Azami, Ramtin2023-09-122023-09-122021-12https://unbscholar.lib.unb.ca/handle/1882/37366Crane selection for construction projects is a complicated and time-consuming process due to a vast number of parameters and inter-related planning constraints. Selecting the most appropriate cranes can improve the productivity and safety of construction projects as selecting the wrong crane can result in deadly incidents. An algorithm for automatic mobile crane selection in heavy industrial construction projects that employs heuristic and artificial neural network methods, entitled Crane Configurator, is introduced in this research. Crane Configurator consists of two stages: 1) mobile crane configuration selector and 2) mobile crane configuration predictor. The developed application considers the module's features (e.g., weight, length, and width), the project’s budget, schedule, and safety. It proposes a crane for the project that satisfies the user’s demand. The proposed mobile crane predictor employs mathematical and machine learning techniques, and it leverages the power of relational databases to train an artificial neural network (ANN) to predict the cranes for future projects. Accuracy rates as high as 74% have been achieved for the final results through evaluating the model using the test set from real projects. Lift engineers, project stakeholders, and construction crew can benefit directly or indirectly through proper crane selection, which shortens the project’s schedule, improves the job site's safety, and reduces the project's cost.ix, 128electronicenhttp://purl.org/coar/access_right/c_abf2TECHNOLOGY::Engineering mechanics::Construction engineeringTECHNOLOGY::Materials science::Construction materialsTECHNOLOGY::Information technology::Automatic controlmaster thesisLei, ZhenCivil Engineering