Visual process scheme making method and system

Abstract

The invention relates to the technical field of process scheme making methods, in particular to a visual process scheme making method and system.The visual process scheme making method comprises the following steps that A, a bubble graph model is constructed, and digital process information of parts is presented in a visual mode; b, deeply analyzing the bubble graph model, mining potential problems and optimizing space; c, automatically generating an equipment processing code according to the bubble graph model; d, the production process is monitored and adjusted in real time; according to the visual process scheme making method, digital process information of parts is presented in a clear and easy-to-understand manner by means of the bubble graph which is a visual and expressive visual tool, so that organic fusion and deep association of the digital process information and rich manufacturing experience data are realized; potential problems and optimization space in the model are deeply mined, the realization of rapid intelligent design is promoted, and the efficiency and quality of development are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of process planning methods, in particular to a visual process planning method and system. BACKGROUND

[0002] Many design aspects still rely on manual operation, and designers need to manually perform modeling, calculation and verification. This highly manual approach makes the design process vulnerable to human factors, resulting in high design error rates. The experience and skill level of designers directly affect the quality of design, and the lack of systematic knowledge management and experience inheritance mechanism makes it difficult to accumulate and share excellent experience. Due to design errors, production delays and other problems, the overall project cost is difficult to control, affecting the profitability and market competitiveness of the enterprise. The rework and modification in the design process not only increases the direct cost, but also may lead to an increase in indirect costs, affecting the economic benefits of the enterprise. Existing design software often has single functions and lacks intelligent design assistance functions. Many software can only complete basic modeling and drawing, and cannot provide advanced analysis and optimization functions required for design. This limits the creativity and design efficiency of designers and cannot meet the needs of modern manufacturing for high precision and high efficiency. SUMMARY

[0003] The present application is aimed at the deficiencies of the prior art and provides a visual process planning method. By using a bubble chart, a visual and expressive tool, the digital process information of the part is presented in a clear and understandable manner. The digital process information is organically integrated with rich manufacturing experience data, and a comprehensive process model is constructed. Advanced data analysis and visualization techniques are used to deeply mine potential problems and optimization spaces in the model, providing a solid basis for developing a scientific and reasonable process plan. This provides accurate and effective guidance for production, promotes the realization of rapid and intelligent design, and improves the efficiency and quality of development. Finally, based on the bubble process model, equipment machining codes covering tool path, cutting parameters, feed speed and other detailed information can be automatically generated, and these codes can be accurately transmitted to the control system of the production equipment, thereby realizing a highly automated machining process. Through advanced technologies and scientific methods for real-time monitoring of equipment machining status, timely and flexible adjustments and optimizations can be made according to actual production conditions to ensure the accuracy and efficiency of the machining process.

[0004] To achieve the above-mentioned purpose, the technical scheme adopted by the present application is as follows: a visual process planning method, comprising the following steps:

[0005] A. Construct a bubble chart model to visually present the digital process information of the part;

[0006] B. In-depth analysis of the bubble chart model to uncover potential problems and optimization space;

[0007] C. Automatically generate device processing code based on the bubble chart model;

[0008] D. Real-time monitoring and adjustment of the production process.

[0009] Further improvement of the above scheme is that the step A specifically includes the following steps:

[0010] A1. Collecting production process data of parts through sensors and data acquisition devices, the production process data including one or more of process parameters, device status and operation records;

[0011] A2. Input the collected production process data into the bubble chart generation module, and generate a bubble chart using graphical algorithms;

[0012] A3. Correlate the bubble chart with empirical data to build a comprehensive process model, and view detailed information by clicking on the bubble to understand the specific parameters and historical data of each process link.

[0013] Further improvement of the above scheme is that the empirical data includes one or more of process parameter settings, device operation status records, and quality test results of successful cases.

[0014] Further improvement of the above scheme is that the bubble includes a bubble pattern, and the bubble pattern includes shape and / or color and / or size classification.

[0015] Further improvement of the above scheme is that the step B specifically includes the following steps:

[0016] B1. Analyze the data in the bubble chart using machine learning and data mining algorithms to identify bottlenecks and problems in the process;

[0017] B2. Automatically generate optimization suggestions based on the analysis results, including one or more of process adjustment, device improvement and operation specification.

[0018] Further improvement of the above scheme is that the step C specifically includes the following steps:

[0019] C1. Automatically calculate tool path, cutting parameters and feed speed according to the process parameters defined in the bubble chart model;

[0020] C2. Convert the calculation results into standard device processing code;

[0021] C3. Transmit the generated device processing code to the control system of the production equipment.

[0022] A further improvement of the above scheme is that the step D specifically includes the following steps:

[0023] D1, real-time monitoring of the running state of the equipment through a sensor, the running state including one or more parameters of temperature, pressure and rotating speed;

[0024] D2, automatically identifying abnormal conditions according to real-time monitoring data;

[0025] D3, when the monitoring occurs abnormal conditions, sending an alarm to the operator and providing corresponding solution suggestions.

[0026] A further improvement of the above scheme is that when the bubble chart model is analyzed in depth, potential problems and optimization space are mined, and AI algorithm is combined to analyze historical design data to provide personalized design suggestions and optimization schemes.

[0027] A further improvement of the above scheme is that when the bubble chart model is constructed, AI technology is used to present 3D drawings in the form of pictures.

[0028] A visual process scheme making system, comprising a processor and a memory, the memory storing program modules, the program modules running on the processor to realize a visual process scheme making method according to any one of the above schemes.

[0029] The present application has the advantages that the visual process scheme making method provided by the present application comprises the following steps:

[0030] A, constructing a bubble chart model to present digital process information of the part in a visual way;

[0031] B, analyzing the bubble chart model in depth to mine potential problems and optimization space;

[0032] C, automatically generating equipment processing codes according to the bubble chart model;

[0033] D, real-time monitoring and adjustment of the production process;

[0034] The visual process scheme formulation method of the application presents the digital process information of the part in a clear and understandable manner by means of the bubble chart, which is a visual and expressive visualization tool; realizes the organic integration and deep correlation of the digital process information and rich manufacturing experience data, and constructs a comprehensive and integrated process model; uses advanced data analysis and visualization technology to deeply mine potential problems and optimization space in the model, and provides a solid basis for formulating a scientific and reasonable process scheme, thereby providing accurate and effective guidance for production, promoting the realization of rapid intelligent design, and improving the efficiency and quality of development; finally, the equipment machining code covering detailed information such as tool path, cutting parameters and feed speed can be automatically generated according to the bubble process model, and it is ensured that these codes can be accurately and correctly transmitted to the control system of the production equipment, and then a highly automated machining process is realized; through advanced technology and scientific methods for real-time monitoring of the equipment machining state, timely and flexible adjustment and optimization can be carried out according to the actual production situation, so as to ensure the accuracy and efficiency of the machining process; the application takes the bubble chart as the core carrier, and realizes the innovation of the "low efficiency, high cost and experience-dependent" mode of traditional process design through four technical pillars of multi-dimensional data coding, AI deep analysis, 3D spatial interaction and whole-process closed-loop control, realizes the transition from manual trial and error to intelligent optimization, from flat charts to 3D spatial mapping, and from lagging alarm to real-time closed-loop control. The innovation is not only in the single-point breakthrough of technology, but also in the construction of a new paradigm of process design driven by visualization, empowered by data and closed-loop by intelligence, which provides an efficient, accurate and easy-to-use solution for the intelligent upgrading of manufacturing industry. DETAILED DESCRIPTION

[0035] The visual process scheme formulation method of the application includes the following steps:

[0036] A. Construct a bubble chart model to present the digital process information of the part in a visual manner;

[0037] B. Deeply analyze the bubble chart model to mine potential problems and optimization space;

[0038] C. Automatically generate equipment machining code according to the bubble chart model;

[0039] D. Real-time monitoring and adjustment of the production process.

[0040] The visual process scheme formulation method of the application presents the digital process information of the part in a clear and easy-to-understand manner by means of the bubble chart, which is a visual and expressive visualization tool; realizes the organic integration and deep correlation of the digital process information and rich manufacturing experience data, and constructs a comprehensive and integrated process model; uses advanced data analysis and visualization technology to deeply mine potential problems and optimization space in the model, and provides a solid basis for formulating a scientific and reasonable process scheme, thereby providing accurate and effective guidance for production, promoting the realization of fast and intelligent design, and improving the efficiency and quality of development; finally, the equipment machining code covering detailed information such as tool path, cutting parameter and feed speed can be automatically generated according to the bubble process model, and it is ensured that these codes can be accurately and correctly transmitted to the control system of the production equipment, and then a highly automated machining process is realized; through advanced technology and scientific methods for real-time monitoring of equipment machining state, timely and flexible adjustment and optimization can be carried out according to the actual production situation, so as to ensure the accuracy and efficiency of the machining process; the application takes the bubble chart as the core carrier, and through four technical pillars of multi-dimensional data coding, AI deep analysis, 3D spatial interaction and whole-process closed-loop control, the "low efficiency, high cost and experience-dependent" mode of traditional process design is completely innovated, and the process from manual trial and error to intelligent optimization, from flat charts to 3D space mapping, from lagging alarm to real-time closed-loop control is realized. The innovation is not only in the single-point breakthrough of technology, but also in the construction of a new paradigm of process design driven by visualization, empowered by data and closed-loop by intelligence, which provides an efficient, accurate and easy-to-use solution for the intelligent upgrading of manufacturing industry.

[0041] The step A specifically comprises the following steps:

[0042] A1, collecting production process data of the part through a sensor and a data acquisition device, wherein the production process data comprises one or more of process parameters, equipment states and operation records;

[0043] A2, inputting the collected production process data into a bubble chart generation module, and generating a bubble chart by using a graphical algorithm;

[0044] A3, associate the bubble chart with empirical data, the bubble chart realizes the structured integration of complex process data through four-dimensional attribute coding (shape / color / size / transparency), builds a comprehensive process model, and can view detailed information and understand specific parameters and historical data of each process link by clicking the bubble; the empirical data includes one or more of process parameter settings of successful cases, equipment operation state records, and quality test results; the bubble chart not only displays the current process design, but also integrates rich historical experience; compared with the traditional static chart which requires manual cross-system data query and cannot realize real-time linkage analysis, this method can dynamically bind the bubble chart with real-time sensor data and historical experience library (such as successful case parameters), and can penetrate to view the historical fluctuation curve of temperature deviation of a certain process, the optimal parameter interval prompt of similar processes, the bubble attribute change preview after adjusting parameters, and other information. Reduce the loss caused by human error and equipment abnormalities, and reduce production cost.

[0045] The bubble includes a bubble pattern, and the bubble pattern includes shape and / or color and / or size classification, and each bubble represents a process link, and the size and color of the bubble can reflect the importance and state of the link; through the collaborative design of shape classification, color mapping, and size classification of the bubble chart, the traditional process data "fragmentation, static, and low efficiency" is upgraded to a new paradigm of structured, dynamic, and intelligent, and through visual intuition design, complex data is clear at a glance. This innovation not only improves the efficiency and accuracy of process design, but also promotes the deep transformation of manufacturing industry towards visualization and intelligence.

[0046] The step B specifically includes the following steps:

[0047] B1, use machine learning and data mining algorithms to analyze the data in the bubble chart, identify bottlenecks and problems in the process;

[0048] B2, automatically generate optimization suggestions according to the analysis results, the optimization suggestions including one or more of process adjustment, equipment improvement, and operation specification.

[0049] Specific implementation, for example: when an automobile parts enterprise processes aluminum alloy shell, the surface roughness exceeds the standard (Ra>1.6μm), the traditional method takes 2 days to locate the root cause.

[0050] The implementation steps are as follows:

[0051] Step 1: data collection and bubble chart generation

[0052] Data input:

[0053] Sensor data: spindle speed (2000 rpm), feed rate (0.15 mm / tooth), and cutting depth (0.5 mm).

[0054] Quality Data: Surface roughness test result (Ra = 2.0 μm).

[0055] Equipment Log: Tool has been used for 120 hours (life threshold 100 hours).

[0056] Bubble Chart Property Mapping:

[0057] Shape: Circle represents a cutting process.

[0058] Color: Green: Ra ≤ 1.6 μm; Red: Ra > 1.6 μm.

[0059] Size: Bubble diameter is positively correlated with tool usage time (diameter + 2 mm every 10 hours).

[0060] Generated Effects:

[0061] Current Process Bubble is displayed in red (Ra exceeds the standard), with a diameter of 24 mm (tool has been used for 20 hours beyond the limit).

[0062] Step 2: AI Analysis and Optimization Suggestions Generation

[0063] Anomaly Detection: Machine learning model identifies the red bubble and correlates with the historical database to find that among similar problems, 80% are caused by tool wear; after the tool is used beyond the limit, the average Ra increases by 0.3 μm.

[0064] Root Cause Localization: The system compares the current bubble properties (tool usage time = 120 hours) with the threshold in the experience library (100 hours) and determines that the tool life exceeding the limit is the main cause.

[0065] Dynamic Optimization Suggestions:

[0066] Suggestion 1 (High Priority):

[0067] Replace the tool (model: TCMT-321), which is expected to reduce Ra to 1.5 μm.

[0068] Simulation Effect: Bubble color changes from red to green, and diameter resets to 20 mm.

[0069] Suggestion 2 (Auxiliary Adjustment):

[0070] Reduce the feed rate to 0.12 mm / tooth to compensate for the impact of tool wear.

[0071] Simulation Effect: Bubble color changes to yellow (Ra = 1.7 μm), which needs further optimization.

[0072] Step 3: Execution Verification and Feedback

[0073] Adopted suggestion: replace new tool, keep original parameters (feed rate 0.15 mm / tooth, rotation speed 2000 rpm).

[0074] Processing result: surface roughness Ra = 1.4 μm, bubble color restores green. Processing time consumption reduces 15% (due to the improvement of tool sharpness).

[0075] Data sedimentation: optimization results (tool life threshold, feed rate adjustment rule) are automatically stored in the experience library for subsequent similar process calling.

[0076] Technical advantage comparison

[0077]

[0078]

[0079] Traditional process optimization relies on artificial experience, which is difficult to handle complex correlations of multiple parameters. This method takes the multi-dimensional structured data of the bubble chart as input, and the machine learning algorithm can automatically identify abnormal patterns (such as clusters of bubbles with abnormal color), accurately locate bottlenecks. By associating with the historical experience library, the system automatically generates targeted suggestions and simulates the changes in the bubble chart after optimization, supporting rapid verification. The bubble chart is not only a visualization tool, but also a structured data source for algorithm input, making AI analysis more efficient and more targeted.

[0080] The step C specifically comprises the following steps:

[0081] C1. Automatically calculate tool path, cutting parameters and feed speed according to the process parameters defined in the bubble chart model;

[0082] C2. Convert the calculation results into standard device processing code such as G-code, and ensure the accuracy and integrity of the code; directly generate device processing code through bubble chart attributes, avoid manual intervention, and improve code generation efficiency by more than 90%;

[0083] C3. Transfer the generated device processing code to the control system of the production equipment to realize automatic processing.

[0084] The step D specifically comprises the following steps:

[0085] D1. Real-time monitoring of the running state of the device through sensors, the running state including one or more parameters of temperature, pressure and rotation speed;

[0086] D2. Automatically identify abnormal conditions according to real-time monitoring data;

[0087] D3, when an abnormal situation occurs, an alarm is sent to the operator and a corresponding solution suggestion is provided; the device parameters are mapped in real time to the bubble attribute changes (such as color gradient, size fluctuation), and the operator can quickly locate the abnormal device through the bubble chart board. The abnormal bubble triggers the automatic diagnosis module, generates the root cause analysis in combination with the historical fault library, and pushes the solution to the terminal. Abstract data is converted into intuitive visual signals, greatly improving work efficiency; according to real-time monitoring data, abnormal situations can be automatically identified and adjusted to ensure the stability and reliability of the production process.

[0088] In the in-depth analysis of the bubble chart model, the potential problems and optimization space are mined, the historical design data are analyzed by combining AI algorithm, the individualized design suggestions and optimization schemes are provided, and the intelligent level of design is further improved; based on the historical successful cases and the current bubble chart features, the AI recommends the optimal parameter combination, and the AI automatically matches the differentiated optimization strategy for different part types. The optimization scheme adopted by the user is automatically included in the experience library, and the AI recommendation accuracy is continuously improved.

[0089] In the construction of the bubble chart model, the AI technology is used to dynamically present the 3D drawing in the form of a picture; the traditional 2D bubble chart cannot reflect the influence of process parameters on the three-dimensional structure of the part, this method dynamically superimposes the bubble chart on the surface of the part 3D model through AI, and the design intuitiveness is improved. The parameter adjustment effect (such as the change of bubble color after modifying the feed rate) is simulated in the 3D view, the physical trial and error cost is reduced; the inherent logic of traditional design is broken through, the AI technology is innovatively used, the 3D drawing is dynamically presented in the form of a picture, the terminal product is taken as the starting point of design, the strong advantages of AI technology and visual technology are combined, the precision and efficiency of the machining process are greatly improved, the production cost is effectively reduced, and the intelligent and efficient development of manufacturing industry is realized.

[0090] A visual process scheme making system, comprising a processor and a memory, the memory storing program modules, the program modules running on the processor to implement a visual process scheme making method as described above; taking the bubble chart as the data hub, realizing efficient collaboration of multiple modules, and avoiding the "data island" problem of traditional systems.

[0091] In order to further illustrate the practical application effect of the present application, the present application is demonstrated by a specific case as follows:

[0092] In the mold intelligent manufacturing workshop, the mold code writing depends on manual operation, the error rate is high (12%), and the single process design takes 3 days.

[0093] The process of the present application can greatly improve the manufacturing efficiency, and the operation details are as follows.

[0094] Step 1: Process attribute labeling and bubble chart generation

[0095] Data integration:

[0096] Collect historical machining data: tool path (G-code), cutting parameters (2000 rpm, feed rate 0.1 mm / tooth), quality test results (surface roughness Ra≤1.6 μm).

[0097] Attribute mapping rules:

[0098] Color: green = roughness meets standards, red = roughness exceeds standards.

[0099] Size: bubble diameter is proportional to processing time (reference diameter = 10 mm, diameter + 5 mm for every additional hour).

[0100] Dynamic bubble chart generation:

[0101] The system automatically analyzes 200 sets of historical mold data and generates a bubble chart library.

[0102] When designing a new mold, input the target parameters (Ra≤1.6 μm), and the bubble chart will automatically label high-risk procedures (red bubbles).

[0103] Step 2: AI-driven code generation and optimization

[0104] Parameter direct translation:

[0105] Green bubbles correspond to cutting parameters (2000 rpm) to directly generate G-code instructions: S2000 M03.

[0106] Dynamic error correction:

[0107] The system detects that the bubble of a certain procedure is red (Ra=2.0 μm), automatically adjusts the feed rate to 0.08 mm / tooth, and regenerates the code.

[0108] Result verification:

[0109] The error rate of generated code has decreased from 12% to 0.5%, and the design cycle has been shortened from 3 days to 1 hour.

[0110] Technical advantages compared with traditional processes

[0111]

[0112] Of course, the above is only the preferred embodiment of the present application, so any equivalent changes or modifications made to the structure, features and principles described in the scope of the present patent application are included in the scope of the present patent application.

Claims

1. A visual process planning method, characterized by, The method comprises the following steps: A. Constructing a bubble chart model to visually present the digital process information of the part; B. In-depth analysis of the bubble chart model to uncover potential problems and optimization space; C. Automatically generating equipment processing code based on the bubble chart model; D. Real-time monitoring and adjustment of the production process.

2. The method of visualizing a process recipe according to claim 1, wherein, The step A specifically comprises the following steps: A1. Collecting production process data of the part through sensors and data acquisition devices, the production process data including one or more of process parameters, equipment status and operation records; A2. Inputting the collected production process data into a bubble chart generation module and generating a bubble chart using a graphical algorithm; A3. Associating the bubble chart with empirical data to construct a comprehensive process model, and clicking on the bubble to view detailed information and understand the specific parameters and historical data of each process link.

3. The method of visualizing a process recipe according to claim 2, wherein: The empirical data includes one or more of process parameter settings of successful cases, equipment operation status records, and quality test results.

4. The method of visualizing a process recipe according to claim 2, wherein: The bubble includes a bubble pattern, and the bubble pattern includes shape and / or color and / or size classification.

5. The method of visualizing a process recipe according to claim 1, wherein, The step B specifically comprises the following steps: B1. Analyzing the data in the bubble chart using machine learning and data mining algorithms to identify bottlenecks and problems in the process; B2. Automatically generating optimization suggestions based on the analysis results, the optimization suggestions including one or more of process adjustment, equipment improvement and operation specification.

6. The method of visualizing a process recipe according to claim 1, wherein, The step C specifically comprises the following steps: C1. Automatically calculating tool path, cutting parameters and feed speed according to the process parameters defined in the bubble chart model; C2. Converting the calculation results into standard equipment processing code; C3. Transmitting the generated equipment processing code to the control system of the production equipment.

7. The method of visualizing a process recipe according to claim 1, wherein, The step D specifically comprises the following steps: D1. Real-time monitoring of the running status of the equipment through sensors, the running status including one or more parameters of temperature, pressure and rotation speed; D2. Automatically identifying abnormal conditions based on real-time monitoring data; D3. When an abnormal condition occurs, sending an alarm to the operator and providing corresponding solution suggestions.

8. The method of visualizing a process recipe according to claim 1, wherein, When in-depth analysis of the bubble chart model, AI algorithm is used to analyze historical design data to provide personalized design suggestions and optimization schemes.

9. The method of visualizing a process recipe according to claim 1, wherein, When constructing the bubble chart model, AI technology is used to present 3D drawings in the form of pictures.

10. A visual process planning system comprising a processor and a memory, the memory storing program modules, characterized by: The program module runs on the processor to implement a visual process scheme development method according to any one of claims 1-9.

Images