Health assessment and life prediction of cutting tools based on support vector regression

Abstract

The integrity of machining tools is important to maintain a high level of surface quality. The wear of the tool can lead to poor surface quality of the workpiece and even to damage of the machine. Furthermore, in some applications such as aeronautics and precision engineering, it is preferable to change the tool earlier rather than to loose the workpiece because of its high price compared to the tool's one. Thus, to maintain a high quality of the manufactured pieces, it is necessary to assess and predict the level of wear of the cutting tool. This can be done by using condition monitoring and prognostics. The aim is then to estimate and predict the amount of wear and calculate the remaining useful life of the cutting tool. This paper presents a method for tool condition assessment and life prediction. The method is based on nonlinear feature reduction and support vector regression. The number of original features extracted from the monitoring signals is first reduced. These features are then used to learn nonlinear regression models to estimate and predict the level of wear. The method is applied on experimental data taken from a set of cuttings and simulation results are given. These results show that the proposed method is suitable for assessing the wear evolution of the cutting tools and predicting their remaining useful life. This information can then be used by the operators to take appropriate maintenance actions.

Parameter Selection Method for Support Vector Regression Based on Adaptive Fusion of the Mixed Kernel Function

“…It also ensures that it will not cause an overlearning phenomenon because of good generalization ability of unknown samples [31].…”

SVM hyperparameters tuning for recursive multi-step-ahead prediction

“…(3)(4)(5)(6)(7)(8) can be used separately as objectives of single-objective optimization or jointly with other model-characteristics-related objectives for tuning hyperparameters in a bi-objective optimization framework. One widely used model-characteristics-related objective is the model complexity of SVM, which describes the complexity (or simplicity) of the model.…”

“…The inputs are features extracted from measurements directly or indirectly related to the prediction of interest. SVM has been used for example in Müller et al [30], Min and Lee [29], Asefa et al [3], Widodo et al [44], Zio and Di Maio [50], Benkedjouh et al [8], Liu et al [28], Namdari and Jazayeri-Rad [31]. Multi-step-ahead prediction, e.g., to compute the remaining useful life, i.e., the time at which the component degradation state reaches a predefined failure threshold, has been done for example in Asefa et al [3], Lin et al [26], Sorjamaa et al [38], Sapankevych and Sankar [36], Nuhic et al [32], Benkedjouh et al [7], Bao et al [5].…”

Prediction of industrial equipment Remaining Useful Life by fuzzy similarity and belief function theory

“…Examples of modeling techniques used in degradation-based approaches are Auto-Regressive models (Benkedjouh et al, 2013;Gorjian et al, 2009), multivariate adaptive regression splines (Lee et al, 2006), Relevance Vector Machines (Nystad, 2009;Di Maio et al, 2012) and Gaussian Processes (Rasmussen, 2006;Baraldi et al, 2013a).…”