scholarly journals Data mining algorithms for bridge health monitoring: Kohonen clustering and LSTM prediction approaches

2019 ◽  
Vol 76 (2) ◽  
pp. 932-947 ◽  
Author(s):  
Aiping Guo ◽  
Ajuan Jiang ◽  
Jie Lin ◽  
Xiaoxiao Li
Keyword(s):  
Neural Network ◽  
Health Monitoring ◽  
Short Term Memory ◽  
Bridge Engineering ◽  
Normal Operation ◽  
Massive Data ◽  
Health State ◽  
Bridge Structure ◽  
Continuous Growth ◽  
Bridge Health Monitoring

Abstract In recent years, bridge health monitoring system has been widely used to deal with massive data produced with the continuous growth of monitoring time. However, how to effectively use these data to comprehensively analyze the state of a bridge and provide early warning of bridge structure changes is an important topic in bridge engineering research. This paper utilizes two algorithms to deal with the massive data, namely Kohonen neural network and long short-term memory (LSTM) neural network. The main contribution of this study is using the two algorithms for health state evaluation of bridges. The Kohonen clustering method is shown to be effective for getting classification pattern in normal operating condition and is straightforward for outliers detection. In addition, the LSTM prediction method has an excellent prediction capability which can be used to predict the future deflection values with good accuracy and mean square error. The predicted deflections agree with the true deflections, which indicate that the LSTM method can be utilized to obtain the deflection value of structure. What’s more, we can observe the changing trend of bridge structure by comparing the predicted value with its limit value under normal operation.

Bridge Health Monitoring Using Accelerometer Responses to Passing Traffic

2019 ◽  
Author(s):  
Eugene Obrien ◽  
Daniel McCrum ◽  
Muhammad Arslan Khan
Keyword(s):  
Statistical Analysis ◽  
Health Monitoring ◽  
Traffic Control ◽  
The Other ◽  
Bridge Structure ◽  
Acceleration Response ◽  
Bridge Health Monitoring ◽  
Weigh In Motion ◽  
Bridge Weigh In Motion ◽  
Strain Responses

<p>This paper develops a method of bridge structure health monitoring using bridge midspan acceleration response and the concept of Bridge Weigh-in-Motion (BWIM). This method does not require any traffic control and works solely with the responses to regular passing truck traffic. Traditional BWIM systems use bridge strain responses to infer vehicle axle weights, but the strain responses are not damage sensitive. Bridge accelerations, on the other hand, vary with the change in the bridge condition at any location. Therefore, this paper focuses on a statistical analysis of the acceleration-based BWIM results to monitor bridge condition. The acceleration-based BWIM system has been found to be very effective in detection change in the bridge condition by showing significant change in the statistical properties of the BWIM results with different damage percentage of the bridge.</p>

The Health Monitoring of Bridges using Artificial Neural Networks

2001 ◽  
Vol 17 (3) ◽  
pp. 157-166
Author(s):  
Pei-Ling Liu ◽  
Shyh-Jang Sun
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Monitoring System ◽  
Health Monitoring ◽  
Network System ◽  
Bridge Structure ◽  
Constant Mass ◽  
Simulation Data ◽  
Neural Network System ◽  
The Neural Networks

ABSTRACTThis study develops a neural network system to monitor the safety of a bridge structure. A truck of constant mass is driven at constant speed through the target bridge. Then, the maximal and minimal values of the bridge elongations are processed by a monitoring system to evaluate the current condition of the bridge. The monitoring system is composed of parallel backpropagation neural networks. Each neural network monitors a part of the bridge. The neural networks are trained using simulation data. The numerical example shows that the monitoring system is effective in the damage detection of the bridge.

Applying KDD to a Structure Health Monitoring System Based on a Real Sited Bridge: Model Reshaping Case

2014 ◽  
Vol 472 ◽  
pp. 535-538 ◽  
Author(s):  
Ming Lei Ma ◽  
Gui Ling Wang ◽  
Dong Mei Miao ◽  
Gui Jun Xian
Keyword(s):  
Data Mining ◽  
Structural Health Monitoring ◽  
Knowledge Discovery ◽  
Health Monitoring ◽  
Bridge Engineering ◽  
Massive Data ◽  
Time Data ◽  
Health Monitoring System ◽  
Bridge Model ◽  
Real Time Data

Knowledge discovery (KDD) method aims to solve the problem of massive data. For bridge engineering, the structural health monitoring (SHM) system is cumulative data from time to time, but the whole system should be understudied in real time. Data mining should be used in one of the KDD process. This article proposed a regular rule of analyzing the SHM data from a real sited bridge. The data aim to help engineers understanding the system degradation of the bridge.

A Neural Network-Based System for Bridge Health Monitoring

2012 ◽  
Vol 452-453 ◽  
pp. 557-563
Author(s):  
Tzu Kang Lin ◽  
Ming Chih Huang ◽  
Jer Fu Wang
Keyword(s):  
Neural Network ◽  
Health Monitoring ◽  
Bridge Health Monitoring

scholarly journals Circuit Health State Estimation via An Integrated Deep Neural Network

2020 ◽  
Vol 14 ◽  
Keyword(s):  
Neural Network ◽  
State Estimation ◽  
Short Term Memory ◽  
Health Management ◽  
Angular Distance ◽  
System Level ◽  
Health State ◽  
Convolutional Autoencoder ◽  
External Conditions ◽  
The Time Domain

accelerating the industry to become more integrated and intricated. It is almost inevitable for a system to encounter failures during its whole life span. Thus, it is imperative to monitor the operating system from a system-level perspective to avoid potential catastrophes. Intuitively, inclusive prior knowledge is required for prognostics and health management (PHM). However, due to time-varying parameters and external conditions, the system is usually too complex to neatly fit into a prior-built model. This paper presents a novel pragmatic method, encompassing the convolutional autoencoder (CAE) and long short-term memory recurrent neural network (LSTM-RNN), to track the health state of a circuit. Briefly, the proposed method can be divided into two steps. First, degradation characteristics are extracted by using the time-domain features and CAE to prepare for the later health state estimation step. Then, the LSTM-RNN is used to finish the predictive process, i.e., to map the extracted abstract features to the health state. In addition, the degradation of a practical circuit considering the angular distance is discussed to quantify the health state of the circuit system. Furthermore, a case study based on that prognostics scheme is conducted to verify the proposed method. The comparison with other existing popular methods indicates the superiority of the proposed methodology.

Wavelet De-noising of GNSS Based Bridge Health Monitoring Data

2014 ◽  
Vol 8 (4) ◽  
Author(s):  
Oluropo Ogundipe ◽  
Jae Kang Lee ◽  
Gethin Wyn Roberts
Keyword(s):  
Wavelet Transform ◽  
Health Monitoring ◽  
Three Dimensional ◽  
Monitoring Systems ◽  
Accurate Information ◽  
Bridge Structure ◽  
Bridge Health Monitoring ◽  
Cable Stayed Bridge ◽  
Multiple Paths ◽  
Health Monitoring Systems

AbstractGNSS signal multipath occurs when the GNSS signal reflects of objects in the antenna environment and arrives at the antenna via multiple paths. A bridge environment is one that is prone to multipath with the bridge structure, as well as passing vehicles providing static and dynamic sources of multipath. In this paper, the Wavelet Transform (WT) is applied to bridge data collected on the Machang cable stayed bridge in Korea. The WT algorithm was applied to the GNSS derived bridge defection data at the mid-span. Up to 41% improvement in RMS was observed afterwavelet shrinkage de-noisingwas applied.Application of this algorithm to the torsion data showed significant improvement with the residual average and RMS decreased by 40% and 45% respectively. This method enabled the generation of more accurate information for bridge health monitoring systems in terms of the analysis of frequency, mode shape and three dimensional defections.

Analysis, Prospect on Non-Linearity and Security Evaluation of Bridge Based on Multi-Chaotic Indexes

2011 ◽  
Vol 52-54 ◽  
pp. 1015-1020
Author(s):  
Jian Xi Yang ◽  
Jian Ting Zhou
Keyword(s):  
Health Monitoring ◽  
Correlation Dimension ◽  
Security Evaluation ◽  
Bridge Structure ◽  
Bridge Health Monitoring ◽  
Bridge Safety ◽  
Solid Foundation ◽  
Lyapunov Index ◽  
Further Development ◽  
Monitoring Information

This paper presents an analysis of the nonlinear characteristics of a bridge structure and the chaos of BHM(bridge health monitoring) information. Chongqing Masangxi bridge’s BHM information is analyzed by using the max Lyapunov index with Wolf and correlation dimension with G_P algorithm. The results show:1) all of the max Lyapunov index is nonnegative ;2)the correlation dimension is non-integeral and greater than 2.These proves that the bridge structure is in the chaos. Meanwhile, with the evolution of time, the index of chaos is sensitive with status of structure system and varies in different key sections of bridge structure. These findings lay a solid foundation for the further development of bridge safety assessment and prediction when non-linear chaotic theory is utilized to analyze the bridge health monitoring information.

Sign in / Sign up

Export Citation Format

Share Document