A type of single neuron adaptive PID regulator with auto-tuning gain is proposed and applied to the work control of fans, waterpumps and air-pressers etc. in Handan Iron & Steel Compel China. The robusthess of ind...A type of single neuron adaptive PID regulator with auto-tuning gain is proposed and applied to the work control of fans, waterpumps and air-pressers etc. in Handan Iron & Steel Compel China. The robusthess of induStrial parameter closed-loop process controlsystems is improved, and the work quality of the systems bettered.展开更多
基于神经网络理论中的神经元模型与学习算法,设计了一种主动队列管理算法SNAPI(Single Neuron-based Adaptive PI controller).控制器根据系统误差在线调整PI控制器的控制参数,以适应动态变化的网络参数.运用Nyquist稳定判据给出了系统...基于神经网络理论中的神经元模型与学习算法,设计了一种主动队列管理算法SNAPI(Single Neuron-based Adaptive PI controller).控制器根据系统误差在线调整PI控制器的控制参数,以适应动态变化的网络参数.运用Nyquist稳定判据给出了系统在平衡点附近的局部稳定条件.最后通过仿真检验了SNAPI,并比较了它与使用固定控制参数的PI算法的性能.展开更多
Control design is important for PEMFC (proton exchange membrane fuel cell) distributed power generator to satisfy user requirement for safe and stable operation. For a complex multi-variable dynamic system, a dynami...Control design is important for PEMFC (proton exchange membrane fuel cell) distributed power generator to satisfy user requirement for safe and stable operation. For a complex multi-variable dynamic system, a dynamic simulation model is first established. In view of close coupling and non-linear relationships between variables, the intelligent auto-adapted PI decoupling control method is used. From the simulation results it is found that, by bringing quadratic performance index in the single neuron, constructing adaptive PI controller, and adjusting gas flow rates through the second pressure relief valve and air compressor coordinately, both anode and cathode pressures can be maintained at ideal levels.展开更多
文摘A type of single neuron adaptive PID regulator with auto-tuning gain is proposed and applied to the work control of fans, waterpumps and air-pressers etc. in Handan Iron & Steel Compel China. The robusthess of induStrial parameter closed-loop process controlsystems is improved, and the work quality of the systems bettered.
文摘基于神经网络理论中的神经元模型与学习算法,设计了一种主动队列管理算法SNAPI(Single Neuron-based Adaptive PI controller).控制器根据系统误差在线调整PI控制器的控制参数,以适应动态变化的网络参数.运用Nyquist稳定判据给出了系统在平衡点附近的局部稳定条件.最后通过仿真检验了SNAPI,并比较了它与使用固定控制参数的PI算法的性能.
基金Project supported by National High-Technology Research andDevelopment Program of China (Grant No .2002AA517020)
文摘Control design is important for PEMFC (proton exchange membrane fuel cell) distributed power generator to satisfy user requirement for safe and stable operation. For a complex multi-variable dynamic system, a dynamic simulation model is first established. In view of close coupling and non-linear relationships between variables, the intelligent auto-adapted PI decoupling control method is used. From the simulation results it is found that, by bringing quadratic performance index in the single neuron, constructing adaptive PI controller, and adjusting gas flow rates through the second pressure relief valve and air compressor coordinately, both anode and cathode pressures can be maintained at ideal levels.