An Improved Principal Component Analysis in the Fault Detection of Multi-sensor System of Mobile Robot

Zhaihe Zhou, Qianyun Zhang, Qingtao Zhao, Ruyi Chen, Qingxi Zeng


To cope with the fault detection in dynamic conditions of inertial components in the mobile robots, an improved principal component analysis (PCA) method was proposed. This work took a five gyroscopes redundancy allocation model to realize the measurement of the attitude. It is hard to distinguish the fault message from dynamic message in dynamic system that results in false alarm and missing inspection, so we firstly used the parity vector to preprocess the measurement data from the sensors. A fault was detected when the preprocessed data was dealt with PCA method. The effectiveness of the improved PCA method introduced in this paper was verified by comparing fault detection capabilities of conventional PCA method under the dynamic conditions of the step fault. The results of the simulation and experimental verification of the method was expected to contribute to the fault detection and improve the accuracy and reliability of the multi-sensors system in dynamic conditions.


Measurement Data Processing; Mobile Robot; Sensor Redundancy; PCA; Parity Vector; Fault Detection

Full Text:


International Journal of Online and Biomedical Engineering (iJOE) – eISSN: 2626-8493
Creative Commons License
Scopus logo Clarivate Analyatics ESCI logo IET Inspec logo DOAJ logo DBLP logo EBSCO logo Ulrich's logo Google Scholar logo MAS logo