Adaptive Demodulation Research Articles

Performance investigation of an OAM-SK optical communication system based on a PCNN-LDPC under atmospheric turbulence

This paper proposes a probabilistic convolutional neural network-low density parity check (PCNN-LDPC) demodulation scheme for orbital angular momentum shift keying free-space optical (OAM-SK-FSO) communication systems, with a focus on its bit error rate (BER) performance. Initially, the original information sequences were encoded by a low-density parity check (LDPC) and transformed into superposition state Laguerre Gaussian (LG) beams using a 16-Ary mapping scheme. The transmission of LG beams through atmospheric turbulence was then simulated using the power spectral inversion method, and the dataset was constructed and trained using a convolutional neural network (CNN). During demodulation, the CNN adaptive demodulator was integrated with the LDPC decoding algorithm. Classification probabilities from the CNN adaptive demodulator were used in the LDPC decoding process to enhance the channel estimation credibility. The computational results demonstrate that the BER of the PCNN-LDPC significantly outperforms both the CNN adaptive demodulator and CNN-LDPC demodulation strategy. Additionally, the performances of three LDPC decoding algorithms—min-sum (MS), normalized min-sum (NMS), and offset min-sum (OMS)—are compared, revealing that the probabilistic convolutional neural network-normalized min-sum (PCNN-NMS) achieves the best BER performance, highest convergence efficiency, and greatest decoding stability. These findings provide theoretical references and technical support for studying the BER performance of OAM-SK-FSO communication systems.

Adaptive Demodulation Extraction Transform for Fault Diagnosis of Rotating Machinery

Abstract The accurate analysis of close and crossed frequency components is a challenge for the existing TFA methods due to energy interference in the adjacent and crossing parts. In addition, the energy error at the intersection is caused because the energy value is superimposed repeatedly. To solve these problems, a new adaptive demodulation extraction transform (ADET) is proposed in this paper. An instantaneous frequency (IF) trajectory estimation method and an amplitude extraction matrix are designed to accurately identify the adjacent and crossing frequencies. The IF trajectory is calculated using the particle swarm optimization algorithm and the generalized demodulation technique. The amplitude extraction matrix extracts the energy value from the time-frequency domain by a position function, which converts the IF trajectory to corresponding time-frequency information. Moreover, an iteration procedure is designed to avoid the superposition of energy at the crossing point. The effectiveness of ADET is confirmed through simulated and experimental signals.

Conditional convolutional GAN-based adaptive demodulator for OAM-SK-FSO communication.

The perturbation of atmosphere turbulence is a significant challenge in orbital angular momentum shift keying-based free space optical communication (OAM-SK-FSO). In this study, we propose an adaptive optical demodulation system based on deep learning techniques. A conditional convolutional GAN (ccGAN) network is applied to recover the distorted intensity pattern and assign it to its specified class. Compared to existing methods based on convolutional neural networks (CNNs), our network demonstrates powerful capability in recovering the distorted light beam, resulting in a higher recognition accuracy rate under the same conditions. The average recognition accuracy rates are 0.9928, 0.9795 and 0.9490 when the atmospheric refractive index structure constant $C_n^2$ is set at 3 × 10-13, 4.45 × 10-13, 6 × 10-13m-2/3, respectively. The ccGAN network provides a promising potential tool for free space optical communication.

Acoustic Sensing System with Three-Wavelength Adaptive Demodulation Based on MG-Y Laser

Acoustic Sensing System with Three-Wavelength Adaptive Demodulation Based on MG-Y Laser

Adaptive demodulation synchro-extracting transform for bearing time-varying fault feature extraction

Since bearing fault-induced impulses are time-varying under variable rotational speeds and often polluted by background noise and other interference components, it is still a challenging task for bearing feature extraction and diagnosis. As such, a novel bearing nonstationary fault feature extraction technique, termed adaptive demodulation synchro-extracting transform (ADSET) is developed in this paper. In the developed technique, the reset criterion is defined and introduced into the generalized demodulation transform (GDT) to transform the time-varying fault characteristic frequency (FCF) with strong anti-noise property; In addition, the local maximum criterion is developed and introduced into the synchro-extracting transform (SET) to extract fault-related harmonics and eliminate other interference components; Finally, the diagnosis index model is constructed to detect bearing fault location. The performance of the developed technique is verified using both simulated and different experiment signals, and the results show that rolling bearing fault is quantitatively characterized and accurately detected without rotational speed measurement.

Response of a large deep-seated gravitational slope deformation to meteorological, seismic, and deglaciation drivers as measured by InSAR

We analyze the sensitivity of a large (area extent ∼3 km2), deep-seated gravitational slope deformation (Fels slide, Alaska Range) to three specific drivers: (i) liquid surface water input from ERA-5 reanalysis snow melt and rainfall; (ii) locally projected seismic activity of Alaskan earthquakes; and (iii) lowering of Fels Glacier at the slide toe estimated from topographic data. A surface displacement map-series is derived from 1991 to 2016 spaceborne multi-sensor InSAR data (ERS, RADARSAT-1/2, ALOS, TerraSAR-X) using adaptive demodulation to unwrap interferograms of variable spatial resolution and quality. On this series we use independent component analysis (ICA) to uncover five displacement patterns that map to independently moving domains of the slide and then correlate the corresponding temporal pattern intensities with the suspected drivers. We find significant sub-annual correlation between displacement pattern intensities and seasonal water input variations. The correlation can be optimized, for each ICA pattern, by choosing appropriate values of temporal smoothing and lag to create depth-propagated versions of the water input driver. Lag time results ranging from one to 3 weeks relate to shallower and deeper propagations of water input, driving the different deformation patterns. For two of the deformation patterns, seasonal sensitivity to water input was strongly amplified by the 2002 Mw7.9 Denali earthquake. Sensitivity of these patterns remained high for 4 years until abruptly dropping to below pre-earthquake values, which suggests a highly non-linear modulation by the seismic driver. Other deformation patterns show a steady intensity increase that appears linked to the deglaciation driver. Despite these observations, the inter-annual variations in ICA pattern intensities show no clear predictability by individual drivers or driver combinations. This suggests that the mechanical and hydraulic evolution of the slide, especially after damaging events such as earthquakes or heavy rainfall, is a crucial factor not adequately modeled in our approach. Despite this limitation, our analysis provides the first direct evidence that the Fels slide comprises several independently moving domains that respond differently to the suspected drivers as is suggestive of a complex slope deformation.

Meta-learning-based optical vector beam high-fidelity communication under high scattering.

While spatial structured light based free space optical communication provides high-bandwidth communication with broad application prospect, severe signal distortion caused by optical scattering from ambient microparticles in the atmosphere can lead to data degradation. A deep-learning-based adaptive demodulator has been demonstrated to resolve the information encoded in the severely distorted channel, but the high generalization ability for different scattering always requires prohibitive costs on data preparation and reiterative training. Here, we demonstrate a meta-learning-based auto-encoder demodulator, which learns from prior theoretical knowledge, and then training with only three realistic samples per class can rectify and recognize transmission distortion. By employing such a demodulator to hybrid vector beams, high fidelity communication can be established, and data costs are reduced when faced with different scattering channels. In a proof-of-principle experiment, an image with 256 gray values is transmitted under severe scattering with an error ratio of less than 0.05%. Our work opens the door to high-fidelity optical communication in random media environments.

Adaptive Demodulation in Impulse Noise Channels

Electromagnetic interference causes considerable performance degradation on wireless communication systems. The performance degradation is largely affected by the characteristics of the interference. Impulse interference commonly occurs in industrial and automotive environments, where many closely located systems and electronic equipment coexist. In this work, we propose two novel algorithms for adaptive demodulation in impulse noise. The proposed methods compute appropriate log-likelihood ratios based on interference classification and estimation of Middleton’s Class A noise model as well as the symmetric <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\alpha$</tex-math></inline-formula> -Stable (S <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\alpha$</tex-math></inline-formula> S) model. The analytical complexity and intractability of the S <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\alpha$</tex-math></inline-formula> S probability density function (PDF) makes real-time applications unfeasible. Therefore, the proposed algorithms are developed using two different techniques for approximating the S <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\alpha$</tex-math></inline-formula> S PDF. The approximations are achieved through interpolation via <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i)</i> approximate closed-form expressions of the PDF for a specific parameter set and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ii)</i> via numerically pre-calculated look-up tables of the PDF for arbitrary parameter choices. The proposed adaptive techniques are shown to provide a performance gain in terms of bit error rate (BER) of up to 20 dB energy per bit to noise power ratio (Eb/N0), in comparison to traditional, non-adaptive, methods for varying levels of impulse interference. The performance loss of approximating the PDF in comparison to exact calculations amount to less than 8 dB Eb/N0, which is small in relation to the performance gain achieved in comparison to traditional methods. However, the complexity in terms of simulation execution time of the proposed approximate algorithms is reduced by up to a factor 250, compared to methods based on exact computation. The algorithms are validated using regular low density parity check (LDPC) codes, in addition to quasi-cyclic (QC)-LDPC and turbo codes. The proposed adaptive demodulation techniques can be used to improve decoding and demodulation performance in many real-life situations where non-Gaussian interference commonly occurs.

Adaptive demodulation of reflection spectrum intensity of fiber grating link

Adaptive demodulation of reflection spectrum intensity of fiber grating link

An Adaptive Demodulation Band Segmentation Method to Optimize Spectral Boundary and Its Application for Wheelset-Bearing Fault Detection

Wheelset-bearing working states directly affect the stability of bogies, and existing defects may threaten the running safety of high-speed trains. Thus, the fault detection of wheelset-bearing is of great importance. In this paper, a novel wheelset-bearing fault detection method, named adaptive autocorrelated kurtogram (AAK), is proposed based on the developed autocorrelated kurtosis and the presented spectral segmentation method. Autocorrelated kurtosis is designed to reduce the unrelated components interference and increase the signal-to-noise ratio (SNR). The spectral segmentation method is proposed to obtain the fault zone as completely as possible. Based on the feature that rotation frequency is related to bearing fault frequency, the rotation frequency-based window size selection and extension strategy is proposed. With different frequency levels, the AAK is formed. The proposed method is validated by simulated and experimental data. The results show that this method can automatically and adaptively search for a reasonable demodulation bandwidth according to the fault information feature and resonance region position. The method can estimate the center frequency and bandwidth and avoid unrelated component interference. The AAK can provide accurate detection results and possesses excellent performance. Thus, it is suitable for wheelset-bearing fault detection.

Adaptive demodulation for phase information and opto-mechanical properties of fibres from blurred digital holography pattern

Adaptive demodulation for phase information and opto-mechanical properties of fibres from blurred digital holography pattern

Adaptive demodulation by deep-learning-based identification of fractional orbital angular momentum modes with structural distortion due to atmospheric turbulence

Since the great success of optical communications utilizing orbital angular momentum (OAM), increasing the number of addressable spatial modes in the given physical resources has always been an important yet challenging problem. The recent improvement in measurement resolution through deep-learning techniques has demonstrated the possibility of high-capacity free-space optical communications based on fractional OAM modes. However, due to a tiny gap between adjacent modes, such systems are highly susceptible to external perturbations such as atmospheric turbulence (AT). Here, we propose an AT adaptive neural network (ATANN) and study high-resolution recognition of fractional OAM modes in the presence of turbulence. We perform simulations of fractional OAM beams propagating through a 1-km optical turbulence channel and analyze the effects of turbulence strength, OAM mode interval, and signal noise on the recognition performance of the ATANN. The recognition of multiplexed fractional modes is also investigated to demonstrate the feasibility of high-dimensional data transmission in the proposed deep-learning-based system. Our results show that the proposed model can predict transmitted modes with high accuracy and high resolution despite the collapse of structured fields due to AT and provide stable performance over a wide SNR range.

Enhanced Frequency Adaptive Demodulation Technique for Grid-Connected Converters

This article presents an enhanced frequency adaptive demodulation technique for grid-synchronization of grid-connected converters in variable frequency condition. Demodulation works by generating demodulated voltages which contain undesired double frequency components. As a result, high-order low-pass filters with high cutoff frequency are required to eliminate the undesired components. This reduces the dynamic performance. Frequency adaptive demodulation technique enhances the dynamic performance by rejecting the double frequency components as opposed to filtering, however, at the cost of additional computational complexity. This article overcomes this problem by using double demodulation without recreating the double frequency component for rejection purposes. This reduces the computational complexity significantly. Suitability of the proposed method is verified through numerical simulation and experimental study. Comparative study with existing frequency adaptive demodulation and second-order generalized integrator phase-locked loop techniques demonstrate the validity and performance improvement by the proposed technique.

A Bat Optimized Reliable Elm (Bore) For an Efficient Throughput of Cap-VLC System

Indoor Visible light communication (VLC) is considered one of the most famous communication technologies in today’s industrial life, showing importance in data broadcasting and glowing instantly with the cost-effective source of light-emitting diode (LED). This kind of high-speed network’s properties is controlled by the source device’s shortened bandwidth (LED). Therefore, it is considering highly efficient modulation technique and extreme adaptive demodulation technique for better data rate in visible light communication. Carrier less amplitude-phase (CAP) modulation is an eminent modulation scheme that increases implementation ease and places good position inefficiency. Somehow, the CAP-VLC system’s impact is signal jamming, poor sensitivity, scattering, and noise issues. To overrule this problem, it witnesses the implementation of VLC system with CAP modulation using advanced neural network system of High-Speed Feed Forward Neural Network, which works based on the principle of Extreme Learning Machine (ELM). The same is adopted and extended using the BAT algorithm. Along with this, algorithm optimization technique has been integrated to enhance the entire CAP-VLC system’s performance. Altogether, it can be named as bat-optimized reliable ELM (BORE). The proposed new learning-based algorithm for CAP-VLC has shown better performance in received power distribution of 90.6% at various modulation indexes, better BER of about 97.6% in the voltage level of 3V, and different distances between transceivers, respectively.

Rolling Bearing Feature Extraction Method Based on Improved Intrinsic Time-Scale Decomposition and Mathematical Morphological Analysis

To overcome the difficulty of extracting the feature frequency of early bearing faults, this paper proposes an adaptive feature extraction scheme. First, the improved intrinsic time-scale decomposition, proposed in this paper, is used as a noise reduction method. Then, we use the adaptive composite quantum morphology analysis method, also proposed in this paper, to perform an adaptive demodulation analysis on the signal, and finally, extract the fault characteristics in the envelope spectrum. The experimental results show that the scheme performs well in the early fault feature extraction of rolling bearings.

Integrator-Less Method for Phase Angle Estimation of Fundamental Frequency Positive-Sequence Component Under Adverse Condition

This article proposes an integrator-less method for phase angle estimation of unbalanced three-phase voltage systems under adverse conditions. It mainly unites abc-to- dq transform, delayed signal cancellation scheme, and a phase error compensation algorithm. It does not demand online operation of integrators, and thus, associated discretization error and instability issue are not present in the proposed method. It is also an unconditionally stable technique as it uses a real open-loop structure. Moreover, the method is relatively simple and computationally efficient due to circumventing online operations of the complex functions, such as square root, trigonometric, and inverse trigonometric. Under alike transient time conditions, the proposed method is more resistant to harmonic disturbances when compared to integrator-based similar competing techniques, such as an enhanced frequency adaptive demodulation approach and a phase error compensation-based open-loop method. The usefulness of the offered method is proved using simulated and experimental results.

General synchroextracting chirplet transform: Application to the rotor rub-impact fault diagnosis

The rub-impact fault between the rotor and the stator surface is a common and serious failure in rotating machinery. The vibration signals acquired during the rotating machinery operation will carry the time-varying characteristics of rapid fluctuating instantaneous frequency (IF) when the healthy condition of rotor system changes. The proposed method is termed as the general synchroextracting chirplet transform which is based on the classical chirplet transform and employs the second-order synchroextracting transform to concentrate the time-frequency representation (TFR). Moreover, an adaptive demodulation parameters determination method based on kurtosis is proposed. The proposed method is non-sensitivity to noise, allows for signal reconstruction, and retains certain processing ability for multicomponent signals. The effectiveness and practical value of the method are verified by the numerical signals and the vibration signals of the heavy oil catalytic cracking machine which has the rotor rub-impact fault.

Free-space 16-ary orbital angular momentum coded optical communication system based on chaotic interleaving and convolutional neural networks.

Recently, orbital angular momentum (OAM) rays passing through free space have attracted the attention of researchers in the field of free-space optical communication systems. Throughout free space, the OAM states are subject to atmospheric turbulence (AT) distortion leading to crosstalk and power discrepancies between states. In this paper, a novel chaotic interleaver is used with low-density parity-check coded OAM-shift keying through an AT channel. Moreover, a convolutional neural network (CNN) is used as an adaptive demodulator to enhance the performance of the wireless optical communication system. The detection process with the conjugate light field method in the presence of chaotic interleaving has a better performance compared to that without chaotic interleaving for different values of propagation distance. Also, the viability of the proposed system is verified by conveying a digital image in the presence of distinctive turbulence conditions with different error correction codes. The impacts of turbulence strength, transmission distance, signal-to-noise ratio (SNR), and CNN parameters and hyperparameters are investigated and taken into consideration. The proposed CNN is chosen with the optimal parameter and hyperparameter values that yield the highest accuracy, utmost mean average precision (MAP), and the largest value of area under curve (AUC) for the different optimizers. The simulation results affirm that the proposed system can achieve better peak SNR values and lower mean square error values in the presence of different AT conditions. By computing accuracy, MAP, and AUC of the proposed system, we realize that the stochastic gradient descent with momentum and the adaptive moment estimation optimizers have better performance compared to the root mean square propagation optimizer.

Model-Driven Deep Learning Scheme for Adaptive Transmission in MIMO-SCFDE System

Adaptive transmission (AT) is considered as one of the critical technologies to enhance the effectiveness of communication systems. In this article, we propose a model-driven deep learning (DL) scheme for AT in multiple-input multiple-output single-carrier frequency-domain equalization (MIMO-SCFDE) systems, in which the adaptive modulation network (AMNet) and adaptive demodulation network (ADNet) are adopted to complete the modulation of the signal and the modulation recognition of the receiver. Under the target bit error rate (BER), the adaptive modulation (AM) scheme can adjust the modulation mode selection of different transmitting antennas adaptively according to the estimated channel information to improve the throughput. The features required by the AMNet are extracted from the received signal, and the labels are assigned according to the optimal modulation scheme got by analyzing the signal detection performance. Since the spectral correlation function has a powerful ability to suppress noise and the cyclic spectrum varies with the modulation mode, we take the preprocessed cyclic spectrogram as the input of ADNet to achieve the adaptive modulation recognition (AMR). Comparative experiments demonstrate that the proposed scheme gets better performance in terms of throughput and reliability in MIMO-SCFDE systems than the traditional scheme and the existing DL scheme.

Non-contrast power Doppler ultrasound imaging for early assessment of trans-arterial chemoembolization of liver tumors

Trans-arterial chemoembolization (TACE) is an important yet variably effective treatment for management of hepatic malignancies. Lack of response can be in part due to inability to assess treatment adequacy in real-time. Gold-standard contrast enhanced computed tomography and magnetic resonance imaging, although effective, suffer from treatment-induced artifacts that prevent early treatment evaluation. Non-contrast ultrasound is a potential solution but has historically been ineffective at detecting treatment response. Here, we propose non-contrast ultrasound with recent perfusion-focused advancements as a tool for immediate evaluation of TACE. We demonstrate initial feasibility in an 11-subject pilot study. Treatment-induced changes in tumor perfusion are detected best when combining adaptive demodulation (AD) and singular value decomposition (SVD) techniques. Using a 0.5 s (300-sample) ensemble size, AD + SVD resulted in a 7.42 dB median decrease in tumor power after TACE compared to only a 0.06 dB median decrease with conventional methods.