|
|
论文:2015,Vol:33,Issue(4):651-657 |
|
|
引用本文： |
|
|
张栋梁, 莫蓉, 孙惠斌, 李春磊. 基于流形学习与隐马尔可夫模型的刀具磨损状况识别[J]. 西北工业大学学报 |
|
|
Zhang Dongliang, Mo Rong, Sun Huibin, Li Chunlei. Tool Wear Condition Monitoring Based on Manifold Learning and Hidden Markov Model[J]. Northwestern polytechnical university |
|
|
|
|
|
|
|
| 基于流形学习与隐马尔可夫模型的刀具磨损状况识别 |
|
| 张栋梁, 莫蓉, 孙惠斌, 李春磊 |
|
| 西北工业大学 现代设计与集成制造技术教育部重点实验室, 陕西 西安 710072 |
| 摘要: |
| 为了提高金属铣削过程中的刀具磨损状态识别的自动化程度与精度,提出了基于局部切空间排列(LTSA)方法与隐Markov模型(HMM)来识别刀具的不同磨损状态的方法。该方法首先利用小波分析技术对铣削过程中的切削进给方向力信号进行处理,构造了高维特征空间。然后使用基于流形学习方法实现了高维特征空间的维数约简。最终利用约简后的低维特征向量训练HMM,从而实现刀具磨损状态的识别。实验结果说明该方法能够有效地识别铣削过程的刀具磨损状态。与未经特征维数约简的识别方法相比,新方法能够提高刀具磨损状态的识别效率与准确率。 |
| 关键词:
维数约简
刀具磨损状态识别
流形学习
隐马尔可夫模型(HMM)
|
|
| Tool Wear Condition Monitoring Based on Manifold Learning and Hidden Markov Model |
|
| Zhang Dongliang, Mo Rong, Sun Huibin, Li Chunlei |
|
| Key Laboratory of Contemporary Design and Integrated Manufacturing Technology, Northwestern Polytechnic University, Xi'an 710072, China |
| Abstract: |
| In order to improve the automation and the precision of tool wear condition recognition in the process of metal milling, we proposed the method based on the manifold learning——the local tangent space alignment (LTSA) method——and the hidden Markov model (HMM) to identify tool wear conditions. First, this method used the time domain and the wavelet analysis technique for signal processing of the milling cutting axial force to construct the high dimensional feature space. Then, the local tangent space alignment (LTSA) method was used to achieve the dimensionality reduction. At last, the low dimensional feature vector was used to train the HMM in order to recognize tool wear conditions. Additional tests were conducted to check the feasibility of the method. Comparison of the performance of the proposed method with that of the method of identification without the feature dimension reduction shows that the proposed method can improve the efficiency and the accuracy of tool wear condition recognition. |
| Key words:
condition monitoring
conformal mapping
design of experiments
efficiency
eigenvalues and eigenfunctions
errors
experiments
feature extraction
flowcharting
hidden Markov models
matrix algebra
milling (machining)
monitoring
probability
signal processing
time domain analysis
wavelet analysis
wear of materials
dimension reduction
local tangent space alignment (LTSA)
the manifold learning
tool wear conditions recognition
|
|
| 收稿日期: 2014-10-20
修回日期:
|
| DOI: |
| 基金项目: 陕西省自然科学基金(2013JM7001)、西北工业大学基础研究基金(JC20110215)与西北工业大学2012校级"新人新方向"基金(12GH14617)资助 |
| 通讯作者:
Email： |
| 作者简介: 张栋梁(1987—),西北工业大学博士研究生,主要从事刀具磨损及切削力建模研究。
|
|
|
|
|
|
|
|
参考文献: |
|
|
[1] Wang G F, Yang Y W, Zhang Y C, et al. Vibration Sensor Based Tool Condition Monitoring Using v Support Vector Machine and Locality Preserving Projection[J]. Sensors and Actuators A: Physical, 2014, 209: 24-32
[2] Wang Guofeng, Guo Zhiwei, Yang Yinwei. Force Sensor Based Online Tool Wear Monitoring Using Distributed Gaussian ARTMAP Network[J]. Sensors and Actuators A: Physical, 2013, 192: 111-118
[3] Ravindra H C, Srinivasa Y G, Krishnamurthy R. Acoustic Emission for Tool Condition Monitoring in Metal Cutting[J]. Wear, 1997, 212(1), 78-84
[4] Zhou J M, Andersson M, Stahl J E. The Monitoring of Flank Wear on the CBN Tool in the Hard Turning Process[J]. Int J Adv Manuf Technol, 2003, 22: 697-702
[5] Ai C S, Sun Y J, He G W, et al. The Milling Tool Wear Monitoring Using the Acoustic Spectrum[J]. Int J Adv Manuf Technol, 2012, 61: 457-463
[6] Susanto V, Chen J C. Fuzzy Logic Based In-Process Tool-Wear Monitoring System in Face Milling Operations[J]. Int J Adv Manuf Technol, 2003, 3:186-192
[7] 张翔, 富宏亚, 孙雅洲, 等. 基于隐Markov模型的微径铣刀磨损监测[J]. 计算机集成制造系统, 2012, 18(01): 141-148 Zhang Xiang, Fu Hongya, Sun Yazhou, et al. Hidden Markov Model Based Micro-Milling Tool Wear Monitoring[J]. Computer Integrated Manufacturing Systems, 2012, 18(1): 141-148 (in Chinese)
[8] Kuo R J, Cohen P H. Intelligent Tool Wear Estimation System through Artificial Neural Networks and Fuzzy Modeling[J]. Artificial Intelligence in Engineering, 1998, 12(3): 229-242
[9] Silva R G, Reuben R L, Baker K J, et al. Tool Wear Monitoring of Turning Operations by Neural Network and Expert System Classification of a Feature Set Generated from Multiple Sensors[J]. Mechanical Systems and Signal Processing, 1998, 12(2): 319-332
[10] Li Xiaoli, Yuan Zhejun. Tool Wear Monitoring with Wavelet Packet Transform-Fuzzy Clustering Method[J]. Wear, 1998, 219(2): 145-154
[11] Tomas Kalvoda, Hwang Yeanren. A Cutter Tool Monitoring in Machining Process Using Hilbert-Huang Transform[J]. International Journal of Machine Tools & Manufacture, 2010, 50(5): 495-501
[12] 徐创文, 陈花玲, 程仲文, 等. 基于时序分析与模糊聚类的铣削刀具磨损状态识别[J]. 机械强度, 2007, 29(4): 525-531 Xu Chuangwen, Chen Hualing, Cheng Zhongwen, et al. Recognition of Milling Tool Wear Based on Time Series Analysis and Fuzzy Cluster[J]. Journal of Mechanical Strength, 2007, 29(4): 525-531 (in Chinese)
[13] Leonard E B, Ted P. Statistical Inference for Probabilistic Functions of Finite State Markov Chains[J]. The Annals of Mathematical Statistics, 1966, 37(6): 1554-1563
[14] Zhang Zhenyue, Zha Hongyuan. Principal Manifolds and Nonlinear Dimensionality Reduction via Tangent Space Alignment[J]. SIAM Journal on Scientific Computing, 2004, 26(1): 313-338
[15] Leonard E B, Ted Petrie, Norman Weiss. A Maximization Technique Occurring in the Statistical Analysis of Probabilistic Functions of Markov Chains[J]. The Annals of Mathematical Statistics, 1970, 41(1), 164-171
[16] Andrew J V. Error Bounds for Convolutional Codes and an Asymptotically Optimum Decoding Algorithm[J]. IEEE Trans on Information Theory, 1967, 13(2): 260-269
[17] MacQueen J. Some Methods for Classification and Analysis of Multivariate Observations[C]//Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, 1967, 1(14): 281-297 |
|
|
|
|
|
|
|
