Papers by Author: Huibo Jia

Abstract: The detection and characterisation of subsurface flaws in nonmetallic materials are very important for people’s health, lives, and environment. Possible damage must be detected early and reliably. A capacitive approach for detecting the subsurface cracks is discussed. A uniplanar capacitive sensor with multi-electrodes for obtaining the corresponding electrical capacitance information of the measured slab is presented. An experimental rig, which is composed of a uniplanar capacitive sensor of 8-electrodes and two engineering plastic samples, has been built for damage detection of nonmetallic material. Principal component analysis is used to extract relevant features from capacitance values for damage detection and identification. The simulated, as well as the preliminary experimental results show that the current approach is capable of detecting subsurface damages of nonmetallic materials and discriminating the flaws. The proposed approach is feasible and effective for damage detection and health monitoring.

Abstract: In case of mechanical system health monitoring, a need to develop normal-knowledge based novelty detection techniques is increasing. The negative selection algorithm, which is inspired from the operation mechanism of human immune system, is one of such approaches. Our approach is to apply the idea for the anomaly detection in the vibration time series of the rotor system. A real-valued negative selection algorithm based on Euclidean distance, as well as cosine similarity, has been implemented. By means of adding the corresponding coverage radius to each antibody elements, the detection efficiency of each antibody element is increased. The detection efficiency is evaluated with simulated data as well as vibration signal sampled from one rotor system. The results indicate that the algorithm can efficiently detect the anomaly in time series data. Moreover, the number of detectors in antibody set is less enough for potential application in online signal monitoring.