formulate a procurement plan based on the production plan and inventory status, and to display the inventory status, inventory turnover rate and material backlog.

[0065] It should be noted that the digital cockpit, as an integrated and intelligent management platform in the manufacturing industry, integrates multiple key modules to improve production efficiency, optimize resource allocation, ensure product quality and guarantee production safety. The functions of each module are introduced below: The production operation module can provide real-time status monitoring of the production line, including key indicators such as output and production progress. Formulate production plans based on market demand and enterprise resources, and monitor the execution of work order plans in real time to ensure orderly production. Intelligent scheduling of resources such as raw materials, human resources, and production equipment can be carried out to improve resource utilization and production efficiency. In addition, abnormal situations in the production process, such as equipment failure and raw material shortage, can be discovered and handled in a timely manner to reduce production interruptions.

[0066] The quality inspection module is used to inspect the quality of semi-finished products and finished products in the production process to ensure that the product quality meets the standards. By recording the information of each link of product production, the quality problem can be traced back, which is convenient for quickly locating the source of the problem. Statistical analysis is performed on the test data to identify the trend of quality problems and provide a basis for quality improvement. Quality control measures are formulated based on the analysis results to improve product quality stability and customer satisfaction. The information displayed in this module can include sample test data, market complaint rate, national shipping complaint ranking, etc.

[0067] The cost management module is used to calculate various costs in the production process, including raw material costs, labor costs, energy costs, etc. In-depth analysis of cost data can be carried out to identify potential cost savings and provide a basis for cost control. Cost control strategies can be formulated to reduce costs by optimizing production processes, reducing energy consumption, and improving equipment utilization. In addition, future cost trends can be predicted based on historical data and current production conditions to provide support for corporate decision-making.

[0068] The equipment management module can provide real-time operation data of the equipment, including key parameters such as temperature, pressure, and speed, and timely detect equipment failures. It can also cover equipment KPL, efficiency and other data. By analyzing the historical data of the equipment, the performance of the equipment can be evaluated and possible problems can be predicted. The equipment maintenance plan is formulated, and the maintenance history is recorded to ensure that the equipment is maintained and repaired in a timely manner. When the equipment is abnormal or requires maintenance, alarms and notifications are issued in a timely manner to ensure that the problem is solved in a timely manner.

[0069] The smart energy module can monitor energy usage in real time, including the consumption of water, electricity, gas and other energy sources. Through in-depth analysis of energy usage data, energy trend analysis results can be obtained, energy waste links can be identified, and a basis for energy conservation and consumption reduction can be provided. Through intelligent algorithms, energy usage can be predicted and optimized, energy costs can be reduced, and energy utilization efficiency can be improved.

[0070] The smart logistics module is used to grasp the inventory quantity and warehouse information of each item in real time, optimize the inventory structure and reduce inventory costs. It is used to track the logistics process of raw materials and finished products in real time to ensure smooth logistics. It optimizes logistics routes and distribution plans through intelligent algorithms to improve logistics efficiency.

[0071] The smart safety and environmental protection module can monitor the production site in real time, analyze the comprehensive safety and environmental protection situation, promptly identify potential safety hazards and take measures to eliminate them. It can also monitor and treat pollutants such as waste gas, wastewater, and solid waste in the production process to ensure that environmental protection standards are met.

[0072] The smart supply module can formulate procurement plans based on production plans and inventory conditions to achieve accurate procurement. It can also display current inventory turnover rates, material backlogs, etc.

[0073] In the embodiment of the present invention, each module of the production cockpit realizes comprehensive monitoring and optimization of the production process through an integrated and intelligent management method, thereby improving production efficiency, product quality and enterprise competitiveness.

[0074] Figure 3 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 3 As shown, the electronic device may include: a processor 310, a communication interface 320, a memory 330 and a communication bus 340, wherein the processor 310, the communication interface 320 and the memory 330 communicate with each other through the communication bus 340. The processor 310 may call the logic instructions in the memory 330 to execute the production cockpit construction method, which includes: obtaining multi-source data and determining the attributes of the multi-source data, wherein the multi-source data includes at least two of production data, quality data, cost data, equipment data, energy data, logistics data, safety data and supply chain data; analyzing the relationship between the multi-source data to obtain a data relationship model; determining a target analysis model based on the attributes of the multi-source data, the data relationship model and the analysis requirements; analyzing the multi-source data based on the target analysis model to obtain analysis results, and applying the equipment layout and production logic flow to visualize the analysis results to build a production cockpit.

[0075] In addition, the logic instructions in the above-mentioned memory 330 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the relevant technology or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0076] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the production cockpit construction method provided by the above methods, which includes: obtaining multi-source data and determining the attributes of the multi-source data, wherein the multi-source data includes at least two of production data, quality data, cost data, equipment data, energy data, logistics data, safety data and supply chain data; analyzing the relationship between the multi-source data to obtain a data relationship model; determining a target analysis model based on the attributes of the multi-source data, the data relationship model and analysis requirements; analyzing the multi-source data based on the target analysis model to obtain analysis results, and applying equipment layout and production logic flow to visualize the analysis results to build a production cockpit.

[0077] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the production cockpit construction method provided by the above-mentioned methods, the method comprising: acquiring multi-source data and determining the attributes of the multi-source data, the multi-source data comprising at least two of production data, quality data, cost data, equipment data, energy data, logistics data, safety data and supply chain data; analyzing the relationship between the multi-source data to obtain a data relationship model; determining a target analysis model based on the attributes of the multi-source data, the data relationship model and analysis requirements; analyzing the multi-source data based on the target analysis model to obtain analysis results, and applying equipment layout and production logic flow to visualize the analysis results to build a production cockpit.

[0078] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiment.

[0079] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for constructing a production cockpit, characterized in that: include: Acquire multi-source data and determine attributes of the multi-source data, wherein the multi-source data includes at least two of production data, quality data, cost data, equipment data, energy data, logistics data, safety data, and supply chain data; Analyze the relationship between the multi-source data to obtain a data relationship model; Determining a target analysis model based on the attributes of the multi-source data, the data relationship model, and the analysis requirements; Based on the target analysis model, the multi-source data is analyzed to obtain analysis results, and the equipment layout and production logic flow are applied to visualize the analysis results to build a production cockpit.

2. The method for constructing a production cockpit according to claim 1, characterized in that: The determining of a target analysis model based on the attributes of the multi-source data, the data relationship model, and the analysis requirements includes: Determining a target analysis model from a set of preset analysis models based on the attributes of the multi-source data, the data relationship model, and the analysis requirements; The preset analysis model set includes at least one of a regression analysis model, a cluster analysis model, a time series analysis model, a classification model, and an anomaly detection model.

3. The production cockpit construction method according to claim 2, characterized in that: The attributes of the multi-source data include at least one of data type, data scale, data distribution, and data usage.

4. The production cockpit construction method according to claim 1, characterized in that: The analysis result includes a production analysis result, and the analysis result is obtained by analyzing the multi-source data based on the target analysis model, including: Extracting historical production volume and real-time production volume from the multi-source data, and applying the historical production volume and the real-time production volume to perform analysis based on the target analysis model to obtain predicted production volume; Determining production efficiency based on production time and / or production cost, and the historical production volume and the real-time production volume; The production analysis result is obtained based on the real-time production volume, the predicted production volume and the production efficiency.

5. The production cockpit construction method according to claim 1, characterized in that: The acquiring of multi-source data includes: Acquire initial multi-source data, where the initial multi-source data is acquired based on at least one of sensor acquisition, API interface, and third-party data platform; The initial multi-source data is cleaned, standardized and integrated to obtain the multi-source data.

6. The method for constructing a production cockpit according to any one of claims 1 to 5, characterized in that: Also includes: Collect various key indicators in the production process in real time and perform anomaly detection based on the key indicators; Based on the key indicators collected historically and in real time, abnormal prediction is performed; When an abnormality is detected or predicted during the production process, an alarm is issued and a solution is pushed.

7. A production cockpit, characterized in that: The production cockpit is obtained based on the production cockpit construction method according to any one of claims 1 to 6, and the production cockpit includes a three-level control system; The first-level control system is used to integrate and manage multiple modules, wherein the multiple modules include at least two of a production operation module, a quality inspection module, a cost management module, an equipment management module, a smart energy module, a smart logistics module, a smart safety and environmental protection module, and a smart supply module; The second level control system is used to display the real-time status information of the multiple modules; The third-level control system is used to analyze and display various key indicators in the production process.

8. The production cockpit according to claim 7, characterized in that The production operation module is used to manage various production equipment in a coordinated manner based on production scheduling information and display information on various production tasks; The quality inspection module is used to manage the product quality inspection during the production process and display the quality inspection data of each product; The cost management module is used to manage various costs incurred during the production process and display various cost data; The equipment management module is used to display the real-time operation data of each production equipment, and to perform performance analysis and maintenance management on each production equipment; The smart energy module is used to monitor and display the energy usage in the production process in real time; The smart logistics module is used to track the logistics information of raw materials and finished products in real time and display the inventory of each item; The smart safety and environmental protection module is used to monitor and display the safety indicators and environmental protection indicators in the production process in real time; The smart supply module is used to formulate a procurement plan based on the production plan and inventory status, and to display the inventory status, inventory turnover rate and material backlog.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the production cockpit construction method according to any one of claims 1 to 6 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the production cockpit construction method according to any one of claims 1 to 6 is implemented.

Images