Digital twin system applied to industrial production

By monitoring the noise frequency of equipment in real time and analyzing the frequency change rate in industrial production, predicting the equipment maintenance time, the problem of long failure coordination time in the existing technology is solved, timely maintenance of equipment and quality management is optimized, and the efficiency of the production line is improved and equipment reliability.

CN118938823APending Publication Date: 2024-11-12DONGFANG ELECTRIC CHENGDU INTELLIGENT TECH CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410983197.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-22
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

The existing digital twin system needs independent statistics in blade production due to the fault process and station, which leads to a long time of failure coordination, and it is impossible to provide timely guidance to production personnel to avoid faults, which brings inconvenience to production quality management.

Method used

By applying a digital twin system in industrial production, the equipment noise frequency is monitored in real time and the frequency change rate is analyzed, the equipment maintenance time is predicted, personnel are promptly guided to inspect, optimize maintenance plans, and provide quality management suggestions in combination with quality inspection data to shorten coordination time.

Benefits of technology

It realizes early detection of potential equipment failures, accurately predict maintenance times, avoid downtime and production losses, improve equipment reliability and availability, optimize maintenance plans, reduce maintenance costs, and improve production line efficiency and product quality stability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118938823A_ABST
    Figure CN118938823A_ABST
Patent Text Reader

Abstract

The invention belongs to the technical field of industrial production digitization, and particularly relates to a digital twin system applied to industrial production, which comprises a sample data analysis module, a digital data acquisition module, a digital workshop module, an intelligent guide module and a quality management module. The invention provides a digital twin system applied to industrial production. Compared with the prior art, by monitoring the noise frequency of the equipment in real time and analyzing the frequency change rate, potential faults of the equipment can be found as early as possible, the maintenance time of the equipment can be accurately predicted, shutdown and production loss caused by sudden faults of the equipment are avoided, and the reliability and usability of the equipment are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of industrial production digitization, and specifically relates to a digital twin system applied to industrial production. Background Art

[0002] The production line digital twin system refers to the construction of a digital twin model based on digital twin technology by collecting data on various equipment, materials, personnel, etc. on the production line to achieve real-time monitoring, prediction and optimization of the production process. The production line digital twin system can improve the efficiency of production control and auxiliary decision-making. By dynamically sensing data such as on-site operation progress, personnel status, resource utilization, etc., it can provide decision makers with more accurate and timely information and improve decision-making efficiency and accuracy.

[0003] Quality problems in industrial production are caused by a variety of factors and generally require statistics. The use of digital twin systems for monitoring, collection, and intelligent optimization has greatly reduced the workload of statistics. Traditional quality problems often enter the information of the fault point into the network cloud, take images of the fault point, and then summarize the causes of the fault and classify them. This can promptly remind personnel in positions where faults are frequent to operate carefully on the job and improve the quality of industrial production.

[0004] When the existing digital twin system is applied to blade production, the image information and cause of the faulty blade are often recorded. The process and workstation where the fault occurred need to be independently counted, and the production personnel who caused the fault need to record it online. The coordination time is long, and it is impossible to provide timely guidance to the production personnel to avoid the fault, which brings great inconvenience to the coordination and overall planning of production quality management. For this reason, we propose a digital twin system for industrial production. Summary of the invention

[0005] The purpose of the present invention is to provide a digital twin system applied to industrial production, which can shorten the coordination time of industrial production management, provide timely guidance to production personnel on how to avoid faults, and bring great convenience to the coordination and overall planning of production quality management.

[0006] In order to achieve the above technical effects, the technical solutions adopted by the present invention are as follows:

[0007] Digital twin systems used in industrial production include:

[0008] Sample data analysis module: Set collection points to obtain the noise frequency of the equipment during operation; obtain the time when the equipment is put into use and the time when it is repaired, and obtain the use time of the equipment; select several monitoring points during the use time, and the selection of monitoring points includes the time when the equipment is put into use and the time when it is repaired;

[0009] Obtain the noise frequency of each monitoring point during the use time of the equipment and record it as sample data; and obtain the maintenance frequency according to the noise frequency of the equipment at the time of maintenance; establish the frequency curve of the equipment according to the sample data; obtain the change rate of the noise frequency at each monitoring point according to the frequency curve, and obtain the relationship between the use time of the equipment and the change rate;

[0010] Digital data acquisition module: used to obtain production line data, including blade production line layout, equipment list, and capacity parameters;

[0011] Digital workshop module: A digital twin model is established based on production line data, and the noise frequency of the equipment obtained in real time is introduced into the digital twin model; the digital twin model establishes a real-time frequency curve of the equipment and obtains the rate of change of the real-time noise frequency, which is recorded as the real-time change rate; based on the real-time change rate and the relationship, the maintenance time of the equipment is predicted;

[0012] Smart guidance module: Determine the location of the equipment that has reached the maintenance time based on the maintenance time predicted by the digital twin model, and guide personnel to check the equipment in time;

[0013] Quality management module: used to obtain product quality inspection data, introduce the product quality inspection data into the digital twin model, and then use the digital twin model to analyze the quality inspection data.

[0014] Furthermore, the equipment usage time in the sample data analysis module is obtained by recording the time period between the time of commissioning and the time of maintenance as the usage time.

[0015] Furthermore, the monitoring point selection process in the sample data analysis module includes: setting a time interval threshold, the time interval threshold is determined according to the use time of the device, and during the use time, each time interval threshold selects a time node, which is recorded as a monitoring point.

[0016] Furthermore, the process of obtaining the maintenance frequency in the sample data analysis module includes:

[0017] Get the noise frequency of all equipment at the time of maintenance, recorded as {f1, f2, ..., f n}, where f1 represents the noise frequency of the first device at the time of maintenance, and n is the total number of devices; the maintenance frequency is Where i∈[1,n] and i is a positive integer.

[0018] Furthermore, the process of obtaining the noise frequency change rate in the sample data analysis module is as follows:

[0019] Obtain the derivatives at each monitoring point on the frequency curve and obtain {D1, D2, ..., D m}, where D1 represents the derivative at the first monitoring point, and m is the total number of monitoring points; then the rate of change of the noise frequency is obtained Where j∈[1,m] and j is a positive integer.

[0020] Furthermore, the process of obtaining the relationship between time and rate of change in the sample data analysis module is as follows:

[0021] According to the sample data, the change rate and usage time of each device are obtained; a rectangular coordinate system is established, and a scatter plot is obtained in the rectangular coordinate system according to the change rate of each device and its corresponding usage time. The scatter plot is fitted to obtain the regression equation of the scatter plot, which is recorded as the relationship between the maintenance time of the equipment and the frequency and the change rate.

[0022] Furthermore, the prediction process of the maintenance time of the equipment by the digital twin model in the digital workshop module is:

[0023] Get the current time, record the time period from the time the equipment is put into use to the current time as the time t0 that has been put into use; record the relationship between the use time and the change rate as T(d), where d represents the change rate of the noise frequency; record the real-time frequency change rate of the equipment as D0, and obtain the predicted use time T(D0) of the equipment; then the predicted maintenance time of the equipment is T(D0)-t0.

[0024] Furthermore, the quality management module classifies the quality inspection items into warehouses. The blade quality inspection work includes self-inspection, mutual inspection, patrol inspection, special inspection, and special inspection. Inspection templates are set for each. Inspection tasks are automatically generated in the system according to template rules. The quality management module supports the following input formats:

[0025] Text input, transmitted through NCR data; the NCR is a report of non-conforming products;

[0026] Data input, recording the inflow and outflow of workpieces and the information of production personnel in each process through the bar code system;

[0027] Photos and photo annotations are used to record the on-site quality problem handling process and processing data.

[0028] Furthermore, the quality inspection steps of the blades are as follows:

[0029] S1. Start: Confirm tool debugging, process documents and quality inspection task rules in sequence;

[0030] S2. Clamping: put the blade to be inspected into the fixture and fix it;

[0031] S3. Inspection: Quality inspectors, process personnel and production personnel jointly visually inspect the blades to confirm various parameters;

[0032] S4, end: affix the corresponding product serial number label, scan and confirm that the inspection is complete, and push it to the assembly area or assembly station;

[0033] S5. Rework: Repair the blades that can be repaired.

[0034] Furthermore, the management regulations of the smart guidance module are as follows:

[0035] 1) Job transfer: transfer production personnel from more difficult process positions to less difficult positions in the same process;

[0036] 2) Resume production: transfer production personnel with high proficiency in the process to the position to maintain the normal operation of the production line in a timely manner and reduce the adverse impact of quality problems on the production plan;

[0037] 3) Improve quality: Planning the time period for completing life goals and conducting centralized training and assessment of production personnel with lower proficiency by process will help improve the overall production level of the blade production line.

[0038] The quality management module and the intelligent guidance module guide the quality management of blades in the blade digital workshop, shorten the coordination time of industrial production management, and provide timely guidance to production personnel on how to avoid faults, which greatly facilitates the coordination and overall planning of production quality management.

[0039] The technical effects achieved by the present invention are:

[0040] When the existing digital twin system is applied to blade production, the image information and cause of the faulty blade are often recorded. The process and workstation where the fault occurs need to be independently counted, and the production personnel who caused the fault need to record it online. The coordination time is long, and it is impossible to provide timely guidance to the production personnel to avoid the fault, which brings great inconvenience to the coordination and overall planning of production quality management. For this reason, the present application proposes a digital twin system for industrial production. Compared with the prior art, the present invention can detect potential equipment failures early by real-time monitoring of the noise frequency of the equipment and analyzing the frequency change rate, accurately predict the maintenance time of the equipment, avoid downtime and production losses caused by sudden equipment failure, and improve the reliability and availability of the equipment.

[0041] This application uses sample data and digital twin models for analysis to provide data-driven decision support and help managers optimize maintenance plans; the digital twin model, combined with quality inspection data, can comprehensively evaluate equipment and product quality and provide more accurate quality management recommendations.

[0042] This application improves the overall efficiency of the production line by optimizing the maintenance time of equipment and reducing unplanned downtime; reasonably dispatches resources, such as personnel and spare parts, to reduce resource waste during maintenance; the intelligent guidance module can promptly notify and guide maintenance personnel to conduct inspections and repairs, ensuring that maintenance work is carried out in a timely and efficient manner.

[0043] The automated scheduling module (AGV) further improves the automation level of production line management and reduces human intervention and errors; the enterprise knowledge portal module (EKP) enables maintenance experience and data to be efficiently shared within the enterprise, improving the overall knowledge level and technical capabilities; the identity and access management module (IAM) ensures the secure management of data and information.

[0044] The present invention can significantly improve the intelligence level of equipment management and maintenance, reduce maintenance costs, improve the operating efficiency of equipment and production lines, and ensure the stability of product quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a structural schematic diagram of the digital twin system of the present invention applied to industrial production. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations.

[0047] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for which protection is sought, but merely represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0048] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0049] In the description of the present application, it should be noted that the terms "upper", "vertical", "inner", "outer", etc. indicate the orientation or position relationship based on the orientation or position relationship shown in the drawings, or the orientation or position relationship in which the product of the application is usually placed when in use, or the orientation or position relationship commonly understood by those skilled in the art. They are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present application. In addition, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0050] In the description of this application, it should also be noted that, unless otherwise clearly specified and limited, the terms "set", "install", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0051] Example 1

[0052] like Figure 1 As shown in the figure, the digital twin system applied to industrial production includes:

[0053] Sample data analysis module: Set collection points to obtain the noise frequency of the equipment during operation; obtain the time when the equipment is put into use and the time when it is repaired, and obtain the use time of the equipment; select several monitoring points during the use time, and the selection of monitoring points includes the time when the equipment is put into use and the time when it is repaired;

[0054] Obtain the noise frequency of each monitoring point during the use time of the equipment and record it as sample data; and obtain the maintenance frequency according to the noise frequency of the equipment at the time of maintenance; establish the frequency curve of the equipment according to the sample data; obtain the change rate of the noise frequency at each monitoring point according to the frequency curve, and obtain the relationship between the use time of the equipment and the change rate;

[0055] Digital data acquisition module: used to obtain production line data, including blade production line layout, equipment list, and capacity parameters;

[0056] Digital workshop module: A digital twin model is established based on production line data, and the noise frequency of the equipment obtained in real time is introduced into the digital twin model; the digital twin model establishes a real-time frequency curve of the equipment and obtains the rate of change of the real-time noise frequency, which is recorded as the real-time change rate; based on the real-time change rate and the relationship, the maintenance time of the equipment is predicted;

[0057] Smart guidance module: Determine the location of the equipment that has reached the maintenance time based on the maintenance time predicted by the digital twin model, and guide personnel to check the equipment in time;

[0058] Quality management module: used to obtain product quality inspection data, introduce the product quality inspection data into the digital twin model, and then use the digital twin model to analyze the quality inspection data.

[0059] When the existing digital twin system is applied to blade production, the image information and cause of the faulty blade are often recorded. The process and workstation where the fault occurs need to be independently counted, and the production personnel who caused the fault need to record it online. The coordination time is long, and it is impossible to provide timely guidance to the production personnel to avoid the fault, which brings great inconvenience to the coordination and overall planning of production quality management. For this reason, the present application proposes a digital twin system for industrial production. Compared with the prior art, the present invention can detect potential equipment failures early by real-time monitoring of the noise frequency of the equipment and analyzing the frequency change rate, accurately predict the maintenance time of the equipment, avoid downtime and production losses caused by sudden equipment failure, and improve the reliability and availability of the equipment.

[0060] This application uses sample data and digital twin models for analysis to provide data-driven decision support and help managers optimize maintenance plans; the digital twin model, combined with quality inspection data, can comprehensively evaluate equipment and product quality and provide more accurate quality management recommendations.

[0061] Example 2

[0062] See also Figure 1 As shown, the present invention is a digital twin system applied to industrial production, comprising:

[0063] Sample data analysis module: including collection points, which are used to obtain the noise frequency when the equipment is running; obtain the time when the equipment is put into use and the time when it is maintained, and obtain the use time of the equipment; select a number of monitoring points during the use time, and the monitoring points include the time when the equipment is put into use and the time when it is maintained.

[0064] Obtain the noise frequency of each monitoring point during the use time of the equipment and record it as sample data; and obtain the maintenance frequency according to the noise frequency of the equipment at the time of maintenance; establish the frequency curve of the equipment according to the sample data; obtain the change rate of the noise frequency at each monitoring point according to the frequency curve, and obtain the relationship between the use time of the equipment and the change rate;

[0065] It should be noted that the process of obtaining the frequency curve includes: establishing a rectangular coordinate system with time as the horizontal coordinate and noise frequency as the vertical coordinate; converting the noise frequency corresponding to each monitoring point into a corresponding coordinate point in the rectangular coordinate system, connecting each coordinate point with a smooth curve, and recording the curve as a frequency curve;

[0066] It is understandable that the collection points are set at key locations, and these collection points can effectively capture the noise generated by the operation of the equipment; the collection points include various sensors or microphones for real-time monitoring and recording of noise data; by recording the time when the equipment is put into use and the time of previous maintenance, the use time of the equipment is obtained, and these data are crucial for analyzing the life and maintenance cycle of the equipment; using the collected sample data, the frequency curve of the equipment is constructed, and this curve depicts the trend of the change of the equipment noise frequency over time, which helps to intuitively understand how the performance of the equipment changes with the use time; the relationship between the equipment use time and the noise frequency change rate is analyzed to find out whether there is a certain pattern or trend, such as whether the noise frequency increases or decreases with the increase of use time, so as to provide a basis for the preventive maintenance strategy of the equipment; by observing the noise frequency at the time of maintenance, a threshold can be set as a reference standard for future maintenance; when the noise frequency is close to this threshold, it means that equipment maintenance or replacement of parts may be required;

[0067] It is worth noting that the selection process of the monitoring point includes setting a time interval threshold, which is determined according to the use time of the device. The longer the use time of the device, the smaller the time interval threshold needs to be set, and the more corresponding monitoring points are selected; during the use time, each time interval threshold selects a time node, which is recorded as a monitoring point;

[0068] The process of obtaining the usage time includes recording the time period between the time of putting into use and the time of maintenance as the usage time;

[0069] The process of obtaining the maintenance frequency includes:

[0070] Get the noise frequency of all equipment at the time of maintenance, recorded as {f1, f2, ..., f n}, where f1 represents the noise frequency of the first device at the time of maintenance, and n is the total number of devices; the maintenance frequency is Where i∈[1,n] and i is a positive integer;

[0071] It can be understood that compared with the arithmetic mean, the geometric mean can better handle extreme values ​​in the data, such as maintenance frequencies that are too large or too small, and provide a smoother and more robust central tendency measure; the geometric mean is particularly suitable for data sets with multiplicative relationships; in noise frequency analysis, the frequency of equipment noise may have the characteristics of exponential growth or decay, so the geometric mean can better reflect these characteristics; the maintenance frequency is used to define the threshold value for equipment maintenance, and when the noise frequency of the equipment reaches or exceeds this geometric mean, it can be considered that the equipment needs maintenance;

[0072] The process of obtaining the rate of change of the noise frequency includes:

[0073] Obtain the derivative at each monitoring point on the frequency curve to obtain {D1, D2, ..., D m}, where D1 represents the derivative at the first monitoring point, and m is the total number of monitoring points; then the rate of change of the noise frequency is obtained Where j∈[1,m] and j is a positive integer;

[0074] The process of obtaining the relationship between the usage time and the change rate includes:

[0075] According to the sample data, the change rate and usage time of each device are obtained; a rectangular coordinate system is established, and a scatter plot is obtained in the rectangular coordinate system according to the change rate of each device and its corresponding usage time, and the scatter plot is fitted to obtain a regression equation of the scatter plot, which is recorded as a relationship between the maintenance time of the equipment and the frequency and the change rate;

[0076] It can be understood that the points in the scatter plot are first connected in sequence with a smooth curve, whether the curve is linear or nonlinear is determined, a suitable regression equation model is determined, the parameters in the regression equation model are continuously modified, the parameters are verified using the least squares method, and the final regression equation is obtained;

[0077] Digital data acquisition module: including material management module (MMS), identity and access management module (IAM), enterprise knowledge portal module (EKP) and automated scheduling module (AGV); the digital data acquisition module is used to obtain production line data, and the production line data includes blade production line layout, equipment list, and capacity parameters;

[0078] It should be noted that the production master data, material inventory information, and primary warehouse material delivery information are obtained from the SAP system (enterprise management software system). At the same time, the product output information and work order material consumption information are sent back to the SAP system during production reporting, which is convenient for the material and product account processing of the SAP system. For the convenience of internal personnel of the enterprise, there is no need to repeatedly enter the account number or password when using MMS, and it is integrated with IAM to verify user permissions. In order to ensure that workshop personnel are reminded of possible process change information in a timely manner and remind process personnel to handle it in a timely manner, MMS is integrated with the EKP module approval process information to remind process and production personnel of all project changes. In the production process, the consumption of workstation materials and the shortage of materials are timely called through MMS to distribute materials, ensuring the timely supply of materials and preventing the production line workstation from stopping due to material shortage.

[0079] Furthermore, the MMS is established based on the database and application server of the central computer room, and fully supports mainstream databases such as Oracle and SQLSERVER. It adopts the back-end technical architecture of Netcore3.1, Dapper, EF, etc. and the front-end technical architecture of element and Vue. The front and back ends are separated, and it supports multi-platform and microservice mode deployment and cloud deployment, which is convenient for users to use PDA, computer and mobile phone to operate the system. The internal master data management includes process standard data, quality standard data, process route data and product structure data, etc.;

[0080] Furthermore, the IAM is designed based on the ERP system, and is interconnected with the MMS in the form of files, API interfaces, intermediate databases or diameter access, including static data and dynamic data;

[0081] Furthermore, the static data includes: customer information, supplier information, product type information, material information, material unit information and product model information, etc., records personnel organization information, assists in personnel information management and position management, and can enter personnel information in each process through fingerprint recognition technology; the dynamic data includes: product BOM information, work order information, order information, material list information, inventory information, etc., which can be used for position authentication and working time analysis;

[0082] Furthermore, the AGV is based on the AGV carts of each process on the production line, which are centrally managed and coordinated to carry out process management, including production with insufficient materials, production with moved materials, temporary storage of wiring and AGV calling for materials;

[0083] Digital workshop module: a digital twin model is established according to the production line data, and the noise frequency of the equipment obtained in real time is introduced into the digital twin model; the digital twin model establishes a real-time frequency curve of the equipment and obtains the change rate of the real-time noise frequency, which is recorded as the real-time change rate; according to the real-time change rate and the relationship, the maintenance time of the equipment is predicted;

[0084] The digital twin model predicts the maintenance time of the equipment by:

[0085] Get the current time, record the time period between the time when the equipment is put into use and the current time as the time t0 that has been put into use; record the relationship between the use time and the change rate as T(d), where d represents the change rate of the noise frequency; record the real-time frequency change rate of the equipment as D0, and obtain the predicted use time of the equipment T(D0); then obtain the predicted maintenance time of the equipment as T(D0)-t0;

[0086] Smart guidance module: determines the location of the equipment that has reached the maintenance time according to the maintenance time of the equipment predicted by the digital twin model, and guides personnel to check the equipment in time;

[0087] It should be noted that based on MMS, the quality supervisor and process supervisor jointly formulate management regulations for production personnel with quality problems, the difficulty of the corresponding process and the proficiency of the production personnel, and guide the production personnel on site to avoid quality problems that have already occurred;

[0088] Quality management module: used to obtain product quality inspection data and introduce the product quality inspection data into the digital twin model, and the digital twin model analyzes the quality inspection data;

[0089] It is worth noting that the quality inspection data covers the quality information of multiple links in the process from production to delivery of products. These data are usually used to ensure that products meet customer needs and industry standards and prevent defective products from entering the market. The quality inspection data includes the quality inspection date, quality inspector information, appearance inspection, functional testing and defect records, etc.

[0090] Furthermore, the quality management module changes the quality inspection from manual paper recording mode to electronic recording mode, which is convenient for traceability and data result viewing, and classifies the quality inspection items into the warehouse. The quality inspection work of the blades includes self-inspection, mutual inspection, patrol inspection, special inspection, and special inspection. Different inspection templates are set, and inspection tasks are automatically generated in the system according to the template rules. In this way, it can ensure that the products are inspected as much as possible and inspected on demand, and the full process traceability of product quality inspection and quality control information can be achieved. The rules of quality inspection items require unified electronic management to ensure that all products can be strictly inspected and managed on-site in accordance with quality management requirements, thereby improving the overall quality management level and standards; the quality management module supports the following input formats:

[0091] Text input, through NCR data transmission, such as system reminder or email; the NCR is a report of non-conforming products;

[0092] Data input, recording the inflow and outflow of workpieces and the information of production personnel in each process through the bar code system;

[0093] Photos and photo annotations are used to record the on-site quality problem handling process and processing data.

[0094] Furthermore, the quality problems caused by production personnel are recorded according to the process, and statistics are made in a line chart using time and quantity standards. The processes are marked with increasing difficulty in the order of the increasing number of quality problems, and the production personnel are marked with increasing proficiency in the order of the decreasing number of quality problems, which is conducive to improving the degree of digitalization of quality management.

[0095] Furthermore, the quality inspection steps of the blades are as follows:

[0096] S1. Start: Confirm tool debugging, process documents and quality inspection task rules in sequence;

[0097] S2. Clamping: put the blade to be inspected into the fixture and fix it;

[0098] S3. Inspection: Quality inspectors, process personnel and production personnel jointly visually inspect the blades, confirm various parameters, reach a consensus on site, and avoid disputes;

[0099] S4, end: affix the corresponding product serial number label, scan and confirm that the inspection is complete, and push it to the assembly area or assembly station;

[0100] S5. Rework: Repair the blades that can be repaired.

[0101] Furthermore, the management regulations of the smart guidance module are as follows:

[0102] 1) Job transfer: transfer production personnel from more difficult process positions to less difficult positions in the same process;

[0103] 2) Resume production: transfer production personnel with high proficiency in the process to the position to maintain the normal operation of the production line in a timely manner and reduce the adverse impact of quality problems on the production plan;

[0104] 3) Improve quality: Plan the time period for completing production targets, and conduct centralized training and assessment for production personnel with lower proficiency by process, which will help improve the overall production level of the blade production line;

[0105] It should be noted that the process of analyzing the quality inspection data by the digital twin model includes effective cleaning, sorting and storage of the quality inspection data to ensure the quality and availability of the data and provide a solid foundation for subsequent analysis; applying statistical methods and machine learning algorithms to conduct in-depth analysis of the collected historical and real-time data to identify patterns and trends that may lead to quality problems; by establishing a predictive model, the digital twin can predict quality problems that may occur under specific production conditions, so as to take preventive measures in advance; when a quality problem is detected, the digital twin model can quickly locate the source of the problem, whether it is unqualified raw materials, abnormal production equipment or operational errors; by analyzing the contextual information and parameter settings that cause the problem, the root cause is found and recorded to provide a basis for completely solving the problem; the digital twin model can automatically generate detailed quality analysis reports, which include defect types, incidence rates, possible causes and countermeasures, etc.

[0106] It should be further explained that, based on the computers of each process, the quality management signals sent by the EKP module are received, the quality inspection process is optimized and paperless, and the quality inspection items are classified and stored, and the product quality inspection and management are carried out on-site.

[0107] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. The digital twin system applied to industrial production is characterized by: include: Sample data analysis module: set the collection points, which are used to obtain the noise frequency when the equipment is running; Obtain the time when the equipment is put into use and the time when it is repaired, and obtain the use time of the equipment; select several monitoring points during the use time, and the selection of monitoring points includes the time when the equipment is put into use and the time when it is repaired; Obtain the noise frequency of each monitoring point during the use time of the equipment and record it as sample data; And obtain the maintenance frequency according to the noise frequency of the equipment at the time of maintenance; According to the sample data, a frequency curve of the equipment is established; according to the frequency curve, the change rate of the noise frequency at each monitoring point is obtained, and a relationship between the use time of the equipment and the change rate is obtained; Digital data acquisition module: used to obtain production line data, including blade production line layout, equipment list, and capacity parameters; Digital workshop module: A digital twin model is established based on production line data, and the noise frequency of the equipment obtained in real time is introduced into the digital twin model; the digital twin model establishes a real-time frequency curve of the equipment and obtains the rate of change of the real-time noise frequency, which is recorded as the real-time change rate; based on the real-time change rate and the relationship, the maintenance time of the equipment is predicted; Smart guidance module: Determine the location of the equipment that has reached the maintenance time based on the maintenance time predicted by the digital twin model, and guide personnel to check the equipment in time; Quality management module: used to obtain product quality inspection data, introduce the product quality inspection data into the digital twin model, and then use the digital twin model to analyze the quality inspection data.

2. The digital twin system applied to industrial production according to claim 1, characterized in that: The equipment usage time in the sample data analysis module is obtained by recording the time period between the time of commissioning and the time of maintenance as the usage time.

3. The digital twin system applied to industrial production according to claim 1, characterized in that: The monitoring point selection process in the sample data analysis module includes: setting a time interval threshold, the time interval threshold is determined according to the use time of the equipment, and during the use time, each time interval threshold selects a time node, which is recorded as a monitoring point.

4. The digital twin system for industrial production according to claim 1, characterized in that: The process of obtaining the maintenance frequency in the sample data analysis module includes: Get the noise frequency of all equipment at the time of maintenance, recorded as {f1, f2, ..., f n }, where f1 represents the noise frequency of the first device at the time of maintenance, and n is the total number of devices; the maintenance frequency is Where i∈[1,n] and i is a positive integer.

5. The digital twin system for industrial production according to claim 1, characterized in that: The process of obtaining the noise frequency change rate in the sample data analysis module is as follows: Obtain the derivatives at each monitoring point on the frequency curve and obtain {D1, D2, ..., D m }, where D1 represents the derivative at the first monitoring point, and m is the total number of monitoring points; then the rate of change of the noise frequency is obtained Where j∈[1,m] and j is a positive integer.

6. The digital twin system for industrial production according to claim 1, characterized in that: The process of obtaining the relationship between time and rate of change in the sample data analysis module is as follows: According to the sample data, the change rate and usage time of each device are obtained; a rectangular coordinate system is established, and a scatter plot is obtained in the rectangular coordinate system according to the change rate of each device and its corresponding usage time. The scatter plot is fitted to obtain the regression equation of the scatter plot, which is recorded as the relationship between the maintenance time of the equipment and the frequency and the change rate.

7. The digital twin system for industrial production according to claim 1, characterized in that: The prediction process of the maintenance time of the equipment by the digital twin model in the digital workshop module is as follows: Get the current time, record the time period from the time the equipment is put into use to the current time as the time t0 that has been put into use; record the relationship between the use time and the change rate as T(d), where d represents the change rate of the noise frequency; record the real-time frequency change rate of the equipment as D0, and obtain the predicted use time T(D0) of the equipment; then the predicted maintenance time of the equipment is T(D0)-t0.

8. The digital twin system for industrial production according to claim 1, characterized in that: The quality management module classifies the quality inspection items into the warehouse. The blade quality inspection work includes self-inspection, mutual inspection, patrol inspection, special inspection, and special inspection. Inspection templates are set for each. Inspection tasks are automatically generated in the system according to the template rules. The quality management module supports the following input formats: Text input, transmitted through NCR data; the NCR is a report of non-conforming products; Data input, recording the inflow and outflow of workpieces and the information of production personnel in each process through the bar code system; Photos and photo annotations are used to record the on-site quality problem handling process and processing data.

9. The digital twin system for industrial production according to claim 8, characterized in that: The quality inspection steps of the leaves are as follows: S1. Start: Confirm tool debugging, process documents and quality inspection task rules in sequence; S2. Clamping: put the blade to be inspected into the fixture and fix it; S3. Inspection: Quality inspectors, process personnel and production personnel jointly visually inspect the blades to confirm various parameters; S4, end: affix the corresponding product serial number label, scan and confirm that the inspection is complete, and push it to the assembly area or assembly station; S5. Rework: Repair the blades that can be repaired.

10. The digital twin system applied to industrial production according to claim 1, characterized in that: The management regulations of the smart guidance module are as follows: 1) Job transfer: transfer production personnel from high-difficulty process positions to low-difficulty positions in the same process; 2) Resume production: transfer production personnel with high proficiency in the process to the position to maintain the normal operation of the production line in a timely manner; 3) Improve quality: Planning the time period for completing life goals and conducting centralized training and assessment of production personnel with lower proficiency by process will help improve the overall production level of the blade production line.