Michele Compare
YOU?
Author Swipe
View article: Deep Reinforcement Learning Based on Proximal Policy Optimization for the Maintenance of a Wind Farm with Multiple Crews
Deep Reinforcement Learning Based on Proximal Policy Optimization for the Maintenance of a Wind Farm with Multiple Crews Open
The life cycle of wind turbines depends on the operation and maintenance policies adopted. With the critical components of wind turbines being equipped with condition monitoring and Prognostics and Health Management (PHM) capabilities, it …
View article: A physics-informed machine learning framework for predictive maintenance applied to turbomachinery assets
A physics-informed machine learning framework for predictive maintenance applied to turbomachinery assets Open
The paper presents an overview of Baker Hughes digital framework for a predictive maintenance service boosted by Machine Learning and asset knowledge, applied to turbomachinery assets. Optimization of the maintenance scenario is performed …
View article: Addendum: Termite, M.R. et al. A Never-Ending Learning Method for Fault Diagnostics in Energy Systems Operating in Evolving Environments. Energies 2019, 12, 4802
Addendum: Termite, M.R. et al. A Never-Ending Learning Method for Fault Diagnostics in Energy Systems Operating in Evolving Environments. Energies 2019, 12, 4802 Open
The authors would like to add the following note to Figure 3 of their paper published in Energies [...]
View article: IRIS: A Novel Approach to Monitoring Risk in Safety Critical Plants
IRIS: A Novel Approach to Monitoring Risk in Safety Critical Plants Open
We present a novel approach for tracking a global risk index of a safety-critical industrial plant. This approach, called Integrated Risk Index by Sapio (IRIS), considers safety as a critical process variable and relies on a combination of…
View article: The Aramis Data Challenge: Prognostics and Health Management in Evolving Environments
The Aramis Data Challenge: Prognostics and Health Management in Evolving Environments Open
The objective of the Aramis Data Challenge is the creation of a public benchmark dataset for the problem of fault detection in evolving environments. A multi-component system in which the degradation of one component accelerates the degrad…
View article: An Interdisciplinary Approach for Investigating an Accident Originating from Leakage in a Gasketed Bolted Joint
An Interdisciplinary Approach for Investigating an Accident Originating from Leakage in a Gasketed Bolted Joint Open
We investigate an accident originating from a leak of hydrochloric acid through a gasketed bolted joint of a measuring equipment operating in aWasteWater Treatment System (WWTS). In spite of the simplicity of the failed component and of th…
View article: Agent-based Modeling and Reinforcement Learning for Optimizing Energy Systems Operation and Maintenance: The Pathmind Solution
Agent-based Modeling and Reinforcement Learning for Optimizing Energy Systems Operation and Maintenance: The Pathmind Solution Open
The optimization of the Operation and Maintenance (O&M) of energy systems equipped with Prognostics and Health Management (PHM) capabilities can be framed as a sequential decision process, which can be addressed by Reinforcement Learni…
View article: Deep Reinforcement Learning for Optimizing Operation and Maintenance of Energy Systems Equipped with PHM Capabilities
Deep Reinforcement Learning for Optimizing Operation and Maintenance of Energy Systems Equipped with PHM Capabilities Open
The Life Cycle Cost (LCC) of energy systems including Renewable Energy Sources (RES) strongly depends on the Operation and Maintenance (O&M) costs. Nowadays, many components of these energy systems are equipped with Prognostics & H…
View article: Enhancements of Reliability Centered Maintenance Analysis and its Application to the Railway Industry
Enhancements of Reliability Centered Maintenance Analysis and its Application to the Railway Industry Open
Reliability Centered Maintenance (RCM) is a mature technique for effective maintenance decision making in complex systems. Although RCM is widely used in industry, there are major limiting factors that prevent its wider application such as…
View article: A Risk-based Diagnostic Campaign Optimization for Electric Power Distribution Networks
A Risk-based Diagnostic Campaign Optimization for Electric Power Distribution Networks Open
Failures of Medium Voltage Distribution Networks (MVDN) can result in power outages, penalties from authorities and large operational costs. To prevent the network failures, diagnostic campaigns are performed to estimate the degradation st…
View article: A Never-Ending Learning Method for Fault Diagnostics in Energy Systems Operating in Evolving Environments
A Never-Ending Learning Method for Fault Diagnostics in Energy Systems Operating in Evolving Environments Open
Condition monitoring (CM) in the energy industry is limited by the lack of pre-classified data about the normal and/or abnormal plant states and the continuous evolution of its operational conditions. The objective is to develop a CM model…
View article: Towards Developing a Novel Framework for Practical PHM: a Sequential Decision Problem solved by Reinforcement Learning and Artificial Neural Networks
Towards Developing a Novel Framework for Practical PHM: a Sequential Decision Problem solved by Reinforcement Learning and Artificial Neural Networks Open
The heart of prognostics and health management (PHM) is to predict the equipment degradation evolution and, thus, its Remaining Useful Life (RUL). These predictions drive the decisions on the equipment Operation and Maintenance (O&M), and …
View article: Homogeneous Continuous-Time, Finite-State Hidden Semi-Markov Modeling for Enhancing Empirical Classification System Diagnostics of Industrial Components
Homogeneous Continuous-Time, Finite-State Hidden Semi-Markov Modeling for Enhancing Empirical Classification System Diagnostics of Industrial Components Open
This work presents a method to improve the diagnostic performance of empirical classification system (ECS), which is used to estimate the degradation state of components based on measured signals. The ECS is embedded in a homogenous contin…
View article: A heterogeneous ensemble approach for the prediction of the remaining useful life of packaging industry machinery
A heterogeneous ensemble approach for the prediction of the remaining useful life of packaging industry machinery Open
We present a method based on heterogeneous ensemble learning for the prediction of the Remaining Useful Life (RUL) of cutting tools (knives) used in the packaging industry. Ensemble diversity is achieved by training multiple prognostic mod…
View article: A clustering approach for mining reliability big data for asset management
A clustering approach for mining reliability big data for asset management Open
Big data from very large fleets of assets challenge the asset management, as the number of maintenance strategies to optimize and administrate may become very large. To address this issue, we exploit a clustering approach that identifies a…
View article: An unsupervised clustering method for assessing the degradation state of cutting tools used in the packaging industry
An unsupervised clustering method for assessing the degradation state of cutting tools used in the packaging industry Open
International audience
View article: Availability Model of a PHM-Equipped Component
Availability Model of a PHM-Equipped Component Open
A variety of prognostic and health management (PHM) algorithms have been developed in the last years and some metrics have been proposed to evaluate their performances. However, a general framework that allows us to quantify the benefit of…