A deep reinforcement learning approach for real-time sensor-driven decision making and predictive analytics. Skordilis, E. & Moghaddass, R. Computers & Industrial Engineering, 147:106600, September, 2020. ![A deep reinforcement learning approach for real-time sensor-driven decision making and predictive analytics [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex The increased complexity of sensor-intensive systems with expensive subsystems and costly repairs and failures calls for efficient real-time control and decision making policies. Deep reinforcement learning has demonstrated great potential in addressing highly complex and challenging control and decision making problems. Despite its potential to derive real-time policies using real-time data for dynamic systems, it has been rarely used for sensor-driven maintenance related problems. In this paper, we propose two novel decision making methods in which reinforcement learning and particle filtering are utilized for (i) deriving real-time maintenance policies and (ii) estimating remaining useful life for sensor-monitored degrading systems. The proposed framework introduces a new direction with many potential opportunities for system monitoring. To demonstrate the effectiveness of the proposed methods, numerical experiments are provided from a set of simulated data and a turbofan engine dataset provided by NASA.
@article{skordilis_deep_2020,
title = {A deep reinforcement learning approach for real-time sensor-driven decision making and predictive analytics},
volume = {147},
issn = {0360-8352},
url = {https://www.sciencedirect.com/science/article/pii/S036083522030334X},
doi = {10.1016/j.cie.2020.106600},
abstract = {The increased complexity of sensor-intensive systems with expensive subsystems and costly repairs and failures calls for efficient real-time control and decision making policies. Deep reinforcement learning has demonstrated great potential in addressing highly complex and challenging control and decision making problems. Despite its potential to derive real-time policies using real-time data for dynamic systems, it has been rarely used for sensor-driven maintenance related problems. In this paper, we propose two novel decision making methods in which reinforcement learning and particle filtering are utilized for (i) deriving real-time maintenance policies and (ii) estimating remaining useful life for sensor-monitored degrading systems. The proposed framework introduces a new direction with many potential opportunities for system monitoring. To demonstrate the effectiveness of the proposed methods, numerical experiments are provided from a set of simulated data and a turbofan engine dataset provided by NASA.},
language = {en},
urldate = {2022-03-03},
journal = {Computers \& Industrial Engineering},
author = {Skordilis, Erotokritos and Moghaddass, Ramin},
month = sep,
year = {2020},
keywords = {Decision-making, Deep reinforcement learning, Particle filters, Real-time control, Remaining useful life estimation},
pages = {106600},
}
Downloads: 0
{"_id":"vnEtPTtJPBgsrMHcK","bibbaseid":"skordilis-moghaddass-adeepreinforcementlearningapproachforrealtimesensordrivendecisionmakingandpredictiveanalytics-2020","author_short":["Skordilis, E.","Moghaddass, R."],"bibdata":{"bibtype":"article","type":"article","title":"A deep reinforcement learning approach for real-time sensor-driven decision making and predictive analytics","volume":"147","issn":"0360-8352","url":"https://www.sciencedirect.com/science/article/pii/S036083522030334X","doi":"10.1016/j.cie.2020.106600","abstract":"The increased complexity of sensor-intensive systems with expensive subsystems and costly repairs and failures calls for efficient real-time control and decision making policies. Deep reinforcement learning has demonstrated great potential in addressing highly complex and challenging control and decision making problems. Despite its potential to derive real-time policies using real-time data for dynamic systems, it has been rarely used for sensor-driven maintenance related problems. In this paper, we propose two novel decision making methods in which reinforcement learning and particle filtering are utilized for (i) deriving real-time maintenance policies and (ii) estimating remaining useful life for sensor-monitored degrading systems. The proposed framework introduces a new direction with many potential opportunities for system monitoring. To demonstrate the effectiveness of the proposed methods, numerical experiments are provided from a set of simulated data and a turbofan engine dataset provided by NASA.","language":"en","urldate":"2022-03-03","journal":"Computers & Industrial Engineering","author":[{"propositions":[],"lastnames":["Skordilis"],"firstnames":["Erotokritos"],"suffixes":[]},{"propositions":[],"lastnames":["Moghaddass"],"firstnames":["Ramin"],"suffixes":[]}],"month":"September","year":"2020","keywords":"Decision-making, Deep reinforcement learning, Particle filters, Real-time control, Remaining useful life estimation","pages":"106600","bibtex":"@article{skordilis_deep_2020,\n\ttitle = {A deep reinforcement learning approach for real-time sensor-driven decision making and predictive analytics},\n\tvolume = {147},\n\tissn = {0360-8352},\n\turl = {https://www.sciencedirect.com/science/article/pii/S036083522030334X},\n\tdoi = {10.1016/j.cie.2020.106600},\n\tabstract = {The increased complexity of sensor-intensive systems with expensive subsystems and costly repairs and failures calls for efficient real-time control and decision making policies. Deep reinforcement learning has demonstrated great potential in addressing highly complex and challenging control and decision making problems. Despite its potential to derive real-time policies using real-time data for dynamic systems, it has been rarely used for sensor-driven maintenance related problems. In this paper, we propose two novel decision making methods in which reinforcement learning and particle filtering are utilized for (i) deriving real-time maintenance policies and (ii) estimating remaining useful life for sensor-monitored degrading systems. The proposed framework introduces a new direction with many potential opportunities for system monitoring. To demonstrate the effectiveness of the proposed methods, numerical experiments are provided from a set of simulated data and a turbofan engine dataset provided by NASA.},\n\tlanguage = {en},\n\turldate = {2022-03-03},\n\tjournal = {Computers \\& Industrial Engineering},\n\tauthor = {Skordilis, Erotokritos and Moghaddass, Ramin},\n\tmonth = sep,\n\tyear = {2020},\n\tkeywords = {Decision-making, Deep reinforcement learning, Particle filters, Real-time control, Remaining useful life estimation},\n\tpages = {106600},\n}\n\n\n\n\n\n\n\n","author_short":["Skordilis, E.","Moghaddass, R."],"key":"skordilis_deep_2020","id":"skordilis_deep_2020","bibbaseid":"skordilis-moghaddass-adeepreinforcementlearningapproachforrealtimesensordrivendecisionmakingandpredictiveanalytics-2020","role":"author","urls":{"Paper":"https://www.sciencedirect.com/science/article/pii/S036083522030334X"},"keyword":["Decision-making","Deep reinforcement learning","Particle filters","Real-time control","Remaining useful life estimation"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"https://bibbase.org/zotero/mh_lenguyen","dataSources":["iwKepCrWBps7ojhDx"],"keywords":["decision-making","deep reinforcement learning","particle filters","real-time control","remaining useful life estimation"],"search_terms":["deep","reinforcement","learning","approach","real","time","sensor","driven","decision","making","predictive","analytics","skordilis","moghaddass"],"title":"A deep reinforcement learning approach for real-time sensor-driven decision making and predictive analytics","year":2020}