Numerical control machining process simulation and machining data mapping analysis method

Abstract

The invention discloses a numerical control machining process simulation and machining data mapping analysis method, and relates to the technical field of numerical control machining. And real-time monitoring and optimization of the numerical control machining process are realized through a high-precision simulation technology and a data mapping algorithm. The method comprises the following steps: firstly, constructing a high-precision simulation environment based on machining parameters and a workpiece model of a numerical control machine tool; secondly, key data in the actual machining process are acquired through a data acquisition system; secondly, comparing and analyzing simulation data and actual data by utilizing a mapping algorithm, identifying a machining error and optimizing machining parameters; finally, the optimized parameters are fed back to the numerical control system, and closed-loop control is achieved. The machining precision and efficiency can be remarkably improved, the production cost is reduced, and the method is suitable for the numerical control machining field of complex parts.

Description

Technical Field

[0001] The present invention relates to the technical field of numerical control machining, and in particular to a numerical control machining process simulation and machining data mapping analysis method. Background Art

[0002] CNC machining technology plays a vital role in modern manufacturing. However, during the machining of complex parts, errors often occur due to improper machining parameter settings or the dynamic characteristics of machine tools. Traditional machining optimization methods rely on experience or trial and error, which is inefficient and difficult to meet high-precision requirements. While existing simulation techniques can be used to predict machining processes, their poor correlation with actual machining data makes precise optimization difficult. Therefore, there is an urgent need for a method that can effectively map and analyze simulation data with actual machining data to improve machining accuracy and efficiency. Summary of the Invention

[0003] In view of the deficiencies in the existing technology, the purpose of the present invention is to provide a CNC machining process simulation and machining data mapping analysis method, which realizes real-time monitoring and optimization of the machining process through high-precision simulation and data mapping technology.

[0004] In order to achieve the above object, the present invention is implemented through the following technical solution: a method for simulating a numerical control machining process and mapping and analyzing machining data, comprising the following steps:

[0005] 1. Simulation environment construction

[0006] Based on the 3D model of the machine tool, a digital twin that includes the tool-workpiece contact dynamics is established; the 3D model of the machined part and the machining parameters are input, and a simulation environment is constructed using finite element analysis software to simulate the cutting force and vibration dynamic characteristics during the machining process.

[0007] 2. Data collection and processing

[0008] A sensor network is installed on the CNC machine tool to collect processing data in real time, remove noise through filtering algorithms, and extract time-frequency domain features to ensure data quality.

[0009] 3. Data Mapping and Analysis

[0010] A nonlinear mapping relationship between simulation data and actual data is established through a machine learning model; based on the mapping results:

[0011] a) Use gradient sensitivity analysis to identify key error sources;

[0012] b) quantifying the deviation between simulation and actual data through the difference function;

[0013] c) Optimize machining parameters with the goal of minimizing deviation;

[0014] 4. Closed-loop control and feedback;

[0015] The optimized parameters (such as spindle speed, feed speed, etc.) are fed back to the CNC system to adjust the machining process in real time to ensure machining accuracy.

[0016] 5. Visualization and report generation

[0017] The machining process is displayed through 3D dynamic simulation diagrams, and an optimization report is generated for the operator's reference.

[0018] Preferably, the data collection in step 2 adopts a distributed sensor network, including:

[0019] Three-axis vibration sensor, sampling frequency ≥ 20kHz, installed on the spindle end and workpiece fixture;

[0020] Infrared temperature sensor, temperature measurement range 20-600℃, spatial resolution 0.05mm;

[0021] Piezoelectric force sensor, range ±5kN, linearity ≤0.3% FS.

[0022] Preferably, the data processing in step 2 includes:

[0023] Perform wavelet packet decomposition on the vibration signal to extract the energy proportion of the 5-10kHz frequency band;

[0024] Kalman filtering is used to fuse multi-sensor temperature data to generate the temperature field of the tool-workpiece contact area.

[0025] Preferably, the data mapping and analysis in step 3 specifically includes:

[0026] 3.1 Time dimension mapping: aligning simulation and physical data timing through the dynamic time warping (DTW) algorithm;

[0027] 3.2 Spatial dimension mapping: using the iterative closest point (ICP) algorithm to match the simulated / actual tool path point cloud;

[0028] 3.3 Deviation calculation: Use the weighted Euclidean distance formula:

[0029]

[0030] where w i is the weight coefficient of cutting force, temperature and vibration parameters; D is the comprehensive deviation; s i is the predicted value of the i-th parameter in the simulation system; p i is the measured value of the i-th parameter in actual processing; m is the total number of parameters involved in the calculation.

[0031] Preferably, the step weight coefficient wi is dynamically adjusted through a machine learning model, and the input features include: material removal rate, tool wear status, and cutting fluid spray coverage.

[0032] Preferably, the closed-loop control and feedback in step 4 specifically include:

[0033] Generate an optimization parameter set ΔP={Δf,Δa p ,Δv c};

[0034] Write parameters to CNC system registers in real time via OPC UA protocol;

[0035] Set a safety threshold to trigger an emergency stop when the predicted surface roughness Ra>1.6μm.

[0036] Preferably, the constraints of the optimization parameters are:

[0037] Where MRR is the material removal rate, F cutting is the measured cutting force; F max The maximum cutting force rated for the machine tool.

[0038] Preferably, the visualization of step 5 includes:

[0039] The three-dimensional color temperature map shows the temperature distribution in the tool-workpiece contact area;

[0040] Real-time update of stability lobe diagram to predict flutter risk;

[0041] The virtual tool path and actual processing deviation are superimposed and displayed through AR glasses.

[0042] The present invention has the following beneficial effects:

[0043] 1. Achieve accurate mapping between simulation data and actual processing data to improve analysis reliability.

[0044] 2. Monitor the machining process in real time, quickly identify and correct errors, and improve machining accuracy.

[0045] 3. Dynamic optimization of processing parameters is achieved through closed-loop control to improve production efficiency.

[0046] 4. Suitable for CNC machining of complex parts, with strong versatility and practicality. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments;

[0048] Figure 1 Flow chart of the method of the present invention. DETAILED DESCRIPTION

[0049] In order to make the technical means, creative features, objectives and effects achieved by the present invention easier to understand, the present invention is further described below in conjunction with specific implementation methods.

[0050] Reference Figure 1 , this specific embodiment adopts the following technical solution: a numerical control machining process simulation and machining data mapping analysis method, comprising the following steps:

[0051] 1. Simulation environment construction

[0052] Based on the 3D model of the machine tool, a digital twin that includes the tool-workpiece contact dynamics is established; the 3D model of the machined part and the machining parameters are input, and a simulation environment is constructed using finite element analysis software to simulate the dynamic characteristics of the cutting force, vibration, etc. during the machining process.

[0053] 2. Data collection and processing

[0054] A distributed sensor network is installed on the CNC machine tool, such as a three-axis vibration sensor with a sampling frequency of ≥20kHz, installed at the spindle end and the workpiece fixture; an infrared temperature sensor with a temperature measurement range of 20-600℃ and a spatial resolution of 0.05mm; a piezoelectric force sensor with a range of ±5kN and a linearity of ≤0.3%FS. These sensors collect processing data in real time, perform wavelet packet decomposition on the vibration signal, and extract the energy proportion in the 5-10kHz frequency band; and use Kalman filtering to fuse multi-sensor temperature data to generate the temperature field of the tool-workpiece contact area.

[0055] 3. Data Mapping and Analysis

[0056] A nonlinear mapping relationship between simulation data and actual data is established through a machine learning model; based on the mapping results:

[0057] a) Use gradient sensitivity analysis to identify key error sources;

[0058] b) quantifying the deviation between simulation and actual data through the difference function;

[0059] c) Optimize machining parameters with the goal of minimizing deviation;

[0060] 4. Closed-loop control and feedback;

[0061] The optimized parameters (such as spindle speed, feed speed, etc.) are fed back to the CNC system to adjust the machining process in real time to ensure machining accuracy.

[0062] 5. Visualization and report generation

[0063] The machining process is displayed through 3D dynamic simulation diagrams, and an optimization report is generated for the operator's reference.

[0064] 5.1 Time dimension mapping: Align simulation and physical data timing using the dynamic time warping (DTW) algorithm;

[0065] 5.2 Spatial dimension mapping: Use the iterative closest point (ICP) algorithm to match the simulated / actual tool path point cloud;

[0066] 5.3 Deviation calculation: Use the weighted Euclidean distance formula:

[0067]

[0068] where w i is the weight coefficient of cutting force, temperature and vibration parameters; D is the comprehensive deviation; s i is the predicted value of the i-th parameter in the simulation system; p i is the measured value of the i-th parameter in actual processing; m is the total number of parameters involved in the calculation.

[0069] The step weight coefficient wi is dynamically adjusted through a machine learning model, and the input features include: material removal rate, tool wear status, and cutting fluid spray coverage.

[0070] The closed-loop control and feedback of step 4 specifically include:

[0071] Generate an optimization parameter set ΔP={Δf,Δa p ,Δv c};

[0072] Write parameters to CNC system registers in real time via OPC UA protocol;

[0073] Set a safety threshold to trigger an emergency stop when the predicted surface roughness Ra>1.6μm.

[0074] The constraints of the optimization parameters are:

[0075]

[0076] The visualization of step 5 includes:

[0077] The three-dimensional color temperature map shows the temperature distribution in the tool-workpiece contact area;

[0078] Real-time update of stability lobe diagram to predict flutter risk;

[0079] The virtual tool path and actual processing deviation are superimposed and displayed through AR glasses.

[0080] This specific embodiment utilizes high-precision simulation technology and a data mapping algorithm to achieve real-time monitoring and optimization of the CNC machining process. The method includes the following steps: first, constructing a high-precision simulation environment based on the CNC machine tool's machining parameters and workpiece model; second, acquiring key data from the actual machining process through a data acquisition system; then, using a mapping algorithm, comparing and analyzing the simulated data with the actual data to identify machining errors and optimize machining parameters; finally, feeding the optimized parameters back to the CNC system to achieve closed-loop control. This invention can significantly improve machining accuracy and efficiency, reduce production costs, and is suitable for CNC machining of complex parts.

[0081] Example 1 (machining of aerospace impellers): Machine tool used: DMU200 monoBLOCK five-axis machining center; workpiece material: Ti-6Al-4V titanium alloy blade; tool: φ6mm solid carbide ball end mill.

[0082] The specific steps are as follows:

[0083] 1. Data collection:

[0084] Vibration signal → FFT analysis of the main frequency band (500-800Hz)

[0085] Temperature field → Identify the highest temperature area (tool rake face, ΔTmax≈120°C)

[0086] 2. Virtual-Real Mapping:

[0087] Fusion of simulated / actual cutting force data through Kalman filtering

[0088] Dynamic adjustment of feed speed:

[0089] 3. Quality prediction:

[0090] Surface roughness calculation:

[0091] Output optimization suggestion: reduce the speed by 15% and increase the axial cutting depth by 0.2mm

[0092] The specific parameter optimization results are as follows:

[0093]

[0094] Example 2 (Mold Steel Precision Machining): Machine Tool: Makino F5 Vertical Machining Center; Workpiece Material: H13 Mold Steel (HRC52); Machining Features: Deep Cavity and Narrow Groove (Aspect Ratio > 8)

[0095] The specific improvements are as follows:

[0096] 1. Special constraint processing: Add lateral force constraint for narrow groove processing:

[0097] 2. Tool wear compensation: online estimation of wear and correction of cutting force model;

[0098] 3. Comparison of implementation effects:

[0099] index Traditional methods The present invention Dimensional accuracy ±0.05mm ±0.02mm Corner overcut 0.12mm 0.03mm Processing efficiency <![CDATA[85cm 3 / hr]]> <![CDATA[112cm 3 / hr]]>

[0100] For sensor disconnection faults: automatically switch to hybrid monitoring mode based on motor current + acoustic emission signals;

[0101] For simulation divergence failures: trigger local mesh refinement (h-adaptation) and restart the calculation.

[0102] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for NC machining process simulation and machining data mapping analysis, characterized in that: The following steps are involved: (1) Construction of simulation environment A digital twin that includes tool-workpiece contact dynamics is established based on the 3D model of the machine tool. The 3D model of the machined part and machining parameters are input, and a simulation environment is constructed using finite element analysis software to simulate the cutting forces and vibration dynamics during machining. (2) Data collection and processing Install a sensor network on the CNC machine tool to collect processing data in real time, remove noise through filtering algorithms, and perform time-frequency domain feature extraction to ensure data quality; (3) Data mapping and analysis A nonlinear mapping relationship between simulation data and actual data is established through a machine learning model; based on the mapping results: (a) Use gradient sensitivity analysis to identify key error sources; (b) Quantify the deviation between simulation and actual data through the difference function; (c) Optimizing machining parameters with the goal of minimizing deviation; (4) Closed-loop control and feedback; Feedback the optimized parameters to the CNC system to adjust the machining process in real time to ensure machining accuracy; (5) Visualization and report generation The machining process is displayed through 3D dynamic simulation diagrams, and an optimization report is generated for the operator's reference.

2. A method for NC machining process simulation and machining data mapping analysis according to claim 1, characterized in that: The data collection in step (2) adopts a distributed sensor network, including: Three-axis vibration sensor, sampling frequency ≥ 20kHz, installed on the spindle end and workpiece fixture; Infrared temperature sensor, temperature measurement range 20-600℃, spatial resolution 0.05mm; Piezoelectric force sensor, range ±5kN, linearity ≤0.3% FS.

3. The method for NC machining process simulation and machining data mapping analysis according to claim 1, characterized in that: The data processing of step (2) includes: Perform wavelet packet decomposition on the vibration signal to extract the energy proportion of the 5-10kHz frequency band; Kalman filtering is used to fuse multi-sensor temperature data to generate the temperature field of the tool-workpiece contact area.

4. A method for NC machining process simulation and machining data mapping analysis according to claim 1, characterized in that: The data mapping and analysis in step (3) specifically includes: (3.1) Time dimension mapping: aligning simulation and physical data timing using the dynamic time warping (DTW) algorithm; (3.2) Spatial dimension mapping: using the iterative closest point (ICP) algorithm to match the simulated / actual tool path point cloud; (3.3) Deviation calculation: Use the weighted Euclidean distance formula: where w i is the weight coefficient of cutting force, temperature and vibration parameters; D is the comprehensive deviation; s i is the predicted value of the i-th parameter in the simulation system; p i is the measured value of the i-th parameter in actual processing; m is the total number of parameters involved in the calculation.

5. A method for NC machining process simulation and machining data mapping analysis according to claim 4, characterized in that: The step weight coefficient wi is dynamically adjusted through a machine learning model, and the input features include: material removal rate, tool wear status, and cutting fluid spray coverage.

6. The method for NC machining process simulation and machining data mapping analysis according to claim 1, characterized in that: The closed-loop control and feedback of step (4) specifically include: Generate an optimization parameter set ΔP={Δf,Δa p ,Δv}; where Δf is the feed speed adjustment; Δa is the axial cutting depth adjustment; Δv is the cutting speed adjustment; Write parameters to CNC system registers in real time via OPC UA protocol; Set a safety threshold to trigger an emergency stop when the predicted surface roughness Ra>1.6μm.

7. A method for NC machining process simulation and machining data mapping analysis according to claim 6, characterized in that: The constraints of the optimization parameters are:

8. The method for NC machining process simulation and machining data mapping analysis according to claim 1, characterized in that: The visualization of step (5) includes: The three-dimensional color temperature map shows the temperature distribution in the tool-workpiece contact area; Real-time update of stability lobe diagram to predict flutter risk; The virtual tool path and actual processing deviation are superimposed and displayed through AR glasses.

Images