A manufacturer’s fabric first undergoes an abrasion test and manual visual inspection to grade the fabric prior to shipment to ensure that there are no defects present. Manual visual classification consumes a considerable amount of human resources. Furthermore, extended use of the eyes during visual inspection often causes occupational injuries, resulting in a decrease in the efficiency of the entire operation. In order to overcome and avoid such situations, this study proposed the use of deep principal components analysis-based neural networks (DPCANNs) for fabric pilling identification. In the proposed DPCANN, the characteristics of the hairball were automatically captured using deep principal components analysis (DPCA), and the hairball class was identified using the neural network and the support vector machine (SVM). The experimental results showed that the proposed DPCANN has an average accuracy of 99.7% at the hairball level, which is in line with the needs of the industry. The results also confirmed that the proposed hairball classification method is superior to other methods.
This paper combines the Taguchi-based response surface methodology (RSM) with a multi-objective hybrid quantum-behaved particle swarm optimization (MOHQPSO) to predict the optimal surface roughness of Al7075-T6 workpiece through a CNC turning machining. First, the Taguchi orthogonal array L27 (36) was applied to determine the crucial cutting parameters: feed rate, tool relief angle, and cutting depth. Subsequently, the RSM was used to construct the predictive models of surface roughness (Ra, Rmax, and Rz). Finally, the MOHQPSO with mutation was used to determine the optimal roughness and cutting conditions. The results show that, compared with the non-optimization, Taguchi and classical multi-objective particle swarm optimization methods (MOPSO), the roughness Ra using MOHQPSO along the Pareto optimal solution are improved by 68.24, 59.31 and 33.80%, respectively. This reveals that the predictive models established can improve the machining quality in CNC turning of Al7075-T6.
This paper combines an artificial neural network (ANN) with a traditional genetic algorithm (GA) method, called hybrid genetic algorithm (HGA), to analyze the warpage of multi-cavity plastic injection molding parts. Simulation results indicate that the minimum and the maximum warpage of the hybrid genetic algorithm (HGA) method were lower than that of the traditional GA method and CAE simulation. These results reveal that, when HGA is applied to multi-cavity plastic warpage analysis, the optimal process conditions are significantly better than those using the traditional GA method or CAE simulation.
There are many different types of manufacturing methods for heat sink fins in the current market. The aim of this study is to design an extrusion die for a radial-finned heat sink using a commercial finite element package, DEFORMTM 3D. We then conduct a series of simulation analyses with different variables such as friction factor, ram velocity, and fin gate stage of the die to evaluate the methods of decreasing the warping in the extrusion process. The die is assumed as a rigid body in the analyses. The results confirm the suitability of DEFORMTM 3D to design an extrusion die achieving a lower warping behavior of the radial-finned heat sink.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.