Anomaly Detection And Classification In Time Series With Kervolutional Neural Networks
This work addresses fault detection in condition monitoring for domains like aerospace, but it is incremental as it adapts an existing method (kervolution) to a new data type.
The paper tackled anomaly detection and classification in time series by applying kervolutional neural networks, showing that a mixed model with convolutional and kervolutional layers improved performance, such as better sensitivity to variations and detection of anomalies in helicopter accelerometer data.
Recently, with the development of deep learning, end-to-end neural network architectures have been increasingly applied to condition monitoring signals. They have demonstrated superior performance for fault detection and classification, in particular using convolutional neural networks. Even more recently, an extension of the concept of convolution to the concept of kervolution has been proposed with some promising results in image classification tasks. In this paper, we explore the potential of kervolutional neural networks applied to time series data. We demonstrate that using a mixture of convolutional and kervolutional layers improves the model performance. The mixed model is first applied to a classification task in time series, as a benchmark dataset. Subsequently, the proposed mixed architecture is used to detect anomalies in time series data recorded by accelerometers on helicopters. We propose a residual-based anomaly detection approach using a temporal auto-encoder. We demonstrate that mixing kervolutional with convolutional layers in the encoder is more sensitive to variations in the input data and is able to detect anomalous time series in a better way.