基于神经网络逆系统方法的链式STATCOM线性化解耦控制

针对链式STATCOM补偿负载无功电流以及稳定电网电压的控制问题,建立了链式STATCOM动态数学模型,得出了双变量δ、M(移相角与调制比)和电流的关系式,提出了一种基于神经网络逆系统控制方法,通过对该链式STATCOM系统可逆的验证、神经网络的构建以及控制系统的设计,实现了链式STATCOM输出的有功-无功电流的线性化解耦控制。仿真结果表明,在感性负载与容性负载进行切换以时,该控制策略取得了良好的动态效果以及稳态效果,使得装置具有较好的抗参数变化、抗负载扰动性能,从而验证了该控制策略的有效性及可行性。

Linearization and decoupling control of cascade STATCOM based on neural network inverse system method

Aiming at the control problem of cascaded STATCOM to compensate the load reactive current and stabilize the grid voltage, this paper establishes dynamic mathematics model of cascaded STATCOM, and obtains the relation-ship of the two variablesδ、M and current, then proposes a control method based on artificial neural networks inverse system.The linearization decoupling control of active and reactive current of cascaded STATCOM is realized through the verification of reversibility, construction of artificial neural networks as well as the design of control system for the system of cascaded STATCOM.Finally, the simulation results show that the control strategy acquires good dynamic effect and static effect when switching inductive load into capacitive load or in turn, which makes the device possess better performance to resist parameters change and load disturbance, thereby, it illustrates the effectiveness and the feasibility of the control strategy.