Teaching-Learning-Based Optimization of Neural Networks for Water Supply Pipe Condition Prediction

The bulk of water pipes experience major degradation and deterioration problems. This research aims at estimating the condition in Shattora Shaker Al-Bahery’s distribution networks, Egypt. developed models involve training Elman neural network (ENN) feed-forward (FFNN) coupled with particle swarm optimization (PSO), genetic algorithms (GA), sine cosine algorithm (SCA), teaching-learning-based (TLBO) algorithm. For network, inputs to these are pipe characteristics such as length, wall thickness, diameter, material, lining coating, surface type, traffic distribution, cathodic protection, flow velocity, c-factor. Al-Bahery data gathered include age, depth, thickness. Three assessment criteria used evaluate suggested machine learning models, namely index agreement (IOA), correlation coefficient (R), root mean squared error (RMSE). results reveal that coupling FFNN TLBO outperforms other prediction models. Therefore, FFNN-TLBO model can be a valuable tool for simulating condition. study could help municipality allocate available budget effectively plan required maintenance rehabilitation actions.