Sedimentation tanks are designed for removal of floating solids in water flowing through the water treatment plants. These tanks are one of the most important parts of water treatment plants and their performance directly affects the functionality of these systems. Flow pattern has an important role in the design and performance improvement of sedimentation tanks. In this work, the neural network model is used to study the particle-laden flow in a rectangular sedimentation tank which used the Kaolin as solid particles. The neural network simulation has been designed to simulate and predict the Shear stress coefficient at the bottom of tank for various inlet concentrations and maximum streamwise velocity along the channel. The system was trained on the available data of the two cases. Therefore, we designed the system for finding the best network that has the ability to have the best test and prediction. The proposed system shows an excellent agreement with that of an experimental data in these cases.