Single Neuron PID Control Based on Expert Experiences for Temperature Difference Control System of a Digester

Considering the temperature difference of displacement cooking characterized by severe non-linearity, large time delay, and real-time control, a cascade PID adaptive control strategy composed of a single neuron is proposed to ensure cooking temperature uniformity. The control strategy introduces expert experiences to adjust the single neuron gain K, while a single neuron PID self-learning and adaptive ability, as well as cascade advantage can be combined to realize the real-time and fast temperature difference control. In the Simulink, the s-function of this control strategy is used to carry out a dynamic simulation experiment with temperature difference characteristics and verify the robustness and response to model mismatch. Compared to conventional temperature difference-flow PID cascade control and single neuron PID cascade control, this control strategy has better robustness and stronger adaptability. The results of real-time control on the THJSK-1 experiment platform indicate this control strategy is feasible.

NEW HYDRAULIC ACTUATOR'S POSITION SERVOCONTROL STRATEGY

A new hydraulic actuator-hydraulic muscle （HM） is described, and the actuator＇s features and applications are analyzed, then a position servocontrol system in which HM is main actuator is set up. The mathematical model of the system is built up and several control strategies are discussed. Based on the mathematical model, simulation research and experimental investigation with subsection PID control, neural network self-adaptive PID control and single neuron self-adaptive PID control adopted respectively are carried out, and the results indicate that compared with PID control, neural network self-adaptive PID control and single neuron self-adaptive PID control don＇t need controlled system＇s accurate model and have fast response, high control accuracy and strong robustness, they are very suitable for HM position servo control system.

Neural network modeling and intelligent control of FCAW penetration

The neural network modeling of FCAW penetration is researched in this paper, molten pool image is acquired by CCD, and preweld gap is gotten from laser vision system, the weld penetration is estimated according to the information include welding current, welding voltage, weld width, molten pool half length and gap width. The training samples of network can be partially gotten by numerical simulation. Single neuron self-tuning PID weld penetration controller is designed, and improved Hebb learning algorithm is applied for weights adjusting. Welding current is adjusted to make the weld penetration stable. The results of experiment with various cross-section and preweld gap workpiece show that this system is suitable to molten pool control.

Modeling and test on height adjustment system of electrically-controlled air suspension for agricultural vehicles

To reduce the damages of pavement,vehicle components and agricultural product during transportation,an electric control air suspension height adjustment system of agricultural transport vehicle was studied by means of simulation and bench test.For the oscillation phenomenon of vehicle height in driving process,the mathematical model of the vehicle height adjustment system was developed,and the controller of vehicle height based on single neuron adaptive PID control algorithm was designed.The control model was simulated via Matlab/Simulink,and bench test was conducted.Results show that the method is feasible and effective to solve the agricultural vehicle body height unstable phenomenon in the process of switching.Compared with other PID algorithms,the single neuron adaptive PID control in agricultural transport vehicle has shorter response time,faster response speed and more stable switching state.The stability of the designed vehicle height adjustment system and the ride comfort of agricultural transport vehicle were improved.