| 1. |
- Aslanidou, Ioanna, et al.
(författare)
-
Towards an Integrated Approach for Micro Gas Turbine Fleet Monitoring, Control and Diagnostics
- 2018
-
Konferensbidrag (refereegranskat)abstract
- Real-time engine condition monitoring and fault diagnostics results in reduced operating and maintenance costs and increased component and engine life. Prediction of faults can change the maintenance model of a system from a fixed maintenance interval to a condition based maintenance interval, further decreasing the total cost of ownership of a system. Technologies developed for engine health monitoring and advanced diagnostic capabilities are generally developed for larger gas turbines, and generally focus on a single system; no solutions are publicly available for engine fleets. This paper presents a concept for fleet monitoring finely tuned to the specific needs of micro gas turbines. The proposed framework includes a physics-based model and a data-driven model with machine learning capabilities for predicting system behaviour, combined with a diagnostic tool for anomaly detection and classification. The integrated system will develop advanced diagnostics and condition monitoring for gas turbines with a power output under 100 kW.
|
|
| 2. |
|
|
| 3. |
- Olsson, Tomas, et al.
(författare)
-
A data-driven approach for predicting long-term degradation of a fleet of micro gas turbines
- 2021
-
Ingår i: Energy and AI. - : Elsevier BV. - 2666-5468. ; 4
-
Tidskriftsartikel (refereegranskat)abstract
- Predictive health monitoring of micro gas turbines can significantly increase the availability and reduce the operating and maintenance costs. Methods for predictive health monitoring are typically developed for large-scale gas turbines and have often focused on single systems. In an effort to enable fleet-level health monitoring of micro gas turbines, this work presents a novel data-driven approach for predicting system degradation over time. The approach utilises operational data from real installations and is not dependent on data from a reference system. The problem was solved in two steps by: 1) estimating the degradation from time-dependent variables and 2) forecasting into the future using only running hours. Linear regression technique is employed both for the estimation and forecasting of degradation. The method was evaluated on five different systems and it is shown that the result is consistent (r>0.8) with an existing method that computes corrected values based on data from a reference system, and the forecasting had a similar performance as the estimation model using only running hours as an input.
|
|
| 4. |
- Söderkvist Vermelin, Wilhelm, et al.
(författare)
-
Self-supervised Learning for Efficient Remaining Useful Life Prediction
- 2022
-
Ingår i: Vol. 14 No. 1 (2022): Proceedings of the Annual Conference of the PHM Society 2022. - : PHM Society.
-
Konferensbidrag (refereegranskat)abstract
- Canonical deep learning-based Remaining Useful Life (RUL) prediction relies on supervised learning methods which in turn requires large data sets of run-to-failure data to ensure model performance. In a large class of cases, run-to-failure data is difficult to collect in practice as it may be expensive and unsafe to operate assets until failure. As such, there is a need to leverage data that are not run-to-failure but may still contain some measurable, and thus learnable, degradation signal. In this paper, we propose utilizing self-supervised learning as a pretraining step to learn representations of the data which will enable efficient training on the downstream task of RUL prediction. The self-supervised learning task chosen is time series sequence ordering, a task that involves constructing tuples each consisting of $n$ sequences sampled from the time series and reordered with some probability $p$. Subsequently, a classifier is trained on the resulting binary classification task; distinguishing between correctly ordered and shuffled tuples. The classifier's weights are then transferred to the RUL-model and fine-tuned using run-to-failure data. We show that the proposed self-supervised learning scheme can retain performance when training on a fraction of the full data set. In addition, we show indications that self-supervised learning as a pretraining step can enhance the performance of the model even when training on the full run-to-failure data set. To conduct our experiments, we use a data set of simulated run-to-failure turbofan jet engines.
|
|
