Several studies have been performed on flow characteristics to estimate the scouring depth around the bridge piers. Due to the complication of the problem and variety of the hydraulic and geometric parameters affecting the scouring phenomena, researchers have not developed a general theory. Artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) are alternatives to overcome these problems. These approaches are effective tools to provide the hydraulic engineers precise estimation of the scouring depth around the bridge piers. Although a large number of former studies have just focused on scouring around the bridge piers under steady flow condition and uniform-graded bed materials even using ANN or ANFIS models, lack of studies exists on scouring under unsteady flood flow condition as well as non-uniform bed materials. Generally, river beds are composed mainly of non-uniform materials. While the motion of finer sediment particles initiates, results in the protective effect of greater particles, namely armoring effect on the bed surface, thereby eliminating further erosion of the bed. Furthermore, in most of the rivers the flow regime is commonly unsteady. During a flood, the maximum scouring depth regarding to the peak of the flood hydrograph would be smaller than the equilibrium scouring depth which is commonly estimated using a constant flow discharge. When the flow unsteadiness is pronounced, the difference between the maximum scouring depth and the equilibrium scouring depth is quite substantial and thus should be addressed. In this study armoring effect on local scouring under unsteady flow condition was investigated based on a comprehensive dataset collected by different former investigators using soft computing procedures including ANN and ANFIS models. For this purpose two different models were constructed. The first model was based on 372 set of data collected during practical studies on different bridges in USA. Measurements were conducted under steady flow condition. The second model was developed for estimating the maximum scouring depth in the beds of uniform materials under unsteady flow condition. To present a more accurate model, some strategies including; reduction of dimension and detection of outlier were used to improve the performance of calculations. Learning of Neural Networks were done by means of trial and error. Genetic algorithm and particle swarm optimization methods were applied to develop a novel hybrid learning algorithm for adaptive network based on fuzzy inference system. The new hybrid learning algorithm involves Evolutionary Algorithms including particle swarm optimization (PSO) and Genetic Algorithms (GA) to train the antecedent part. Then the least square method was applied for training the conclusion part. It was shown that ANN and ANFIS models give more accurate results of scouring depth under both steady and unsteady flow conditions compared to the empirical methods. Results highlighted the effectiveness of the data on the estimations of ANN and ANFIS models. Furthermore according to the results, this presented new approach is potentially able to train the ANFIS model in both steady and unsteady flow conditions. In contrast, the weighted training neural networks model optimized with evolutionary algorithms in significantly affected the results. Key Words Bridge piers, scouring, unsteady flow, armoring effects, ANN and ANFIS, optimization algorithms.