Search

Accurate identification of the tool wear states in machining of titanium alloys continues to be a thorny problem. Rapid construction of accurate and effective tool wear predictive models with regard to various titanium alloys is indispensable for promoting the development of intelligent manufacturing. This article presents a novel WOA-SVM model that integrates support vector machine (SVM) and whale optimization algorithm (WOA), which is utilized for accurate estimation of the tool wear in end milling of titanium alloy Ti-6Al-4V under variable cutting conditions. The signal features in three domains are extracted from the original cutting forces and constitute the “complete features” that are adopted as the monitoring features. Besides, neighborhood preserving embedding (NPE) is utilized to fuse the monitoring features and realize dimension reduction, which aims at improving the modeling efficiency of the novel WOA-SVM model. The experimental results show that under the premise of guaranteeing prediction accuracy, the utilization of NPE reduces the modeling time-consumption of WOA-SVM by more than 90%. In comparison with the commonly used methods (such as PSO-SVM and GSA-SVM), WOA-SVM takes on comparable prediction accuracy and can reduce the modeling time-consumption by more than 30% in most cases. Moreover, the WOA-SVM model has better prediction accuracy and stability than other classical methods, such as ${k}$ -nearest neighbor ($k$ -NN), feedforward neural network (FFNN), linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), and classification and regression tree (CART). Therefore, the combination of NPE and WOA-SVM provides a guarantee for rapidly constructing accurate tool wear predictive models in machining of titanium alloys. [ABSTRACT FROM AUTHOR]

The computer numerical control (CNC) equipment is playing essential role in production and manufacturing, thus, its reliability estimation is crucial for industrial systems. Existing research studies mainly focused on univariate degradation data or multiple correlated data, which might not be accurate in equipment reliability assessment. In real CNC equipment, the degradation data consists of correlated and non-correlated degradation data and the data sample might be scarce, which bring great challenges for maintenance managers to assess risk and prevent failure ahead of fault occurrence. This paper proposes a reliability assessment approach based on multiple non-correlated and correlated degradation data with focusing on small size of data sample. Using the multiple degradation data of CNC equipment, a covariance matrix is built to determine the correlation between the performance signals. If the performance signals are not correlated, the degradation trajectory of the performance signals is curve fitted by least squares support vector machines (LS-SVM). The reliability which indicates the degradation curve not reaching its specified threshold is calculated. If the performance signals are correlated, according to the degradation data, the degradation curve of the performance signal is fitted by multivariate regression using LS-SVM, and the joint probability density function is derived. According to both the reliabilities of non-correlated degradation data and correlated degradation data, the joint reliability of the system is calculated. Finally, using a specific type of CNC machine tool as an example, the performance reliability assessment method is verified. [ABSTRACT FROM AUTHOR]