In recent years, a number of machining centers have been built using linear motors. These machining centers have great potential for precision and high-speed machining. Nevertheless, a number of problems remain unsolved, such as monitoring and control. This paper presents a new tool breakage monitoring method for this type of machining center using the current signal of the linear motor. First, the relationship between the cutting force and the motor current is analyzed. Then, the new tool breakage method is presented. From a mathematical point of view, the new method uses a nonlinear energy operator to capture the abrupt changes of the motor current signal, which is directly related to the tool breakage. The experiment validation is included.

A new method for workpiece error analysis and compensation in turning is introduced. It is known that the workpiece error consists of two parts: machine tool error (including the geometric error and thermal-induced error) and cutting induced error. The geometric error of the machine tool is independent on machining operation and, hence, can be measured o. -line using a

Epileptic seizures prediction is an interesting issue in epileptology, since it can promise a novel approach to control seizures and understand the mechanism of epileptic seizures. In this paper, we describe a new method, called wavelet-based nonlinear similarity index (WNSI), to predict epileptic seizures using EEG recordings in real time. This method combines wavelet techniques and nonlinear dynamics. The test results of EEG recordings of rats and humans show that WNSI can track the hidden dynamical changes of brain electrical activity. Particularly, we found that it can obtain the best performance of seizure prediction at the beta (10–30 Hz) frequency band of EEG signals. A possible reason is suggested from the functional connectivity of the brain. In terms of this study, it is recommended that wavelet technique is very useful to improve the performance of epileptic seizures prediction.

This paper presents a new condition monitoring method based on a latent process model. The method consists of three steps. First, a sensor signal is modeled by a latent process model that is a combination of a time-varying auto-regression model and a dynamic linear model, which decomposes the signal into several components, and each component represents a different part of the monitored system with different time-frequency behavior. Based on the latent process model, important features are extracted. Finally, using the generative topographic mapping, the selected features are mapped to a lower (two)- dimension space for classification. The proposed method is tested in condition monitoring of sheet metal stamping processes. A large number of experiments were conducted. In particular, two cases are presented in detail. From the testing results, it is found that the proposed method is able to detect various defects with a success rate around 98%. This result is significantly better than the conventional artificial neural network method. In addition, the new method is a self-organizing method and hence, little training is necessary. These advantages make the method very attractive for practical applications.

In this paper, an effective algorithm based on improved time-domain averaging is proposed to detect tool flute breakage during end milling using feed-motor current signatures. The algorithm proposed is demonstrated to be effective in detecting tool flute breakage in real time through a series of milling experiments, and is also demonstrated to be insensitive to the effects for transients, such as cutter runout, entry/exit cuts, and noise in the feed-motor current signals. Results indicated that the approach showed excellent potential for practical, on-line application for tool flute breakage detection during end milling.