K
K. Verbert
Researcher at Delft University of Technology
Publications - 8
Citations - 439
K. Verbert is an academic researcher from Delft University of Technology. The author has contributed to research in topics: Fault (power engineering) & Stuck-at fault. The author has an hindex of 7, co-authored 8 publications receiving 306 citations.
Papers
More filters
Journal ArticleDOI
Railway Track Circuit Fault Diagnosis Using Recurrent Neural Networks
TL;DR: The long-short-term memory (LSTM) recurrent neural network is proposed to accomplish fault detection and identification tasks based on the commonly available measurement signals by considering the signals from multiple track circuits in a geographic area.
Journal ArticleDOI
Timely condition-based maintenance planning for multi-component systems
TL;DR: This paper proposes a new strategy for timely maintenance planning in multi-component systems that accounts for economic and structural dependence with the aim to profit from spreading or combining various maintenance activities.
Journal ArticleDOI
Combining knowledge and historical data for system-level fault diagnosis of HVAC systems
TL;DR: A multiple-model approach to system-level HVAC fault diagnosis that takes component interdependencies and multiple operating modes into account is proposed and it is shown that component interependencies provide useful features for fault diagnosis.
Journal ArticleDOI
Bayesian and DempsterShafer reasoning for knowledge-based fault diagnosisA comparative study
TL;DR: This paper analyzes how a knowledge-based diagnosis task is influenced by uncertainty, investigates which additional objectives are of relevance, and compares how these characteristics and objectives are handled in two well-known frameworks, namely the Bayesian and the Dempster-Shafer reasoning framework.
Journal ArticleDOI
A Multiple-Model Reliability Prediction Approach for Condition-Based Maintenance
TL;DR: This work establishes a link between failure prognosis and maintenance optimization, and proposes a multivariate multiple-model approach to system reliability prediction, which concludes that in the presence of multiple degradation modes and provided they are correctly identified, a multiple- model approach outperforms a single-model approaches with respect to the prediction accuracy.