To enable exoskeleton wearers to walk on level ground, estimation of lower limb movement is particularly indispensable. In fact, it allows the exoskeleton to follow the human movement in real time. In this paper, the general regression neural network optimized by golden section algorithm (GS-GRNN) is used to realize prediction of the human lower limb joint angle. The human body hip joint angle and the surface electromyographic (sEMG) signals of the thigh muscles are taken as the inputs of a neural network to predict joint angles of lower limbs. To improve the prediction accuracy in different gait phases, the plantar pressure signals are also added into the input. After that, the error between the prediction result and the actual data decreases significantly. Finally, compared with the prediction result of the BP neural network, GRNN shows splendid prediction performance for its less processing time and higher prediction accuracy.

Polyamide 66 (PA66) is a material with high wear resistance, toughness, and heat resistance. However, low stiffness and thermal deformation during thermal processes define applications in many conditions. Carbon powder efficiently enhances stiffness and reduces thermal deformation, which makes up defects of plastic materials. However, forming a composite with fused deposition modeling (FDM) that accumulates material to a specified location by melting plastic filaments is limited, including fluidity and viscosity to form normally. In this paper, filaments of polyamide 66 (PA66) reinforced with carbon powder were produced. Digimat was used to analyze the composite material properties of different carbon contents and predict the proper carbon content. Then, the material properties were imported to ANSYS software to simulate the thermal deformation of the workpieces during processing. It was verified that adding carbon powder is helpful in decreasing thermal deformation. Comparing experiments and simulations, we found that 20% carbon mass fraction was best, and that thermal deformation was minimal at 240 °C nozzle temperature while hot bed temperature was 90 °C. The optimal ratio of extrusion speed to filling speed was 0.87, and the best aspect ratio was 0.25.

A deleterious Laves phase forms in the solidified structure of Inconel 718 (IN718) alloy during laser cladding. However, effective removal methods have not yet been identified. In this study, we first added the IN718 alloy cladding layers with a trace amount of vanadium (V, 0.066 wt.%). Then, we studied the solidification structure of cladding layers using a confocal laser scanning microscope and scanning electron microscopy. The microstructure and Laves phase morphology were investigated. The distribution of niobium (Nb) was observed by experiment as well. We found that V is evenly distributed in dendrites and interdendritic zones. A more refined dendrite structure, reduced second dendrite arm spacing and lower volume fraction of Laves phase were observed in the solidification structure. The results of linear energy-dispersive X-ray spectroscopy (EDS) indicate that the concentration of Nb decreases with an increasing of the distance from the Laves phase. The V-containing sample displayed a relatively slower decreasing tendency. The IN718 alloy sample was harder with the addition of V. In addition, the porosity of the sample decreased compared with the blank sample. The presented findings outline a new method to inhibit the Nb segregation in IN718 alloy during laser cladding, providing reference significance for improving the performance of IN718 alloy samples during actual processing.

In order to study the modular design of computer numerical control machine tools oriented to customer demands, the customer demand information model was established based on rough analytic hierarchy process and information entropy by analyzing and transforming customer demands. Based on the domain mapping method of axiomatic design and quality function deployment integration, the product function model and structure model of computer numerical control machine tools are established. Based on fuzzy clustering analysis, the module division of computer numerical control machine tools is studied, and the dynamic clustering diagram of computer numerical control machine tools is formed with MATLAB as the operating environment. Based on Technique for Order Preference by Similarity to Ideal Solution method, the scheme of computer numerical control machine tools module division is evaluated. Taking the horizontal computer numerical control machine tool products of Shenyang Machine Tool Group as an example, the module division is carried out. The example design and the result analysis prove that the module division system is very effective and fast.