Combined Fuzzy and Genetic Algorithm for the Optimisation of Hybrid Composite-Polymer Joints Obtained by Two-Step Laser Joining Process

In the present work, genetic algorithms and fuzzy logic were combined to model and optimise the shear strength of hybrid composite-polymer joints obtained by two step laser joining process. The first step of the process consists of a surface treatment (cleaning) of the carbon fibre-reinforced polymer (CFRP) laminate, by way of a 30 W nanosecond laser. This phase allows removing the first matrix layer from the CFRP and was performed under fixed process parameters condition. In the second step, a diode laser was adopted to join the CFRP to polycarbonate (PC) sheet by laser-assisted direct joining (LADJ). The experimentation was performed adopting an experimental plan developed according to the design of experiment (DOE) methodology, changing the laser power and the laser energy. In order to verify the cleaning effect, untreated laminated were also joined and tested adopting the same process conditions. Analysis of variance (ANOVA) was adopted to detect the statistical influence of the process parameters. Results showed that both the laser treatment and the process parameters strongly influence the joint performances. Then, an uncertain model based on the combination of fuzzy logic and genetic algorithms was developed and adopted to find the best process parameters’ set able to give the maximum joint strength against the lowest uncertainty level. This type of approach is especially useful to provide information about how much the precision of the model and the process varies by changing the process parameters.