為診斷加工機台異常，透過如振動或噪音等來源的感測資料，可藉由訊號處理如時域、頻域、或小波轉換等萃取特徵，方能進行其診斷分析。其中，有效特徵為診斷效能的關鍵；然由於異常模式的物理特性差異，特徵的萃取與選擇實仍為診斷分析的挑戰。
本研究提出一啟發式特徵維度縮減程序，以於不同感測來源與異常特性下，在最大化診斷正確率下，以較少的實驗次數，獲得最小化之特徵集合。因此，當進行特徵選擇時，若不同特徵之原特徵如時間區間、頻帶、或來源等相似度高時，則保留具較佳診斷效益之特徵。此程序尤適用於小波訊號頻帶的最佳化選擇，以獲得與各錯誤分類方法的最適特徵組合。
以機台軸承損壞模式診斷為例，其軸承破壞模式如內環、外環、與滾子等單一與複合損壞模式等之振動資料。本程序可於6次實驗內，有效縮減28個特徵為9個。經特徵所建構之複合損壞模式診斷分析結果，比較縮減前後，倒傳遞類神經網路分類正確率可由90.78%提升至92.23%；此外，機率類神經分類正確率可由86.67%提升至87.21%。

Signals detected from accelerate and acoustic sensors should be processed to extract features by using such as time-domain, frequency-domain, and wavelet transform to diagnose machine faults. Effective features decide diagnostic performance. However, causing physics of fault modes, feature extraction and selection is a diagnostic analysis challenge.
This work proposed a heuristic dimension reduction procedure to derive limited feature dimensions with maximum diagnostic accuracy in fewer experiments. In this procedure, higher diagnostic effect is selected from features which possess similar meta-attributes, e.g., time duration, frequency bandwidth, and source. Moreover, selection of original signal and the agreeing wavelet band is supported to reduce analyzing time for deriving the agreeing feature sets of the following classification methods.
A machining bearing diagnostics case which included single and mixture fault modes of inner race, outer race, and roller is presented. It shows twenty-eight major features extracted from vibration data can be reduced to nine features in six experiments by using the proposed procedure. After training diagnostic models by using features, comparison of two conditions mixture failure modes classification accuracy of back-propagation neural network is improved from 90.78% to 92.23%; meanwhile, probabilistic neural network is improved from 86.67% to 87.21%.

[1]M-C García, M-A Sanz-Bobi, and del J. Pico, “SIMAP: Intelligent System for Predictive Maintenance. Application to the health condition monitoring of a wind-turbine gearbox, “ Comput Ind., vol. 56, no. 6, pp. 552-568, 2006.
[2]鄭芳田、顏家鈺、蔡明祺、楊燿州、施文彬、陳裕民、楊大和、周立芃 (2008)，Intelligent Manufacturing Systems，自動化科技學會會刊，6期，頁16-17.
[3]R.B.W. Heng and M.J.M. Nor, “Statistical Analysis of Sound and Vibration Signals for Monitoring Rolling Element Bearing Condititi- on,” Applied Acoustics, Vol. 53, No.1-3, pp.211-226, 1998.
[4]Jie Liu,WilsonWang, Farid Golnaraghi and Kefu Liu, “Wavelet spectrum analysis for bearing fault diagnostics,” Measurement Science and Technology, VOL. 19, 2008.
[5]S Wadhwani, S P Gupta, and V Kumar, “Wavelet Based Vibration Monitoring for Detection of Faults in Ball Bearings of Rotating Machines,” Journal Inst. Eng. (India) –EL,vol.86, no. 4, pp. 77-81, Sep. 2005.
[6]Bo Li, Mo-Yuen Chow, Yodyium Tipsuwan, and James C. Hung, “Neural-Network-Based Motor Rolling Bearing Fault Diagnosis,” IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, VOL. 47, NO. 5, pp. 1060-1069, OCTOBER 2000.
[7]S. Tyagi," A Comparative Study of SVM Classifiers and Artificial Neural Networks Application for Rolling Element Bearing Fault Diagnosis using Wavelet Transformation Preprocessing," in Processing of World Academy of Science, Engineering and Technology, vol. 33, pp. 319-327, 2008.
[8]Howard C. Choe, Bryan, Yulun Wan and Andrew K. Chan, “Neural pattern identification of railroad wheel-bearing fault from audible acoustic signals: Comparison of FFT, CFT, and DWT features,” Proceedings of the SPIE, (3078):480-496, 1997.
[9]B. Samanta, Khamis R. Al-Balushi, and Saeed A. Al-Araimi, “Bearing Fault Detection Using Artificial Neural Networks and Genetic Algorithm,” EURASIP Journal on Applied Signal Processing, VOL. 3, pp. 366–377, 2004.
[10]B. Samanta, Khamis R. Al-Balushi, and Saeed A. Al-Araimi, “Bearing Fault Detection Using Artificial Neural Networks and Genetic Algorithm,” EURASIP Journal on Applied Signal Processing, VOL. 3, pp. 366–377, 2004.
[11]Arnaz Malhi and Robert X. Gao, “PCA-Based Feature Selection Scheme for Machine Defect Classification,” IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, VOL. 53, NO. 6, pp. 366–377, DECEMBER 2004.
[12]楊建國「小波分析及其工程應用」，機械工業出版社，2005.
[13]F.-T. Cheng, Y.-T. Chen, Y.-C. Su, and D.-L. Zeng, "Evaluating reliance level of a virtual metrology system," IEEE Transactions on Semiconductor Manufacturing, vol. 21, no. 1, pp. 92-103, Feb. 2008.