Prediction of pile-bearing capacity developing artificial intelligence models has been done over the last decade. Such predictive tools can assist geotechnical engineers to easily determine the ultimate pile bearing capacity instead of conducting any difficult field tests. The main aim of this study is to predict the bearing capacity of pile developing several smart models, i.e., neuro-genetic, neuro-imperialism, genetic programing (GP) and artificial neural network (ANN). For this purpose, a number of concrete pile characteristics and its dynamic load test specifications were investigated to select pile cross-sectional area, pile length, pile set, hammer weight and drop height as five input variables which have the most impacts on pile bearing capacity as the single output variable. It should be noted that all the aforementioned parameters were measured by conducting a series of pile driving analyzer tests on precast concrete piles located in Pekanbaru, Indonesia. The recorded data were used to establish a database of 50 test cases. With regard to data modelling, many smart models of neuro-genetic, neuro-imperialism, GP and ANN were developed and then evaluated based on the three most common statistical indices, i.e., root mean squared error (RMSE), coefficient determination (R2) and variance account for (VAF). Based on the simulation results and the computed indices’ values, it is observed that the proposed GP model with training and test RMSE values of 0.041 and 0.040, respectively, performs noticeably better than the proposed neuro-genetic model with RMSE values of 0.042 and 0.040, neuro-imperialism model with RMSE values of 0.045 and 0.059, and ANN model with RMSE values of 0.116 and 0.108 for training and test sets, respectively. Therefore, this GP-based model can provide a new applicable equation to effectively predict the ultimate pile bearing capacity.
相似文献The pile bearing capacity is considered as the most essential factor in designing deep foundations. Direct determination of this parameter in site is costly and difficult. Hence, this study presents a new technique of intelligence system based on the adaptive neuro-fuzzy inference system (ANFIS)-group method of data handling (GMDH) optimized by the imperialism competitive algorithm (ICA), ANFIS-GMDH-ICA for forecasting pile bearing capacity. In this advanced structure, the ICA role is to optimize the membership functions obtained by ANFIS-GMDH technique for receiving a higher accuracy level and lower error. To develop this model, the results of 257 high strain dynamic load tests (performed by authors) were considered and used in the analysis. For comparison purposes, ANFIS and GMDH models were selected and built for pile bearing capacity estimation. In terms of model accuracy, the obtained results showed that the newly developed model (i.e., ANFIS-GMDH-ICA) receives more accurate predicted values of pile bearing capacity compared to those obtained by ANFIS and GMDH predictive models. The proposed ANFIS-GMDH-ICA can be utilized as an advanced, applicable and powerful technique in issues related to foundation engineering and its design.
相似文献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 nature-inspired 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.
相似文献