Using optimal assembly relationships, companies can enhance product quality without significantly increasing production costs. However, predicting Assembly Geometric Errors presents a challenging real-world problem in the manufacturing domain. To address this challenge, this paper introduces a highly efficient Transformer-based neural network model known as Predicting Assembly Geometric Errors based on Transformer (PAGEformer). This model accurately captures long-range assembly relationships and predicts final assembly errors. The proposed model incorporates two unique features: firstly, an enhanced self-attention mechanism to more effectively handle long-range dependencies, and secondly, the generation of positional information regarding gaps and fillings to better capture assembly relationships. This paper collected actual assembly data for folding rudder blades for unmanned aerial vehicles and established a Mechanical Assembly Relationship Dataset (MARD) for a comparative study. To further illustrate PAGEformer performance, we conducted extensive testing on a large-scale dataset and performed ablation experiments. The experimental results demonstrated a 15.3% improvement in PAGEformer accuracy compared to ARIMA on the MARD. On the ETH, Weather, and ECL open datasets, PAGEformer accuracy increased by 15.17%, 17.17%, and 9.5%, respectively, compared to the mainstream neural network models.

This article presents a data-driven framework for fault detection and diagnosis (FDD) in permanent magnet synchronous motor (PMSM) drive systems using conditional invertible neural network (CINN). Unlike conventional deep models that operate as closed boxes, the proposed CINN framework establishes a bidirectional and control-theoretically consistent mapping between process data and residual signals, enabling explainable fault reasoning. First, an analytically interpretable formulation of the CINN-based residual mapping is derived using composite operators, and two sets of residual signals are designed to enhance FDD. Second, a Bayesian classification-based fault diagnosis strategy is implemented through a detailed analysis of the residual signals. The proposed FDD scheme offers the following advantages: 1) the system modeling and residual construction are integrated into the CINN; and 2) its design is grounded in control-theoretic principles to ensure the theoretical soundness of the learning mechanism. Experimental results verify that the proposed method achieves fast and accurate fault detection along with effective diagnosis for various fault types in PMSM drive systems.

Ischemic stroke (IS) is a leading cause of mortality and long-term disability, underpinned by complex molecular mechanisms, such as oxidative stress, neuroinflammation, and apoptosis. The flavonoid Engeletin exhibits promising neuroprotective properties, but its mechanism of action remains largely unknown. In this study, we employed a systems biology approach, combined with artificial intelligence (AI), to uncover the multitarget mechanisms of Engeletin in IS. Potential targets were predicted using SwissTargetPrediction and PharmMapper and were found to intersect with IS-related genes from multiple disease databases. Functional enrichment analyses (GO/KEGG) revealed significant involvement in three classical neuroprotective pathways: PI3K-Akt-mTOR/Caspase/BCL2 (anti-apoptotic), TLR4/NF-κB (anti-inflammatory), and NRF2/KEAP1/HO-1 (antioxidant). Notably, we integrated six machine learning models (RF, SVM, GLM, KNN) to identify robust IS-specific biomarkers from the GSE22255 transcriptomic database. We used CIBERSORTx to characterize immune cell infiltration patterns in IS, revealing elevated populations of CD8⁺ T cells, M0 macrophages, and other PBMC-derived immune cells, suggesting the presence of an immunologically dynamic microenvironment. Molecular docking predicted favorable binding affinities of Engeletin to core targets (e.g., EGFR, IGF1R, KEAP1, JAK2). Finally, in vitro experiments using a Na₂S₂O₄-induced PC12 cell model confirmed Engeletin’s efficacy in reducing oxidative stress, modulating calcium overload, and regulating apoptosis- and inflammation-related genes. Overall, our study establishes a comprehensive pharmacological mechanistic framework for Engeletin in combating IS and reveals the multitarget and multi-pathway neuroprotective mechanisms, thus providing preliminary support for using Engeletin in combating ischemic stroke.

Fault diagnosis of complex electromechanical systems is critical for ensuring safe operation of industrial equipment. Belief Rule Base (BRB) demonstrates significant advantages in small-sample and uncertain environments by combining expert knowledge with data-driven modeling. However, it faces the challenge of combinatorial explosion in high-dimensional feature scenarios. The number of rules grows exponentially. This severely limits its engineering applications. To address this challenge, this paper proposes a Hierarchical Tree-Structured BRB (HTS-BRB) method. It breaks the constraint of full rule combinations through hierarchical decomposition strategy. The proposed method first employs mutual information-based quantification integrated with expert knowledge to rank feature importance and select critical feature subsets. Subsequently, it constructs a hierarchical tree based on feature ranking. It employs an evolutionary algorithm to generate a high-quality sub-BRB set. Finally, it introduces the MAKER framework to model correlation coefficients for non-independent evidence fusion. The effectiveness of the proposed method is validated through permanent magnet synchronous motor fault diagnosis experiments.

Despite significant advancements in communication systems, inherent limitations persist in providing reliable data transmission for emerging applications with massive data exchanges. Semantic communication offers promising solutions by extracting and transmitting meaningful information rather than raw bit sequences. However, it faces challenges from high mobility and dynamic channel conditions in wireless environments. In this paper, we design a ground-to-air network architecture that integrates a rotary-wing unmanned aerial vehicle (UAV) and ground terminals to maximize semantic transmission efficiency while maintaining low energy consumption. This approach leverages the high mobility of the UAV for flexible deployment and the data reduction capabilities of semantic communication. Therefore, we formulate a multi-objective optimization problem to simultaneously balance the total semantic transmission rate and the UAV propulsion energy consumption by jointly optimizing the UAV hovering position, semantic encoding lengths, and resource block (RB) allocation. The problem is complex, with mixed continuous and discrete variables, which necessitates an advanced optimization method. To address these challenges, we propose a novel greedy-enhanced adaptive multi-objective cellular genetic algorithm (GEAMOCell), which utilizes an adaptive neighborhood selection mechanism to balance exploration and exploitation, and employs a crowding-guided archive feedback mechanism to maintain population diversity. The simulation results demonstrate that the proposed GEAMOCell algorithm outperforms baseline algorithms in terms of convergence, semantic transmission rate, and energy efficiency.