Mini-term, a novel paradigm for fault detection

Abstract

The present paper shows, for the first time, how mini-terms could replace common sensors for machine fault detection. The system is based on the sub-cycle time monitoring (mini-terms) and how the cycle time variability of machine parts can be used as a deterioration indicator that could describe the dynamic of the failure for the machine parts. The mini-term, by definition, is a sub-cycle time and had only been used to improve production. The most used sensors to perform the maintenance prognosis are vibration, noise, temperature, pressure, flow, etc. These sensors use an abrupt change (Change point) in the measurement as an indicator that something anomalous is happening. The present paper demonstrates that the Change point also affects the cycle time but with some important advantages compared with common sensors, the mini-term is easy and cheap to install. It is cheap because no additional hardware installation is required to measure the sub-cycle time, only the use of the PLC and sensors installed for the automated production process, and it is easy because we only need to code extra timers into the PLC. At the end of the paper is shown the experimental setup to measure mini-terms at Ford plant in Almussafes factory, the so-called Mini-term 4.0 and a summary of the different kinds of pathologies that through the mini-terms we are able to detect until now.