DG
D.S. Goglio
info
Please Note
<p>This page displays the records of the person named above and is not linked to a unique person identifier. This record may need to be merged to a profile.</p>
3 records found
1
An efficient and cost-effective maintenance strategy is key to ensuring availability and performance of industrial assets. Conventional time-based scheduled maintenance often fails to achieve this goal, especially as it is static: it does not take into account asset condition evolution nor evolution in operational conditions over time. Here, we propose a predictive maintenance strategy which is dynamic, based on asset remaining useful life (RUL), and risk-informed. Building on a recently introduced time transformation that facilitates RUL estimation, this work develops a simulation framework that enables implementation, testing, and optimization of a dynamic maintenance strategy for a fleet of identical assets. RUL estimates are continuously updated, and the timing of the next maintenance intervention is optimized such that the probability of failure before that time does not exceed a specified bound. Alternatively, a warning threshold and the probability bound can be selected to minimize the total expected cost of preventive maintenance actions and failures (the latter including corrective maintenance and failure consequences). The proposed dynamic strategy is benchmarked against conventional (static) scheduled maintenance strategies. The cost of the scheduled preventive maintenance policy is compared with that of the predictive maintenance policy. The study also examines the effects of imperfect maintenance. A simplified yet realistic example is presented to demonstrate the applicability of the method.
...
An efficient and cost-effective maintenance strategy is key to ensuring availability and performance of industrial assets. Conventional time-based scheduled maintenance often fails to achieve this goal, especially as it is static: it does not take into account asset condition evolution nor evolution in operational conditions over time. Here, we propose a predictive maintenance strategy which is dynamic, based on asset remaining useful life (RUL), and risk-informed. Building on a recently introduced time transformation that facilitates RUL estimation, this work develops a simulation framework that enables implementation, testing, and optimization of a dynamic maintenance strategy for a fleet of identical assets. RUL estimates are continuously updated, and the timing of the next maintenance intervention is optimized such that the probability of failure before that time does not exceed a specified bound. Alternatively, a warning threshold and the probability bound can be selected to minimize the total expected cost of preventive maintenance actions and failures (the latter including corrective maintenance and failure consequences). The proposed dynamic strategy is benchmarked against conventional (static) scheduled maintenance strategies. The cost of the scheduled preventive maintenance policy is compared with that of the predictive maintenance policy. The study also examines the effects of imperfect maintenance. A simplified yet realistic example is presented to demonstrate the applicability of the method.
Unforeseen technical failures contribute significantly to airline delays, highlighting the need for predictive maintenance. However, developing reliable prognostic models in aviation is challenging due to strict safety requirements, limited labeled data, and the need for interpretable and trustworthy predictions. This research proposes a hybrid framework for remaining useful life (RUL) prediction that integrates multimodal domain knowledge available to airlines, such as sensor data, contextual information and reliability insights, into interpretable and uncertainty-aware algorithms. To this end, the proposed framework resorts to unsupervised degradation extraction with knowledge-informed autoencoders and supports extensions for failure mode segmentation. Initial experiments on a benchmark dataset show promising results, and application to real-world commercial aircraft data is planned to further validate the approach.
...
Unforeseen technical failures contribute significantly to airline delays, highlighting the need for predictive maintenance. However, developing reliable prognostic models in aviation is challenging due to strict safety requirements, limited labeled data, and the need for interpretable and trustworthy predictions. This research proposes a hybrid framework for remaining useful life (RUL) prediction that integrates multimodal domain knowledge available to airlines, such as sensor data, contextual information and reliability insights, into interpretable and uncertainty-aware algorithms. To this end, the proposed framework resorts to unsupervised degradation extraction with knowledge-informed autoencoders and supports extensions for failure mode segmentation. Initial experiments on a benchmark dataset show promising results, and application to real-world commercial aircraft data is planned to further validate the approach.
Analytical Health Indices
Towards Reliability-Informed Deep Learning for PHM
Deep learning has demonstrated significant potential for prognostics in complex systems (Fink et al., 2020). Recent advances in physics-informed machine learning have integrated physics-of-failure principles within data-driven models (Arias Chao, Kulkarni, Goebel, & Fink, 2022). Beyond physical laws, fleet-level time-to-failure (TTF) distributions provide valuable prior knowledge for individual asset life predictions. In this paper we derive a probabilistic analytical health index(HI) model based on power-law degradation, enabling a probabilistic description that reconciles individual variability with fleet-wide trends. We show that, under Weibull, Gamma, and Pareto-distributed TTFs, the HI evolution follows an analytical form, allowing explicit characterization of time to reach intermediate degradation levels. Therefore, this work provides a theoretical foundation for integrating reliability principles with deep learning, advancing towards Reliability-Informed Deep Learning (RIDL). The approach is validated on synthetic turbofan engine data and real-world battery degradation datasets. This work establishes a rigorous basis for embedding reliability engineering principles into deep learning, improving predictive maintenance and remaining useful life (RUL) estimation.
...
Deep learning has demonstrated significant potential for prognostics in complex systems (Fink et al., 2020). Recent advances in physics-informed machine learning have integrated physics-of-failure principles within data-driven models (Arias Chao, Kulkarni, Goebel, & Fink, 2022). Beyond physical laws, fleet-level time-to-failure (TTF) distributions provide valuable prior knowledge for individual asset life predictions. In this paper we derive a probabilistic analytical health index(HI) model based on power-law degradation, enabling a probabilistic description that reconciles individual variability with fleet-wide trends. We show that, under Weibull, Gamma, and Pareto-distributed TTFs, the HI evolution follows an analytical form, allowing explicit characterization of time to reach intermediate degradation levels. Therefore, this work provides a theoretical foundation for integrating reliability principles with deep learning, advancing towards Reliability-Informed Deep Learning (RIDL). The approach is validated on synthetic turbofan engine data and real-world battery degradation datasets. This work establishes a rigorous basis for embedding reliability engineering principles into deep learning, improving predictive maintenance and remaining useful life (RUL) estimation.