Stochastic RUL Calculation Enhanced With TDNN-Based IGBT Failure Modeling

Power electronics are widely used in the transport and energy sectors. Hence, the reliability of these power electronic components is critical to reducing the maintenance cost of these assets. It is vital that the health of these components is monitored for increasing the safety and availability of a system. The aim of this paper is to develop a prognostic technique for estimating the remaining useful life (RUL) of power electronic components. There is a need for an efficient prognostic algorithm that is embeddable and able to support on-board real-time decision-making. A time delay neural network (TDNN) is used in the development of failure modes for an insulated gate bipolar transistor (IGBT). Initially, the time delay neural network is constructed from training IGBTs' ageing samples. A stochastic process is performed for the estimation results to compute the probability of the health state during the degradation process. The proposed TDNN fusion with a statistical approach benefits the probability distribution function by improving the accuracy of the results of the TDDN in RUL prediction. The RUL (i.e., mean and confidence bounds) is then calculated from the simulation of the estimated degradation states. The prognostic results are evaluated using root mean square error (RMSE) and relative accuracy (RA) prognostic evaluation metrics.

[1]  Frede Blaabjerg,et al.  Transitioning to Physics-of-Failure as a Reliability Driver in Power Electronics , 2014, IEEE Journal of Emerging and Selected Topics in Power Electronics.

[2]  Epaminondas Kapetanios,et al.  Developing Prognostic Models Using Duality Principles for DC-to-DC Converters , 2015, IEEE Transactions on Power Electronics.

[3]  Chun-Yi Su,et al.  NEURAL NETWORK BASED TIME-DELAY ESTIMATION FOR NONLINEAR DYNAMIC SYSTEMS , 2002 .

[4]  Zhigang Tian,et al.  An artificial neural network method for remaining useful life prediction of equipment subject to condition monitoring , 2012, J. Intell. Manuf..

[5]  Siem Jan Koopman,et al.  Time Series Analysis by State Space Methods , 2001 .

[6]  Suresh Perinpanayagam,et al.  Probabilistic Monte-Carlo method for modelling and prediction of electronics component life , 2014 .

[7]  G. Nicoletti,et al.  Fast power cycling test of IGBT modules in traction application , 1997, Proceedings of Second International Conference on Power Electronics and Drive Systems.

[8]  Vijay K. Garg,et al.  Prognostic and Warning System for Power-Electronic Modules in Electric, Hybrid Electric, and Fuel-Cell Vehicles , 2008, IEEE Transactions on Industrial Electronics.

[9]  Zhigang Tian,et al.  An artificial neural network approach for remaining useful life prediction of equipments subject to condition monitoring , 2009, 2009 8th International Conference on Reliability, Maintainability and Safety.

[10]  Lun Ma,et al.  Modeling the impact of prognostic errors on CBM effectiveness using discrete-event simulation , 2012, 2012 International Conference on Quality, Reliability, Risk, Maintenance, and Safety Engineering.

[11]  Michael G. Pecht,et al.  A prognostics and health management roadmap for information and electronics-rich systems , 2010, Microelectron. Reliab..

[12]  Bongtae Han,et al.  Physics-of-Failure, Condition Monitoring, and Prognostics of Insulated Gate Bipolar Transistor Modules: A Review , 2015, IEEE Transactions on Power Electronics.

[13]  Jay Lee,et al.  Robust performance degradation assessment methods for enhanced rolling element bearing prognostics , 2003, Adv. Eng. Informatics.

[14]  Frede Blaabjerg,et al.  Catastrophic failure and fault-tolerant design of IGBT power electronic converters - an overview , 2013, IECON 2013 - 39th Annual Conference of the IEEE Industrial Electronics Society.

[15]  B. Saha,et al.  Towards prognostics for electronics components , 2009, 2009 IEEE Aerospace conference.

[16]  Bing Ji,et al.  In-situ Bond Wire and Solder Layer Health Monitoring Circuit for IGBT Power Modules , 2012, 2012 7th International Conference on Integrated Power Electronics Systems (CIPS).

[17]  K. Goebel,et al.  An agile accelerated aging, characterization and scenario simulation system for gate controlled power transistors , 2008, 2008 IEEE AUTOTESTCON.

[18]  Mounira Berkani,et al.  Ageing and Failure Modes of IGBT Modules in High-Temperature Power Cycling , 2011, IEEE Transactions on Industrial Electronics.

[19]  F.O. Heimes,et al.  Recurrent neural networks for remaining useful life estimation , 2008, 2008 International Conference on Prognostics and Health Management.

[20]  Michael G. Pecht,et al.  A hybrid prognostics methodology for electronic products , 2008, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).

[21]  M. Pecht,et al.  Precursor Parameter Identification for Insulated Gate Bipolar Transistor (IGBT) Prognostics , 2009, IEEE Transactions on Reliability.

[22]  Lin Ma,et al.  Prognostic modelling options for remaining useful life estimation by industry , 2011 .

[23]  Jay Lee,et al.  An Auto-Associative Residual Processing and K-means Clustering Approach for Anemometer Health Assessment , 2011 .

[24]  Sid-Ahmed Selouani,et al.  An Autoregressive Time Delay Neural Network for speech steganalysis , 2012, 2012 11th International Conference on Information Science, Signal Processing and their Applications (ISSPA).

[25]  M. Thoben,et al.  Power cycling tests at high temperatures with IGBT power modules for hybrid electrical vehicle applications , 2010, 3rd Electronics System Integration Technology Conference ESTC.

[26]  Lei Zhang,et al.  A review of fault prognostics in condition based maintenance , 2006, International Symposium on Instrumentation and Control Technology.

[27]  H. Hirose,et al.  Electrical Insulation Diagnosing using a New Statistical Classification Method , 2006, 2006 IEEE 8th International Conference on Properties & applications of Dielectric Materials.

[28]  Guy Lefranc,et al.  High temperature reliability on automotive power modules verified by power cycling tests up to 150degreeC , 2003, Microelectron. Reliab..

[29]  Ujjwal Maulik,et al.  Genetic algorithm-based clustering technique , 2000, Pattern Recognit..

[30]  Miguel Pinzolas,et al.  Neighborhood based Levenberg-Marquardt algorithm for neural network training , 2002, IEEE Trans. Neural Networks.

[31]  Varun Dutt,et al.  Machine Learning and Data Mining in Pattern Recognition , 2015, Lecture Notes in Computer Science.

[32]  Michael G. Pecht,et al.  A prognostic approach for non-punch through and field stop IGBTs , 2012, Microelectron. Reliab..

[33]  Wai Lok Woo,et al.  Breast cancer prediction and cross validation using multilayer perceptron neural networks , 2010, 2010 7th International Symposium on Communication Systems, Networks & Digital Signal Processing (CSNDSP 2010).

[34]  Tarapong Sreenuch,et al.  Computationally Efficient, Real-Time, and Embeddable Prognostic Techniques for Power Electronics , 2015, IEEE Transactions on Power Electronics.

[35]  R. Derakhshani,et al.  Continuous time delay neural networks for detection of temporal patterns in signals , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[36]  Donghua Zhou,et al.  Remaining useful life estimation - A review on the statistical data driven approaches , 2011, Eur. J. Oper. Res..

[37]  Noureddine Zerhouni,et al.  Remaining Useful Life Estimation of Critical Components With Application to Bearings , 2012, IEEE Transactions on Reliability.

[38]  K. Goebel,et al.  Prognostics approach for power MOSFET under thermal-stress aging , 2012, 2012 Proceedings Annual Reliability and Maintainability Symposium.

[39]  Renate Sitte,et al.  Analysis of the predictive ability of time delay neural networks applied to the S&P 500 time series , 2000, IEEE Trans. Syst. Man Cybern. Part C.

[40]  Jose C. Principe,et al.  Improving pattern recognition of electronic nose data with time-delay neural networks , 2003 .

[41]  C. Kandler,et al.  A new framework for remaining useful life estimation using Support Vector Machine classifier , 2013, 2013 Conference on Control and Fault-Tolerant Systems (SysTol).

[42]  Noel Y. A. Shammas,et al.  Present problems of power module packaging technology , 2003, Microelectron. Reliab..

[43]  Sankalita Saha,et al.  Accelerated aging system for prognostics of power semiconductor devices , 2010, 2010 IEEE AUTOTESTCON.

[44]  Chunyan Yin,et al.  In-service life consumption estimation in power modules , 2008, 2008 13th International Power Electronics and Motion Control Conference.

[45]  Richard M. Crowder.  Electrically powered actuation for civil aircraft , 1996 .