Explore the vast range of titles available.

Machining non-circular inner profiles on CNC lathes is challenging due to the lack of built-in interpolation functions. Conventional macro programs using fixed-step approximations often result in inefficient toolpaths with excessive air-cutting. This paper proposes a Genetic Algorithm (GA) approach to globally optimize the toolpath strategy. By discretizing the machining area, the GA evolves an optimal sequence of cutting segments to minimize total machining time and non-productive travel while maintaining profile accuracy. Comparative experiments on an inner elliptical profile demonstrate that the GA-generated path reduces total time and non-productive travel by over 25% compared to traditional strategies, providing a robust framework for efficient, high-precision internal machining.

High-quality and cost-effective production in micro-milling involves the use of tools of diameter 50–800  μ m, at high rotational speeds, along complex tool paths. These tools are susceptible to high wear and unexpected breakage, and hence a high-precision tool condition monitoring system is required to predict the tool wear states. In this work, we propose a novel approach for high-precision tool condition monitoring in micro-milling using cutting force signals. The method correlates dominant frequency variations with the tool condition along its complete life cycle, considering both straight and circular tool paths to mimic real-life machining scenarios. Therefore, using multiple micro-milling experiments, dominant frequency was characterized using Wavelet transform and Short Time Fourier Transform, and a tool condition prognostic model was developed using LSTM networks. The model accurately predicts force signals with an RMSE less than 0.09, enabling indirect prediction of the tool condition.

With the advancement of tool path planning, milling trajectories have evolved beyond straight lines. Since tool path geometry strongly influences milling forces, this study develops a unified prediction model incorporating both tool path radius and cutting width—factors often neglected in previous research. Based on geometric modeling, discretized cutting elements, and oblique cutting theory, the model achieves theoretical computation of milling forces under linear and circular paths. Simulation results show that path radius notably affects the magnitude and direction of milling forces, confirming the model’s accuracy and applicability. The findings provide theoretical guidance for optimizing tool path parameters in complex surface machining.

The cutting tool and leading tool are the primary cutting combinations when the super large diameter shield cutter head is excavated in the soft soil stratum. The cutter size, cutting parameters, and layout relationship will affect the tunneling efficiency of the cutter head. The explicit dynamics are used to simulate the cutting tool, the leading tool, and their combination. The effects of four factors, such as stratum, tool width, cutting depth, and cutting speed, on the cutting force and cutting efficiency of the cutting tool and the leading tool are studied through orthogonal test design. The research results indicate that the main factors affecting the cutting performance of cutting tools are the cutting speed and stratum. Reasonable leading tool layouts can reduce the fluctuation range of cutting force. When the leading tool path coincides with both sides of the cutting tool path, the cutter force can be significantly reduced, and the tool life can be prolonged. The research results can provide a reference for shield cutter group modeling and the layout of the cutting tool and leading tool.

In this study, the effect of four different machining methods consisting of “Trochoidal,” “Follow Part,” “Zig,” and “Zig-Zag” which are common in CAM package programs and used often in the industry has been investigated. Firstly, the 3D model of samples is produced in the CAD program. Models are machined in CNC milling workbench. In order to examine the effect of tool path strategies on tool life, the amount of wear loss as a criterion and the SEM images of tool wear as a supporting criterion are taken into account. According to the results, the “Zig-Zag” tool path strategy is the tool path that causes the highest weight loss in the cutting tool, while the “Trochoidal” tool path strategy causes in the least weight loss in the cutting tool. In addition, the surface roughness of the samples taken from different regions of the model and the operation time of the different tool paths are determined. In this context, the operation time of the test sample is maximum in “Zig” team path strategy, while it is at least in “Follow part” team path strategy. By examining the surface roughness, the best surface roughness values are obtained with the strategy of “Follow Part” and “Trochoidal” tool path, while the worst values are obtained in the “Zig” tool path strategy. As a result of the examination, the optimum tool path strategy for cutting tool life was found to be “Trochoidal” tool path. This work differs from the counterparts as handling the AISI X210Cr12 steel which make the paper first in determining the effect of tool path strategies on machinability. Lastly, obtained findings are useful for the organization of this type of steel in manufacturing chain of industrial companies.

Predicting cutting forces in hard turning optimizes toolpaths, improving machining efficiency and precision, minimizing tool wear, and enhancing manufacturing processes. This study assesses the potential of ensemble machine learning models for predicting machining force components during the hard turning of AISI 52100 bearing steel. Firstly, it conducts a comprehensive evaluation of Random Forest, Gradient Boosting, XGBoost, and CatBoost machine learning models using experimental data collected during AISI 52100 bearing steel turning with a CBN cutting tool. Cubic Spline-based data augmentation is employed to enrich the data, further enhancing prediction quality. A comparative analysis of the considered models on both original and augmented datasets reveals significant performance improvements associated with the utilization of augmented data. Moreover, this study utilizes SHAP (SHapley Additive exPlanations) to elucidate model predictions, providing insights into the contribution of each feature. Results indicate that ensemble learning methods, particularly CatBoost and XGBoost, demonstrate satisfactory predictive results with an averaged R 2 of 0.96 and 0.945, respectively. Ensemble models like CatBoost and XGBoost, coupled with data augmentation, prove effective in predicting cutting forces during hard turning, emphasizing the potential for enhanced machining optimization.

In the aerospace industry, high-precision components like impellers and blisks present considerable challenges in machining due to their intricate geometries and the need for reliable performance. Blades, often classified as thin-walled parts with complex, free-form surfaces, are crucial in ensuring the efficiency and safety of aircraft engines. Their geometries and materials require strict control over cutting parameters, such as tool path and orientation, to avoid deformation and maintain surface integrity. This study investigates the impact of tilt angle variation during ball end milling of Ti6Al4V thin-walled parts. Four different tilt angles (15°, 30°, 45°, and 60°) were analysed to evaluate their effect on dimensional accuracy and surface roughness. The results show that tilt angle significantly influences surface quality and dimensional precision. A tilt angle of 30° achieved the best balance between surface finish and dimensional tolerances, with flatness values ranging from 0.038 mm at 30° to 0.101 mm at 60°, representing a 152.5% increase in flatness. The findings provide practical guidelines for optimizing ball end milling of thin-walled components, emphasizing the importance of tool orientation in reducing deformation and enhancing surface quality.

Carbon-fiber reinforced silicon carbide matrix (C/SiC) composites are typical difficult-to-cut materials due to high hardness and brittleness. Aiming at the problem of the serious tool wear in conventional milling (CM) C/SiC composite process, ultrasonic vibration–assisted milling (UVAM) and conventional milling tests with a diamond-coated milling cutter were conducted. Theoretical and experimental research on the cutting force during the ultrasonic vibration milling process of C/SiC composites is carried out. Based on the kinematics analysis of tool path during ultrasonic vibration milling process, the cutting force model of ultrasonic vibration milling is established, and the influence mechanism of ultrasonic vibration on the cutting force is revealed. Based on the analysis of the evolution law of tool wear profile and wear curve during the traditional milling and ultrasonic vibration milling of C/SiC, the tool wear forms and mechanism of diamond-coated milling cutters in two processing modes and the influence mechanism of ultrasonic vibration on tool wear are revealed. It is found that the main wear mechanism of the diamond-coated milling cutter is abrasive wear, and the main wear form is the coating peeling. Compared with the traditional milling, the tool wear can be reduced by the ultrasonic vibration milling in machining process. In the range of test parameters, the tool wear decreases first and then increases with the increase of ultrasonic amplitude.

Dynamic tool-axis inclination in five-axis CNC milling alters cutting mechanics and may induce harmonic disturbances that cannot be adequately detected using conventional force-magnitude indicators. This study investigates instability during slot milling with continuous inclination transitions of 15, 30, and 45 degrees along 30 mm and 60 mm toolpaths. Multi-axis cutting forces were measured using a tri-axial dynamometer and processed through filtering, window segmentation, and frequency-domain analysis. A Harmonic Amplitude Ratio (HAR) metric is introduced to quantify relative harmonic amplification with respect to the tooth-passing frequency. The results show that although the resultant RMS force decreases with increasing inclination, inclination-dependent harmonic behavior is clearly revealed by HAR. For the 30 mm toolpath, HAR varies between 0.3890 and 0.4597, while for the 60 mm toolpath, HAR increases from 0.4256 to a peak value of 0.6045 at the intermediate inclination angle. These findings demonstrate that force magnitude alone is insufficient for detecting dynamic instability, whereas HAR provides a lightweight, physically interpretable, and sensitive indicator suitable for real-time stability monitoring in multi-axis milling.

With the rapid development of science and technology, five-axis CNC machine tools are widely used in the field of complex surface parts processing and manufacturing, so the part geometry model of the complex surface becomes more and more complex. Most traditional machining methods use fixed cutting parameters to calculate and generate five-axis machining toolpaths. If the fixed cutting parameters are used to generate the 5-axis machining toolpaths, the optimal cutting condition will not be obtained in some parts, and the generated machining toolpaths will be less adaptable. In this paper, the complex surface is partitioned and the cutting parameters are optimally adjusted to different parts of the workpiece during the cutting process to respond to the change in the cutting state.