Multi-domain Features Research Articles

A bearing remaining life prediction method under variable operating conditions based on cross-transformer fusioning segmented data cleaning

Bearing remaining useful life (RUL) prediction research based on deep learning mostly emphasizes model performance and effective feature vectors, overlooking different densities of outlier distributions in vibration signals at varying degradation stages. Moreover, forecasting models focus on capturing cross-time dependencies, ignoring the dependencies between different variables. To solve these problems, this paper proposes an unsupervised segmented data cleaning algorithm and a RUL prediction framework adaptable to variable operating conditions. The method consists of four steps: (1) Multi-domain feature extraction and selection establish a feature vector space reflecting degradation trends. (2) Segmented data cleaning divides degradation stages, using different penalty factors for outlier cleaning. (3) Cleaned vibration signals undergo a second round of multidomain feature engineering and degradation-stage division. (4) A two-stage Cross-Transformer model is used for RUL prediction. The method proposed has been validated on the prognostics and health management (PHM) bearing degradation dataset. In the constant condition prediction task, the root mean square error (RMSE) and mean absolute error (MAE) were improved to 1.88 and 5.78, respectively. In the variable condition prediction task, the proposed method outperformed existing methods, with an improvement of 59.10 % in RMSE, demonstrating strong generalization performance and practical application value.

A hybrid prognosis scheme for rolling bearings based on a novel health indicator and nonlinear Wiener process

This paper proposes a novel hybrid method aiming at the fault prognosis of bearings. A nonlinear health indicator (HI) is first constructed using Complete Ensemble Empirical Mode Decomposition with Adaptive Noise and Kernel Principal Component Analysis to reflect the health state of a bearing accurately and convincingly. Subsequently, multi-domain features are extracted from vibration signals and the Dual-Channel Transformer Network with the Convolutional Block Attention Module is applied for constructing HIs of the rest bearings. Moreover, the 3σ criterion is employed to establish the condition monitoring interval of health state and detect the First Prediction Time, with which degradation modeling and probabilistic Remaining Useful Life (RUL) prediction are conducted with the assistance of nonlinear Wiener process with random effects. The superior performance of the proposed hybrid prognostic method confirms that the method contributes to the accurate RUL prediction and uncertainty quantification.

Rolling bearing fault diagnosis based on multi-domain features and whale optimized support vector machine

Rolling bearing is an important rotating support component in mechanical equipment. It is very prone to wear, defects, and other faults, which directly affect the reliable operation of mechanical equipment. Its running condition monitoring and fault diagnosis have always been a matter of concern to engineers and researchers. A rolling bearing fault diagnosis technique based on multi-domain feature and whale optimization algorithm-support vector machine (MDF-WOA-SVM) is proposed. Firstly, recursive analysis is performed on vibration signal and the recursive features are employed as nonlinear recursive feature vector including recursive rate (RR), deterministic rate (DET), recursive entropy (RE), and diagonal average length (DAL). Then, a comprehensive multi-domain feature vector is constructed by combining three time-domain features including root mean square, variance, and peak to peak. Finally, whale optimization algorithm (WOA) is introduced to optimize the penalty factor C and kernel function parameter g to construct the optimal WOA-SVM model. The rolling bearing datasets of Jiangnan University is employed for instance analysis, and the results show that the 10-CV accuracy of the technique proposed is good with an accuracy of 99%. Compared with recursive features or time-domain features, multi-domain features are more accurate and comprehensive in describing characters of the signal. Some popular supervised learning models are also introduced for comparison including K-nearest neighbor (KNN) and decision tree (DT), and the result shows that the proposed method has a higher accuracy and certain advantages.

Bearing Fault Diagnosis Method Based on Multi-Domain Feature Selection and the Fuzzy Broad Learning System

In recent years, the Broad Learning System (BLS) has been acknowledged for its potential to revolutionize traditional artificial intelligence methods due to its short training time, strong interpretability, and simple structure. In the evolution of BLS, Prof. C. L. Philip Chen’s team introduced the Fuzzy Broad Learning System (FBLS) by replacing the feature nodes of BLS with fuzzy subsystems, thereby further reducing the training time. However, the traditional FBLS, with its straightforward structure, falls short in achieving higher fault diagnosis accuracy when handling raw vibration signals. This paper presents a bearing fault diagnosis approach employing multi-domain feature selection and the fuzzy broad learning system (MS-FBLS), aiming to enhance the diagnostic accuracy of FBLS through multi-domain feature selection. Primarily, a set of 49 features spanning time domain, frequency domain, time-frequency domain, and entropy values is extracted from the original vibrational signals. This combination builds a 49-dimensional multidomain feature set that exploits the information behind the input data as much as possible, thus compensating for the lack of feature extraction capability in FBLS. Afterward, the Random Forest algorithm assesses the significance of all features, leading to a reordering of the multidomain feature set based on their respective importance levels. Ultimately, the reorganized multidomain feature set is then fed into the FBLS, enabling the identification of various failure states within the bearing. The experimental validation conducted on the rolling bearing fault simulation test bed showcased that, in comparison to the traditional FBLS, the MS-FBLS method not only elevates diagnostic accuracy by 23.46%, but also substantially enhances diagnostic speed. These results serve as comprehensive evidence affirming the effectiveness of the method.

Hidden Markov Models based intelligent health assessment and fault diagnosis of rolling element bearings.

Hidden Markov Models (HMMs) have become an immensely popular tool for health assessment and fault diagnosis of rolling element bearings. The advantages of an HMM include its simplicity, robustness, and interpretability, while the generalization capability of the model still needs to be enhanced. The Dempster-Shafer theory of evidence can be used to conduct a comprehensive evaluation, and Stacking provides a novel training strategy. Therefore, the HMM-based fusion method and ensemble learning method are proposed to increase the credibility of quantitative analysis and optimize classifiers respectively. Firstly, vibration signals captured from bearings are decomposed into intrinsic mode functions (IMFs) using ensemble empirical mode decomposition (EEMD), and then the Hilbert envelope spectra of main components are obtained; Secondly, multi-domain features are extracted as model input from preprocessed signals; Finally, HMM-based intelligent health assessment framework and fault diagnosis framework are established. In this work, the life cycle health assessment modeling is performed using a few training samples, the bearing degradation state is quantitatively evaluated, normal and abnormal samples are effectively distinguished, and the accuracy of fault diagnosis is significantly improved.

Multimodal and Multidomain Feature Fusion for Emotion Classification Based on Electrocardiogram and Galvanic Skin Response Signals

Emotion classification using physiological signals is a promising approach that is likely to become the most prevalent method. Bio-signals such as those derived from Electrocardiograms (ECGs) and the Galvanic Skin Response (GSR) are more reliable than facial and voice recognition signals because they are not influenced by the participant’s subjective perception. However, the precision of emotion classification with ECG and GSR signals is not satisfactory, and new methods need to be developed to improve it. In addition, the fusion of the time and frequency features of ECG and GSR signals should be explored to increase classification accuracy. Therefore, we propose a novel technique for emotion classification that exploits the early fusion of ECG and GSR features extracted from data in the AMIGOS database. To validate the performance of the model, we used various machine learning classifiers, such as Support Vector Machine (SVM), Decision Tree, Random Forest (RF), and K-Nearest Neighbor (KNN) classifiers. The KNN classifier gives the highest accuracy for Valence and Arousal, with 69% and 70% for ECG and 96% and 94% for GSR, respectively. The mutual information technique of feature selection and KNN for classification outperformed the performance of other classifiers. Interestingly, the classification accuracy for the GSR was higher than for the ECG, indicating that the GSR is the preferred modality for emotion detection. Moreover, the fusion of features significantly enhances the accuracy of classification in comparison to the ECG. Overall, our findings demonstrate that the proposed model based on the multiple modalities is suitable for classifying emotions.

Improving cross-subject classification performance of motor imagery signals: a data augmentation-focused deep learning framework

Motor imagery brain-computer interfaces (MI-BCIs) have gained a lot of attention in recent years thanks to their potential to enhance rehabilitation and control of prosthetic devices for individuals with motor disabilities. However, accurate classification of motor imagery signals remains a challenging task due to the high inter-subject variability and non-stationarity in the electroencephalogram (EEG) data. In the context of MI-BCIs, with limited data availability, the acquisition of EEG data can be difficult. In this study, several data augmentation techniques have been compared with the proposed data augmentation technique adaptive cross-subject segment replacement (ACSSR). This technique, in conjunction with the proposed deep learning framework, allows for a combination of similar subject pairs to take advantage of one another and boost the classification performance of MI-BCIs. The proposed framework features a multi-domain feature extractor based on common spatial patterns with a sliding window and a parallel two-branch convolutional neural network. The performance of the proposed methodology has been evaluated on the multi-class BCI Competition IV Dataset 2a through repeated 10-fold cross-validation. Experimental results indicated that the implementation of the ACSSR method (80.47%) in the proposed framework has led to a considerable improvement in the classification performance compared to the classification without data augmentation (77.63%), and other fundamental data augmentation techniques used in the literature. The study contributes to the advancements for the development of effective MI-BCIs by showcasing the ability of the ACSSR method to address the challenges in motor imagery signal classification tasks.

Intelligent real-time perception method for rock strength based on vibration and power fusion characteristics

To improve the sensing accuracy of rock strength parameters, a method based on the fusion of vibration response and electrical response is proposed. Firstly, multi-layer noise reduction based on local mean decomposition is carried out for vibration response, and the product function containing exceeds 85% of the original information is selected by the multi-index comprehensive decision method, and the wavelet threshold denoising is used as the pre-processing unit of singular value decomposition. Next, the multi-domain feature extraction and KPCA are carried out for vibration signal after noise reduction to construct fusion feature vectors. Also, the statistical characteristics of the electrical parameters are extracted and fused with the fusion features. Finally, multi-source information is input into the least squares support vector machine model optimized by the improved whale algorithm to perceive the rock strength parameters. The experimental results show that the sensing accuracy of the proposed method is the highest (96.875%) compared with the single information while drilling and the traditional prediction method, which verifies the superiority of the proposed method.

A cross-domain state monitoring method for high-speed train brake pads based on data generation under small sample conditions

The proper functioning of the high-speed train brake system is of utmost importance to ensure the train comes to a halt at the intended distance. Among the key components, brake pads are susceptible to abnormal wear over prolonged usage, posing a safety risk to train operations. However, limited real-world data on brake pad damage poses challenges for effective monitoring. This paper proposes an effective transfer learning model that utilizes a small amount of data at different speeds, which can solve the small sample data problem on brake pad damage. Initially, a deep convolutional generative adversarial network (DCGAN) is employed to simulate and expand a limited dataset of vibration signals. The generated signals accurately preserve both the high-frequency and low-frequency characteristics observed in the actual signals. Subsequently, a domain-adversarial neural network (DANN) is utilized to map features from the source and target domains onto a shared feature space, enabling multi-domain feature extraction and adaptation. Finally, an intelligent monitoring network is employed to identify the health status of unlabeled brake pads under fluctuating speeds. Experimental results demonstrate the proposed approach outperforms other commonly used algorithms, providing evidence of the feasibility to monitor the small sample conditions of high-speed train brake pads.

A life prediction method based on MDFF and DITCN-ABiGRU mixed network model

A single network model exhibits limitations in the life prediction of rotating machinery for the various fault types and uncertain fault occurrence. Therefore, a network prediction model combining multi-domain feature fusion (MDFF) and distributed TCN-Attention-BiGRU (DITCN-ABiGRU) is proposed to enable a more accurate life prediction of rotating machinery. Firstly, the features of vibration signals collected from multiple sensors are extracted in the time, frequency, and time-frequency domains. Subsequently, dimensionality reduction optimization is conducted on these multi-domain features to eliminate useless information features. The temporal convolutional network (TCN) model is constructed to capture the critical information reflecting the fault characteristics of rotating machinery through the attention mechanism, and the dependencies of the whole training process are captured by the BiGRU network. Finally, precise prediction of the lifespan of rotating machinery is achieved by constructing a health indicator curve (HI). The proposed methods are verified through the life prediction of rolling bearings from the IEEE PHM Challenge 2012 dataset and ball screw pairs from a designed experiment. The experimental results show that the proposed MDFF and DITCN-ABiGRU model achieves a better score and lower error than the convolutional neural network (CNN) and GRU models.

Simulation workflow for fault detection and localization in sandwich panels

Sandwich panels in civil engineering have the advantage of a high flexural strength and thermal insulation while providing a very low density. They are made of two steel sheets and a core of polyurethane or polyisocyanurate foam. Due to the manufacturing process, the panels occasionally have defects, that are not visible from the outside. These may cause visible damages after installation in building facades. This paper presents a workflow for the detection and localization of the defects exploiting their influence on the response to a dynamic excitation. It uses an experimentally validated finite element model, feature engineering, and a neural network. The workflow initiates with the development and validation of a mechanical finite element model using experimental data. The model serves as the foundation for a simulation campaign, examining both defect-free and models with defects. The simulation process incorporates variations in material parameters based on experimentally obtained standard deviations, ensuring a robust representation of real-world uncertainties. The resultant simulation dataset is subjected to a feature engineering process encompassing time and frequency domain features. This multi-domain feature extraction enhances the dataset’s informativeness. The feature dataset is employed to train a neural network for two primary use cases: Firstly, to differentiate between faulty and fault-free models, providing an accurate fault detection mechanism. And secondly, to localize faults within the model. The effectiveness of this approach is demonstrated using various testing datasets. The proposed methodology represents a combination of a synthetically created database from a validated finite element model, multi-domain feature engineering, and neural network capabilities. It offers a methodology for fault detection and localization in sandwich panels. Using a dataset of several hundred samples, a detection rate of 94.8 % and a localization rate of 81.3 % are achieved in this work. In practical use, this approach can lead to significant reduction of customer complaints, and savings in replacement costs and hence carbon footprint.

Vibration-Based Fault Diagnosis for Railway Point Machines Using Multi-Domain Features, Ensemble Feature Selection and SVM

Vibration-Based Fault Diagnosis for Railway Point Machines Using Multi-Domain Features, Ensemble Feature Selection and SVM

MXRFCS : Development of an enhanced multidomain X-ray feature representation model for the detection and classification of COVID severity levels

Global healthcare has been under stress due to the COVID-19 pandemic, necessitating effective methods to determine COVID-19 patient severity and distribute resources accordingly. Current COVID-19 X-ray models are either too complicated or too ineffective to employ in real time. This paper introduces a novel method for assessing COVID-19 severity using an enhanced multimodal X-ray model. A strong patient representation is produced by combining demographics, clinical information, and X-ray results. Multidomain features, including frequency, Gabor, Wavelet, and entropy components, are produced from this data. Using this model, a customized neural network is trained to predict COVID-19 severity levels. A dataset of X-ray pictures and clinical information from COVID-19 patients were used to evaluate the model. The suggested model achieves 98.5% accuracy on several datasets, outperforming existing approaches in the identification of COVID-19 severity levels, according to the results. Performance shows promise in terms of accuracy, memory, and latency, supporting early and efficient management of severe COVID-19 cases and thwarting the pandemic without clinical usage.

An Ensemble Voting Approach With Innovative Multi-Domain Feature Fusion for Neonatal Sleep Stratification

An Ensemble Voting Approach With Innovative Multi-Domain Feature Fusion for Neonatal Sleep Stratification

Fortifying Centers and Edges: Multidomain Feature Learning Meets Hyperspectral Image Classification

Fortifying Centers and Edges: Multidomain Feature Learning Meets Hyperspectral Image Classification

Deep Factor Learning for Accurate Brain Neuroimaging Data Analysis on Discrimination for Structural MRI and Functional MRI.

Analysis of neuroimaging data (e.g., Magnetic Resonance Imaging, structural and functional MRI) plays an important role in monitoring brain dynamics and probing brain structures. Neuroimaging data are multi-featured and non-linear by nature, and it is a natural way to organise these data as tensors prior to performing automated analyses such as discrimination of neurological disorders like Parkinson's Disease (PD) and Attention Deficit and Hyperactivity Disorder (ADHD). However, the existing approaches are often subject to performance bottlenecks (e.g., conventional feature extraction and deep learning based feature construction), as these can lose the structural information that correlates multiple data dimensions or/and demands excessive empirical and application-specific settings. This study proposes a Deep Factor Learning model on a Hilbert Basis tensor (namely, HB-DFL) to automatically derive latent low-dimensional and concise factors of tensors. This is achieved through the application of multiple Convolutional Neural Networks (CNNs) in a non-linear manner along all possible dimensions with no assumed a priori knowledge. HB-DFL leverages the Hilbert basis tensor to enhance the stability of the solution by regularizing the core tensor to allow any component in a certain domain to interact with any component in the other dimensions. The final multi-domain features are handled through another multi-branch CNN to achieve reliable classification, exemplified here using MRI discrimination as a typical case. A case study of MRI discrimination has been performed on public MRI datasets for discrimination of PD and ADHD. Results indicate that 1) HB-DFL outperforms the counterparts in terms of FIT, mSIR and stability (mSC and umSC) of factor learning; 2) HB-DFL identifies PD and ADHD with an accuracy significantly higher than state-of-the-art methods do. Overall, HB-DFL has significant potentials for neuroimaging data analysis applications with its stability of automatic construction of structural features.

A Computer-Aided Screening Solution for the Identification of Diabetic Neuropathy from Standing Balance by Leveraging Multi-Domain Features.

The early diagnosis of diabetic neuropathy (DN) is fundamental in order to enact timely therapeutic strategies for limiting disease progression. In this work, we explored the suitability of standing balance task for identifying the presence of DN. Further, we proposed two diagnosis pathways in order to succeed in distinguishing between different stages of the disease. We considered a cohort of non-neuropathic (NN), asymptomatic neuropathic (AN), and symptomatic neuropathic (SN) diabetic patients. From the center of pressure (COP), a series of features belonging to different description domains were extracted. In order to exploit the whole information retrievable from COP, a majority voting ensemble was applied to the output of classifiers trained separately on different COP components. The ensemble of kNN classifiers provided over 86% accuracy for the first diagnosis pathway, made by a 3-class classification task for distinguishing between NN, AN, and SN patients. The second pathway offered higher performances, with over 97% accuracy in identifying patients with symptomatic and asymptomatic neuropathy. Notably, in the last case, no asymptomatic patient went undetected. This work showed that properly leveraging all the information that can be mined from COP trajectory recorded during standing balance is effective for achieving reliable DN identification. This work is a step toward a clinical tool for neuropathy diagnosis, also in the early stages of the disease.

MIDGNWD : Design of an efficient multimodal iterative deep graph network wearable interface for detecting drowsy drivers

Drowsy driving is a significant contributor to road traffic accidents, necessitating the development of robust and efficient detection systems. Existing approaches for detecting drowsy drivers often rely on single modalities such as image-based facial analysis or vehiclebased metrics, which may lack precision and be susceptible to environmental variations. Furthermore, the existing models might be computationally expensive and result in delayed responses. To address these limitations, this paper proposes a novel Multimodal Iterative Deep Graph Network Wearable Interface that leverages a rich set of data including heart rate, respiration, accelerometer movement, location (speed), traffic, and weather data. These data samples are processed through a fusion of different Recurrent Neural Network processes. The Bidirectional Long Short-Term Memory (BiLSTM) which is used to generate augmented features, is fused with Bidirectional Gated Recurrent Unit (BiGRU) which assists in estimating multidomain feature sets. These features are then used to train an efficient Deep Graph Recurrent Network (DGRN), which facilitates the real-time identification of drowsy drivers. The proposed model significantly enhances the precision of drowsy driver detection by 8.5%, accuracy by 9.5%, recall by 8.3%, and Area Under the Curve (AUC) by 4.9%, while also improving specificity by 5.5% and reducing delay by 10.4%. These improvements collectively contribute to a substantial enhancement in road safety, potentially saving lives by preventing accidents due to drowsy driving. The proposed system, with its real-time processing capability and high accuracy, stands as a significant improvement for identifying drowsy drivers, paving the way for safer and smarter transportation systems.

Online unsupervised monitoring for hob wear based on multi-domain vibration features extraction and improved Q-statistic control chart

Current mainstream wear diagnosis approaches rely on the entire lifecycle wear-labeled datasets, which is costly, delayed, and low-universality. To achieve the monitoring goal of online, real-time, and strong generalization for hob wear and get rid of the dependence on the wear datasets, an online unsupervised monitoring method is explored based on the multi-domain features extraction and improved Q-statistic control chart, which is progressive. First, the monitoring feature matrix of each hob shifting period is transformed into the principal component subspace, the wear subspace, and the interference subspace based on the principal component analysis (PCA). Then, features in the wear subspace of the previous shifting period are used to get the control limit and those of the next shifting period are used to calculate the Q-statistic. The hob wear status is determined by comparing the control limit and the Q-statistic. The gear hobbing experiment verifies the feasibility of the proposed method.

LIMFA: label-irrelevant multi-domain feature alignment-based fake news detection for unseen domain

LIMFA: label-irrelevant multi-domain feature alignment-based fake news detection for unseen domain