Predictive Maintenance - Bridging Artificial Intelligence and IoT

Abstract

This paper highlights the trends in the field of predictive maintenance with the use of machine learning. With the continuous development of the Fourth Industrial Revolution, through IoT, the technologies that use artificial intelligence are evolving. As a result, industries have been using these technologies to optimize their production. Through scientific research conducted for this paper, conclusions were drawn about the trends in Predictive Maintenance applications with the use of machine learning bridging Artificial Intelligence and IoT. These trends are related to the types of industries in which Predictive Maintenance was applied, the models of artificial intelligence were implemented, mainly of machine learning and the types of sensors that are applied through the IoT to the applications. Six sectors were presented and the production sector was dominant as it accounted for 54.54% of total publications. In terms of artificial intelligence models, the most prevalent among ten were the Artificial Neural Networks, Support Vector Machine and Random Forest with 27.84%, 17.72% and 13.92% respectively. Finally, twelve categories of sensors emerged, of which the most widely used were the sensors of temperature and vibration with percentages of 60.71% and 46.42% correspondingly.

Review on the Evolution and Impact of Iot-Driven Predictive Maintenance: Assessing Advancements, Their Role in Enhancing System Longevity, and Sustainable Operations in Both Mechanical and Electrical Realms

“…This innovation represents a milestone in IoT predictive maintenance, as it enables more efficient and accurate monitoring across a manufacturing plant (Liu et al, 2022). Samatas, Moumgiakmas, and Papakostas (2021) explore the convergence of AI and IoT in predictive maintenance, highlighting the trends and applications in various industries. Their research indicates that the integration of machine learning models with IoT has become increasingly prevalent in predictive maintenance applications.…”

“…The study identifies the dominant sectors and AI models used in these applications, emphasizing the widespread adoption of IoT in predictive maintenance. This convergence has led to more sophisticated and effective maintenance strategies, significantly contributing to the sustainability and efficiency of industrial systems (Samatas, Moumgiakmas, & Papakostas, 2021). Therefore, the milestones in IoT-driven maintenance and system sustainability are marked by the automation of predictive maintenance, the integration of AI, and the effective combination of IoT with AI.…”

“…These developments are characterized by the integration of artificial intelligence (AI), advancements in real-time monitoring techniques, and the need to address security challenges in IoT networks. Samatas, Moumgiakmas, and Papakostas (2021) explore the convergence of AI and IoT in predictive maintenance. Their research highlights the growing trend of using machine learning to bridge AI and IoT, optimizing production in various industries.…”

Energy-Based Prognostics for Gradual Loss of Conveyor Belt Tension in Discrete Manufacturing Systems

“…The Run-2-Failure maintenance strategy (also known as the reactive, fault-driven or fire-fighting maintenance strategy) is a maintenance strategy where maintenance activity starts when either an obvious equipment functional failure, malfunction or equipment breakdown occurs. As it is a reactive maintenance strategy, the corrective measurements are governed by random failure events and sometimes these failures lead to very large equipment or machine downtimes, an extensive equipment repair time as well as high repair cost, which decrease production in the manufacturing system [7][8][9][10].…”

The Artificial Intelligence (AI) Model Canvas Framework and Use Cases

“…There is no doubt that the manufacturing industry is leading the way in the adoption of AI technologies. Artificial neural networks and machine learning combined with IoT are employed to support predictive maintenance of the health status of industrial equipment, which can accurately predict asset malfunction [42][43] [44]. It helps the management take timely measures to restore the equipment and increase the utilization rate of the components and increase their remaining useful lives.…”