Surface condensers are among the widest equipment used in various industrial sectors as well as in power plants. One of the most common types of surface condensers is shell and tube heat exchangers which are robust and easy to use in multifold environments. On the other hand, adaptive neuro-fuzzy inference systems (ANFIS) are widely used in many engineering applications such as healthcare services, production management, quality control, emergency responses, traffic control and so on. In the current study, a shell-and-tube-surface condenser is represented by a phenomenological model and a parametric analysis of the operational and geometric variables is performed. These results are adjusted by an ANFIS in order to enable a systematic tool that allows the design and evaluation of the equipment under other operating conditions. The use of ANFIS to evaluate the operation of a surface condenser or to make a previous design based on certain operating conditions demonstrates advantages over the use of traditional approaches such as the Engineering Equation Solver (EES) because the use of fuzzy rules offers a high combinatorial option in the analysis that joint with the possibility of learning of neural networks allow to obtain a reliable and easy application tool to quickly achieve the desired results within a planned range of operation and design, being possible, in addition, to change the ranges of the input variables without needing to do calculations, only reusing the tool obtained with different data, depending on the conditions of the process in question. The results obtained were compared with a conventional evaluation tool (EES) and the percentage error when comparing both approaches is lesser than 10%, which demonstrates the validity of the neuro-fuzzy system proposed. (C) 2019 Elsevier Ltd. All rights reserved.