Cost estimation of timber bridges using neural networks

Journal Article · Mon May 01 04:00:00 EDT 1995 · Cost Engineering

OSTI ID:133244

Creese, R C; Li, L

Neural network models, or more simply {open_quotes}neural nets,{close_quotes} have great potential application in speech and image recognition. They also have great potential for cost estimating. Neural networks are particularly effective for complex estimation where the relationship between the output and the input cannot be expressed by simple mathematic relationships. A neural network method was applied to the cost estimation of timber bridges to illustrate the technique. The results of the neural network method were evaluated by the coefficient of determination, The R square value for the key input variables. A comparison of the neural network results and the standard linear regression results was performed upon the timber bridge data. A step-by-step validation is presented to make it easy to understand the application of neural networks to this estimation process. The input is propagated from the input through each layer until an output is generated. The output is compared with the desired output and the error is distributed for each node in the outer layer. The error is transmitted backward (thus the phase {open_quotes}back propagation{close_quotes}) from the output layer to the intermediate layers and then to the input layer. Based upon the errors, the weights are adjusted and the procedure is repeated. The number of training cycles is 15,000 to 50,000 for simple networks, but this usually takes only a few minutes on a personal computer. 7 refs., 4 figs., 11 tabs.

• OSTI ID: 133244
• Journal Information: Cost Engineering, Journal Name: Cost Engineering Journal Issue: 5 Vol. 37; ISSN CSTEDM; ISSN 0274-9696
• Country of Publication: United States
• Language: English

Related Subjects

42 ENGINEERING
99 GENERAL AND MISCELLANEOUS
BRIDGES
CIVIL ENGINEERING
COST ESTIMATION
MATRICES
NEURAL NETWORKS
PLANNING
TRANSFER FUNCTIONS
WOOD