Explore the vast range of titles available.

Currently, SiC particle–reinforced aluminum matrix (SiCp/Al) materials are extensively utilized in industries. However, during the cutting process, the extrusion of the cutting tool onto the materials induces a significant stress concentration phenomenon, subsequently increasing tearing of the Al matrix as well as pull-out and fracture of the SiC particles. These phenomena can lead to severe cutting tool wear. Nanosecond pulsed laser–assisted cutting has been chosen for 45% volume fraction SiCp/Al to improve the cutting tool wear. The cutting simulation and experiments are used to analyze the types of cutting tool wear. The adjustment of pulsed laser power (0–50 W) and pulse width (0–100 ns) can effectively mitigate the cutting tool wear by inducing a thermal softening effect. The simulation and experimental results demonstrate that the utilization of the pulsed laser enhances the plastic deformation of the Al matrix and mitigates the fracture of the SiC particles, thereby potentially reducing abrasive wear on the cutting tools. The increase in pulse width and pulsed laser frequency may result in enhanced adhesive wear on the rake surface under elevated temperature conditions. Therefore, by adjusting the pulsed laser parameters, the interaction between the cutting tool and Al matrix as well as SiC particles can be improved during the cutting process, thereby reducing the cutting tool wear.

In conventional machining, one of the main tasks is to ensure that the required dimensional accuracy and the desired surface quality of a part or product meet the customer needs. The successful accomplishment of these parameters in milling, turning, milling, drilling, grinding and other conventional machining operations directly depends on the current level of tool wear and cutting edge conditions. One of the proven non-contact methods of tool condition monitoring (TCM) is measuring systems based on image processing technologies that allow assessing the current state of the machined surface and the quantitative indicators of tool wear. This review article discusses image processing for tool monitoring in the conventional machining domain. For the first time, a comprehensive review of the application of image processing techniques for tool condition monitoring in conventional machining processes is provided for both direct and indirect measurement methods. Here we consider both applications of image processing in conventional machining processes, for the analysis of the tool cutting edge and for the control of surface images after machining. It also discusses the predominance, limitations and perspectives on the application of imaging systems as a tool for controlling machining processes. The perspectives and trends in the development of image processing in Industry 4.0, namely artificial intelligence, smart manufacturing, the internet of things and big data, were also elaborated and analysed.

An effective strategy to predict the remaining useful life (RUL) of a cutting tool could maximise tool utilisation, optimise machining cost, and improve machining quality. In this paper, a novel approach, which is enabled by a hybrid CNN-LSTM (convolutional neural network-long short-term memory network) model with an embedded transfer learning mechanism, is designed for predicting the RUL of a cutting tool. The innovative characteristics of the approach are that the volume of datasets required for training the deep learning model for a cutting tool is alleviated by introducing the transfer learning mechanism, and the hybrid CNN-LSTM model is designed to improve the accuracy of the prediction. In specific, this approach, which takes multimodal data of a cutting tool as input, leverages a pre-trained ResNet-18 CNN model to extract features from visual inspection images of the cutting tool, the maximum mean discrepancy (MMD)-based transfer learning to adapt the trained model to the cutting tool, and a LSTM model to conduct the RUL prediction based on the image features aggregated with machining process parameters (MPPs). The performance of the approach is evaluated in terms of the root mean square error (RMS) and the mean absolute error (MAE). The results indicate the suitability of the approach for accurate wear and RUL prediction of cutting tools, enabling adaptive prognostics and health management (PHM) on cutting tools.

In the present research, three typical cutting tool wear mechanisms (abrasive wear, adhesive wear, and diffusive wear) were taken into consideration in the FE simulation of cutting tool with a specific user-defined subroutine. Based on the influence of temperature on the cutting tool wear form, a novel wear rate model was built integrating Usui, Takeyama, and Attanasio wear rate equation. The high-speed cutting tests were carried out on Ti6Al4V to determine the proposed wear rate model constant. The cutting forces and rack face wear morphologies obtained from FE simulation match well with those from experimental cutting tests. Finally, the effect of cutting parameters on tool wear was studied by FEM. The simulation results show that the impact of the cutting speed on the cutting tool life is more significant than that of feed rate, and the preferred ranges of cutting speed and feed rate for extending cemented carbide cutting tool in high-speed dry cutting Ti6Al4V are 90–150 m/min and 0.10–0.20 mm/r, respectively.

The main objective of this article is to perform the turning operation on an EN36B steel work-billet with a tungsten carbide tool, to study the optimal cutting parameters and carry out an analysis of flank-wear. Experimental and simulation-based research methodology was opted in this study. Experimental results were obtained from the lab setup, and optimisation of parameters was performed using RSM (response surface methodology). Using RSM, cutting-tool flank-wear was optimised, and the cutting parameters which affect the flank wear were determined. In results main effect plot, contour plot, the surface plot for flank-wear and forces (Fx, Fy and Fz) were successfully obtained. It was concluded that tool flank-wear is affected by depth of cut, and that flank-wear generally increases linearly with increasing cutting-speed, depth of cut and feed-rate. To validate the obtained results, predicated and measured values were plotted and were in very close agreement, having an accuracy level of 96.33% to 98.92%.

Accurately predicting tool wear is essential for maintaining high machining quality. Currently, deep learning models are extensively utilized in predicting tool wear. However, purely data-driven deep learning models are prone to local optima, and the limited tool wear sample data along with multi-sensor feature fusion also limit the models’ ability to generalize and extract valid information. To solve the above problems, a semi-supervised milling cutter wear prediction method based on the empirical formula for cutting force wear is proposed in this paper, with the model (IRM-CFAM) consisting of an Inception-ResNet module (IRM) and a channel feature adaptation module (CFAM). By introducing an empirical formula for cutting force wear, the cutting forces in the unlabeled samples are input to estimate wear values and construct wear curves. Based on the constructed wear curves, a monotonic loss function guided by an empirical curve of milling cutter wear is proposed. Meanwhile, the estimated wear values are combined with unlabeled samples to form a second data source, which is then merged with the labeled samples to expand the dataset. The constructed CFAM consists of channel attention and cross-attention mechanisms, which achieves adaptive fusion of weights. Following validation on the PHM2010 milling cutter dataset, the proposed method attained average RMSE and MAE values of 6.693 and 5.136, respectively, across three test sets, showing a significant advantage over other methods. This research facilitates the accurate prediction of milling cutter wear and introduces a novel approach for expanding sample data.

The heat generated during the machining of titanium alloys accumulates in the cutting area during machining. These high temperatures lead to tool wear, affect the quality of the machined surface, and alter the cutting force. In light of this, a new method for mixing vegetable oil additives is proposed herein, through the addition of graphene nanoparticles and sulfur-based extreme pressure (EP) additives to canola oil to improve the lubrication and cooling performance of the machining area. The optimum results were found for the combination of canola oil + graphene + sulfur-based EP additives, which effectively decreased the temperature of the cutting area and wear of cutting tools. In comparison to canola oil, the flank wear value decreased by 56.4%. Similarly, the surface roughness and cutting force when using the canola oil + graphene + sulfur-based EP additive were the lowest, exhibiting a decrease of 36.1% and 27.0%, respectively, in comparison to simple canola oil. The inorganic film produced by the EP additive molecule helps prevent direct contact between the tool and the workpiece, reducing tool wear and improving surface quality. Furthermore, adhered chips were also observed, with a layered morphology. Graphene shortens the length of the chip-adhesion layer (0.081 mm) and reduces adhesion wear. Elemental testing confirmed that graphene penetrates more easily into the manufacturing area, which is beneficial to reducing abrasive wear and the cutting force. In addition, the higher thermal conductivity of graphene will effectively reduce the temperature of the cutting area, which impedes the agglomeration of these chips. This weakens the adhesion of the chips to the surface of the workpiece.

In this study, the correlation between chip surface chromaticity and wear of cutting tools is established through experiments, and a system for judging and predicting tool wear by observing chip color is proposed. At present, the life prediction of cutting tools is indirectly measured and predicted by using vibration and current. In this study, chip color change is used to predict tool wear, and back-propagation Artificial Neural Networks (ANN) is used to predict and verify. The average error percentage between the predicted value and the actual value of tool wear is only 1.73% and 1.66%, respectively, which was confirmed by cutting test and verification experiments. This study uses Taylor’s tool life model and chip color to analyze, and after repeated tests and experimental analysis, the average error of repeatability is 4.5%. In the verification of stainless steel cutting hard-cutting materials, the equipment accuracy is between 0.5 and 3.0 color difference values of grade 2 to 3. Therefore, the measurement and model establishment of the system can accurately and quickly predict tool wear. In prediction experiment and analysis, the back neural network is used for test, the maximum error ranges are 0.0012 mm and 0.0097 mm, the mean error percentages are only 1.73% and 1.66%.

Cutting tools are one type of critical component of modern computer numerical control (CNC) machining systems. They wear out continuously during the machining process until they fail, and cutting tool failure can lead to the collapse of the entire system and even cause substantial losses. Therefore, it is of great importance to study the method for tool wear prediction. A new model for wear prediction of cutting tools is established based on a multi-stage Wiener process, where the degradation rates of cutting tools are considered to change in three stages based on the typical cutting tool wear curve model. Firstly, the degradation processes of cutting tools are divided into three stages. Secondly, the parameter estimation for each stage of the degradation processes of cutting tools is completed, respectively, by utilizing the EM (expectation–maximization) algorithm. Then, the wear of cutting tools is predicted, and the reliability of cutting tools is analyzed by using a numerical integration simulation method based on the Monte Carlo algorithm. Finally, the proposed model is illustrated and verified via the flank wear data of cutting tools, and the prediction accuracy is measured by mean squared error (MSE) and the coefficient of determination (R2). The prediction results show that the proposed model enables us to make more economical maintenance by delaying the tool replacement time with fewer degradation data. Compared to the traditional methods based on machine learning (ML), the proposed model can complete the wear prediction and reliability analysis more accurately.

This article focuses on turning superalloy Udimet 720, which is difficult to work with, using different coolant/lubricant methods. The study includes delivering Graphene and Multi-Walled Carbon Nanotubes nanopowders homogeneously dispersed in vegetable oil to the cutting area with the minimum quantity lubrication (MQL) method. Experiments at different cutting speeds and feed rates were repeated in four different cutting environments. Compared to dry turning, the cutting zone temperature of the cutting fluid delivered to the cutting zone by MQL methods decreased. In addition, thanks to the nanopowders, it formed an oil film by better penetrating the cutting tool-chip interface and reducing the cutting tool’s wear. With the reduced cutting tool wear, the cutting tool could maintain its form for a longer period of time, so better quality surfaces were obtained on the workpiece surface. As a result of the study, it was found that cutting zone temperature improved by 30%, tool wear by 51.8% and surface roughness by 43.9%.