Intelligent optimization and machine learning algorithms for structural anomaly detection using seismic signals

Trapp, Maximilian; Bogoclu, Can; Nestorović, Tamara; Roos, Dirk

doi:10.1016/j.ymssp.2019.106250

Cited by 15 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1 is inspired by [9] and developed by the research group "Mechanics of Adaptive Systems" (Ruhr-Universität Bochum). First validations with respect to exploration in mechanized tunneling for several time domain FWI approaches have been performed using measurements form this setup [6,10,11]. A computer sends a source function to the waveform generator Keysight 33500, which transforms the digital to a electric signal, which is in the next step enhanced by the power amplifier 1040L of the company Electronics & Innovation.…”

Section: Small-scale Experimental Setupmentioning

confidence: 99%

Frequency domain full waveform inversion with small‐scale laboratory measurements for reconnaissance in mechanized tunneling

Riedel

Musayev

Baitsch

et al. 2023

Proc Appl Math and Mech

View full text Add to dashboard Cite

In mechanized tunneling, so-called tunnel boring machines (TBMs) drill through the ground in an automatized manner. Therefore, the drilling process is very efficient but the maintenance costs are high. Seismic exploration seems appropriate to identify changing ground conditions in front of the TBM to reduce costs from damages of the TBM and from the corresponding dwell times. Today's seismic exploration techniques are using only a small amount of the information, which is contained in the seismic records from field observations, whereas full waveform inversion (FWI) tries to use the whole content. The potential of different FWI approaches for the application in mechanized tunneling has been investigated. An analysis of the performance of FWI not only employing synthetic examples but additionally measured waveforms is essential. Since seismic surveys at the construction side are not performed with FWI in mind, the data sets are usually not appropriate for testing the developed algorithms. Nevertheless, a validation of FWI approaches by measured waveforms is possible by using waveform recordings from a small-scale experimental setup. A small-scale super high strength grout specimen is constructed for validating an adjoint frequency domain FWI approach. Frequency domain models compute the seismic response of a system for an infinite time interval. The attenuation of the material as well as the attenuation effects at the free surfaces are hard to quantify over an infinite time interval. Therefore, the specimen is designed in a way that four of the six borders can be modeled as absorbing boundaries. For this purpose, the displacement recordings are truncated just before the waves that are reflected at the excluded borders arrive at the measurement points. This design in combination with a notch representing a rectangular tunnel makes the measurements more similar to data from a tunnel construction side. A rectangular hole is embedded in the specimen and acts as material discontinuity, which the FWI approach is aiming to detect.

show abstract

Section: Small-scale Experimental Setupmentioning

confidence: 99%

Frequency domain full waveform inversion with small‐scale laboratory measurements for reconnaissance in mechanized tunneling

Riedel

Musayev

Baitsch

et al. 2023

Proc Appl Math and Mech

View full text Add to dashboard Cite

show abstract

“…With the growing volume of data, the improvements in computing power, and computer technology innovations, artificial intelligence techniques can reshape and change our lives (Fathi et al, 2021;Haeberle et al, 2019;Hussien et al, 2022a;Tavasoli et al, 2021). In the technology and computer revolution-3rd the industrial revolution, data can be similar to electricity and stream that can be considered as two valuable energy sources for the industry progress advancement (Hussien & Amin, 2022;Hussien et al, 2017a;Hussien et al, 2020c;Trapp et al, 2019). Nowadays, we are in the fourth industrial revolution era in which optimization algorithms become one of the most important weapons for finding solutions to complicated and high-dimensional optimization problems (Abualigah et al, 2020;Fang et al, 2010;Hussien et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

A multi-strategy enhanced African vultures optimization algorithm for global optimization problems

Zheng

Hussien

Qaddoura

et al. 2023

Journal of Computational Design and Engineering

View full text Add to dashboard Cite

The African vultures optimization algorithm (AVOA) is a recently proposed metaheuristic inspired by the African vultures’ behaviors. Though the basic AVOA performs very well for most optimization problems, it still suffers from the shortcomings of slow convergence rate and local optimal stagnation when solving complex optimization tasks. Therefore, this study introduces a modified version named Enhanced AVOA (EAVOA). The proposed EAVOA uses three different techniques namely representative vulture selection strategy, rotating flight strategy, and selecting accumulation mechanism, respectively, which are developed based on the basic AVOA. The representative vulture selection strategy strikes a good balance between global and local searches. The rotating flight strategy and selecting accumulation mechanism are utilized to improve the quality of the solution. The performance of EAVOA is validated on twenty-three classical benchmark functions with various types and dimensions and compared to those of nine other state-of-the-art methods according to numerical results and convergence curves. In addition, three real-world engineering design optimization problems are adopted to evaluate the practical applicability of EAVOA. Furthermore, EAVOA has been applied to classify multilayer perception using XOR and cancer datasets. The experimental results clearly show that the EAVOA has superiority compared to other methods.

show abstract

“…Reconstruction and estimation of the input of a structure, based on its outputs is an ill-posed problem [13]. To solve this class of the problems, deterministic, regularized technique, and probabilistic approaches can be implemented.…”

Section: Introductionmentioning

confidence: 99%

Assessment of a Dual Kalman Filter-Based Approach for Input/Output Estimation in an Aluminum Plate

Sattarifar

Nestorović

2021

Lecture Notes in Civil Engineering

Self Cite

View full text Add to dashboard Cite

Vulnerability of structures to damage during their service time brings up the necessity of design and implementation of an intelligent procedure to assure the health of the structure. In the sight of this requisite, current work deals with extending the capability of a dual Kalman filter (DKF) state estimation scheme to assist vibration-based health monitoring methods. This is met by estimating the response of the structure for locations at which a sensor cannot be placed. The capability of the DKF method in the estimation of states of a linear system with an unknown input has been presented in various recent works. In this paper, a DKF approach incorporated with a reduced order structural model (in this case an aluminum plate) is utilized to obtain an estimation of applied force and the response of the structure in terms of acceleration, velocity, and displacement. These estimations are based on measured accelerations at a limited number of points on the aluminum plate as well as the state-space model of the dynamic system. Numerical simulations and experimental works are performed to obtain the mentioned datasets. To assess the robustness of the method concerning various conditions, the effect of the frequency, as well as type of the function of the input force on the validity of the method, is presented. Moreover, it is shown to what extent the number of selected modes in model reduction procedure can influence the accuracy of the DKF technique.

show abstract

Intelligent optimization and machine learning algorithms for structural anomaly detection using seismic signals

Cited by 15 publications

References 20 publications

Frequency domain full waveform inversion with small‐scale laboratory measurements for reconnaissance in mechanized tunneling

Frequency domain full waveform inversion with small‐scale laboratory measurements for reconnaissance in mechanized tunneling

A multi-strategy enhanced African vultures optimization algorithm for global optimization problems

Assessment of a Dual Kalman Filter-Based Approach for Input/Output Estimation in an Aluminum Plate

Contact Info

Product

Resources

About