Abstract Bistable mechanisms can maintain two distinct stable equilibrium states without continuous energy input. Although translational bistable mechanisms have attracted considerable research attention, rotational bistable mechanisms (RBMs) remain relatively underexplored, and a systematic optimization-based framework for designing RBMs subject to specific constraints is still lacking. This paper proposes an automated optimization framework that integrates the chained beam constraint model (CBCM) with the Non-dominated Sorting Genetic Algorithm II (NSGA-II). The accuracy and computational efficiency of CBCM in large-deflection analysis enable NSGA-II to efficiently explore the design space and identify Pareto-optimal solutions. The proposed framework produced a compact RBM with an outer diameter of 50 mm and a rotational stroke of up to 90°. Experimental validation showed that the fabricated mechanism reached its second stable equilibrium position at approximately 87°. These results demonstrate the feasibility of designing compact RBMs with large angular strokes. In addition, a parametric study was conducted to evaluate the effect of beam width on the agreement between CBCM and finite element analysis (FEA), thereby clarifying the applicability and limitations of CBCM for RBM design.
Abstract Nighttime road-scene parsing is a core function of autonomous driving perception. Low illumination, local overexposure, and motion blur severely degrade boundary clarity and impair the parsing of small objects, elongated structures, and complex semantic transition regions. Most existing methods rely on image enhancement or domain adaptation, but rarely examine the decoding stage where these degradations accumulate. We propose NightNext, a segmentation framework that addresses these challenges through targeted reconstruction of the decoding stage without relying on image enhancement or domain adaptation. We introduce two complementary modules and one training strategy: a Structure-aware Detail Enhancement Module that gates noisy shallow features and refines them through frequency-domain recalibration and multi-scale convolution, a Boundary-aware Detail-Context Fusion Module that adaptively balances detail and semantics using boundary priors, and a Decoupled Boundary Supervision strategy that prevents unstable boundary responses from directly modulating detail features. Experiments on NightCity and ACDC Night show that NightNext delivers strong segmentation accuracy, reaching 57.74 mIoU on NightCity and 55.38 mIoU on ACDC Night while keeping the model at 14.83M parameters.
Abstract Bayesian neural networks represent model parameters using probability distributions and can provide information about parameter and predictive uncertainty. However, the sampling operations associated with Bayesian inference can increase computational and hardware requirements, in resource-constrained embedded systems. This work investigates an implementation-oriented workflow for converting a Bayesian-trained neural network into a deterministic fixed-point representation for FPGA-oriented evaluation. A BNN was trained on the MNIST handwritten-digit dataset using variational inference. Following training, the posterior means of the learned parameters were extracted to construct a deterministic approximation, thereby removing stochastic parameter sampling during inference. The resulting deterministic model was quantized using QKeras with a 10-bit fixed-point representation and evaluated in software. A separate fixed-point representation of the deterministic model was used to generate a custom Verilog-oriented implementation for RTL verification and FPGA-oriented analysis. The Bayesian neural network achieved a classification accuracy of 94.01\% on the complete MNIST test dataset using 30 Monte Carlo samples, while the posterior-mean deterministic model achieved 93.98\%. The 10-bit quantized software model achieved 93.87\% on the same test dataset. The available synthesis results reported 2,474 lookup tables, 2,201 flip-flops, and 141 DSP resources. The reported power consumption of 1.665 W was obtained through Vivado power estimation and therefore represents a tool-based estimate rather than a direct board-level measurement. Hardware-oriented validation was limited to directed test vectors and was used to verify the functional operation of the RTL implementation rather than to establish complete test-set accuracy. The results demonstrate the feasibility of converting a variationally trained Bayesian neural network into a deterministic and quantized FPGA-oriented representation. However, explicit uncertainty estimation is not retained after posterior-mean conversion, and complete hardware test-set accuracy, measured latency, and board-level power consumption were not established. The study therefore presents an implementation-oriented feasibility case study rather than a new Bayesian inference algorithm or FPGA architecture.
Abstract In bearing fault diagnosis, the scarcity of fault samples creates severe class imbalance and makes minority fault distributions difficult to learn reliably. Existing data-level methods mainly rely on interpolation, neighborhood relationships, or distribution modeling strategies to synthesize minority samples, which may fail to preserve complex temporal structures and fault-related local patterns. Although GAN-based methods provide flexible distribution modeling capabilities, their conditioning mechanisms often lack explicit representation of class-discriminative local patterns across temporal and spectral domains. To address these limitations, we propose ShapeGAN, a dual-domain shapelet-guided conditional generative framework for minority fault sample augmentation. Specifically, ShapeGAN first discovers class-specific temporal shapelets from minority and majority samples and derives the spectral representation of each retained segment using the discrete Fourier transform (DFT). A Conditional Mixing Module samples these paired representations, which are integrated by a bidirectional cross-attention generator. Training then proceeds from single-shapelet to multi-shapelet conditioning through the proposed Two-Stage Mixed Training strategy. Experiments on 24 imbalanced bearing fault scenarios show that ShapeGAN achieves the highest average Macro-F1 and G-Mean with the MLP classifier, while its average AUC remains comparable to that of the strongest baseline. With LSTM and ResNet, ShapeGAN achieves the best average performance across all three metrics, demonstrating the effectiveness of the proposed augmentation method across different downstream classifier architectures.
Abstract Bearings are key components of rotating machinery, and their operational status directly affects the reliability and safety of the entire mechanical system. High-precision and efficient fault diagnosis is of great significance for the predictive maintenance of bearing systems and the reduction of operational risks. Aiming at the problems of low accuracy, poor generalization ability, and difficulty of model hyperparameters selection in current methods under complex working conditions, a hybrid model of STBCA integrating Swin Transformer, Bidirectional Mogrifier-Gated Recurrent Unit(BiMGRU), and Cross-attention mechanism is firstly proposed, where Swin Transformer is used to extract the local and global spatial features, BiMGRU is adopted to capture the temporal sequence features, and crossattention is utilized to realize the effective fusion of spatial-temporal features to enhance the discriminability of fault features. Furthermore, an improved crow search algorithm (ICSA) is developed in this study to realize the hyperparameters automatic optimization for the proposed model in the training phase, which gets rid of the drawbacks of inefficiency brought by manual trial-and-error parameters adjustment. Experimental results reveal that the presented method achieves better performance in accuracy, anti-interference and generalization capacity compared with existing mainstream schemes. The findings confirm its rationality and competitive advantages, and offer a feasible technical reference for intelligent fault identification of bearings.
