Anomaly Detection of 2.4L Diesel Engine Using One-Class SVM with Variational Autoencoder

Abstract

Despite the intensive research, the study on preventing the breakdown of the construction machine is still at its early stage, so we need to develop an autonomous and robust solution that minimizes equipment downtime and ensures the rigidity of equipment through predictive diagnostics. In particular, engine failure is critical to cause the entire system to stop, so that it is important to determine and predict the symptoms before the failure. However, at present, it is at a level to set specific indicators based on domain knowledge in order to judge the failure. This paper proposes an anomaly detection model for a 2.4L diesel engine, and verify the model using two main faults. The proposed method extracts 130 feature parameters based on autoencoder, which is a deep learning method, and distinguishes between normal and abnormal states by one-class SVM (OCSVM). Autoencoder automatically extracts useful features from multiple sensors on an excavator engine. The data from the engine can represent robust features by using features learned in latent variables using variational autoencoder to extract optimal features. In addition, OCSVM can detect abnormal state and then distinguish between two fault and unknown factors. The experimental results show the accuracy of about 73%, and the false alarm related to the reliability of this abnormality diagnosis model can be minimized to about 17%. Finally, to solve the problem of reliability and analysis of the model itself due to the problem of blackbox, which is a disadvantage of the deep learning model, the LIME analysis method is applied to list the sensor data that affected the determination of the abnormal state. Experts can easily make professional judgments about abnormal conditions and build a model in which known data about faults and symptoms are continuously increasing. The proposed method could improve the accuracy of the model by adding expert knowledge to data-based model.

Explainable Predictive Maintenance: A Survey of Current Methods, Challenges and Opportunities

“…Articles Shapley Additive Explanations (V-A1) [72], [96], [99], [117], [118], [130], [132] [36]- [38], [42], [66], [75]- [77], [120], [131], [134], [135] Local Interpretable Model-agnostic Explanations (V-A2) [35]- [38], [44], [50], [51], [54], [61], [66], [76], [84] Feature Importance (V-A3) [34], [54], [67], [85], [86], [93], [101], [115], [137], [139] Layer-wise Relevance Propagation (V-A4) [37], [44], [68], [87], [109], [116] Rule-based (V-A5) [65], [70], [71], [73] Class Activation Mapping (CAM) and Gradient-weighted CAM (V-B1) [37], [44],…”

Variational Convolutional Autoencoders for Anomaly Detection in Scanning Transmission Electron Microscopy

“…Although a relatively recent technique, [ 11 ] the use of variational autoencoders (VAEs) has since become a common method for anomaly detection. [ 12–15 ] The CVAE architecture blends together several notable techniques that have been developed over several decades.…”

Towards Explainable Machine Learning for Anomaly Detection in Real-World Contexts

“…In (Jang & Cho, 2019) the authors use OCSVM and Variational Autoencoders for detecting engine faults within 2.4L diesel engines. The faults, which may belong to two types, are precisely the anomalies.…”