Abstract The wide range of rivets usage goes back to the processes of manufacturing and repairing an aircraft fuselage. When it comes to structural joints, adhesive bonding is said to have some merits which overshadow other joining methods, such as bolting, riveting, and welding. Today, the applications of structural adhesives do not end in aerospace, but they also are ideal for the automotive industry, where the need is to join plates of dissimilar adhesives to produce lightweight car bodies. The hybrid joints also are one of the methods of joining diferent parts of the machine in a durable way in which some benefts such as the signifcant tensile strength, the dissipated energy, and higher reliability during long-term working stand out. In this research, the efect of rivets layout on strength and failure of nanocomposite rivet and hybrid adhesive-rivet joints through two experimental and numerical methods was evaluated. Also, using the artifcial neural networks method, force–displacement curves for specimens were obtained. The results of the experimental tests and the fnite element analysis showed that as the number of rivets increased in the joint of the nanocomposite components, the strength of the joint increased. The layout of the rivets has a signifcant efect on the strength of the rivet joint. According to the performed experiments for achieving the efcient strength in the hybrid joints for the nanocomposite plates, since the strength of the adhesive is very efective, adhesive selection and the appropriate number of rivets are the key factors. The fracture modes in the internal plates of nanocomposite joints (adhesive, rivet, and adhesive-rivet joints) were observed as follows: net-tension, bearing, shear-out, crack propagation, tearing, and shear in adhesive layers. Besides, the numerical model of the work is done using ABAQUS software. The results of software simulation in the numerical model are compatible with the experimental method’s fndings. However, the agreement between the results of experimental and neural network methods is higher. Owing to the results of experiments, the polypropylene nanocomposite as well as the appropriate jointing method can be put forward in the structures of the automotive industry.
