A key enabler of intelligent maintenance systems is the ability to predict the remaining useful lifetime (RUL) of its components, i.e., prognostics. The development of data-driven prognostics models requires datasets with run-to-failure trajectories. However, large representative run-to-failure datasets are often unavailable in real applications because failures are rare in many safety-critical systems. To foster the development of prognostics methods, we develop a new realistic dataset of run-to-failure trajectories for a fleet of aircraft engines under real flight conditions. The dataset was generated with the Commercial Modular Aero-Propulsion System Simulation (CMAPSS) model developed at NASA. The damage propagation modelling used in this dataset builds on the modelling strategy from previous work and incorporates two new levels of fidelity. First, it considers real flight conditions as recorded on board of a commercial jet. Second, it extends the degradation modelling by relating the degradation process to its operation history. This dataset also provides the health, respectively, fault class. Therefore, besides its applicability to prognostics problems, the dataset can be used for fault diagnostics.
1 January 2022 in Reliability Engineering & System Safety
Accurate and timely diagnosis of transmission line faults is key for reliable operations of power systems. Existing fault-diagnosis methods rely on expert knowledge or extensive feature extraction, which is also highly dependent on expert knowledge. Additionally, most methods for fault diagnosis of transmission lines require multiple separate subalgorithms for fault classification and location performing each function independently and sequentially. In this research, an integrated framework combining fault classification and location is proposed by applying an innovative machine-learning algorithm: the summation-wavelet extreme learning machine (SW-ELM) that integrates feature extraction in the learning process. As a further contribution, an extension of the SW-ELM, i.e., the summation-Gaussian extreme learning machine (SG-ELM), is proposed and successfully applied to transmission line fault diagnosis. SG-ELM is fully self-learning and does not require ad-hoc feature extraction, making it deployable with minimum expert subjectivity. The developed framework is applied to three transmission-line topologies without any prior parameter tuning or ad-hoc feature extraction. Evaluations on a simulated dataset show that the proposed method can diagnose faults within a single cycle, remain immune to fault resistance and inception angle variation, and deliver high accuracy for both tasks of fault diagnosis: fault type classification and fault location estimation.
22 April 2015 in IEEE Transactions on Neural Networks and Learning Systems
The increasing liberalization of European electricity markets, the growing proportion of intermittent renewable energy being fed into the energy grids, and also new challenges in the patterns of energy consumption (such as electric mobility) require flexible and intelligent power grids capable of providing efficient, reliable, economical, and sustainable energy production and distribution. From the supplier side, particularly, the integration of renewable energy sources (e.g., wind and solar) into the grid imposes an engineering and economic challenge because of the limited ability to control and dispatch these energy sources due to their intermittent characteristics. Time-series prediction of wind speed for wind power production is a particularly important and challenging task, wherein prediction intervals (PIs) are preferable results of the prediction, rather than point estimates, because they provide information on the confidence in the prediction. In this paper, two different machine learning approaches to assess PIs of time-series predictions are considered and compared: 1) multilayer perceptron neural networks trained with a multiobjective genetic algorithm and 2) extreme learning machines combined with the nearest neighbors approach. The proposed approaches are applied for short-term wind speed prediction from a real data set of hourly wind speed measurements for the region of Regina in Saskatchewan, Canada. Both approaches demonstrate good prediction precision and provide complementary advantages with respect to different evaluation criteria.
18 February 2022 in Proceedings of the National Academy of Sciences
Significance: Monitoring of industrial assets often relies on high-frequency (HF) signal measurements. One difficulty of dealing with such measurements in the industrial context is the conciliation between the high-frequency sampling and low-dimensional decision states (e.g., healthy/unhealthy), in a context where, very often, labels are not available. Here, we propose a fully unsupervised deep-learning framework for high-frequency time series that is able to extract meaningful and sparse representation of raw signals and is able to handle different lengths of time series flexibly, overcoming thereby several of the limitations of existing deep-learning approaches. The decomposition framework will be very useful for handling in an automatic manner high-frequency signals and is an important basis for future applications with HF data.