Tian Yantao

Jilin University, Yung-chi, Jilin Sheng, China

Are you Tian Yantao?

Claim your profile

Publications (16)1.63 Total impact

  • Xu Zhuojun · Tian Yantao · Li Yang
    [Show abstract] [Hide abstract]
    ABSTRACT: Two new feature extraction methods, window sample entropy and window kurtosis, were proposed, which mainly aims to complete the surface Electromyography (sEMG)-muscle force pattern recognition for intelligent bionic limb. The inspiration is drawn from physiological process of muscle force generation. Five hand movement tasks were implemented for sEMG-muscle force data record. With two classical features: Integrated Electromyography (IEMG) and Root Mean Square (RMS), two new features were fed into the wavelet neural network to predict the muscle force. To solve the issues that amputates' residual limb couldn't provide full train data for pattern recognition, it is proposed that force was predicted by neural network which is trained by contralateral data in this paper. The feasibility of the proposed features extraction methods was demonstrated by both ipsilateral and contralateral experimental results. The ipsilateral experimental results give very promising pattern classification accuracy with normalized mean square 0.58 ± 0.05. In addition, unilateral transradial amputees will benefit from the proposed method in the contralateral experiment, which probably helps them to train the intelligent bionic limb by their own sEMG.
    No preview · Article · Apr 2015 · Journal of Bionic Engineering
  • Y. Zhiming · T. Yantao · X. Zhuojun · L. Yang
    [Show abstract] [Hide abstract]
    ABSTRACT: Intelligent prosthesis is an important component of rehabilitation medicine works, and it plays a decisive role in people's lives. In order to reduce the unnecessary material and time-consuming, and improve design efficiency in the actual prosthetics physical prototype design process, this paper proposes a solution that studying virtual bionic hands in mechanical virtual prototyping, Adams software, which can avoid the mass experiments in development of prototyping, so exploiting virtual bionic hands is significant. Thus, this paper uses virtual technology to build a simulation system. First, use the Adams software to create a virtual humanoid robot model with 14 degrees of freedom; second, build a virtual bionic hand's control system by Matlab/Simulink module. As the complexity of the bionic hand model, this paper choose PD controller, it simply and easily to achieve. Finally, realize the co-simulation of Matlab and Adams virtual bionic hand model with multi-degree of freedom by the model and control system interface module. Simulation results show that the virtual bionic hand has good tracking ability, and can complete the relevant action steadily.
    No preview · Article · Oct 2014
  • Dong Bing · Tian Yantao · Zhou Changjiu
    [Show abstract] [Hide abstract]
    ABSTRACT: This thesis takes the Li-ion power battery as the researching object, and makes the experiment comparison on the popular battery dynamic equivalent circuit model. Though the analyzing result of the experiment, and combination of the power battery actual characteristics, the author points out the battery dynamic equivalent circuit model based on the first order RC net, and identificates the parameters, validates the simulation precision. At the same time, basing on this model, the author optimizes the popular estimating method of state of charge of power battery. At last, by the experiment, the thesis validates the precision of the estimating method.
    No preview · Conference Paper · Jan 2014
  • Xu Zhuojun · Tian Yantao · Zhang Li · Yang Zhiming
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, three experiments were conducted about the extension/flexion movements of the index finger at two speeds 0.4Hz and 0.8Hz of the 10 subjects. AR coefficients of sEMG signals were used as the feature parameters fed into the fuzzy neural network. The motion direction identification, fixed finger joint angle recognition and trajectory forecast are implemented in this study. The experimental results are generally satisfactory: the accuracy rate of motion direction identification is 100% (0.4Hz) and 92.5% (0.8Hz); the accuracy rates of fixed finger joint angle recognition all reached 100% in 0.4Hz and 0.8Hz experiments; joint angle forecast achieved a good trajectory tracking. The results of this study show the feasibility of extraction finger joint angle information from sEMG.
    No preview · Conference Paper · Jan 2013
  • Shang Xiaojing · Tian Yantao · Li Yang
    [Show abstract] [Hide abstract]
    ABSTRACT: The surface EMG (sEMG) is a biological electrical signal of neuromuscular activity distribution. From the point of the non-stationary and nonlinear, the independent component analysis method is firstly used to eliminate the power frequency interference in sEMG. Secondly, the low noise signal is processed by empirical mode decomposition (EMD), then use the decomposed signal to establish AR model. The model coefficients are used as signal features and PNN optimized by particle swarm optimization (PSO) is used to classify six types of forearm motions. The experimental results demonstrate the effectiveness of the proposed method.
    No preview · Conference Paper · Sep 2011
  • Xu Zhuojun · Tian Yantao · Li Yang
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we use ADAMS to design a model of intelligent prosthetic hand, which has the high humanoid shape, its weight and size are similar to adults hand The proposed model has 16 degrees of freedom (dofs), which are split into 14 dofs for the five fingers, and 2 dofs for the wrist. The model allows the execution of Activities of Daily Living (ADLs) like grasp, wrist turn and so on, in order to the research the control algorithm of the prosthetic hand, Integration of ADAMS with MATLAB for designing and developing prosthetic hand system is presented in this paper. The model can complete simple movements by proportional control algorithm.
    No preview · Conference Paper · Sep 2011
  • Zhang Li · Tian Yantao · Li Yang
    [Show abstract] [Hide abstract]
    ABSTRACT: In order to improve the accuracy rate of surface EMG (sEMG) pattern recognition, a modified Kohonen self-organizing competitive network is presented in this paper. Kohonen network has a simple algorithm and short time for clustering. There we adjust the structure of this network, and turn it into a supervised learning network by adding an output layer, then optimize the initial weight. The integrate EMG and power spectral density ratio of sEMG as the input of modified Kohonen network to identify the five kinds of movement patterns: extension of thumb, extension of wrist, flexion of wrist, side flexion of wrist and extension of palm. Experiments show that, compared with the traditional Kohonen network, the modified neural network classifier has the higher classification ability.
    No preview · Conference Paper · Jan 2011
  • Bai Ming · Tian Yantao · Wang Yongxiang
    [Show abstract] [Hide abstract]
    ABSTRACT: A decoupled fuzzy sliding mode controller design is proposed. The decoupled method provides a simple way to achieve asymptotic stability for a class of eighth order nonlinear systems with only seven fuzzy rules. Using single input fuzzy logic model and signed distance concept, the response of system will converge faster than that of previous reports with conventional fuzzy algorithm. Simulation and experimental results demonstrate the effectiveness of the proposed approach.
    No preview · Article · Jan 2011
  • Li Yang · Tian Yantao · Chen Yantao
    [Show abstract] [Hide abstract]
    ABSTRACT: For realizing seven hand gestures classification correctly, wavelet transform is used firstly to eliminate the noise in sEMG, because of its multi-resolution analysis characteristic. Then combine time domain features (such as EMG integral, variance, the third-order AR model coefficients) with frequency domain features (power-spectrum) as the inputs of neural network classifier to discriminate seven motion patterns. According to the shortcoming of traditional BP neural network algorithm which is easily trapped into local minimum, an improved one based on existing BP algorithm and simulated annealing algorithm is proposed in this paper. The experimental results indicate that the correct rate is above 90% by using the above algorithm. Comparing with traditional BP algorithm, the novel one has better recognition capability.
    No preview · Conference Paper · Aug 2010
  • Tao Jun · Tian Yantao · Tao Jianwu
    [Show abstract] [Hide abstract]
    ABSTRACT: In the paper, the effect of airborne environment is analyzed to measuring model of electromagnetic vector sensor array and the measuring model of airborne electromagnetic vector sensor array is built based on the polarization of electromagnetic wave and response of electromagnetic vector sensor. The establishment of measuring model is theoretic base of application of airborne electromagnetic vector sensor array.
    No preview · Article · May 2010
  • Gong Xun · Tian Yantao · Liu Dejun
    [Show abstract] [Hide abstract]
    ABSTRACT: Passive dynamic walking refers to a class of bipedal machines that are able to walk down a gentle slope with no external control or energy input. The two-dimensional passive dynamic model has been shown to been inherently stable, and the three-dimensional model introduce another problematic degree of freedom: roll. In this paper we introduce some 3D biped walking models. In these 3D models, we find that passive walking cycles exist, but the roll motion is unstable, resembling that of an inverted pendulum. At last we introduce some control laws for stabilizing this motion.
    No preview · Article · Jan 2010
  • Qi Jilong · Tian Yantao · Gong Yimin · Zhucheng
    [Show abstract] [Hide abstract]
    ABSTRACT: Extended Kalman filter observer for the direct torque controlled permanent magnet synchronous motor drive is talked about, the estimation schemes for PMSM rotor initial position and rotate speed are obtained. Direct torque control is studied. The PMSM rotor initial position is indispensable to sensorless PMSM direct torque control systems. High frequency voltage signal is injected into stator winding to calculate the PMSM rotor initial position with the high frequency current signal generated. The PMSM rotor initial position is applied in the sensorless PMSM direct torque control system based on EKF(extended Kalman filter observer) observer. The sensorless PMSM direct torque control system is realized in the Matlab environment. The simulation results indicate that the PMSM rotor initial position calculated from current signal is accurate, moreover, the rotor position and speed obtained from Extended Kalman filter observer track the actual rotor position and speed rapidly.
    No preview · Conference Paper · Nov 2008
  • Wang Hongrui · Tian Yantao · Fu Siyan · Sui Zhen
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper proposes nonlinear control methods for output regulation of ball and plate system. Positions of the ball are regulated with double feedback loops. Recursive backstepping design is employed for the external feedback loop, while switching control scheme is used in the inner feedback loop. System performance was tuned by backstepping parameters. Simulation results show that the proposed nonlinear control works wells in both stabilization and tracking control. Asymptotical stabilities are also achieved under unknown external disturbance in the experiments.
    No preview · Conference Paper · Aug 2008
  • Liu Zhenze · Zhang Peijie · Tian Yantao · Zhou Changjiu
    [Show abstract] [Hide abstract]
    ABSTRACT: Some basic passive energy tracking control strategies on the passive compass biped, with controller added at the hip and at the ankle respectively following the model Goswami has presented in 1997, has been addressed in the paper. The idea is, with the use of the hip and ankle control respectively, to attain to the reference energy of certain limit cycle more efficiently than that without control and also to attain to any target limit cycle we expect within some region. In addition, we analyze the global control property on the robots in detail and moreover a comparison between the simply ankle and hip control respectively has been discussed, Consequently, a result comes out that both the control laws we presented will enlarge the basin of attraction of the limit cycle in great degree.
    No preview · Conference Paper · Jul 2007
  • Hong Wei · Tian Yantao · Xu Bin
    [Show abstract] [Hide abstract]
    ABSTRACT: A dynamic map-matching method for adaptability is presented by analyzing the change in requirement of map-matching performance in the process of vehicular navigation. The method is provided with the capability of identifying three different states (selecting a road initially, selecting a follow-up road and positioning in the known road) and determining corresponding algorithms of map-matching dynamically. In order to satisfy the needs of map-matching in different states, some algorithms are developed respectively. Simulated experiments show that the method implements more timely map-matching successfully.
    No preview · Article · Jan 2007
  • Zhang Peijie · Tian Yantao · Gong Yimin
    [Show abstract] [Hide abstract]
    ABSTRACT: The basic principle of direct torque control of PMSM was analyzed. To drive the motor in a wide speed range, a direct torque control system was presented. Constant torque control was adopted when rotor's speed was less than the rating speed, or else, the field weakening control was employed. At discrete time, the estimation of stator flux linkage was revised using the current model. The estimation error was reduced and robustness was enhanced. It is proved that fast torque response can be obtained by simulation and implementation of the control strategy
    No preview · Article · Jan 2006