There are an increasing number of studies that use the artificial neural networks (ANN) as a prediction tool in the field of foundations with satisfactory results. In this paper, multilayer perceptrons are used to develop prediction models for the shaft and tip bearing capacities of single piles based on a supervised training using the error back propagation algorithm. Results from static load tests carried out on 95 instrumented single piles executed in different regions of Brazil were used in the ANN modelling. The prediction models of shaft and tip bearing capacities of single piles were obtained portraying indicated in the validation phase determination coefficients equal to 95% and 99%, respectively. To demonstrate their applicability and efficiency, such models were used to estimate the bearing capacity of single piles unused in the models’ development, as well as groups of two and three piles. The results demonstrated that the neuron models were much closer to the values of the bearing capacities measured in single pile tests and groups of piles, than the estimated results using semi-empirical methods. As a result of overestimating the predicted bearing capacities in relation to the results of the load tests, it is recommended to use models applying reduction factors of 0.88 for single piles, and 0.75 for groups of up to three piles.

RESUMO: Para o dimensionamento geotécnico de fundações superficiais é necessário conhecer a tensão admissível do solo, obtida indiretamente a partir da capacidade de carga; ou diretamente aplicando-se os métodos semiempíricos. Uma alternativa para automatizar esses cálculos é a utilização de planilha eletrônica, uma ferramenta simples, com o intuito de otimizar o tempo e reduzir as falhas humanas. Para demonstrar a aplicabilidade e a eficiência desta ferramenta, desenvolveu-se uma planilha eletrônica através do software Microsoft Excel que, a partir de variáveis como: coesão, ângulo de atrito, peso específico e nível freático; dentre outras, é capaz de estimar a capacidade de carga e a tensão admissível para sapata isolada, em diferentes ocasiões, por diversas metodologias consagradas e, além disso, exibir graficamente a comparação entre os resultados obtidos. Por fim, a ferramenta foi aplicada em três cenários fictícios: (1) sapata quadrada com variação da cota de assentamento; (2) sapata retangular com variação do nível freático e (3) sapata circular com realização de ensaio de placa, comprovando que é possível testar várias hipóteses para um mesmo problema em um curto período de tempo. ABSTRACT: For geotechnical design of shallow foundations it is necessary to know the allowable stress of the soil, obtained indirectly from the load bearing capacity; or directly, applying the semi-empirical methods. An alternative to automate these calculations is the use of spreadsheet, a simple tool, aiming to optimize time and reduce human error. To demonstrate the applicability and effectiveness of this tool, a spreadsheet was developed using the Microsoft Excel software, based on some variables such as: cohesion; friction angle; specific weight; groundwater level; among others, to estimate the load bearing capacity and the allowable stress for isolated footing on different occasions, by several methodologies, and in addition, to show graphically the comparison between the results obtained. Finally, the tool was applied on three fictitious scenarios: (1) Square isolated footing with variation of the settlement quota; (2) rectangular isolated footing with variation of the water level and (3) circular isolated footing with execution of the Plate Load Test, proving that it is possible to test several hypotheses for the same problem in a short period of time.