Zhou Jianting

A Study on the Application of GA-BP Neural Network in the Bridge Reliability Assessment

In the design of the bridge reliability assessment proposal, the application of the BP neural network model can help overcome some shortcomings in the traditional bridge reliability assessment, such as the poor model adaptability, the low calculation efficiency and so on. However, there are also some problems in the BP neural network model, for example, the uneasily determinable initial weights and easily local optimum. The BP neural network model optimized by the application of GA global optimum characteristics can get the optimum relation quickly. Therefore, this paper puts forward a GA-BP neural network model based on the real number coding system to analyze the bridge reliability assessment and applies it to the reliability assessment in Masangxi Yangtze River Bridge. The results of the application show that the GA-BP neural network model has a higher accuracy, higher reliability and application value in the assessment of the engineering works than the traditional BP neural network model.

Remote Real-time Health Monitoring and Evaluation System for Long Bridge Structure

In this paper, a fast evaluation system for remote real-time health monitoring and evaluation of long bridge structure is proposed. The main idea of this system is to apply the reliability design theory for static structure into the dynamic remote health monitoring and reliability evaluation of bridges. The real-time safety evaluation of bridges includes the following components: (1) dynamic acquisition of optimal statistical parameters through distribution testing of fitting performance; (2) real-time analysis of section dynamic reliability of bridge structure; and (3) evaluation of bridge structure reliability by using PNET method in comparison to the standard reliability index commonly used in highway engineering. This research first realizes the real-time dynamic bridge reliability analysis based on the monitoring data analysis and then evaluates in real time the objective health conditions of bridge. The performance of remote monitoring and evaluation over long bridges demonstrates that the proposed evaluation system can deal with real-time information monitoring, evaluate reliably the bridge safety and promote intelligent development of bridge structures.

Application of Modern Sensor- and Info-Technology in Long-Term Safety Monitoring of Long Span Rigid-Frame Bridge

The issue of safety has been concerned throughout the world. This paper, taking a long span continuous rigid-frame bridge as an example, introduces the application of the modern sensor- and info-technology in the said bridge by presenting the components of the monitoring system, the acquisition and transmission of the monitored data, and the bridge safety evaluation system. The experiment has proved that the application of the sensor- and info-technology into civil engineering projects can bring about good social, economical and scientific effects

A method for analysis linear correlation for multi-sensor of bridge monitoring system

This article puts forward the process and model of scale measured points correlation of bridge monitoring system on the base of analyzing linear and non-linear correlation of measured points. The process and model are put forward mainly for the characteristics of the stability in short term assessment, linear and lasting non-stability, and non-linear of the bridge monitoring. From the analysis of the monitoring data taking from Mashangxi Yangtse River Bridge, it shows that, when the analysis of measured points correlation is carried out in the cycle of a month, each correlation indicator is stable, and meanwhile, the result also accords with the conclusion of structure mechanics analysis. Finally, this article puts forward the research direction of the application of measured points in bridge safety assessment, which lays basis to further improve the accuracy of safety assessment.

Study of surface damage of concrete towers based on microcosmic numerical simulation

Strength characteristic of towers of cable-stayed bridges, acting as main compression member, is mainly to bear vertical component force produced by cables. This paper simulates mechanical behavior of the surface of towers by using PFC software and applies Fish language programming to analyze structural materials of concrete on the surface of towers, boundary control conditions, as well as appliance of load. Three states of particle clusters are employed to simulate microcosmic damage on the surface of concrete towers. It also describes in detail the produce of microcrack, the expansion of crack, as well as the energy changing in the process of cracking, which is a evolution of damage at the beginning of surface cracking on towers: the bigger the radius of particle clusters is, the severer the damage is, among which the predominant energy is strain energy.

A New Strategy for Structural Health Monitoring based on Structural Destroyed Mode and Data Correlation

Abstract This paper provides anew strategy for study of Structural Health Monitoring, and discusses establishment of structural safety monitoring system based on the structural destroyed modes and data correlation. Two concepts, structural destroyed mode and data correlation, are given and discussed. The structural destroyed mode refers to the pattern of certain structural state or situation that some kind of failure occurred. The study on data correlation focuses on the relations existed between different sensors and locations. A structural safety monitoring system for a simply supported beam including several damage indices is built, and the numerical experiment shows it works effectively.

The Discussion on Deflected Pre-Stressed Tendons and Diagonal Cracks of Webs in PSC Box Girders

Abstract In order to find the relationship between deflected pre-stressed tendons and diagonal cracks of webs and provide basis to design and construction of bridges, a characteristics section model of a long span pre-stressed concrete continuous box girder, which is now under construction in Chongqing is analyzed by using nonlinear finite element program Midas-FEA. A numerical simulation analysis to the tensile stress in the webs was down based on the actual construction situation. As the research shows: 1, Stress concentration exists at the point where pre-stressed tendons are anchored, and the stress value was higher in anchorage area, which accord with the Saint-Venant Principle.2, The main tensile stress of webs in the anchorage area is lower than 1.04MPa, which did not surpass the standard 2.74MPa of the concrete tensile stress of C55, as a result, webs would not craze from finite element analysis. 3, Cracks brought by other normal or abnormal reasons existed in the process of casting the cantilever...

Analysis on Network Model Parameters of BP Neural Network in the Assessment for Bridge Reliability

Using of back propagation (BP) neural network model to evaluate the bridge reliability would not only overcome the shortcomings of the traditional assessment methods, but also present many features such as dynamic adjustment, high precision, high efficiency and strong portability. Through analysis experiments on the parameters influenced by the learning samples, the learning rates, the hidden layer nodes and the initial weights in the reliability assessment of Masangxi Yangtze River Bridge, Proposed a 14-16-1 BP neural network with the learning rate of 0.005 to evaluate the reliability of Masangxi Yangtze River Bridge, which has 1000 groups of learning samples. This model has higher precision and assessment efficiency, which make some useful exploration for this intelligent algorithm model applied in other bridges’ reliability assessment.