An online hidden feature extraction algorithm is proposed for unknown and unstructured agricultural environments based on a supervised kernel locally linear embedding (SKLLE) algorithm. Firstly, an online obtaining method for scene training samples is given to obtain original feature data. Secondly, Bayesian estimation of the a posteriori probability of a cluster center is performed. Thirdly, nonlinear kernel mapping function construction is employed to map the original feature data to hyper-high dimensional kernel space. Fourthly, the automatic deter mination of hidden feature dimensions is performed using a local manifold learning algorithm. Then, a low-level manifold computation in hidden space is completed. Finally, long-range scene perception is realized using a 1-NN classifier. Experiments are conducted to show the effectiveness and the influence of parameter selection for the proposed algorithm. The kernel principal component analysis (KPCA), locally linear embedding (LLE), and supervised locally linear embedding (SLLE) methods are compared under the same experimental unstructured agricultural environment scene. Test results show that the proposed algorithm is more suitable for unstructured agricultural environments than other existing methods, and that the computational load is significantly reduced.
Zhong-Hua MiaoChen-Hui MaZhi-Yuan GaoMing-Jun WangCheng-Liang Liu
Cam-rotor vane motor(CRVM) is one of the new continuous hydraulic servo motors with the characteristics of no pulsation of instantaneous flow rate and output torque,small volume and rotating inertia.It is one of the appropriate actuators for hydraulic servo system which has good dynamic and steady-state performance requirements.The ideal output torque of CRVM is pulseless,but the actual output torque of CRVM is pulsating.This is caused by the disturbing torque of contact components,especially the friction between vane and cam-rotor.In order to get better performance of CRVM,which means more stable output torque and smaller disturbing torque,we discuss four kinds of vane end faces(VEFs).Analytic formulae of the normal contact force and the disturbing torque caused by the vane are derived from systematical force analysis.The normal contact force and the disturbing torque vary through a period under different VEF,and the reduced oil pressure is simulated in this paper.The simulation shows that the VEF with the proper round and reduced oil pressure can significantly decrease the disturbing torque and get better servo performance.The experiment results verify the correctness of the theoretical analysis and simulation.
