The complexity of real-world optimization problems has been steadily driving computer science researchers to come up with new and efficient optimization techniques. Precise modeling of the plastic boards by use of experimental data, in which discarded surgical masks are used, is a major challenge to engineering professionals. In this article, a Modified Gaussian Quantum Particle Swarm Optimization (GQPSO) is proposed for the efficient and accurate estimation of manufacturing plastic board characteristics. The algorithm was initially tested using two benchmark functions, which included Elongation at fracture (EF) and Percentage of total elongation at maximum force (MF), using material compositions including those of polypropylene (PP), Maleic anhydride Grafted Polypropylenes (MA), Titanium dioxide (TiO2), and Tensile Strength (TS). Experiment findings and comparisons with other optimization techniques clearly show that this suggested method is successful in terms of final solution correctness, success rate, convergence speed, and stability. The suggested GQPSO optimization approach was then evaluated against the manufacturer’s datasheet of the optimal outcome of both elongations at fracture and the percentage of total elongation at maximum force are 29.678%, 11.082%, 0.4412%, and 26.712, respectively for polypropylene (PP), Maleic anhydrite Grafted polypropylene (MA), Titanium dioxide (TiO2), and Tensile Strength (TS) during waste surgical mask design. The findings prove the efficiency of the Gaussian Quantum-behaved Particle swarm optimization (GQPSO) algorithm in different working conditions.