Applications of Artificial Intelligence in Industry 4.0/5.0: Innovations, Challenges, and Future Directions

1. Introduction

Artificial Intelligence (AI) has become a fundamental enabling technology in the transformation of modern industrial systems. Within the Industry 4.0 paradigm, the integration of cyber–physical systems (CPS), industrial internet of things (IIoT), cloud and edge computing, and advanced automation technologies has enabled the development of intelligent manufacturing environments capable of real-time monitoring, predictive maintenance, and data-driven decision-making [1,2,3,4,5]. These technologies support improved operational efficiency, flexibility, and quality control across industrial processes.

More recently, the concept of Industry 5.0 has emerged as an evolution of Industry 4.0, emphasizing human-centricity, sustainability, and resilience in industrial ecosystems. Unlike previous paradigms focused primarily on automation and productivity, Industry 5.0 promotes collaboration between humans and intelligent machines, integrating technological innovation with social and environmental objectives [6,7,8]. In this context, intelligent automation, collaborative robotics, and human–machine interaction are key components of next-generation industrial systems.

Artificial Intelligence plays a central role in enabling this transition. Advances in machine learning, deep learning, and reinforcement learning have significantly expanded the capabilities of industrial systems, enabling predictive modelling, intelligent control, and adaptive optimization in complex production environments [9,10,11]. In addition, the integration of AI with CPS architectures and industrial communication frameworks enables real-time data processing and distributed decision-making in smart factories.

Recent research has emphasized the integration of AI with industrial automation and digital transformation frameworks, highlighting the critical role of interoperability, real-time analytics, and system-level integration in enabling scalable and resilient smart manufacturing systems [12]. Furthermore, advances in distributed architectures, including edge computing and blockchain technologies, have been proposed to enhance security, scalability, and resilience in Industry 5.0 environments [13].

The integration of AI with computer vision and collaborative robotics has also gained significant attention, enabling intelligent inspection systems and real-time industrial applications. These approaches demonstrate the potential of deep learning techniques to improve quality control, automation, and human–machine collaboration in industrial settings [14].

Despite these advances, several challenges remain, including scalability, explainability, interoperability, and the integration of AI with legacy industrial infrastructures. Addressing these challenges requires interdisciplinary research combining Artificial Intelligence, industrial engineering, and manufacturing systems [15].

In this context, this Special Issue, titled “Applications of Artificial Intelligence in Industry 4.0/5.0: Innovations, Challenges, and Future Directions”, provides a comprehensive overview of recent advances in AI-driven industrial technologies, covering predictive modelling, intelligent automation, computer vision, reinforcement learning, and systematic analyses of AI methodologies in industrial environments.

2. Overview of Published Articles

The first article (Contribution 1) presents an AI-driven approach to manufacturing digitalization through real-time predictive models, enabling proactive decision-making and improved operational efficiency.

The second article (Contribution 2) proposes a neural-network-based framework for estimating wind power density, demonstrating how AI can support sustainable energy planning and industrial decision-making.

The third article (Contribution 3) investigates reinforcement learning for optimizing an automated substrate irrigation system, illustrating the application of adaptive control strategies in industrial environments.

The fourth article (Contribution 4) provides a systematic review of biases in AI-supported Industry 4.0 research, proposing mitigation strategies to improve transparency and reliability.

The fifth article (Contribution 5) explores computer vision techniques for automated construction waste sorting, demonstrating the potential of AI-driven perception systems in industrial recycling processes.

The sixth article (Contribution 6) presents an automated wastewater treatment system combining PLC-based control with LSTM neural networks for process optimization.

The seventh article (Contribution 7) proposes a framework for integrating Robotic Process Automation with Artificial Intelligence in Industry 5.0 environments, highlighting the role of intelligent automation in human-centric industrial systems.

The eighth article (Contribution 8) analyzes the transition from Industry 4.0 to Industry 5.0 through bibliometric methods, identifying key research trends and thematic developments.

The ninth article (Contribution 9) presents a systematic review of machine learning methods applied to process optimization in laser welding, contributing to advanced manufacturing research.

The tenth article (Contribution 10) provides a systematic review of reinforcement learning in process industries, proposing a taxonomy of applications and future research directions.

Taken together, these contributions demonstrate that AI is being successfully applied across multiple industrial domains, ranging from manufacturing and energy systems to process industries, computer vision, automation, and decision support, illustrating both the technological maturity and multidisciplinary nature of AI-driven Industry 5.0.

3. Conclusions

The contributions presented in this Special Issue demonstrate the growing impact of Artificial Intelligence in industrial systems. The articles cover a wide range of applications, including predictive modelling, reinforcement learning, computer vision, intelligent automation, and systematic analyses of AI methodologies.

These studies highlight the transformation of industrial environments into intelligent, adaptive, and data-driven ecosystems. At the same time, the transition toward Industry 5.0 emphasizes the importance of human-centric design, sustainability, and resilience.

Future research should focus on improving the scalability and robustness of AI models, enhancing explainability and transparency, and strengthening the integration between Artificial Intelligence, cyber–physical systems, and human operators.

These findings reinforce the role of Artificial Intelligence as a cornerstone technology in the transition toward Industry 5.0, enabling the development of sustainable, resilient, and human-centric industrial systems.

Overall, the papers gathered in this Special Issue confirm that Artificial Intelligence is no longer a peripheral technological addition but rather a strategic enabler of next-generation industrial systems. Beyond efficiency and automation, the contributions also highlight the increasing importance of sustainability, resilience, interoperability, and human-centricity as defining principles of Industry 5.0.