Computer numerical control (CNC) milling is one of the most critical manufacturing processes for metal-cutting applications in different industry sectors. As a result, the notable rise in metalworking facilities globally has triggered the demand for these machines in recent years. Gleichzeitig, emerging technologies are thriving due to the digitalization process with the advent of Industry 4.0. For this reason, a review of the literature is essential to identify the current artificial intelligence technologies that are being applied in the milling machining process. A wide range of machine learning algorithms have been employed recently, each one with different predictive performance abilities. Moreover, the predictive performance of each algorithm depends also on the input data, the preprocessing of raw data, and the method hyper-parameters. Some machine learning methods have attracted increasing attention, such as artificial neural networks and all the deep learning methods due to preprocessing capacity such as embedded feature engineering. In this survey, we also attempted to describe the types of input data (e.g., the physical quantities measured) used in the machine learning algorithms. Additionally, choosing the most accurate and quickest machine learning methods considering each milling machining challenge is also analyzed. Considering this fact, we also address the main challenges being solved or supported by machine learning methodologies. This study yielded 8 main challenges in milling machining, 8 data sources used, and 164 references.

Instantaneous material removal volume (IMRV) is a key parameter for predicting the cutting power, cutting force, and machining process. This paper presents a novel approach, known as the point cloud contour-filling method, for calculating the IMRV for each cutting tool edge at any instantaneous moment. Firstly, the kinematics during milling operations are analyzed to capture the exact motion trajectory envelope point cloud of the cutting tool edge. Secondly, the Z-map algorithm and Boolean operations are utilized to calculate the point cloud of the intersection between the workpiece and tool-edge trajectory envelope within unit time steps Δt (known as the IMRV point cloud). Finally, the 3D alpha method and Delaunay triangulation are employed to calculate the shape and volume of the IMRV. The proposed model considers the real tool-edge trajectory and tool installation errors, and introduces the variable of tool-workpiece engagement time t for the first time. The model is verified using milling tests. The proposed method provides a visualization of instantaneous complex engagement between the tool and workpiece during the milling process and can be further used for simulating milling forces and cutting power.

A large amount of work in the ultrasonic cutting of honeycomb cores is concentrated in the roughing stage, but the existing roughing path planning methods cannot achieve high efficiency machining. To solve this problem, this paper proposes a novel method that utilizes a straight blade for overlapping V-shaped cuttings. The proposed method reduces the number of disc cutter cuts by reducing the residual height, thereby significantly reducing the overall machining time. By establishing a cutting efficiency model for the traditional and proposed methods, we demonstrate the high efficiency of the proposed method. Additionally, methods for generating tool pre-processing paths are provided for planar, inclined, and curved parts. By analyzing the machining characteristics of the overlapping V-shaped process, we propose corresponding post-processing schemes. Subsequently, the analysis results of the pre-processing and post-processing were integrated and compiled, and a dedicated processor for honeycomb core roughing-path planning was developed using Matlab. Cutting research on the three roughing processes was conducted using the simulation software Vericut, which further verified the efficiency of the overlapping V-shaped process quantitatively. Finally, by comparing the machining effects of the simulation and experiment, we proved that the honeycomb core roughing processor developed in this study could satisfy actual machining requirements.

Wire arc additive manufacturing (WAAM) is an economical and efficient technology for manufacturing large metal parts with complex physical states that are difficult to observe in situ. However, in-depth systematic research on the fluid flow state and droplet transition behavior in WAAM under complex paths is lacking. Firstly, the free surface of the molten pool was tracked using the volume-of-fluid (VOF) method. Subsequently, by integrating matrix transformation methods, the dual ellipsoidal heat source was varied over time, and its dynamic effects on the molten pool were studied. Finally, the shapes and sizes of the deposited bead and weld pool were determined. The results showed that the droplets brought heat and kinetic energy to the molten pool and that the kinetic energy of the molten pool was more easily dissipated on complex paths than on straight paths. The impact of droplets on the molten pool, creating a negative pressure, is one of the reasons for the precipitation of gas and the eventual formation of a unique bubble distribution. The primary reason for the tilt of the molten pool in the moving direction was the influence of the liquid tension and arc pressure. The simulated profiles of the deposited bead and droplet transfer are validated using experimental cross-sectional and high-speed camera images. The consistency between the simulation results and the experimental outcomes was good, aiding the precise control of specific requirements in future production.

Compared to meta-aramid honeycombs (MAHs), para-aramid honeycombs (PAHs) exhibit superior mechanical and physical properties and can therefore be used in more demanding environments. However, the excellent properties of PAH also bring great challenges to the traditional machining methods, often resulting in terms of large burrs, delamination, tearing, and cell collapse of the honeycomb, as well as severe tool wear problems. These challenges severely limit the application of the PAH. Therefore, investigating effective machining methods for PAH and optimizing the machining quality by determining the influence laws of the process parameters are crucial. In this paper, series of single factor orthogonal experiments were performed to study the effects of machining parameters on ultrasonic cutting characteristics between PAH and MAH in terms of cutting force, cutting temperature and surface quality by disc cutter. Furthermore, this study compared the microscopic ultrasonic cutting processes of PAH and MAH, analyzed the impact of aramid fiber differences on the honeycomb walls fracture process, and revealed the reasons for the differences in experimental results between PAH and MAH. Results proved that PAH exhibited poorer cutting performance compared to MAH: the cutting force and cutting temperature of PAH were both higher than those of MAH, and the machined surface was rougher. The processed surface damage of PAH predominantly manifests as clusters of long uncut fibers, whereas MAH is mostly short burrs. Increasing the ultrasonic amplitude can reduce the cutting forces for PAH and MAH, with a particularly greater reduction in force for PAH. The present study can be used as basis for comprehensive understanding of the differences in the cutting performance and mechanisms of PAH and MAH and optimization of machining parameters for ultrasonic cutting by disc cutter.

Cutting chatter is a major factor that limits machining efficiency and can negatively impact the quality of a cutting surface. Chatter suppression is crucial for improving machining efficiency and maximizing business benefits. However, most chatter suppression techniques are difficult to use on a massive scale in actual production because of their high cost and limited applicability. In the investigation of chatter suppression, particularly in recent years, unique and effective suppression methods have been developed that must be summarized and arranged, and their advantages and disadvantages must be evaluated in depth. Therefore, this paper summarizes and systematically discusses recent research advancements in chatter suppression methods. Furthermore, future research directions for chatter suppression technologies are predicted.

The combination of wire electro-discharge grinding (WEDG) and a rotary spindle provides an effective means for the online fabrication of microtool electrodes, thus eliminating secondary clamping errors. However, significant wear of the electrodes occurs during the micro-electrical discharge machining (micro-EDM) process, causing rapid degradation of usability. Therefore, for the practical application of micro-EDM in continuous manufacturing processes, it is essential to integrate electrode wear compensation into the spindle feed function. This study proposes a high-precision spindle head with a combined function of rotation and inchworm feed for micro-EDM with WEDG. The spindle head maximizes tool electrode length utilization with a unique arrangement of upper and lower clamps. The separate control of rotational drive and accuracy, as well as the servo feed for machining gap and inchworm compensation, enhanced the electrode’s rotational and feed precision. The measured radial runout is less than 3.9 μm, and the deviation angle of parallelism error equals 0.019°. Utilizing the tangential feed WEDG process, the diameter consistency of the prepared electrodes is less than 2 μm, and the consistency accuracy of electrodes in repeated production is less than 3 μm. Arrayed Φ 65 μm and Φ 40 μm micro-holes with great dimensional consistency are achieved using prepared Φ 55 μm and Φ 30 μm electrodes, respectively. Moreover, electrodes with noncircular cross sections were prepared to machine square and triangular-arrayed micro-holes with high shape and size accuracy. Using the developed servo scanning micro-EDM technology and a layered depth-constrained algorithm, we machined micro-patterns of gears, stars, and special Chinese characters for “Tsinghua University”, as well as arrayed hemispheres, pentagons, and hexagons. The dimensions and shapes are consistent with the design models, with the least cumulative depth errors less than 2 μm and shape errors primarily arise from the inevitable rounded corners due to electrode radius.

High-shear and low-pressure grinding with a body-armor-like grinding wheel is a novel grinding method with great potential for ultraprecision machining of difficult-to-cut materials. However, the material removal rate model for the new grinding process is still lacking. In this study, elastohydrodynamic pressure distribution at the working interface between a body-armor-like grinding wheel and the workpiece was revealed. The microcontact state of the single abrasive grain in the interface was uncovered. The formulas of the forces acting on the rubbing, plowing, and cutting abrasive grain were analyzed. Based on the force model of the single abrasive grain and the Gaussian distribution of the grain protrusion heights, the actual grinding depth of the cut model and specific removal rate model were proposed for the novel high-shear and low-pressure grinding process. The influence of the grinding wheel and processing parameters on the material removal rate was investigated. It was found that the actual cut grinding depth decreased with the increase of the workpiece feed rate while the material removal rate remained almost constant. By comparing with experimental and theoretical results, it was shown that the model could accurately predict the actual grinding depth of cut and specific removal rate under different processing parameters, with a minimum prediction error of 1.5%. The maximum actual grinding depth of cut (i.e., 0.60 μm), was obtained for Inconel 718 workpiece. The findings of this study provide theoretical guidance for the practical application of high-shear and low-pressure grinding.

High-temperature-resistant and chemically stable ceramic materials exhibit great adaptability across numerous industrial applications. Grinding is an essential component of the precision shaping and manufacturing processes for ceramic structural components. However, the low machining efficiency and high machining damage rate caused by hard and brittle material properties have been a challenge in both academia and industry. Grinding force is the most critical parameter reflecting the grinding system, and establishing an accurate prediction model is highly significant in reducing machining damage. However, a knowledge gap remains in the comprehensive review and evaluation of grinding force models for ceramic materials, which is undoubtedly not conducive to further theoretical advances. This review discusses the removal mechanism for polycrystalline ceramic materials. Subsequently, it comprehensively reviews and comparatively evaluates detailed grinding force modeling knowledge. Furthermore, it explores the specificities of the ultrasonic and laser energy-field-assisted grinding of ceramic materials in terms of their physical behavior and mechanical modeling. Finally, the theoretical value of grinding force modeling for predicting the damage to ceramic materials is explored. The current limitations of the grinding process, mechanical modeling of ceramic materials, corresponding potential research directions, and valuable research content are provided. The goal is to derive actionable low-damage grinding guidelines and establish a robust theoretical framework that enhances the quality of grinding processes for ceramics and other hard and brittle solids.