scholarly journals Contour Error Modeling and Compensation of CNC Machining Based on Deep Learning and Reinforcement Learning

2021 ◽  
Author(s):  
Yakun Jiang ◽  
Jihong Chen ◽  
Huicheng Zhou ◽  
Jianzhong Yang ◽  
Pengcheng Hu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Reinforcement Learning ◽  
Tracking Error ◽  
Cnc Machining ◽  
Numerical Control ◽  
Contour Error ◽  
Error Prediction ◽  
Machining Accuracy ◽  
Good Precision ◽  
Compensation Strategy

Abstract Contour error compensation of the Computer Numerical Control (CNC) machine tool is a vital technology that can improve machining accuracy and quality. To achieve this goal, the tracking error of a feeding axis, which is a dominant issue incurring the contour error, should be firstly modeled and then a proper compensation strategy should be determined. However, building the precise tracking error prediction model is a challenging task because of the nonlinear issues like backlash and friction involved in the feeding axis; besides, the optimal compensation parameter is also difficult to determine because it is sensitive to the machining tool path. In this paper, a set of novel approaches for contour error prediction and compensation is presented based on the technologies of deep learning and reinforcement learning. By utilizing the internal data of the CNC system, the tracking error of the feeding axis is modeled as a Nonlinear Auto-Regressive Long-Short Term Memory (NAR-LSTM) network, considering all the nonlinear issues of the feeding axis. Given the contour error as calculated based on the predicted tracking error of each feeding axis, a compensation strategy is presented with its parameters identified efficiently by a Time-Series Deep Q-Network (TS-DQN) as designed in our work. To validate the feasibility and advantage of the proposed approaches, extensive experiments are conducted, testifying that, our approaches can predict the tracking error and contour error with very good precision (better than about 99% and 90% respectively), and the contour error compensated based on the predicted results and our compensation strategy is significantly reduced (about 70%~85% reduction) with the machining quality improved drastically (machining error reduced about 50%).

scholarly journals Multi-Stage Prediction of Feed System Time Series

2021 ◽  
Author(s):  
Lihua Shen ◽  
Biling Wang ◽  
Hongjun Liu
Keyword(s):  
Time Series ◽  
Prediction Models ◽  
Tracking Error ◽  
Cnc Machining ◽  
Numerical Control ◽  
Machining Accuracy ◽  
Feed Speed ◽  
Feed System ◽  
Multi Stage ◽  
Robust Prediction

In order to reduce the tracking error of the computer numerical control (CNC) feed system and improve the CNC machining accuracy, a novel prediction model is proposed based on fuzzy C-means robust variational echo state network. Firstly, the feed speed time series is clustered, and then reconstructed for different categories. The multi-stage robust prediction models are established to realize the multi-state robust prediction of the CNC machining feed velocity to reduce the tracking error of the feed system. Finally, the reference and actual time series with different feed speed are used to verify the established models. The results show that the proposed method can reduce the tracking error and realize the effective prediction of the time series of the feed system.

Synchronous Adjustment of Milling Tool Path Based on the Relative Deviation

2011 ◽  
Vol 133 (5) ◽  
Author(s):  
Xiao-Jin Wan ◽  
Cai-Hua Xiong ◽  
Lin Hua
Keyword(s):  
Tool Path ◽  
Cutting Tool ◽  
Cnc Machining ◽  
Numerical Control ◽  
Machining Process ◽  
Machining Accuracy ◽  
Source File ◽  
Modern Computer ◽  
Adjustment Strategy ◽  
Machining System

In machining process, machining accuracy of part mainly depends on the position and orientation of the cutting tool with respect to the workpiece which is influenced by errors of machine tools and cutter-workpiece-fixture system. A systematic modeling method is presented to integrate the two types of error sources into the deviation of the cutting tool relative to the workpiece which determines the accuracy of the machining system. For the purpose of minimizing the machining error, an adjustment strategy of tool path is proposed on the basis of the generation principle of the cutter location source file (CLSF) in modern computer aided manufacturing (CAM) system by means of the prediction deviation, namely, the deviation of the cutting tool relative to the workpiece in computer numerical control (CNC) machining operation. The resulting errors are introduced as adjustment values to adjust the nominal tool path points from cutter location source file from commercial CAM system prior to machining. Finally, this paper demonstrates the effectiveness of the prediction model and the adjustment technique by two study cases.

scholarly journals A Novel Position Domain Controller For Contour Tracking Performance Improvement

2021 ◽  
Author(s):  
Truong Dam
Keyword(s):  
Time Domain ◽  
Phase Error ◽  
Common Factor ◽  
Tracking Error ◽  
Numerical Control ◽  
Tracking Performance ◽  
Contour Error ◽  
Contour Tracking ◽  
Cnc Machine ◽  
Equivalent Time

A common problem with modern manufacturing processes that utilize high feed-rate machining is how to accurately track a given contour for the tool center point (TCP) of a system. Various methods have been developed to increase axial tracking performance and contouring performance of computerized numerical control (CNC) machines. These include: high gain feedback controllers, feedforward controllers, zero phase error tracking controllers (ZPETC), cross-coupled control (CCC), and iterative learning control to mention a few. The common factor amongst these methods is that they are all based in time domain. This thesis will propose a new control law based in position domain applied to contour tracking control of a CNC machine. The goal of this developed controller is to improve the overall tracking and contouring performance of a CNC system. The idea behind a position domain control involves transforming the dynamics of a system from time domain into position domain through a one-to-one mapping. In the position domain system control, the motion of one of the axis is used as an independent reference by sampling equidistantly to control the remaining axes according to the contouring requirements. The overall contour error in a position domain controller should be lower relative to an equivalent time domain controller since there will be a zero tracking error from the reference motion. The stability of the proposed position domain control is proven through the Lyapunov method. Simulations with linear and nonlinear TCP contours using the proposed position domain controller and an equivalent time domain controller indicate that the proposed position domain control can improve tracking and contouring performance. In addition, a position domain controller with cross-coupled control was also proposed to further improve contour performance.

Tracking Error Transform in Parallel Kinematic Machining

2010 ◽  
Vol 450 ◽  
pp. 585-588
Author(s):  
Ghasem Amirian ◽  
Christian Schenck ◽  
Bernd Kuhfuss
Keyword(s):  
Machine Tools ◽  
High Speed ◽  
Tracking Error ◽  
Contour Error ◽  
Machining Accuracy ◽  
Tracking Errors ◽  
High Productivity ◽  
Machine Errors ◽  
Parallel Kinematic ◽  
Servo Tracking

Parallel kinematic machine tools (PKM) are developed to increase dynamic parameters for high speed and high accuracy machining to gain short lead times and high productivity. One of the most important components of machine tools is the numerical controller (NC). Most NCs are organized in a cascaded structure, comprising the position, velocity and current loops. Commonly applied servo controllers generate tracking errors in each axis. These tracking errors are a significant factor that affects machining accuracy, beside geometric machine errors, vibrations, temperature changes and tool errors. In this paper the contour error originated from servo tracking controller in Cartesian kinematic machine tools (CKM) with perpendicular arranged machine axes and PKM is presented. The effects of the forward transformation of the tracking errors in PKM are addressed with experiment and simulation results. The servo tracking effect on trace accuracy is discussed by a tripod mechanism and radial deviations are measured with double ball bar method (DBB).

Research on Subdivision Interpolation for High Speed CNC Applications

2011 ◽  
Vol 141 ◽  
pp. 449-454
Author(s):  
Jing Chuan Dong ◽  
Qing Jian Liu ◽  
Tai Yong Wang
Keyword(s):  
High Speed ◽  
Tool Path ◽  
Tracking Error ◽  
Linear Interpolation ◽  
Cnc Machining ◽  
Contour Error ◽  
Interpolation Scheme ◽  
Simulation Results ◽  
Cnc Controller ◽  
Better Than

High speed CNC machining relies on the smooth interpolation of tool path in order to prevent impact and vibration. We present a new interpolation scheme for CNC controller based on 6-point subdivision. The subdivision interpolation improves the smoothness of the original trajectory, while maintaining the accuracy. The algorithm is simple and effective, and therefore it is suitable for real-time execution in CNC controllers. Simulation results show that the proposed method performs better than linear interpolation, since the tracking error and contour error is reduced.

scholarly journals The Application of Intelligent Manufacturing Technology in CNC Tools Design and Machining

2021 ◽  
Vol 2143 (1) ◽  
pp. 012045
Author(s):  
Zhaohui Su
Keyword(s):  
Cutting Tools ◽  
Development Trend ◽  
Intelligent Manufacturing ◽  
Manufacturing Technology ◽  
Cnc Machining ◽  
Numerical Control ◽  
Quality Level ◽  
Machining Accuracy ◽  
Industrial Manufacturing ◽  
Manufacturing Intelligence

Abstract CNC tool is a kind of cutting tools in industrial manufacturing. With the improvement of CNC machining accuracy and quality level, it puts forward more strict requirements for the performance of the cutting tool. Its manufacturing intelligence has become the inevitable choice for the development of the industry. In this paper, the key manufacturing technology of numerical control tools and the application of intelligence in numerical control tool manufacturing are described. the development trend of intelligent manufacturing of numerical control tools is analyzed.

scholarly journals Thermal error modeling based on BiLSTM deep learning for CNC machine tool

2021 ◽  
Author(s):  
Pu-Ling Liu ◽  
Zheng-Chun Du ◽  
Hui-Min Li ◽  
Ming Deng ◽  
Xiao-Bing Feng ◽  
...  
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Machine Tools ◽  
Thermal Error ◽  
Error Modeling ◽  
Numerical Control ◽  
Machining Accuracy ◽  
Depth Variation ◽  
Thermal Error Modeling ◽  
Proposed Model

AbstractThe machining accuracy of computer numerical control machine tools has always been a focus of the manufacturing industry. Among all errors, thermal error affects the machining accuracy considerably. Because of the significant impact of Industry 4.0 on machine tools, existing thermal error modeling methods have encountered unprecedented challenges in terms of model complexity and capability of dealing with a large number of time series data. A thermal error modeling method is proposed based on bidirectional long short-term memory (BiLSTM) deep learning, which has good learning ability and a strong capability to handle a large group of dynamic data. A four-layer model framework that includes BiLSTM, a feedforward neural network, and the max pooling is constructed. An elaborately designed algorithm is proposed for better and faster model training. The window length of the input sequence is selected based on the phase space reconstruction of the time series. The model prediction accuracy and model robustness were verified experimentally by three validation tests in which thermal errors predicted by the proposed model were compensated for real workpiece cutting. The average depth variation of the workpiece was reduced from approximately 50 µm to less than 2 µm after compensation. The reduction in maximum depth variation was more than 85%. The proposed model was proved to be feasible and effective for improving machining accuracy significantly.

Adaptive Error Control Algorithm for High Speed Two-Axis CNC Contouring

2013 ◽  
Vol 584 ◽  
pp. 149-153
Author(s):  
Jing Chuan Dong ◽  
Tai Yong Wang ◽  
Yan Yu Ding ◽  
Yu Long Cui
Keyword(s):  
High Speed ◽  
Control Algorithm ◽  
Error Control ◽  
Tool Path ◽  
Cnc Machining ◽  
Numerical Control ◽  
Contour Error ◽  
Curvature Radius ◽  
Contour Error Control ◽  
Cnc Controller

The computerized numerical control (CNC) machining program usually contains a large number of small line segments. The CNC controller must generate a smooth and optimized motion profile to achieve high speed and high precision machining. This paper proposed an adaptive contour error control algorithm. The curvature radius of the tool path is obtained by analyzing the geometry relationship. The algorithm uses the curvature information and a simplified servo error model to realize contour error estimation and adaptive control. The target feet rate filter (TFF) and planning unit merging (PUM) are introduced to obtain a smooth profile. Experiments result demonstrated the efficiency of the proposed algorithm.

Sign in / Sign up

Export Citation Format

Share Document