K-PdM: KPI-Oriented Machinery Deterioration Estimation Framework for Predictive Maintenance Using Cluster-Based Hidden Markov Model

Explosive increase of industrial data collected from sensors has brought increasing attractions to the data-driven predictive maintenance for industrial machines in cyber-physical systems (CPSs). Since machinery faults are always caused by performance deterioration of components, learning the deteriorating mode from observed sensor data facilitates the prognostics of impeding faults and predicting the remaining useful life (RUL). In modern CPSs, several key performance indicators (KPIs) are monitored to detect the corresponding fine-grained deteriorating modes of industrial machines. However, the overall deterioration estimation and RUL prediction based on these KPIs with various patterns have been a great challenge, especially without labels of deteriorating index or uninterpretable of root causes. In this paper, we proposed K-PdM, a cluster-based hidden Markov model for the machinery deterioration estimation and RUL prediction based on multiple KPIs. The method uncovers the fine-grained deteriorating modes of machines through each unlabeled KPI data and learns a mapping between each deteriorating KPI index and RULs. Accordingly, an overall deterioration estimation and RUL prediction of machine are able to be achieved based on the combination of each KPI’s deterioration estimation. Moreover, a set of interpretable semantic rules are setup to analyze the root cause of performance deterioration among KPIs. An experimental application is proposed to demonstrate its applicability based on the PHM08 data sets. The obtained results show their effectiveness to predict the RULs of machines.

[1]  Karl Aberer,et al.  Online unsupervised state recognition in sensor data , 2015, 2015 IEEE International Conference on Pervasive Computing and Communications (PerCom).

[2]  David J. C. MacKay,et al.  Information Theory, Inference, and Learning Algorithms , 2004, IEEE Transactions on Information Theory.

[3]  M. D. Pandey,et al.  Condition Based Maintenance of Low Speed Rolling Element Bearings using Hidden Markov Model , 2020 .

[4]  Lovekesh Vig,et al.  Multi-Sensor Prognostics using an Unsupervised Health Index based on LSTM Encoder-Decoder , 2016, ArXiv.

[5]  C. D. Kemp,et al.  Density Estimation for Statistics and Data Analysis , 1987 .

[6]  Jay Lee,et al.  Cyber-Physical Systems in Future Maintenance , 2015 .

[7]  Xiang Li,et al.  Remaining useful life estimation in prognostics using deep convolution neural networks , 2018, Reliab. Eng. Syst. Saf..

[8]  Christophe Bérenguer,et al.  Hidden Markov Models for diagnostics and prognostics of systems under multiple deterioration modes , 2014 .

[9]  Tianyou Zhang,et al.  Health Index-Based Prognostics for Remaining Useful Life Predictions in Electrical Machines , 2016, IEEE Transactions on Industrial Electronics.

[10]  Tangbin Xia,et al.  Manufacturing paradigm-oriented PHM methodologies for cyber-physical systems , 2019, J. Intell. Manuf..

[11]  Sauro Longhi,et al.  Hidden Markov Model for Health Estimation and Prognosis of Turbofan Engines , 2011 .

[12]  Zhenyu Wu,et al.  An Integrated Ensemble Learning Model for Imbalanced Fault Diagnostics and Prognostics , 2018, IEEE Access.

[13]  Abhinav Saxena,et al.  Performance Benchmarking and Analysis of Prognostic Methods for CMAPSS Datasets , 2020, International Journal of Prognostics and Health Management.

[14]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[15]  M. Rosenblatt.  Remarks on Some Nonparametric Estimates of a Density Function , 1956 .

[16]  Manzar Abbas.  System-level health assessment of complex engineered processes , 2010 .

[17]  Hao Luo,et al.  An unsupervised degradation estimation framework for diagnostics and prognostics in cyber-physical system , 2018, 2018 IEEE 4th World Forum on Internet of Things (WF-IoT).

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

[19]  Faa-Jeng Lin,et al.  Fault-Tolerant Control for Six-Phase PMSM Drive System via Intelligent Complementary Sliding-Mode Control Using TSKFNN-AMF , 2013, IEEE Transactions on Industrial Electronics.

[20]  Haixun Wang,et al.  Finding semantics in time series , 2011, SIGMOD '11.

[21]  Hanz Richter.  Engine Models and Simulation Tools , 2012 .

[22]  Zhenyu Wu,et al.  Towards a Semantic Web of Things: A Hybrid Semantic Annotation, Extraction, and Reasoning Framework for Cyber-Physical System , 2017, Sensors.

[23]  P. Baruah,et al.  HMMs for diagnostics and prognostics in machining processes , 2005 .

[24]  Myeongsu Kang,et al.  An FPGA-Based Multicore System for Real-Time Bearing Fault Diagnosis Using Ultrasampling Rate AE Signals , 2015, IEEE Transactions on Industrial Electronics.

[25]  Lovekesh Vig,et al.  Predicting Remaining Useful Life using Time Series Embeddings based on Recurrent Neural Networks , 2017, International Journal of Prognostics and Health Management.