Multichannel Data Research Articles

Enhancing Recovery of Structural Health Monitoring Data Using CNN Combined with GRU

Structural health monitoring (SHM) plays a crucial role in ensuring the safety of infrastructure in general, especially critical infrastructure such as bridges. SHM systems allow the real-time monitoring of structural conditions and early detection of abnormalities. This enables managers to make accurate decisions during the operation of the infrastructure. However, for various reasons, data from SHM systems may be interrupted or faulty, leading to serious consequences. This study proposes using a Convolutional Neural Network (CNN) combined with Gated Recurrent Units (GRUs) to recover lost data from accelerometer sensors in SHM systems. CNNs are adept at capturing spatial patterns in data, making them highly effective for recognizing localized features in sensor signals. At the same time, GRUs are designed to model sequential dependencies over time, making the combined architecture particularly suited for time-series data. A dataset collected from a real bridge structure will be used to validate the proposed method. Different cases of data loss are considered to demonstrate the feasibility and potential of the CNN-GRU approach. The results show that the CNN-GRU hybrid network effectively recovers data in both single-channel and multi-channel data loss scenarios.

Optically Transparent Complex-Amplitude Metasurface for Full-Space Manipulation of Frequency-Multiplexed Holographic Imaging.

Restricted by the physical properties of materials, most traditional metasurfaces (MSs) cannot achieve transparent stealth in the visible spectrum. Although some metasurfaces for holography have been designed, there is no standard method for evaluating the advancement of wavefront manipulation under different design algorithms. Here, a complex-amplitude metasurface with optical transparency (OT) and full-space manipulation is presented in the millimeterwave band. Through frequency multiplexing, two holographic images "HOLO" and "GRAM" with high quality are designed, achieving the signal-to-noise ratios of 14.6 and 14.4 dB, respectively. The 64 × 64 bilayered metasurface consists of glass and poly(ethylene terephthalate) (PET) substrates and three metallic mesh layers. By change of the opening size and oriented angle of split rings, phase and amplitude modulations are independently realized. Besides, a new method is provided to assess the superiority of the metasurface holography system for near-field energy regulation. The prototype was fabricated using micro-nano-technology and tested. Two holographic images were experimentally demonstrated and show good agreement with theoretical calculations and simulated results. With the advantages of OT and full-space complex-amplitude customization, the proposed metasurface holograms for frequency-multiplexed may find prospective application aspects in target perception, multichannel data storage and encryption, and many other related fields.

Fault diagnosis of rolling bearings driven by multi-channel data fusion and feature fusion under time-varying speed conditions

Abstract Bearings, as the core component for power transmission, are crucial in ensuring the safe and reliable operation of equipment. However, the fault information contained in a single-channel vibration signal is inherently limited. Additionally, under time-varying speed conditions, features are prone to drift, and the cross-domain diagnostic performance of most traditional domain adaptation (DA) models may drop dramatically. To solve the above problems and enhance the ability of DA models in extracting domain invariant features, this paper introduces a Multi-channel data fusion and Attention-guided Multi-feature Fusion-driven Center-aligned Network (MAMC). Initially, a multi-channel time-frequency information fusion strategy based on wavelet transform is constructed to achieve a comprehensive fusion of multi-channel data, thereby obtaining richer fault feature representations. Subsequently, a multi-branch feature fusion network, integrated with an attention mechanism, is devised to capture significant features across various dimensions and scales, resulting in more comprehensive and representative fault features. Finally, a novel Center-Aligned Domain Adaptation method (CADA) is proposed based on domain adversarial methods and center loss. By minimizing the distance between deep domain invariant features and trainable common class centers, the issue of domain shift between data is effectively alleviated, and the cross-domain diagnostic performance of DA models under the time-varying speed conditions is improved. The experimental results indicate that the MAMC method exhibits superior performance on both bearing datasets and is a promising approach for cross-domain intelligent fault diagnosis.

Tactile-GAT: tactile graph attention networks for robot tactile perception classification.

As one of the most important senses in human beings, touch can also help robots better perceive and adapt to complex environmental information, improving their autonomous decision-making and execution capabilities. Compared to other perception methods, tactile perception needs to handle multi-channel tactile signals simultaneously, such as pressure, bending, temperature, and humidity. However, directly transferring deep learning algorithms that work well on temporal signals to tactile signal tasks does not effectively utilize the physical spatial connectivity information of tactile sensors. In this paper, we propose a tactile perception framework based on graph attention networks, which incorporates explicit and latent relation graphs. This framework can effectively utilize the structural information between different tactile signal channels. We constructed a tactile glove and collected a dataset of pressure and bending tactile signals during grasping and holding objects, and our method achieved 89.58% accuracy in object tactile signal classification. Compared to existing time-series signal classification algorithms, our graph-based tactile perception algorithm can better utilize and learn sensor spatial information, making it more suitable for processing multi-channel tactile data. Our method can serve as a general strategy to improve a robot's tactile perception capabilities.

A hydraulic motor fault diagnosis method based on weighted multi-channel information fusion

Abstract In response to the limitations of the existing single-sensor hydraulic motor fault diagnosis model, which includes significant fluctuations in fault identification accuracy, low data utilization, poor reliability, and insufficient generalization ability under variable working conditions, a novel hydraulic motor fault diagnosis method based on weighted fusion of multi-channel data and migration learning is proposed. Firstly, in order to fully extract the information content in the multi-channel data set of the hydraulic motor, a multi channel-fusion method based on information entropy weighting is proposed. The information entropy method is employed to calculate the fusion weight of each channel of data, and the sampled data of each channel is weighted and fused. Subsequently, the fusion data from the source domain is employed to pre-train the depth transmission model, with the model parameters obtained from this pre-training serving as the initialization parameters for the target domain model. Subsequently, the parameters of the target domain model's feature extractor are fixed, and the parameters of its classifier are fine-tuned using the target domain's fusion data. The distance between the source and target domains is reduced by incorporating an attention mechanism and constructing a loss function. The migration from the source domain to the target domain is achieved, which enables the classifier to adapt to the novel target sample recognition task. Ultimately, the experimental results of hydraulic motor migration diagnosis under variable operating conditions demonstrate that the proposed method is an efficacious approach for hydraulic motor fault diagnosis. In comparison to conventional models such as
CNN and GRU, the proposed method exhibits superior migration diagnosis accuracy and enhanced generalization and robustness under variable operating conditions.

Clustered slumping in the northern South China Sea: Implications for chronology and geohazards

Seismic facies analysis is the most widely used method to identify event deposits from subaqueous environments. However, the internal structures of a chaotic or transparent seismic unit that represent event deposits are usually poorly imaged. This is primarily due to the limited resolution (usually <10 m) of commonly available multi-channel seismic reflection data. As a consequence, potential (sub)meter-thick, interbedded background sediments that may divide the chaotic layer cannot be discerned on such a seismic profile. The result of this, is that a complex of multiple moderate-thickness event layers can be misinterpreted as a single, thick event layer and this can greatly impact age-depth model reconstruction and geohazard assessment. One approach to resolve the problem is to correlate seismic data with high-resolution sediment core analysis. To address the problem in the South China Sea, we combine multiple methods to identify event deposits in the IODP holes U1499A and U1432C. Our dataset reveals that: (1) the previously interpreted ~50 m-thick slumping unit in the region is a complex of multiple moderately sized units; (2) the slumping events are clustered between 0.6 and 0.4 Ma. Using our new understanding of event emplacement, we define event-free age models for mass wasting on the margin of the South China Sea, improving our understanding of local geohazards. Our methods here represent a sedimentological approach which could be used in other subaqueous environments to reconstruct event-free age models and geohazard histories.

Decoding aging and cognitive functioning through spatiotemporal EEG patterns: Introducing spatiotemporal information-based similarity analysis.

Exploring spatiotemporal patterns of high-dimensional electroencephalography (EEG) time series generated from complex brain system is crucial for deciphering aging and cognitive functioning. Analyzing high-dimensional EEG series poses challenges, particularly when employing distance-based methods for spatiotemporal dynamics. Therefore, we proposed an innovative methodology for multi-channel EEG data, termed as Spatiotemporal Information-based Similarity (STIBS) analysis. The core of this method is to first perform state space compression of multi-channel EEG time series using global field power, which can provide insight into the dynamic integration of spatiotemporal patterns between the steady states and non-steady states of brain. Subsequently, we quantify the pairwise differences and non-randomness of spatiotemporal patterns using an information-based similarity analysis. Results demonstrated that this method holds the potential to serve as a distinguishing marker between young and elderly on both pairwise differences and non-randomness indices. Young individuals and those with higher cognitive abilities exhibit more complex macrostructure and non-random spatiotemporal patterns, whereas both aging and cognitive decline lead to more randomized spatiotemporal patterns. We further extended the proposed analytics to brain regions adversarial STIBS (bra-STIBS), highlighting differences between young and elderly, as well as high and low cognitive groups. Furthermore, utilizing the STIBS-based XGBoost model yields superior recognition accuracy in aging (93.05%) and cognitive functioning (74.29%, 64.19%, and 80.28%, respectively, for attention, memory, and compatibility performance recognition). STIBS-based methodology not only contributes to the ongoing exploration of neurobiological changes in aging but also provides a powerful tool for characterizing the spatiotemporal nonlinear dynamics of the brain and their implications for cognitive functioning.

Bearing fault diagnosis based on wavelet adaptive threshold filtering and multi-channel fusion cross-attention neural network.

In industrial applications, it is difficult to extract the fault feature directly when the rolling bearing works under strong background noise. In addition, single-channel vibration sensor data pose limitations in providing a comprehensive representation of bearing fault features; how to effectively fuse data of each channel and extract features is a challenge. To solve the above-mentioned problems, a fault diagnosis method based on wavelet adaptive threshold filtering and multi-channel fusion cross-attention neural network is proposed in this paper. First, the multi-scale discrete wavelet transform is applied to obtain the wavelet coefficients of each channel. Adaptive threshold filtering is conducted to filter out noise and extract symbolic features. The threshold updates with the training of the network. Then, the wavelet coefficients are reconstructed and the channel attention is performed to further extract the symbolic features of the fault signal. Finally, the multi-channel fault signals are fused by a cross-attention module. This module can fully extract the features of each channel and fuse multi-channel data. To improve the generalization ability of the network, residual connections are added. To verify the effectiveness of the proposed method, experiments are carried out on the rolling bearing datasets of Case Western Reserve University and Xi'an Jiaotong University. In addition, the gas turbine main bearing dataset is also applied to prove the reliability of this method.

Artificial Intelligence-Based Precipitation Estimation Method Using Fengyun-4B Satellite Data

This paper proposes a novel precipitation estimation method based on FY-4B meteorological satellite data (FY-4B_AI). This method facilitates the spatiotemporal matching of 125 features derived from the multi-temporal and multi-channel data of the FY-4B satellite with precipitation data at stations. Subsequently, a precipitation model was constructed using the light gradient boosting machine (LGBM) algorithm. A comparative analysis of FY-4B_AI and GPM/IMERG-L products for over 450 million station cases throughout 2023 revealed the following: (1) The results demonstrate that FY-4B_AI is more accurate than GPM/IMERG-L. Six of the eight evaluation indices exhibit superior performance for FY-4B_AI in comparison to GPM/IMERG-L. These indices include the mean absolute error (MAE), root mean square error (RMSE), relative error (RE), correlation coefficient (CC), probability of detection (POD), and critical success index (CSI). As for the MAE, the results are 1.67 (FY-4B_AI) and 1.92 (GPM/IMERG-L), respectively. The RMSEs are 3.68 and 4.07, respectively. The REs are 17.72% and 26.28%, respectively. The CCs are 0.44 and 0.36, respectively. The PODs are 61.84% and 47.31%, respectively. The CSIs are 0.30 and 0.27, respectively. However, with regard to the mean errors (MEs) and false alarm rates (FARs), FY-4B_AI (−0.88 and 62.85%, respectively) displays a slight degree of inferiority in comparison to GPM/IMERG-L (−0.80 and 62.21%, respectively). (2) An evaluation of two strong weather events to represent the spatial distribution of precipitation in different climatic zones revealed that both FY-4B_AI and GPM/IMERG-L are equally capable of accurately representing these phenomena, irrespective of whether the region in question is humid, as is the case in the southeast, or dry, as is the case in the northwest.

Intelligence data acquisition based on embedded system in Chinese cuisine cooker (CCICR V1.0)

The Chinese cooking process, intricate and diverse, encompasses a wide range of dishes, generating substantial data that often poses significant challenges for automation. To address these challenges, this paper introduces a versatile, highly reliable, user-friendly, and intelligent data recorder specifically designed for Chinese cuisine-the Chinese Cuisine Intelligent Cooker Recorder-V1.0 (CCICR-V1.0). This device is intended to record data generated during the cooking process and provide essential support for intelligent cooking robot systems. The core of CCICR-V1.0 is a STM32 microcontroller, equipped with sensors that monitor temperature, pressure, and attitude. These sensors facilitate the intelligent collection of data related to dishes, ingredients, and the movements of cookware throughout the cooking process. To ensure efficient data acquisition and storage, CCICR-V1.0 employs a multi-task data buffering storage method that effectively allocates CPU resources. NAND Flash is used as the storage medium, guaranteeing secure storage, management, and preservation of high-frequency, multi-channel data. Experimental results demonstrate the effectiveness of CCICR-V1.0 in achieving multi-channel, high-frequency data acquisition and storage in complex environments. This leads to an increase in automation efficiency of 89.9%. The weighing module demonstrates a maximum relative error of only 0.288%, while the attitude sensor experiment shows an attitude information error of just 0.22°C. Furthermore, the non-contact infrared temperature measurement module exhibits impressive performance with a maximum absolute error of 0.258∘C\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$^\\circ C$$\\end{document} and a maximum relative error of 0.88%. Notably, this measurement module has achieved a cost reduction of approximately 91.7% and an accuracy improvement of around 40%. Additionally, the response time of CCICR-V1.0 is less than 3 ms. With its ability to effectively capture data related to Chinese cooking, CCICR-V1.0 holds commercial value for widespread adoption and application in the field of intelligent cooking.

Estimation of CO 2 saturation maps from synthetic seismic data using a deep-learning method with a multi-scale approach

In the context of Carbon Capture and Storage (CCS), monitoring the behaviour of CO 2 within subsurface reservoirs is pivotal for efficient and safe storage operations. This study proposes a new approach to enhance the accuracy of predicting CO 2 saturation maps directly from shot gathers, using a combination of deep learning (DL) and feature extraction methods. We employ a U-Net model, specifically tailored to solve regression tasks, and two-dimensional continuous wavelet transform (2D-CWT) to analyse shot gathers at different scales. We introduce a novel approach using multi-channel input data for the DL model, combining shot gathers and CWT images. The DL model was trained and tested using both single channel and multichannel input. The single channel datasets included shot gathers and CWT images at the first scale, while the multi-channel datasets integrated shot gathers with either two or four scales of CWT. We conducted a sensitivity analysis on the number of training epochs to compare the performance of the model with multichannel and single channel input. Additionally, a Transfer Learning approach was implemented to improve performance in noisy conditions by leveraging knowledge from a pre-trained model on noise-free images. Monte Carlo dropout was used to predict pixel-scale variability and provided a prediction variability with a standard deviation ranging from 0.019 to 0.194, enhancing the robustness of CO 2 saturation estimates. Our results suggest that combining feature extraction using 2D-CWT with the U-Net architecture improves the prediction performance of CO 2 saturation in a synthetic CCS model. Additionally, using multi-channel input instead of single channel is more efficient as it requires less training and prediction time to achieve comparable results. This confirms the effectiveness of 2D-CWT as a pre-processing technique, contributing valuable insights and advances in the field of data-driven geophysical inversion problems.

Deep learning-based spike sorting: a survey.

Objective.Deep learning is increasingly permeating neuroscience, leading to a rise in signal-processing applications for extracellular recordings. These signals capture the activity of small neuronal populations, necessitating 'spike sorting' to assign action potentials (spikes) to their underlying neurons. With the rise in publications delving into new methodologies and techniques for deep learning-based spike sorting, it is crucial to synthesise these findings critically. This survey provides an in-depth evaluation of the approaches, methodologies and outcomes presented in recent articles, shedding light on the current state-of-the-art.Approach.Twenty-four articles published until December 2023 on deep learning-based spike sorting have been examined. The proposed methods are divided into three sub-problems of spike sorting: spike detection, feature extraction and classification. Moreover, integrated systems, i.e., models that detect spikes and extract features or do classification within a single network, are included.Main Results.Although most algorithms have been developed for single-channel recordings, models utilising multi-channel data have already shown promising results, with efficient hardware implementations running quantised models on ASICs and FPGAs. Convolutional neural networks have been used extensively for spike detection and classification as the data can be processed spatiotemporally while maintaining low-parameter models and increasing generalisation and efficiency. Autoencoders have been mainly utilised for dimensionality reduction, enabling subsequent clustering with standard methods. Also, integrated systems have shown great potential in solving the spike sorting problem from end to end.Significance.This survey explores recent articles on deep learning-based spike sorting and highlights the capabilities of deep neural networks in overcoming associated challenges, but also highlights potential biases of certain models. Serving as a resource for both newcomers and seasoned researchers in the field, this work provides insights into the latest advancements and may inspire future model development.

Combined Keyword Spotting and Localization Network Based on Multi-Task Learning

The advent of voice assistance technology and its integration into smart devices has facilitated many useful services, such as texting and application execution. However, most assistive technologies lack the capability to enable the system to act as a human who can localize the speaker and selectively spot meaningful keywords. Because keyword spotting (KWS) and sound source localization (SSL) are essential and must operate in real time, the efficiency of a neural network model is crucial for memory and computation. In this paper, a single neural network model for KWS and SSL is proposed to overcome the limitations of sequential KWS and SSL, which require more memory and inference time. The proposed model uses multi-task learning to utilize the limited resources of the device efficiently. A shared encoder is used as the initial layer to extract common features from the multichannel audio data. Subsequently, the task-specific parallel layers utilize these features for KWS and SSL. The proposed model was evaluated on a synthetic dataset with multiple speakers, and a 7-module shared encoder structure was identified as optimal in terms of accuracy, direction of arrival (DOA) accuracy, DOA error, and latency. It achieved a KWS accuracy of 94.51%, DOA error of 12.397°, and DOA accuracy of 89.86%. Consequently, the proposed model requires significantly less memory owing to the shared network architecture, which enhances the inference time without compromising KWS accuracy, DOA error, and DOA accuracy.

Accelerated cardiac cine with spatio-coil regularized deep learning reconstruction.

To develop an iterative deep learning (DL) reconstruction with spatio-coil regularization and multichannel k-space data consistency for accelerated cine imaging. This study proposes a Spatio-Coil Regularized DL (SCR-DL) approach for iterative deep learning reconstruction incorporating multicoil information in data consistency and regularizer. SCR-DL uses shift-invariant convolutional kernels to interpolate missing k-space lines and reconstruct individual coil images, followed by a regularizer that operates simultaneously across spatial and coil dimensions using learned image priors. At 8-fold acceleration, SCR-DL was compared with Generalized Autocalibrating Partially Parallel Acquisition (GRAPPA), sensitivity encoding (SENSE)-based DL and spatio-temporal regularized (STR)-DL reconstruction. In the retrospective undersampled cine, images were quantitatively evaluated using normalized mean square error (NMSE) and structural similarity index measure (SSIM). Additionally, agreement for left-ventricular ejection fraction and left-ventricular mass were assessed using prospectively accelerated cine images at 2-fold and 8-fold accelerations. The SCR-DL algorithm successfully reconstructed highly accelerated cine images. SCR-DL had significant improvements in NMSE (0.03 ± 0.02) and SSIM (91.4% ± 2.7%) compared with GRAPPA (NMSE: 0.09 ± 0.04, SSIM: 69.9% ± 11.1%; p < 0.001), SENSE-DL (NMSE: 0.07 ± 0.04, SSIM: 86.9% ± 3.2%; p < 0.001), and STR-DL (NMSE: 0.04 ± 0.03, SSIM: 90.0% ± 2.5%; p < 0.001) with retrospective undersampled cine. Despite the 3-fold reduction in scan time, there was no difference between left-ventricular ejection fraction (59.8 ± 4.5 vs. 60.8 ± 4.8, p = 0.46) or left-ventricular mass (73.6 ± 19.4 g vs. 73.2 ± 19.7 g, p = 0.95) between R = 2 and R = 8 prospectively accelerated cine images. SCR-DL enabled highly accelerated cardiac cine imaging, significantly reducing breath-hold time. Compared with GRAPPA or SENSE-DL, images reconstructed with SCR-DL showed superior NMSE and SSIM.

Multichannel Data Acquisition and Monitoring System Utilizing Modbus Protocol with IIoT Automation

This paper introduces a multi-channel data acquisition and monitoring system that integrates Modbus communication protocol and IIoT automation to improve business. The system is designed to capture and monitor multiple parameter data simultaneously, providing accurate and fast measurements of variables such as temperature, humidity, and pressure in various applications. The system uses the widely used Modbus protocol, known for its reliability in industrial automation, to ensure seamless communication between interconnected devices and thus promote interoperability in more diverse aspects of the network environment. Working with IIoT automation, the system not only facilitates data collection, but also helps increase intelligence to focus on business efficiency. Its multi-channel architecture supports data obtained from eight different channels, making it adaptable to complex business processes or research operations that require high precision and scalability. In addition, the system is designed to provide a powerful and flexible solution to meet today's system business needs by prioritizing functionality and ease of integration. The ability to interpret effectively demonstrates its importance as a reliable tool for instant collection and monitoring of information in an environment where accuracy and speed are important.

A noise-enhanced machine fault diagnosis method with multi-channel information fusion

ABSTRACT Condition health monitoring and fault diagnosis is able to safeguard against potential threats to machines. Nevertheless, the acquired signals by using a plenty of sensors are often accompanied by noise and meanwhile the useful information contained in the signals is not both complete and reliable, thereby together reducing the accuracy and stability of the fault diagnosis. Therefore, this paper proposes a noise-enhanced intelligent fault diagnosis method with multi-channel information fusion. Here, it would inject the varying levels of Gaussian noise into multi-channel input data as well as intelligent diagnostic models, with a view to elucidating the benefits of noise. Furthermore, the proposed method is validated through three experiments. The experimental results demonstrate that the diagnostic accuracy of the hydraulic motor and the two different bearings reaches 99.85%, 99.89%, and 99.85% by using the proposed method, respectively, which are increased by 2.50%, 4.09%, and 2.50%, respectively, compared with one without the injection of noise. In addition, by comparing the diagnostic accuracy of ones with single-channel and multi-channel information fusion under the optimal noise level in both cases, it is found that one with multi-channel information fusion shows an average of 3.20% increase than the single-channel one.

Varying free-gas zone (FGZ) and bottom-simulating reflection (BSR) response across a deep graben off Trujillo, central Peru

The complexity of marine gas hydrate systems at the Peruvian convergent margin has been linked to the post-Miocene history of vertical tectonics and subduction erosion that affected the forearc. Here, multichannel seismic data and published findings reveal that such a complexity has been further extended by the occurrence of the pre-Miocene deep Morsa Norte Graben (MNG) off Trujillo (8°–9° S) in the Central Peru margin. At water depths of 650–750 m in the upper slope, directly above the MNG depocentre (which has a 4–6 km overburden thickness), continuous bottom-simulating reflections (BSRs) and concentrated sub-BSR high-amplitude reflections are confined beneath a layered basin with a low–moderate near-seafloor heat flow (7–33 mW m −2 ). A deeper BSR modelled with a thermogenic gas composition is associated with the enhanced reflections. At a water depth of 900 m, sub-BSR reflections become less frequent in an area with a layered sediment cover defined by a moderate near-seafloor heat flow (15–33 mW m −2 ). At a water depth of 1200 m, where the MNG is relatively thick (3–4 km overburden thickness), faults connect patchy BSRs with a moderate–high near-seafloor heat flow (52–110 mW m −2 ). There, sub-BSR enhanced reflections are scarce. Immediately above the top of the gas hydrate stability zone (GHSZ), the near-seafloor heat flow reaches 81 mW m −2 . Modelling suggests a water depth-dependent transport of heat towards the seafloor with respect to the top of the GHSZ, implying that the closer the seafloor is to the top of the GHSZ, the lower the advection of heat, and vice versa. Recent seafloor-related depositional and structural features amplify such relations in agreement with near-seafloor heat-flow variability. However, towards the area outside the extent of the MNG (&lt;3 km overburden thickness), continuous BSRs are not linked either to a deeper BSR or to sub-BSR enhanced reflections. The continuity of one of these BSRs is deflected upwards beneath a slump, suggesting an incomplete thermal re-equilibration of the GHSZ. Therefore, we conclude that the BSR responds to: (1) the confinement and thickening of the free-gas zone (FGZ) above the MNG depocentre due to the sealing effect of recent sedimentation close to the top of the GHSZ; (2) the seepage of gas-rich fluids from a thinned FGZ above the relatively thick MNG, due to the enabling effect of faults cutting the GHSZ far from the top of the GHSZ; (3) the undisturbed state of the FGZ outside the extent of the MNG; and (4) the disequilibrium state of the base of the GHSZ due to the unloading of sediments in an unstable slope environment prone to failure.

A method for predicting remaining useful life using enhanced Savitzky–Golay filter and improved deep learning framework

Ensuring operational integrity in large-scale equipment hinges on effective fault prediction and health management. Prognostics and health management (PHM) face the challenge of accurately predicting remaining useful life (RUL) using multivariate sensor data. Traditional methods often require extensive prior knowledge for indicator construction and processing. Deep learning offers a promising alternative. This study presents a multi-channel multi-scale deep learning approach. Initially, an improved Savitzky‒Golay filter (ISG) addresses challenges posed by large and rapidly changing data volumes, enhancing data preprocessing. Subsequently, a framework integrates convolutional neural networks (CNNs) with long short-term memory (LSTM) to capture hierarchical signal information and make integrated predictions. The CNN extracts spatial features from multi-channel input data, while the LSTM captures temporal dependencies. By fusing outputs from both components, the framework enhances predictive accuracy and robustness for complex operational datasets. Experimental validation on the C-MAPSS dataset tests various fusion methods and CNN depths, determining parameters and evaluating filtering effectiveness. Comparative analyses show promising performance, particularly under dynamic conditions. While not optimal for predicting multiple fault types, it outperforms classical algorithms, especially in single fault type prediction tasks.

Deep learning and genetic algorithm driven accelerated design for frequency-multiplexed complex-amplitude coding meta-hologram

Frequency-multiplexed metasurfaces represent a significant innovation in breaking the functional limitations of traditional metasurfaces, showing immense potential in multi-channel communication. However, existing frequency-multiplexed metasurfaces primarily focus on pure phase and linear polarization modulation, neglecting the modulation for complex amplitude and circularly polarized waves. Additionally, crosstalk suppression between dual-frequency channels often requires meticulous tuning of the meta-atom structure. Therefore, manually designing a set of meta-atoms that satisfies both complex amplitude modulation and low crosstalk at dual frequencies is extremely challenging and time-consuming. Here, we utilize the method of deep learning and genetic algorithm to design a kind of meta-atom capable of bi-spectral 2-bit amplitude and arbitrary phase modulation, which greatly reduces the design difficulty and achieves excellent low-crosstalk performance. This method can be easily generalized to the design of other complex meta-atoms to improve the design efficiency. Furthermore, we propose a frequency-multiplexed complex-amplitude coding meta-hologram for modulating left-handed circularly polarized (LCP) waves. When illuminated with LCP light, it can reconstruct two distinct holographic images at two different frequencies in the near field with high quality. The independent modulation capability of the metasurface for multiple degrees of freedom of frequency, amplitude and phase gives it broad application prospects in multi-channel communication, data storage and perfect holography.

Advanced power quality monitoring with dilated convolutional neural networks for smart nanogrids

This study presents the development of an advanced power quality monitoring (PQM) system using dilated convolutional deep neural networks (DCDNN) for smart nanogrids. Traditional convolutional neural networks (CNNs) face challenges in efficiently handling high-dimensional data and identifying nuanced features due to their limited receptive field. To overcome these limitations, our DCDNN model employs a novel use of dilated convolutions to expand the receptive field without increasing network complexity, enabling the capture of long-range dependencies essential for accurate classification of power quality disturbances (PQDs). In addition, the integration of multi-channel time-series data processing, including voltage, current, and frequency measurements, is unique to our approach. The model processes multi-channel time-series data, including voltage, current, and frequency measurements, achieving an average accuracy of 98.9% across 29 PQD classes and 100% accuracy in 6 main classes, with a reduced detection time of 47 µs per segment. This approach not only improves real-time disturbance detection but also enhances the reliability and efficiency of electrical systems. The results demonstrate significant improvements over existing methods, underscoring the potential of DCDNNs in advancing PQM practices. Future work will focus on validating the model in real-world conditions and optimizing its computational efficiency.