Predicting machine failures from industrial time series data

This paper addresses the problem of predicting machine failures in an industrial manufacturing process based on multivariate time series data. A workflow is presented for cleaning and preprocessing the data, and for training and evaluating a predictive model. Its implementation is modular and extensible to support changes in the underlying production processes and the gathered data. Two predictive models are presented, based on Convolutional Neural Networks and Recurrent Neural Networks, and evaluated on data from an advanced machining process used for cutting complex shapes into metal pieces.

[1]  J. Kurths,et al.  Comparison of correlation analysis techniques for irregularly sampled time series , 2011 .

[2]  Trevor Hastie,et al.  An Introduction to Statistical Learning , 2013, Springer Texts in Statistics.

[3]  Michael Y. Hu,et al.  A Cross‐Validation Analysis of Neural Network Out‐of‐Sample Performance in Exchange Rate Forecasting , 1999 .

[4]  Yoshua Bengio,et al.  Convolutional networks for images, speech, and time series , 1998 .

[5]  Charbel Sakr,et al.  PredictiveNet: An energy-efficient convolutional neural network via zero prediction , 2017, 2017 IEEE International Symposium on Circuits and Systems (ISCAS).

[6]  Sylvain Arlot,et al.  A survey of cross-validation procedures for model selection , 2009, 0907.4728.

[7]  Xiangang Li,et al.  Constructing long short-term memory based deep recurrent neural networks for large vocabulary speech recognition , 2014, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[8]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[9]  Jimeng Sun,et al.  Using recurrent neural network models for early detection of heart failure onset , 2016, J. Am. Medical Informatics Assoc..

[10]  Tim Oates,et al.  Spatially Encoding Temporal Correlations to Classify Temporal Data Using Convolutional Neural Networks , 2015, ArXiv.

[11]  Zachary Chase Lipton.  A Critical Review of Recurrent Neural Networks for Sequence Learning , 2015, ArXiv.

[12]  Jeremy Berkowitz,et al.  Recent developments in bootstrapping time series , 1996 .

[13]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[14]  Joseph F. Murray,et al.  Machine Learning Methods for Predicting Failures in Hard Drives: A Multiple-Instance Application , 2005, J. Mach. Learn. Res..

[15]  Jürgen Schmidhuber,et al.  Learning to Forget: Continual Prediction with LSTM , 2000, Neural Computation.

[16]  Seetha Hari,et al.  Learning From Imbalanced Data , 2019, Advances in Computer and Electrical Engineering.