Mittuniversitetet

The importance of anomaly detection in multivariate time series has led to the development of several prominent deep learning solutions. As a part of the anomaly detection method, the scoring method has shown to be of significant importance when separating non-anomalous points from anomalous ones. At this time, most of the solutions utilize an aggregated score which means that relevant information created by the anomaly detection model might be lost. Therefore, this study has set out to examine to what extent anomaly detection in multivariate time series based on deep learning can be improved if all the residuals from each individual channel is considered in the anomaly score. To achieve this, an aggregated and separated scoring method has been applied with a simple denoising convulutional autoencoder (DCAE). In addition, the performance has been compared with other state-of-the-art methods. The result showed that the separated approach has the potential to generate a significantly higher performance than the aggregated one. At the same time, there were some indications suggesting that an aggregated scoring is better at generalizing when no labels to base the anomaly thresholds on, are available. Therefore, the result should serve as an encouragement to use a separated scoring approach together with a small sample of labeled anomalies to optimise the thresholds. Lastly, due to the impact of the anomaly score, the result suggests that future research within this field should consider applying the same anomaly scoring method when comparing the performance of deep learning algorithms. 

Anomaly detection in multivariate time series is valuable for many applications. In this context, unsupervised and semi-supervised deep learning methods that estimate how normal a new observation is have shown promising results on benchmark datasets. These methods are dependent on a threshold that determines which points should be regarded as anomalous and not be anomalous. However, finding the optimal threshold is not easy since no information about the ground truth is known in advance, which implies that there are limitations to automatic threshold-setting methods available today. An alternative is to utilize the expertise of users that can interact in a threshold-setting procedure, but for this to be practically feasible, the method needs to be both accurate and efficient in relation to the state-of-the-art automatic methods. Therefore, this study develops an interactive threshold-setting schema and examines to what extent it can outperform the current state-of-the-art automatic threshold-setting methods. The result of the study strongly indicates that the suggested method with little effort can provide higher accuracy than the automatic threshold-setting methods on a general basis. 

The importance of preventing failures in bearings has led to a large amount of research being conducted to find methods for fault diagnostics and prognostics. Many of these solutions, such as deep learning methods, require a significant amount of data to perform well. This is a reason why publicly available data are important, and there currently exist several open datasets that contain different conditions and faults. However, one challenge is that almost all of these data come from a laboratory setting, where conditions might differ from those found in an industrial environment where the methods are intended to be used. This also means that there may be characteristics of the industrial data that are important to take into account. Therefore, this study describes a completely new dataset for bearing faults from a pulp mill. The analysis of the data shows that the faults vary significantly in terms of fault development, rotation speed, and the amplitude of the vibration signal. It also suggests that methods built for this environment need to consider that no historical examples of faults in the target domain exist and that external events can occur that are not related to any condition of the bearing.

Reliable methods for bearing fault diagnosis are of great importance because they provide the possibility of preventing failures in machines. A significant challenge is developing solutions that can handle the variances in the data across different domains i.e., the operational context of the bearing and settings including noise, bearing type, rotational speed, and sampling frequency. To solve this issue, a common approach is to use transfer learning. However, most existing methods either assume that faults are available in the target domain or that only operational conditions on a single machine are changed between the source and target domain. Unfortunately, neither of these assumptions can be made in an industrial environment where there is a need to deploy the method on new machines with no historical faults. Therefore, there is a need to develop methods for bearing fault diagnosis that can provide accurate predictions on a general basis without needing access to historical faults from the target domain. To address this problem, this study develops a novel method including a knowledge-enriched standardization procedure used to lower the domain shift, a feature-targeted metric learning procedure enriched with contextual data that can be deployed to any new domain without having access to historical faults. The method is compared against state-of-the-art solutions in three cases with various tasks where it achieves the highest accuracy and displays high robustness and generalizability. The results also show a low level of false positives, a high level of fault segment recall and the possibility of giving feedback to the user about the model's decision. The conclusion is that the method can be used on a general basis for fault diagnosis of bearings without having access to historical faults from the target domain. 

Methods for estimating the remaining useful life of bearings are of great value in preventing them from failing. Because of this, different types of methods have been suggested. One of the most prominent is transfer learning since it achieves high performance despite the discrepancies in data expected in industrial applications. However, most current research ignores aspects such as the influence of non-bearing related faults, the non-existence of historical run-to-failure data from the target domain and knowledge transfer between machines. Considering this, how existing methods will cope with these scenarios is not established. Therefore, this study examines the performance of transfer learning methods based on current studies methodologies. The result suggests that there are limitations to the assumptions made in the current research and that more considerations for scenarios found in industrial applications are needed both in the development and evaluation phases to increase the possibility of applying transfer learning methods in practice.