Robust Output Only Health Monitoring of Steel Railway Bridges

2020 ◽  
pp. 24-41
Author(s):  
Ahmed Rageh ◽  
Daniel Linzell ◽  
Samantha Lopez ◽  
Saeed Eftekhar Azam
Keyword(s):  
Health Monitoring ◽  
Three Dimensional ◽  
Supervised Machine Learning ◽  
Damage Scenario ◽  
Railway Bridges ◽  
Bridge Span ◽  
Structural Responses ◽  
Girder Bridge ◽  
Output Only ◽  
Double Track

This chapter extends application of a framework proposed by the authors (73, 74) for automated damage detection using strain measurements to study feasibility of using sensors that can measure accelerations, tilts, and displacements. The study utilized three-dimensional (3D) finite element models of double track, riveted, steel truss span, and girder bridge span under routine train loads. The chapter also includes three instrumentation schemes for each bridge span (65) to investigate the applicability of the framework to other bridge systems and sensor networks. Connection damage was simulated by reducing rotational spring stiffness at member ends and various responses were extracted for each damage scenario. The methodology utilizes Supervised Machine Learning to automatically determine damage location (DL) and intensity (DI). Simulated experiments showed that DLs and DIs were detected accurately for both spans with various structural responses and using different instrumentation plans.

Assessment and identification of concrete box-girder bridges

2019 ◽  
Author(s):  
Edward A. Baron
Keyword(s):  
Neural Network ◽  
Health Monitoring ◽  
Concrete Bridge ◽  
Fe Model ◽  
Box Girder Bridges ◽  
Box Girder ◽  
Damage Scenarios ◽  
Girder Bridges ◽  
Concrete Box Girder Bridges ◽  
Girder Bridge

<p>This work consists in identify and assess the properties related to material, geometry and physic sources, in a pre-stressed concrete bridge through a surrogate model. The use of this mathematical model allows to generate a relationship between bridge properties and its dynamic response, with the purpose to develop a tool to predict the analytical values of the studied properties from measured eigenfrequencies. Therefore, it is introduced the identification of damage scenarios, giving the application for validate the generated metamodel (Artificial Neural Network). A FE model is developed to simulate the studied structure, a Colombian bridge called "El Tablazo", one of the higher in the country of this type (box-girder bridge). Once the damage scenarios are defined, this work allows to indicate the basis for futures plans of structural health monitoring.</p>

Evaluation of the effect of operational modal analysis algorithms on identified modal parameters of railway bridges

2021 ◽  
Author(s):  
Mohammadreza Salehi ◽  
Kultigin Demirlioglu ◽  
Emrah Erduran
Keyword(s):  
Modal Analysis ◽  
Health Monitoring ◽  
Iron Ore ◽  
Operational Modal Analysis ◽  
Modal Parameters ◽  
Vibration Source ◽  
Light Weight ◽  
Railway Bridges ◽  
Different Types ◽  
Vibration Responses

<p>The accuracy of modal parameters identified by Operational Modal Analysis (OMA) algorithms is of vital importance in vibration-based health monitoring. This paper reports the effects of using different OMA algorithms on identified modal parameters of railway bridges. For this purpose, comparison and application of three different OMA methods including FDD, ARX, SSI-COV are discussed. The vibration measurements are conducted on two railway bridges in Northern Norway for using five triaxial accelerometers. The first bridge is a single-span bridge with the length of 50 m, while the second is a two-span bridge with a total length of 85m. OMA has been conducted on the free vibration responses after passage of different types of trains including light-weight railway vehicles and heavily loaded iron ore trains to evaluate the variation of the identified modal parameters with the chosen algorithm and the vibration source on the OMA results.</p>

Railway Bridges Identification Techniques

2005 ◽  
Author(s):  
Luigi Garibaldi ◽  
Luigi Bregant ◽  
Claudio Valente ◽  
Fabio Brancaleoni ◽  
Giuseppe Catania
Keyword(s):  
Reference Model ◽  
Random Access ◽  
Random Excitation ◽  
Correct Identification ◽  
Railway Bridges ◽  
The Road ◽  
Alternative Techniques ◽  
Road Surface Roughness ◽  
Output Only ◽  
Identification Techniques

Output-only methodologies are nowadays well established to extract modal parameters in many areas of engineering, such as civil, mechanical and aeronautical. In the past, civil engineering tests have been mainly developed for road bridges, with the vehicle passage over the bridge deck representing the main source of excitation with some contribution given by the ambient noise. In the road bridge cases, the excitation is considered to be a function of the road surface roughness, the vehicles speed, the weight and suspension vehicles characteristics, and also the random access of the vehicles over the bridge, whilst for the railway case, not all these issues are correctly addressed, and other characteristics rise-up, possibly advantageous for a correct identification process; to demonstrate this statement, we can bear in mind how the random access of the vehicles becomes meaningless for railway bridges, the single train being a quasi deterministic source; furthermore, the influence of the train weight should be considered if compared to usual road vehicles. Since output-only techniques are conceived for random excitation noise, their use in these conditions is considerably stressed and special care, or alternative techniques, has to be considered to avoid errors. In this sense, the bridge reference model becomes more important and some special techniques have to be developed.

scholarly journals Development of a Pattern Recognition Tool for the Classification of Electronic Tongue Signals Using Machine Learning

2021 ◽  
Vol 5 (1) ◽  
pp. 21
Author(s):  
Edgar G. Mendez-Lopez ◽  
Jersson X. Leon-Medina ◽  
Diego A. Tibaduiza
Keyword(s):  
Machine Learning ◽  
Dimensionality Reduction ◽  
Performance Measures ◽  
Sensor Array ◽  
Three Dimensional ◽  
Electronic Tongue ◽  
Sensor Arrays ◽  
Classification Performance ◽  
Supervised Machine Learning ◽  
Electrochemical Tests

Electronic tongue type sensor arrays are made of different materials with the property of capturing signals independently by each sensor. The signals captured when conducting electrochemical tests often have high dimensionality, which increases when performing the data unfolding process. This unfolding process consists of arranging the data coming from different experiments, sensors, and sample times, thus the obtained information is arranged in a two-dimensional matrix. In this work, a description of a tool for the analysis of electronic tongue signals is developed. This tool is developed in Matlab® App Designer, to process and classify the data from different substances analyzed by an electronic tongue type sensor array. The data processing is carried out through the execution of the following stages: (1) data unfolding, (2) normalization, (3) dimensionality reduction, (4) classification through a supervised machine learning model, and finally (5) a cross-validation procedure to calculate a set of classification performance measures. Some important characteristics of this tool are the possibility to tune the parameters of the dimensionality reduction and classifier algorithms, and also plot the two and three-dimensional scatter plot of the features after reduced the dimensionality. This to see the data separability between classes and compatibility in each class. This interface is successfully tested with two electronic tongue sensor array datasets with multi-frequency large amplitude pulse voltammetry (MLAPV) signals. The developed graphical user interface allows comparing different methods in each of the mentioned stages to find the best combination of methods and thus obtain the highest values of classification performance measures.

An Investigation of the Structural Dynamics of a Racing Yacht

1999 ◽  
Author(s):  
Frederic Louarn ◽  
Pandeli Temarel
Keyword(s):  
Dynamic Properties ◽  
Three Dimensional ◽  
Element Model ◽  
Point Of View ◽  
Mode Shapes ◽  
Function Technique ◽  
Operational Conditions ◽  
Principal Coordinates ◽  
Modal Summation ◽  
Structural Responses

The dynamic behaviour of a WOR 60 is investigated using three dimensional hydroelasticity theory. Global structural responses (e.g. stresses) in waves are obtained corresponding to the upright as well as to the more realistic heeled sailing configurations, revealing the connection between the ballast keel and the hull as being a critical area of the structure. For the "dry hull" analysis, a global finite element model has been developed, incorporating the hull and deck shell, the internal structure, the ballast keel and the rig together with rigging loads. The modular nature of the model has been used to assess the relative influence of each of the aforementioned components upon the required characteristic dynamic properties (e.g. natural frequencies and principal mode shapes). Regarding the "wet hull" analysis, a three dimensional Green's function technique, using pulsating sources distributed over the wetted surface, provides a numerical solution to the case of the yacht sailing in regular waves at arbitrary heading. Principal coordinates for the rigid body motions and flexible distortions of interest are evaluated and the latter are used to obtain the dynamic stresses in waves using modal summation. This paper will describe the modelling techniques used and discuss the applicability / limitations of hydroelasticity theory regarding this type of structures in the light of the results obtained for the upright and heeled operational conditions, as well as from the point of view of design aspects such as "L" and "T" keel configurations. The ABS design criteria will provide a practical reference for comparing the results from the dynamic analysis.

Sign in / Sign up

Export Citation Format

Share Document