To improve the quality of the additive manufacturing (AM) products, it is necessary to estimate surface roughness distribution in advance. Although surface roughness…
To improve the quality of the additive manufacturing (AM) products, it is necessary to estimate surface roughness distribution in advance. Although surface roughness estimation has been previously studied, factors leading to the creation of a rough surface and a comprehensive test for model validation have not been adequately investigated. Therefore, this paper aims to establish a robust model using empirical data based on optimized artificial neural networks (ANNs) to estimate the surface roughness distribution in fused deposition modelling parts. Accordingly, process parameters such as time, cost and quality should be optimized in the process planning stage.
Process parameters were selected via a literature review of surface roughness estimation modelling by analytical and empirical methods, and then a specific test part was fabricated to provide a complete evaluation of the proposed model. The ANN structure was optimized by trial and error method and evolutionary algorithms. A novel methodology based on the combination of the intelligent algorithms including the ANN, linked to the particle swarm optimization (PSO) and imperialist competitive algorithm (ICA), was developed. The PSOICA algorithm was implemented to increase the capability of the ANN to perform much faster and converge more precisely to favorable results. The performances of the ANN models were compared to the most well-known analytical models at build angle intervals of equal size. The most effective process variable was found by sensitivity analysis. The validity of proposed model was studied comprehensively where different truncheon parts and medical case studies including molar tooth, skull, femur and a custom-made hip stem were built.
This paper presents several improvements in surface roughness distribution modelling including a more suitable method for process parameter selection according to the design criteria and improvements in the overall surface roughness of parts as compared to analytical methods. The optimized ANN based on the proposed advanced algorithm (PSOICA) represents precise estimation and faster convergence. The validity assessment confirms that the proposed methodology performs better in varied conditions and complex shapes.
This research fills an important gap in surface roughness distribution estimation modelling by using a test part designed for that purpose and optimized ANN models which uses purely empirical data. The novel PSOICA combination enhances the ability of the ANN to perform more accurately and quickly. The advantage in using actual surface roughness values is that all factors resulting in the creation of a rough surface are included, which is impossible if other methods are used.