Predictive Maintenance and Fault Monitoring Enabled by Machine Learning: Experimental Analysis of a TA-48 Multistage Centrifugal Plant Compressor DOI Creative Commons
Mounia Achouch, Mariya Dimitrova, Rizck Dhouib

et al.

Applied Sciences, Journal Year: 2023, Volume and Issue: 13(3), P. 1790 - 1790

Published: Jan. 30, 2023

In an increasingly competitive industrial world, the need to adapt any change at time has become a major necessity for every industry remain and survive in their environments. Industries are undergoing rapid perpetual changes on several levels. Indeed, latter requires companies be more reactive involved policies of continuous improvement order satisfy customers maximize quantity quality production, while keeping cost production as low possible. Reducing downtime is one objectives these industries future. This paper aimed apply machine learning algorithms TA-48 multistage centrifugal compressor failure prediction remaining useful life (RUL), i.e., reduce system using predictive maintenance (PdM) approach through adoption Industry 4.0 approaches. To achieve our goal, we followed methodology workflow that allows us explore process data model training. Thus, comparative study different was carried out arrive final choice, which based implementation LSTM neural networks. addition, its performance improved sets were fed incremented. Finally, deployed allow operators know times compressors subsequently ensure minimum rates by making decisions before failures occur.

Language: Английский

A comprehensive literature review of the applications of AI techniques through the lifecycle of industrial equipment DOI Creative Commons
Mahboob Elahi, Samuel Olaiya Afolaranmi, José L. Martínez Lastra

et al.

Discover Artificial Intelligence, Journal Year: 2023, Volume and Issue: 3(1)

Published: Dec. 7, 2023

Abstract Driven by the ongoing migration towards Industry 4.0, increasing adoption of artificial intelligence (AI) has empowered smart manufacturing and digital transformation. AI enhances industry 4.0 through AI-based decision-making analyzing real-time data to optimize different processes such as production planning, predictive maintenance, quality control etc., thus guaranteeing reduced costs, high precision, efficiency accuracy. This paper explores AI-driven manufacturing, revolutionizing traditional approaches unlocking new possibilities throughout major phases industrial equipment lifecycle. Through a comprehensive review, we delve into wide range techniques employed tackle challenges optimizing process control, machining parameters, facilitating decision-making, elevating maintenance strategies within an These encompass design, recycling/retrofitting. As reported in 2022 McKinsey Global Survey ( https://www.mckinsey.com/capabilities/quantumblack/our-insights/the-state-of-ai-in-2022-and-a-half-decade-in-review ), witnessed more than two-fold increase since 2017. contributed research last six years. Therefore, from meticulous search relevant electronic databases, carefully selected synthesized 42 articles spanning 01 January 2017 20 May 2023 highlight review most recent research, adhering specific inclusion exclusion criteria, shedding light on latest trends popular adopted researchers. includes Convolutional Neural Networks (CNN), Generative Adversarial (GAN), Bayesian Networks, Support Vector Machines (SVM) which are extensively discussed this paper. Additionally, provide insights advantages (e.g., enhanced decision making) integration with legacy systems due technical complexities compatibilities) integrating across stages operations. Strategically implementing each phase enables industries achieve productivity, improved product quality, cost-effectiveness, sustainability. exploration potential fosters agile resilient processes, keeping at forefront technological advancements harnessing full solutions improve products.

Language: Английский

Citations

127

Artificial Intelligence for Predictive Maintenance Applications: Key Components, Trustworthiness, and Future Trends DOI Creative Commons
Ayşegül Uçar, Mehmet Karaköse, Necim Kırımça

et al.

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(2), P. 898 - 898

Published: Jan. 20, 2024

Predictive maintenance (PdM) is a policy applying data and analytics to predict when one of the components in real system has been destroyed, some anomalies appear so that can be performed before breakdown takes place. Using cutting-edge technologies like artificial intelligence (AI) enhances performance accuracy predictive systems increases their autonomy adaptability complex dynamic working environments. This paper reviews recent developments AI-based PdM, focusing on key components, trustworthiness, future trends. The state-of-the-art (SOTA) techniques, challenges, opportunities associated with PdM are first analyzed. integration AI into real-world applications, human–robot interaction, ethical issues emerging from using AI, testing validation abilities developed policies later discussed. study exhibits potential areas for research, such as digital twin, metaverse, generative collaborative robots (cobots), blockchain technology, trustworthy Industrial Internet Things (IIoT), utilizing comprehensive survey current SOTA opportunities, challenges allied PdM.

Language: Английский

Citations

80

Envisioning maintenance 5.0: Insights from a systematic literature review of Industry 4.0 and a proposed framework DOI Creative Commons
Foivos Psarommatis, Gökan May, Victor Azamfirei

et al.

Journal of Manufacturing Systems, Journal Year: 2023, Volume and Issue: 68, P. 376 - 399

Published: May 9, 2023

To provide direction and advice for future research on Industry 4.0 maintenance, we conducted a comprehensive analysis of 344 eligible journal papers published between 2013 2022. Our systematic literature review identifies key trends in advanced maintenance techniques the consolidation traditional concepts, which are driven by increasing adoption technologies need to optimize manufacturing systems' performance reliability. In light our findings, highlight importance addressing sustainability factors, human aspects, implementation environmental KPIs research. Building upon these insights, introduce Maintenance 5.0 framework, emphasizes integration human-centered AI-driven strategies achieving efficient sustainable Zero-Defect Manufacturing (ZDM) systems. We propose novel framework that links policies small medium-sized enterprises (SMEs) facilitate field. This work underscores bridge gap policies, enabling seamless transition SMEs towards practices, while fostering socially responsible operations.

Language: Английский

Citations

62

Transforming equipment management in oil and gas with AI-Driven predictive maintenance DOI Creative Commons

Dazok Donald Jambol,

Oludayo Olatoye Sofoluwe,

Ayemere Ukato

et al.

Computer Science & IT Research Journal, Journal Year: 2024, Volume and Issue: 5(5), P. 1090 - 1112

Published: May 5, 2024

The oil and gas industry faces significant challenges in managing equipment maintenance due to the complexity criticality of its assets. Traditional approaches are often reactive inefficient, leading costly downtime safety risks. However, emergence artificial intelligence (AI) predictive technologies offers a transformative solution these challenges. This paper explores role AI-driven revolutionizing management sector. leverages machine learning algorithms analyze data predict when is required before breakdown occurs. By monitoring performance real-time, AI can identify potential issues early, allowing operators take proactive actions. approach helps minimize downtime, reduce costs, improve overall reliability safety. implementation requires comprehensive strategy that includes collection, analysis, integration with existing practices. Successful adoption lead benefits for companies, including increased uptime, extended asset lifespan, enhanced operational efficiency. reviews current landscape industry, highlighting limitations traditional practices need more approach. It then examines principles maintenance, showcasing real-world examples successful implementation. Finally, discusses considerations implementing provides recommendations companies looking transform their Keywords: Transforming Equipment; Management; Oil Gas; AI-Driven; Predictive Maintenance.

Language: Английский

Citations

36

A survey-based approach of framework development for improving the application of internet of things in the construction industry of Malaysia DOI Creative Commons
Muhammad Ali Musarat, Wesam Salah Alaloul,

Abdul Mateen Khan

et al.

Results in Engineering, Journal Year: 2024, Volume and Issue: 21, P. 101823 - 101823

Published: Jan. 27, 2024

The progress of our society is reflected in the building sector, which emphasises necessity constantly modifying instruments to take advantage new opportunities. An example cutting-edge technology with potential completely transform construction sector Internet Things (IoT). goal this comprehensive analysis help industry improve understanding how crucial it embrace IoT. In study, a systematic review relevant literature was conducted identify factors that contribute enhancing IoT applications industry. primary objective list and evaluate most important uses, advantages difficulties using sector. This revealed has significant by improving productivity, safety, sustainability quality across entire lifecycle. However, barriers such as data privacy cybersecurity lack standardised protocols need be addressed. concludes likely revolutionise coming years if these challenges can overcome. These findings imply firms experiment analytic tools phased use cases, whilst policy groups must collaborate on standards protocols. Although obstacles exist, strategic implementation promises major operational breakthroughs near future.

Language: Английский

Citations

29

Digital technologies for a net-zero energy future: A comprehensive review DOI
Md Meftahul Ferdaus, Tanmoy Dam, Sreenatha G. Anavatti

et al.

Renewable and Sustainable Energy Reviews, Journal Year: 2024, Volume and Issue: 202, P. 114681 - 114681

Published: July 2, 2024

Language: Английский

Citations

28

Machine Learning and Deep Learning Paradigms: From Techniques to Practical Applications and Research Frontiers DOI Creative Commons
Kamran Razzaq, Mahmood Shah

Computers, Journal Year: 2025, Volume and Issue: 14(3), P. 93 - 93

Published: March 6, 2025

Machine learning (ML) and deep (DL), subsets of artificial intelligence (AI), are the core technologies that lead significant transformation innovation in various industries by integrating AI-driven solutions. Understanding ML DL is essential to logically analyse applicability identify their effectiveness different areas like healthcare, finance, agriculture, manufacturing, transportation. consists supervised, unsupervised, semi-supervised, reinforcement techniques. On other hand, DL, a subfield ML, comprising neural networks (NNs), can deal with complicated datasets health, autonomous systems, finance industries. This study presents holistic view technologies, analysing algorithms application’s capacity address real-world problems. The investigates application which techniques implemented. Moreover, highlights latest trends possible future avenues for research development (R&D), consist developing hybrid models, generative AI, incorporating technologies. aims provide comprehensive on serve as reference guide researchers, industry professionals, practitioners, policy makers.

Language: Английский

Citations

4

Towards Predictive Maintenance in the Maritime Industry: A Component-Based Overview DOI Creative Commons
Alexandros Kalafatelis, Νικόλαος Νομικός, Anastasios Giannopoulos

et al.

Journal of Marine Science and Engineering, Journal Year: 2025, Volume and Issue: 13(3), P. 425 - 425

Published: Feb. 25, 2025

The maritime industry has a significant influence on the global economy, underscoring need for operational availability and safety through effective maintenance practices. Predictive emerges as promising solution compared to conventional schemes currently employed by industry, offering proactive failure predictions, reduced downtime events, extended machinery lifespan. This paper addresses critical gap in existing literature providing comprehensive overview of main data-driven PdM systems. Specifically, review explores common issues found vessel components (i.e., propulsion, auxiliary, electric, hull), examining how different state-of-the-art architectures, ranging from basic machine learning models advanced deep techniques aim address them. Additionally, concepts centralized learning, federated, transfer are also discussed, demonstrating their potential enhance systems well limitations. Finally, current challenges hindering adoption together with future directions advance implementation field.

Language: Английский

Citations

3

A real-time adaptive model for bearing fault classification and remaining useful life estimation using deep neural network DOI Creative Commons
Muktesh Gupta, Rajesh Wadhvani, Akhtar Rasool

et al.

Knowledge-Based Systems, Journal Year: 2022, Volume and Issue: 259, P. 110070 - 110070

Published: Oct. 30, 2022

Language: Английский

Citations

49

Maintenance Performance in the Age of Industry 4.0: A Bibliometric Performance Analysis and a Systematic Literature Review DOI Creative Commons
Sylwia Werbińska-Wojciechowska, Klaudia Winiarska

Sensors, Journal Year: 2023, Volume and Issue: 23(3), P. 1409 - 1409

Published: Jan. 27, 2023

Recently, there has been a growing interest in issues related to maintenance performance management, which is confirmed by significant number of publications and reports devoted these problems. However, theoretical application studies indicate lack research on the systematic literature reviews surveys that would focus evolution Industry 4.0 technologies used area cross-sectional manner. Therefore, paper existing present an up-to-date content-relevant analysis this field. The proposed methodology includes bibliometric review literature. First, general was conducted based Scopus Web Science databases. Later, search performed using Primo multi-search tool following Preferred Reporting Items for Systematic Reviews Meta-Analyses (PRISMA) guidelines. main inclusion criteria included publication dates (studies published from 2012–2022), English, found selected In addition, authors focused work within scope Maintenance study. papers fields were selected: (a) augmented reality, (b) virtual (c) system architecture, (d) data-driven decision, (e) Operator 4.0, (f) cybersecurity. This resulted selection 214 most relevant investigated area. Finally, articles categorized into five groups: (1) Data-driven decision-making (2) (3) Virtual Augmented reality maintenance, (4) (5) Cybersecurity maintenance. obtained results have led specify problems trends analyzed identify gaps future investigation academic engineering perspectives.

Language: Английский

Citations

36