This paper presents a new method for the condition monitoring based on the so-called information maximum (InfoMax). First, the InfoMax concept is employed to build a neural network. The neural network is used for independent component analysis to identify the source (input)that causes malfunctions (output). To demonstrate the new method, two application examples were included. First, tool breakage detection in an end milling process. The monitoring signal is the current of the feed-motor, which is used to detect the change of the cutting force and accordingly, to detect tool breakage. Second, is the monitoring of a water pump. In this example, seven acceleration signals were simultaneously acquired and used to identify the location of the fault (bearing crack). The experiment results indicate that the new method is effective.

Estimating the interaction among neural networks is an interesting issue in neuroscience. Some methods have been proposed to estimate the coupling strength among neural networks; however, few estimations of the coupling direction (information flow) among neural networks have been attempted. It is known that Bayesian estimator is based on a priori knowledge and a probability of event occurrence. In this paper, a new method is proposed to estimate coupling directions among neural networks with conditional mutual information that is estimated by Bayesian estimation. First, this method is applied to analyze the simulated EEG series generated by a nonlinear lumped-parameter model. In comparison with the conditional mutual information with Shannon entropy, it is found that this method is more successful in estimating the coupling direction, and is insensitive to the length of EEG series. Therefore, this method is suitable to analyze a short time series in practice. Second, we demonstrate how this method can be applied to the analysis of human intracranial epileptic electroencephalogram (EEG) recordings, and to indicate the coupling directions among neural networks. Therefore, this method helps to elucidate the epileptic focus localization.

Most practical industrial process data contain contributions at multiple scales in time and frequency. Unfortunately, conventional statistical process control approaches often detect events at only one scale. This paper addresses a new method, called multiscale statistical process monitoring, for tool condition monitoring in a machining process, which integrates discrete wavelet transform (WT) and statistical process control. Firstly, discrete WT is applied to decompose the collected data from the manufacturing system into uncorrelated components. Next, the detection limits are formed for each decomposed component by using Shewhart control charts. A case study, i.e., tool condition monitoring in turning using an acoustic emission signal, demonstrates that the new method is able to detect abnormal events (serious tool wear or breakage) in the machining process.