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

Abstract

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.

Soft Computing Techniques for Laser-Induced Surface Wettability Control

“…Starting from the empirical model so optimized (from Equation (2)), i.e., once found , , , , for each output variable, a different fuzzy regression model can be written, as described by Equation (3): where is the fuzzy function determined through the Transformation Method [ 46 ], while , , , , , are fuzzy numbers. Such an approach is proved to be able to propagate both sources of uncertainty, i.e., the random one due to the process variability and the systematic one due to the simplification introduced by the model itself, to the output qualities [ 51 , 52 ]. This is carried out by implementing the fuzzy arithmetic as a series of interval computations, i.e., α-cut strategy, which are numerically solved by sampling the interval based on a defined schema.…”

An integrated approach for the modelling of silicon carbide components laser milling process

“…This kind of laser source was chosen for the good absorption of SiC at its wavelength, the possibility to release high pulse power (up to 20 kW) and the higher conversion efficiency (about 25%) as well as its flexibility, which makes it suitable to perform different operations, like marking, texturing, micromachining and surface treatments on several materials, such as metals [20,43,52,53], composite materials [29,54] and, of course, ceramics [13,19,55]. In Table 2, the detailed characteristics of the laser system are reported, while in Fig.…”

“…Conversely, cognitive systems, and in particular artificial neural networks (ANNs), extract the relationship directly from data as an input/output (domain/range) pair by imposing a priori architecture (the NN) rather than an existing model. The advantage of this approach is that, under the appropriate conditions, ANNs are able to model a complicated relationship for the modelling to adapt to the different problems [38,39], solving engineering issues in industrial applications, such as in-process control [40,41], and optimisation procedures [42][43][44], as well as in non-destructive evaluation [45]. Moreover, ANNs can allow robust models even in the presence of a high noise ratio [38,46,47].…”

An Integrated Approach for the Modelling of Silicon Carbide Components Laser Milling Process

“…This kind of laser source was chosen for the good absorption of SiC at its wavelength, the possibility to release high pulse power (up to 20 kW), the higher conversion efficiency (about 25%) as well as its flexibility, which makes it suitable to perform different operations, like marking, texturing, micromachining and surface treatments on several materials; such as metals [20,43,52,53], composite materials [29,54] and, of course, ceramics [13,19,55]. In Table 2 the detailed characteristics of the laser system are reported, while in Fig.…”

“…Conversely, Cognitive Systems, and in particular Artificial Neural Networks (ANNs), extract the relationship directly from data as an input/output (domain/range) pair by imposing a priori architecture (the NN) rather than an existing model. The advantage of this approach is that, under the appropriate conditions, ANNs are able to model complicated relationship for the modelling to adapts to the different problems [38,39], solving engineering issues in industrial applications, such as in-process control [40,41], optimisation procedures [42][43][44], as well as in non-destructive evaluation [45]. Moreover, ANNs can allow robust models even in the presence of a high noise ratio [38,46,47].…”