Data-driven Health Evaluation of Multifunctional Self-validating Sensor Using Health Reliability Degree

摘要

Aiming at the desired status self-validation of traditional multifunctional sensor, a novel multifunctional self-validating sensor functional model is proposed to improve the measurement reliability. Detailed self-validating functions are presented, especially the proposed health evaluation emphasized in this study. Being different from traditional fault diagnosis, it is improved from a quantitative perspective, in which a novel conception Health Reliability Degree (HRD) is defined to indicate the level. The HRD methodology is implemented by using the grey theory coupled with neural network-based multiple data fusion. The information entropy method is employed to obtain the weights distribution of each sensitive unit to indicate the distinct importance. A health evaluation experimental system of multifunctional self-validating sensor was designed to produce the actual samples and further verify the proposed methodology. Experimental results demonstrate that the proposed strategy could be used to indicate the health level quantitatively and provide a good solution to the health evaluation of multifunctional self-validating sensor.