Application of Array Pressure Sensor in Roller Fault Detection

Abstract

In order to diagnose the fault of roller group, we have designed an array pressure sensor and a scan circuit with weak crosstalk of the column signal for collecting pressure distribution data. Furthermore, these data are processed via both the probabilistic neural network (PNN) fault diagnosis model and the back propagation (BP) neural network fault diagnosis model. Experimental results reveal that the PNN fault diagnosis model has more accuracy and shorter period of constructing and training model than BP fault diagnosis model. Our research opens up a new way for roller fault detection from via indirect information (such as sound, vibration and other signals) to via direct digitization pressure image. This method reduces the interference of environmental noise on fault detection. It is more accurate, intuitive, and potential for the applications in all kinds of mechanical fault detection.

Real time defect detection during composite layup via Tactile Shape Sensing

“…There are a wide range of devices that can detect pressure or force, but crucially cannot detect three-dimensional shape. Many of these use pressure sensitive films [15,16], or pressure sensors embedded into a rubber matrix [10]. In the case of defects occurring during composites layup, the vast majority will manifest as a 3D shape, such as a wrinkle, a bridge across a concave corner or a foreign object trapped in the layup [1].…”