Neural Networks in Civil Engineering. I: Principles and Understanding
Journal of Computing in Civil EngineeringPublished 1 April 1994
Ian Flood, Nabil Kartam
Citations582
SJR quartileQ1
SJR score1.24
SNIP1.76
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
An understanding of how these devices operate is developed and the main issues concerning their use are explained, including factors affecting their ability to learn and generalize.
Abstract
This is the first of two papers providing a discourse on the understanding, usage, and potential for application of artificial neural networks within civil engineering. The present paper develops an understanding of how these devices operate and explains the main issues concerning their use. A simple structural‐analysis problem is solved using the most popular form of neural‐networking system—a feedforward network trained using a supervised scheme. A graphical interpretation of the way in which neural networks operate is first presented. This is followed by discussions of the primary concepts and issues concerning their use, including factors affecting their ability to learn and generalize, the selection of an appropriate set of training patterns, theoretical limitations of alternative network configurations, and network validation. The second paper demonstrates the ways in which different types of civil engineering problems can be tackled using neural networks. The objective of the two papers is to ensure the successful development and application of this technology to civil engineering problems.
Keywords
Computer ScienceEngineering
Learning Internal Representations by Error Propagation
16,235 Citations1985David E. Rumelhart, Geoffrey E. Hinton +1 more
Springer series in information sciencesSelf-Organization and Associative Memory
8,770 Citations1989Teuvo Kohonen
Perceptrons: an introduction to computational geometry
3,308 Citations1969Marvin Minsky, Seymour Papert
Theory of the backpropagation neural network
2,225 Citations1989Hecht-Nielsen
IEEE Transactions on Neural NetworksA simple procedure for pruning back-propagation trained neural networks
664 Citations1990Ehud D. Karnin
Shadow arrays are introduced which keep track of the incremental changes to the synaptic weights during a single pass of back-propagating learning and are ordered by decreasing sensitivity numbers so that the network can be efficiently pruned by discarding the last items of the sorted list.
Journal of Computing in Civil EngineeringNeural Networks in Civil Engineering. II: Systems and Application
182 Citations1994Ian Flood, Nabil Kartam
The versatility of neural networks as a problem-solving tool is demonstrated, and how they can be applied to different problems in civil engineering is shown.
Journal of Intelligent ManufacturingEngineering applications of neural networks
121 Citations1993James H. Garrett, Michael P. Case +6 more
This paper describes several prototypical applications of neural network technology to engineering problems, representative of many of the engineering problems for which neural networks are applicable: adaptive control, feature recognition, and design.
Journal of Computing in Civil EngineeringNeuroform—Neural Network System for Vertical Formwork Selection
76 Citations1992Sagar Kamarthi, Victor E. Sanvido +1 more
The performance of Neuroform is validated comparing its recommendations with that of Wallform, a rule-based expert system for vertical formwork selection, and the system’s fault-tolerant and generalization properties are demonstrated.
Journal of Computing in Civil EngineeringComputing Truck Attributes with Artificial Neural Networks
57 Citations1994Nicolas Gagarin, Ian Flood +1 more
The paper describes the application of neural networks to the problem of determining truck attributes purely from strain‐response readings taken from the structure over which the truck is traveling, designed to remove both the need for tape switches on the deck of the bridge to obtain such data and associated problems.
IEE Proceedings D Control Theory and ApplicationsSelf-adaptive design of a nonlinear temperature control system
34 Citations1991A. Chotai, Peter C. Young +1 more
Proceedings of the ... ISARCSimulating the Construction Process Using Neural Networks
29 Citations1990Ian Flood
Proceedings of the ... ISARCA Neural Network Approach to the Sequencing of Construction Tasks
26 Citations1989Ian Flood
A neural network based method for solving complex construction operational problems, using networks developed through a process of simulated evolution, and the effectiveness of this approach is evaluated in terms of both the rate at which networks can be evolved and the efficiency of the solutions they produce.
Proceedings of the ... ISARCA Hybrid Neural Network Methodology for Cost Estimation
17 Citations1991Osama Moselhi, Tarek Hegazy +1 more
An integrated system approach utilizing Neural Networks, an Al-based technique that emulates the human ability to learn from past experience and derive speedy solutions to new situations, based mainly on intuitive judgement that is difficult to model by other AIbased techniques including expert systems is presented.
Weighing trucks in motion using Gaussian-based neural networks
16 Citations2003Nicolas Gagarine, Ian Flood +1 more
The Gaussian-based approach demonstrates the feasibility of using neural networks to determine track axle loads from strain data by demonstrating a much faster rate of convergence and a much higher degree of accuracy.
A Gaussian-based feedforward network architecture and complementary training algorithm
14 Citations1991Ian Flood
The author describes a neural network architecture and training procedure that provide an efficient means of modeling complicated surface functions that ensures convergence on a solution to within any tolerance for a set of training patterns, converges rapidly, and circumvents the issue of how many hidden neurons to incorporate in a network.
Artificial intelligence for engineering design analysis and manufacturingIntegrating knowledge-based systems and artificial neural networks for engineering
13 Citations1995Nabil Kartam, Ian Flood +1 more
This paper identifies and describes how KBSs and ANNs can be integrated, and provides an evaluation of the advantages that will accrue in engineering applications.
The Knowledge Engineering ReviewExpert systems in construction engineering and management: state of the art
11 Citations1990Raymond E. Levitt, Nabil Kartam
The broad scope of this field, combined with the empirical nature of many facets of construction engineering and management practice, have led to a significant amount of expert system activity in this domain.
OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)Expanding the power of expert systems applications with neural networks
1 Citations1990J.J. Ferrada, I.W. Osborne-Lee +1 more
This work demonstrates the use of knowledge that is pattern driven rather than heuristic and may be fuzzy, which is characteristic of many problems in chemical engineering, and the feasibility of combining these two artificial intelligence (AI) technologies is explored.