دانلود رایگان مقاله انگلیسی ارزیابی عملکرد الگوریتم های الهام گرفته از طبیعت برای طراحی فونداسیون شمعی درجا - اشپرینگر 2016

Abstract

The bored pile foundations are gaining popularity in construction industry because of ease in construction, low noise and vibrations. The load-carrying capacity of bored pile foundations is dependent upon soil– structure interaction. This being a three-dimensional problem is further complicated due to large variations in soil properties. Also, modeling of soil is difficult because of its nonlinear and anisotropic nature. For such cases, the artificial neural network (ANN) and nature-inspired optimization techniques have been found to be highly suitable to attain acceptable levels of accuracy. In the present study, two ANNs have been trained for determination of unit skin friction and unit end bearing capacity from soil properties. The training data for ANNs have been obtained from finite element analysis of pile foundations for 4809 different soil types. A dataset of 50 field pile loading test results is used to check the performance of the developed artificial neural networks. To enhance the accuracy of the developed ANNs, two correlation factors have been determined by applying four popular nature-inspired optimization algorithms: particle swarm optimization (PSO), fire flies, cuckoo search and bacterial foraging. In order to rank these optimization algorithms, parametric and nonparametric statistical analysis has been carried out. The results of optimization algorithms have been compared to find the most suitable solution for this multi-dimensional problem which has a large number of nonlinear equality constraints. The effectiveness and suitability of the natureinspired algorithms for the presented problem have been demonstrated by computing correlation coefficients with field pile loading test results and then with the total execution time taken by each algorithm. The results of comparison show that PSO is the best performer for such constrained problems.

7 Conclusion

The study portrays that the use of nature-inspired algorithms for finding the correlation factors substantially improves the accuracy of ANNs for predicting the pile load capacities. The dataset comprising of 50 full-scale pile loading tests has been used for calculating the correlation factors. The ANNs have been developed using the data acquired from the finite element analysis of axially loaded piles of various geometrical properties and from the data pertaining to a wide range of soil parameters. The pile foundation was analyzed 4809 times to ascertain the exact soil–structure interaction and for determining the accurate values of unit skin friction and unit end bearing capacity. The skin friction correlation factor was taken as objective function. A comparative study of four nature-inspired algorithms for designing bored pile foundation was carried out. Data pertaining to field pile loading tests were used for the evaluating the performance of these algorithms. The correlation coefficient between the predicted values and field pile loading test data was found to be the highest (0.982) in the case of PSO. The PSO was thus found to be the best performing algorithm. PSO was also found to exhibit maximum computational efficiency as it took least computational time due to less number of calculation steps. Parametric and nonparametric statistical analysis tests were carried out to further substantiate the results obtained. The P value obtained using ANOVA test showed maximum similarity between the PSO predicted values and field test values. The P values of Tukey HSD, Scheffe´ and Bonferroni also depicted similar results. The PSO has also been found to be more efficient in terms of time taken and is less complex as compared to conventional methods like load transfer method and elastic method for finding the pile load capacity. Hence, it can be concluded that PSO algorithm is the most suitable algorithm for the optimization of pile foundation design in a constrained environment.