Research on online non-intrusive load identification system based on multi-threaded CUSUM-MLP algorithm

Author(s):  
Hang Zhao ◽  
Guangfen Wei ◽  
Chunhua Hu ◽  
Qian Liu
2015 ◽  
Vol 4 (5) ◽  
pp. 367-370 ◽  
Author(s):  
M. Felgueiras ◽  
◽  
N. Cruz ◽  
F. Martins ◽  
R. Martins

2012 ◽  
Vol 204-208 ◽  
pp. 1247-1254
Author(s):  
Guang Yang ◽  
Wei Zhen Chen ◽  
Jun Xu

In China recent accidents of sudden collapses of in-service bridges have aroused great concern about the real traffic load and bearing capacity of existing bridges. The proper management of existing bridges relies on accurate information of bridge operating load which is essential for correct assessment of operation and safety of bridges. An integrated load identification system for operating traffic which is built on characteristics of orthotropic steel deck, that is, the locality of stress influence line of orthotropic steel deck, and is based upon BWIM technique to establish functional relation between axle load and stress history, Case study of stress monitoring was carried out on two truss bridges with orthotropic steel deck under both controlled and normal traffic conditions to verify the system. In the case of controlled traffic, monitored information was used to back calculate axle load. The load information was compared with synchronous video recording of the traffic to check inversely calculated data about wheel weight and its lateral deviation between actual condition, The results show that the established identification system is accurate and valid. In the case of normal traffic, monitored stress data were used to back calculate axle load and wheel lateral distribution. From the results, axle load spectrum is abstracted and can directly help assessment of real load capacity and fatigue life of the bridge.


2020 ◽  
pp. 65-72
Author(s):  
V. V. Savchenko ◽  
A. V. Savchenko

This paper is devoted to the presence of distortions in a speech signal transmitted over a communication channel to a biometric system during voice-based remote identification. We propose to preliminary correct the frequency spectrum of the received signal based on the pre-distortion principle. Taking into account a priori uncertainty, a new information indicator of speech signal distortions and a method for measuring it in conditions of small samples of observations are proposed. An example of fast practical implementation of the method based on a parametric spectral analysis algorithm is considered. Experimental results of our approach are provided for three different versions of communication channel. It is shown that the usage of the proposed method makes it possible to transform the initially distorted speech signal into compliance on the registered voice template by using acceptable information discrimination criterion. It is demonstrated that our approach may be used in existing biometric systems and technologies of speaker identification.


Sign in / Sign up

Export Citation Format

Share Document