Intelligent manufacturing system for large complex thin-walled workpiece
By introducing process databases, intelligent control systems and monitoring systems in the manufacturing of large and complex thin-walled parts, combined with computer vision and fault diagnosis algorithms, the problems of machine-added deformation and low production efficiency during the milling process are solved, and high quality and high efficiency are achieved intelligent manufacturing system.
Patent Information
- Application Number
- CN202411213680.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-30
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2044-08-30
AI Technical Summary
During the milling and manufacturing process, large and complex thin-walled parts have problems such as machine deformation, processing vibration, relying on experience in process flow, high working strength of operators, and low production efficiency, resulting in impact on surface quality and production efficiency.
Using process database, intelligent control system, processing system, measurement and feedback system and monitoring system, combined with computer vision, point cloud technology, vibration sensor, acoustic sensor and fault diagnosis neural network algorithm, to realize automated and intelligent processing process management and real-time monitoring and adjust processing parameters, dynamically optimize process routes and parameters.
It improves the forming quality and production efficiency of thin-walled parts, reduces machine-added deformation and processing vibration, realizes automated and intelligent full-process management, and improves the processing efficiency and quality stability of the product.
Smart Images

Figure CN119077358A_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the technical field of intelligent manufacturing and relates to an intelligent manufacturing system for large-scale complex thin-walled parts. Background Art
[0002] Large and complex thin-walled parts are widely used in shipbuilding, automobile, aerospace and other engineering fields as skins, load-bearing structures, fuel tanks and other parts due to their unique low mass, high load-bearing and high strength characteristics. Large and complex thin-walled parts are widely used, and they are generally formed by milling, but there are still a series of difficulties and shortcomings in the milling manufacturing process:
[0003] (1) Due to the large amount of material removal, the material stress is completely released, which is very easy to produce large machining deformation. In addition, thin-walled parts have low rigidity and are prone to machining vibration during milling, which seriously affects the surface quality after forming.
[0004] (2) In the process of forming, in order to avoid the influence of machining deformation on the forming process, it is necessary to insert the heat treatment process into the machining material removal process. However, the arrangement of the process flow is based solely on the experience of the process personnel, which poses a hidden danger to the performance of the product.
[0005] (3) The workload of operators in production and processing is high. During the processing, the surface quality and machining deformation need to be manually inspected at any time, and the machine tool cutting parameters need to be adjusted, resulting in low product processing efficiency.
[0006] (4) The thin-walled parts forming process is complex and needs to be transferred between various equipment in various workshops, which brings great difficulties to the arrangement of workshop production tasks and seriously affects the production efficiency of products. Summary of the invention
[0007] The purpose of the present invention is to overcome the deficiencies in the prior art and provide an intelligent manufacturing system for large complex thin-walled parts.
[0008] In order to achieve the above object, the present invention adopts the following technical solutions:
[0009] A large-scale complex thin-walled parts intelligent manufacturing system, including process database, intelligent control system, processing system, measurement feedback system, monitoring system,
[0010] The process database is used to collect and store process data and process experience data in the manufacturing process, perform knowledge modeling on the process data and process experience data, and form an expert knowledge system; combined with the input workpiece information to be processed, the process route and processing parameters are output;
[0011] The intelligent control system is used to receive the process route and processing parameters from the process database, generate NC programs, and perform intelligent scheduling of production plans;
[0012] After receiving the instruction from the intelligent control system, the processing system completes the machining and heat treatment process according to the NC program and process regulations;
[0013] The monitoring system uses vibration sensors, acoustic sensors, temperature sensors and monitoring cameras to monitor the operation of the equipment, and the obtained equipment operation information is fed back to the intelligent control system in real time;
[0014] The measurement feedback system utilizes computer vision and point cloud technology to perform three-dimensional reconstruction of the workpiece to be processed, detects its deformation in real time, and feeds back the deformation to the process database.
[0015] As a preferred embodiment, the process database adjusts the processing parameters and process routes according to the machining deformation information fed back by the measurement feedback system.
[0016] As a preferred embodiment, the process data include machine tool rotation speed, feed speed, back cutting depth, and their corresponding key dimensions of the workpiece to be processed.
[0017] As a preferred embodiment, the process experience data includes the process route, the processing allowance of each process step and the heat treatment node.
[0018] As a preferred method, the process database establishes a dynamic multi-objective optimization algorithm for product processability. Based on the process route formulated by the expert knowledge system, in each process, the dynamic multi-objective optimization algorithm for product processability is used to obtain the most suitable processing parameters for the process. The model of the dynamic multi-objective optimization algorithm is:
[0019]
[0020] Among them, x is the three elements of machining (machine tool speed, feed speed, back cutting amount), key dimensions, and processing time; X is the actual three elements of machining, key dimensions, and processing time; μ is the three elements of machining, key dimensions, and processing time in the database; n represents the number of data groups in the process database; R is the change limit of the three elements of machining, key dimensions, and processing time.
[0021] As a preferred embodiment, the monitoring system integrates a fault diagnosis neural network algorithm, inputs machine tool temperature (T1, T2...Tm), sound signals (H1, H2...Hk), and vibration signals (f1, f2...fn) into the fault diagnosis neural network algorithm, and outputs the probability of equipment failure.
[0022] The present invention has the following advantages:
[0023] The present invention provides an automated and intelligent intelligent manufacturing system for the entire process of machining large-scale complex thin-walled parts. BRIEF DESCRIPTION OF THE DRAWINGS
[0024] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION
[0025] The present invention will be described in detail below in conjunction with the accompanying drawings.
[0026] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.
[0027] Example:
[0028] A large-scale complex thin-walled parts intelligent manufacturing system, including process database, intelligent control system, processing system, measurement feedback system, monitoring system,
[0029] (1) Based on the previous process experience and processing data, a database of part process regulations and processing data is established. The database is supported by the PDM system (process experience) and QMS system (process data) commonly used in digital workshops. The process experience includes the process route, the processing allowance of each process, and the heat treatment node; the processing data includes the three elements of machining (machine tool speed, feed speed, back cutting amount) and the inspection of the key dimensions of the product corresponding to the three elements of machining.
[0030] (2) Based on the data in the processing database, after obtaining clear and reliable processing data through data cleaning and data mining technology, the processing data is modeled using the transformer natural language processing model based on the seq2seq architecture to build an expert knowledge system. The structural characteristics, raw material model, materials, key dimensions, etc. of the target processing parts are input into the expert knowledge system in the form of questions and answers, so as to obtain the processing process route given by the expert knowledge system.
[0031] (3) Using the process experience stored in the database and the influence of processing parameters on part machining deformation and processing efficiency, a dynamic multi-objective optimization algorithm for product processability is established.
[0032] The model of the dynamic multi-objective optimization algorithm is:
[0033]
[0034] Where x is the three elements of machining, key dimensions and processing time, X is the actual three elements of machining, key dimensions and processing time, μ is the three elements of machining, key dimensions and processing time in the database, n represents the number of data groups in the database, and R is the variation limit of the three elements of machining, key dimensions and processing time.
[0035] Based on the process route proposed by the expert knowledge system, in each process, the dynamic multi-objective optimization algorithm of product processability is used to obtain the most suitable processing parameters for the process.
[0036] (4) After receiving the process route and processing parameters from the process database, the intelligent control system can generate NC programs and intelligently schedule production plans.
[0037] (5) After receiving instructions from the intelligent control system, the processing system can complete the corresponding machining and heat treatment processes according to the NC program and process regulations.
[0038] (6) The monitoring system uses vibration sensors, acoustic sensors, temperature sensors and surveillance cameras to monitor the operation of equipment such as machine tools and thermal aging furnaces. The monitoring system integrates a fault diagnosis neural network algorithm, inputs machine tool temperature (T1, T2...Tm), acoustic signals (H1, H2...Hk), and vibration signals (f1, f2...fn) into the fault diagnosis neural network algorithm, outputs the probability of equipment failure, and the obtained equipment operation information is fed back to the intelligent control system in real time.
[0039] (7) During the machining process, the measurement feedback system uses computer vision and point cloud technology to perform three-dimensional reconstruction of the workpiece. The deformation is detected in real time and fed back to the process database. After receiving the deformation information, the process database updates the process experience data in the library and optimizes the processing parameters and process routes in a targeted manner. This achieves closed-loop control of the entire system to ensure product quality.
[0040] The present invention is not limited to the above-mentioned specific embodiments, but extends to any new features or any new combination disclosed in this specification, as well as any new method or process steps or any new combination disclosed.
Claims
1. An intelligent manufacturing system for large complex thin-walled parts, characterized by: Including process database, intelligent control system, processing system, measurement feedback system, monitoring system, The process database is used to collect and store process data and process experience data in the manufacturing process, perform knowledge modeling on the process data and process experience data, and form an expert knowledge system; combined with the input workpiece information to be processed, the process route and processing parameters are output; The intelligent control system is used to receive the process route and processing parameters from the process database, generate NC programs, and perform intelligent scheduling of production plans; After receiving the instruction from the intelligent control system, the processing system completes the machining and heat treatment process according to the NC program and process regulations; The monitoring system uses vibration sensors, acoustic sensors, temperature sensors and monitoring cameras to monitor the operation of the equipment, and the obtained equipment operation information is fed back to the intelligent control system in real time; The measurement feedback system utilizes computer vision and point cloud technology to perform three-dimensional reconstruction of the workpiece to be processed, detects its deformation in real time, and feeds back the deformation to the process database.
2. According to claim 1, a large-scale complex thin-walled parts intelligent manufacturing system is characterized by: The process database adjusts the processing parameters and process routes according to the machining deformation information fed back by the measurement feedback system.
3. According to claim 1, a large-scale complex thin-walled parts intelligent manufacturing system is characterized by: The process data include machine tool rotation speed, feed speed, cutting depth, and their corresponding key dimensions of the workpiece to be processed.
4. According to claim 1, a large-scale complex thin-walled parts intelligent manufacturing system is characterized by: The process experience data includes the process route, the processing allowance of each process step and the heat treatment node.
5. According to claim 1, a large-scale complex thin-walled parts intelligent manufacturing system is characterized by: The process database establishes a dynamic multi-objective optimization algorithm for product processability. Based on the process route formulated by the expert knowledge system, in each process, the dynamic multi-objective optimization algorithm for product processability is used to obtain the most suitable processing parameters for the process. The model of the dynamic multi-objective optimization algorithm is: Among them, x is the three elements of machining, key dimensions, and processing time; X is the actual three elements of machining, key dimensions, and processing time; μ is the three elements of machining, key dimensions, and processing time in the database; n represents the number of data groups in the process database; R is the variation limit of the three elements of machining, key dimensions, and processing time.
6. According to claim 1, a large-scale complex thin-walled parts intelligent manufacturing system is characterized by: The monitoring system integrates a fault diagnosis neural network algorithm, into which machine tool temperature (T1, T2...Tm), sound signals (H1, H2...Hk), and vibration signals (f1, f2...fn) are input, and the probability of equipment failure is output.
Citation Information
Patent Citations
Intelligent spinning system and spinning method
CN108405696A
Control system of industrial machine
CN110737242A
Numerical control machine tool process parameter real-time dynamic multi-objective optimization method under information physical system
CN116820029A
Digital twin polishing and grinding method and system with self-adaptive function
CN118493091A
Digital twin systems and methods for transportation systems
US20210287459A1
