Cross-domain simultaneous fault diagnosis of marine machinery with multi-source and multi-scale feature fusion

Multi-label classification for simultaneous fault diagnosis of marine machinery: A comparative study

Simultaneous fault diagnosis of proton exchange membrane fuel cell systems based on an Incremental Multi-label Classification Network

Many heads are better than one: A multiscale neural information feature fusion framework for spatial route selections decoding from multichannel neural recordings of pigeons

Intelligent simultaneous fault diagnosis for solid oxide fuel cell system based on deep learning

LiM-Net: Lightweight multi-level multiscale network with deep residual learning for automatic liver segmentation in CT images

A multi-scale semantic feature fusion method for remote sensing crop classification

Purpose: Segmentation of lung nodules in chest CT images is essential for image-driven lung cancer diagnosis and follow-up treatment planning. Manual segmentation of lung nodules is subjective because the approach depends on the knowledge and experience of the specialist. We proposed a multiscale fully convolutional three-dimensional UNet (MF-3D UNet) model for automatic segmentation of lung nodules in CT images. Approach: The proposed model employs two strategies, fusion of multiscale features with Maxout aggregation and trainable downsampling, to improve the performance of nodule segmentation in 3D CT images. The fusion of multiscale (fine and coarse) features with the Maxout function allows the model to retain the most important features while suppressing the low-contribution features. The trainable downsampling process is used instead of fixed pooling-based downsampling. Results: The performance of the proposed MF-3D UNet model is examined by evaluating the model with CT scans obtained from the Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) dataset. A quantitative and visual comparative analysis of the proposed work with various customized UNet models is also presented. The comparative analysis shows that the proposed model yields reliable segmentation results compared with other methods. The experimental result of 3D MF-UNet shows encouraging results in the segmentation of different types of nodules, including juxta-pleural, solitary pulmonary, and non-solid nodules, with an average Dice similarity coefficient of , and it outperforms other CNN-based segmentation models. Conclusions: The proposed model accurately segments the nodules using multiscale feature aggregation and trainable downsampling approaches. Also, 3D operations enable precise segmentation of complex nodules using inter-slice connections.

Simultaneous fault diagnosis in chemical plants using support Vector Machines

This paper studies the simultaneous fault diagnosis of the main reducer in the automobile transmission system assembly based on vibration signals. A simultaneous fault diagnosis model based on Paired Relevance Vector Machine (Paired-RVM) is proposed for the simultaneous fault of the main reducer, and each binary sub-classifier is trained with single fault samples and then fused by a pairing strategy. With F-measure as a measurement indicator of diagnosis precision, the threshold set DThreshold is used to train a threshold optimization algorithm so as to generate the optimal decision threshold, thus converting the probability output generated by the classification model into the final simultaneous fault mode. A contrast experiment is made between Paired-RVM and some commonly used supervised learning models of SVM, ELM and KELM, and the experimental results show that the performance of Paired-RVM proposed in this paper is superior to that of other models in simultaneous fault diagnosis and single fault diagnosis, verifying the effectiveness of the proposed method.

Lacking of the management of simultaneous fault is one of the limitations of condition monitoring for a gas turbine, which is critical for the safety and decision-making of aircraft operation. To this end, this paper employed a multi-label (ML) learning strategy to address the simultaneous fault issues. Moreover, a feature selection algorithm is proposed, which is based on the viewpoint that different class labels might be distinguished by certain specific characteristics of their own. The proposed algorithm achieves the goal of label-specific feature selection by iteratively optimizing the weight reconstruction matrix, and the learned label-specific features for the corresponding label can be used for multi-label classification. As thus, sensor data for different components of aircraft engines can be determined by the proposed algorithm to deal with the simultaneous fault diagnosis. Finally, comprehensive experiments on the benchmark data sets of multi-label learning validate the advantages and feasibility of the presented approaches, and the effectiveness of their application to simultaneous fault diagnosis of aircraft engines is also proved by extensive experiments.

Objective Biological image detection and classification is a classic and challenging task at present. In order to accurately and automatically identify biological species and ownership relationship, a new classification model and tree structure are proposed to improve the performance of biological detection or classification. Methods Two groups of experiments were set up. Using YOLOv5 as the first layer of the tree structure, YOLOv5 is easy to deploy and can roughly locate the image and remove noise information beyond the target. Then the first group of experiments were trained with RESNET-101, RESNET-200 and DenSenet-201 at different levels of biological tree structure, respectively, and the results were compared with those directly using YOLOv5. In the second group of experiments, the new multi-scale bilinear feature fusion classification model is used to classify images successively, and finally obtain the accurate classification of objects. Result In the first group of experiments, the best result of the customized data set of 80 insect species was 1.09% higher than the mAP value of YOLOv5x. In the second group of experiments, the accuracy of cuB-200-2011(Caltech- UCSDbirds-200-2011) data was 86.4%. The accuracy is 2.3% higher than that of B-CNN classification model, which verifies the effectiveness of the improved method and model in this paper. Conclusion More complementary information can be obtained by multi-scale feature fusion. Bilinear fusion of features at different scales can fully express features at different scales and improve the accuracy of classification tasks. The tree structure effectively removes irrelevant noise information, and at the same time classifies layer by layer, simplifies the classification task, enriches the feature information, and makes the result more accurate

A cross-subject MDD detection approach based on multiscale nonlinear analysis in resting state EEG.

Forecasting stock price trends accurately appears a huge challenge because the environment of stock markets is extremely stochastic and complicated. This challenge persistently motivates us to seek reliable pathways to guide stock trading. While the Long Short-Term Memory (LSTM) network has the dedicated gate structure quite suitable for the prediction based on contextual features, we propose a novel LSTM-based model. Also, we devise a multiscale convolutional feature fusion mechanism for the model to extensively exploit the contextual relationships hidden in consecutive time steps. The significance of our designed scheme is twofold. (1) Benefiting from the gate structure designed for both long- and short-term memories, our model can use the given stock history data more adaptively than traditional models, which greatly guarantees the prediction performance in financial time series (FTS) scenarios and thus profits the prediction of stock trends. (2) The multiscale convolutional feature fusion mechanism can diversify the feature representation and more extensively capture the FTS feature essence than traditional models, which fairly facilitates the generalizability. Empirical studies conducted on three classic stock history data sets, i.e., S&P 500, DJIA, and VIX, demonstrated the effectiveness and stability superiority of the suggested method against a few state-of-the-art models using multiple validity indices. For example, our method achieved the highest average directional accuracy (around 0.71) on the three employed stock data sets.

Fault detection and isolation system is crucial for the safety and reliability of aircraft engine. Traditional techniques of data-driven fault diagnosis for aircraft engine mainly focus on single fault diagnosis problems by means of the single-label learning strategy. However, the simultaneous fault diagnosis problems cannot be ignored in reality. In this research, two data-driven approaches based on multi-label learning and support vector machine are proposed to address the simultaneous fault diagnosis for an aircraft engine. Given that the simultaneous fault data are more difficult to obtain than single fault data, the proposed approaches have the ability to diagnose both single fault and simultaneous fault for aircraft engine when the fault diagnosis system is trained using single fault data only. The experimental results show that the proposed approaches can diagnose the simultaneous fault for an aircraft engine with high accuracy requiring low computation burden and a small number of single fault training data. In addition, the supplementary experiment confirms that the diagnosis accuracy of the proposed methods can be further improved by adding a small amount of the simultaneous fault data into the training dataset.

Effective image tampering localization with multi-scale ConvNeXt feature fusion