In this paper, adaptive neural control is proposed for a class of multi-input multi-output (MIMO) nonlinear unknown state time-varying delay systems in block-triangular control structure. Radial basis function (RBF...In this paper, adaptive neural control is proposed for a class of multi-input multi-output (MIMO) nonlinear unknown state time-varying delay systems in block-triangular control structure. Radial basis function (RBF) neural net- works (NNs) are utilized to estimate the unknown continuous functions. The unknown time-varying delays are compensated for using integral-type Lyapunov-Krasovskii functionals in the design. The main advantage of our result not only efficiently avoids the controller singularity, but also relaxes the restriction on unknown virtual control coefficients. Boundedness of all the signals in the closed-loop of MIMO nonlinear systems is achieved, while The outputs of the systems are proven to converge to a small neighborhood of the desired trajectories. The feasibility is investigated by two simulation examples.展开更多
To increase the accuracy and real-time performance of on-line assessment of maize planting,a CAN bus based maize monitoring system for precision planting was designed and tested both in laboratory and field.The system...To increase the accuracy and real-time performance of on-line assessment of maize planting,a CAN bus based maize monitoring system for precision planting was designed and tested both in laboratory and field.The system was mainly comprised of:(a)seeding rate sensors based on opposite-type infrared photoelectric cell for counting the dropping seeds;(b)a decimeter GPS receiver for acquiring planter position and operation speed;(c)a vehicle monitoring terminal based on ARM Cotex-m4 core chip to acquire and process the whole-system data;(d)a touchscreen monitor to display the planter performance for the operator;and(e)a buzzer alarm to sound a warning when skip and double seeding happened.Taking the applicability,dependability and feasibility of the monitoring system into consideration,the opposite-type infrared photoelectric sensors were selected and their deployment strategies in the 6-port seed tube were analyzed.To decrease the average response time,a distributed information communication structure was adopted.In this information communication mode,collectors were designed for each individual sensor and communicated with sensors through two-wire CAN bus.A sensor together with the designed collector is called a sensor node,and each of them worked individually and took the responsibility for acquiring,processing,and transiting the on-going information.Laboratory test results showed that the random error distribution was approximately normal,and by liner analysis,the system observed value and the true value had as a liner relationship with coefficient of determination R^(2)=0.9991.Series of field tests showed that the seeding rate maximum relative error of the 6-port seed tube was 2.92%,and the maximum root mean square error(RMSE)was about 1.64%.The monitoring system,including sensor nodes,vehicle monitoring terminal and a touch-screen monitor,was proved to be dependable and stable with more than 14 d of continuous experiments in field.展开更多
基金supported by the National Natural Science Foundation of China(Nos.60864001,61074124)
文摘In this paper, adaptive neural control is proposed for a class of multi-input multi-output (MIMO) nonlinear unknown state time-varying delay systems in block-triangular control structure. Radial basis function (RBF) neural net- works (NNs) are utilized to estimate the unknown continuous functions. The unknown time-varying delays are compensated for using integral-type Lyapunov-Krasovskii functionals in the design. The main advantage of our result not only efficiently avoids the controller singularity, but also relaxes the restriction on unknown virtual control coefficients. Boundedness of all the signals in the closed-loop of MIMO nonlinear systems is achieved, while The outputs of the systems are proven to converge to a small neighborhood of the desired trajectories. The feasibility is investigated by two simulation examples.
基金We acknowledge that this work was financially supported by the National Key Research and Development Program of China(2017YFD0700604,2017YFD0700701)the Beijing Science&Technology Plan Project(D161100003216001)the academy of science and technology innovation team program supported by Beijing Academy of Agriculture and Forestry(JNKYT201607).
文摘To increase the accuracy and real-time performance of on-line assessment of maize planting,a CAN bus based maize monitoring system for precision planting was designed and tested both in laboratory and field.The system was mainly comprised of:(a)seeding rate sensors based on opposite-type infrared photoelectric cell for counting the dropping seeds;(b)a decimeter GPS receiver for acquiring planter position and operation speed;(c)a vehicle monitoring terminal based on ARM Cotex-m4 core chip to acquire and process the whole-system data;(d)a touchscreen monitor to display the planter performance for the operator;and(e)a buzzer alarm to sound a warning when skip and double seeding happened.Taking the applicability,dependability and feasibility of the monitoring system into consideration,the opposite-type infrared photoelectric sensors were selected and their deployment strategies in the 6-port seed tube were analyzed.To decrease the average response time,a distributed information communication structure was adopted.In this information communication mode,collectors were designed for each individual sensor and communicated with sensors through two-wire CAN bus.A sensor together with the designed collector is called a sensor node,and each of them worked individually and took the responsibility for acquiring,processing,and transiting the on-going information.Laboratory test results showed that the random error distribution was approximately normal,and by liner analysis,the system observed value and the true value had as a liner relationship with coefficient of determination R^(2)=0.9991.Series of field tests showed that the seeding rate maximum relative error of the 6-port seed tube was 2.92%,and the maximum root mean square error(RMSE)was about 1.64%.The monitoring system,including sensor nodes,vehicle monitoring terminal and a touch-screen monitor,was proved to be dependable and stable with more than 14 d of continuous experiments in field.