Hybrid Intelligent-Assisted Approach for Process Parameters Optimization to Enhance the Sustainable Manufacturing of Thermoplastic Laminates

Thermoplastic fiber-reinforced polymer (FRP) composites present a more sustainable alternative to their thermoset-based counterparts, owing to their potential for repair and recycling. Their capacity to meet sustainability standards, along with their ability to provide high stiffness and strength, has increased the use of thermoplastic FRP composites in load-bearing applications. Improving thermoplastic FRP's performance and sustainability is instrumentally dependent on optimizing their fabrication process parameters to minimize the energy consumed in their manufacturing without compromising their structural properties. Accordingly, this work utilizes experiments and artificial intelligence to model the relationship between interlaminar shear strength and the critical processing parameters in thermoplastic FRP laminate fabrication. These parameters are processing time, temperature, and pressure. Moreover, this work aims to utilize artificial intelligence to design the most sustainable processing sequence that reduces energy consumption without affecting FRP's structural integrity, represented by interlaminar shear strength. The artificial intelligence (AI) approach combines the use of an Adaptive Neuro Fuzzy Inference System (ANFIS) model and a Particle Swarm Optimization (PSO) algorithm in a Hybrid Intelligent-Assisted Model. Results demonstrated that increasing the processing time, pressure, and temperature beyond a certain threshold can deteriorate the fabricated laminates' performance. Moreover, results show that the energy consumption of the process can be reduced by reducing processing time without affecting the produced laminate's structural properties. A processing time of 6.44 minutes was determined by using a cascading Hybrid approach intelligent as the minimum time that can be used without affecting the interlaminar shear strength. Minimizing the processing time can reduce energy consumption by 34.56%.