TECHNICAL PAPER Modelling and control of weld height reinforcement in the GMAW process Jorge Giron Cruz 1 • Edna Moncayo Torres 1 • Sadek C. Absi Alfaro 1 Received: 9 January 2017 / Accepted: 13 February 2018 Ó The Brazilian Society of Mechanical Sciences and Engineering 2018 Abstract In a recent research related to technological application in monitoring and control of welding, the use of various approaches to improve the productivity and quality through the development of techniques and automatic control systems is observed. This paper presents a methodology for modelling and control of the weld height reinforcement, allowing adjusting the process parameters, which can be implemented in the field of research or, in certain cases, in the industrial sector as an approach to the control of weld bead geometries. This was developed for the geometric characteristic studied in an integrated system of images acquisition, modelling and control system. The weld bead formation is measured through an acquisition system and processing of images using a low-cost web cam. The wire feed speed, the welding speed and voltage are predicted using an artificial neural network based on the desired weld height reinforcement. The control system is based on fuzzy logic. Keywords Gas metal arc welding (GMAW) Á Digital image processing Á Artificial neural networks Á Fuzzy logic 1 Introduction The joining of metal pieces by electric arc welding with shielding gas is one of the manufacturing processes most frequently used in the metal construction industry. In recent years, many new applications and welding processes were developed based on technological innovation and market demands. Monitoring of the physical variables generated by the electric arc; monitoring of the weld pool; analysis opera- tional of the process parameters; visual inspection and the definition of strategies of control for the process and the weld bead geometric characteristics have been considered important factors in the efforts for the monitoring and controlling of the welding process, as well as improving weld quality. This paper proposes a monitoring of some physical variables generated by the electric arc and the weld bead geometric parameters in the gas metal arc welding (GMAW) process, to the analysis of their potential to use as manipulated and measured variables in a feedback control system. The purpose of the research is to present a methodology that serves as a guide to the modelling and control of the weld height reinforcement and the possibility of the monitoring of the weld bead formation. A study is made to determine the appropriate process parameters to generate weld beads with good appearance and the desired characteristics. To find the best parameter setting, artificial neural networks have been used for the design of models that represent the relationship between certain responses based on different input variables. Empirical rules used by specialized operators for the analysis and modification of the dimensions of the weld bead are used to develop fuzzy logic controllers for the weld height reinforcement, based on the measurement of the images acquired from the weld bead formation (through a web camera) with the desired measurements in the weld bead. According to the control strategies adopted in the controllers, it is necessary to change the wire feed speed to Technical Editor: Ma´rcio Bacci da Silva. & Jorge Giron Cruz jorgeandres@unb.br Edna Moncayo Torres emmoncayo@unb.br Sadek C. Absi Alfaro sadek@unb.br 1 Departamento de Engenharia Mecaˆnica, Universidade de Brası ´lia, Brası ´lia, Brazil 123 Journal of the Brazilian Society of Mechanical Sciences and Engineering (2018)40:164 https://doi.org/10.1007/s40430-018-1080-1