Tool wear is critical to quality, productivity, and sustainability in manufacturing processes. Therefore, accurately monitoring and predicting wear is one of the primary goals of smart manufacturing systems. While AI-based approaches have achieved significant success in this area in recent years, issues such as physical inconsistency, limited generalizability, and low interpretability associated with solely data-driven methods have necessitated the development of hybrid approaches. This study systematically examines the literature published between 2020 and 2025 and comprehensively analyzes hybrid AI systems used in tool wear monitoring. Hybrid systems are categorized into four main groups: physics-based hybrids, knowledge-driven hybrids, transfer learning-based hybrids, and heterogeneous model hybrids. This classification holistically evaluates the synergistic effects and performance gains achieved by combining different methods. The findings demonstrate that the combined use of physical models, expert knowledge, and data-driven learning approaches provides significant advantages in terms of both accuracy and explainability. However, challenges such as data shortage, model complexity, and computational cost remain limitations to widespread industrial use of hybrid systems. The study demonstrates that hybrid AI systems represent a new research direction enabling the development of more reliable, transparent, and efficient solutions in smart manufacturing.

In machining processes, cutting tool wear is a critical problem affecting key performance parameters such as surface quality, production time, and cost. High temperatures cause deformation and wear in the tool material and shorten tool life. This reduces production efficiency and negatively affects the sustainability of quality-oriented goals such as zerodefect manufacturing. In this review study, the current literature on the prediction of cutting tool wear in machining processes using thermal imaging and deep learning techniques is analyzed. With advancing manufacturing technologies, unattended machining capability and the proliferation of approaches such as Zero Defect Manufacturing (ZDM), realtime and accurate monitoring of cutting tool conditions is a strategic requirement for production efficiency and quality control. In this context, the possibilities offered by indirect wear detection methods based on temperature data and the applications of deep learning-based models in this field are evaluated. Significant success has been achieved in tool life prediction by processing temperature maps obtained with thermal cameras, thermocouples, and infrared (IR) imaging systems using algorithms such as CNN and ANN. The methods in the literature are discussed comparatively and their advantages and limitations are discussed. This paper systematically reviews the existing approaches in the literature for tool wear monitoring using temperature-based methods and provides a comprehensive review for future research in this area.