Autoencoder-based anomaly root cause analysis for wind turbines

Abstract A popular method to detect anomalous behaviour or specific failures in wind turbine sensor data uses a specific type of neural network called an autoencoder. These models have proven to be very successful in detecting such deviations, yet cannot show the underlying cause or failure directly. Such information is necessary for the implementation of these models in the planning of maintenance actions. In this paper we introduce a novel method: ARCANA. We use ARCANA to identify the possible root causes of anomalies detected by an autoencoder. It describes the process of reconstruction as an optimisation problem that aims to remove anomalous properties from an anomaly considerably. This reconstruction must be similar to the anomaly and thus identify only a few, but highly explanatory anomalous features, in the sense of Ockham’s razor. The proposed method is applied on an open data set of wind turbine sensor data, where an artificial error was added onto the wind speed sensor measurements to acquire a controlled test environment. The results are compared with the reconstruction errors of the autoencoder output. The ARCANA method points out the wind speed sensor correctly with a significantly higher feature importance than the other features, whereas using the non-optimised reconstruction error does not. Even though the deviation in one specific input feature is very large, the reconstruction error of many other features is large as well, complicating the interpretation of the detected anomaly. Additionally, we apply ARCANA to a set of offshore wind turbine data. Two case studies are discussed, demonstrating the technical relevance of ARCANA.

[1]  Zijun Zhang,et al.  Wind Turbine Blade Breakage Monitoring With Deep Autoencoders , 2018, IEEE Transactions on Smart Grid.

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

[3]  Philip S. Yu,et al.  WaveletAE: A Wavelet-enhanced Autoencoder for Wind Turbine Blade Icing Detection , 2019 .

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

[5]  Haibo He,et al.  Wind Turbine Fault Detection Using a Denoising Autoencoder With Temporal Information , 2017, IEEE/ASME Transactions on Mechatronics.

[6]  Kian Hsiang Low,et al.  GEE: A Gradient-based Explainable Variational Autoencoder for Network Anomaly Detection , 2019, 2019 IEEE Conference on Communications and Network Security (CNS).

[7]  Yukihiro Tadokoro,et al.  Structured Denoising Autoencoder for Fault Detection and Analysis , 2014, ACML.

[8]  Niklas Renström,et al.  System-wide anomaly detection in wind turbines using deep autoencoders , 2020 .

[9]  Katrien van Driessen,et al.  A Fast Algorithm for the Minimum Covariance Determinant Estimator , 1999, Technometrics.

[10]  Marc-Alexander Lutz,et al.  Evaluation of Anomaly Detection of an Autoencoder Based on Maintenace Information and Scada-Data , 2020 .

[11]  Jordi Cusidó,et al.  Feature Selection Algorithms for Wind Turbine Failure Prediction , 2019, Energies.

[12]  Ryoichi Kawahara,et al.  Anomaly Detection and Interpretation using Multimodal Autoencoder and Sparse Optimization , 2018, ArXiv.

[13]  Lior Rokach,et al.  Explaining Anomalies Detected by Autoencoders Using SHAP , 2019, ArXiv.

[14]  Xin Lei,et al.  PHM based predictive maintenance optimization for offshore wind farms , 2015, 2015 IEEE Conference on Prognostics and Health Management (PHM).

[15]  Xiaoli Li,et al.  A Multi-Level-Denoising Autoencoder Approach for Wind Turbine Fault Detection , 2019, IEEE Access.

[16]  L. Longo,et al.  Explainable Artificial Intelligence: a Systematic Review , 2020, ArXiv.

[17]  Georg Helbing,et al.  Deep Learning for fault detection in wind turbines , 2018, Renewable and Sustainable Energy Reviews.

[18]  Wenjing Hu,et al.  Anomaly detection and fault analysis of wind turbine components based on deep learning network , 2018, Renewable Energy.

[19]  Vaishak Belle,et al.  Principles and Practice of Explainable Machine Learning , 2020, Frontiers in Big Data.

[20]  Avanti Shrikumar,et al.  Learning Important Features Through Propagating Activation Differences , 2017, ICML.

[21]  Dahai Zhang,et al.  A Data-Driven Design for Fault Detection of Wind Turbines Using Random Forests and XGboost , 2018, IEEE Access.

[22]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[23]  Nina Dethlefs,et al.  Deep learning with knowledge transfer for explainable anomaly prediction in wind turbines , 2020 .

[24]  Goran Nenadic,et al.  Machine learning methods for wind turbine condition monitoring: A review , 2019, Renewable Energy.