A Hybrid Approach of ANN and HMM for Cutting Chatter Monitoring


Article Preview

The Hidden Markov Model (HMM) offers a powerful framework for temporal modeling of features extracted from time varying signals, and the Artificial Neural Network (ANN) has been widely used for pattern recognition, time series prediction, and optimization and forecasting. This paper describes a hybrid HMM/ANN approach which is a very competitive alternative to standard HMM for cutting chatter monitoring both in terms of performances and recognition accuracy. The hybrid HMM/ANN system uses ANN, usually a Multi-layer Perceptron ANN, to integrate the multi-stream inputs as feature transformation, whose goal is to take the advantages from the properties of both HMM and ANN. Experimental results show the efficiency of the hybrid system in monitoring of cutting process.



Advanced Materials Research (Volumes 97-101)

Edited by:

Zhengyi Jiang and Chunliang Zhang




C. L. Zhang et al., "A Hybrid Approach of ANN and HMM for Cutting Chatter Monitoring", Advanced Materials Research, Vols. 97-101, pp. 3225-3232, 2010

Online since:

March 2010




[1] Heck LP, McClellan JH: Mechanical system monitoring using hidden Markov models. IEEE Int Conf Acoustics, Speech, and Signal Processing (1991), P. 1697-1700.

DOI: https://doi.org/10.1109/icassp.1991.150631

[2] H. Bourlard, N. Morgan: Connectionist Speech Recognition - A Hybrid Approach. Kluwer Academic Press (1994. ).

[3] H. Ney: Speech Recognition in a Neural Network Framework: Discriminative Training of Gaussian Models and Mixture Densities as Radial Basis Functions. IEEE Int Conf Acoustics, Speech, and Signal Processing (1991), P. 573-576.

DOI: https://doi.org/10.1109/icassp.1991.150404

[4] Roberto Gemello: Hybrid HMM Neural Network based Speech Recognition in Loquendo ASR, http: /www. loquendo. com/en/brochure/Speech_Recognition_ASR. pdf.

[5] Gerhard Rigoll: Maximum Mutual Information Neural Networks for Hybrid Connectionist-HMM. Speech Recognition Systems. IEEE Transactions on speech and audio processing, Vol. 2(1994), pp.175-184.

DOI: https://doi.org/10.1109/89.260360

[6] Gerhard Rigoll, Daniel Willett: A NN/HMM hybrid for continuous speech recognition with a discriminant nonlinear feature extraction. IEEE Int Conf Acoustics, Speech, and Signal Processing (1998), P. 9-12.

DOI: https://doi.org/10.1109/icassp.1998.674354

[7] Daniel Willett, Gerhard Rigoll: Hybrid NN/HMM-Based Speech Recognition with a Discriminant Neural Feature Extraction. Proceedings of the 1997 conference on Advances in Neural Information Processing Systems 10(1998), pp.763-769.

DOI: https://doi.org/10.1109/icassp.1998.674354

[8] L. Bahl, P. Brown, P. de Souza and R. Mercer: Maximum mutual information estimation of hidden Markov model parameters for speech recognition. IEEE Int Conf Acoustics, Speech, and Signal Processing (1986), P. 49-52.

DOI: https://doi.org/10.1109/icassp.1986.1169179

[9] J.M. Lee, S.J. Kim, Y. Hwang: Mechanical Signal Analysis Using Hidden Markov Model. International Congress on Sound and Vibration 9(2002).

[10] J.M. Lee, S.J. Kim, Y. Hwang: Diagnosis of mechanical fault signal using continuous hidden Markov model. Journal of Sound and Vibration. Vol. 276(2004), pp.1065-1080.

[11] N. Baydar, A. Ball: Detection of Gear Failures via Vibration and Acoustic Signals Using Wavelet Transform. Mechanical Systems and Signal Processing. Vol. 17(2003), pp.787-804.

DOI: https://doi.org/10.1006/mssp.2001.1435

[12] Y. Xu, M. Ge: Hidden Markov model-based process monitoring system. Journal of Intelligent Manufacturing. Vol. 15(2004), pp.337-350.

DOI: https://doi.org/10.1023/b:jims.0000026572.03164.64

[13] Cho Wongyu, Lee Kim. Modeling and recognition of cursive words with Hidden Markov Models. Pattern Recognition. Vol. 28(1991), p.1945-(1953).

DOI: https://doi.org/10.1016/0031-3203(95)00041-0

[14] V. Purushotham, S. Narayanan, Suryanarayana A.N. Prasad: Multi-fault diagnosis of rolling bearing elements using wavelet analysis and hidden Markov model based fault recognition. NDT&E International 38(2005), pp.654-664.

DOI: https://doi.org/10.1016/j.ndteint.2005.04.003

Fetching data from Crossref.
This may take some time to load.