Sectors are the main drivers of economic expansion. However, the changes brought about by the technological revolutions have a direct impact on the industries and their personnel. By fusing human experience with precise, clever, and effective machinery, Industry 5.0 aims to create more user-friendly and efficient production solutions than Industry 4.0. A number of innovative methods and applications are under development, which will enable Industry 5.0 to increase output and logically provide services that are customised for each unique consumer. Strong empirical evidence supporting the transformative potential of ML and DL methods when incorporated into Industry 5.0 is provided by this substantial experimental investigation. ANN, RNN, GAN, and BRDT are a few deep learning algorithm examples. The findings offer concrete evidence of the vital roles ML and DL methods play in enhancing energy efficiency, optimising production processes, and increasing the bar for product quality in the fast-paced Industry 5.0 scenario.
Top1. Introduction
Cutting-edge technology is now a major force behind societal change. The progressive transition from agricultural to industrialised society is addressed by modernization; hence it is important to look at technology developments in a variety of practice contexts. New breakthroughs by themselves do not change societies. Change is instead driven by how we respond to technology. While innovation is often acknowledged, it is rarely put to long-term use. Subsequently, it can become widely accepted and transform the entire population (Crozier et al 2021, Ansari et al., 2022).
A number of industries, such as textiles, agriculture, glass, mining and others were impacted as machinery took the position of handicrafts as the primary economic engine during the first industrial revolution (Longo et al., 2020).
A later change known as Industry 2.0 occurred in the industrial sector among 1871 and 1914 and encouraged the quick spread of novel ideas. Electricity was the catalyst for the 2.0 Industrial Revolution, transforming old industries into state-of-the-art manufacturing that led to significant economic growth and increased productivity.
With the advent of automation and memory-programmed controls in the 1970s, Industry 3.0, often known as the digital revolution, got underway. Production got more and more mechanized with the introduction of field-level computers and communication technology. This phase's primary goals consist of mass production, digital logic, integrated circuit chip utilisation, and associated innovations including computers, the internet, and digital mobile phones (Pathak et al., 2021; He et al., 2017).
The digital revolution has made it possible to transform technology into digital form. The term “Industry 4.0” describes how digital technologies such as robotics, IoT, 3D printing, cloud computing, and AI are combined with physical assets. Companies using Industry 4.0 are adaptable and prepared to make choices based on information (Leone, 2020).
By combining human cognitive and critical thinking with intelligent, linked technology, the goal of Industry 5.0 is to increase industry effectiveness and promote human-machine flexibility (Maddikunta et al., 2022; Zeb et al., 2022). While giving computers and robots the boring and repetitive jobs, this next industrial revolution may raise the standard of output overall while retaining human workers to handle creative problem-solving. Moreover, industry 4.0, the fourth industrial revolution, provides the foundation for industry 5.0, which transcends manufacturing (Gaba et al., 2020; Boopalan et al., 2022; Masud et al., 2021). ICT innovations include robotics, edge computing, Internet of Things (IoT), automation, artificial intelligence (AI), and big data analytics make it possible.
The purpose of the study was to present concrete proof of the possible applications of DL (deep learning) and ML (machine learning) methods in Industry 5.0. There is currently a lack of real-world industrial use for these algorithms, despite the fact that the evidence supports their theoretical potential. This research investigation aims to bridge this gap by closely examining the effectiveness of ML and DL methods in improving manufacturing quality, increasing energy consumption, and optimising operational procedures. Using actual data, the research closes the knowledge gap and offers helpful suggestions for businesses planning to implement Industry 5.0. (Kim et al., 2022; Mondal et al., 2023; El-Brawnay et al., 2023).