Опубликована: Янв. 1, 2023
Язык: Английский
Energy and AI, Год журнала: 2024, Номер 17, С. 100380 - 100380
Опубликована: Июнь 12, 2024
Proton-exchange membrane fuel cells (PEMFCs) are critical components of zero-emission electro-hydrogen generators. Accurate performance prediction is vital to the optimal operation management and preventive maintenance these Polarization curve remains one most important features representing PEMFCs in terms efficiency durability. However, predicting polarization not trivial as involve complex electrochemical reactions that feature multiple nonlinear relationships between operating variables inputs voltage outputs. Herein, we present an artificial-intelligence-based approach for PEMFCs' performance. In way, propose first explainable solution selecting relevant based on kernel principal component analysis mutual information. Then, develop a machine learning XGBRegressor Bayesian optimization explore predict The robustness proposed tested validated through real industrial dataset including 10 PEMFCs. Furthermore, several comparison studies with two popular learning-based methods PEMFC performance, such artificial neural network (ANN) support vector regressor (SVR) also conducted. obtained results show more robust outperforms conventional all considered Indeed, according coefficient determination criterion, model gains improvement 6.35%, 6.8%, 4.8% compared ANN, SVR, respectively.
Язык: Английский
Процитировано
16
Engineering, Год журнала: 2025, Номер unknown
Опубликована: Янв. 1, 2025
Язык: Английский
Процитировано
1
Fundamental Research, Год журнала: 2024, Номер unknown
Опубликована: Янв. 1, 2024
As one of the key technologies to maintain safety and reliability stochastic degrading systems, remaining useful life (RUL) prediction, also known as prognostics, has been attached great importance in recent years. Particularly, with rapid development industrial 4.0 internet-of-things (IoT), prognostics for systems under big data have paid much attention years various prognosis methods reported. However, there not a critical review particularly focused on strengths weaknesses these provoke new ideas research. To fill this gap, facing realistic demand background data, paper profoundly analyzes basic research ideas, trends, common problems data-driven methods, mainly including statistical machine learning (ML) based hybrid ML methods. discusses emerging topic incomplete possible opportunities future are highlighted. Through discussing pros cons existing we provide discussions challenges steer data. While an exhaustive remains elusive, hope that perspectives can serve stimulus era
Язык: Английский
Процитировано
6
Journal of risk and financial management, Год журнала: 2024, Номер 17(2), С. 54 - 54
Опубликована: Янв. 31, 2024
This paper examines how the combination of artificial intelligence (AI) and blockchain technology can enable autonomous AI agents to engage execute economic financial transactions. We critically examine constraints on in achieving predefined objectives independently, especially due their limited access institutions. argue that AI’s these institutions is vital enhancing its capabilities augment human productivity. Drawing theory institutional economics, we propose provides a solution for creating digital institutions, permitting with through management private keys. extends form contracts, participate marketplaces, utilize services autonomously. The encourages further research as general-purpose an unlock full agents.
Язык: Английский
Процитировано
6
Array, Год журнала: 2024, Номер 23, С. 100358 - 100358
Опубликована: Июль 26, 2024
This paper explores the challenges and potential solutions related to data collection, integration, processing, utilization in defense manufacturing within context of Industry 4.0. While 4.0 envisions integration various technologies achieve seamless operations industries, unique characteristics manufacturing, such as stringent limitations security requirements, make direct translation challenging. Through a comprehensive review academic literature, key themes were identified, including quality control, digitalization, cyber–physical aspects, sustainability, risk management, ownership information, security. Drawing from reviewed publications, distilled into approaches, governance frameworks, exchange standards, blockchain, additive transparent digital supply chains, smart factories. These present opportunities for Australian industry overcome identified leverage benefits 4.0, improved increased efficiency, enhanced security, optimized chains. By embracing these opportunities, sector can successfully navigate complexities realize its vision continued growth success.
Язык: Английский
Процитировано
6
Results in Engineering, Год журнала: 2024, Номер 24, С. 103420 - 103420
Опубликована: Ноя. 16, 2024
Язык: Английский
Процитировано
5
Computers & Industrial Engineering, Год журнала: 2024, Номер 197, С. 110520 - 110520
Опубликована: Авг. 30, 2024
Язык: Английский
Процитировано
4
Electronics, Год журнала: 2024, Номер 13(10), С. 1979 - 1979
Опубликована: Май 18, 2024
The future generation of mobile networks envision Artificial Intelligence (AI) and the Internet Things (IoT) as key enabling technologies that will foster emergence sophisticated use cases, with industrial sector being one to benefit most. This survey reviews related works in this field, a particular focus on specific role network softwarization. Furthermore, delves into their context trends, categorizing several types comparing them based contribution advancement state art. Since our analysis yields lack integrated practical implementations potential desynchronization current standards, we finalize study summary challenges research ideas.
Язык: Английский
Процитировано
3
Reliability Engineering & System Safety, Год журнала: 2025, Номер unknown, С. 110904 - 110904
Опубликована: Фев. 1, 2025
Язык: Английский
Процитировано
0
Computers & Industrial Engineering, Год журнала: 2025, Номер unknown, С. 110988 - 110988
Опубликована: Фев. 1, 2025
Язык: Английский
Процитировано
0