Defect recognition is an important task in intelligent manufacturing. Due to the subjectivity of human annotation, the collected defect data usually contains a lot of noise and unpredictable uncertainties, which have a great negative influence on defect recognition. It is a significant challenge to discover an effective defect recognition model with satisfactory uncertainty processing ability. A natural way is to automatically search for an efficient deep model, which can be realized by neural architecture search (NAS). To achieve this, we propose an efficient fuzzy NAS framework for defect recognition, where the searched architecture can effectively handle uncertain information from the given datasets. Specifically, we first design a fuzzy search space and the related encoding strategy for fuzzy NAS. Then, we propose a comparator-based evolutionary search approach, where an online end-to-end comparator is learned to directly determine the selection of candidate architectures from the evolutionary population. The comparator works in an end-to-end way and it transforms the complex ranking problem of evaluating architectures into a simple classification task, which overcomes the rank disorder issue suffered from traditional performance predictors. A series of experimental results demonstrate that the architecture with fewer #Params (1.22 M) search by fuzzy neural architecture search framework for defect recognition method achieves higher accuracy (92.26%) compared to the state-of-the-art results (i.e., DARTS-PV) on the ELPV dataset, as well as competitive results (accuracy = 76.4%, #Params = 1.04 M) on the CODEBRIM dataset. Experimental results show the effectiveness and efficiency of our proposed method in handling uncertain problems.

The dynamic task allocation problem for Unmanned Aerial Vehicle (UAV) swarms is characterized by dynamic uncertainty, high nonlinearity, and multimodality, which increasingly becomes a focal point and challenge within the realm of task allocation. This study investigates the mixed interaction modes of “individual-individual,” “individual-environment,” and “swarm-environment,” drawing inspiration from the labor division observed in wolf packs. We design a mechanism for alliance formation that is predicated on both individual democratic choice and centralized swarm decision-making, integrating the concept of alliance formation with a labor division model. Moreover, we propose a democratic-centralization model (DCM) that incorporates a bottom-up labor division approach aligned with the wolf pack alliance framework. This model is adeptly adapted to the dynamic task allocation for UAV swarms, employing a strategy of “individual cyclic competition plus overall coordinated decision-making.” We compare simulation experiments using the DCM with three contemporary, leading methods addressing the dynamic allocation problem for UAV swarms tasked with dynamic operations. The results demonstrate that our model can efficiently orchestrate the dynamic allocation of UAV swarms, exhibiting considerable dynamic adaptability, collaborative efficiency, and robustness.