Insufficient Feature Extraction Research Articles

Detection of Small Targets in Photovoltaic Cell Defect Polarization Imaging Based on Improved YOLOv7

A photovoltaic cell defect polarization imaging small target detection method based on improved YOLOv7 is proposed to address the problem of low detection accuracy caused by insufficient feature extraction ability in the process of small target defect detection. Firstly, polarization imaging technology is introduced, using polarization degree images as inputs to enhance the edge contour information of YOLOv7 for detecting small targets; then, the COT self-attention mechanism is added to reconstruct the SPPCSPC module to improve YOLOv7’s ability to capture and fuse small target features in complex backgrounds; next, the normalized Wasserstein distance (NWD) is used to replace the traditional loss function based on intersection over union (IoU) metric, reducing the boundary offset between the prior box and the closest real target box in the prediction process of the object detection model and reducing the sensitivity of the YOLOv7 network to small object position deviations; finally, by constructing a shortwave infrared polarization imaging system to obtain polarization images of photovoltaic cells and detect small targets with scratch defects in photovoltaic cells, the applicability and effectiveness of the proposed method are verified. The results show that the proposed method has good recognition ability for small target defects in photovoltaic cells. By applying the constructed dataset, the detection accuracy reaches 98.08%, the recall rate reaches 95.06% and the mAP reaches 98.83%.

An NLOS Ranging Error Mitigation Method for 5G Positioning in Indoor Environments

Positioning based on wireless signals such as mobile communication networks has become an important means to provide high-precision location services in environments where satellite signals are blocked. In complex environments such as indoors and underground, wireless signal propagation is obstructed and non-line-of-sight (NLOS) phenomena appear due to serious occlusion and reflection. The time delay caused by NLOS effects has little impact on communication system but can significantly increase positioning errors in positioning systems. Therefore, the effective suppression of NLOS errors is crucial to improving 5G positioning accuracy. To address the insufficient feature extraction of existing NLOS error suppression methods, the neglect of residual NLOS measurement errors, and poor stability of position estimation results, this paper innovatively proposes an NLOS mitigation and location estimation method for 5G positioning terminals. Simulation and experimental test results demonstrate that the proposed method outperforms the comparative methods both theoretically and practically, achieving an average positioning accuracy of 1.85 m in complex indoor NLOS environments. The method proposed in this paper provides a new strategy for NLOS error suppression in indoor 5G positioning, which can significantly contribute to high-precision location services based on commercial 5G networks.

The Remaining Life Prediction of Rails Based on Convolutional Bi-Directional Long and Short-Term Memory Neural Network with Residual Self-Attention Mechanism

In the railway industry, the rail is the basic load-bearing structure of railway tracks. The prediction of the remaining useful life (RUL) for rails is important to avoid unexpected system failures and reduce the cost of maintaining the system. However, the existing detection of rail flaws is difficult, the rail deterioration mechanisms are diverse, and the traditional data-driven methods have insufficient feature extraction. This causes low prediction accuracy. With objectives set in relation to the problems outlined above, a rail RUL prediction approach based on a convolutional bidirectional long- and short-term memory neural network with a residual self-attention (CNNBiLSTM-RSA) mechanism is designed. Firstly, the pre-processed vibration data are taken as the input for the convolutional bi-directional long- and short-term memory neural network (CNNBiLSTM) to extract the forward and backward dependencies and features of the rail data. Secondly, the RSA mechanism is introduced in order to obtain the contributions of the features at different moments during the degradation process of the rail. Finally, an end-to-end RUL prediction implementation based on the convolutional bi-directional long- and short-term memory neural network with the residual self-attention mechanism is established. The experiments were carried out using the full life-cycle data of rails collected at the railway site. The results show that the method achieves a higher accuracy in the RUL prediction of rails.

An epilepsy detection method based on multi-dimensional feature extraction and dual-branch hypergraph convolutional network.

Epilepsy is a disease caused by abnormal neural discharge, which severely harms the health of patients. Its pathogenesis is complex and variable with various forms of seizures, leading to significant differences in epilepsy manifestations among different patients. The changes of brain network are strongly correlated with related pathologies. Therefore, it is crucial to effectively and deeply explore the intrinsic features of epilepsy signals to reveal the rules of epilepsy occurrence and achieve accurate detection. Existing methods have faced the following issues: 1) single approach for feature extraction, resulting in insufficient classification information due to the lack of rich dimensions in captured features; 2) inability to deeply analyze the essential commonality of epilepsy signal after feature extraction, making the model susceptible to data distribution and noise interference. Thus, we proposed a high-precision and robust model for epileptic seizure detection, which, for the first time, applies hypergraph convolution to the field of epilepsy detection. Through a hypergraph network structure constructed based on relationships between channels in electroencephalogram (EEG) signals, the model explores higher-order characteristics of epilepsy EEG data. Specifically, we use the Conv-LSTM module and Power spectral density (PSD), a two-branch parallel method, to extract channel features from space-time and frequency domains to solve the problem of insufficient feature extraction, and can adequately describe the data structure and distribution from multiple perspectives through double-branch parallel feature extraction. In addition, we construct a hypergraph on the captured features to explore the intrinsic features in the high-dimensional space in an attempt to reveal the essential commonality of epileptic signal feature extraction. Finally, using the ensemble learning concept, we accomplished epilepsy detection on the dual-branch hypergraph convolution. The model underwent leave-one-out cross-validation on the TUH dataset, achieving an average accuracy of 96.9%, F1 score of 97.3%, Pre of 98.2% and Re of 96.7%. In addition, the model was generalized performance tested on CHB-MIT scalp EEG dataset with leave-one-out cross-validation, and the average ACC, F1 score, Pre and Re were 94.4%, 95.1%, 95.8%, and 93.9% respectively. Experimental results indicate that the model outperforms related literature, providing valuable reference for the clinical application of epilepsy detection.

A Physics-Guided MFL Deformed Defect Recovery Method

Magnetic flux leakage (MFL) testing and analysis is an effective non-destructive testing (NDT) method of pipeline health. The health status of pipelines is evaluated by analyzing MFL signals, especially the defect analysis. However, complex operating conditions and equipment deviations may cause deformation on the defects. Availability and integrity of the MFL defects are the keys to accurate signal processing. Due to the limited interpretability of abstract networks and insufficient feature extraction, it is hard to accurately recover the deformed defects. Considering the problems above, an MFL deformed defect recovery method with the guidance of physical features is proposed. The proposed method integrates a deep feature extraction model into a sparse autoencoder, whose parameters are guided by the combination of MSE loss and physics loss. First, the deep feature extraction model fully extracts the abstract features, which contains more information on deformed defects. Second, the sparse penalty factor in the sparse autoencoder reduces the feature redundancy of deformed defects. Third, the physical features are extracted to guide the MFL deformed defect recovery relying on the MFL mechanism for the first time, which enhances the robustness and accuracy of the network. Finally, several comparison experiments have been conducted on measured and simulated MFL defects. The results show that the proposed method is effective in deformed defect recovery. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —The motivation of this paper is a practical problem of MFL deformed defect recovery. The deformation on MFL defects affects defect inversion and evaluation seriously, which causes great potential harm to pipeline safety transmission. In this paper, compared with traditional neural network-based methods, physical features based on MFL mechanism are extracted to guide the parameter update. In addition, a pre-trained model replaces regular convolutional layers to extract features sufficiently, while a sparse factor is applied to reduce redundant features. The proposed method not only utilizes deep features from deep networks, but also increases the guidance of physical features, so that the algorithm is more robust and accurate. The experiment results show that our proposed method is more effective than the comparative methods on MFL simulated and measured defects. In a word, the proposed method has strong theoretical research and practical value.

An infrared and visible image fusion network based on multi‐scale feature cascades and non‐local attention

AbstractIn recent years, research on infrared and visible image fusion has mainly focused on deep learning‐based approaches, particularly deep neural networks with auto‐encoder architectures. However, these approaches suffer from problems such as insufficient feature extraction capability and inefficient fusion strategies. Therefore, this paper introduces a novel image fusion network to address the limitations of infrared and visible image fusion networks with auto‐encoder architectures. In the designed network, the encoder employs a multi‐branch cascade structure, and these convolution branches with different kernel sizes provide the encoder with an adaptive receptive field to extract multi‐scale features. In addition, the fusion layer incorporates a non‐local attention module that is inspired by the self‐attention mechanism. With its global receptive field, this module is used to build a non‐local attention fusion network, which works together with the ‐norm spatial fusion strategy to extract, split, filter, and fuse global and local features. Comparative experiments on the TNO and MSRS datasets demonstrate that the proposed method outperforms other state‐of‐the‐art fusion approaches.

A Bi-GRU-DSA-based social network rumor detection approach

Abstract In the rumor detection based on crowd intelligence, the crowd behavior is constructed as a graph model or probability mode. The detection of rumors is achieved through the collaborative utilization of data and knowledge. Aiming at the problems of insufficient feature extraction ability and data redundancy of current rumor detection methods based on deep learning model, a social network rumor detection method based on bidirectional gated recurrent unit (Bi-GRU) and double self-attention (DSA) mechanism is suggested. First, a combination of application program interface and third-party crawler approach is used to obtain microblogging data from publicly available fake microblogging information pages, including both rumor and non-rumor information. Second, Bi-GRU is used to capture the tendency of medium- and long-term dependence of data and is flexible enough to deal with variable length input. Finally, the DSA mechanism is introduced to help reduce the redundant information in the dataset, thereby enhancing the model’s efficacy. The results of the experiments indicate that the proposed method outperforms existing advanced methods by at least 0.114, 0.108, 0.064, and 0.085 in terms of accuracy, precision, recall, and F1-scores, respectively. Therefore, the proposed method can significantly enhance the ability of social network rumor detection.

ADF-Net: An Attention-Guided Dual-Branch Fusion Network for Building Change Detection near the Shanghai Metro Line Using Sequences of TerraSAR-X Images

Building change detection (BCD) plays a vital role in city planning and development, ensuring the timely detection of urban changes near metro lines. Synthetic Aperture Radar (SAR) has the advantage of providing continuous image time series with all-weather and all-time capabilities for earth observation compared with optical remote sensors. Deep learning algorithms have extensively been applied for BCD to realize the automatic detection of building changes. However, existing deep learning-based BCD methods with SAR images suffer limited accuracy due to the speckle noise effect and insufficient feature extraction. In this paper, an attention-guided dual-branch fusion network (ADF-Net) is proposed for urban BCD to address this limitation. Specifically, high-resolution SAR images collected by TerraSAR-X have been utilized to detect building changes near metro line 8 in Shanghai with the ADF-Net model. In particular, a dual-branch structure is employed in ADF-Net to extract heterogeneous features from radiometrically calibrated TerraSAR-X images and log ratio images (i.e., difference images (DIs) in dB scale). In addition, the attention-guided cross-layer addition (ACLA) blocks are used to precisely locate the features of changed areas with the transformer-based attention mechanism, and the global attention mechanism with the residual unit (GAM-RU) blocks is introduced to enhance the representation learning capabilities and solve the problems of gradient fading. The effectiveness of ADF-Net is verified using evaluation metrics. The results demonstrate that ADF-Net generates better building change maps than other methods, including U-Net, FC-EF, SNUNet-CD, A2Net, DMINet, USFFCNet, EATDer, and DRPNet. As a result, some building area changes near metro line 8 in Shanghai have been accurately detected by ADF-Net. Furthermore, the prediction results are consistent with the changes derived from high-resolution optical remote sensing images.

LVIF-Net: Learning synchronous visible and infrared image fusion and enhancement under low-light conditions

In recent years, the fusion of infrared and visible images has gained significant prominence in the effort to seamlessly integrate salient objects and intricate textures within the fused imagery. While numerous fusion techniques have demonstrated commendable performance, the image quality is notably compromised in low-light environments. This predicament can be attributed to insufficient feature extraction, the inherent low-illumination characteristics of the source images, and the suppression of dark backgrounds. In this study, we introduce a novel approach for simultaneous image fusion and enhancement, aiming to achieve robust fusion performance even in low-light conditions. Our proposed method involves the development of an image fusion network, known as LVIF-Net, which is designed to facilitate multi-layer feature interactions for the enhancement of complementary low-light visible and infrared feature extraction. To solve the problem of low illumination in fused images, we further introduce an Image Decomposition Network (IDN) to guide the LVIF-Net to correct the illumination component of the fused image to obtain enhanced fused images. In addition, for coping with influence of dark background, we design a local region content loss to enhance infrared information in different intensity regions between source images. Extensive experiments on the low-light images on LLVIP and MFNet datasets have shown that the proposed method achieves significant advantages under low-light conditions.

A series fault arc detection method based on denoising autoencoder and deep residual network

Given the problem that the existing series arc fault identification methods use existing features such as the time-frequency domain of the current signal as the basis for identification, resulting in relatively limited arc detection solutions, and that the methods of directly extracting current signal features using deep learning algorithms have insufficient feature extraction, a new series arc fault detection method based on denoising autoencoder (DAE) and deep residual network (ResNet) is proposed. First, a large number of training samples are obtained through sliding window and data normalization methods, and then high-dimensional abstract feature data are obtained from the fault and normal samples collected in the experiment through denoising autoencoders, converted into grayscale images, and processed in pseudo-color. The single-channel grayscale images are mapped into three-channel color values, and finally, the three-channel values are input into the constructed deep residual network for deep learning training. In the 152 super high-level ResNet, the arc fault recognition rate can reach 99.7%. For loads that have not participated in ResNet network training, the recognition rate can also reach 97.6%.

Multimodal fusion of deep neural networks for transmission line flashover classification

ABSTRACT The power system plays a vital role in modern society. However, the occurrence of transmission line flashover faults seriously threatens the safety and stability of the power system. In this paper, a deep neural network flashover classification model based on multimodal attention aggregation is proposed. By using the model, the problems of insufficient feature extraction capability of the unimodal flashover data model and easy loss of key feature information in the process of audiovisual multimodal flashover data alignment are solved. Experiments on the arc- flashover fault dataset show that the flashover fault detection model proposed in this paper can be used stably and effectively for flashover fault detection.

Advanced hybrid CNN-Bi-LSTM model augmented with GA and FFO for enhanced cyclone intensity forecasting

Predicting cyclone intensity is an important aspect of weather forecasting since it influences disaster preparation and response. This framework addresses the pressing need for precise cyclone intensity prediction by presenting a unique predictive model based on a hybrid CNN and Bi-LSTM architecture optimized using a Genetic Algorithm (GA) enhanced Fruit Fly Optimizer (FFO). Existing methods have primarily relied on traditional machine learning models and meteorological data, demonstrating limitations in capturing the complex spatial-temporal patterns inherent in cyclone evolution. These drawbacks include insufficient feature extraction abilities, underutilization of convolutional neural networks (CNN), and poor model tuning. This unique method incorporates a hybrid CNN and Bi-LSTM architecture that is tuned by a Genetic Algorithm (GA) enhanced Fruit Fly Optimizer (FFO), resulting in higher cyclone intensity prediction accuracy. The experimental results are implemented in Python software, and they reveal that this method outperforms current models by an average of 21% when compared to existing methods such as VGG-16 achieved an accuracy of 78% and Ty 5-CNN (95.23%). The suggested CNN-Bi-LSTM model predicts cyclone strength with an excellent accuracy of 99.4%. This unique approach offers a possible avenue for increasing cyclone intensity prediction, hence improving disaster preparedness and risk mitigation efforts in sensitive locations.

MMF-CNN: a multimodal fusion CNN network for winter wheat extraction incorporating active and passive time series data

ABSTRACT Timely and accurate acquisition of winter wheat planting areas is crucial for food security. In this study, Sentinel-1 and Sentinel-2 time-series data are integrated at the feature level to enhance the accuracy of winter wheat extraction. However, existing feature-level fusion models suffer from insufficient feature extraction and lack of feature completeness, thereby overlooking the complementarity and correlation between these two modalities. A Multimodal Fusion Convolutional Neural Network (MMF-CNN) model is proposed to address the issues above. Firstly, the images of Sentinel-1 and Sentinel-2 are processed to obtain the NDVI and backscatter characteristics of the winter wheat time series life cycle. A single feature and a combination of two features are then imported into each end of the model. The model adds a feature fusion module, which can fully extract the feature information. At the same time, the original features are retained in the process of multiscale feature fusion, which avoids the loss of the original information. Finally, Support Vector Machine (SVM), Long Short-Term Memory (LSTM), and Visual Geometry Group (VGG) are selected as the comparison models for comparative experiments, and the classification results of remote sensing images are obtained. These results demonstrate that the joint utilization of SAR and optical data yields the highest classification accuracy, with an F1 score of 97.42% for winter wheat. The overall accuracy (OA) of the proposed MMF-CNN method in this study is 96.87%, representing a 1.86% improvement compared to the Conv1D-CNN model. This improvement signifies adaptive feature learning at different hierarchical levels. Comparing the accuracy with other mainstream methods, the OA improves by 1.75%–4.37%, reveals finer ground details, and demonstrates faster performance. This study can provide methodological references for crop extraction studies based on multi-source data and time series analysis.

Robust Chinese Short Text Entity Disambiguation Method Based on Feature Fusion and Contrastive Learning

To address the limitations of existing methods of short-text entity disambiguation, specifically in terms of their insufficient feature extraction and reliance on massive training samples, we propose an entity disambiguation model called COLBERT, which fuses LDA-based topic features and BERT-based semantic features, as well as using contrastive learning, to enhance the disambiguation process. Experiments on a publicly available Chinese short-text entity disambiguation dataset show that the proposed model achieves an F1-score of 84.0%, which outperforms the benchmark method by 0.6%. Moreover, our model achieves an F1-score of 74.5% with a limited number of training samples, which is 2.8% higher than the benchmark method. These results demonstrate that our model achieves better effectiveness and robustness and can reduce the burden of data annotation as well as training costs.

Forecasting tourism demand with search engine data: A hybrid CNN-BiLSTM model based on Boruta feature selection

Using search engine data (SED) to forecast tourist flow is essential for management and security warnings at tourist attractions. Existing prediction models cannot effectively handle noise in the SED and external uncertainties. Thus, insufficient feature extraction may hinder the fitting of tourist flow time series. To improve the prediction accuracy, a forecasting method combining the Boruta algorithm (Boruta), bidirectional long short-term memory (BiLSTM), and a convolutional neural network (CNN) is proposed in this study. The model was tested using a monthly tourist flow dataset of three adjacent tourist attractions (Hongcun Village, Mount Huangshan, and Xidi Village) in Anhui Province, China, from January 2011 to March 2021. Forecasting for Hongcun Village shows that the proposed model performs best in three-step-ahead forecasting with a root mean square error (RMSE) of 2341.77 and a mean absolute percentage error (MAPE) of 2.85 %. A comparative analysis demonstrated that the hybrid CNN-BiLSTM model outperformed benchmark models. Meanwhile, Boruta reduced the RMSE and MAPE of the model by 59.93 % and 54.11 %, respectively, which were superior to those of the baseline methods. Furthermore, a robustness test was applied considering Mount Huangshan and Xidi Village as additional exercises for prediction. The robustness test confirmed that the proposed model has the proper generalization capability. Accordingly, the forecasting framework used in this study is robust and operational. This can facilitate a new approach for tourism demand forecasting with SED and assist operators in making managerial decisions.

Research on Event Target Recognition Based on DRUNet and Multi-scale Attention

Aiming at the problem of noise and insufficient feature extraction in event camera-based target recognition task, we proposes an event target recognition method based on DRUNet and multi-scale attention. Firstly, DRUNet is added as a filter to reduce the event noise during the conversion of the event stream into event tensor; secondly, a multi-scale convolutional layer is used instead of a single convolutional layer to extract feature information at different scales, and a depth-separable convolution is utilized to replace part of the standard convolution in the network structure to reduce the number of network parameters without losing the performance of the network; thirdly, multi-scale features are performed on different channel fusion and connecting the channel attention module to enhance the network’s representation of effective features; then the classifier is redesigned to reduce feature loss and improve recognition accuracy by compressing the semantic information layer-by-layer and step-by-step; finally, the Adam optimizer based on the gradient centered algorithm is used for training to improve the network’s generalization ability and training speed. On the N-Caltech101 and N-Cars datasets, the recognition accuracy of the model is 87.2%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\%$$\\end{document} and 96.3%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\%$$\\end{document}, respectively, which is significantly higher than other algorithms.

TriFNet: A triple-branch feature fusion network for pH determination by surface-enhanced Raman spectroscopy

Due to the acidic tumor microenvironment caused by metabolic changes in tumor cells, the accurate pH detection of extracellular fluid is helpful for doctors in precise tumor resection. The combination of Raman spectroscopy and deep learning provides a solution for pH detection. However, most existing studies use one-dimensional convolutional neural networks (1D-CNNs) for spectral analysis, which limits the performance due to insufficient feature extraction. In this work, we propose a 2D triple-branch feature fusion network (TriFNet) for accurate pH determination using surface-enhanced Raman spectra (SERS). Specifically, we design a triple-branch network structure by converting Raman spectra into three types of images to extensively extract complex patterns in spectra. In addition, an attention fusion module, which leverages the complementarity among features in both space and channel, is designed to obtain the valuable information, achieving further accurate pH determination. On our Raman spectral dataset containing 14,137 samples, we achieved mean absolute error (MAE) of 0.059, standard deviation of the absolute error (SD) of 0.07, root mean squared error (RMSE) of 0.092, and coefficient of determination (R2) of 0.991 on the test set. Compared with other published methods, the four metrics showed an average improvement of 47%, 39%, 43%, and 6%, respectively. In addition, visualization validates the diagnostic capability of our model to correlate with biomolecular signatures. Meanwhile, our model has robustness to different SERS chips. These results prove the potential of our method to develop an effective technology based on Raman spectroscopy for accurate pH determination to guide surgery.

Lightweight Detection Method for X-ray Security Inspection with Occlusion

Identifying the classes and locations of prohibited items is the target of security inspection. However, X-ray security inspection images with insufficient feature extraction, imbalance between easy and hard samples, and occlusion lead to poor detection accuracy. To address the above problems, an object-detection method based on YOLOv8 is proposed. Firstly, an ASFF (adaptive spatial feature fusion) and a weighted feature concatenation algorithm are introduced to fully extract the scale features from input images. In this way, the model can learn further details in training. Secondly, CoordAtt (coordinate attention module), which belongs to the hybrid attention mechanism, is embedded to enhance the learning of features of interest. Then, the slide loss function is introduced to balance the simple samples and the difficult samples. Finally, Soft-NMS (non-maximum suppression) is introduced to resist the conditions containing occlusion. The experimental result shows that mAP (mean average precision) achieves 90.2%, 90.5%, 79.1%, and 91.4% on the Easy, Hard, and Hidden sets of the PIDray and SIXray public test set, respectively. Contrasted with original model, the mAP of our proposed YOLOv8n model increased by 2.7%, 3.1%, 9.3%, and 2.4%, respectively. Furthermore, the parameter count of the modified YOLOv8n model is roughly only 3 million.

Prior Knowledge-Augmented Broad Reinforcement Learning Framework for Fault Diagnosis of Heterogeneous Multiagent Systems

A heterogeneous multiagent system (MAS) can easily experience unpredictable faults due to its complex structure and involvement of different individuals. However, existing approaches have several issues, including complicated network architecture, insufficient feature extraction, and poor generalization ability. This study proposes a novel framework called prior-knowledge-augmented broad reinforcement learning (PK-BRL) to effectively diagnose faults in a heterogeneous MAS. First, we construct a highly realistic visualized heterogeneous MAS and perfom fault injection. Second, we present a novel fault diagnosis framework based on broad reinforcement learning with prior knowledge that effectively integrates offline reinforcement learning and broad learning into the fault diagnosis process. The interaction between heterogeneous multiagents and the constructed environment enables us to learn a superior fault diagnosis strategy. Finally, experiments conducted on software-in-the-loop and hardware-in-the-loop platforms demonstrate that the proposed PK-BRL framework has a state-of-the-art diagnostic accuracy for the heterogeneous MAS, which offers valuable theoretical and practical significance for real-world application.

A double broad learning approach based on variational modal decomposition for Lithium-Ion battery prognostics

Predicting the remaining life of lithium-ion battery equipment is becoming increasingly important as enterprises transition to smart manufacturing. Accurate prediction results can be used to effectively determine the battery's health status and improve operational safety. However, during the decline process, lithium-ion battery capacity regeneration occurs, resulting in significant fluctuations in the degradation data that can easily lead to insufficient prediction accuracies. At the same time, a factor influencing the prediction results is the unification of modal information and insufficient feature extraction of the battery capacity data in the prediction process. Therefore, in this paper, a novel model based on variational modal decomposition and double broad learning (VMD-DBL) is proposed. First, we use VMD to perform adaptive decomposition of the degraded data to form intrinsic mode function (IMF) components and residual components to solve the data noise problem. Second, these two modal data of the feature extraction and modal fusion are inputted into the trained DBL model. Finally, the two modes are connected to the output layer to obtain the predicted result. The NASA dataset is used for experimental validation in this paper, and the results show that our proposed method outperforms other methods in terms of accuracy and feasibility.