Under certain cutting conditions in end milling, the signs of cutting forces change from positive to negative during a revolution of the tool. The change of force direction causes the cutting dynamics to be unstable w...Under certain cutting conditions in end milling, the signs of cutting forces change from positive to negative during a revolution of the tool. The change of force direction causes the cutting dynamics to be unstable which results in chatter vibration. Therefore, cutting force signal monitoring and classification are needed to determine the optimal cutting conditions and to improve the efficiency of cut. Artificial neural networks are powerful tools for solving highly complex and nonlinear problems. It can be divided into supervised and unsupervised learning machines based on the availability of a teacher. Hybrid neural network was introduced with both of functions of multilayer perceptron (MLP) trained with the back-propagation algorithm for monitoring and detecting abnormal state, and self organizing feature map (SOFM) for treating huge datum such as image processing and pattern recognition, for predicting and classifying cutting force signal patterns simultaneously. The validity of the results is verified with cutting experiments and simulation tests.展开更多
In this paper, a series of experiments were performed by high speed milling of Ti-6.5Al-2Zr-1Mo-1V (TA15) by use of polycrystalline diamond (PCD) tools. The characteristics of high speed machining (HSM) dynamic millin...In this paper, a series of experiments were performed by high speed milling of Ti-6.5Al-2Zr-1Mo-1V (TA15) by use of polycrystalline diamond (PCD) tools. The characteristics of high speed machining (HSM) dynamic milling forces were investi- gated. The effects of the parameters of the process, i.e., cutting speed, feed per tooth, and depth of axial cut, on cutting forces were studied. The cutting force signals under different cutting speed conditions and different cutting tool wear stages were analyzed by frequency spectrum analysis. The trend and frequency domain aspects of the dynamic forces were evaluated and discussed. The results indicate that a characteristic frequency in cutting force power spectrum does in fact exist. The amplitudes increase with the increase of cutting speed and tool wear level, which could be applied to the monitoring of the cutting process.展开更多
文摘Under certain cutting conditions in end milling, the signs of cutting forces change from positive to negative during a revolution of the tool. The change of force direction causes the cutting dynamics to be unstable which results in chatter vibration. Therefore, cutting force signal monitoring and classification are needed to determine the optimal cutting conditions and to improve the efficiency of cut. Artificial neural networks are powerful tools for solving highly complex and nonlinear problems. It can be divided into supervised and unsupervised learning machines based on the availability of a teacher. Hybrid neural network was introduced with both of functions of multilayer perceptron (MLP) trained with the back-propagation algorithm for monitoring and detecting abnormal state, and self organizing feature map (SOFM) for treating huge datum such as image processing and pattern recognition, for predicting and classifying cutting force signal patterns simultaneously. The validity of the results is verified with cutting experiments and simulation tests.
基金Project (No.IRT0837) supported by the Program for Changjiang Scholars and Innovative Research Team in University of China
文摘In this paper, a series of experiments were performed by high speed milling of Ti-6.5Al-2Zr-1Mo-1V (TA15) by use of polycrystalline diamond (PCD) tools. The characteristics of high speed machining (HSM) dynamic milling forces were investi- gated. The effects of the parameters of the process, i.e., cutting speed, feed per tooth, and depth of axial cut, on cutting forces were studied. The cutting force signals under different cutting speed conditions and different cutting tool wear stages were analyzed by frequency spectrum analysis. The trend and frequency domain aspects of the dynamic forces were evaluated and discussed. The results indicate that a characteristic frequency in cutting force power spectrum does in fact exist. The amplitudes increase with the increase of cutting speed and tool wear level, which could be applied to the monitoring of the cutting process.
