Active Noise Hybrid Feedforward/Feedback Control Using Neural Network Compensation*

2001 ◽  
Vol 124 (1) ◽  
pp. 100-104 ◽  
Author(s):  
Zhang Qizhi ◽  
Jia Yongle
Keyword(s):  
Neural Network ◽  
Noise Control ◽  
Control Method ◽  
Active Noise Control ◽  
Equivalent Model ◽  
Gradient Descent Method ◽  
Nonlinear Simulation ◽  
Control Approach ◽  
Active Noise ◽  
Nonlinear Noise

The nonlinear active noise control (ANC) is studied. The nonlinear ANC system is approximated by an equivalent model composed of a simple linear sub-model plus a nonlinear sub-model. Feedforward neural networks are selected to approximate the nonlinear sub-model. An adaptive active nonlinear noise control approach using a neural network enhancement is derived, and a simplified neural network control approach is proposed. The feedforward compensation and output error feedback technology are utilized in the controller designing. The on-line learning algorithm based on the error gradient descent method is proposed, and local stability of closed loop system is proved based on the discrete Lyapunov function. A nonlinear simulation example shows that the adaptive active noise control method based on neural network compensation is very effective to the nonlinear noise control, and the convergence of the NNEH control is superior to that of the NN control.

scholarly journals Active Noise Feedback Control Using a Neural Network

2001 ◽  
Vol 8 (1) ◽  
pp. 15-19 ◽  
Author(s):  
Zhang Qizhi ◽  
Jia Yongle
Keyword(s):  
Neural Network ◽  
Control System ◽  
Feedback Control ◽  
Noise Control ◽  
Finite Impulse Response ◽  
Gradient Descent Method ◽  
Noise Power ◽  
Nonlinear Simulation ◽  
Active Noise ◽  
Nonlinear Noise

The active noise control (ANC) is discussed. Many digital ANC systems often based on the filter-x algorithm for finite impulse response (FIR) filter use adaptive filtering techniques. But if the primary noise path is nonlinear, the control system based on adaptive filter technology will be invalid. In this paper, an adaptive active nonlinear noise feedback control approach using a neural network is derived. The feedback control system drives a secondary signal to destructively interfere with the original noise to cut down the noise power. An on-line learning algorithm based on the error gradient descent method was proposed, and the local stability of closed loop system is proved using the discrete Lyapunov function. A nonlinear simulation example shows that the adaptive active noise feedback control method based on a neural network is very effective to the nonlinear noise control.

Active Noise Control Using Phase-Compensated, Damped Resonant Filters

2005 ◽  
Vol 128 (2) ◽  
pp. 148-155 ◽  
Author(s):  
Jesse B. Bisnette ◽  
Adam K. Smith ◽  
Jeffrey S. Vipperman ◽  
Daniel D. Budny
Keyword(s):  
Noise Control ◽  
Control Method ◽  
Active Noise Control ◽  
Control Device ◽  
Modal Control ◽  
Pass Filter ◽  
Acoustic Transducers ◽  
Active Noise ◽  
The Impact ◽  
Resonant Filters

An active noise control device called active noise absorber or ANA, which is based upon damped, resonant filters is developed and demonstrated. It is similar to structural positive position feedback (PPF) control, with two exceptions: (1) Acoustic transducers (microphone and speaker) cannot be truly collocated, and (2) the acoustic actuator (loudspeaker) has significant dynamics. The speaker dynamics can affect performance and stability and must be compensated. While acoustic modal control approaches are typically not sought, there are a number of applications where controlling a few room modes is adequate. A model of a duct with speakers at each end is developed and used to demonstrate the control method, including the impact of the speaker dynamics. An all-pass filter is used to provide phase compensation and improve controller performance and permits the control of nonminimum phase plants. A companion experimental study validated the simulation results and demonstrated nearly 8 dB of control in the first duct mode. A multi-modal control example was also demonstrated producing an average of 3 dB of control in the first four duct modes.

scholarly journals Selective Fixed-filter Active Noise Control Based on Convolutional Neural Network

2021 ◽  
pp. 108317
Author(s):  
Dongyuan Shi ◽  
Bhan Lam ◽  
Kenneth Ooi ◽  
Xiaoyi Shen ◽  
Woon-Seng Gan
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Noise Control ◽  
Active Noise Control ◽  
Active Noise

scholarly journals Noise cancellation system based on active noise control. 2nd Report, Adaptive control method.

1991 ◽  
Vol 57 (534) ◽  
pp. 431-436
Author(s):  
Seiichirou SUZUKI ◽  
Takurou HAYASHI ◽  
Katsuyoshi NAGAYASU ◽  
Susumu SARUTA ◽  
Hiroshi TAMURA
Keyword(s):  
Adaptive Control ◽  
Noise Control ◽  
Control Method ◽  
Active Noise Control ◽  
Noise Cancellation ◽  
Active Noise

Reinforcement Learning for Active Noise Control in a Hydraulic System

2021 ◽  
Vol 143 (6) ◽  
Author(s):  
Eric R. Anderson ◽  
Brian L. Steward
Keyword(s):  
Reinforcement Learning ◽  
Hydraulic System ◽  
Noise Control ◽  
Control Method ◽  
Active Noise Control ◽  
Operating Point ◽  
Hydraulic Pressure ◽  
Hydraulic Systems ◽  
Active Noise ◽  
Pressure Ripple

Abstract Hydraulic pressure ripple in a pump, as a result of converting rotational power to fluid power, continues to be a problem faced when developing hydraulic systems due to the resulting noise generated. In this paper, we present simulation results from leveraging an actor-critic reinforcement learning method as the control method for active noise control in a hydraulic system. The results demonstrate greater than 96%, 81%, and 61% pressure ripple reduction for the first, second, and third harmonics, respectively, in a single operating point test, along with the advantage of feed forward like control for high bandwidth response during dynamic changes in the operating point. It also demonstrates the disadvantage of long convergence times while the controller is effectively learning the optimal control policy. Additionally, this work demonstrates the ancillary benefit of the elimination of the injection of white noise for the purpose of system identification in the current state of the art.

scholarly journals Active Noise Control Using a Functional Link Artificial Neural Network with the Simultaneous Perturbation Learning Rule

2009 ◽  
Vol 16 (3) ◽  
pp. 325-334 ◽  
Author(s):  
Ya-li Zhou ◽  
Qi-zhi Zhang ◽  
Tao Zhang ◽  
Xiao-dong Li ◽  
Woon-seng Gan
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Noise Control ◽  
Active Noise Control ◽  
Time Varying ◽  
Mean Square ◽  
Least Mean Square ◽  
Functional Link ◽  
Active Noise ◽  
Artificial Neural

In practical active noise control (ANC) systems, the primary path and the secondary path may be nonlinear and time-varying. It has been reported that the linear techniques used to control such ANC systems exhibit degradation in performance. In addition, the actuators of an ANC system very often have nonminimum-phase response. A linear controller under such situations yields poor performance. A novel functional link artificial neural network (FLANN)-based simultaneous perturbation stochastic approximation (SPSA) algorithm, which functions as a nonlinear mode-free (MF) controller, is proposed in this paper. Computer simulations have been carried out to demonstrate that the proposed algorithm outperforms the standard filtered-x least mean square (FXLMS) algorithm, and performs better than the recently proposed filtered-s least mean square (FSLMS) algorithm when the secondary path is time-varying. This observation implies that the SPSA-based MF controller can eliminate the need of the modeling of the secondary path for the ANC system.

Improved functional link artificial neural network via convex combination for nonlinear active noise control

2016 ◽  
Vol 42 ◽  
pp. 351-359 ◽  
Author(s):  
Haiquan Zhao ◽  
Xiangping Zeng ◽  
Zhengyou He ◽  
Shujian Yu ◽  
Badong Chen
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Noise Control ◽  
Convex Combination ◽  
Active Noise Control ◽  
Functional Link ◽  
Active Noise ◽  
Artificial Neural
Sign in / Sign up

Export Citation Format

Share Document