Martin Tveten

Machine learning and statistical methods can improve conventional motor protection systems by providing early warning and detection of emerging failures. Data-driven methods rely on historical data to learn how the system is expected to behave under normal circumstances. An unexpected change in the underlying system may alter the statistical properties of the data, thereby affecting the performance of the fault detection algorithm in terms of time to detection and false alarms. This kind of change, called concept drift, requires adaptations to maintain constant performance. In this article, we present a machine learning approach for detecting overheating in the stator windings of marine electrical propulsion motors. Using simulated overheating faults injected into operational data, the methods are shown to provide early detection compared to conventional methods based on temperature readings and fixed limits. The proposed monitors are designed to operate for a type of concept drift observed in operational data collected from a specific class of motors in a fleet of ships. Using a mix of real and simulated concept drifts, it is shown that the proposed monitors are able to provide early detections during and after concept drifts, without the need for full model retraining.

We propose a computationally efficient and sparsity adaptive procedure for estimating changes in unknown subsets of a high-dimensional data sequence. Assuming the data sequence is Gaussian, we prove that the new method successfully estimates the number and locations of changepoints with a given error rate and under minimal conditions for all sparsities of the changing subset. Our method has computational complexity linear up to logarithmic factors in both the length and number of time series, making it applicable to large data sets. Through extensive numerical studies we show that the new methodology is highly competitive in terms of both estimation accuracy and computational cost. The practical usefulness of the method is illustrated by analysing sensor data from a hydro power plant, and an efficient R implementation is available.

Motivated by a condition monitoring application arising from subsea engineering, we derive a novel, scalable approach to detecting anomalous mean structure in a subset of correlated multivariate time series. Given the need to analyse such series efficiently, we explore a computationally efficient approximation of the maximum likelihood solution to the resulting modelling framework and develop a new dynamic programming algorithm for solving the resulting binary quadratic programme when the precision matrix of the time series at any given time point is banded. Through a comprehensive simulation study we show that the resulting methods perform favorably compared to competing methods, both in the anomaly and change detection settings, even when the sparsity structure of the precision matrix estimate is misspecified. We also demonstrate its ability to correctly detect faulty time periods of a pump within the motivating application.

Thermal protection in marine electrical propulsion motors is commonly implemented by installing temperature sensors on the windings of the motor. An alarm is issued once the temperature reaches the alarm limit, while the motor shuts down once the trip limit is reached. Field experience shows that this protection scheme in some cases is insufficient, as the motor may already be damaged before reaching the trip limit. In this paper, we develop a machine learning algorithm to predict overheating, based on past data collected from a class of identical vessels. All methods were implemented to comply with real-time requirements of the on-board protective systems with minimal need for memory and computational power. Our two-stage overheating detection algorithm first predicts the temperature in a normal state using linear regression fitted to regular operation motor performance measurements, with exponentially smoothed predictors accounting for time dynamics. Then it identifies and monitors temperature deviations between the observed and predicted temperatures using an adaptive cumulative sum (CUSUM) procedure. Using data from a real fault case, the monitor alerts between 60 to 90 min before failure occurs, and it is able to detect the emerging fault at temperatures below the current alarm limits.