Search

The health status of bearings seriously affects the operational efficiency of equipment, and it is important to carry out bearing health status detection. A bearing fault diagnosis method based on stepwise variational modal decomposition (SVMD) with adaptive initialization center frequency and Gramian angular difference field is proposed. Firstly, a method of center frequency initialization base on frequency energy distribution characteristics is proposed to improve the decomposition speed and stability. Secondly, SVMD with single component decomposition and local decomposition is proposed to improve decomposition efficiency. It can effectively avoid inconsistency in different signal parameter settings and ensures consistency in the number of signal components, which is very suitable for batch processing of signals. Finally, Gramian angular field (GAF) and convolutional neural networks (CNNs) are combined to extract features of the reconstructed signal spectrum and enhance the differential characteristics between different signal spectrum. The experiment shows that the center frequency initialization method can shorten the single decomposition time from 11.13 to 6.71 s. The overall recognition rate can reach 95.2%, which is at least 1.9% higher than other decomposition methods. [ABSTRACT FROM AUTHOR]

By transforming time series into images, a robust and transferable tactical intent recognition framework was proposed, which integrated curve filtering technology and the EfficientNetV2 image recognition network. Curve filtering technology effectively reduced redundancy in numerous time-domain features, model parameters, and training time, an enhanced Gramian angular field (GAF) method was proposed to encode time series into images, enhancing the feature extraction capabilities of convolutional neural networks. The EfficientNetV2 network was adept at processing intent images and could serve as a pre-trained model, facilitating transfer learning across different systems. Experimental results demonstrate that the proposed framework achieves over 0.99% higher accuracy compared to machine learning and deep learning methods, exhibiting superior performance, scalability, robustness, and transferability.

Due to the limitations of deep learning models in processing one-dimensional signal feature extraction, and high model complexity leading to low training accuracy and large consumption of computing resources, this paper innovatively proposes a rolling bearing fault diagnosis method based on Gramian Angular Field (GAF) and enhanced lightweight residual network. Firstly, the one-dimensional signal is transformed into a two-dimensional GAF image, fully preserving the signal's temporal dependency. Secondly, to address the parameter redundancy and high computational complexity of the ResNet-18 model, its residual blocks are improved. The second convolutional layer in the downsampling residual blocks is removed, traditional convolutional layers are replaced with depthwise separable convolutions, and the lightweight Efficient Channel Attention (ECA) module is embedded after each residual block. This further enhances the model's ability to capture key features while maintaining low computational cost, resulting in a lightweight model referred to as E-ResNet13. Finally, the generated GAF feature maps are fed into the E-ResNet13 model for training, and through a global average pooling layer, they are mapped to a fully connected layer for classifying the faults of rolling bearings. Verifying the superiority of the proposed GAF-E-ResNet13 model, experimental results show that the GAF image encoding method achieves higher fault recognition accuracy compared to other encoding methods. Compared with other intelligent diagnosis methods, the E-ResNet13 model demonstrates strong diagnostic performance and generalization capability under both a single condition and complex varying conditions, fully proving the innovation and practicality of this method. [ABSTRACT FROM AUTHOR]

To address the problems of low detection accuracy of rolling bearings under different loads and the difficulty of effectively identifying the lack of labelled data, a rolling bearing fault diagnosis method combining GADF-DFT image coding and Multi-kernel domain coordinated adaptation network is proposed. Firstly, the vibration signal is converted into a two-dimensional image using GADF coding technology, and then the GADF image is converted into the frequency domain using discrete Fourier transform to extract deeper feature information. Combined with the multi-source domain adaptive method, the public feature extraction module is used to initially achieve feature mining of the image; the MK-MMD algorithm of the domain-specific adaptive module reduces the difference in feature distribution between the source and target domains; and the final classification difference minimization module reduces the problems caused by the classification errors that may be generated by the different domain classifiers due to the fact that the data samples are located near the category boundaries. The test uses the Case Western Reserve University dataset and divides the dataset with different operating conditions as the source and target domains, and the test results show that the proposed model demonstrates its effectiveness in responding to the complex operating condition changes in rolling bearing fault detection in multiple operating condition migration tasks, good adaptability and robustness, and is able to achieve accurate fault diagnosis under different operating conditions. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Hubei Minzu University (Natural Science Edition) is the property of Journal of Hubei Minzu University (Natural Sciences Edition) Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Electric Power Automation Equipment / Dianli Zidonghua Shebei is the property of Electric Power Automation Equipment Press and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

To enhance the safety of autonomous vehicles in mixed traffic and connected environment, it is crucial to recognize the lane-changing intentions (LCIs) of human-driven vehicles for autonomous vehicles. This paper presents a novel method for LCI recognition, which extracts features from the driving state and relative motion of the target vehicle and its neighbors. The method applies short-time Fourier transform, Gramian angular summation field, and Gramian angular difference field to the time-series data, and generates three grayscale images, which are merged into one information fusion image (IFI) by image processing techniques. The IFIs are then classified into three categories: lane keeping, lane-changing left, and lane-changing right, using the Vision Transformer model with transfer learning to speed up convergence and reduce training cost. The experimental results demonstrate that the proposed method outperforms the traditional methods, achieving an accuracy of 95.65% for recognizing LCI 3s before the lane change point. [ABSTRACT FROM AUTHOR]

Forecasting energy demand is critical to ensure the steady operation of the power system. However, present approaches to estimating power load are still unsatisfactory in terms of accuracy, precision, and efficiency. In this paper, we propose a novel method, named ELFNet, for estimating short-term electricity consumption, based on the deep convolutional neural network model with a double-attention mechanism. The Gramian Angular Field method is utilized to convert electrical load time series into 2D image data for input into the proposed model. The prediction accuracy is greatly improved through the use of a convolutional neural network to extract the intrinsic characteristics from the input data, along with channel attention and spatial attention modules, to enhance the crucial features and suppress the irrelevant ones. The present ELFNet method is compared to several classic deep learning networks across different prediction horizons using publicly available data on real power demands from the Belgian grid firm Elia. The results show that the suggested approach is competitive and effective for short-term power load forecasting. [ABSTRACT FROM AUTHOR]

Congestive heart failure (CHF) is a serious threat to human health. Electrocardiogram (ECG) signals have been proven to be useful in the detection of CHF. However, the low amplitude and short duration of the ECG signals, as well as the superimposed noise during the real-time acquisition of the signal, seriously affect the CHF detection. To improve the detection rate of CHF, this paper proposes a congestive heart failure detection method based on Gramian angular field (GAF) and two-dimensional symbolic phase permutation entropy (SPPE2D). The significant advantage of this method is that it reduces the sensitivity to noise, and good performance can be obtained without denoising using raw ECG signals. We segment the original ECG signals into 2 s non-overlapping segments and convert them into images using the GAF method. Then, the SPPE2D algorithm is proposed to measure the complexity between normal sinus rhythm (NSR) and CHF, and analyze the anti-noise performance of the algorithm. Finally, the SPPE2D features of GAF images are computed and input into a support vector machine (SVM) for CHF detection. Classification accuracy on the Massachusetts Institute of Technology − Beth Israel Hospital Normal Sinus Rhythm Database and Beth Israel Deaconess Medical Center Congestive Heart Failure Database is 99.59%, sensitivity is 99.42%, specificity is 99.80%, and F1-score is 99.62%. The accuracy of detecting CHF reach more than 97.75% in the other five CHF databases. The experimental results show that the method based on GAF and SPPE2D can effectively detect CHF by images of ECG signals and has good robustness. CHF can be detected using the 2 s sample lengths of ECG signals recording with high sensitivity, giving clinicians ample time to treat patients with CHF. [ABSTRACT FROM AUTHOR]

Relative permeability (RP) curves which provide fundamental insights into porous media flow behavior serve as critical parameters in reservoir engineering and numerical simulation studies. However, obtaining accurate RP curves remains a challenge due to expensive experimental costs, core contamination, measurement errors, and other factors. To address this issue, an innovative approach using deep learning strategy is proposed for the prediction of rock sample RP curves directly from mercury injection capillary pressure (MICP) measurements which include the mercury injection curve, mercury withdrawal curve, and pore size distribution. To capture the distinct characteristics of different rock samples' MICP curves effectively, the Gramian Angular Field (GAF) based graph transformation method is introduced for mapping the curves into richly informative image forms. Subsequently, these 2D images are combined into three-channel red, green, blue (RGB) images and fed into a Convolutional Long Short-Term Memory (ConvLSTM) model within our established self-supervised learning framework. Simultaneously the dependencies and evolutionary sequences among image samples are captured through the limited MICP-RP samples and self-supervised learning framework. After that, a highly generalized RP curve calculation proxy framework based on deep learning called RPCDL is constructed by the autonomously generated nearly infinite training samples. The remarkable performance of the proposed method is verified with the experimental data from rock samples in the X oilfield. When applied to 37 small-sample data spaces for the prediction of 10 test samples, the average relative error is 3.6%, which demonstrates the effectiveness of our approach in mapping MICP experimental results to corresponding RP curves. Moreover, the comparison study against traditional CNN and LSTM illustrated the great performance of the RPCDL method in the prediction of both So and Sw lines in oil–water RP curves. To this end, this method offers an intelligent and robust means for efficiently estimating RP curves in various reservoir engineering scenarios without costly experiments. [ABSTRACT FROM AUTHOR]

Abstract Relative permeability (RP) curves which provide fundamental insights into porous media flow behavior serve as critical parameters in reservoir engineering and numerical simulation studies. However, obtaining accurate RP curves remains a challenge due to expensive experimental costs, core contamination, measurement errors, and other factors. To address this issue, an innovative approach using deep learning strategy is proposed for the prediction of rock sample RP curves directly from mercury injection capillary pressure (MICP) measurements which include the mercury injection curve, mercury withdrawal curve, and pore size distribution. To capture the distinct characteristics of different rock samples' MICP curves effectively, the Gramian Angular Field (GAF) based graph transformation method is introduced for mapping the curves into richly informative image forms. Subsequently, these 2D images are combined into three-channel red, green, blue (RGB) images and fed into a Convolutional Long Short-Term Memory (ConvLSTM) model within our established self-supervised learning framework. Simultaneously the dependencies and evolutionary sequences among image samples are captured through the limited MICP-RP samples and self-supervised learning framework. After that, a highly generalized RP curve calculation proxy framework based on deep learning called RPCDL is constructed by the autonomously generated nearly infinite training samples. The remarkable performance of the proposed method is verified with the experimental data from rock samples in the X oilfield. When applied to 37 small-sample data spaces for the prediction of 10 test samples, the average relative error is 3.6%, which demonstrates the effectiveness of our approach in mapping MICP experimental results to corresponding RP curves. Moreover, the comparison study against traditional CNN and LSTM illustrated the great performance of the RPCDL method in the prediction of both S o and S w lines in oil–water RP curves. To this end, this method offers an intelligent and robust means for efficiently estimating RP curves in various reservoir engineering scenarios without costly experiments.

Fault diagnosis is one of the important applications of edge computing in the Industrial Internet of Things (IIoT). To address the issue that traditional fault diagnosis methods often struggle to effectively extract fault features, this paper proposes a novel rolling bearing fault diagnosis method that integrates Gramian Angular Field (GAF), Convolutional Neural Network (CNN), and Vision Transformer (ViT). First, GAF is used to convert one-dimensional vibration signals from sensors into two-dimensional images, effectively retaining the fault features of the vibration signal. Then, the CNN branch is used to extract the local features of the image, which are combined with the global features extracted by the ViT branch to diagnose the bearing fault. The effectiveness of this method is validated with two datasets. Experimental results show that the proposed method achieves average accuracies of 99.79% and 99.63% on the CWRU and XJTU-SY rolling bearing fault datasets, respectively. Compared with several widely used fault diagnosis methods, the proposed method achieves higher accuracy for different fault classifications, providing reliable technical support for performing complex fault diagnosis on edge devices. [ABSTRACT FROM AUTHOR]

With the COVID-19 outbreak, schools and universities have massively adopted online learning to ensure the continuation of the learning process. However, in such setting, instructors lack efficient mechanisms to evaluate the learning gains and get insights about difficulties learners encounter. In this research work, we tackle the problem of predicting learner performance in online learning using a deep learning-based approach. Our proposed solution allows stakeholders involved in the online learning to anticipate the learner outcome ahead of the final assessment hence offering the opportunity for proactive measures to assist the learners. We propose a two-pathway deep learning model to classify learner performance using their interaction during the online sessions in the form of clickstreams. We also propose to transform these time series of clicks into images using the Gramian Angular Field. The learning model makes use of the available extra demographic and assessment information. We evaluate our approach on the Open University Learning Analytics Dataset. Comprehensive comparative study is conducted with evaluation against state-of-art approaches under different experimental settings. We also demonstrate the importance of including extra demographic and assessment data in the prediction process. [ABSTRACT FROM AUTHOR]

Aiming at the problem of fault diagnosis and classification of rolling bearing and gear of gearboxes, a novel method based on matrix distance features of Gramian angular field (GAF) image is proposed based on sliding window compressible GAF transformation. The method converts the one-dimensional fault signal into a two-dimensional feature matrix and constructs the discrimination matrix of each fault category by establishing the mean value of the feature matrix of a priori samples. For the new sampled signal, after converting it into a two-dimensional feature matrix, the feature matrix is obtained. The fault classification is carried out by using the matrix distance between feature matrix and the discrimination matrix of each category. The method is validated by the test data of Case Western Reserve University and the acoustic emission data from a gearbox test bench. The classification accuracy is 99.17% and 95.71%, which presented the feasibility and effectiveness of the novel method proposed in this paper. [ABSTRACT FROM AUTHOR]

The symmetry of vibration signals collected from healthy machinery, which gradually degenerates with the development of faults, must be detected for timely diagnosis and prognosis. However, conventional methods may miss spatiotemporal relationships, struggle with varying sampling rates, and lack adaptability to changing loads and conditions, affecting diagnostic accuracy. A novel bearing fault diagnosis approach is proposed to address these issues, which integrates the Gramian angular field (GAF) transformation with a parallel deep convolutional neural network (DCNN). The crux of this method lies in the preprocessing of input signals, where sampling rate normalization is employed to minimize the effects of varying sampling rates on diagnostic outcomes. Subsequently, the processed signals undergo GAF transformation, converting them into an image format that effectively represents their spatiotemporal relationships in a two-dimensional space. These images serve as inputs to the parallel DCNN, facilitating feature extraction and fault classification through deep learning techniques and leading to improved generalization capabilities on test data. The proposed method achieves an overall accuracy of 96.96%, even in the absence of training data within the test set. Discussions are also conducted to quantify the effects of sampling rate normalization and model structures on diagnostic accuracy. [ABSTRACT FROM AUTHOR]

With the increasing scale of photovoltaic (PV) power stations, timely anomaly detection through analyzing the PV output power curve is crucial. However, overlooking the impact of external factors on the expected power output would lead to inaccurate identification of PV station anomalies. This study focuses on the discrepancy between measured and expected PV power generation values, using a dual classification system. The system leverages two-dimensional Gramian angular field (GAF) data and curve features extracted from one-dimensional time series, along with attention weights from a CNN network. This approach effectively classifies anomalies, including normal operation, aging pollution, and arc faults, achieving an overall classification accuracy of 95.83%. [ABSTRACT FROM AUTHOR]

In order to improve the accuracy of bearing fault diagnosis under a small sample, variable load, and noise conditions, a new fault diagnosis method based on an image information fusion and Vision Transformer (ViT) transfer learning model is proposed in this paper. Firstly, the method applies continuous wavelet transform (CWT), Gramian angular summation field (GASF), and Gramian angular difference field (GADF) to the time series data, and generates three grayscale images. Then, the generated three grayscale images are merged into an information fusion image (IFI) using image processing techniques. Finally, the obtained IFIs are fed into the advanced ViT model and trained based on transfer learning. In order to verify the effectiveness and superiority of the proposed method, the rolling bearing dataset from Case Western Reserve University (CWRU) is used to carry out experimental studies under different working conditions. Experimental results show that the method proposed in this paper is superior to other traditional methods in terms of accuracy, and the effect of ViT model based on transfer learning (TLViT) training is better than that of the Resnet50 model based on transfer learning training (TLResnet50) under variable loads and small sample conditions. In addition, the experimental results also prove that the IFI with multiple image information has better anti-noise ability than the single information image. Therefore, the method proposed in this paper can improve the accuracy of bearing fault diagnosis under small sample, variable load and noise conditions, and provide a new method for bearing fault diagnosis. [ABSTRACT FROM AUTHOR]

Specific emitter identification (SEI) is a methodology employed to identify emitters by exploiting the hardware impairments inherent in transmitting devices. In the real world, there are challenges in performing SEI on radiation source signals, such as serious imbalance among samples, leading to low model accuracy, poor generalization, and limited practical application. These challenges widely occur in modern military, security, and other fields, but related research works have been conducted relatively late. In this paper, we propose a generative adversarial network (GAN) with the Gramian angular field (GAF) method to address few-shot case data. Specifically, the proposed method employs GAF transformation to convert temporal radar data into a two-dimensional image format and utilizes an enhanced GAN to improve the classifier for imbalanced data based on the characteristics of GAF through training on both augmented and original samples. The experiments were conducted on real-world automatic dependent surveillance-broadcast (ADS-B) signals, demonstrating the effectiveness of the proposed method. The method could significantly improve the performance of the SEI model in inter-class imbalanced scenarios. [ABSTRACT FROM AUTHOR]

Neutron detection is an important technology in the field of nuclear energy development and is involved in many research and application areas, such as particle physics, material science, cosmic ray detection and even environmental monitoring, oil well detection and nuclear medicine, etc. Since neutron scintillator detectors often respond to both neutron and γ-ray, effective discrimination between neutron and γ-ray is a prerequisite for high-precision neutron detection. In order to further explore way to enhance the performance of n/γ discrimination, this paper combined the pulse shape discrimination (PSD) technique and the Gramian angular field (GAF) image transformation method, and applied the convolutional neural network (CNN) classification model to the n/γ discrimination work. The 239Pu-Be neutron source and the Cs2LiYCl6:Ce3+ (CLYC) detector were used to set up an experimental platform for the n/γ hybrid radiation field, and 20 000 original pulsed one-dimensional sequence samples were acquired through the Tektronix model DPO4034 oscilloscope. In the experiment, the charge comparison method was adopted to discriminate the original samples, and the discrimination results can be used to produce the labels of the dataset used in the GAF-CNN method and for the final comparison of the discriminative performance of the various methods. Due to the excellent performance of the CLYC detector, the discrimination effect of the charge comparison method is good, which ensures that the labeling of the dataset can be produced with high accuracy, and after the best performance of the charge comparison method has been achieved through the optimization of the window, the gap between the upper limit of the performance of the traditional method and the neural network method can be clearly found. The GAF-CNN discrimination method transformed the n/γ pulse data into a two-dimensional image through the GAF, after which the image was fed into the CNN classification model for sample discrimination, which transformed the n/γ discrimination problem into a simple image binary classification problem. Since the nuclear pulse signal is a typical time series, the use of GAF can retain the time domain features of the nuclear pulse in a more complete way, and the convolution operation of the CNN can utilize the frequency domain features, so the GAF-CNN is a kind of discrimination method that can utilize the time-frequency features at the same time. In order to verify the accuracy of GAF-CNN discrimination, the discrimination effect was compared with the traditional CNN discrimination method and the charge comparison method, where the traditional CNN discrimination method refers to the method of simply collapsing the pulsed one-dimensional sample sequences into a two-dimensional matrix and inputting it to the CNN for sample identification. The results show that the GAF-CNN discrimination method has a lower discrimination error rate and shorter processing time, and the figure of merit (FOM) of n/γ discrimination has an order of magnitude improvement. Meanwhile, it has the characteristics of network lightweight, which helps to realize the embedded deployment of convolutional neural network PSD algorithm, and provides a feasible PSD technology solution for the development of high-performance n/γ composite detection spectrometer.

The origin of seeds is a crucial environmental factor that significantly impacts crop production. Accurate identification of seed origin holds immense importance for ensuring traceability in the seed industry. Currently, traditional methods used for identifying the origin of maize seeds involve mineral element analysis and isotope fingerprinting, which are laborious, destructive, time-consuming, and suffer from various limitations. In this experiment, near-infrared spectroscopy was employed to collect 1360 maize seeds belonging to 12 different varieties from 8 distinct origins. Spectral information within the range of 11,550–3950 cm−1 was analyzed while eliminating multiple interferences through first-order derivative combined with standard normal transform (SNV). The processed one-dimensional spectral data were then transformed into three-dimensional spectral maps using Gram's Angle Field (GAF) to be used as input values along with the VGG-19 network model. Additionally, a convolution layer with a step size of 1 × 1 and the padding value set at 1 was added, while pooling layers had a step size of 2 × 2. A batch size of 48 and learning rate set at 10−8 were utilized while incorporating the Dropout mechanism to prevent model overfitting. This resulted in the construction of the GAF-VGG network model which successfully decoded the output into accurate place-of-origin labels for maize seed detection. The findings suggest that the GAF-VGG network model exhibits significantly superior performance compared to both the original data and the PCA-based origin identification model in terms of accuracy, recall, specificity, and precision (96.81%, 97.23%, 95.35%, and 95.12%, respectively). The GAF-VGGNet model effectively captures the NIR features of different origins of maize seeds without requiring feature wavelength extraction, thereby reducing training time and enhancing accuracy in identifying maize seed origin. Moreover, it simplifies near-infrared (NIR) spectral modeling complexity and presents a novel approach to maize seed origin identification and traceability analysis. [ABSTRACT FROM AUTHOR]

Obstructive sleep apnea (OSA), a prevalent sleep disorder, is intimately associated with various other diseases, particularly cardiovascular conditions. The conventional diagnostic method, nocturnal polysomnography (PSG), despite its widespread use, faces challenges due to its high cost and prolonged duration. Recent developments in electrocardiogram-based diagnostic techniques have opened new avenues for addressing these challenges, although they often require a deep understanding of feature engineering. In this study, we introduce an innovative method for OSA classification that combines a composite deep convolutional neural network model with a multimodal strategy for automatic feature extraction. This approach involves transforming the original dataset into scalogram images that reflect heart rate variability attributes and Gramian angular field matrix images that reveal temporal characteristics, aiming to enhance the diversity and richness of data features. The model comprises automatic feature extraction and feature enhancement components and has been trained and validated on the PhysioNet Apnea-ECG database. The experimental results demonstrate the model's exceptional performance in diagnosing OSA, achieving an accuracy of 96.37%, a sensitivity of 94.67%, a specificity of 97.44%, and an AUC of 0.96. These outcomes underscore the potential of our proposed model as an efficient, accurate, and convenient tool for OSA diagnosis. [ABSTRACT FROM AUTHOR]

Copyright of Atomic Energy Science & Technology is the property of Editorial Board of Atomic Energy Science & Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Aerial sensor fault detection is of great importance in flight missions. However, the dimensionality of sensor time-series data is extremely high and the time span is extremely long, which lead to poor detection performance of existing methods. To address these problems, this paper proposes a time-series to 2D fault detection (T2D) method for aerial sensor fault detection based on time-series. Firstly, the information entropy is applied to the classification and aggregation approximation algorithm to achieve effective compression of the data while fully retaining the time-series features. Secondly, the gramian angular field is introduced to encode the reduced-dimensional data into two-dimensional images, maintaining the long-range dependence of the original sequence. Finally, a flexible convolution block is designed and inserted into the encoder of the detection network Vision Transformer to improve the detection accuracy of the model. Experimental results show that the T2D model performs significantly better than other models on a simulated time-series dataset of a civilian aircraft test flight, indicating the effectiveness and superiority of the proposed method.

Objective: To realize the rapid traceability detection of Astragalus membranaceus from different origins. Methods: This study proposed a rapid detection method for the origin of Astragalus membranaceus based on the improved MobileNetv3 network based on the combination of electronic tongue and electronic eye. The electronic tongue and electronic eye were used to collect the one-dimensional fingerprint and two-dimensional appearance image information of different samples of Astragalus membranaceus. The Gramian Angular Field (GAF) was used to convert the one-dimensional electronic tongue signal into two-dimensional image information, retain the time series related features in the electronic tongue signal, and then fused them with the image information collected by the electronic eye. Finally, the MobileNetv3 model improved based on Pyramid Split Attention (PSA) was adopted to realize the classification and recognition of Astragalus samples from different habitats. Results: The experimental results showed that the method in this paper had higher recognition accuracy than using electronic tongue or electronic eye alone. The accuracy, precision, rrecall and F1-score of the test set were 98.8%, 98.8%, 98.8% and 0.99, respectively. The classification accuracy of the improved MobileNetv3 network was 8% higher than that of the original model, and the parameter quantity was only about 1/5 of the original parameter quantity. Conclusion: The improved MobileNetv3 network can effectively reduce the calculation of parameters and improve the recognition accuracy of Astragalus membranaceus from different origins.

Non-technical losses (NTL) refer to unrecorded power consumption generated by dishonest customers, which is a substantial issue affecting the power system stability and economic efficiency of the power grid. The detection of dishonest customers is hindered by the complexity of NTL such as data feature selection, retention time feature, and power consumption pattern judgment. This work addresses these issues using meter recording data, proposing an NTL detection approach with Gram’s angle field (GAF) and deep residual network (ResNet). Principal component analysis (PCA) method is applied to compress multiple electricity detection indexes, which aims to obtain multi-dimensional power consumption data characteristics without changing its timing characteristics. The GAF method is used to convert the time-series power features of individual users into a two-dimensional image, achieving the purpose of maintaining the user’s time-series features and user-based units. The images generated by the GAF method, which contain information about the electricity consumption characteristics of many customers, are classified by ResNet to highlight customers with NTL. The claimed algorithm was tested on a dataset consisting of both fraudulent and non-fraudulent subscriber data. The results demonstrated that the NTL detection method based on GAF and ResNet is superior to the traditional NTL detection method and has high accuracy.

Due to the limitations of deep learning models in processing one-dimensional signal feature extraction, and high model complexity leading to low training accuracy and large consumption of computing resources, this paper innovatively proposes a rolling bearing fault diagnosis method based on Gramian Angular Field (GAF) and enhanced lightweight residual network. Firstly, the one-dimensional signal is transformed into a two-dimensional GAF image, fully preserving the signal’s temporal dependency. Secondly, to address the parameter redundancy and high computational complexity of the ResNet-18 model, its residual blocks are improved. The second convolutional layer in the downsampling residual blocks is removed, traditional convolutional layers are replaced with depthwise separable convolutions, and the lightweight Efficient Channel Attention (ECA) module is embedded after each residual block. This further enhances the model’s ability to capture key features while maintaining low computational cost, resulting in a lightweight model referred to as E-ResNet13. Finally, the generated GAF feature maps are fed into the E-ResNet13 model for training, and through a global average pooling layer, they are mapped to a fully connected layer for classifying the faults of rolling bearings. Verifying the superiority of the proposed GAF-E-ResNet13 model, experimental results show that the GAF image encoding method achieves higher fault recognition accuracy compared to other encoding methods. Compared with other intelligent diagnosis methods, the E-ResNet13 model demonstrates strong diagnostic performance and generalization capability under both a single condition and complex varying conditions, fully proving the innovation and practicality of this method.

Forecasting energy demand is critical to ensure the steady operation of the power system. However, present approaches to estimating power load are still unsatisfactory in terms of accuracy, precision, and efficiency. In this paper, we propose a novel method, named ELFNet, for estimating short-term electricity consumption, based on the deep convolutional neural network model with a double-attention mechanism. The Gramian Angular Field method is utilized to convert electrical load time series into 2D image data for input into the proposed model. The prediction accuracy is greatly improved through the use of a convolutional neural network to extract the intrinsic characteristics from the input data, along with channel attention and spatial attention modules, to enhance the crucial features and suppress the irrelevant ones. The present ELFNet method is compared to several classic deep learning networks across different prediction horizons using publicly available data on real power demands from the Belgian grid firm Elia. The results show that the suggested approach is competitive and effective for short-term power load forecasting.

This paper proposes fault diagnosis methods aimed at proactively preventing potential safety issues in robot systems, particularly human coexistence robots (HCRs) used in industrial environments. The data were collected from durability tests of the driving module for HCRs, gathering time-series vibration data until the module failed. In this study, to apply classification methods in the absence of post-failure data, the initial 50% of the collected data were designated as the normal section, and the data from the 10 h immediately preceding the failure were selected as the fault section. To generate additional data for the limited fault dataset, the Wasserstein generative adversarial networks with gradient penalty (WGAN-GP) model was utilized and residual connections were added to the generator to maintain the basic structure while preventing the loss of key features of the data. Considering that the performance of image encoding techniques varies depending on the dataset type, this study applied and compared five image encoding methods and four CNN models to facilitate the selection of the most suitable algorithm. The time-series data were converted into image data using image encoding techniques including recurrence plot, Gramian angular field, Markov transition field, spectrogram, and scalogram. These images were then applied to CNN models, including VGGNet, GoogleNet, ResNet, and DenseNet, to calculate the accuracy of fault diagnosis and compare the performance of each model. The experimental results demonstrated significant improvements in diagnostic accuracy when employing the WGAN-GP model to generate fault data, and among the image encoding techniques and convolutional neural network models, spectrogram and DenseNet exhibited superior performance, respectively. [ABSTRACT FROM AUTHOR]

Fault diagnosis methods for rolling bearings based on deep learning have become a research hotspot. However, these methods mostly use convolutional neural networks (CNNs), which have the problem of gradient dispersion or disappearance as the network deepens. Moreover, directly converting vibration signals into images as network input cannot preserve the temporal correlation between signals. In the case of small datasets and complex and variable working conditions, the accuracy of fault diagnosis is low and the generalisation ability is poor. To solve the above problems, a rolling bearing fault diagnosis method based on the Gramian angular field (GAF) and an SE-ResNeXt50 transfer learning model is proposed. Firstly, the parameters of the GAF obtained from multiple experiments are selected and the one-dimensional time-series vibration signal is encoded by combining the data enhancement method, and converted into a Gramian angular difference field (GADF) diagram and a Gramian angular sum field (GASF) diagram with local time information and uniqueness. Then, a fine-tuning transfer learning strategy is used to transfer the pre-trained model parameters to an SE-ResNeXt50 model, which improves the training speed of the model and improves the overfitting problem of the model on small target datasets. Finally, the GAF diagram is used as the input to the model and a feature recalibration strategy is used to adaptively obtain the importance of each feature channel, which further improves the feature utilisation. To verify the effectiveness and superiority of the proposed method, the rolling bearing data from Case Western Reserve University are selected for experimental verification and the generalisation performance of the proposed method is tested under varying loads and different dataset scales. The results show that when there is only a small amount of data, the proposed method can still achieve high diagnosis accuracy for different loads and has better recognition accuracy and generalisation compared to other fault diagnosis methods. [ABSTRACT FROM AUTHOR]

Fault diagnosis is one of the important applications of edge computing in the Industrial Internet of Things (IIoT). To address the issue that traditional fault diagnosis methods often struggle to effectively extract fault features, this paper proposes a novel rolling bearing fault diagnosis method that integrates Gramian Angular Field (GAF), Convolutional Neural Network (CNN), and Vision Transformer (ViT). First, GAF is used to convert one-dimensional vibration signals from sensors into two-dimensional images, effectively retaining the fault features of the vibration signal. Then, the CNN branch is used to extract the local features of the image, which are combined with the global features extracted by the ViT branch to diagnose the bearing fault. The effectiveness of this method is validated with two datasets. Experimental results show that the proposed method achieves average accuracies of 99.79% and 99.63% on the CWRU and XJTU-SY rolling bearing fault datasets, respectively. Compared with several widely used fault diagnosis methods, the proposed method achieves higher accuracy for different fault classifications, providing reliable technical support for performing complex fault diagnosis on edge devices.

The symmetry of vibration signals collected from healthy machinery, which gradually degenerates with the development of faults, must be detected for timely diagnosis and prognosis. However, conventional methods may miss spatiotemporal relationships, struggle with varying sampling rates, and lack adaptability to changing loads and conditions, affecting diagnostic accuracy. A novel bearing fault diagnosis approach is proposed to address these issues, which integrates the Gramian angular field (GAF) transformation with a parallel deep convolutional neural network (DCNN). The crux of this method lies in the preprocessing of input signals, where sampling rate normalization is employed to minimize the effects of varying sampling rates on diagnostic outcomes. Subsequently, the processed signals undergo GAF transformation, converting them into an image format that effectively represents their spatiotemporal relationships in a two-dimensional space. These images serve as inputs to the parallel DCNN, facilitating feature extraction and fault classification through deep learning techniques and leading to improved generalization capabilities on test data. The proposed method achieves an overall accuracy of 96.96%, even in the absence of training data within the test set. Discussions are also conducted to quantify the effects of sampling rate normalization and model structures on diagnostic accuracy.

The accomplishment of condition monitoring and intelligent maintenance for cantilever structure‐based energy harvesting devices remains a challenge. Here, to tackle the problems, a novel cantilever‐structure freestanding triboelectric nanogenerator (CSF‐TENG) is proposed, which can capture ambient energy or transmit sensory information. First, with and without a crack in cantilevers, the simulations are carried out. According to simulation results, the maximum change ratios of natural frequency and amplitude are 1.1% and 2.2%, causing difficulties in identifying defects by these variations. Thus, based on Gramian angular field and convolutional neural network, a defect detection model is established to achieve the condition monitoring of the CSF‐TENG, and the experimental result manifests that the accuracy of the model is 99.2%. Besides, the relation between the deflection of cantilevers and the output voltages of the CSF‐TENG is first built, and then the defect identification digital twin system is successfully created. Consequently, the system is capable of duplicating the operation of the CSF‐TENG in a real environment, and displaying defect recognition results, so the intelligent maintenance of the CSF‐TENG can be realized. [ABSTRACT FROM AUTHOR]

Prebaked carbon anodes are a critical consumable in the aluminum electrolysis industry. Prebaked carbon anode paste is the intermediate product of the prebaked carbon anode, and its quality significantly impacts the prebaked carbon anode. Therefore, inspecting the quality of the prebaked carbon anode paste is essential. Currently, the quality inspection of the paste still relies on laboratory analysis or manual experience. A laboratory inspection cannot obtain results in real time, while manual inspection poses potential risks. To address these issues, an online intelligent inspection method for prebaked carbon anode paste based on an anomaly detection algorithm was proposed. Firstly, we acquired the temperature of the paste and the power of the kneading motor. Secondly, we transformed these time-series data into images using the Gramian Angular Field (GAF) technique and joined them to create the paste anomaly detection dataset. Thirdly, we trained a matched anomaly detection model based on the PatchCore algorithm. Finally, we compared two advanced models: HaloAE and TSRD. PatchCore performs best on our dataset with an AUC-ROC score of 0.9943, followed by HaloAE (0.9906) and TSRD (0.9811). Our proposed method enables on-time intelligent inspection of prebaked carbon anode paste quality. This eliminates the need for manual inspection, reduces labor requirements, and ensures worker safety. [ABSTRACT FROM AUTHOR]

Abstract This paper presents a research work which focuses on generating synthetic data to enrich the training‐set of a deep learning (DL) based classification system to classify power system transient events using PMU frequency measurements. The synthetically improved training‐set is shown to increase the classification performance compared to the case when only the actual‐data training‐set is used. The proposed classification system helps to reveal high‐frequency transient variation information out of PMU measurements collected at a relatively much lower rate, especially when a small set of training‐data exists. Synthetic PMU frequency data is generated based on the DFT analysis statistics on the limited‐size PMU frequency data. Generation of the synthetic data is achieved by re‐synthesis of the PMU frequency data using inverse DFT, which imitates the DFT frequency and phase behaviour for each event type separately. Then the DL structure is trained to classify the power system transients using the synthetically enriched train set. The proposed method of generating synthetically supported training‐set has lower computational complexity compared to the existing methods in the literature and helps to obtain improved classification results. It can be used to increase the classification performances of power quality devices performing transient event analysis, especially for those with access to a limited set of training‐set.

Automatic Modulation Classification (AMC) is a critical issue in electromagnetic spatial perception. Currently traditional recognition techniques are difficult to adapt to complex signal situations. Most existing modulation classification algorithms ignore the complementarity between different features and the importance of feature fusion. Based on this, we proposed a method for image feature fusion for AMC that fully uses the complementarity between different image features. The original signal is converted into an image by the Gramian Angular Field (GAF) method, and the GAF image is used as the input to the network, meanwhile the received signal is converted from the Inphase-Quadrature (I-Q) domain to the r- $\theta $ domain using the Accumulated Polar Feature conversion technique, and the original signal is feature coded from the r- $\theta $ domain and then converted into an image. The fused features of the two images are used as input to the neural network for model training to achieve automatic modulation classification of multiple types of signals. In the evaluation phase, the differences in the recognition effectiveness of the proposed method by different neural networks are discussed. Experiments show that the best performance is achieved using the Swin-Transformer network model, with a more than 90% recognition rate for the modulation method at signal-to-noise ratios greater than 4dB.

Copyright of Food & Machinery is the property of Food & Machinery Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Image classification methods based on deep learning have been widely used in the study of nonintrusive load identification. However, in the process of encoding the load electrical signals into images, how to fully retain features of the raw data and thus increase the recognizability of loads carried with very similar current signals are still challenging, and the loss of load features will cause the overall accuracy of load identification to decrease. To deal with this problem, this paper proposes a nonintrusive load identification method based on the improved Gramian angular field (iGAF) and ResNet18. In the proposed method, fast Fourier transform is used to calculate the amplitude spectrum and the phase spectrum to reconstruct the pixel matrices of the B channel, G channel, and R channel of generated GAF images so that the color image fused by the three channels contains more information. This improvement to the GAF method enables generated images to retain the amplitude feature and phase feature of the raw data that are usually missed in the general GAF image. ResNet18 is trained with iGAF images for nonintrusive load identification. Experiments are conducted on two private datasets, ESEAD and EMCAD, and two public datasets, PLAID and WHITED. Experimental results suggest that the proposed method performs well on both private and public datasets, achieving overall identification accuracies of 99.545%, 99.375%, 98.964%, and 100% on the four datasets, respectively. In particular, the method demonstrates significant identification effects for loads with similar current waveforms in private datasets. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Fuzhou University is the property of Journal of Fuzhou University, Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Due to the complexity of electromechanical equipment and the difficulties in obtaining large-scale health monitoring datasets, as well as the long-tailed distribution of data, existing methods ignore certain characteristics of health monitoring data. In order to solve these problems, this paper proposes a method for the fault diagnosis of rolling bearings in electromechanical equipment based on an improved prototypical network—the weight prototypical networks (WPorNet). The main contributions of this paper are as follows: (1) the prototypical networks, which perform well on small-sample classification tasks, were improved by calculating the different levels of influence of support sample distributions in order to achieve the prototypical calculation. The change in sample influence was calculated using the Kullback–Leibler divergence of the sample distribution. The influence change in a specific sample can be measured by assessing how much the distribution changes in the absence of that sample; and (2) The Gramian Angular Field (GAF) algorithm was used to transform one-dimensional time series into two-dimensional vibration images, which greatly improved the application effect of the 2D convolutional neural network (CNN). Through experiments on MAFAULDA and CWRU bearing datasets, it was shown that this network effectively solves the shortcomings of a small number of valid samples and a long-tail distribution in health monitoring data, it enhances the dependency between the samples and the global data, it improves the model's feature extraction ability, and it enhances the accuracy of model classification. Compared with the prototypical network, the improved network model increased the performance of the 2-way 10-shot, 2-way 20-shot, and 2-way 50-shot classification tasks by 5.23%, 5.74%, and 4.37%, respectively, and it increased the performance of the 4-way 10-shot, 4-way 20-shot, and 4-way 50-shot classification tasks by 12.02%, 10.47%, and 4.66%, respectively. Experimental results show that the improved prototypical network model has higher sample classification accuracy and stronger anti-interference ability compared with traditional small-sample classification models. [ABSTRACT FROM AUTHOR]

A lightweight neural network fault diagnosis method based on Gramian angular field (GAF) feature map construction and efficient channel attention (ECA) optimization is presented herein to address the problem of the complex structure of traditional neural networks in bearing fault diagnosis. Firstly, a GAF is used to encode vibration signals into a temporal image. Secondly, the double-layer separation residual convolution neural network (DRCNN) is used to learn advanced features of the sample. The multi-branch structure is used as the receiving domain. ECA learns the correlation between feature channels. The extracted feature channels are adaptively weighted by adding a small additional computational cost. Finally, the method is tested and evaluated using wind turbine bearing data. The experimental results show that, compared with the traditional neural network, the DRCNN model based on GAF achieves higher diagnostic accuracy with less parameter calculation. [ABSTRACT FROM AUTHOR]