Concentrated loads on steel beams are frequently found in engineering practice. In situations where the load application point is fixed, transversal web stiffeners can be used to provide an adequate resistance, but for economic reasons should be avoided whenever possible. For moving loads, the knowledge of the unstiffened web resistance becomes imperative. Many theories were developed for a better understanding of the problem, however, a 40% error is still present in the current design formulas. A more accurate design formula for this structural problem is very difficult to be obtained, due to the influence of several interdependent parameters and to the insufficient number of experiments found in literature. On the other hand, the structural collapse can be associated to: web yielding, web buckling, web crippling or by their combined influence. Despite this fact, no investigations were found in literature to access their partial of global influence on the beam patch load resistance Neural networks were inspired in the brain structure in order to present human characteristics such as: learning from experience; and generalization of new data from a current set of standards. Preliminary studies used the neural networks potential to forecast the ultimate load of steel beams subjected to concentrated loads. The main aim of Fuzzy Logic is to model the complex approximated way of inference, trying to represent the human ability of making sensible decisions when facing uncertainties. Thus, fuzzy logic is an artificial intelligence technique capable of generating a mechanism for treating inaccurate and incomplete information such as: slenderness, flexibility and stiffness, still being capable of establishing gradual boundaries among the physical phenomena involved. Genetic algorithms are inspired on the Darwins principle of the species evolution and genetics. They are probabilistic algorithms that generate a mechanism of parallel and adaptive best fit survival principle and their reproduction and have been long used in several optimisation problems. This work extends the research developed in a previous MSc. program (Fonseca, 1999) and intends to evaluate and investigate the structural behaviour of steel beams subjected to concentrated loads, identifying the influence of several related parameters. This will be achieved by the use of a neuro-fuzzy system, able to model the intrinsic relationships between the related parameters. The proposed system aim is to relate the physical and geometrical variables that govern the ultimate load with its associated physical behaviour (web yielding, web crippling and web buckling), being capable of establishing gradual boundaries among the physical phenomena involved. This investigation was focused on the development of a neuro fuzzy system. The proposed neuro fuzzy system was trained with data where the collapse mechanism were properly identified validating its results. This investigation also presents a study of patch load design formulae optimization based on genetic algorithm principles. The obtained results may help the future development of a more accurate design formula, that could be incorporated in steel structures design codes, allowing a safer and economical design.