Scholarlink

<p>This paper proposes a decentralized Multiple Channel Active Noise Control System (MCANCS) using Exponential Expanded Random Vector Functional Link Artificial Neural Network (EE-RVFLANN) with optimal parameter based Efficient Variational Mode Decomposition (EVMD). The parameters like number of modes and data-fidelity balancing constraint are optimally selected using the Modified Firefly Algorithm (MFA) based on Weighted Kurtosis Index (WKI). The optimization of EVMD parameters ensures better preservation of signal characteristics by enhancing feature quality. The considered MFA is equipped with enhanced searching capability and mutation mechanisms and thus, highly effective for parameter optimization in VMD. The hybrid EVMD-EE-RVFLANN approach is robust against non-stationary noise signal, computationally efficient and well suited for complex signal processing tasks. The effectiveness of the EVMD-ERVFLANN model is validated through extensive simulations and performance analysis. Comparative evaluations with other techniques such as Least Mean Square (LMS), Trigonometric FLANN (TrFLANN), Chebyshev FLANN (ChFLANN), Exponential Expanded ChFLANN (EE-ChFLANN) and EE-RVFLANN models based on Empirical Mode Decomposition (EMD) &amp; VMD demonstrate the superior performance of the proposed system. The superiority of the proposed framework is further validated using practical acoustic disturbances as well as laboratory experiments conducted using NI-USB-6008 platform. A statistical analysis is performed using paired t-tests and 95% confidence intervals to evaluate the reliability and accuracy of the models.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A multiple channel active noise control system based on exponential expanded random vector functional link artificial neural network integrated with optimized parameter efficient variational mode decomposition

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月31日

查看全文
  • Shaktinarayana Mishra,
  • Prachitara Satapathy,
  • Satyendra Singh Yadav,
  • Pradipta Kishore Dash

摘要

This paper proposes a decentralized Multiple Channel Active Noise Control System (MCANCS) using Exponential Expanded Random Vector Functional Link Artificial Neural Network (EE-RVFLANN) with optimal parameter based Efficient Variational Mode Decomposition (EVMD). The parameters like number of modes and data-fidelity balancing constraint are optimally selected using the Modified Firefly Algorithm (MFA) based on Weighted Kurtosis Index (WKI). The optimization of EVMD parameters ensures better preservation of signal characteristics by enhancing feature quality. The considered MFA is equipped with enhanced searching capability and mutation mechanisms and thus, highly effective for parameter optimization in VMD. The hybrid EVMD-EE-RVFLANN approach is robust against non-stationary noise signal, computationally efficient and well suited for complex signal processing tasks. The effectiveness of the EVMD-ERVFLANN model is validated through extensive simulations and performance analysis. Comparative evaluations with other techniques such as Least Mean Square (LMS), Trigonometric FLANN (TrFLANN), Chebyshev FLANN (ChFLANN), Exponential Expanded ChFLANN (EE-ChFLANN) and EE-RVFLANN models based on Empirical Mode Decomposition (EMD) & VMD demonstrate the superior performance of the proposed system. The superiority of the proposed framework is further validated using practical acoustic disturbances as well as laboratory experiments conducted using NI-USB-6008 platform. A statistical analysis is performed using paired t-tests and 95% confidence intervals to evaluate the reliability and accuracy of the models.