Papers by Author: Wei Min Chen

Abstract: Bridge plays an important role in modern transportation. Once it is damaged, there will be great loss. So assessment of bridge state has become more and more important in modern society. Ambient around bridge always are very complex and bridge is affected by many factors. So in all response of bridge, noise and useful signals mixed together. The noise generally includes temperature effect, wind load effect, live-load effect, and so on. In order to get the useful signals we must separate the live-load effect from the total effect by using multi-scale analysis firstly. EMD brought a new method for multi-scale analysis and it is superior to wavelet to some extent. But it has some shortcomings also. In order to improve the performance of the EMD further, EEMD is introduced to extract live-load effect of bridge. The practical and simulation results verified the feasibility of the new method based on EEMD and the results is much better than those based on wavelet.

Abstract: This paper focuses on the problem of detecting sensor faults in feedback control systems with multistage RBF neural network ensemble-based estimators. The sensor fault detection framework is introduced. The modeling process of the estimator is presented. Fault detection is accomplished by evaluating residuals, which are the differences between the actual values of sensor outputs and the estimated values. The particular feature of the fault detection approach is using the data sequences of multi-sensor readings and controller outputs to establish the bank of estimators and fault-sensitive detectors. A detectability study has also been done with the additive type of sensor faults. The effectiveness of the proposed approach is demonstrated by means of three tank system experiment results.