Adaptive Noise Reduction Research Articles

A new Method for Predicting PM2.5 Concentrations in Subway Stations Based on a Multiscale Adaptive Noise Reduction Transformer -BiGRU Model and an Error Correction Method

A new Method for Predicting PM2.5 Concentrations in Subway Stations Based on a Multiscale Adaptive Noise Reduction Transformer -BiGRU Model and an Error Correction Method

An improved Takagi–Sugeon–Kang-based FxLMS algorithm and its active noise control in electric bus driving position

This paper proposed an improved filtered-x least mean square (FxLMS) algorithm based on the fuzzy control rule of Takagi–Sugeon–Kang (TSK) to solve the drawback of slow convergence for standard FxLMS algorithm. The TSK-FxLMS is a control framework with two inputs and three outputs constructed by the error signal and its integral as input variables. To validate its effectiveness and applicability, in-vehicle active noise control (ANC) modelling and adaptive noise reduction at the driver’s position of an electric bus are thoroughly investigated. Firstly, the four noise signals for the different working conditions at 50 km/h, acceleration, coasting and braking are collected, and their spectral analyses are performed. Secondly, the effects of step size and fuzzy control parameters of ANC model on weight convergence and noise reduction effect are analysed and determined. Finally, the results of calculating and comparing the residual signals’ waveforms, frequency spectra, sound pressure levels and tracking performance indicate that the proposed TSK-FxLMS algorithm outperforms the standard FxLMS algorithm with faster convergence and better noise reduction effect.

Domain adaptive noise reduction with iterative knowledge transfer and style generalization learning

Low-dose computed tomography (LDCT) denoising tasks face significant challenges in practical imaging scenarios. Supervised methods encounter difficulties in real-world scenarios as there are no paired data for training. Moreover, when applied to datasets with varying noise patterns, these methods may experience decreased performance owing to the domain gap. Conversely, unsupervised methods do not require paired data and can be directly trained on real-world data. However, they often exhibit inferior performance compared to supervised methods. To address this issue, it is necessary to leverage the strengths of these supervised and unsupervised methods. In this paper, we propose a novel domain adaptive noise reduction framework (DANRF), which integrates both knowledge transfer and style generalization learning to effectively tackle the domain gap problem. Specifically, an iterative knowledge transfer method with knowledge distillation is selected to train the target model using unlabeled target data and a pre-trained source model trained with paired simulation data. Meanwhile, we introduce the mean teacher mechanism to update the source model, enabling it to adapt to the target domain. Furthermore, an iterative style generalization learning process is also designed to enrich the style diversity of the training dataset. We evaluate the performance of our approach through experiments conducted on multi-source datasets. The results demonstrate the feasibility and effectiveness of our proposed DANRF model in multi-source LDCT image processing tasks. Given its hybrid nature, which combines the advantages of supervised and unsupervised learning, and its ability to bridge domain gaps, our approach is well-suited for improving practical low-dose CT imaging in clinical settings. Code for our proposed approach is publicly available at https://github.com/tyfeiii/DANRF.

An Adaptive Noise Reduction Method for High Temperature and Low Voltage Electromagnetic Detection Signals Based on SVMD Combined with ICEEMDAN.

In view of the low signal-to-noise ratio (SNR) of shear wave electromagnetic acoustic transducers (EMAT) in the detection of high-temperature equipment, the use of low excitation voltage (LEV) further deteriorates the detection results, resulting in the echo signal containing defects being drowned in noise. For the extraction of the EMAT signal, an adaptive noise reduction method is proposed. Firstly, the minimum envelope entropy is taken as the fitness function for the Harris Hawks Optimizer (HHO), and the optimal successive variational mode decomposition (SVMD) balance parameter is searched by HHO adaptive iteration to decompose LEV EMAT signals at high temperatures. Then the filter is carried out according to the excitation center frequency and correlation coefficient threshold function. Then, improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) is used to decompose the filtered signal and combine the kurtosis factor to select the appropriate intrinsic mode functions. Finally, the signal is extracted by the Hilbert transform. In order to verify the effectiveness of the method, it is applied to the low-voltage detection of 40Cr from 25 °C to 700 °C. The results show that the method not only suppresses the background noise and clutter noise but also significantly improves the SNR of EMAT signals, and most importantly, it is able to detect and extract the 2 mm small defects from the echo signals. It has great application prospects and value in the LEV detection of high-temperature equipment.

Audio fault diagnosis of belt conveyors based on improved variational modal decomposition and improved adaptive noise reduction convolutional network in strong noise environments

Abstract Fault diagnosis of belt conveyors is crucial for coal mine production, but audio-based fault diagnosis in underground coal mines remains challenging due to the strong noise environment. To address this problem, a method for audio fault diagnosis of belt conveyors based on improved variational modal decomposition and improved adaptive noise reduction convolutional networks in a strong noise environment is proposed. Firstly, the improved beluga whale optimization is designed by introducing the non-linear balance factor and non-linear probability and combining them with the proposed cyclical shock factor to optimize the variational modal decomposition parameters to achieve noise reduction and signal reconstruction. Secondly, an improved adaptive noise reduction convolutional network is developed using an adaptive threshold activation function and an improved loss function to enhance noise robustness and fault diagnosis accuracy. Finally, the proposed method's effectiveness is evaluated in low and strong noise environments, with experimental results demonstrating superior fault diagnosis performance. In low noise environments, the fault diagnosis accuracy is 98.61%, and in strong noise environments, it is 98.96%, outperforming existing fault diagnosis methods.

A machine-learning architecture with two strategies for low-speed impact localization of composite laminates

In this paper, a machine-learning architecture with the integration of two strategies including data enhancement and adaptive generation scheme for Impact Localization (IL) are developed to address the aforementioned issues for location identification of impacts on composite laminates. Two main contributions are included in this research: First, response signals collected from low-speed impact experiments under various working conditions are denoised using Adaptive Sparse Noise Reduction Algorithm (ASNRA), which aims at maximizing the preservation of the original signal amplitude, thereby avoiding the underestimation of pulse features during denoising. Then a RIME-optimized Dual-layer Support Vector Regression (RDSVR) method for the real-time update of hyperparameters is implemented in the machine-learning architecture to realize IL. The superior performances of the IL architecture over different IL models are validated throughout the numerical examples in terms of stability and efficiency. Results demonstrate that proposed architecture has the ability to realize the accurate and robust IL of composite laminates.

Composite fault feature extraction for gears based on MCKD-EWT adaptive wavelet threshold noise reduction

For the strong noise gear fault vibration signal is relatively weak, and the transmission path is complex and variable, in the case of composite faults, the modulation of different fault characteristics of the frequency, coupling, resulting in the actual acquisition of the fault characteristics are difficult to extract and separate. Aiming at fault feature extraction and separation, an adaptive threshold denoising fault detection method based on Maximum correlated kurtosis deconvolution (MCKD) and Empirical wavelet transform (EWT) is proposed. Firstly, envelope entropy and information entropy are used as fitness functions, and the parameters of the MCKD algorithm are optimized by the improved particle swarm algorithm, then the empirical wavelet decomposition is carried out on the signals, and finally adaptive wavelet threshold denoising is carried out on the decomposed Intrinsic mode functions (IMFs) components. The results of experimental data analysis show that compared with the feature extraction methods such as spatial scale threshold EWT-MCKD and Complete Ensemble Empirical Mode Decomposition (CEEMDAN)-MCKD, the proposed method is more suitable for the diagnosis of gear composite faults in a strong background noise environment, the noise interference is effectively suppressed, and the extraction effect of gear composite fault features is more obvious.

Incipient Bearing Fault Extraction based on an Adaptive Multi-stage Noise Reduction Method

Considering the strong nonlinear and non-stationary characteristics of rolling bearing vibration signals, this paper proposes a multi-stage noise reduction method using adaptive variational mode decomposition and modulation signal bispectrum (AVMD-MSB) to extract the fault features of rolling bearings. Firstly, the AVMD is employed to adaptively select VMD parameters K and α and decompose the signal into a series of Intrinsic mode functions (IMFs), which allows an adaptive selection of the parameters of VMD. Then, all IMF components are reconstructed with weights according to the index of correlation kurtosis to avoid accidental omission of the IMFs containing important fault information. Finally, MSB is implemented to further suppress residual noises and interference components in the signal, precisely extract the bearing fault features. Numerical simulation and case study show that the AVMD-MSB is more advantageous in extracting fault characteristics from rolling bearing vibration signals compared with AVMD-Envelope and conventional VMD-MSB.

Machine Tool Wear Prediction Technology Based on Multi-Sensor Information Fusion.

The intelligent monitoring of cutting tools used in the manufacturing industry is steadily becoming more convenient. To accurately predict the state of tools and tool breakages, this study proposes a tool wear prediction technique based on multi-sensor information fusion. First, the vibrational, current, and cutting force signals transmitted during the machining process were collected, and the features were extracted. Next, the Kalman filtering algorithm was used for feature fusion, and a predictive model for tool wear was constructed by combining the ResNet and long short-term memory (LSTM) models (called ResNet-LSTM). Experimental data for thin-walled parts obtained under various machining conditions were utilized to monitor the changes in tool conditions. A comparison between the ResNet and LSTM tool wear prediction models indicated that the proposed ResNet-LSTM model significantly improved the prediction accuracy compared to the individual LSTM and ResNet models. Moreover, ResNet-LSTM exhibited adaptive noise reduction capabilities at the front end of the network for signal feature extraction, thereby enhancing the signal feature extraction capability. The ResNet-LSTM model yielded an average prediction error of 0.0085 mm and a tool wear prediction accuracy of 98.25%. These results validate the feasibility of the tool wear prediction method proposed in this study.

CNN-based noise reduction for multi-channel speech enhancement system with discrete wavelet transform (DWT) preprocessing.

Speech enhancement algorithms are applied in multiple levels of enhancement to improve the quality of speech signals under noisy environments known as multi-channel speech enhancement (MCSE) systems. Numerous existing algorithms are used to filter noise in speech enhancement systems, which are typically employed as a pre-processor to reduce noise and improve speech quality. They may, however, be limited in performing well under low signal-to-noise ratio (SNR) situations. The speech devices are exposed to all kinds of environmental noises which may go up to a high-level frequency of noises. The objective of this research is to conduct a noise reduction experiment for a multi-channel speech enhancement (MCSE) system in stationary and non-stationary environmental noisy situations with varying speech signal SNR levels. The experiments examined the performance of the existing and the proposed MCSE systems for environmental noises in filtering low to high SNRs environmental noises (-10 dB to 20 dB). The experiments were conducted using the AURORA and LibriSpeech datasets, which consist of different types of environmental noises. The existing MCSE (BAV-MCSE) makes use of beamforming, adaptive noise reduction and voice activity detection algorithms (BAV) to filter the noises from speech signals. The proposed MCSE (DWT-CNN-MCSE) system was developed based on discrete wavelet transform (DWT) preprocessing and convolution neural network (CNN) for denoising the input noisy speech signals to improve the performance accuracy. The performance of the existing BAV-MCSE and the proposed DWT-CNN-MCSE were measured using spectrogram analysis and word recognition rate (WRR). It was identified that the existing BAV-MCSE reported the highest WRR at 93.77% for a high SNR (at 20 dB) and 5.64% on average for a low SNR (at -10 dB) for different noises. The proposed DWT-CNN-MCSE system has proven to perform well at a low SNR with WRR of 70.55% and the highest improvement (64.91% WRR) at -10 dB SNR.

A New Efficient Multi-Channel Fast NLMS (MC-FNLMS) Adaptive Algorithm for Audio Teleconferencing systems

In this paper, we propose a new multichannel fast normalized least mean square (MC-FNLMS) algorithm for audio teleconferencing systems. The main idea behind the proposed MC-FNLMS algorithm is based on the introduction of a first order prediction process on the input noisy signals before the adaptive filtering process of each channel. The proposed algorithm is considered as an alternative solution for the existing algorithm in multi-channel applications. A full stability analysis of the proposed algorithm is derived along this paper. Simulation results of a comparison between the proposed MC-FNLMS algorithm and the two classical Multichannel Normalized Least Mean Square (MC-NLMS) and the Multichannel Affine Projection (MC-APA) algorithms, in terms of convergence speed, noise reduction and computational complexity, show the superiority of the proposed algorithm on multichannel adaptive noise reduction.

An efficient Automatic Modulation Classification method based on the Convolution Adaptive Noise Reduction network

Due to the influence of noise in the received signal in non-cooperative communication, it is difficult for existing Automatic modulation classification methods to balance classification accuracy and model complexity. This paper proposes a novel Convolutional Adaptive Noise Reduction (CANR) network, which consists of an Adaptive Noise Reduction (ANR) module and a Convolutional Feature Extraction (CFE) module. The ANR and CFE modules denoise the combined input and capture the spatiotemporal features in the time series. Experiments on benchmark datasets show that the proposed network has the fewest training parameters and state-of-the-art recognition accuracy under the same conditions.

A Study of Fault Signal Noise Reduction Based on Improved CEEMDAN-SVD

In light of the challenges posed by the complex structural characteristics and significant coupling of vibration signals in rotating machinery, this study proposes an adaptive noise reduction method called Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN). Additionally, an enhanced threshold screening Singular Value Decomposition (SVD) algorithm is introduced to address the issues pertaining to noise identification and feature extraction in the context of vibration signals from rotating machinery, which are subjected to complex noise interference. The effectiveness of the proposed approach is substantiated through the evaluation of key metrics, such as the signal-to-noise ratio (SNR), as well as the utilization of advanced signal analysis techniques, including Short Time Fourier Transform (STFT) and Continuous Wavelet Transform (CWT). The experimental results validate the finding that the combination of the improved CEEMDAN and the enhanced threshold screening SVD algorithm effectively reduces noise interference in vibration signals from rotating machinery. This integrated denoising approach successfully preserves the informative characteristics of the vibration signals, thereby laying a foundation for the subsequent fault diagnosis of rotating machinery.

MSSA-based adaptive low-frequency noise reduction using spectrum overlap measure

A multistage singular spectrum analysis based method is presented to extract the useful component from the residue stage by stage. In every stage of the decomposition, the sum of the signal-dominated SSA components is treated as the denoised signal. The signal-to-noise ratios of the denoised signals first increase and then decrease. A measurement called spectrum overlap factor (SOF) is proposed to estimate the optimal stage which achieves the highest SNR. First, the factor is calculated to measure the spectrum overlap degree between the residue and the denoised signal in every stage. Then, the curve of the SOF with respect to the number of stages is analyzed. Further, the minimum of the SOFs, which indicates the less spectrum overlap, allows for the estimation of the optimal stage. The proposed strategy avoids inappropriate parameter selection effectively since the estimation of the optimal stage is automatic. Besides, simulation results show that the proposed method has satisfactory denoising performance in different test scenarios.

Multi‐component condition monitoring method for wind turbine gearbox based on adaptive noise reduction

AbstractWind turbine gearbox condition monitoring (C&M) is a key technology to promote wind farm maintenance cost reduction and power generation improvement. Existing gearbox C&M methods usually adopt the component‐by‐component modelling approach. Firstly, this approach is inefficient in modelling; secondly, due to the thermal conduction effect, abnormalities in one gearbox component usually affect other components, making it difficult to identify the source of faults. To solve these problems, a normal behaviour model (NBM) combining data adaptive noise reduction and an improved variational auto‐encoder (VAE) is proposed, which can monitor the operational condition of multiple components of one gearbox simultaneously and takes into account the correlation between components when warning of the specific abnormal component. As verified by practical cases, the method balances the modelling accuracy and efficiency of the multi‐component NBM and achieves effective early warning and accurate localization of gearbox abnormalities. The proposed model has lower false alarm and missed alarm rates compared to other single‐component and multi‐component NBMs.

Prediction of Joint Angles Based on Human Lower Limb Surface Electromyography

Wearable exoskeletons can help people with mobility impairments by improving their rehabilitation. As electromyography (EMG) signals occur before movement, they can be used as input signals for the exoskeletons to predict the body’s movement intention. In this paper, the OpenSim software is used to determine the muscle sites to be measured, i.e., rectus femoris, vastus lateralis, semitendinosus, biceps femoris, lateral gastrocnemius, and tibial anterior. The surface electromyography (sEMG) signals and inertial data are collected from the lower limbs while the human body is walking, going upstairs, and going uphill. The sEMG noise is reduced by a wavelet-threshold-based complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) reduction algorithm, and the time-domain features are extracted from the noise-reduced sEMG signals. Knee and hip angles during motion are calculated using quaternions through coordinate transformations. The random forest (RF) regression algorithm optimized by cuckoo search (CS), shortened as CS-RF, is used to establish the prediction model of lower limb joint angles by sEMG signals. Finally, root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R2) are used as evaluation metrics to compare the prediction performance of the RF, support vector machine (SVM), back propagation (BP) neural network, and CS-RF. The evaluation results of CS-RF are superior to other algorithms under the three motion scenarios, with optimal metric values of 1.9167, 1.3893, and 0.9815, respectively.

Research on rolling bearing fault diagnosis method based on AMVMD and convolutional neural networks

Due to the uncertainty of the actual industrial environment, the effective features of the collected multivariate data are submerged by environmental noise. Due to the limited ability of single signal analysis method to recognize the features of multivariate data. Therefore, this paper proposes a rolling bearing fault diagnosis method based on adaptive multivariate variational mode decomposition (AMVMD) and multi-scale convolutional neural network (Multi-scale CNN). Firstly, based on the multivariate variational modal algorithm, the minimum modal overlapping component (MMOC) index is proposed and used as the objective function to seek the optimal solution of the main parameters of multivariate variational modes, to realize the adaptive decomposition and noise reduction of the original signal. Then, the multi-scale convolutional neural network was used to extract and recognize the denoising feature vectors in a deeper level, and finally the bearing fault diagnosis under complex working conditions is realized. Bearing data from Paderborn University were used to verify the proposed method. The results show that under the same conditions, the fault diagnosis accuracy of AMVMD-MSCNNs can achieve 98.60%, which has certain advantages and practical application significance.

Adaptive Noise Reduction Algorithm Based on SPP and NMF for Environmental Sound Event Recognition under Low-SNR Conditions

Nonnegative matrix factorization- (NMF-) based noise reduction methods can effectively improve the performance of environmental sound recognition. However, when the environmental sound overlaps highly with the noise, the spectral line loss and noise residue will occur in the low signal-to-noise ratio (SNR) condition. An adaptive noise reduction algorithm was proposed in this paper. First, noisy environmental sound is separated into estimated noise and environmental sound using NMF. Then, the estimated noise is used to calculate sound presence probability (SPP), which is adapted to decrease spectral line loss and achieve accurately estimated noise. Subsequently, the estimated noise combines with noisy environmental sound to obtain the estimated environmental sound. Finally, SPP is applied to reduce residual noise in the estimated environmental sound and reconstruct the environmental sound. The simulation results demonstrate that the proposed algorithm outperforms the traditional algorithms and NMF-based methods in terms of perceptual evaluation of speech quality (PESQ) and global SNR with increase of X% and X%, respectively. Moreover, the proposed method can effectively improve the environmental sound recognition rate. Particularly, the proposed method makes a 16.2% increase of F1-score in car horn recognition under the realistic acoustic condition.

Reduction in the Motion Artifacts in Noncontact ECG Measurements Using a Novel Designed Electrode Structure.

A noncontact ECG is applicable to wearable bioelectricity acquisition because it can provide more comfort to the patient for long-term monitoring. However, the motion artifact is a significant source of noise in an ECG recording. Adaptive noise reduction is highly effective in suppressing motion artifact, usually through the use of external sensors, thus increasing the design complexity and cost. In this paper, a novel ECG electrode structure is designed to collect ECG data and reference data simultaneously. Combined with the adaptive filter, it effectively suppresses the motion artifact in the ECG acquisition. This method adds one more signal acquisition channel based on the single-channel ECG acquisition system to acquire the reference signal without introducing other sensors. Firstly, the design of the novel ECG electrode structure is introduced based on the principle of noise reduction. Secondly, a multichannel signal acquisition circuit system and ECG electrodes are implemented. Finally, experiments under normal walking conditions are carried out, and the performance is verified by the experiment results, which shows that the proposed design effectively suppresses motion artifacts and maintains the stability of the signal quality during the noncontact ECG acquisition. The signal-to-noise ratio of the ECG signal after noise reduction is 14 dB higher than that of the original ECG signal with the motion artifact.

Multi-leakage source localization of safety valve based on improved KDE algorithm

The safety valve is the core component of the safety pressure relief protection device of the pressure-bearing special equipment. When the safety valve leaks, the medium of the pressure vessel will be lost and wasted, which may lead to safety accidents. Aiming at the problem that it is difficult to accurately locate multiple tiny leak holes in safety valves, multi-leakage source localization of safety valve combining the acoustic emission (AE) test with improved approximate kernel density estimation (KDE) algorithm is proposed. The algorithm first introduces the improved wavelet threshold function denoising method to extract the time-frequency support domain which is less affected by environmental noise and the energy of the leaked sound source is dominant, which makes the premise of the application of the KDE algorithm established. In the aspect of improving the wavelet threshold function, an improved adaptive wavelet threshold noise reduction method is proposed by using the decay characteristics of the exponential function. On this basis, the high-frequency aliasing is suppressed by frequency division fusion processing, the approximate kernel density function is calculated, and the three-dimensional spectral base of the approximate kernel density function is reduced. Through numerical calculation, the location coordinates of the leakage source of the safety valve are obtained according to the peak value of the improved KDE spectrum. The results show that the relative errors of the leakage location results of safety valves with working pressures of 0.72 MPa, 0.75 MPa and 0.77 MPa are all within 10%. The method of combining the acoustic emission test with the improved KDE algorithm can accurately locate the leakage source of the safety valve, and with the increase of the working pressure of the safety valve, the positioning accuracy is also improved accordingly.