相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
Article
Computer Science, Interdisciplinary Applications
Vishal Gupta et al.
Summary: This article explores the maintenance of airports' baggage handling systems and examines the use of predictive maintenance as an alternative to periodic maintenance. The unique challenges faced by baggage handling systems, such as random noise from IoT sensors and complex interconnected components, are discussed. The article proposes a scalable and cost-effective maintenance 4.0 solution using real-time sensor data. An algorithm is presented to differentiate between anomaly detection and outlier detection and remove irrelevant data. Integrated machine learning techniques are employed to detect and diagnose defects early on. The article also compares the performance of different machine learning algorithms and suggests future research directions.
COMPUTERS & INDUSTRIAL ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Antonio L. S. Pacheco et al.
Summary: This paper proposes an artificial neural system to estimate the cooling capacity of compressors in the production line. The proposed method combines bootstrap techniques with Monte Carlo simulations to ensure reliable results. The average difference between the proposed method and laboratory tests was 0.65%, with a standard deviation of 0.47%. The uncertainty of the estimates was 5.1%, which is similar to the typical value observed in laboratory tests. By integrating this tool into compressor assembly lines, the cooling capacity parameter for all produced units can be estimated.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Chemistry, Multidisciplinary
Francesco Del Buono et al.
Summary: Predictive Maintenance (PdM) is a new strategy that utilizes Machine Learning (ML) algorithms, particularly autoencoders, to predict failure and maximize component lifespan in industrial maintenance management. This paper presents a systematic study of autoencoder-based novelty detection methods and their effectiveness in industrial plant environments.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Interdisciplinary Applications
Yuchen Jiang et al.
Summary: This article introduces a general PdM framework based on Internet-of-Things technology, cloud computing, and total productive maintenance. It proposes an attribute attentioned long short-term memory network (A(2)-LSTM) to predict the remaining useful life of manufacturing equipment.
COMPUTERS & INDUSTRIAL ENGINEERING
(2022)
Article
Computer Science, Artificial Intelligence
Gyumin Lee et al.
Summary: This study develops an interpretable machine learning model to estimate the future state-of-health (SOH) of lithium-ion batteries in the early stages of qualification tests. The proposed approach reduces testing time and error, and highlights the importance of SOH value changes for predicting future battery health, particularly in the early stages of testing.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Chuang Chen et al.
Summary: This paper proposes a novel data-driven predictive maintenance strategy, which includes a Local Uncertainty Estimation (LUE) model and a Maintenance Cost Rate (MCR) function, to address the separate and hierarchical tasks of RUL prediction and maintenance decision-making. The strategy is validated in the field of aero-engine health monitoring and shows promising results in reducing system maintenance costs.
Proceedings Paper
Computer Science, Theory & Methods
Daniel Coelho et al.
Summary: This paper proposes a maintenance approach for predicting downtime, which combines anomaly detection, feature dimension reduction, and machine learning classification algorithms. Experimental results show that this approach can improve the macro F1-score by approximately 22.971% compared to traditional approaches, and Randomized Decision Trees achieve a ROC AUC index of 96%.
3RD INTERNATIONAL CONFERENCE ON INDUSTRY 4.0 AND SMART MANUFACTURING
(2022)
Article
Computer Science, Artificial Intelligence
Serkan Ayvaz et al.
Summary: The study developed a data-driven predictive maintenance system for manufacturing production lines, utilizing real-time data from IoT sensors to detect potential failures before they occur. The system was successful in identifying indicators of potential failures and the best performing machine learning models were integrated into the production system in the factory.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Energy & Fuels
Hamzeh Soltanali et al.
Summary: The study identifies process integrity, insufficient data, and system complexity in the automotive manufacturing sector as major uncertainty factors influencing failure probability. It introduces a fuzzy fault tree analysis approach to estimate failure probability for maintenance planning, and incorporates Bayesian network theory to address the undynamic relationship between failure in complex systems. The results show that while changes in decision attributes have minimal impact on failure probability, the Bayesian network model significantly improves prediction accuracy by considering dynamic relationships.
Review
Automation & Control Systems
Vahid Nasir et al.
Summary: This paper reviews the opportunities and challenges of deep learning for intelligent machining and tool monitoring, discusses the main DL models, and introduces the components of an intelligent monitoring framework. It also highlights the advantages of machine learning models and compares them with deep models offering a hybrid intelligent models. Challenges associated with data size, data nature, model selection, and process uncertainty are outlined.
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY
(2021)
Article
Engineering, Industrial
Hector Rivera-Gomez et al.
Summary: This paper proposes a new joint control policy that considers the interactions between production quality and maintenance. A stochastic mathematical model is developed using specialized optimization techniques to solve the quality constrained problem. Numerical examples are provided to demonstrate the usefulness of the proposed approach and investigate the interactions between production-quality and maintenance strategies.
JOURNAL OF MANUFACTURING SYSTEMS
(2021)
Article
Computer Science, Interdisciplinary Applications
Mustafa Cakir et al.
Summary: With the rise of the fourth industrial revolution, traditional maintenance in manufacturing is being replaced by IIoT systems like CMS for real-time monitoring and notification of potential failures. A low-cost, industry 4.0 compatible CMS was designed in this study, consisting of an experimental setup, IIoT-based CMA, and ML models. Through data collection and modeling, it was found that additional features beyond vibration data can enhance classification accuracy, with ML algorithms showing high success rates in predicting bearing damage.
COMPUTERS & INDUSTRIAL ENGINEERING
(2021)
Article
Computer Science, Artificial Intelligence
Chong Chen et al.
ADVANCED ENGINEERING INFORMATICS
(2020)
Review
Computer Science, Interdisciplinary Applications
Tiago Zonta et al.
COMPUTERS & INDUSTRIAL ENGINEERING
(2020)
Review
Computer Science, Interdisciplinary Applications
Thyago P. Carvalho et al.
COMPUTERS & INDUSTRIAL ENGINEERING
(2019)
Proceedings Paper
Engineering, Industrial
Wo Jae Lee et al.
26TH CIRP CONFERENCE ON LIFE CYCLE ENGINEERING (LCE)
(2019)
Proceedings Paper
Automation & Control Systems
Emiliano Traini et al.
Article
Engineering, Industrial
Jianjing Zhang et al.
JOURNAL OF MANUFACTURING SYSTEMS
(2018)
Proceedings Paper
Automation & Control Systems
Domingo Llorente Rivera et al.
Article
Business
Scott A. Wright et al.
Article
Engineering, Manufacturing
Zhe Li et al.
ADVANCES IN MANUFACTURING
(2017)
Article
Computer Science, Hardware & Architecture
Shiyong Wang et al.
Article
Economics
Rob J. Hyndman et al.
INTERNATIONAL JOURNAL OF FORECASTING
(2006)
Article
Environmental Sciences
CJ Willmott et al.
Article
Computer Science, Interdisciplinary Applications
SL Ho et al.
COMPUTERS & INDUSTRIAL ENGINEERING
(2002)
