Under varying conditions, the stage evolution of tool wear exhibits disparate characteristics, with pronounced differences in wear rate and transition points across stages. This variability renders real-time, high-precision measurement and unified monitoring of tool wear exceptionally challenging. To address this issue, a data-distribution-based feature screening and three-stage physics-informed meta-learning are proposed in this paper for multi-condition tool wear unified monitoring. First, high-dimensional data acquired during the cutting process are exploited to construct a time–frequency feature matrix. Information criteria are employed to identify the distribution of tool wear increments. And features whose exhibit maximal multidimensional similarity to both the wear state and its distribution are selected via FSI. Then, a novel three-stage wear physical model is embedded into the monitoring model. These physics-based constraints, together with the measured data, jointly restrict the solution space. An improved meta-optimizer is subsequently adopted to distill the domain-invariant representations shared across multi-conditions. Finally, the monitoring model is rapidly adapted to a new condition with only a handful of samples, enabling real-time and accurate tool wear monitoring. A multi-condition wear experiment conducted on indexable CNC milling inserts demonstrated that, compared with state-of-the-art methods, the proposed method exhibits markedly higher precision, stability, and adaptability in new conditions.

ABSTRACT The core challenge of fine‐grained image recognition (FGIR) tasks is distinguishing highly similar subclasses within the same base category. Most CNN‐based deep learning methods typically focus on extracting information from local regions while overlook the inherent structure between subclasses and the complex relationships between features. This paper presents a two‐stage feature selection method based on partial order analysis (POA) and heterogeneity evaluation (HE) for FGIR tasks, guiding the model to focus on distinctive features while reducing uncertainty caused by interfering information. Specifically, in the POA stage, clustering first groups similar subcategories into a medium‐granularity category. Formal concept analysis then models their hierarchical partial order, identifying “shared features” among subcategories and “exclusive features” unique to each. This structured representation highlights key contrastive cues. In the HE stage, a novel heterogeneity index is introduced to measure the fluctuation of low‐level features within each fine‐grained category. This index guides the model to suppress pseudo‐discriminative features with high heterogeneity, mitigating the impact of noisy and unstable information on decision‐making. We perform comprehensive experiments on three commonly used benchmark datasets (CUB‐200‐2011, Stanford Cars, and FGVC‐Aircraft). Experimental results show that the proposed method outperforms classic FGIC methods, validating the effectiveness of our approach.

Spectral coherence (SCoh) is a powerful tool to reveal the hidden periodicities of signals, which has been widely used for rolling bearing fault diagnosis. However, most SCoh-based methods focus on searching a single demodulation band, which results in their inability to compound fault diagnosis and discrete frequency band localization. Moreover, many studies are conducted based on prior fault characteristic frequencies (FCFs), which limits their application in limited vision cases. To solve such issues, a prior knowledge-needless method namely clustering weighted envelope spectrum (CWES) is proposed for rolling bearing fault diagnosis. Firstly, based on the algorithms of peak searching and multiple relation checking, the potential FCFs (PFCFs) of each spectral frequency slice (SFS) of SCoh are automatically identified without any prior knowledge. The PFCFs of each SFS are regarded as its fault type label and are used to design a weight to evaluate its fault information abundance. Then, the SFSs with similar labels are clustered and other SFSs are ignored. Each cluster is considered to be associated with a potential cyclostationary component, and the importance of all clusters is sorted based on their maximum weights. Finally, to further enhance the fault characteristics, CWESs are defined as the weighted average of the SFSs in each top-ranked cluster. By using this method, the discrete informative frequency bands of multiple faults can be quickly located without prior FCFs and iterative optimization. The advantages of CWES over the state-of-the-art methods are validated by the experimental data of bearing single and compound faults. The results indicate that CWES has the best completeness in fault information extraction and the highest accuracy of fault diagnosis compared with other methods. Moreover, the robustness and computational efficiency of the proposed method are also advantageous.Note to Practitioners—This paper is motivated by the problems of discrete frequency band localization and compound fault separation in the field of rolling bearing fault diagnosis. Different from other prior FCF-oriented methods, we design a prior knowledge-needless algorithm to identify the PFCFs of each SFS of the SCoh. The PFCFs of each SFS can not only indicate the fault type but also quantify the abundance of fault information. Based on the identified PFCFs, several CWESs can be generated for fault diagnosis through the clustering algorithm and the weighted mechanism. Our experimental results show the proposed method has higher diagnostic accuracy than the existing methods.

Aerodynamic identification accuracy is one of the key factors determining the success or failure of hypersonic aircraft development. However, the inertial force (mid-frequency) generated by the shock flow and the instrument noise (high-frequency) introduced by the acquisition equipment seriously affect the identification accuracy. To address this challenge, first, a convolutional neural network is introduced to filter out high-frequency noise, and the influence of kernel size on feature extraction ability is discussed. Second, a dense block with adaptive empirical mode decomposition, which filters out inertial force component, alleviates the dependence of the model on the number of samples, and gives a distinct physical meaning to the output of each layer, is proposed. Based on the above-mentioned research, an aerodynamic identification model based on a large convolutional kernel and dense block (AI-LSK&DB) is proposed. Wind tunnel experimental results show that the identification accuracy, robustness, and stability of AI-LSK&DB are significantly improved compared with those of frequency domain models and deep learning models.

Single-cell omics data are growing at an unprecedented rate, whereas effective integration of them remains challenging due to different sequencing methods, quality, and expression pattern of each omics data. In this study, we propose a universal framework for the integration of single-cell multi-omics data based on graph convolutional network (GCN-SC). Among the multiple single-cell data, GCN-SC usually selects one data with the largest number of cells as the reference and the rest as the query dataset. It utilizes mutual nearest neighbor algorithm to identify cell-pairs, which provide connections between cells both within and across the reference and query datasets. A GCN algorithm further takes the mixed graph constructed from these cell-pairs to adjust count matrices from the query datasets. Finally, dimension reduction is performed by using non-negative matrix factorization before visualization. By applying GCN-SC on six datasets, we show that GCN-SC can effectively integrate sequencing data from multiple single-cell sequencing technologies, species or different omics, which outperforms the state-of-the-art methods, including Seurat, LIGER, GLUER and Pamona.

Interactions between DNA and transcription factors (TFs) play an essential role in understanding transcriptional regulation mechanisms and gene expression. Due to the large accumulation of training data and low expense, deep learning methods have shown huge potential in determining the specificity of TFs-DNA interactions. Convolutional network-based and self-attention network-based methods have been proposed for transcription factor binding sites (TFBSs) prediction. Convolutional operations are efficient to extract local features but easy to ignore global information, while self-attention mechanisms are expert in capturing long-distance dependencies but difficult to pay attention to local feature details. To discover comprehensive features for a given sequence as far as possible, we propose a Dual-branch model combining Self-Attention and Convolution, dubbed as DSAC, which fuses local features and global representations in an interactive way. In terms of features, convolution and self-attention contribute to feature extraction collaboratively, enhancing the representation learning. In terms of structure, a lightweight but efficient architecture of network is designed for the prediction, in particular, the dual-branch structure makes the convolution and the self-attention mechanism can be fully utilized to improve the predictive ability of our model. The experiment results on 165 ChIP-seq datasets show that DSAC obviously outperforms other five deep learning based methods and demonstrate that our model can effectively predict TFBSs based on sequence feature alone. The source code of DSAC is available at https://github.com/YuBinLab-QUST/DSAC/.

The prediction of drug-drug interactions (DDIs) is essential for the development and repositioning of new drugs. Meanwhile, they play a vital role in the fields of biopharmaceuticals, disease diagnosis and pharmacological treatment. This article proposes a new method called DBGRU-SE for predicting DDIs. Firstly, FP3 fingerprints, MACCS fingerprints, Pubchem fingerprints and 1D and 2D molecular descriptors are used to extract the feature information of the drugs. Secondly, Group Lasso is used to remove redundant features. Then, SMOTE-ENN is applied to balance the data to obtain the best feature vectors. Finally, the best feature vectors are fed into the classifier combining BiGRU and squeeze-and-excitation (SE) attention mechanisms to predict DDIs. After applying five-fold cross-validation, The ACC values of DBGRU-SE model on the two datasets are 97.51 and 94.98%, and the AUC are 99.60 and 98.85%, respectively. The results showed that DBGRU-SE had good predictive performance for drug-drug interactions.

Advances in single-cell RNA sequencing (scRNA-seq) technologies allow researchers to analyze the genome-wide transcription profile and to solve biological problems at the individual-cell resolution. However, existing clustering methods on scRNA-seq suffer from high dropout rate and curse of dimensionality in the data. Here, we propose a novel pipeline, scBKAP, the cornerstone of which is a single-cell bisecting K-means clustering method based on an autoencoder network and a dimensionality reduction model MPDR. Specially, scBKAP utilizes an autoencoder network to reconstruct gene expression values from scRNA-seq data to alleviate the dropout issue, and the MPDR model composed of the M3Drop feature selection algorithm and the PHATE dimensionality reduction algorithm to reduce the dimensions of reconstructed data. The dimensionality-reduced data are then fed into the bisecting K-means clustering algorithm to identify the clusters of cells. Comprehensive experiments demonstrate scBKAP's superior performance over nine state-of-the-art single-cell clustering methods on 21 public scRNA-seq datasets and simulated datasets. The source codes and datasets are available at https://github.com/YuBinLab-QUST/scBKAP/ and https://doi.org/10.24433/CO.4592131.v1.

MOTIVATION: Multi-label (ML) protein subcellular localization (SCL) is an indispensable way to study protein function. It can locate a certain protein (such as the human transmembrane protein that promotes the invasion of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)) or expression product at a specific location in a cell, which can provide a reference for clinical treatment of diseases such as coronavirus disease 2019 (COVID-19). RESULTS: The article proposes a novel method named ML-locMLFE. First of all, six feature extraction methods are adopted to obtain protein effective information. These methods include pseudo amino acid composition, encoding based on grouped weight, gene ontology, multi-scale continuous and discontinuous, residue probing transformation and evolutionary distance transformation. In the next part, we utilize the ML information latent semantic index method to avoid the interference of redundant information. In the end, ML learning with feature-induced labeling information enrichment is adopted to predict the ML protein SCL. The Gram-positive bacteria dataset is chosen as a training set, while the Gram-negative bacteria dataset, virus dataset, newPlant dataset and SARS-CoV-2 dataset as the test sets. The overall actual accuracy of the first four datasets are 99.23%, 93.82%, 93.24% and 96.72% by the leave-one-out cross validation. It is worth mentioning that the overall actual accuracy prediction result of our predictor on the SARS-CoV-2 dataset is 72.73%. The results indicate that the ML-locMLFE method has obvious advantages in predicting the SCL of ML protein, which provides new ideas for further research on the SCL of ML protein. AVAILABILITY AND IMPLEMENTATION: The source codes and datasets are publicly available at https://github.com/QUST-AIBBDRC/ML-locMLFE/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Rotary encoders are commonly used for dynamic control and positioning of industrial robots. Results of this study suggested that rotary encoder signal can also be used to monitor the efficiency of industrial robot systems effectively after proper processing. A novel strategy using singular spectrum analysis (SSA) integrated with hierarchical hyper-Laplacian prior prototype (HHLP) is proposed in this study for defect detection in industrial robots. Sparsity-assisted techniques are efficient flaw-based extraction techniques that have been extensively investigated in recent years. However, the selection of an appropriate sparse prior from the point of view of probability theory remains unverified. First, SSA enables the separation of complicated encoding signals to several interpretable components, including a trend, a set of cyclic oscillations, and residual oscillations (noise). Second, we describe HHLP by maximizing posterior probability of robot flaw diagnosis. HHLP is proposed to extract noise interference, cyclic pulse, and harmonic interference from the residual signal using the SSA technique. We infer that the hyper-Laplacian prior in the prototype may present a more efficient prototype flaw than the Laplacian prior. In addition, HHLP incorporates physical characteristics necessary to distinguish harmonic intervention. This study primarily establishes a modern prototype that represents the former dispersed from the perspective of maximizing the probability of the latter. Meanwhile, generalized minimax-concave regularization inductive and kurtosis-based weighted sparse prototypes are compared and spectral kurtosis is used to confirm the efficacy of HHLP. Note to Practitioners—This study aims to solve the problem of industrial robot fault diagnosis during the operation process to avoid production delays. Rotary encoder sensor is attached to each joint to collect raw information and identify the robot position. Data from the rotary encoder sensor can also be used for the efficient health status assessment of the performance of the industrial robot system after proper processing. Therefore, a new approach using singular spectrum analysis combined with hierarchical hyper-Laplacian pre-induced prototype is proposed in this study. The residual signal extracted using the singular spectrum analysis method for processing in a hierarchical hyper-Laplacian pre-induced prototype is used to improve the weak fault feature. We describe a hierarchical hyper-Laplacian preprototype by maximizing the posterior probability of the flaw diagnosis. We introduce a hierarchical hyper-Laplacian prior that integrates physical characteristics to distinguish between harmonic interferences. The distribution of coefficients acquired through other dictionaries or transformations and selection of the optimal priority for the extraction of flaw characteristics will be the foci of future investigations.

A milling cutter is one of the most important parts of machine tools. Its working status significantly influences the precision of workpiece. Due to the complex wear mechanism, the single sensor may be difficult to acquire the complete degradation information of milling cutters. Therefore, in this article, a feature learning based method is proposed to automatically extract features from multisource data and predict the remaining useful life of cutting tools in real time. First, a statistic-based method is constructed to detect and delete the outliers hidden in the monitoring data. Second, the clean data are input into a multiscale convolutional attention network (MSAN) to learn features and fuse multisource data. At last, the fused data are used to predict the remaining useful life of cutting tools in a regression layer. Compared with traditional tool life prediction methods, the proposed method is able to fuse multisource data through an attention feature learning model to conduct the life prediction of tools. Additionally, the data cleaning and model optimization methods are also proposed to promote engineering practicability. To validate the effectiveness of such method, the life testing experiments on milling cutters are conducted to obtain run-to-failure data. In those experiments, multisensor monitor data are acquired, which are used to conduct validation experiments testing the effectiveness of the proposed method. The results indicate the superiority of the proposed method in remaining useful life prediction milling cutters.

In the industrial applications of mechanical fault diagnosis, machines work in normal condition at most time. In other words, most of the collected datasets are highly imbalanced. Although deep learning has been widely applied in intelligent diagnosis, it is unsuitable for such imbalanced situation. In addition, few studies attempted to determine the parameters in the diagnosis models. For solving such problems, Pareto-optimal adaptive loss residual shrinkage network (PALRSN) is proposed. First, a fixed length-based encoding method is implemented to represent the candidate architectures of PALRSN. Then, multiply accumulate operations and Gmean value representing the model complexity and identification performance, respectively, on imbalanced datasets are selected as the optimization targets to search for the optimal PALRSN architecture. In the training process, an adaptive loss function assigns different misclassification costs on all categories according to their number discrepancy to highlight the minority samples. The proposed method is validated by bearing data and milling cutter data with different imbalanced ratio. The experimental results demonstrate that such approach outperforms the state-of-the-art methods in imbalanced classification.

Reliable remaining useful life (RUL) prediction of industrial equipment key components is of considerable importance in condition-based maintenance to avoid catastrophic failure, promote reliability and reduce cost during the production. Diamond-coated mechanical seal is one of the most critical wearing components in petroleum chemical, nuclear power and other process industries. Estimating the RUL is of critical importance. We consider the data-driven approaches for diamond-coated mechanical seal RUL estimation based on AE sensor data, since it is difficult to construct an explicit mathematical degradation model of seal. The challenges of this work are dealing with the noisy AE sensor data and modeling the degradation process with fluctuation. Faced with these challenges, we propose a pipeline method CDF-CNN to estimate the RUL for mechanical seal: WPD-KLD to raise the signal-to-noise ratio, novel CDF-based statistics to represent seal degradation process and CNN structure to estimate RUL. To acquire AE sensor data, several diamond-coated seals are tested from new to failure in three working conditions. Experimental results demonstrate that the proposed method can accurately predict the RUL of diamond-coated mechanical seal based on AE signals. The proposed prediction method can be generalized to other various mechanical assets.

We present an adaptive hierarchical sliding mode control based on fuzzy neural network (AFNNHSMC) for a class of underactuated nonlinear systems. The approach is applied to the problem of high-precision trajectory tracking. The underactuated nonlinear system is viewed as several subsystems. One subsystem is used to design the first layer sliding surface, which constructs the second layer sliding surface with another subsystem. When the top layer, the nth layer, includes all the subsystems, the design process is finished. Meanwhile, the equivalent control law and the switching control law are achieved at every layer. Because the hierarchical sliding mode control (HSMC) law relies excessively on the requirement of detailed information of the underactuated dynamic system, and because that method causes an inevitable chattering phenomenon, an online fuzzy neural network (FNN) system is applied to mimic the HSMC law. Moreover, the bounds of system uncertainties, time-varying external disturbances, and modeling error caused by the fuzzy neural network system are estimated online by a robust term. The stability of the closed-loop system is guaranteed based on the Lyapunov theory and the Barbalat's Lemma. Finally, the example of a single-pendulum-type overhead crane system is simulated and used to verify the effectiveness and robustness of the proposed method compared with the conventional HSMC method.