Generic Application of Deep Learning Framework for Real-Time Engineering Data Analysis

The need for computer-assisted real-time anomaly detection in engineering data used for condition monitoring is apparent in various applications, including the oil and gas, automotive industries and many other engineering domains. To reduce the reliance on domain-specific experts' knowledge, this paper proposes a deep learning framework that can assist in building a versatile anomaly detection tool needed for effective condition monitoring. The framework enables building a computational anomaly detection model using different types of neural networks and supervised learning. While building such a model, three types of ANN units were compared: a recurrent neural network, a long short-term memory network, and a gated recurrent unit. Each of these units has been evaluated on two benchmark public datasets. The experimental results of this comparative study revealed that the LSTM network unit that uses the sigmoid activation function, the Mean Absolute Error as the objective Loss function and the Adam optimizer as the output layer showed the best performance and attained the accuracy of over 77 % in detecting anomalous values in the datasets. Having determined the best performing combination of the neural network components, a computational anomaly detection model was built within the framework, which was successfully evaluated on real-life engineering datasets comprising the timeseries datasets from an offshore installation in North Sea and another dataset from the automotive industry, which enabled exploring the anomaly classification capability of the proposed framework.