Production traceability control method and system of digital chemical plant under internet of things

Abstract

The application discloses a production traceability control method and system of a digital intelligent factory under the Internet of Things, and relates to the technical field of production traceability control methods. The current production path is determined according to the current working state of the digital intelligent factory and the model of a workpiece, and the production abnormal area of the workpiece is determined based on the current production path and an abnormal production path, thereby improving the accuracy of the production abnormal area of the workpiece. Therefore, the repair time nodes of each abnormal factory component are determined based on the abnormal factory components corresponding to the production abnormal area, the Internet of Things and the current production position of the workpiece, the repair workloads of each abnormal factory component are determined according to the repair time nodes of each abnormal factory component and the production procedure table corresponding to the workpiece, and the autonomous repair strategy of the digital intelligent factory for the workpiece is determined according to the repair workloads of each abnormal factory component and the Internet of Things, thereby improving the accuracy of the autonomous repair strategy of the digital intelligent factory for the workpiece.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of production traceability control methods, and particularly relates to a production traceability control method and system of a digital intelligent factory under the Internet of Things. BACKGROUND

[0002] With the development of science and technology, digital intelligent factories are gradually applied to people's lives and can produce workpieces in an unmanned state. A digital intelligent factory deeply integrates a physical production environment and a digital virtual environment, and is a modern factory mode that comprehensively digitizes production, management, operation and other links of a factory. In the prior art, a workpiece is autonomously processed in a digital intelligent factory, and is produced in corresponding factory components along each process item content of a production process table. However, the digital intelligent factory has some abnormal production data for the production of the workpiece, and triggers the digital intelligent factory to stop the production of the workpiece based on the abnormal production data, and cannot trace and control the abnormal production data, which affects the accuracy of the autonomous repair strategy of the digital intelligent factory for the workpiece. SUMMARY

[0003] The present application aims to overcome the shortcomings of the prior art, and provides a production traceability control method and system of a digital intelligent factory under the Internet of Things.

[0004] The embodiment of the present application provides a production traceability control method of a digital intelligent factory under the Internet of Things, which comprises the following steps: collecting a plurality of production data combinations of a digital intelligent factory at different production nodes, and constructing a digital intelligent database based on each production data combination and the Internet of Things; performing production traceability on a plurality of abnormal production data in each production data combination based on the digital intelligent database to determine corresponding abnormal production nodes, and determining an abnormal production path according to the positions of each abnormal production node and the abnormal ranges of the abnormal production data; determining a current production path according to the current working state of the digital intelligent factory and the model of a workpiece, determining a production abnormal area of the workpiece based on the current production path and the abnormal production path; determining a repair time node of each abnormal factory component based on the abnormal factory components corresponding to the production abnormal area, the Internet of Things and the current production position of the workpiece, determining the repair workloads of each abnormal factory component according to the repair time nodes of each abnormal factory component and a production process table corresponding to the workpiece; determining an autonomous repair strategy of the digital intelligent factory for the workpiece according to the repair workloads of each abnormal factory component and the Internet of Things, and not affecting the normal production of the workpiece, so as to repair each abnormal factory component as early as possible.

[0005] The embodiment of the present application provides a production traceability control system of a digital intelligent factory under the Internet of Things, which is applied to the production traceability control method of the digital intelligent factory under the Internet of Things, and comprises:

[0006] The intelligent digital database module is used to collect multiple production data combinations at different production nodes in the intelligent digital factory, and to build an intelligent digital database based on each production data combination and the Internet of Things;

[0007] The abnormal production path module is used to trace the source of multiple abnormal production data in various production data combinations based on the digital database, in order to identify the corresponding abnormal production nodes, and to determine the abnormal production path based on the location of each abnormal node and the abnormal range of the abnormal data.

[0008] The production anomaly area module is used to determine the current production path based on the current working status of the smart factory and the model of the workpiece, and to determine the production anomaly area of ​​the workpiece based on the current production path and the abnormal production path.

[0009] The repair workload module is used to determine the repair time node for each abnormal factory component based on the current production location of the abnormal factory component, IoT and workpiece corresponding to the abnormal production area, and to determine the repair workload for each abnormal factory component according to the repair time node of each abnormal factory component and the production process table corresponding to the workpiece.

[0010] The autonomous repair strategy module is used to determine the autonomous repair strategy for each abnormal factory component based on the repair workload and IoT, without affecting the normal production of the component, so as to repair each abnormal factory component in advance.

[0011] Compared with the prior art, the beneficial effects of the present invention are:

[0012] In this embodiment of the invention, the abnormal production path is determined based on the location of each abnormal production node and the abnormal range of the abnormal production data. The current production path is determined based on the current working status of the intelligent factory and the model of the workpiece. Based on the current production path and the abnormal production path, the abnormal production area of ​​the workpiece is determined. By introducing each abnormal production node, the overall consideration of the current production path and the abnormal production path is taken into account, which improves the accuracy of the abnormal production area of ​​the workpiece and enables traceability and control of the production of the intelligent factory.

[0013] Therefore, the repair time node of each abnormal factory component is determined based on the abnormal factory component corresponding to the abnormal production area, the current production position of the Internet of Things and the workpiece, the repair workload of each abnormal factory component is determined according to the repair time node of each abnormal factory component and the production process table corresponding to the workpiece, and the autonomous repair strategy of the smart factory for the workpiece is determined according to the repair workload of each abnormal factory component and the Internet of Things. The repair time node of each abnormal factory component is introduced, the overall consideration of the repair workload of each abnormal factory component and the Internet of Things is realized, the accuracy of the autonomous repair strategy of the smart factory for the workpiece is improved, and the normal production of the workpiece is not affected, so as to repair each abnormal factory component as early as possible. BRIEF DESCRIPTION OF DRAWINGS

[0014] Figure 1 is a flowchart of a production traceability control method of a smart factory under the Internet of Things in an embodiment of the application;

[0015] Figure 2 is a flowchart of step S11 in the production traceability control method of the smart factory under the Internet of Things in an embodiment of the application;

[0016] Figure 3 is a flowchart of step S12 in the production traceability control method of the smart factory under the Internet of Things in an embodiment of the application;

[0017] Figure 4 is a flowchart of step S13 in the production traceability control method of the smart factory under the Internet of Things in an embodiment of the application;

[0018] Figure 5 is a flowchart of step S14 in the production traceability control method of the smart factory under the Internet of Things in an embodiment of the application;

[0019] Figure 6 is a flowchart of step S15 in the production traceability control method of the smart factory under the Internet of Things in an embodiment of the application;

[0020] Figure 7 is a structural composition diagram of a production traceability control system of a smart factory under the Internet of Things in an embodiment of the application. DETAILED DESCRIPTION

[0021] The technical solutions in the embodiments of the application will be described clearly and completely below with reference to the drawings in the embodiments of the application.

[0022] Please refer to Figures 1 to 7 A production traceability control method of a smart factory under the Internet of Things, applied to a production traceability control scene; the production traceability control method of the smart factory under the Internet of Things comprises:

[0023] Step S11: Collect multiple production data combinations of the intelligent factory at different production nodes, and build an intelligent database based on each production data combination and the Internet of Things;

[0024] Step S12: Multiple abnormal production data in each production data combination is subjected to production traceability based on the intelligent database to determine the corresponding abnormal production node, and the abnormal production path is determined according to the position of each abnormal production node and the abnormal range of the abnormal production data;

[0025] Step S13: Determine the current production path according to the current working state of the intelligent factory and the model of the workpiece, and determine the production abnormal area of the workpiece based on the current production path and the abnormal production path;

[0026] Step S14: Determine the repair time node of each abnormal factory component based on the abnormal factory component corresponding to the production abnormal area, the Internet of Things, and the current production position of the workpiece, and determine the repair workload of each abnormal factory component according to the repair time node of each abnormal factory component and the production process table corresponding to the workpiece;

[0027] Step S15: Determine the autonomous repair strategy of the intelligent factory for the workpiece according to the repair workload of each abnormal factory component and the Internet of Things, and do not affect the normal production of the workpiece, so as to repair each abnormal factory component in advance.

[0028] Reference Figure 2 In step S11, the specific steps are:

[0029] S111: When the workpiece is machined by the intelligent factory, the numerical process of the workpiece in the intelligent factory is collected, and multiple autonomous production processes are determined according to the division of the numerical process, and multiple production nodes are determined according to the multiple autonomous production processes and the model of the workpiece;

[0030] S112: Multiple production nodes are distributed at different positions of the intelligent factory and are used for different machining processes of the workpiece; multiple production data of each production node are collected by real-time monitoring of the multiple production nodes, and the corresponding production data combination is determined according to the synthesis of the multiple production data in each production node;

[0031] S113: Based on the node position of the production node, the corresponding production data combination, and the synthesis of the Internet of Things corresponding to the intelligent factory, an intelligent database is built, which is dynamically updated with the increase of production data.

[0032] In the embodiments of the present application, when unmanned machining is performed on a workpiece in a smart factory, a numerical process for the workpiece is introduced into the smart factory, which refers to detailed digital instructions and blueprints describing how to manufacture the workpiece, and is usually derived from CAD (Computer Aided Design) and CAM (Computer Aided Manufacturing) systems; the numerical process usually includes geometric information, process information, and operation steps.

[0033] The purpose of division is to divide a continuous or complex numerical process into smaller parts; the basis for division can include physical equipment / positions, operation types, and logical stages, to output multiple autonomous production processes, which are relatively independent manufacturing units.

[0034] Multiple autonomous production processes and workpiece models are introduced, different workpiece models (even the same series of products) have different sizes, materials, precision requirements, or machining paths; therefore, workpiece model information needs to be considered to ensure that the defined production nodes are specific to the current workpiece.

[0035] A production node is a specific embodiment of an autonomous production process in physical space or logical flow, which is usually a key point with a clear location and monitoring requirement; one autonomous production process corresponds to one or more production nodes, for example, the autonomous production process of "CNC fine milling" corresponds to multiple production nodes such as "clamping positioning completion point", "fine milling processing start point", "fine milling processing end point" on CNC machine C, and each node needs to collect different data (such as clamping force, vibration during processing, size after processing, etc.).

[0036] Further, multiple production nodes are distributed in different positions of the smart factory, and each production node is associated with one or more specific machining processes, for example, the "CNCA rough milling process point" corresponds to the rough milling machining process performed on the CNCA machine, and this association ensures that the collected data can be correctly attributed to the corresponding manufacturing step.

[0037] Real-time monitoring of multiple production nodes is achieved through Internet of Things sensors and actuators deployed at each production node; sensors convert physical world signals (such as temperature, vibration, position) into digital signals, and these devices are connected to edge computing nodes or directly connected to cloud platforms / data centers through wired or wireless networks; each production node usually has more than one sensor or data source, for example, a CNC machine node outputs multiple data streams such as spindle speed, feed speed, X / Y / Z axis position, current, temperature, etc., which collectively describe the running state of the node.

[0038] The synthesis of multiple production data is not simply data accumulation, but refers to the integration, correlation or calculation of multiple related data items from the same production node to form a more meaningful data structure or feature vector that can reflect the overall state of the node; the synthesis method depends on the application requirements and analysis goals; including: simple aggregation: such as calculating the average, maximum, minimum, standard deviation, etc. in a period of time; state description: combining multiple Boolean signals into a state description (such as "device running normally", "processing", "waiting for materials"); feature extraction: using signal processing techniques (such as FFT for frequency domain analysis) or statistical methods to extract key features from raw data; the "production data combination" after synthesis should be more concise and informative than the original data.

[0039] Therefore, based on the node position of the production node, the corresponding production data combination and the synthesis of the corresponding Internet of Things of the digital intelligent factory, a digital intelligent database is constructed, which is dynamically updated with the increase of production data, and the overall consideration of the node position of the production node, the corresponding production data combination and the synthesis of the corresponding Internet of Things of the digital intelligent factory is compatible, which ensures the accuracy of the digital intelligent database.

[0040] At this time, the node position of the production node, the corresponding production data combination and the corresponding Internet of Things of the digital intelligent factory are introduced, each production node has its unique physical position information, which is the coordinate in the workshop, equipment number or process number, etc.; the corresponding production data combination refers to the structured data set collected from each production node in real time, as described above, including timestamp, process parameter, equipment state, etc. These data combinations need to be associated with a specific production node to ensure data consistency and accuracy; the Internet of Things technology provides the infrastructure for data acquisition, transmission and storage, including sensors, communication networks, data storage servers, etc.

[0041] Integrate the node position, production data combination and Internet of Things infrastructure to build a unified digital intelligent database, which needs to support real-time storage, query and analysis of large-scale data; as production proceeds, new data will be continuously generated and need to be added to the database; the database needs to support real-time updating to ensure the timeliness and accuracy of the data; integrate scattered production data into a centralized and structured digital intelligent database.

[0042] Reference Figure 3 In step S12, the specific steps are:

[0043] S121: Collect each production data combination, determine the corresponding abnormal production detection mode based on the matching of each production data combination and the digital intelligent database, and trigger the abnormal detection of each production data combination along the abnormal production detection mode to output multiple abnormal production data;

[0044] S122: Label the abnormal positions corresponding to the plurality of abnormal production data, determine the corresponding production traceability mode according to the abnormal positions, the corresponding abnormal production data and the digitalization database, determine a plurality of traceability items based on the analysis of the production traceability mode, the plurality of traceability items cross-trace the workpiece, and trigger production traceability of the plurality of abnormal production data to determine a plurality of abnormal production nodes;

[0045] S123: At each abnormal production node, determine the abnormal range of abnormal production data based on the comparison of the corresponding plurality of abnormal production data, and determine the abnormal production path based on the position of each abnormal production node, the abnormal range of abnormal production data and the workpiece;

[0046] In the embodiments of the present application, each production data combination is collected, and the digitalization database not only stores real-time data, but also stores historical normal data, equipment parameters, process procedures, and even predefined abnormal mode templates. The "matching" here refers to comparing the currently collected production data combination with the information stored in the database.

[0047] The matching process involves: checking whether the current data exceeds the normal parameter range of the node, the workpiece model, and the process stored in the database (for example, the normal range of spindle current is 10-15A, and the normal range of vibration amplitude is 0.05-0.20mm / s); comparing the current data pattern with the known abnormal patterns stored in the database (for example, the pattern of simultaneous abnormality of vibration and current in history usually corresponds to tool wear); applying the rule engine stored in the database, which is generated based on expert knowledge or machine learning model (for example, "if the vibration amplitude exceeds 0.25mm / s for 3 times in a row, and the spindle current exceeds 13A, then trigger an abnormal alarm"); using the statistical model (such as control chart, time series model) or machine learning model (such as model parameters of anomaly detection algorithm) stored in the database to judge whether the current data meets the expectation.

[0048] Once the applicable abnormal detection mode is determined, the system will analyze the collected production data combination according to the definition of the mode to identify specific abnormal points or abnormal periods. According to the determined mode, the detection is performed: if it is parameter range matching, check which data points exceed the range; if it is historical pattern matching, calculate the similarity and judge whether the abnormal threshold is reached; if it is a rule engine, check whether the rule condition is met; if it is model matching, use the model to predict the normal value, calculate the deviation between the actual value and the predicted value, and judge whether it is abnormal.

[0049] Further, the abnormal position corresponding to the plurality of abnormal production data is marked, and the marking contains key information of the abnormal data itself, such as abnormal type, occurrence time, specific parameter value involved, workpiece ID to which it belongs, and most importantly, the production node position where it occurs; optionally, the system updates the record in the database, or maintains an abnormal list in the memory, which clearly indicates that "workpiece W-2025-0715-001 has an abnormality of tool wear suspicion at CNC A Rough Mill node during 2025-07-1514:14:00-14:15:00, and the key indicator is vibration 0.32 mm / s and current 13.5 A".

[0050] The system needs to select the most appropriate traceability method according to the position where the abnormality occurs (which node), the specific characteristics of the abnormality (what abnormality, how serious), and the process knowledge, material flow information, and equipment association stored in the database.

[0051] The traceability methods include: forward traceability: starting from the abnormal node, tracing the reason backward (for example, the processing quality of the previous node, the problem of the material itself, the state of the tooling fixture, etc.); backward traceability: starting from the abnormal node, tracing the impact backward (for example, how the abnormality affects the processing accuracy of the subsequent process, the detection pass rate of the final product, etc.); path traceability: tracing along the actual processing path of the workpiece to check the data and state of all related nodes on the path; causal traceability: attempting to analyze the causal relationship between abnormal data and potential causes (for example, whether vibration abnormality necessarily leads to size deviation).

[0052] The system analyzes the abnormal data, for example, "tool wear suspicion" usually means that the problem originates from the tool itself (forward traceability) or the processing state of the previous step (forward traceability), and also affects the processing accuracy of the subsequent step (backward traceability); the system queries the database to see if there is any associated information about CNCA rough milling process, upstream clamping process, downstream fine milling process, and tool replacement record, etc.; the database stores the rule that "rough milling quality directly affects the fine milling allowance", or records the fact that "tool T-12345 was last replaced on 2025-07-10"; the system determines that the traceability method mainly uses "forward traceability" combined with "path traceability", and focuses on the state of CNCA clamping process point (CNCALoad) and tool T-12345.

[0053] After the traceability mode is determined, it needs to be decomposed into specific and executable operation items, i.e. traceability items, which are the units of actually performing traceability analysis; the traceability items include: checking the historical data of a specific parameter: for example, checking the vibration and current data trends of tool T-12345 in the past few days; comparing the data of different workpieces: for example, comparing the data of workpiece W-2025-0715-001 with other workpieces in the same batch at the CNCARoughMill node; querying the material / equipment status: for example, querying the clamping force data of the workpiece at the CNCALoad node, querying the inventory record and wear record of tool T-12345; checking the process parameters: for example, checking whether the cutting parameters (rotation speed, feed rate) of the CNCA rough milling process are consistent with the process specification.

[0054] The system executes the traceability items determined in S122-3 in parallel or in series to collect information from different angles; then, the system cross-compares and analyzes these information from different items to verify the hypothesis, exclude interference, and finally determine which production nodes are directly related to the current anomaly.

[0055] Cross-tracing means that the results obtained from different traceability items need to be verified by each other, for example, if the tool historical data shows that its vibration has been normal, and the clamping force data shows an anomaly, then the clamping problem is the cause; vice versa; if the data of other workpieces in the same batch is normal, it points to the problem of the workpiece itself or its specific machining process.

[0056] Performing traceability items is actually a process of extracting relevant information from the database and correlating and analyzing these information with the initial anomaly data; the ultimate goal is to find out those production nodes that directly cause or significantly affect the current anomaly, which includes the nodes where the anomaly occurs, as well as the upstream or downstream nodes.

[0057] Therefore, the abnormal range of the abnormal production data is determined based on the comparison of the corresponding multiple abnormal production data at each abnormal production node, and the abnormal production path is determined based on the position of each abnormal production node, the abnormal range of the abnormal production data, and the workpiece, which is compatible with the overall consideration of the position of each abnormal production node, the abnormal range of the abnormal production data, and the workpiece, ensuring the accuracy of the abnormal production path.

[0058] At this time, at each abnormal production node, the corresponding multiple abnormal production data are compared. The comparison usually includes the following: time series comparison: observe the trend of abnormal data over time; is it a sudden jump or a slow deterioration, how long does the abnormality last, threshold comparison: compare the abnormal data with the pre-defined threshold (such as used in S121), determine the amplitude and duration of exceeding the threshold, historical data comparison: compare the current abnormal data with the data of the same type of workpiece in the past normal production of the node, see the amplitude of deviation from the normal range, same batch / same condition comparison: if there are multiple workpieces passing through the node in the same time period, compare their data to see if the abnormality is specific to a certain workpiece or universal, parameter comparison: analyze the correlation between different sensor data in the same node, for example, whether vibration abnormality is accompanied by current abnormality, whether temperature rises, through the above comparison, determine the specific performance of the abnormality (such as vibration amplitude exceeding the normal range by 0.1mm / s for 30 seconds), the degree of influence (slight, moderate, severe) and the range of influence (only affecting the current workpiece specific area, or affecting the subsequent process); the system will generate a detailed abnormality analysis report to quantify the degree of abnormality.

[0059] The position of each abnormal production node, the abnormal range of abnormal production data, and the workpiece, node order: the order of the production process; abnormal range: the severity and nature of the impact of the abnormality (whether it directly affects the geometry of the workpiece, or indirectly affects the state of the subsequent process); workpiece characteristics: the process sensitivity of the workpiece itself; the system will mark the abnormal path on the visualization interface (such as the production process diagram) according to the analysis results, or generate a written report to describe the path; the abnormal path describes how the problem affects the workpiece from the source, and how it manifests or intensifies in subsequent nodes.

[0060] Reference Figure 4 In step S13, the specific steps are as follows:

[0061] S131: Collect the response signals of each production node in the intelligent factory, determine the state coefficient of each production node according to the analysis of each response signal, and determine the current working state of the intelligent factory according to the node position, state coefficient of each production node, and the number of processed workpieces corresponding to the intelligent database;

[0062] S132: Collect the model of the workpiece, determine the processing form of the workpiece according to the model and external form of the workpiece, and determine the current production path according to the processing form of the workpiece, the current working state of the intelligent factory, and the multiple production nodes;

[0063] S133: comparing the current production path and the abnormal production path, determining an overlapping region according to the comparison of the current production path and the abnormal production path, determining a plurality of sub-abnormal regions according to the detection of the overlapping region, and determining a production abnormal region of the workpiece according to the synthesis of the plurality of sub-abnormal regions;

[0064] In the embodiments of the present application, the current state information of each production node (such as machine tools, robots, sensors, detection equipment, etc.) in the factory is collected in real time or quasi-real time, and the information is transmitted through an Internet of Things (IoT) network.

[0065] Data types: status signals: “NodeA: processing”, “NodeB: idle”, “NodeD: detection completed”; performance signals: “NodeA: spindle speed 8000 RPM”, “NodeA: feed speed 500 mm / min”, “NodeC: tool wear 0.05 mm”; sensor signals: “NodeA: cutting area temperature 85°C”, “NodeC: vibration sensor reading 0.8g”, “environmental temperature and humidity”; event signals: “NodeA: alarm ALM-101 (tool breakage) occurred”, “NodeD: out-of-tolerance workpiece detected”; material signals: “NodeA: workpiece has been loaded”, “NodeB: abrasive bucket liquid level low”.

[0066] The collected raw response signals are usually discrete, heterogeneous, and difficult to directly use for overall state evaluation; therefore, it is necessary to analyze and convert these signals to one or more “state coefficients” that can quantify the current operating status of the node, and this analysis process involves: filtering, denoising, and normalizing the raw signals; comparing continuous signals (such as temperature, vibration) with preset thresholds to determine whether they are in normal, warning, or dangerous states, for example, if the vibration sensor reading of NodeC exceeds 1.0g, it is determined to be in a dangerous state; using machine learning models (such as SVM, neural networks) to comprehensively analyze a group of signals to determine whether the node is in a specific mode (such as normal processing, standby, overload, impending failure); assigning weights to different types of signals or states and calculating a comprehensive score as a state coefficient, for example, a simple scoring formula is: state coefficient = w1*state score + w2*performance score + w3*safety score, where each score comes from the analysis of the corresponding signal.

[0067] The state coefficients of individual nodes, combined with their positions in the factory production process and the overall production progress of the factory, form a macroscopic evaluation of the current working state of the entire factory; the number of workpieces that have successfully completed processing is recorded in the digital database, which reflects the production efficiency and current load of the factory.

[0068] Node position: Understanding the position of nodes helps identify production bottlenecks. For example, if Node D, located at the end of the process, has a low state coefficient (e.g., due to a malfunction), the entire production process will stall, even if the nodes before it are in good condition. If an intermediate node (e.g., Node B) has a low state coefficient, it will affect the quality or speed of input to subsequent nodes. State coefficient: By combining the state coefficients of all nodes, a factory-wide state index (e.g., a weighted average) can be calculated, which reflects the overall health of the factory (whether it is running smoothly, partially restricted, or close to collapse).

[0069] Number of processed workpieces: This number reflects the output speed and load of the factory. If the number of processed workpieces is much lower than planned, combined with the node state coefficients, it can be determined that the factory is in a state of low efficiency or stagnation. If the number is close to or reaches the plan, and the node state coefficients are generally high, it indicates that the factory is running well. The system will combine the above information to generate a descriptive "current working state," which is a textual description (e.g., "the factory is running smoothly, efficiency meets standards, Node C has a slight vibration anomaly, attention needed") and a comprehensive score (e.g., "factory state index: 0.82"), or a more structured state report.

[0070] Further, the model of the collected workpiece is collected, and the model and external form of the workpiece are introduced. Using the workpiece model information, combined with its actual physical state (external form), the specific processing operation type and sequence needed are determined, which involves mapping general model information to specific processing strategies. "External form" refers to the current actual state of the workpiece, including: initial state: blank, semi-finished product, or workpiece needing repair; processed features: which parts have been processed; which parts still need to be processed; physical state: whether there is deformation or damage; whether the size is within the allowed range.

[0071] The system will query the process database or digital twin model related to the model; the database stores recommended processing strategies for different models and different initial / current forms, such as the processing form of "TL-A2-V3" blank is "rough machining + deburring + finishing"; while the processing form of a "TL-A2-V3" semi-finished product (rough machining completed) is "deburring + finishing"; the system will combine sensor data (such as visual inspection, size measurement) to confirm the current external form of the workpiece, ensuring the accuracy of the processing form.

[0072] Generating a specific, executable workpiece movement and processing route in the factory requires comprehensive consideration of: processing mode: determine which types of processes need to be passed (such as rough machining, deburring, finishing); current working state (from S131): each production node (machine tool, robot, etc.) is currently idle, busy, failure or performance decline; whether the material handling equipment (such as AGV) is available; whether the energy supply is stable; multiple production nodes: which devices can perform the required processes, where are their locations; whether there is a specific device suitable for processing the model workpiece (such as a specific model machine tool).

[0073] The system will select the appropriate process node according to the processing mode; then, combined with the state of each node determined in S131, intelligent scheduling is carried out: preferentially select nodes with good state (high state coefficient), idle or about to be idle; if there are multiple selectable nodes (for example, there are two rough machining centers), the one with lower current load, better location (reduce material handling time) or better state will be selected; the physical connection between nodes and the material handling capacity (such as AGV path planning) need to be considered; finally, a specific, time-sequenced node sequence, i.e. "current production path", is determined.

[0074] Therefore, by comparing the current production path and the abnormal production path, determining the overlapping area according to the comparison of the current production path and the abnormal production path, determining a plurality of sub-exceptional areas according to the detection of the overlapping area, and determining the production abnormal area of the workpiece according to the synthesis of the plurality of sub-exceptional areas, the synthesis of the plurality of sub-exceptional areas is compatible, the accuracy of the production abnormal area of the workpiece is guaranteed, meanwhile, the introduction of each abnormal production node is compatible, the overall consideration of the current production path and the abnormal production path is improved, the accuracy of the production abnormal area of the workpiece is improved, and the production of the intelligent factory is traced and controlled.

[0075] At this time, find the similar or overlapping part between the processing flow of the current workpiece and the known abnormal processing flow, where "abnormal production path" refers to the production node sequence involved in the previously detected abnormal data; The comparison is not only to see if the node names are the same, but also to consider whether the node type, processing content, workpiece state, etc. are related.

[0076] The system will match the current production path (a sequence of nodes) with the historical production paths (or abnormal paths) stored in the database that are related to the confirmed abnormality, for example, the database records an abnormal path: AGV > CNCARoughMill > AGV > DeburrRobot > AGV > CNCARoughMill > AGV > DimensionInspection; when comparing, the system will check which nodes in the current path and the abnormal path are the same, or which nodes have similar functions / positions although their names are different; the current production path comes from the output of S132; the abnormal production path comes from the abnormal production nodes determined by S122, combined with the historical production process information related to these nodes stored in the database.

[0077] The overlapping area refers to the production nodes or continuous production node segments that are common to the current production path and at least one abnormal production path; the purpose of determining the overlapping area is to identify the key links of the current workpiece that are affected by historical abnormalities; through the comparison results of the previous step, the system marks the nodes that are contained in both the current path and the abnormal path, and these nodes and their connected path segments are the overlapping area; if the nodes in the abnormal path do not exist in the current path, but they are very close to some nodes in the current path in space or function, the system will also mark these nodes as potential overlapping areas; the overlapping area is usually represented in the form of a node list or a node sequence, for example, if the current path is A > B > C > D, and the abnormal path is A > B > A > D, then the overlapping area is node B and node D.

[0078] The "sub-abnormal area" is a local range related to a specific abnormality that is further refined within the overlapping area; one overlapping area involves multiple processing steps or equipment, but not all parts are directly affected by the previous specific abnormality, for example, an overlapping area contains a processing node and a detection node, but the previous abnormality is only related to the processing node; the system will analyze each node or node segment within the overlapping area, combined with the specific type and location of the previous abnormality (from S122), to determine which parts are most affected by the abnormality, which involves: time correlation, spatial correlation, process correlation; the system will mark these sub-areas as "high risk", "medium risk" or "low risk".

[0079] The sub-abnormal area can be represented as a sub-node within the overlapping area, a device component (such as a tool, a fixture), or a specific feature area on the workpiece, for example, in the overlapping areas B and D, if the previous abnormality is tool wear caused by rough milling (at node A that is not in the current path), then the sub-abnormal area is mainly marked at node B (de-burring, affecting subsequent processes) and node D (detection, used to verify the impact of the abnormality).

[0080] The multiple sub-exceptional areas identified in the previous step are integrated and comprehensively judged to ultimately form a clear description of the abnormal impact range existing in the current production process of the workpiece, which is the final definition of the abnormal impact range; the system will consider the risk level, mutual relationship and comprehensive impact on the final quality of the workpiece of all sub-exceptional areas, for example, if multiple sub-areas are marked as high risk, or they collectively point to a certain key feature on the workpiece, then the final "production exception area" will be defined more clearly and critically; The "production exception area" finally determined is a positioning of the problems existing in the production process of the workpiece or the workpiece itself, which is a specific equipment node, a specific processing step, a certain feature area on the workpiece, or a label indicating the risk level.

[0081] The production exception area is a comprehensive description, for example: "The production exception area of the current workpiece TL-A2-V3 mainly involves the deburring process (NodeB) and the finishing process (NodeC), and attention should be paid to the burr condition of the blade edge and the final size accuracy, especially the thickness of the blade tip area" or more specifically: "Production exception area: tool path area #3 of finishing center C (NodeC), corresponding to the blade leading edge #45-#60 degree range".

[0082] Specifically, the current path is A>B>C>D; assume that there is an exception path A>B>A>D in the database related to the previous CNCARoughMill (NodeA) tool wear exception; by comparing, it is found that nodes B and D are coincident; the coincident area is determined as node B (deburring robot) and node D (size detection).

[0083] System analysis: Node B: deburring; although the previous exception occurred in rough milling (Node A), the burr condition after rough milling will affect the deburring effect; if the previous tool wear causes the workpiece edge to be irregular, then the deburring process (Node B of the current path) is the sub-area that needs to be focused on; Node D: size detection; detection is the key to verify the final quality, and any deviation introduced in the previous process will eventually be reflected in the detection link; therefore, size detection (Node D) is also a sub-exceptional area for confirming the abnormal impact; Node C: finishing center; although the finishing center of the current path is Node C', not Node A where the exception occurred, finishing is a key process and uses a new tool; the system judges that the risk of Node C' is low, but still needs to pay attention to its processing result; or, if the previous exception affects the overall appearance of the workpiece, then the processing of Node C' is also affected; assuming that the system judges that the risk of Node C' is low, it is temporarily not listed as a high-risk sub-area; therefore, the main sub-exceptional areas are Node B and Node D.

[0084] System comprehensive judgment, due to the previous abnormal (rough milling tool wear) affects the workpiece edge state, and this influence will be passed on to the subsequent process, and finally confirmed in the detection link; Therefore, the final determination of the production abnormal area is: "the production abnormal area of the current workpiece TL-A2-V3 mainly involves the deburring process (NodeB) and the size detection process (NodeD); Need to focus on the edge state after deburring and the final size tolerance, especially the blade tip thickness and blade profile, to confirm whether it is affected by the previous rough machining anomaly".

[0085] Reference Figure 5 In step S14, the specific steps are:

[0086] S141 : Collect the production abnormal area, determine a plurality of component features based on the detection of the production abnormal area, and determine the abnormal factory component corresponding to the production abnormal area according to the plurality of component features and the photographed image corresponding to the production abnormal area;

[0087] S142: Mark the Internet of Things of the intelligent factory, and based on the Internet of Things, control each abnormal factory component, and output the working data of each abnormal factory component, and determine the repair time node of each abnormal factory component according to the working data of each abnormal factory component and the current production position of the workpiece;

[0088] S143: Collect the production process table corresponding to the workpiece, determine the production time of the workpiece in each production process based on the analysis of the production process table, and determine the repair work amount of each abnormal factory component according to the repair time node of each abnormal factory component, the production time of the workpiece in each production process and the work amount of the abnormal factory in the production process;

[0089] In the embodiment of the present application, the system analyzes the collected data to find patterns or features related to "abnormalities", which involves: threshold comparison: compare real-time data with pre-set normal working threshold; Trend analysis: observe the trend of data over time; Statistical analysis: calculate the statistics (such as mean, standard deviation) of the data and compare with the historical normal value; Extract the key features that can represent "abnormalities" from the analysis results, these features should be able to point to specific physical components or subsystems, for example, "Z-axis deburring force continuously higher than threshold", "motor current fluctuation abnormal", "processing time 20% longer than standard" and so on.

[0090] Specifically, the system first locks the "deburring process" (NodeB), which starts collecting: force sensor data on the deburring tool (e.g., a rotating grinding head): X-axis force, Y-axis force, Z-axis force; position data of the robot joint encoders; current and voltage data of the motors driving the deburring motor and robot joint motors; NodeB PLC alarm logs (e.g., whether there are records of "tool overload" or "motion timeout"); real-time video stream taken by the monitoring camera installed next to the robot (showing the contact between the tool and the blade); historical statistics data such as the average deburring force and average current value during the past 24 hours when NodeB processed TL-A2-V3 blades.

[0091] The system analyzes the collected data: it finds that the Z-axis deburring force (perpendicular to the blade surface) in the last 5 pieces of processed blades is 15% higher than the standard value, and the standard deviation is also large, indicating that the force value is unstable and high; at the same time, the current driving the deburring motor also presents synchronous and periodic fluctuations, with a peak value about 10% higher than the normal value; there is no explicit hard alarm in the PLC log, but the record shows that the average deburring single piece time is about 3 minutes longer than the standard 15 minutes.

[0092] The "component features" extracted by the system include: "abnormally high deburring force (+15%)"; "increased deburring force volatility"; "abnormal deburring motor current fluctuation"; "single piece processing time extension (+20%)".

[0093] Correlate the "component features" extracted in the previous step with each physical component included in this production area (NodeB), for example, "abnormally high deburring force" is usually related to the wear or installation problem of the deburring tool; "abnormal motor current fluctuation" is related to the motor itself, driver or transmission mechanism.

[0094] Combined with the visual images collected before, for example, the image taken by the monitoring camera directly shows that the tool is severely worn, or the blade position is offset during clamping, causing abnormal deburring force; images can provide direct evidence to help confirm or correct judgments based on sensor data; through comprehensive analysis, it is finally determined which specific factory component has a problem, which is a specific hardware such as a sensor, an actuator, a tool, a motor, or a small mechanical structure.

[0095] Specifically, the system correlates the extracted features: "abnormally high deburring force" + "increased force fluctuation" + "abnormal current fluctuation" + "extended processing time" — these feature combinations strongly point to a problem with the deburring tool itself, most commonly tool wear or dulling; the system retrieves images from the NodeB's monitoring camera; the images show that the deburring tool has a large contact area with the blade's burr, and visible signs of wear on the tool's surface; combining the sensor data and visual images, the system finally determines that the "abnormal factory component" is the "GrinderBlade-456" (e.g., model number) mounted on the NodeB's deburring robot.

[0096] Further, the Internet of Things of the smart factory is marked, and each abnormal factory component is abnormally controlled based on the Internet of Things, and the working data of each abnormal factory component is output, and the repair time node of each abnormal factory component is determined according to the working data of each abnormal factory component and the current production position of the workpiece, which is compatible with the overall consideration of the working data of each abnormal factory component and the current production position of the workpiece, and ensures the accuracy of the repair time node of each abnormal factory component.

[0097] At this time, the Internet of Things of the smart factory is marked, and the marking not only changes the state, but also needs to associate this abnormal information with specific equipment (NodeB), components (GrinderBlade-456), abnormal types (wear), detection time, detection basis (sensor data, images), etc. Form a complete event record, this marking operation usually triggers a notification; the system will send an alarm or update information to the relevant maintenance team, equipment operator, production scheduler, or even MES system, informing them that a component has a problem; the level of the notification (e.g., urgent, important, general) is automatically set according to the severity of the anomaly; on the factory's monitoring big screen or maintenance personnel's mobile terminal, the icon of the relevant equipment or the identification of the component will change color (such as red) or pop up an alarm message, making the problem obvious.

[0098] According to the severity of the anomaly, the system will automatically restrict or prohibit the component / equipment from performing certain operations, for example, if the tool wear is severe enough to cause workpiece scrap or equipment damage, the system can automatically suspend the NodeB's processing task, or set it to "maintenance mode" to prohibit automatic operation.

[0099] In some cases, if the anomaly is allowed, the system will automatically adjust the equipment parameters to mitigate the impact, for example, if it is only slight wear, the system will automatically reduce the deburring force or speed to extend the tool life or ensure the processing quality until the maintenance personnel arrives.

[0100] The system can adjust the relevant resource allocation according to the abnormal information, for example, temporarily guide the workpiece that needs deburring to the standby equipment (if exists), or adjust the priority of other processes; the system will isolate the subsequent operation data of the component, or increase the data acquisition frequency, in order to record the behavior during the abnormal period in more detail, and provide the basis for subsequent analysis.

[0101] Specifically, the system finds the device object representing the deburring robot NodeB in the IoT platform of the factory (for example, a cloud-based device management platform); under this object, the component object representing GrinderBlade-456 is found; the system updates the state of GrinderBlade-456 from "normal" to "wear abnormality (need to replace)"; at the same time, the system records the type of abnormality, the detection time (for example, 2025-07-1514:30), and the basis for detection (force, current abnormality, image confirmation of wear); the IoT platform automatically pushes an alarm information to the dedicated App of the maintenance team: "Device NodeB (deburring robot) component GrinderBlade-456 detects wear abnormality, please handle as soon as possible", on the central monitoring screen of the factory, the icon of NodeB becomes yellow flashing, and is accompanied by a brief description of the abnormality.

[0102] Since the wear of GrinderBlade-456 has caused the deburring force to be abnormally high, the system determines that it is not appropriate to continue using the damaged workpiece or accelerating the tool to further wear; therefore, the system sends an instruction to the controller of NodeB through the IoT platform, sets the state of NodeB to "maintenance pause"; the robot of NodeB stops automatic operation, and the display screen prompts "maintenance pause: wear of grinding head tool is abnormal, please contact maintenance"; the system also checks whether there is a standby deburring equipment (for example, NodeB'); if not, the system will notify the production scheduling system to temporarily skip the deburring process for subsequent workpieces that need to be deburred (such as TL-A2-V4 after TL-A2-V3), or wait for NodeB to be repaired before processing.

[0103] The system needs to extract detailed working data related to the abnormal component from the IoT platform, device logs, and sensor historical database, which includes but is not limited to: running time, start-stop times, load history (current, force, temperature, etc.), error codes, alarm records, maintenance history, etc. These data need to be output in an easy-to-understand and analyze way; forms include: generating a detailed report, displaying key data charts (such as load change curve over time) on the interface of maintenance personnel, providing download links, etc. These data are important basis for maintenance personnel to diagnose and make decisions; maintenance personnel can analyze these data to better understand the causes of the abnormality and the degree of wear of the component, and determine the best repair solution (for example, whether to replace or repair).

[0104] The maintenance personnel (or an auxiliary decision module in the system) analyzes the outputted work data, combines their knowledge of the component, assesses the urgency and required time for repair, for example, the data shows that the component is about to fail completely, or the repair requires a specific spare part; the system needs to know where the workpiece currently being produced or about to enter this abnormal process is located, which can be obtained through the MES system or WMS (Warehouse Management System), for example, the workpiece is in the waiting area, is being processed in other processes, or is about to arrive at this abnormal equipment; the system combines the repair time required and the workpiece location / planning information to determine the optimal repair time window.

[0105] The system combines the repair time required and the workpiece location / planning information to determine the optimal repair time window; the system can calculate that it is best to perform the repair at a certain time period, which has the least impact on the overall production plan, for example, is it best to repair immediately after the current workpiece is processed, or wait until the next shift, or wait until after a certain key workpiece passes; determining the time node also means that the maintenance resources (personnel, spare parts, tools) need to be coordinated to be available at that time point; finally, one or more repair time suggestions are determined and recorded, which are used to guide subsequent maintenance actions.

[0106] Specifically, the system automatically generates a detailed work data report for GrinderBlade-456 and pushes it to the engineer responsible for the equipment through the maintenance team's App; the report includes: component basic information: model GrinderBlade-456, installation date, expected life; running history: cumulative running time (e.g., 1200 hours), start-stop times (e.g., 1500 times); load data: force sensor reading curve in the past 24 hours (showing that the force value gradually increases and reaches an abnormal peak at 14:30), current sensor reading curve (showing that the current fluctuation increases); error record: alarm code recorded by NodeB controller at 14:30 (e.g., alarm code #E503: deburring force exceeds limit); maintenance history: time of last tool replacement (e.g., 2025-05-10, about 800 hours of operation).

[0107] The maintenance engineer reviews the work data report of GrinderBlade-456 and, based on experience, determines that the tool is severely worn and needs to be replaced immediately. The estimated replacement time is 30-45 minutes (including obtaining spare parts and replacement operations). At the same time, the MES system shows that the TL-A2-V3 blade currently being processed has completed rough machining and is on its way to the deburring process (NodeB) and is expected to arrive in 15 minutes. TL-A2-V4 will also arrive shortly after TL-A2-V3 is completed. Considering that NodeB has been suspended and the next workpiece will arrive soon, the engineer decides to start preparing for replacement immediately. The system confirms that there is an engineer available at around 15:00 based on the maintenance team's schedule and spare parts inventory information, and that the spare parts (new GrinderBlade-456) are available in the spare parts inventory, and it is estimated that the replacement can start at 15:10. Therefore, the system determines the repair time node of GrinderBlade-456 as "estimated start time of replacement: 15:10, estimated completion time: 15:55", this information is recorded and notified to the relevant engineers and production schedulers.

[0108] Therefore, the production process table corresponding to the workpiece is collected, the production time of the workpiece in each production process is determined based on the analysis of the production process table, and the repair workload of each abnormal factory component is determined according to the repair time node of each abnormal factory component, the production time of the workpiece in each production process and the workload of the abnormal factory component in the production process, which takes into account the overall consideration of the repair time node of each abnormal factory component, the production time of the workpiece in each production process and the workload of the abnormal factory component in the production process, and ensures the accuracy of the repair workload of each abnormal factory component.

[0109] At this time, the system needs to extract the standard production plan of the workpiece currently being processed (such as TL-A2-V3) from the MES (Manufacturing Execution System) or ERP (Enterprise Resource Planning System), which details all the production nodes (processes) that the workpiece needs to go through, the operations that each node should perform, the equipment used, the standard processing time, the quality detection requirements, etc. This process table is usually a structured data file containing process ID, process name, equipment / node name, standard working hours, operation description, required tools / clamps, quality standards, etc. After obtaining the process table, the system will perform some verification, such as checking whether the workpiece model matches, whether the process table is the latest version, etc. to ensure that the subsequent calculation is based on accurate basic data.

[0110] The system extracts the standard production time for each process from the process table, which is optimized and verified, representing the time required to complete the process under normal circumstances; in addition to the standard production time, the system also extracts other time information, such as preparation time, mold changing time, quality detection time, etc., but in this step, the main focus is on direct processing or handling time; the system organizes these extracted time information in sequence according to the process, forming a time sequence for subsequent calculation and analysis.

[0111] Specifically, for TL-A2-V3 blade, the system retrieves its production process table from MES; the table shows: Process 1: Rough machining (NodeA), standard time: 2 hours, equipment: CNC-Mill-001; Process 2: Deburring (NodeB), standard time: 15 minutes, equipment: RoboDeburr-023, tool: GrinderBlade-456; Process 3: Finishing (NodeC), standard time: 3 hours, equipment: CNC-Mill-002; Process 4: Dimension detection (NodeD), standard time: 10 minutes, equipment: CMM-005; Process 5: Surface treatment (NodeE), standard time: 4 hours, equipment: PlatingChamber-010; the system parses the process table of TL-A2-V3 and extracts the standard production time of each process: Process 1 (NodeA): 2 hours; Process 2 (NodeB): 15 minutes; Process 3 (NodeC): 3 hours; Process 4 (NodeD): 10 minutes; Process 5 (NodeE): 4 hours.

[0112] Compare the repair time node (15:10-15:55) of the previously determined abnormal component (GrinderBlade-456) with the current production position of the workpiece (TL-A2-V3 is going to NodeB) and the standard time of each process; determine whether the repair activity will affect the normal production of the workpiece or other subsequent workpieces; analyze whether the repair time overlaps with the expected occupation time of the workpiece in the relevant process, for example, if TL-A2-V3 is expected to arrive at NodeB at 15:30, then the repair time (15:10-15:55) of GrinderBlade-456 will overlap with the processing time (15:30-15:45) of TL-A2-V3 at NodeB for 15 minutes, which means that the repair work must be completed during this period, or the progress of the workpiece needs to be adjusted.

[0113] "repair effort" here is a comprehensive index, not only the time needed for physical repair, but also: direct repair time: the actual operation time of replacing GrinderBlade-456 (for example, 15:10-15:55, a total of 45 minutes), which includes disassembling the old blade, installing the new blade, preliminary calibration, etc.; preparation time: the time for obtaining spare parts, preparing tools, and engineers going to the site; adjustment / calibration time: after repair, additional adjustment or calibration of the equipment is needed to ensure its normal performance, which also needs to be counted; impact assessment on production: if the repair time is too long, causing the workpiece to wait at NodeB, then the waiting time should also be considered as part of the impact of repair work, and additional operations (such as re-queuing, adjusting subsequent process time) need to be added; resource demand: engineers with specific skills, specific tools, spare parts inventory, etc., the demand for these resources is also a manifestation of the workload; combining the above factors, the total repair effort required to repair GrinderBlade-456 is calculated, for example, it is a data structure containing "total time consumed (hours)", "labor required (engineer level)", "spare parts required (quantity, type)", "tools required (list)" and other dimensions.

[0114] Specifically, repair time: 15:10-15:55 (45 minutes); TL-A2-V3 arrives at NodeB time: about 15:30; TL-A2-V3 standard processing time at NodeB: 15 minutes (15:30-15:45); overlap time: 15:30-15:45 (15 minutes).

[0115] System determination: direct repair time: 45 minutes (included in 15:10-15:55); preparation time: it is assumed that the engineer needs to arrive 10 minutes in advance to prepare, and the spare parts need 5 minutes to be taken out from the warehouse, the total preparation time is about 15 minutes (assuming it is completed before 15:00); adjustment / calibration time: 5-10 minutes of calibration is needed after replacement, assuming 10 minutes (15:55-16:05); impact on production: there are 15 minutes of overlap, which means that TL-A2-V3 will wait at NodeB, or NodeB will process TL-A2-V3 immediately after repair, causing the delay of subsequent workpiece TL-A2-V4; resource demand: 1 senior robot maintenance engineer, a set of robot maintenance tools, and 1 new GrinderBlade-456 spare part.

[0116] The system calculates the "repair effort" as follows: total time: approximately 1 hour (including preparation, direct repair, calibration, and considering waiting / adjustment time); required manpower: 1 senior engineer; required spare parts: 1 x GrinderBlade-456; required tools: standard robot maintenance tool kit; impact assessment on production: causes TL-A2-V3 to delay at NodeB for about 15 minutes, which needs to be notified to subsequent processes.

[0117] Reference Figure 6 In step S15, the specific steps are:

[0118] S151: The Internet of Things performs abnormal control on each abnormal factory component, collects repair data of each abnormal factory component at different time nodes, and collects the processing area of the workpiece relative to the abnormal factory component, determines a first repair event according to the plurality of repair data and the processing area of the workpiece;

[0119] S152: According to the first repair event, the repair effort of each abnormal factory component and the Internet of Things, determine the autonomous repair strategy of the smart factory for the workpiece at this time, analyze the autonomous repair strategy and output the autonomous repair process, determine the early repair event of each abnormal factory component according to the dynamic interaction of the autonomous repair process and the production process of the workpiece, and repair each abnormal factory component early.

[0120] In the embodiment of the present application, the Internet of Things performs abnormal control on each abnormal factory component, collects repair data of each abnormal factory component at different time nodes, and collects the processing area of the workpiece relative to the abnormal factory component, determines a first repair event according to the plurality of repair data and the processing area of the workpiece, which is compatible with the overall consideration of the plurality of repair data and the processing area of the workpiece, and ensures the accuracy of the first repair event.

[0121] At this time, the Internet of Things system first accurately identifies GrinderBlade-456 and the deburring robot (NodeB) where it is located through sensors, controllers (such as PLC) and device interfaces in its network, which usually requires the device itself to have a unique identifier (such as RFID tag, MAC address, etc.).

[0122] The system sends instructions to the control unit of NodeB to set its state to "maintenance" or "shutdown", which includes: prohibition of scheduling: the MES or APS (Advanced Planning and Scheduling) system of the factory will receive the notification and will no longer allocate new workpieces to NodeB; physical isolation (optional): if physical security doors or area locking devices are configured, the system will automatically lock them to prevent personnel from entering or devices from starting accidentally; software isolation: at the software level, the operation interface of NodeB will display "maintenance mode" to prohibit operators from performing production-related operations.

[0123] In the control state, the IoT system will increase the monitoring frequency of GrinderBlade-456 and its related components (such as motors, bearings), for example, more frequently collect vibration, temperature, current, etc. Data to more accurately assess its current state and the urgency of repair.

[0124] Specifically, the IoT system identifies GrinderBlade-456 as an abnormal component through the sensor interface and built-in communication module on the NodeB control cabinet; the system immediately sends a message to the MES: "NodeB-GrinderBlade-456 enters maintenance state"; the MES updates the production plan immediately, suspending the allocation of new blade processing tasks to NodeB; at the same time, the HMI (Human Machine Interface) of NodeB pops up a red warning box, displaying "Maintenance mode: waiting for tool replacement"; the system starts collecting vibration and motor current data of the tool at a frequency of 1 per second, and continues monitoring.

[0125] Repair data comes from multiple sources, collected through the sensor network and device interface of the Internet of Things: component state data: as mentioned above, real-time data such as vibration, temperature, current, wear (if wear sensors are installed or calculated through image recognition), pressure, etc.; historical data: retrieve GrinderBlade-456's installation time, last replacement time, cumulative usage time, past repair records, etc. from device history records or maintenance database; environmental data: such as workshop temperature, humidity, etc. Data affecting repair process or component state; operation data: NodeB operation log before the abnormality occurs, such as processing parameters, processing workpiece types, processing duration, etc.

[0126] Data collection is not one-time, but at different time points, forming time series data, for example, at key time points such as 1 minute, 5 minutes, 10 minutes, 30 minutes after the abnormality is confirmed, or continuously collected according to the preset frequency (such as every minute); The collected data will be sent to the factory's data platform or edge computing node for preliminary cleaning, formatting, and association to GrinderBlade-456 this specific component and abnormal event.

[0127] The system needs to identify which workpiece is currently being processed by the abnormal component, which is usually confirmed by the MES system or RFID readers on the workstation, for example, confirming that NodeB is currently processing workpiece TL-A2-V3; The system needs to identify which workpiece is currently being processed by the abnormal component, which is usually confirmed by the MES system or RFID readers on the workstation, for example, confirming that NodeB is currently processing workpiece TL-A2-V3; Process file: Extract the processing process file of this workpiece from the CAD / CAM system or process database, and specify the specific position of the tool contact with the blade (such as a certain angle range of the blade edge) when GrinderBlade-456 performs the deburring operation on NodeB; Real-time state: If the system supports, the current position and attitude of the tool, as well as the contact point information with the workpiece, can be obtained from the real-time motion control data of NodeB; Visual information: If the workstation is equipped with a vision system, the image can be analyzed to confirm the workpiece area being processed by the tool, and this "processing area" is usually described as a geometric area on the workpiece, such as "blade edge, from the blade root to the blade tip, angle range 15° to 30°".

[0128] The system will analyze the collected repair data (component state, historical data, etc.) and the determined processing area information, for example, analyze the vibration and current data of GrinderBlade-456, combine its historical wear rate and the current processing area (near the blade tip, usually with larger burrs and faster wear), and evaluate the remaining life or damage degree of the tool; Combined with the processing area information, evaluate the specific impact on the workpiece quality caused by continuing to use the abnormal component (for example, whether it will leave scratches or remove too much material on the blade edge); At the same time, combined with the repair workload calculated by S14, evaluate the time required for repair.

[0129] Based on preset rules or algorithms (for example, "if the vibration exceeds threshold X and is processing a critical area, then must be repaired within Y minutes"), or based on the evaluation of the impact on the production plan (for example, "if not repaired now, TL-A2-V3 will be delayed beyond the allowed value, and the next workpiece TL-A2-V4 will arrive before repair, causing two consecutive workpieces to be delayed"), the system determines a preliminary repair time point, which is the "first repair event", which is a relatively conservative or preliminary repair decision based on all available information at the moment, it is a specific date and time (such as "2025-07-15 15:50"), it is also a relative time (such as "30 minutes before the next workpiece arrives") or condition (such as "when the tool vibration exceeds 1.5g").

[0130] Further, the intelligent factory determines the autonomous repair strategy for the workpiece according to the first repair event, the repair workload of each abnormal factory component, and the Internet of Things, at this time, the autonomous repair strategy is analyzed, and the autonomous repair procedure is output, and the early repair event of each abnormal factory component is determined according to the dynamic interaction of the autonomous repair procedure and the production procedure of the workpiece, so as to repair each abnormal factory component in advance, realize the dynamic interaction of the autonomous repair procedure and the production procedure of the workpiece, further accurately control the early repair event of each abnormal factory component, at the same time, the repair time node of each abnormal factory component is introduced, the overall consideration of the repair workload of each abnormal factory component and the Internet of Things is realized, the accuracy of the autonomous repair strategy of the intelligent factory for the workpiece is improved, and the normal production of the workpiece is not affected, so as to repair each abnormal factory component in advance.

[0131] At this time, the system inputs the first repair event (15:15 starts preparation, target 15:20 starts replacement, 15:45 completes) determined in S151, the repair workload (45 minutes) of GrinderBlade-456, and the information provided by the Internet of Things in real time (such as the real-time progress of TL-A2-V3, the transportation state of TL-A2-V4, the load condition of other procedures, the spare part inventory state, the maintenance personnel availability, etc.) into the advanced decision algorithm.

[0132] To formulate an optimal repair plan that minimizes the waiting time of workpiece TL-A2-V3 and does not delay the processing of subsequent workpiece TL-A2-V4, it needs to consider multiple factors: time window: the replacement must be done after TL-A2-V3 finishes the current operation and before TL-A2-V4 arrives; resource availability: check if there is spare grinder blade inventory; whether maintenance engineer A is available between 15:20-15:45; whether the robot arm that needs to be replaced needs additional debugging time; parallel tasks: whether engineer A can handle other low-priority maintenance tasks at the same time, or needs to focus entirely on the replacement of GrinderBlade-456; risk factors: if engineer A cannot arrive immediately at 15:20, is there a backup plan (such as waiting for engineer B, but this takes more time).

[0133] Based on the above analysis, the system generates a preliminary autonomous repair strategy, for example: Strategy A: strictly follow the first repair event, Engineer A prepares tools and spare parts at 15:15, TL-A2-V3 starts replacing as soon as the operation is completed, and is expected to be completed at 15:45; Strategy B: if it is found that Engineer A does have a short conflict at 15:20, the strategy is: Engineer A starts preparing at 15:15, but the actual replacement is delayed to start at 15:30, and is expected to be completed at 16:15, which means TL-A2-V4 will be delayed for 15 minutes waiting; the system will choose the strategy with the lowest risk and the smallest impact (in this case, Strategy A).

[0134] The system decomposes the selected autonomous repair strategy (for example, Strategy A) into a series of specific, executable operation steps, not just "replace GrinderBlade-456", but a more detailed process; the system generates an "autonomous repair procedure" list and sends it to the relevant execution units (such as maintenance terminals, robot control panels, material handling systems, etc.) through the Internet of Things; for the replacement of GrinderBlade-456, the list includes: 15:15: material handling robot goes to the spare parts warehouse to take out the spare grinder blade tool numbered GB-456-BACKUP; 15:15: Engineer A's mobile terminal receives a notification: "Please immediately go to NodeB to replace GrinderBlade-456, tools needed: wrench set #12, torque wrench #3"; 15:15: NodeB's robot control system receives instructions: "Enter maintenance mode, prepare to release the locking device of GrinderBlade-456"; 15:20: TL-A2-V3 completes the deburring operation, and the system automatically suspends its subsequent procedures; 15:20: NodeB's robot control system receives instructions: "Execute GrinderBlade-456 disassembly procedure"; 15:20: the material handling robot transports the old tool GB-456 to the scrap area and the new tool GB-456-BACKUP to the designated position of NodeB; 15:25: NodeB's robot control system receives instructions: "Execute GB-456-BACKUP installation procedure" 15:35: NodeB's robot control system receives instructions: "Execute automatic calibration procedure for new tool GB-456-BACKUP"; 15:45: NodeB's robot control system receives instructions: "Exit maintenance mode, prepare to receive the next workpiece TL-A2-V4"; 15:45: TL-A2-V3 resumes subsequent procedures; 15:45: TL-A2-V4 is guided to NodeB to start the deburring process.

[0135] During the autonomous repair procedure execution, the system continuously monitors the actual situation; the IoT provides real-time feedback: actual completion time of TL-A2-V3 (whether ahead of or behind schedule); actual arrival time of the material handling robot (whether on time); actual arrival and operation time of Engineer A (whether according to plan); actual time spent on robot disassembly, installation, and calibration (whether consistent with expectations); actual arrival time of TL-A2-V4 (whether on time).

[0136] The system compares and analyzes the real-time progress of the autonomous repair procedure with the production procedures of workpieces TL-A2-V3 and TL-A2-V4; case one (according to plan): if everything goes according to plan, TL-A2-V3 is completed at 15:20, the replacement is completed at 15:45, and TL-A2-V4 arrives at 15:45 and immediately starts processing; then the "early repair event" is the originally planned replacement at 15:20; case two (deviation occurs): suppose TL-A2-V3 actually completes the deburring operation at 15:18 due to a minor processing deviation and pauses; at the same time, Engineer A also arrives 5 minutes (15:10) earlier and is ready with the tools; the IoT captures these changes.

[0137] TL-A2-V3 has been completed, 2 minutes ahead of schedule; Engineer A is already in place, 5 minutes ahead of schedule; and the new tool is also in place (assuming the material robot is also ahead of schedule); although the original plan was to start the replacement at 15:20, there is now a window to start earlier, such as 15:15, which can further shorten the total waiting time of TL-A2-V3 (from 2 minutes to 0) and ensure that NodeB is absolutely ready when TL-A2-V4 arrives at 15:45; the system assesses the risk: will starting the replacement early affect Engineer A's other arrangements, and is there enough time to complete the calibration, and concludes that it is feasible; the system generates an "early repair event": instructs the replacement of GrinderBlade-456 to start at 15:15; based on this new "early repair event", the system dynamically adjusts the start time of the autonomous repair procedure and notifies the relevant execution units.

[0138] Please refer to Figure 7 , Figure 7 is a structural composition diagram of a production traceability control system of a digital and intelligent factory under the Internet of Things in an embodiment of the present application; the production traceability control system of the digital and intelligent factory under the Internet of Things comprises:

[0139] a digital and intelligent database module 21, configured to collect a plurality of production data combinations of the digital and intelligent factory at different production nodes, and construct a digital and intelligent database based on each production data combination and the Internet of Things;

[0140] An abnormal production path module 22 is configured to perform production traceability on a plurality of abnormal production data in each production data combination based on the digitized database, to determine corresponding abnormal production nodes, and to determine an abnormal production path according to positions of the abnormal production nodes and abnormal ranges of the abnormal production data;

[0141] A production abnormal area module 23 is configured to determine a current production path according to a current working state of the digitized factory and a model of the workpiece, and to determine a production abnormal area of the workpiece based on the current production path and the abnormal production path;

[0142] A repair workload module 24 is configured to determine a repair time node of each abnormal factory component based on an abnormal factory component corresponding to the production abnormal area, the Internet of Things, and a current production position of the workpiece, and to determine a repair workload of each abnormal factory component according to the repair time node of each abnormal factory component and a production procedure table corresponding to the workpiece;

[0143] An autonomous repair strategy module 25 is configured to determine an autonomous repair strategy of the digitized factory for the workpiece according to the repair workload of each abnormal factory component and the Internet of Things, and not to affect normal production of the workpiece, so as to repair each abnormal factory component in advance.

[0144] Any combination of the technical features of the above embodiments is possible. In order to make the description simple, not all combinations of the technical features in the above embodiments are described, however, as long as the combinations of the technical features do not exist, they should be considered as the scope of the present disclosure.

Claims

1. A production traceability control method of a digitalized factory under the Internet of Things, characterized in that, The application comprises the following steps: Collecting multiple production data combinations of a smart factory at different production nodes, and constructing a smart database based on each production data combination and the Internet of Things; the production data combination refers to a structured data set collected in real time from each production node; Performing production tracing on multiple abnormal production data in each production data combination based on the smart database to determine the corresponding abnormal production node, and determining the abnormal production path according to the position of each abnormal production node and the abnormal range of the abnormal production data; the abnormal range refers to the severity and influence of the abnormality; Determining the current production path according to the current working state of the smart factory and the model of the workpiece, determining the production abnormal area of the workpiece based on the current production path and the abnormal production path, comprising: comparing the current production path and the abnormal production path, determining the overlapping area according to the comparison between the current production path and the abnormal production path, determining multiple sub-abnormal areas according to the detection of the overlapping area, and determining the production abnormal area of the workpiece according to the synthesis of the multiple sub-abnormal areas; Determining the repair time node of each abnormal factory component based on the corresponding abnormal factory component of the production abnormal area, the Internet of Things and the current production position of the workpiece, and determining the repair workload of each abnormal factory component according to the repair time node of each abnormal factory component and the production process table corresponding to the workpiece; the repair workload comprises total time consumption, required manpower, required spare parts, required tools and evaluation of the impact on production; Determining the autonomous repair strategy of the smart factory for the workpiece according to the repair workload of each abnormal factory component and the Internet of Things.

2. The production traceability control method of the digital factory under the Internet of Things according to claim 1, characterized in that, The application comprises the following steps: When the smart factory performs unmanned machining on the workpiece, the numerical machining process of the smart factory on the workpiece is collected, multiple autonomous production processes are determined according to the division of the numerical machining process, and multiple production nodes are determined according to the multiple autonomous production processes and the model of the workpiece; The multiple production nodes are distributed at different positions of the smart factory and are used for different machining processes of the workpiece; the multiple production nodes are monitored in real time, and multiple production data of each production node are collected; in each production node, the corresponding production data combination is determined according to the synthesis of the multiple production data; The smart database is constructed based on the node position of the production node, the corresponding production data combination and the synthesis of the Internet of Things corresponding to the smart factory, and the smart database is dynamically updated as the production data increases.

3. The production traceability control method of the digital factory under the Internet of Things according to claim 1, characterized in that, The application comprises the following steps: Collecting each production data combination, determining the corresponding abnormal production detection mode based on the matching between each production data combination and the smart database, triggering abnormal detection of each production data combination along the abnormal production detection mode, and outputting multiple abnormal production data; Mark the abnormal positions corresponding to the plurality of abnormal production data, determine the corresponding production traceability mode according to the abnormal positions, the corresponding abnormal production data and the digitalization database, determine a plurality of traceability items based on the analysis of the production traceability mode, cross-trace the workpiece by using the plurality of traceability items, and trigger the production traceability of the plurality of abnormal production data to determine a plurality of abnormal production nodes; the cross-trace means to verify the results obtained by different traceability items with each other; At each abnormal production node, determine the abnormal range of abnormal production data based on the comparison of the corresponding plurality of abnormal production data, and determine the abnormal production path based on the position of each abnormal production node, the abnormal range of abnormal production data and the workpiece.

4. The production traceability control method of the digital factory under the Internet of Things according to claim 1, characterized in that, The current production path is determined according to the current working state of the digital factory and the model of the workpiece, and the production abnormal area of the workpiece is determined based on the current production path and the abnormal production path, which comprises: Collect the response signals of each production node in the digital factory, determine the state coefficient of each production node according to the analysis of each response signal, and determine the current working state of the digital factory according to the node position, state coefficient and the number of processed workpieces corresponding to the digitalization database of each production node.

5. The production traceability control method of the digital factory under the Internet of Things according to claim 4, characterized in that, The current production path is determined according to the current working state of the digital factory and the model of the workpiece, and the production abnormal area of the workpiece is determined based on the current production path and the abnormal production path, which further comprises: Collect the model of the workpiece, determine the processing form of the workpiece according to the model and external form of the workpiece, and determine the current production path according to the processing form of the workpiece, the current working state of the digital factory and the plurality of production nodes.

6. The production traceability control method of the digital factory under the Internet of Things according to claim 1, characterized in that, The repair time node of each abnormal factory component is determined based on the abnormal factory component corresponding to the production abnormal area, the Internet of Things and the current production position of the workpiece, and the repair workload of each abnormal factory component is determined according to the repair time node of each abnormal factory component and the production process table corresponding to the workpiece, which comprises: Collect the production abnormal area, determine a plurality of component features based on the detection of the production abnormal area, and determine the abnormal factory component corresponding to the production abnormal area according to the plurality of component features and the photographed image corresponding to the production abnormal area; Mark the Internet of Things of the digital factory, and perform abnormal control on each abnormal factory component based on the Internet of Things, and output the working data of each abnormal factory component, and determine the repair time node of each abnormal factory component according to the working data of each abnormal factory component and the current production position of the workpiece.

7. The production traceability control method of the digital factory under the Internet of Things according to claim 6, characterized in that, The repair time node of each abnormal factory component is determined based on the abnormal factory component corresponding to the production abnormal area, the Internet of Things and the current production position of the workpiece, and the repair workload of each abnormal factory component is determined according to the repair time node of each abnormal factory component and the production process table corresponding to the workpiece, which further comprises: The production procedure table corresponding to the workpiece is collected, the production time of the workpiece in each production procedure is determined based on analysis of the production procedure table, and the repair workloads of each abnormal factory component are determined according to the repair time nodes of each abnormal factory component, the production time of the workpiece in each production procedure, and the workloads of the abnormal factory components in the production procedure.

8. The production traceability control method of the digital factory under the Internet of Things according to claim 1, characterized in that, The autonomous repair strategy of the smart factory for the workpiece is determined according to the repair workloads of each abnormal factory component and the Internet of Things, including: The Internet of Things performs abnormal control on each abnormal factory component, collects repair data of each abnormal factory component at different time nodes, and simultaneously collects the processing area of the workpiece relative to the abnormal factory component, and determines a first repair event according to the multiple repair data and the processing area of the workpiece.

9. The production traceability control method of the digital factory under the Internet of Things according to claim 8, characterized in that, The autonomous repair strategy of the smart factory for the workpiece is determined according to the repair workloads of each abnormal factory component and the Internet of Things, including: The autonomous repair strategy of the smart factory for the workpiece is determined according to the repair workloads of each abnormal factory component and the Internet of Things, including:

10. A production traceability control system of a digitalized factory under the Internet of Things, characterized in that, The autonomous repair strategy of the smart factory for the workpiece is determined according to the repair workloads of each abnormal factory component and the Internet of Things, including: The production traceability control system of the smart factory under the Internet of Things is applied to the production traceability control method of the smart factory under the Internet of Things as claimed in any one of claims 1-9, and the production traceability control system of the smart factory under the Internet of Things includes: A smart database module is configured to collect multiple production data combinations of the smart factory at different production nodes, and construct a smart database based on each production data combination and the Internet of Things; An abnormal production path module is configured to perform production traceability on multiple abnormal production data in each production data combination based on the smart database to determine corresponding abnormal production nodes, and determine an abnormal production path according to the positions of each abnormal production node and the abnormal ranges of the abnormal production data; A production abnormal area module is configured to determine a current production path according to the current working state of the smart factory and the model of the workpiece, and determine a production abnormal area of the workpiece based on the current production path and the abnormal production path; A repair workload module is configured to determine repair time nodes of each abnormal factory component based on the abnormal factory components corresponding to the production abnormal area, the Internet of Things, and the current production position of the workpiece, and determine repair workloads of each abnormal factory component according to the repair time nodes of each abnormal factory component and the production procedure table corresponding to the workpiece; An autonomous repair strategy module is configured to determine an autonomous repair strategy of the smart factory for the workpiece according to the repair workloads of each abnormal factory component and the Internet of Things.

Images