Real-time adaptive classification system for intelligent sensing in manufacturing environment A feasibility study

Abstract

The deployment of a sensor node to manage a group of sensors and collate their readings for system health monitoring is gaining popularity within the manufacturing industry. Such a sensor node is able to perform real-time configurations of the individual sensors that are assigned to it. Sensors are capable of acquiring data at different sampling frequencies based on the sensing requirements. The different sampling rates not only affect the power consumption, sensor lifespan, and the resultant network bandwidth usage due to the data transfer incurred. These settings also have an immediate impact on the accuracy of the diagnostics/prognostics models that are employed for system health monitoring. In this paper we propose an adaptive classification system architecture for system health monitoring that is well suited to accommodate and to take advantage of the variable sampling rate of sensors. In this paper, we demonstrate how our proposed system is able to work and control a sensor network with adaptive sampling frequencies. This will in turn yield a more effective health monitoring system with reduced power consumption thereby extending the sensors' lifespan and reducing the resultant network traffic and data logging requirements.