Tool Wear Prediction Based on Artificial Neural Network during Aluminum Matrix Composite Milling

A Novel Piecewise Cubic Hermite Interpolating Polynomial-Enhanced Convolutional Gated Recurrent Method under Multiple Sensor Feature Fusion for Tool Wear Prediction

The monitoring of the lifetime of cutting tools often faces problems such as life data loss, drift, and distortion. The prediction of the lifetime in this situation is greatly compromised with respect to the accuracy. The recent rise of deep learning, such as Gated Recurrent Unit Units (GRUs), Hidden Markov Models (HMMs), Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Attention networks, and Transformers, has dramatically improved the data problems in tool lifetime prediction, substantially enhancing the accuracy of tool wear prediction. In this paper, we introduce a novel approach known as PCHIP-Enhanced ConvGRU (PECG), which leverages multiple-feature fusion for tool wear prediction. When compared to traditional models such as CNNs, the CNN Block, and GRUs, our method consistently outperformed them across all key performance metrics, with a primary focus on the accuracy. PECG addresses the challenge of missing tool wear measurement data in relation to sensor data. By employing PCHIP interpolation to fill in the gaps in the wear values, we have developed a model that combines the strengths of both CNNs and GRUs with data augmentation. The experimental results demonstrate that our proposed method achieved an exceptional relative accuracy of 0.8522, while also exhibiting a Pearson's Correlation Coefficient (PCC) exceeding 0.95. This innovative approach not only predicts tool wear with remarkable precision, but also offers enhanced stability.

Monitoring of Cutting Process and Tool Condition of Metal and Metal Composite

Machining is a manufacturing process that involves the use of machines to remove materials from a workpiece to create a desired shape and size [...].

Unsupervised Tool Wear Monitoring in the Corner Milling of a Titanium Alloy Based on a Cutting Condition-Independent Method

Real-time tool condition monitoring (TCM) for corner milling often poses significant challenges. On one hand, corner milling requires configuring complex milling paths, leading to the failure of conventional feature extraction methods to characterize tool conditions. On the other hand, it is costly to obtain sufficient test data on corner milling for most of the current pattern recognition methods, which are based on the supervised method. In this work, we propose a time-frequency intrinsic feature extraction strategy of acoustic emission signal (AEs) to construct a cutting condition-independent method for tool wear monitoring. The proposed new feature-extraction strategy is used to obtain the tool wear conditions through the intrinsic information of the time-frequency image of AEs. In addition, an unsupervised tool condition recognition framework, including the unsupervised feature selection, the clustering based on adjacent grids searching (CAGS) and the density factor based on CAGS, is proposed to determine the relationship between tool wear values and AE features. To test the effectiveness of the monitoring system, the experiment is conducted through the corner milling of a titanium alloy workpiece. Five metrics, PUR, CSM, NMI, CluCE and ClaCE, are used to evaluate the effectiveness of the recognition results. Compared with the state-of-the-art supervised methods, our method provides commensurate monitoring effectiveness but requires much fewer test data to build the model, which greatly reduces the operating cost of the TCM system.

Prediction of abrasive wears behavior of dental composites using an artificial neural network

Resin composites are widely used as dental restorative materials since dental parts are subjected to prolonged wear and ultimately need to be replaced. The objective of this study is to analyze the potential of the feed-forward back propagation artificial neural network (ANN) in assessing the wear of dental composite materials when immersed in chewable tobacco solution, by utilizing the in-vitro test results of the pin-on-disc tribometer [ASTM G99-04]. In this study, four different dental composite material specimens are dipped in a chewable tobacco solution for a few days, and the specimens are removed from the solution for conducting the wear test. Three different training procedures are used to simulate ANN models for predicting the wear of dental composite specimens. The Bayesian regularization training algorithm outperforms the other algorithms significantly. The findings of the ANN modeling were prominently matching with the results of the experiments; therefore, parametric analysis was used based on the model's predicted values.

Numerical Simulation and Experimental Study on Compound Casting of Layered Aluminum Matrix Composite Brake Drum

The requirements of high-strength, wear-resistance and lightweight of brake drums have been continually increasing in recent years and any specific aluminum alloy or particle-reinforced aluminum matrix composites may not satisfy all the demands. Combining dissimilar materials to play their respective advantages is a solution to this problem. In this study, a compound casting method was used to combine solid SiC_p/A357 composite and a liquid 7050 aluminum alloy to prepare an aluminum matrix composite with a layered structure. The ProCAST numerical simulation software was used to predict the heat transfer in compound casting process and guide the preheating temperature of the wear-resistant ring in the experiment. An Optical Microscope (OM) and Scanning Electron Microscope (SEM) were used to observe microstructures around the solid–liquid bonding interface, the element distribution and phase component of which were analyzed by Energy Dispersive Spectroscopy (EDS) and mechanical properties were evaluated by microhardness and shear tests. The results showed that the interface of the layered aluminum matrix composite prepared by this method achieved complete metallurgical bonding and a transition zone formed on the solid surface. After T6 heat treatment, the average shear strength of the interface increased from 19.8 MPa to 33.8 MPa.

Influence of Microstructure and Chemical Composition on Microhardness and Wear Properties of Laser Borided Monel 400

In this study, wear properties of Monel 400 after laser alloying with boron are described. Surfaces were prepared by covering them with boron paste layers of two different thicknesses (100 µm and 200 μm) and re-melting using diode laser. Laser beam power density was equal to 178.3 kW/cm². Two laser beam scanning velocities were chosen for the process: 5 m/min and 50 m/min. Surfaces alloyed with boron were investigated in terms of wear resistance, and the surface of untreated Monel 400 was examined for comparison. Wear tests were performed using counterspecimen made from steel 100Cr6 and water as a lubricant. Both quantitative and qualitative analysis of surfaces after wear test are described in this paper. Additionally, microstructures and properties of obtained laser alloyed surfaces are presented. It was found that the wear resistance increased from four to tens of times, depending on parameters of the laser boriding process. The wear mechanism was mainly adhesive for surfaces alloyed with initial boron layer 100 µm thick and evolves to abrasive with increasing boron content and laser beam scanning velocity. Iron particles detached from counterspecimens were detected on each borided surface after the wear test, and it was found that the harder the surface the less built-ups are present. Moreover, adhered iron particles oxidized during the wear test.