<p>Reliable transportation of crude oil, a resource indispensable for meeting global demands, particularly in transportation and energy sectors, is paramount for ensuring economic stability and sustained development. For the sustainable operation of pipelines, which are frequently used in the carrying of crude oil, the maintenance and operating parameters of the pipeline must be followed precisely. Wax formed in crude oil pipelines jeopardizes the operational reliability of the crude oil pipeline due to many serious problems it will bring. Regular monitoring of wax formation is not possible due to the fact that pipelines traverse very different geographical conditions. In order to overcome this difficulty, a comprehensive study has been carried out on estimating the wax appearance distance in a crude oil pipeline with an artificial intelligence approach and defining the optimal artificial intelligence algorithm. Three dissimilar artificial neural network models with Levenberg-Marquardt, Bayesian Regularization and Scaled Conjugate Gradient algorithms were established and the prediction performance of each was analyzed. In the input layer of artificial neural networks, parameters affecting wax formation such as wall thickness, pipe thermal conductivity, surrounding heat transfer coefficient and ambient temperature are defined as input parameters. In the output layer, wax appearance distances were obtained in the near pipe wall and near pipe center. The outcomes revealed that the model with Bayesian Regularization algorithm can predict the wax appearance distance in crude oil pipelines with higher accuracy compared to other models.</p>