Article
Computer Science, Information Systems
Thirupathi Samala, Vijaya Kumar Manupati, Jose Machado, Shubham Khandelwal, Katarzyna Antosz
Summary: This paper investigates the most used performance measures for diagnostics of manufacturing systems and proposes a simulation approach based on MCDM-TOPSIS to improve system performance and maximize production rate. The results show that throughput time is the most affected parameter, while maximum stay time is the least affected parameter.
Review
Engineering, Multidisciplinary
Fei Peng, Li Zheng, Yongdong Peng, Congcong Fang, Xianghui Meng
Summary: This paper introduces the potential of digital twin technology in the field of rolling bearings and reviews its development history. Through a literature survey, this paper investigates the core technologies of digital twin construction for rolling bearings and analyzes the challenges that this technology faces in future research.
Article
Green & Sustainable Science & Technology
Meiling Yue, Samir Jemei, Noureddine Zerhouni, Rafael Gouriveau
Summary: This paper provides a comprehensive review of existing prognostics research on proton exchange membrane fuel cells (PEMFC), highlighting key issues that have not been fully addressed and proposing four principal directions of post-prognostics decision-making. Research challenges and development perspectives in the aspects of data, prognostics, and decision-making are discussed based on the findings.
Article
Energy & Fuels
Shentong Ni, Yang Tang, Guorong Wang, Liu Yang, Bo Lei, Zhidong Zhang
Summary: Equipment failure risk identification and risk assessment are crucial for offshore platform equipment integrity management. This paper proposes a new quantitative risk assessment method based on fuzzy set theory, gray correlation analysis, and fuzzy Borda method. The proposed method effectively captures and aggregates diversity evaluations of FMECA team members and solves the existing issues in quantitative risk assessment. It provides a reference for maintenance decision-making in complex industrial systems.
Article
Automation & Control Systems
Hamidreza Seiti, Mahdi Fathi, Ashkan Hafezalkotob, Enrique Herrera-Viedma, Ibrahim A. Hameed
Summary: Failure mode and effect analysis (FMEA) is widely used in various industries to identify and eliminate failures in the process of product design, development, and production. This paper introduces a resilience-based risk priority number and a risk-based fuzzy information processing and decision-making method to address some issues in traditional FMEA calculations.
Article
Engineering, Industrial
Austin D. Lewis, Katrina M. Groth
Summary: This paper introduces a new taxonomy of metrics to assess and compare the performance of system-level health monitoring models. It also describes a verification process and provides an illustrative example for applying these metrics in model design decision. The comprehensive set of metrics enables both PRA and PHM communities to rigorously evaluate system-level health monitoring models.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2022)
Article
Computer Science, Information Systems
Banalata Bera, Chun-Ling Lin, Shyh-Chin Huang, Jin-Wei Liang, Po Ting Lin
Summary: Recently, prognostics and health management (PHM) has gained attention in industry for cost-effective maintenance and safe operation. Vibration-based predictive maintenance is crucial for diagnosing and predicting faults. This study presents a prognostic model using a mathematical model and statistical/machine learning methods to forecast future unbalance trend in a rotor-bearing system. The model is used to predict real-time unbalance values of an industrial turbine rotor for the next month. The proposed model is validated using data from a local plastic company and proves to accurately detect future system unbalance.
Article
Computer Science, Interdisciplinary Applications
Adalberto Polenghi, Irene Roda, Marco Macchi, Alessandro Pozzetti
Summary: In smart factories, the use of ontology-based solutions can support joint maintenance and production management decisions by considering the health state of assets, thereby fulfilling production requirements.
JOURNAL OF INDUSTRIAL INFORMATION INTEGRATION
(2022)
Review
Green & Sustainable Science & Technology
Ying Zhang, Yan-Fu Li
Summary: This paper summarizes the applications of deep learning-based PHM of Li-ion battery, including data acquisition, deep learning methods, and performance evaluation. It also discusses the prospects of using deep learning techniques in the PHM of Li-ion battery.
RENEWABLE & SUSTAINABLE ENERGY REVIEWS
(2022)
Article
Engineering, Electrical & Electronic
Peng Zhang, Zeyu Gao, Lele Cao, Fangyang Dong, Yongjiu Zou, Kai Wang, Yuewen Zhang, Peiting Sun
Summary: This article presents a review of the framework of prognostics and health management (PHM) in the marine field, covering the technical processes of health condition monitoring, fault diagnosis, health prognosis, and maintenance decision. The methods and applications of each process are summarized, and the challenges of implementing PHM for intelligent ships are discussed.
Article
Automation & Control Systems
Diyin Tang, Mengtong Gong, Jinsong Yu, Liwei Guo, Junwei Di
Summary: This study presents a system-level prognostic method for predicting the performance of an infrared (IR) system. The method considers IR system degradation as energy redistribution between different degradation levels and quantifies system degradation using a constructed health indicator. The effectiveness and advantages of the method are evaluated and verified through simulations and real data analysis.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2022)
Article
Computer Science, Artificial Intelligence
Marcia L. Baptista, Elsa M. P. Henriques
Summary: The performance of prognostics is closely related to the quality of condition monitoring signals. This paper proposes a 1-D Denoising Generative Adversarial Network (1D-DGAN-PHM) for prognostics and health management, which is trained on synthetic data generated with physics-of-failure knowledge. The results show that 1D-DGAN-PHM significantly improves prognosability and achieves better denoising performance compared to baseline methods.
APPLIED SOFT COMPUTING
(2022)
Article
Chemistry, Multidisciplinary
Francesca Calabrese, Alberto Regattieri, Raffaele Piscitelli, Marco Bortolini, Francesco Gabriele Galizia
Summary: Extracting representative feature sets from raw signals is crucial in understanding components' behavior in Prognostics and Health Management (PHM). This paper adopts Genetic Programming (GP) to extract system-level and component-level features, and evaluates their performance through classification accuracy and Remaining Useful Life (RUL) prediction error.
APPLIED SCIENCES-BASEL
(2022)
Article
Automation & Control Systems
Dong Wang, Zhike Peng, Lifeng Xi
Summary: Prognostics and health management of rotating machines aim to use monitoring data to infer health conditions, with health indices being the basis. Spectral Lp/Lq norm ratio and spectral Gini index are popular health indices characterizing impulsiveness caused by faults. Special forms include spectral kurtosis and spectral L2/L1 norm ratio. Experimental investigations showed that these indices characterize impulsiveness effectively, with a fused health index proposed to address issues with impulsive noises.
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
(2021)
Article
Engineering, Industrial
Michele Compare, Federico Antonello, Luca Pinciroli, Enrico Zio
Summary: This work proposes a general modelling approach to estimate the life cycle cost of a system equipped with PHM capabilities and undergoing a CBM policy. The approach is based on the Markov Chain framework and incorporates transition probabilities linked to PHM performance metrics and a novel metric. The model can guide economic decisions about CBM development regardless of the specific PHM algorithm, as long as its performance metrics can be estimated. The model is validated through a case study on a mechanical component affected by fatigue degradation, considering two different prognostic algorithms: Particle Filtering and a Model-Based approach.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2022)
Article
Computer Science, Artificial Intelligence
Don J. Rude, Stephen Adams, Peter A. Beling
JOURNAL OF INTELLIGENT MANUFACTURING
(2018)
Editorial Material
Engineering, Industrial
Stephen Conway Adams, Peter Beling, William Scherer, Cody Fleming, James H. Lambert
SYSTEMS ENGINEERING
(2019)
Article
Computer Science, Artificial Intelligence
Xiaomin Lin, Stephen C. Adams, Peter A. Beling
JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH
(2019)
Article
Engineering, Mechanical
Stephen Adams, Ryan Meekins, Peter A. Beling, Kevin Farinholt, Nathan Brown, Sherwood Polter, Qing Dong
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2019)
Article
Environmental Sciences
Sami M. Saliba, Benjamin D. Bowes, Stephen Adams, Peter A. Beling, Jonathan L. Goodall
Article
Management
Alex Langevin, Tyler Cody, Stephen Adams, Peter Beling
Summary: Augmenting a dataset with synthetic samples is a common step in machine learning to improve model performance, and it can also benefit sharing information between cooperating parties while maintaining customer privacy. However, the potential gains from synthetic data augmentation are often overlooked in relation to data distribution. A case study in credit card fraud detection suggests that customer distributions can impact the effectiveness of augmentation with Generative Adversarial Networks.
JOURNAL OF THE OPERATIONAL RESEARCH SOCIETY
(2022)
Article
Computer Science, Hardware & Architecture
Cody Fleming, Carl R. Elks, Georgios Bakirtzis, Stephen C. Adams, Bryan Carter, Peter A. Beling, Barry Horowitz
Summary: Cyberphysical systems require resiliency techniques for defense, and multicriteria resiliency problems need an approach that evaluates systems for current threats and potential design solutions. A systems-oriented view of cyberphysical security, termed Mission Aware, is proposed based on a holistic understanding of mission goals, system dynamics, and risk.
Article
Computer Science, Artificial Intelligence
Jianyu Su, Jing Huang, Stephen Adams, Qing Chang, Peter A. Beling
Summary: The study utilizes a novel multi-agent modeling approach to support adaptive learning in obtaining cost efficient PM policies, which effectively improves production efficiency. Compared to centralized RL methods, the proposed framework demonstrates better performance in simulation study and does not require prior knowledge about the environment and maintenance strategies.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Information Systems
Tyler Cody, Stephen Adams, Peter A. Beling
Summary: The paper discusses the use of systems engineering to address constraints on algorithmic learning in transfer learning, as well as the application of transfer distance in quantifying model transferability and its role in the design of machine rebuild procedures and prediction of operational performance in computer vision. Practitioners can benefit from this methodology in designing and operating systems while considering the learning theoretic challenges faced by component learning systems.
IEEE SYSTEMS JOURNAL
(2022)
Article
Computer Science, Artificial Intelligence
Faraz Dadgosari, Mauricio Guim, Peter A. Beling, Michael A. Livermore, Daniel N. Rockmore
Summary: This article introduces a mathematical model that frames the behavior and cognitive framework of law search as a sequential decision process. The model is implemented and assessed on a subset of U.S. Supreme Court opinions, showing the potential for machine law search to achieve human or near-human levels of performance with further work and refinement.
ARTIFICIAL INTELLIGENCE AND LAW
(2021)
Proceedings Paper
Computer Science, Theory & Methods
Jie Liu, Stephen Adams, Peter A. Beling
2020 IEEE 6TH WORLD FORUM ON INTERNET OF THINGS (WF-IOT)
(2020)
Article
Psychology, Clinical
Miranda L. Beltzer, Stephen Adams, Peter A. Beling, Bethany A. Teachman
CLINICAL PSYCHOLOGICAL SCIENCE
(2019)
Article
Computer Science, Artificial Intelligence
Stephen Adams, Peter A. Beling
ARTIFICIAL INTELLIGENCE REVIEW
(2019)
Proceedings Paper
Computer Science, Interdisciplinary Applications
Jarett Cestaro, David Conklin, Douglas Ziman, Edmund Pan, Grant Anhorn, Matthew Cunningham, Nevan Schulte, Faraz Dadgostari, Peter Beling
2019 SYSTEMS AND INFORMATION ENGINEERING DESIGN SYMPOSIUM (SIEDS)
(2019)
Article
Social Sciences, Interdisciplinary
Bryan Carter, Stephen Adams, Georgios Bakirtzis, Tim Sherburne, Peter Beling, Barry Horowitz, Cody Fleming
Article
Engineering, Industrial
Xiaoliang Yan, Reed Williams, Elena Arvanitis, Shreyes Melkote
Summary: This paper extends prior work by developing a semantic segmentation approach for machinable volume decomposition using pre-trained generative process capability models, providing manufacturability feedback and labels of candidate machining operations for query 3D parts.
JOURNAL OF MANUFACTURING SYSTEMS
(2024)
Article
Engineering, Industrial
Jing Huang, Zhifen Zhang, Rui Qin, Yanlong Yu, Guangrui Wen, Wei Cheng, Xuefeng Chen
Summary: In this study, a deep learning framework that combines interpretability and feature fusion is proposed for real-time monitoring of pipeline leaks. The proposed method extracts abstract feature details of leak acoustic emission signals through multi-level dynamic receptive fields and optimizes the learning process of the network using a feature fusion module. Experimental results show that the proposed method can effectively extract distinguishing features of leak acoustic emission signals, achieving higher recognition accuracy compared to typical deep learning methods. Additionally, feature map visualization demonstrates the physical interpretability of the proposed method in abstract feature extraction.
JOURNAL OF MANUFACTURING SYSTEMS
(2024)