Abstract: Arbitrary wave loads are detected and reconstructed by a sensor system based on an inverse mechanism of continuous structure responses. A sensor system comprising a sensing component configured with a sandwich-structured beam of composite materials can generate the structural responses as a moving wave propagates across the beam. In one example, an Arnoldi-Tikhonov algorithm coupled with generalized cross-validation technique can be utilized to determine a regularization parameter that is utilized to compensate for the presence of noise in the wave load and/or the highly ill-posed problems of the inverse matrix that is utilized for wave reconstruction. Further, the Tikhonov algorithm can be utilized to reconstruct wave loads (e.g., at different location on the beam and/or different times) based on the structural response parameters and the regularization parameter. As an example, an image of the determined wave load values can be rendered in three dimensions (3-D) versus time and location.
Type:
Grant
Filed:
January 27, 2014
Date of Patent:
October 4, 2016
Assignee:
ENJOYOR COMPANY LIMITED
Inventors:
Biaobiao Zhang, Hui Wang, Xiaohong Qian, Lihong Xu, Ke Lin Du
Abstract: Arbitrary wave loads are detected and reconstructed by a sensor system based on an inverse mechanism of continuous structure responses. A sensor system comprising a sensing component configured with a sandwich-structured beam of composite materials can generate the structural responses as a moving wave propagates across the beam. In one example, an Arnoldi-Tikhonov algorithm coupled with generalized cross-validation technique can be utilized to determine a regularization parameter that is utilized to compensate for the presence of noise in the wave load and/or the highly ill-posed problems of the inverse matrix that is utilized for wave reconstruction. Further, the Tikhonov algorithm can be utilized to reconstruct wave loads (e.g., at different location on the beam and/or different times) based on the structural response parameters and the regularization parameter. As an example, an image of the determined wave load values can be rendered in three dimensions (3-D) versus time and location.
Type:
Application
Filed:
January 27, 2014
Publication date:
July 30, 2015
Applicant:
ENJOYOR COMPANY LIMITED
Inventors:
Biaobiao Zhang, Hui Wang, Xiaohong Qian, Lihong Xu, Ke Lin Du
Abstract: A system and method that facilitates urban traffic state detection based on support vector machine (SVM) and multilayer perceptron (MLP) classifiers is provided. Moreover, the SVM and MLP classifiers are fused into a cascaded two-tier classifier that improves the accuracy of the traffic state classification. To further improve the accuracy, the cascaded two-tier classifier (e.g., MLP-SVM), a single SVM classifier and a single MLP classifier are fused to determine a final decision for a traffic state. In addition, fusion strategies are employed during training and implementation phases to compensate for data acquisition and classification errors caused by noise and/or outliers.
Type:
Grant
Filed:
October 18, 2012
Date of Patent:
May 19, 2015
Assignee:
Enjoyor Company Limited
Inventors:
Lu-Sha Han, Hui Wang, Hong Peng, Limin Meng, Ke Lin Du
Abstract: A system and method that facilitates urban traffic state detection based on support vector machine (SVM) and multilayer perceptron (MLP) classifiers is provided. Moreover, the SVM and MLP classifiers are fused into a cascaded two-tier classifier that improves the accuracy of the traffic state classification. To further improve the accuracy, the cascaded two-tier classifier (e.g., MLP-SVM), a single SVM classifier and a single MLP classifier are fused to determine a final decision for a traffic state. In addition, fusion strategies are employed during training and implementation phases to compensate for data acquisition and classification errors caused by noise and/or outliers.
Type:
Application
Filed:
October 18, 2012
Publication date:
April 24, 2014
Applicant:
ENJOYOR COMPANY LIMITED
Inventors:
Lu-Sha Han, Hui Wang, Hong Peng, Limin Meng, Ke Lin Du