Neural Nets and Structural Safety: Applications and Ideas (original) (raw)
Related papers
Artificial Neural Networks in Structural Engineering: Concept and Applications
Journal of King Abdulaziz University-Engineering Sciences, 1999
ABSTRACTAE Artificial neural networks are algorithms for cognitive tasks, such as learning and optimization. They have the ability to learn and generalize from examples without knowledge of rules. Research into artificial neural networks and their application to structural engineering problems is gaining interest and is growing rapidly. The use of artificial neural networks in structural engineering has evolved as a new computing paradigm, even though still very limited.
Applications of Neural Networks in Modeling and Design of Structural Systems
There has been considerable recent activity in exploring biological motivated computational paradigms in problems of engineering analysis and design. Such computational models are placed in a broad category of soft-computing tools that span the gap between traditional procedural methods of computation on one side, and heuristics driven inference engines (non procedural methods) on the other. Of these, methods of neural computing and evolutionary search have been extensively explored in problems of structural analysis and design. The purpose of the present chapter is twofold. It provides an overview of those neural network architectures that are pertinent to the problem of structural analysis and design, including the back-propagation network, the counterpropagation network, the ART network, and the Hopfield network. It then provides a summary of select applications of neurocomputing in the field of structural synthesis. This summary includes the applications of neural networks in function modeling, in establishing causality in design data, in function optimization, and in diagnostics of structural systems.
Application of neural networks to the prediction of the behavior of reinforced composite bridges *
2014
Studies conducted in recent years have shown the effectiveness of composites materials on the behavior of repaired bridges and their influence on the dynamic behavior of these structures, and by experimental-numerical comparisons. However, and in most cases the error (or gap) observed by these confrontations is difficult to readjust. This is why neural networks seems to be an alternative solution to promote this readjustment and therefore reduce the observed error. We propose in this article a study on a set of bridges located in Algeria, in areas of medium and high seismicity, in order to assess their dynamic behavior by measuring frequencies, before and after strengthening by carbon fiber composites. A parametric study (by neural networks) is proposed and its results will be compared to those found by the method of finite elements of a recent case study.
Nonlinear Analysis of Concrete Gravity Dams by Neural Networks
Abstract—Multi-layer neural networks have been used in this paper for modeling nonlinear behaviour of concrete gravity dams under earthquake excitation. Koyna dam which has been studied extensively by other authors in the past has been studied as test example in this paper too, where the nonlinear response of its crest has been modelled by the proposed algorithm. The main steps of the algorithm are as follows: First the concrete gravity dam has been numerically analyzed for its nonlinear behavior under earthquake excitation to generate numerical data to be used in the training of the neural networks. To this end the dam has been subjected to a white noise excitation so that the generated data could be rich enough for the training of a general neuro-modeller of the dam response. The neuro-modeller has then been trained on the generated data to learn the hysteretic behavior of the dam implicitly. Then the neural network has been tested on a number of earthquakes including near field as well as very strong earthquakes for verification. The results obtained in this study prove that the method has been successful regarding the generalization capabilities of the trained neuro-modeller where other earthquakes than those used in its training have been used in its testing. In the tests, the neuro-modeller could predict the response with high precision. One significant benefit of using this algorithm is in cases where it is desired to use collected data from tests on experimental models or through monitoring of the response of a dam to prepare a suitable model for predicting its response under any earthquake. Another benefit is the time of analysis which can be reduced by this method. Once the neuro-modeller is trained, it can predict the response of the dam to any earthquake without the need to be updated.
Neural Network Modelling of Forces on Vertical Structures
Coastal Engineering 1998, 1999
For the design of vertical breakwaters, reliable predictions of the horizontal forces are required. Through physical modelling useful predictions can be made but, due to the very complex interaction between waves and structures, the derivation of reliable empirical relations based on such tests can still be rather difficult. Here, based on a large data-set from physical model tests, use is made of Neural Network modelling to predict horizontal forces on vertical structures. In addition, a method is developed to estimate the reliability-intervals around the predictions. The resulting tool is a complementary design-tool for predicting forces on vertical breakwaters and also a suitable tool for application in probabilistic design methods.
Neural networks for assessing the failure load of a construction
Journal of Computational and Applied Mathematics, 2004
In this contribution, neural networks are applied to the ÿeld of structural engineering. The prediction of the failure load of a construction is a tedious task if one considers the geometrical imperfections of the construction. Experiments on models in a laboratory lead to test results. The guaranteed strength of a construction can be found by searching for a lower bound of the test results. In this contribution, this lower bound is obtained with neural networks. The method is based on the knowledge of the tolerances on the geometrical features of the construction.
Neural Networks: Some Successful Applications in Computational Mechanics
This article presents recent applications of neural computations in the field of stochastic finite element analysis of structures and earthquake engineering. The incorporation of Neural Networks (NN) in this type of problems is crucial since it leads to substantial reduction of the excessive computational cost. Earthquake- resistant design of structures using Probabilistic Safety Analysis (PSA) is an emerging field in structural engineering. The efficiency of soft computing methodologies is investigated when incorporated into the solution of computationally intensive earthquake engineering problems considering uncertainties.
Transforming Results from Model to Prototype of Concrete Gravity Dams Using Neural Networks
2011
Multi-layer neural networks have been used in this paper for modeling nonlinear behaviour of concrete gravity dams under earthquake excitation. Koyna dam which has been studied extensively by other authors in the past has been studied as test example in this paper too, where the nonlinear response of its crest has been modelled by the proposed algorithm. The main steps of the algorithm are as follows: First the concrete gravity dam has been numerically analyzed for its nonlinear behaviour under earthquake excitation to generate numerical data to be used in the training of the neural networks. To this end the dam has been subjected to a white noise excitation so that the generated data could be rich enough for the training of a general neuro-modeller of the dam response. The neuro-modeller has then been trained on the generated data to learn the hysteretic behaviour of the dam implicitly. Then the neural network has been tested on a number of earthquakes including near field as well as very strong earthquakes for verification. The results obtained in this study prove that the method has been successful regarding the generalization capabilities of the trained neuro-modeller where other earthquakes than those used in its training have been used in its testing. In the tests, the neuro-modeller could predict the response with high precision. One significant benefit of using this algorithm is in cases where it is desired to use collected data from tests on experimental models or through monitoring of the response of a dam to prepare a suitable model for predicting its response under any earthquake. Another benefit is the time of analysis which can be reduced by this method. Once the neuro-modeller is trained, it can predict the response of the dam to any earthquake without the need to be updated.
Predicting the Behavior of Concrete Dams Using Artificial Neural Networks (Case study of Dez Dam)
2021
Large dams store a significant amount of water behind them. Therefore, their safety and stability control have a special place. Changes in temperature and hydrostatic pressure are the most important factors that affect the dam structure; And will cause shifts in the crown of the dam upstream and downstream. Therefore, the data obtained from the monitoring center should be evaluated regularly in order to analyze the behavior of the dam. Due to this issue, in this study, using artificial neural networks, a model is presented to predict the horizontal displacement of the Dez dam crown due to changes in pressure and temperature. According to the results, it is observed that the neural network has a good performance in predicting real values. The average error of the modeled network is about 4%. This indicates that the network is well trained. Using the generated network, the radial displacement changes against the reservoir water level for different temperatures are obtained, and plotted. Using diagrams, it is possible to predict the behavior of Dez dam for different temperatures and changes in reservoir water level, which can be very useful in monitoring and maintaining this dam.
2019
Machine learning has been the focus of attention in recent decades, and the influence of the artificial neural networks (ANN) is notable as the most extensively used models of machine learning in the assessment of infrastructures. This paper presents the state of the art of analysis and prediction of seismic damage in infrastructure. The survey demonstrates that ANNs are the essential tools for predicting damage detection of seismic performances of RC bridges. It was also shown that efficiency stresses of the reinforcements are one of the important sources of uncertainty in fragility analysis of RC bridges. It is evident from this evaluation that ANNs have been successfully applied to many infrastructure engineering areas like prediction, risk analysis, decision-making, resources optimisation, classification, and selection.