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.

The scarcity of fault samples degrades the accuracy of data-driven intelligent fault diagnosis (IFD). An auxiliary classifier generative adversarial network (GAN) has therefore emerged as a dominant paradigm for generating multiclass data to mitigate this issue; however, this framework suffers from low intraclass diversity and gradient instability. Specifically, the classifier's strong class-label separability compresses the category's support space, reducing diversity and also causing optimization conflicts. To this end, this article proposes a discriminative condition-guided generative model (DCGM) to synthesize high-fidelity data across categories for induction motor fault diagnosis under small-sample conditions. First, a discriminative classifier is integrated into the conditional GAN to replace the auxiliary classifier, theoretically alleviating diversity constraints and instability. After that, an adaptive feature matching loss based on supervised contrastive learning is proposed to enhance the synthetic quality of the class-label data. Then, three novel evaluation metrics are developed to quantitatively assess the generated data quality. Extensive experiments on induction motor datasets demonstrate that DCGM achieves state-of-the-art evaluation scores compared to diffusion-, transformer-, and GANs-based models. Finally, small-sample fault diagnosis further validates the superiority of the proposed approach, highlighting its potential in engineering applications. To the best of our knowledge, this is the first to introduce the novel discriminative generative framework for conditional data generation in the IFD field.

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.

The significance of intelligent fault diagnosis techniques is increasing in maintaining the security and reliability of railway operations. In particular, few-shot learning shows promise since it can address the issue of limited fault samples. However, the existing approaches have the following shortcomings. First, they ignore rich fault information in the joint distributions of multi-dimensional features, limiting the improvement of diagnosis accuracy. Second, they lack specialized mechanisms to alleviate severe degradation in diagnosis accuracy caused by label mistakes in engineering scenarios. To address the above issues, a Brownian distance covariance-based few-shot learning framework of fault diagnosis considering noisy labels is proposed for train transmission systems. In network construction, a novel joint distribution expression (JDE) layer is developed and embedded into the prototypical network, implementing similarity measures based on the joint distribution characteristics. In network training, a new antimislabeling learning strategy is designed for few-shot fault diagnosis tasks, in which a similarity-weighted prototype aggregation mechanism mitigates the negative effects of mislabeled support samples and a loss function with outlier attenuation avoids disruptions from mislabeled query samples. Taking a fault diagnosis study case of motors, gearboxes, and axle boxes as examples, it is demonstrated that the proposed framework can effectively learn and recognize faults, even using limited training datasets containing parts of mislabeled samples. Moreover, the superiority of the proposed framework is demonstrated by comparing it with other state-of-the-art methods.

Operating condition monitoring of wind turbine (WT) key components is of significant importance to preventative maintenance and the improvement of WT reliability. To realize this industrial target, health indicator (HI) construction is a crucial and indispensable step. While most of the recently reported HIs are emphasized effective in stationary cases, they are insufficiently applicable to variable speed conditions. To address this issue, a novel HI through operating speed slicing and discrepancy compensation is proposed in this article for WT generator bearing condition monitoring. First, signal probability distributions of the collected degradation data are appropriately characterized by an optimized multiparameter regression method. Then, benchmark distributions established at the normal state are identified through operating speed slicing, and the discrepancies induced by the time-varying operating condition are subsequently calibrated with a compensation strategy. On this basis, a globally comparable metric, by quantitatively evaluating the degree to which the currently established distribution deviates from the corresponding slice-related benchmark, is accordingly constructed. Experimental tests demonstrate that the proposed HI can make a more effective health state assessment for WT generator bearing under variable speed conditions when compared with the conventional indicators.

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.