Data cleansing for energy-saving: a case of Cyber-Physical Machine Tools health monitoring system

Abstract

Cyber-Physical Production Systems (CPPS) often use wireless sensor networks (WSNs) for monitoring purposes. However, data from WSNs may be inaccurate and unreliable due to power exhaustion, noise and other issues. In order to achieve a reliable and accurate data acquisition while ensuring low energy consumption and long lifetime of WSNs, data cleansing algorithms for energy-saving are proposed in this research. The cleansing algorithms are computationally lightweight in local sensors and energy-efficient due to low energy consumption in communications. Dynamic voltage scaling and dynamic power management are adopted for reducing energy consumption, without compromising the performance at system level. A low-power protocol for sink node communication is proposed at network level. A health monitoring system for a Cyber-Physical Machine Tool (a typical example of CPPS) is designed. Experiment results show that the proposed energy-saving data cleansing algorithm yields high-performance and effective monitoring.