Interpreting Remaining Useful Life estimations combining Explainable Artificial Intelligence and domain knowledge in industrial machinery

This paper presents the implementation and explanations of a remaining life estimator model based on machine learning, applied to industrial data. Concretely, the model has been applied to a bushings testbed, where fatigue life tests are performed to find more suitable bushing characteristics. Different regressors have been compared Environmental and Operational Condition and setting variables as input data to prognosticate the remaining life on each observation during fatigue tests, where final model is a Random Forest was chosen given its accuracy and explainability potential. The model creation, optimisation and interpretation has been guided combining eXplainable Artificial Intelligence with domain knowledge.Precisely, ELI5 and LIME explainable techniques have been used to perform local and global explanations. These were used to understand the relevance of predictor variables in individual and overall remaining life estimations. The achieved results have been process knowledge gain and expert knowledge validation, assertion of huge potential of data-driven models in industrial processes and highlight the need of collaboration between expert knowledge technicians and eXplainable Artificial Intelligence techniques to understand advanced machine learning models.

[1]  Jana-Rebecca Rehse,et al.  Towards Explainable Process Predictions for Industry 4.0 in the DFKI-Smart-Lego-Factory , 2019, KI - Künstliche Intelligenz.

[2]  Basilio Sierra,et al.  Data-driven prognostics using a combination of constrained K-means clustering, fuzzy modeling and LOF-based score , 2017, Neurocomputing.

[3]  Lotfi A. Zadeh,et al.  Outline of a New Approach to the Analysis of Complex Systems and Decision Processes , 1973, IEEE Trans. Syst. Man Cybern..

[4]  Edwin Lughofer,et al.  Fault detection in reciprocating compressor valves under varying load conditions , 2016 .

[5]  Fuhui Long,et al.  Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy , 2003, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Amina Adadi,et al.  Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI) , 2018, IEEE Access.

[7]  Ronald R. Yager,et al.  Information Processing and Management of Uncertainty in Knowledge-Based Systems. Theory and Foundations , 2018, Communications in Computer and Information Science.

[8]  Wojciech Samek,et al.  Explainable AI: Interpreting, Explaining and Visualizing Deep Learning , 2019, Explainable AI.

[9]  Scott Lundberg,et al.  A Unified Approach to Interpreting Model Predictions , 2017, NIPS.

[10]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[11]  Alexander Binder,et al.  On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation , 2015, PloS one.

[12]  Francisco Herrera,et al.  Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI , 2020, Inf. Fusion.

[13]  José M. Alonso,et al.  A Bibliometric Analysis of the Explainable Artificial Intelligence Research Field , 2018, IPMU.

[14]  Osama A. A. Hassin.  Condition monitoring of journal bearings for predictive maintenance management based on high frequency vibration analysis , 2017 .

[15]  Gian Antonio Susto,et al.  Explainable Machine Learning in Industry 4.0: Evaluating Feature Importance in Anomaly Detection to Enable Root Cause Analysis , 2019, 2019 IEEE International Conference on Systems, Man and Cybernetics (SMC).

[16]  Dimitrios Tzovaras,et al.  Forecasting faults of industrial equipment using machine learning classifiers , 2018, 2018 Innovations in Intelligent Systems and Applications (INISTA).

[17]  Steven Y. Liang,et al.  STOCHASTIC PROGNOSTICS FOR ROLLING ELEMENT BEARINGS , 2000 .

[18]  Zhiqiang Ge,et al.  Data Mining and Analytics in the Process Industry: The Role of Machine Learning , 2017, IEEE Access.

[19]  Carlos Guestrin,et al.  "Why Should I Trust You?": Explaining the Predictions of Any Classifier , 2016, ArXiv.

[20]  José M. Alonso,et al.  HILK: A new methodology for designing highly interpretable linguistic knowledge bases using the fuzzy logic formalism , 2008, Int. J. Intell. Syst..

[21]  Linxia Liao,et al.  A hybrid framework combining data-driven and model-based methods for system remaining useful life prediction , 2016, Appl. Soft Comput..

[22]  Dusko Lukac,et al.  The fourth ICT-based industrial revolution "Industry 4.0" — HMI and the case of CAE/CAD innovation with EPLAN P8 , 2015, 2015 23rd Telecommunications Forum Telfor (TELFOR).

[23]  Donghua Zhou,et al.  A Wiener-process-based degradation model with a recursive filter algorithm for remaining useful life estimation , 2013 .

[24]  Alexander Binder,et al.  Unmasking Clever Hans predictors and assessing what machines really learn , 2019, Nature Communications.

[25]  Zhigang Tian,et al.  Uncertainty Quantification in Gear Remaining Useful Life Prediction Through an Integrated Prognostics Method , 2013, IEEE Transactions on Reliability.

[26]  Liang Guo,et al.  A recurrent neural network based health indicator for remaining useful life prediction of bearings , 2017, Neurocomputing.

[27]  Kenneth A. Loparo,et al.  Physically based diagnosis and prognosis of cracked rotor shafts , 2002, SPIE Defense + Commercial Sensing.