Few-shot learning seeks to recognize novel classes from limited examples. Model-agnostic meta-learning (MAML), known for its simplicity and flexibility, learns an effective initialization for fast adaptation in data-scarce settings. However, MAML-based methods face challenges when there is a significant distributional shift between training and testing tasks, leading to inefficient learning and poor generalization across domains. In this work, we identify the core issues: inflexible weight update rules and limited adaptive learning capabilities. Instead of focusing solely on better initialization, we aim to enhance the adaptation process. Consequently, we propose a novel Layer-Adaptive Proportional-Integral-Derivative (LA-PID) optimizer integrated into a meta-learning framework. This design incorporates classical control theory, utilizing PID control to dynamically adjust task-specific gains at each network layer. Additionally, the theoretical conditions for optimal hyperparameter initialization and global model convergence are addressed from both control and optimization perspectives. Experiments on benchmark datasets show that LA-PID achieves state-of-the-art performance in few-shot classification, cross-domain, and regression tasks, while requiring fewer training steps.

Deep learning has achieved remarkable success in fault diagnosis but remains vulnerable to distribution shifts due to its reliance on the assumption of independent and identically distributed (i.i.d.) data. In real-world industrial scenarios, changing operating conditions often result in severe performance degradation. Although domain generalization (DG) offers a promising direction for cross-condition fault diagnosis, existing methods underutilize the diverse knowledge embedded in source models and data, limiting their generalization capability. To address this, we proposeKD2G(Knowledge Distillation with feature decoupling for Domain Generalization), a novel approach that constructs pseudo multi-source information via multi-teacher distillation and enhances representation diversity through feature decoupling. KD2G integrates feature engineering into the distillation process by extracting domain-invariant and class-specific knowledge from multiple teachers, enabling the student model to generalize across unseen domains more effectively. Extensive experiments on benchmark datasets validate the superiority of KD2G, yielding an average accuracy improvement of 8.5% over state-of-the-art DG methods. This work offers a new perspective on advancing DG theory and provides a scalable solution for robust fault diagnosis under complex operating conditions.

The intelligent fault diagnosis has achieved notable success in identifying known mechanical failures; however, reliably detecting out-of-distribution (OOD) faults remains a key challenge to achieve the diagnostic robustness. In industrial applications, vibration signals are typically collected as time-series data whose dynamic characteristics vary with load, speed, and environmental interference, with weak early fault patterns that blur class boundaries. As a result, models trained under limited laboratory conditions inevitably encounter unseen OOD inputs after deployment, requiring the ability to recognize and reject them reliably. Existing representation- and similarity-based OOD methods have shown promise but typically rely on single-granularity prototypes, capturing only coarse similarity structures and overlooking latent subclass relations—thus limiting the generalization under complex degradation modes. To address these limitations, we propose a multigranularity fuzzy inference (MgFI) framework for enhanced uncertainty quantification in fault diagnosis. MgFI models fine-grained subclass memberships on a hyperspherical manifold, aggregates them into class-level fuzzy sets, and infers coarse-grained In-distribution (ID) confidence through the hierarchical fuzzy reasoning. Extensive experiments demonstrate that MgFI substantially improves the OOD detection accuracy and provides a principled, interpretable framework for trustworthy open-set industrial diagnostics.

An automatic vision-based sewer inspection plays a vital role of sewage system in a modern city. Existing methods have utilized evidential deep learning to construct trusted models. Although the acceptable performance has been achieved in sewer defect classification, the fine-grained information of sewer defects in videos is ignored. Meanwhile, the trade-off between multi-label classification and uncertainty estimation remains challenging. In this paper, support clip-based pareto-optimal evidential network (POEN) is proposed for trusted video-based sewer inspection. Specifically, support clip module (SCM) is designed to capture the fine-grained visual representation of defects from local scale segments. Then, evidential deep learning is introduced to quantify the uncertainty for out-of-distribution detection. Furthermore, Pareto-optimal weighting scheme (PWS) is designed to solve the common trade-off dilemma in multi-task learning. Extensive experiments are conducted on VideoPipe, in which the superiority of POEN is demonstrated compared with the state-of-the-art methods.

The fault diagnosis based on supervised learning has achieved remarkable results in the intelligent manufacturing, making it an important guarantee for long-term safe and stable operation in modern industry. However, the accuracy heavily relies on high-quality annotation labels, which are expensive to obtain, limiting the diagnosis models applicability in many scenarios. Although obtaining automatically annotated samples from annotators is a promising solution, the generated dataset is always containing incorrect labels (noisy labels), due to perceptual limitations, resulting in low or even invalid the accuracy of model. With the goal of handling this challenge, a diagnostic approach based on multi-granularity information fusion to combat noisy labels, called MgCNL, is proposed, to train the model with high-accuracy, without knowing the specific noise ratio. Specifically, inspired by granular-ball computing, a confidence evaluation method of labels is designed, so that samples with high confidence labels can be selected from dataset with noisy labels for supervised learning, thus avoiding the negative impact of incorrect labels on model performance. Finally, the efficacy was demonstrated on three datasets using different backbones: MgCNL successfully reduced the adverse impact of noisy labels, achieving significantly better results than other advanced methods in various noisy scenarios, which offers a competitive model training strategy for practitioners in intelligent manufacturing or industrial fault diagnosis who are hampered by the costs associated with sample labeling. Note to Practitioners—In modern industry, the cost of manual/expert annotation for high-quality data is is prohibitively expensive, and the data annotated by automatic annotators often contains noisy labels that seriously damages the accuracy of models, which makes many data-driven diagnosis models constrained by training data and difficult to put into practice, posing an urgent challenge to the automation and intelligence of the manufacturing industry. To address this challenge, this article proposed a robust training strategy called MgCNL, aimed at offsetting the negative impact of noisy labels, in the hope that automatic annotation strategy with lower cost can be more widely applied in model training tasks for industrial practice. MgCNL, based on multi-granularity information, can effectively select high-confidence samples from datasets for supervised learning, even under unknown proportions of noise labels, thus reducing the misleading impact of noisy labels on diagnostic models. As a result, MgCNL possesses the ability to robustly train high-accuracy diagnostic models in data with noisy labels, thus enabling automatic annotators to replace experts in dataset construction as a more economical and efficient potential technical approach. Meanwhile, MgCNL also brings value to datasets with uncertain labels, making them applicable without the need to invest significant human resources to verify label reliability.

Deep learning has demonstrated exceptional performance in fault diagnosis tasks that rely on large-scale datasets. However, the high cost of annotating such datasets has led to the emergence of various automatic annotation methods. While these methods reduce labeling costs, they inevitably introduce noisy labels, which pose significant challenges to the generalization and accuracy of deep learning-based diagnostic models. Although Learning with Noisy Labels (LNL) methods mitigate the adverse effects of noisy labels through strategies such as sample separation or label correction, many rely heavily on their own prediction results to guide subsequent training, which often introduces confirmation bias, limiting the effectiveness of the trained models. To address this limitation, this article draws inspiration from quantum collapse and proposes a novel LNL strategy named Multigranularity Labeling (MgL). By integrating observed labels, pseudolabels, and collapsed labels, MgL constructs the multigranularity labels, designed to suppress confirmation bias and improve the model's tolerance to noisy labels. Extensive experiments validate the effectiveness and superiority of MgL, particularly on training datasets with high noise intensity, such as those with 90% symmetric noise. This advancement offers promising opportunities for applying datasets with lower annotation costs in real-world scenarios, ultimately contributing to intelligent diagnostic systems.

Model-Agnostic Meta-Learning (MAML) and its variants have shown remarkable performance in scenarios characterized by a scarcity of labeled data during the training phase of machine learning models. Despite these successes, MAMLbased approaches encounter significant challenges when there is a substantial discrepancy in the distribution of training and testing tasks, resulting in inefficient learning and limited generalization across domains. Inspired by classical proportional-integral-derivative (PID) control theory, this study introduces a Layer-Adaptive PID (LA-PID) Optimizer, a MAML-based optimizer that employs efficient parameter optimization methods to dynamically adjust task-specific PID control gains at each layer of the network, conducting a first-principles analysis of optimal convergence conditions. A series of experiments conducted on four standard benchmark datasets demonstrate the efficacy of the LA-PID optimizer, indicating that LA-PID achieves state-oftheart performance in few-shot classification and cross-domain tasks, accomplishing these objectives with fewer training steps. Code is available on https://github.com/yuguopin/LA-PID.

In the absence of a pre-built indoor map, robot navigation suffers from the limitations of sensors and environments, resulting in decreased efficiency in performing ad-hoc tasks. Given that blueprints are difficult to obtain, an intuitive method is to provide robots with prior knowledge via hand-drawn floor plans. However, due to the inability of robots to directly comprehend hand-drawn styles, the applicability of this method is limited. In this paper, we present a novel framework for hand-drawn floor plan reconstruction that can recognize abstract hand-drawn elements and standardize the reconstruction of hand-drawn floor plans, thereby providing robots with valuable global map information. Specifically, we design a new series of structure descriptors as reconstruction components and employ a deep learning-based model for recognition. Then the standardized results are obtained through the proposed floor plan reconstruction algorithm. To verify the effectiveness of the framework, we conduct experiments on electronic and paper hand-drawn floor plans. Compared with other state-of-the-art methods, our proposed method achieves superior reconstruction results. This work expands the application scenarios for indoor robots, enabling them to quickly comprehend the semantics of complex scenes, thereby enhancing the competitiveness in downstream tasks.

Unmanned aerial vehicles (UAVs) represent an essential component of advanced intelligent equipment that can be used as an aerial perception system by installing various sensors such as vision, hearing, touch, taste, and smell to achieve intelligently integrated perception of environments. However, these perception system with environmental information may be threatened by various internal and external attacks, causing a great challenge to the security of the UAV. The original security system relied on an expert knowledge base to prevent attacks, but the weaknesses of lacking proactivity and flexibility are gradually exposed. The strong resistance and survivability of biological systems can be used to fill this capability gap and provide new ideas for the security of the UAV perception system. Therefore, an endogenous security framework (ESUAV-NI) based on the neural system and immune system is proposed in this article. Through breeding artificial intelligence (AI) vaccines and distributed neural hierarchical control, we achieve the security protection for the UAV perception system. Moreover, we evaluated the AI vaccine breeding approach in the ESUAV-NI by conducting extensive experiments on internal threats and external aerial imagery camouflage data, respectively. The results show that the proposed approach has a superior performance for the UAV perception system.