Continual learning for predictive maintenance: Overview and challenges

Hurtado, Julio; Dario, Salvati,; Rudy, Semola,; Bosio, Mattia; Lomonaco, Vincenzo

doi:10.1016/j.iswa.2023.200251

Cited by 17 publications

(3 citation statements)

References 107 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hurtado et al [11] provided an in-depth exploration of the challenges and opportunities associated with continual learning for PdM. They emphasized the dynamic nature of machinery conditions and the need for adaptive learning algorithms that can continuously update and adapt to changing operational environments.…”

Section: Literature Reviewmentioning

confidence: 99%

Intelligent Mechanisms for PdM in Automotive Machinery: A Comprehensive Analysis using ML/DL

Snehal A. Patil

2024

jes

View full text Add to dashboard Cite

Predictive maintenance (PdM) technique involves analyzing and utilizing data to identify problems before they happen. It can help prevent costly repairs and downtime. In the past few years, the use of intelligent tools for PdM in automotive machinery has been increasing. These tools can be used to analyze and collect data from various sources, such as cloud computing and sensors. In the prediction of failures, this data can be used in combination with machine learning algorithms. With the help of advanced technologies, such as machine learning and sensors, PdM has become a viable option to maintain machinery while minimizing costs and downtime. The paper presents a comprehensive analysis of the various components of the intelligent tools that are used for PdM. It starts by exploring the different kinds of sensors and their functions in monitoring the condition of the equipment. The paper then explores the synergistic relationship between machine learning and data analytics, demonstrating how these technologies can help identify potential issues, predict the remaining useful life of the equipment, and detect early anomalies. The paper reviews the literature on the use of intelligent tools and sensors for PdM in automotive machinery. It delves into the diverse kinds of mechanisms that have been employed for this type of PdM, the pros and cons of using such tools, as well as the possible directions in this domain. Despite the various challenges that have been presented, the potential of implementing intelligent tools in automotive machinery is still immense. They can help prevent equipment downtime and improve the safety and efficiency of the operations of the machinery. As the technology matures, we can expect the adoption of such mechanisms to increase. The report emphasizes the significant contribution of intelligent tools and sensors to the optimization of the maintenance schedules and the reduction of unplanned downtime in automotive machinery. The findings of this study provide a roadmap for practitioners, researchers, and industrial organizations looking to harness the potential of such mechanisms to guarantee the longevity of their assets.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Intelligent Mechanisms for PdM in Automotive Machinery: A Comprehensive Analysis using ML/DL

Snehal A. Patil

2024

jes

View full text Add to dashboard Cite

show abstract

“…Overall, predictive modeling techniques offer powerful tools for forecasting the remaining useful life of power electronic devices and enabling proactive maintenance strategies. By leveraging machine learning algorithms and time-series analysis, engineers can develop robust models that accurately capture the complex interactions between various factors influencing device degradation and failure [4].…”

Section: Predictive Modelingmentioning

confidence: 99%

Advancing maintenance, monitoring, and control techniques for the optimization of power electronic systems

Zhu

2024

TNS

View full text Add to dashboard Cite

This paper explores the innovative methodologies and technologies in predictive maintenance, real-time monitoring, fault detection, and advanced control strategies for power electronic devices. Initially, we delve into data acquisition and preprocessing techniques crucial for ensuring the quality and reliability of data used in predictive models. These models, leveraging machine learning and time-series analysis, predict the remaining useful life of devices, guiding proactive maintenance strategies. Furthermore, we discuss the significance of risk assessment and decision support systems in prioritizing maintenance tasks and allocating resources efficiently. The narrative then shifts to real-time monitoring and fault detection, emphasizing the role of sensor integration, data fusion, anomaly detection, and diagnostics in maintaining system integrity. Condition-based maintenance strategies, underscored by real-time data analytics, are presented as a means to optimize maintenance activities and enhance operational performance. The paper concludes with a detailed examination of advanced control strategies, including model predictive control, reinforcement learning, and distributed control and optimization techniques, highlighting their potential to improve system efficiency, reliability, and adaptability. Through comprehensive research and analysis, this work aims to provide valuable insights into the development of sophisticated maintenance and control mechanisms for power electronic systems, ultimately contributing to their longevity and operational efficacy.

show abstract

“…We are in the digital age, where predictive maintenance (PM) is based on monitoring performance in the active state. According to Hurtado et al (2023), PM is an approach to identify the best time to maintain it before it breaks down. PM has become a necessity for intervention in order to make the production process efficient and more flexible.…”

Section: Introductionmentioning

confidence: 99%

Artificial intelligence-based predictive maintenance, time-sensitive networking, and big data-driven algorithmic decision-making in the economics of Industrial Internet of Things

Kliestik,

Nica,

Durana

et al. 2023

View full text Add to dashboard Cite

Research background: The article explores the integration of Artificial Intelligence (AI) in predictive maintenance (PM) within Industrial Internet of Things (IIoT) context. It addresses the increasing importance of leveraging advanced technologies to enhance maintenance practices in industrial settings. Purpose of the article: The primary objective of the article is to investigate and demonstrate the application of AI-driven PM in the IIoT. The authors aim to shed light on the potential benefits and implications of incorporating AI into maintenance strategies within industrial environments. Methods: The article employs a research methodology focused on the practical implementation of AI algorithms for PM. It involves the analysis of data from sensors and other sources within the IIoT ecosystem to present predictive models. The methods used in the study contribute to understanding the feasibility and effectiveness of AI-driven PM solutions. Findings & value added: The article presents significant findings regarding the impact of AI-driven PM on industrial operations. It discusses how the implementation of AI technologies contributes to increased efficiency. The added value of the research lies in providing insights into the transformative potential of AI within the IIoT for optimizing maintenance practices and improving overall industrial performance.

show abstract

Continual learning for predictive maintenance: Overview and challenges

Cited by 17 publications

References 107 publications

Intelligent Mechanisms for PdM in Automotive Machinery: A Comprehensive Analysis using ML/DL

Intelligent Mechanisms for PdM in Automotive Machinery: A Comprehensive Analysis using ML/DL

Advancing maintenance, monitoring, and control techniques for the optimization of power electronic systems

Artificial intelligence-based predictive maintenance, time-sensitive networking, and big data-driven algorithmic decision-making in the economics of Industrial Internet of Things

Contact Info

Product

Resources

About