Predictive maintenance (PdM) in CNC machine tools has gained significant attention due to its potential to reduce downtime and increase operational efficiency. This paper explores automated diagnostic techniques used in predictive maintenance for CNC machines, focusing on fault detection, prognosis, and decision-making processes. With the advent of Industry 4.0, intelligent sensors and data analytics have revolutionized machine monitoring, enabling the prediction of failures before they occur. The integration of real-time monitoring systems, vibration analysis, acoustic emission monitoring, and machine learning algorithms has proven effective in diagnosing potential failures. This paper provides an in-depth review of various approaches to automated diagnostics, highlighting the advancements in machine learning models, artificial intelligence (AI), and the Internet of Things (IoT) technologies in enhancing PdM. The research also examines the challenges associated with implementing PdM systems, such as data acquisition complexities, sensor calibration, and computational costs. Through case studies and application examples, the paper discusses how these diagnostic systems can optimize maintenance schedules, minimize machine downtime, and improve overall productivity. The objective of this research is to provide a comprehensive understanding of automated diagnostic methods and their role in predictive maintenance systems for CNC machine tools. The hypothesis posits that the application of advanced diagnostic techniques using AI and IoT will lead to a significant reduction in unplanned downtime and maintenance costs. The findings suggest that the continued development of predictive maintenance systems can lead to improved reliability and lifespan of CNC machines, benefiting industries where precision and continuous operation are critical.

In this paper, a method is proposed to provide the localization of bearing contact in the meshing of circular worm drive by machining the teeth of circular worm gear more convex than the standard. The effect of five variables affecting the tooth shape of the circular worm gear, namely tool diameter and setting angle, tool screw parameter, tool arc profile radius and pressure angle, was analyzed, and the results obtained that the crowning in circular worm drive could not be achieved by one way of increasing tool diameter, such as ZI worm drive or ZN worm drive. It is also analytically proved that the reasonably correct modification of these five parameters can localize the bearing contact so that the contact on the tooth surface of the worm wheel is carried out on the exit side where the meshing with the arc worm ends. Then, according to the analysis results, the flyblade was manufactured, the circular worm gear was machined, and the effectiveness of the proposed crowning method was demonstrated by performing meshing experiments with the circular worm.

Tool failure is a critical issue in lathe machining operations, often leading to unplanned downtime, compromised surface finish, and increased production costs. This study aims to develop an efficient and accurate tool failure prediction model based on vibration signal processing techniques, addressing the growing need for real-time predictive maintenance in modern manufacturing. The primary objective is to analyze the correlation between vibration signal features and different stages of tool wear, and to utilize this information for machine learning-based classification of tool health conditions. Vibration signals were captured from a CNC lathe using a high-frequency accelerometer under varying machining conditions. These signals were preprocessed to remove noise and segmented for analysis. Feature extraction focused on both time-domain (RMS, Kurtosis) and frequency-domain (Spectral Energy) parameters. Statistical validation through one-way ANOVA confirmed significant differences across tool states-Healthy, Worn, and Failed-for all three features, with p-values well below 0.0001. Visualizations using boxplots further demonstrated the non-overlapping distribution of these features among different tool conditions, reinforcing their discriminative power. Supervised learning models including Random Forest, SVM, ANN, and KNN were trained on the extracted features. Random Forest achieved the highest classification accuracy of 95.8%, followed by SVM and ANN. These results validate the practical applicability of vibration-based signal features in detecting tool degradation. The study also compared the outcomes with existing literature, finding strong alignment with previous works on tool wear monitoring. The conclusion emphasizes the model’s relevance for predictive maintenance, recommending its integration into industrial CNC systems to reduce downtime and optimize tool utilization. The proposed model not only contributes to smart manufacturing practices but also offers a scalable approach to condition monitoring for precision machining environments.