A self-organizing map and a normalizing multi-layer perceptron approach to baselining in prognostics under dynamic regimes

Abstract When the influence of changing operational and environmental conditions is not factored out, it can be dificult to observe a clear deterioration path. This can significantly affect the task of prognostics and other analytic operations. To address this issue, it is necessary to baseline the data, typically by first finding the operating regimes and then normalizing the data within each regime. In this paper, we propose the use of machine learning techniques to perform baselining. A self-organizing map identifies the regimes, and a multi-layer perceptron normalizes the data based on the detected regimes. Tests are performed on the C-MAPSS data. The approach is capable of producing similar results to classical methods without the need to specify in advance the number of regimes and the explicit computation of the statistical properties of a hold-out dataset. Importantly, the techniques can be integrated into a deep learning system to perform prognostics in a single pass.

[1]  Esa Alhoniemi,et al.  Clustering of the self-organizing map , 2000, IEEE Trans. Neural Networks Learn. Syst..

[2]  Kai Goebel,et al.  More effective prognostics with elbow point detection and deep learning , 2021 .

[3]  Razvan Pascanu,et al.  Understanding the exploding gradient problem , 2012, ArXiv.

[4]  J. H. Ward.  Hierarchical Grouping to Optimize an Objective Function , 1963 .

[5]  Jing Pan,et al.  Prognostic Degradation Models for Computing and Updating Residual Life Distributions in a Time-Varying Environment , 2008, IEEE Transactions on Reliability.

[6]  Hoon Sohn,et al.  Effects of environmental and operational variability on structural health monitoring , 2007, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[7]  G. De Roeck,et al.  Vibration based Structural Health Monitoring using output-only measurements under changing environment , 2008 .

[8]  Enrico Zio,et al.  A data-driven approach for predicting failure scenarios in nuclear systems , 2010 .

[9]  S. D. Lokhande,et al.  Neural Network Fault Diagnosis of Voltage Source Inverter under variable load conditions at different frequencies , 2016 .

[10]  T. Kohonen.  Self-organized formation of topographically correct feature maps , 1982 .

[11]  Arthur Flexer.  On the use of self-organizing maps for clustering and visualization , 2001 .

[12]  Michael Pecht,et al.  Prognostics and health management for energetic material systems , 2010, 2010 Prognostics and System Health Management Conference.

[13]  Yaguo Lei,et al.  Remaining useful life prediction of machinery under time-varying operating conditions based on a two-factor state-space model , 2019, Reliab. Eng. Syst. Saf..

[14]  Teuvo Kohonen,et al.  Self-organized formation of topologically correct feature maps , 2004, Biological Cybernetics.

[15]  Gaëtan Kerschen,et al.  Structural damage diagnosis under varying environmental conditions—Part I: A linear analysis , 2005 .

[16]  Enrico Zio,et al.  Particle Filter-Based Prognostics for an Electrolytic Capacitor Working in Variable Operating Conditions , 2016, IEEE Transactions on Power Electronics.

[17]  Yi-Qing Ni,et al.  Correlating modal properties with temperature using long-term monitoring data and support vector machine technique , 2005 .

[18]  Enrico Zio,et al.  Remaining useful life estimation in heterogeneous fleets working under variable operating conditions , 2016, Reliab. Eng. Syst. Saf..

[19]  Babak Moaveni,et al.  Effects of changing ambient temperature on finite element model updating of the Dowling Hall Footbridge , 2012 .

[20]  Tianyi Wang,et al.  Trajectory Similarity Based Prediction for Remaining Useful Life Estimation , 2010 .

[21]  Jerome H Travert.  Flight Regime and Maneuver Recognition for Complex Maneuvers , 2009 .

[22]  Joseph Hoshen,et al.  On the application of the enhanced Hoshen-Kopelman algorithm for image analysis , 1998, Pattern Recognit. Lett..

[23]  Zainah Ibrahim,et al.  Nondestructive test methods for concrete bridges: A review , 2016 .

[24]  Michael Pecht,et al.  Prognostics uncertainty reduction by fusing on-line monitoring data based on a state-space-based degradation model , 2014 .

[25]  You-Lin Xu,et al.  Temperature effect on vibration properties of civil structures: a literature review and case studies , 2012 .

[26]  Joseph Mathew,et al.  Rotating machinery prognostics. State of the art, challenges and opportunities , 2009 .

[27]  Babak Moaveni,et al.  Environmental effects on the identified natural frequencies of the Dowling Hall Footbridge , 2011 .

[28]  Jay Lee,et al.  Review and recent advances in battery health monitoring and prognostics technologies for electric vehicle (EV) safety and mobility , 2014 .

[29]  Nagi Gebraeel,et al.  Degradation modeling for real-time estimation of residual lifetimes in dynamic environments , 2015 .

[30]  Guido De Roeck,et al.  One-year monitoring of the Z24-Bridge : environmental effects versus damage events , 2001 .

[31]  Hans-Peter Kriegel,et al.  A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise , 1996, KDD.

[32]  Alfredo Petrosino,et al.  Competitive neural networks on message-passing parallel computers , 1993, Concurr. Pract. Exp..

[33]  Michael Brower,et al.  Correction factors for NRG #40 anemometers potentially affected by dry friction whip: characterization, analysis, and validation , 2012 .

[34]  J. Bezdek,et al.  FCM: The fuzzy c-means clustering algorithm , 1984 .

[35]  Gaëtan Kerschen,et al.  Structural damage diagnosis under varying environmental conditions - Part II: local PCA for non-linear cases , 2005 .

[36]  Charles R. Farrar,et al.  Machine learning algorithms for damage detection under operational and environmental variability , 2011 .

[37]  Yizong Cheng,et al.  Mean Shift, Mode Seeking, and Clustering , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[38]  Teuvo Kohonen,et al.  Things you haven't heard about the self-organizing map , 1993, IEEE International Conference on Neural Networks.

[39]  Charles R Farrar,et al.  Damage prognosis: the future of structural health monitoring , 2007, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[40]  Paul J. Werbos,et al.  Backpropagation Through Time: What It Does and How to Do It , 1990, Proc. IEEE.

[41]  Raoul Kopelman,et al.  Percolation and cluster distribution. I. Cluster multiple labeling technique and critical concentration algorithm , 1976 .

[42]  Jeffrey Alun Jones,et al.  Reducing Dimensionality of Multi-regime Data for Failure Prognostics , 2017, Journal of Failure Analysis and Prevention.

[43]  Jong-Myon Kim,et al.  Acoustic spectral imaging and transfer learning for reliable bearing fault diagnosis under variable speed conditions , 2019, Measurement.

[44]  Weiwen Peng,et al.  Bayesian Degradation Analysis With Inverse Gaussian Process Models Under Time-Varying Degradation Rates , 2017, IEEE Transactions on Reliability.

[45]  Hoon Sohn,et al.  An experimental study of temperature effect on modal parameters of the Alamosa Canyon Bridge , 1999 .

[46]  Luca Saglietti,et al.  Gaussian Process Prior Variational Autoencoders , 2018, NeurIPS.

[47]  Daniel P. Dennies.  The organization of a failure investigation , 2002 .