多通道PID神经网络解耦有源控制算法

Decoupling Algorithm Based on PID Neural Network for Multi-channel Active Noise Control

为满足多目标区域降噪要求,研究多通道有源噪声控制系统至关重要。随着声通道数量增加,通道间会出现相互耦合,增加系统复杂性且影响系统稳定性。为解决通道耦合问题,提出一种基于比例积分微分(PID)神经网络和滤波x最小均方算法(FxLMS)的多通道噪声解耦算法(PIDNN-FxLMS)。在传统FxLMS算法基础上,利用PID神经网络对有源控制系统控制参数进行调整,获得最优控制,同时对多通道有源控制系统解耦和控制问题进行处理。结果表明,PIDNN-FxLMS算法的收敛速度明显快于传统FxLMS算法,在降噪效果方面,该算法残余误差信号幅值最小,更适用于多通道有源噪声控制系统。

It is critical to study the multi-channel active noise control(ANC) systems for satisfying the requirements of noise reduction in multi-target positions.As the number of acoustic channels increases,there will be coupling among them,which will increase the complexity of the system and affect the stability of the system.To solve the channel coupling problem,a decoupling algorithm based on the Proportion Integration Differentiation(PID) neural network and the filtered-x least-mean-square(FxLMS) for the multi-channel ANC is proposed.Based on the traditional FxLMS algorithm,PID neural network is used to adjust the control parameters of the active control system to obtain the optimal control.Meanwhile,the decoupling and control problems of the multi-channel active control system are processed.The results show that the convergence speed of the PIDNN-FxLMS algorithm is much faster than the traditional FxLMS algorithm.The proposed algorithm has the best control effect and the smallest error signal amplitude,and is more suitable for multi-channel ANC.