Utilization of information maximum for condition monitoring in a machining process and a water pump

Research output: Contribution to journalArticle


Colleges, School and Institutes


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.


Original languageEnglish
Pages (from-to)711-714
Number of pages4
JournalIEEE/ASME Transactions on Mechatronics
Issue number4
Publication statusPublished - 1 Jan 2004