基于NARMA-L2的岸电并网电压控制策略研究  被引量:2

Research on Shore Power Grid connected Voltage Control Strategy Based on Neural NetworkNARMA-L2

在线阅读下载全文

作  者:乔森 杨奕飞[1,2] QIAO Sen;YANG Yi-fei(School of Electronics and Information,Jiangsu University of Science and Technology,ZhenjiangJiangsu 212003,China;Marine Equipment and Technology Institute,Jiangsu University of Science and Technology,Zhenjiang Jiangsu 212003,China)

机构地区:[1]江苏科技大学电子信息学院,江苏镇江212003 [2]江苏科技大学海洋装备研究院,江苏镇江212003

出  处:《计算机仿真》2021年第7期83-88,共6页Computer Simulation

基  金:江苏省科技厅产业前瞻与共性关键技术项目(BE2018109);江苏省研究生科研与实践创新计划项目(SJCX191192)。

摘  要:岸电并网控制技术是船舶岸电的核心技术之一,能够实现岸侧对靠港船舶的不间断和稳定供电。针对传统岸电控制策略在并网瞬间和负载变换时电压产生较大波动的问题,提出了一种基于神经NARMA-L2自校正模型的岸电并网V/F控制策略,使岸电控制器具有更强的动态响应能力和控制精度,在岸电合闸之前使用预同步控制技术对岸侧电源进行调节,减少并网时刻产生的电流冲击。通过仿真表明,基于神经自校正改进的V/F控制策略相比传统的V/F控制策略,能够明显提升并网时刻和负载切换时刻的电压稳定性,减少船舶电网的电压波动。The shore-connected grid control technology is one of the core technologies of ship shore power, which can realize uninterrupted and stable power supply to the ship on the shore. Aiming at the problem that the voltage of the traditional shore power control strategy is greatly fluctuated during the grid-connected instant and load change, a V/F control strategy based on the neural NARMA-L2 self-correction model is proposed. The shore power controller has stronger dynamic response capability and control precision. Before the shore power was closed, the pre-synchronous control technology was used to adjust the shore power supply to reduce the current impact generated during the grid connection. Simulation experiments show that the V/F control strategy based on neural self-correction can significantly improve the voltage stability of grid-connected time and load switching time and reduce the voltage fluctuation of ship power grid compared with the traditional V/F control strategy.

关 键 词:岸电 并网控制 非线性自回归滑动平均模型 恒压频比控制 

分 类 号:TM464[电气工程—电器]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象