Artificial Neural Networks for the Analysis of Slabs Under Simultaneous Aircraft and Temperature Loading

This study focuses on the development and performance of a comprehensive artificial neural network (ANN) model for the analysis of jointed concrete slabs under simultaneous aircraft and temperature loading. Using the results from the ILLI-SLAB finite element program, a comprehensive artificial neural network model was trained for the different loading conditions of gear load only, temperature load only, and simultaneous aircraft and temperature loading cases. Special consideration has been given to the loading of a typical jointed slab assembly under the tri-tandem type gear of the Boeing 777 aircraft. In addition to various slab load locations (interior, corners, and two mid-span slab edges) and joint load transfer efficiencies, a wide range of realistic airfield slab thicknesses and subgrade supports have been considered as ANN input conditions. Comparing the ANN predictions to the ILLI-SLAB solutions validated the performance of the ANN model. The trained ANN model gave maximum bending stresses and maximum vertical deflections within an average error of 1.4 percent of those obtained directly from ILLI-SLAB analyses. It is also shown that the principle of superposition is not valid for simply adding the critical pavement responses (slab deflections and bending stresses) obtained under gear loading only and temperature loading only cases. The summation does not usually produce the same pavement response as obtained from the simultaneous gear and temperature loading. The typical ANN prediction time is about 0.3 million times faster than the average ILLI-SLAB finite element solution. The use of an ANN-based design tool is deemed to be very effective for studying hundreds or thousands of "what if" scenarios for including the temperature effects in pavement analysis and design.