Publications by authors named "Rongwu Xu"
Impact Load Localization Based on Multi-Scale Feature Fusion Convolutional Neural Network.
Sensors (Basel)
September 2024
Article Synopsis
- The paper presents a new method called multi-scale feature fusion convolutional neural network (MSFF-CNN) to accurately locate impact loads in complex structures like ships using raw vibration signals.
- It utilizes an end-to-end machine learning approach that eliminates the need for manual feature extraction by learning features automatically through multiple convolutional layers with varying kernel sizes.
- The MSFF-CNN method achieved a high accuracy of 94.29% for classification and localization of impact loads, surpassing traditional CNN approaches, and shows promise for practical engineering applications.
Article Synopsis
- This paper introduces a new method for locating impacts in large, complex cylindrical structures without needing specific prior knowledge about the structure or wave velocities.
- The method utilizes techniques like energy power filtering and wavelet packet decomposition to enhance the detection of Lamb wave signals, followed by time-reversal amplification to improve signal recognition.
- Experimental results show that this method achieves a low average error in locating impacts, even under challenging conditions, outperforming traditional triangulation methods.
GACEM: Genetic Algorithm Based Classifier Ensemble in a Multi-sensor System.
Sensors (Basel)
October 2008
Multi-sensor systems (MSS) have been increasingly applied in pattern classification while searching for the optimal classification framework is still an open problem. The development of the classifier ensemble seems to provide a promising solution. The classifier ensemble is a learning paradigm where many classifiers are jointly used to solve a problem, which has been proven an effective method for enhancing the classification ability.
View Article and Find Full Text PDF