Real-Time Predictive Maintenance-Based Process Parameters: Towards an Industrial Sustainability Improvement

Real-time predictive maintenance is a pivotal driver for the evolution of smart factories, deeply impacting the realm of sustainable industry practices. Its core function of continuous monitoring and analysis of manufacturing process parameters not only ensures operational efficiency but also significantly contributes to sustainable practices. By promptly identifying deviations from standard operating conditions and issuing early alerts for potential issues, this approach plays a vital role in extending the lifespan of machinery and optimizing resource-intensive maintenance activities. This paper extensively explores the proactive decision-making facet of real-time predictive maintenance, necessitating the seamless integration of sensor technologies, data acquisition systems, and advanced analytics platforms. The study places particular emphasis on the application of online learning algorithms to construct a robust prediction model that delves into the correlation between changing process parameters and degradation factors, offering a comprehensive insight into machine behavior. This paper is structured as follows: We begin with a comprehensive introduction that highlights the increasing significance of predictive maintenance in smart factories and its profound implications for sustainable industry practices. Then, the paper delves into the challenges surrounding proactive decision-making in real-time predictive maintenance. The crux of the problematic landscape is the need to construct a robust prediction model, combined with the complexity of analyzing features in a dynamic environment. The Methodology section employs a rigorous review methodology to analyze and synthesize the existing body of knowledge in real-time predictive maintenance. The core of this review focuses on synthesizing results that contribute to perspectives on sustainability improvement. The culmination of our review is the conclusion, which encapsulates the paper’s overarching findings.