LBLin-Yuan Bai

Lin-Yuan Bai

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Lin-Yuan Bai has a total of 31 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Effect of SiC Content on the Microstructure and High-Temperature Tribological Properties of Laser-Cladded AlCoCrFeNi Coatings

    by Shengli Song, Xiaolong Wang, Binning Peng, Linyuan Bai, Shuangyu Liu, Jiadong Shen, Xinyu Miao

    In this study, SiC nanoparticle-reinforced AlCoCrFeNi high-entropy alloy composite coatings (AlCoCrFeNi + x wt% SiC, x = 0, 10, 20, and 30) were fabricated on 316L stainless steel substrates by laser cladding. Their high temperature tribological behavior was systematically investigated under dry sliding conditions at 600 ℃ and 800 ℃. Among the tested coatings, the coating containing 20 wt% SiC exhibited the best overall tribological performance, with average friction coefficients of 0.28 and 0.40 and wear volumes of 0.3997 mm³ and 0.1575 mm³ at 600 ℃ and 800 ℃, respectively. These wear volumes correspond to reductions of 60.91% and 78.32% compared with the SiC-free coating.The corresponding wear rates were 8.65×10⁻⁵ and 3.41×10⁻⁵ mm³/(N·m). Microhardness measurements indicate that SiC addition improves the load-bearing capability of the coating, whereas excessive SiC increases brittleness and promotes spallation. Multi-scale characterizations suggest that the superior performance of the 20 wt% SiC coating is associated with the formation of a relatively continuous tribo-reaction layer composed mainly of Cr–Fe-rich oxides together with Si–O-related species. In addition, a heterogeneous subsurface structure consisting of Cr-enriched banded regions and Ni/Al-enriched island-like regions was observed after sliding at 800 ℃, which is likely related to enhanced shear accommodation and load support. These results indicate that an appropriate SiC content can improve the high-temperature tribological performance of laser-cladded AlCoCrFeNi coatings by stabilizing the interfacial reaction layer and reducing material removal.

  • Open Access

    Strengthening mechanism of CeO2 on the high-temperature friction and wear performance of laser-cladded AlCoCrFeNi high-entropy alloy

    by Shengli Song, Xianrui Zhao, Zhanjiang Li, Xiaolong Wang, Linyuan Bai, Jiadong Shen, Shengli Song

    AlCoCrFeNi high-entropy alloy coatings reinforced with CeO₂ were fabricated on 316L stainless steel via laser cladding to enhance high-temperature tribological performance. A data-assisted approach combining chemical descriptors with a support vector regression model was used to predict the optimal CeO₂ content based on wear-related indicators. The model identified an optimal content of 2.96 wt%, which was validated by experiments at 600 °C and 800 °C. The results show that CeO₂ addition refines the microstructure, promotes grain boundary pinning, and facilitates the formation of dense Cr₂O₃- and Fe₂O₃-rich tribo-oxide films. The coating with 2.96 wt% CeO₂ exhibits the lowest friction coefficient, with wear-track width reduced by 44.0% and 47.0% and wear depth decreased by 19.0% and 57.9% at 600 °C and 800 °C, respectively, compared with the CeO₂-free coating. The dominant wear mechanism shifts from adhesive wear to mild abrasive wear. Microstructural analysis reveals the formation of a nanocrystalline subsurface layer and the evolution of dislocations from tangles to stable walls, indicating enhanced structural stability. The improved performance is attributed to the synergistic effect of grain refinement and stabilized tribo-oxide films. This study provides a data-guided strategy for optimizing rare-earth-modified HEA coatings for high-temperature applications.

  • Open Access

    MCAH-ACO: A Multi-Criteria Adaptive Hybrid Ant Colony Optimization for Last-Mile Delivery Vehicle Routing

    by De-Tian Chu, Xin-Yu Cheng, Lin-Yuan Bai, Hai-Feng Ling

    The growing demand for efficient last-mile delivery has made routing optimization a critical challenge for logistics providers. Traditional vehicle routing models typically minimize a single criterion, such as travel distance or time, without considering broader social and environmental impacts. This paper proposes a novel Multi-Criteria Adaptive Hybrid Ant Colony Optimization (MCAH-ACO) algorithm for solving the delivery vehicle routing problem formulated as a Multiple Traveling Salesman Problem (MTSP). The proposed MCAH-ACO introduces three key innovations: a multi-criteria pheromone decomposition strategy that maintains separate pheromone matrices for each optimization objective, an adaptive weight balancing mechanism that dynamically adjusts criterion weights to prevent dominance by any single objective, and a 2-opt local search enhancement integrated with elite archive diversity preservation. A comprehensive cost function is designed to integrate four categories of factors: distance, time, social-environmental impact, and safety. Extensive experiments on real-world data from the Greater Toronto Area demonstrate that MCAH-ACO significantly outperforms existing approaches including Genetic Algorithm (GA), Adaptive GA, and standard Max–Min Ant System (MMAS), achieving 12.3% lower total cost and 18.7% fewer safety-critical events compared with the best baseline while maintaining computational efficiency.


  • Open Access

    EvoMail: Self-Evolving Cognitive Agents for Adaptive Spam and Phishing Email Defense

    by Wei Huang, Detian Chu, Linyuan Bai, Wei Kang, Haitao Zhang, Bo Li, Jing Ge, Haifeng Ling

    Modern email spam and phishing attacks have evolved far beyond keyword blacklists or simple heuristics. Adversaries now craft multi-modal campaigns that combine natural-language text with obfuscated URLs, forged headers, and malicious attachments, adapting their strategies within days to bypass filters. Traditional spam detection systems, which rely on static rules or single-modality models, struggle to integrate heterogeneous signals or to continuously adapt, leading to rapid performance degradation. We propose EvoMail, a self-evolving cognitive agent framework for robust detection of spam and phishing. EvoMail first constructs a unified heterogeneous email graph that fuses textual content, metadata (headers, senders, domains), and embedded resources (URLs, attachments). A Cognitive Graph Neural Network enhanced by a Large Language Model (LLM) performs context-aware reasoning across these sources to identify coordinated spam campaigns. Most critically, EvoMail engages in an adversarial self-evolution loop: a ''red-team'' agent generates novel evasion tactics---such as character obfuscation or AI-generated phishing text---while the ''blue-team'' detector learns from failures, compresses experiences into a memory module, and reuses them for future reasoning.Extensive experiments on real-world datasets (Enron-Spam, Ling-Spam, SpamAssassin, and TREC) and synthetic adversarial variants demonstrate that EvoMail consistently outperforms state-of-the-art baselines in detection accuracy, adaptability to evolving spam tactics, and interpretability of reasoning traces. These results highlight EvoMail's potential as a resilient and explainable defense framework against next-generation spam and phishing threats.

  • Open Access

    MCAH-ACO: A Multi-Criteria Adaptive Hybrid Ant Colony Optimization for Last-Mile Delivery Vehicle Routing

    by De-Tian Chu, Xin-Yu Chen, Lin-Yuan Bai, Hai-Feng Ling

    Last-mile delivery routing has become a pressing challenge as e-commerce volumes continue to surge. Most existing vehicle routing models focus on minimizing just one criterion---travel distance or time---while overlooking social and environmental costs. How can we balance these competing factors? This paper present MCAH-ACO, a Multi-Criteria Adaptive Hybrid Ant Colony Optimization algorithm that treats delivery routing as a Multiple Traveling Salesman Problem (MTSP). Our approach is distinguished by three mechanisms. First, multi-criteria pheromone decomposition maintain separate pheromone matrices for each objective. Second, an adaptive weight balancing scheme adjust criterion weights on the fly, preventing any single factor from dominating. Third, 2-opt local search works alongside an elite archive that preserves solution diversity. The cost function capture four aspects: distance, time, social-environmental impact, and safety. We tested MCAH-ACO on real delivery data from the Greater Toronto Area. Results show 12.3% lower total cost and 18.7% fewer safety-critical events versus the strongest baseline (Max--Min Ant System), with runtime remaining competitive.

  • Open Access

    Cooperative Drone and Water Supply Truck Scheduling for Wildfire Fighting Using Deep Reinforcement Learning

    by Lin-Yuan Bai, Xin-Ya Chen, Hai-Feng Ling, Yu-Jun Zheng

    Wildfires often spread rapidly and cause significant casualties and economic losses. Firefighting drones carrying water capsules provide an efficient way for wildfire extinguishing, but their operational capabilities are limited by their payloads. This weakness can be compensated by using ground vehicles to provide mobile water supply. To this end, this paper presents an optimization problem of scheduling multiple drones and water supply trucks for wildfire fighting, which allocates burning subareas to drones, routes drones to perform fire-extinguishing operations in burning subareas and reload water between every two consecutive operations, and routes trucks to provide timely water supply for drones. To solve the problem within the limited emergency response time, we propose a deep reinforcement learning method, which consists of an encoder for embedding the input instance features and a decoder for generating a solution by iteratively predicting the subarea selection decision through attention. Computational results on test instances constructed upon real-world wilderness areas demonstrate the performance advantages of the proposed method over a collection of heuristic and metaheuristic optimization methods.


  • Memetic Optimization of Collaborative Human-UAV-Truck Search-and-Rescue Task Scheduling in Earthquakes

    by Kang-Cong Lv, Zhi-Yuan Zhang, Lin-Yuan Bai, Xun-Lin Jiang, Yu-Jun Zheng

    Unmanned aerial vehicles (UAVs) have become increasingly used in search and rescue tasks in disasters. However, there are many tasks that cannot be completed solely by UAVs; instead, they should be completed by cooperation of UAVs and human rescuers. Moreover, as battery capacity is a major limiting factor in UAV operations, using ground vehicles (trucks) to provide mobile battery swapping services is an efficient approach. To this end, this paper studies a problem of collaborative human-UAV-truck search-and-rescue task scheduling in earthquakes, where UAVs are used to quickly search for survivors who are expected to be ultimately rescued by human rescuers, while a truck serves as a mobile battery depot for UAVs, such that the survivors can be rescued as many as possible and as early as possible. To solve the problem, we propose a memetic algorithm that combines the ecogeography-based optimization metaheuristic for global exploration, adaptive local search for improving solution accuracy, and a Gaussian binary simulated annealing method for truck path planning. Numerical experiments on a set of real-world problem instances demonstrate the effectiveness and efficiency of the proposed method.


  • Open Access

    Enhanced Safety in Autonomous Driving: Integrating a Latent State Diffusion Model for End-to-End Navigation

    by De-Tian Chu, Lin-Yuan Bai, Jia-Nuo Huang, Zhen-Long Fang, Peng Zhang, Wei Kang, Hai-Feng Ling

    Ensuring safety in autonomous driving is crucial for effective motion planning and navigation. However, most end-to-end planning methodologies lack sufficient safety measures. This study tackles this issue by formulating the control optimization problem in autonomous driving as Constrained Markov Decision Processes (CMDPs). We introduce an innovative, model-based approach for policy optimization, employing a conditional Value-at-Risk (VaR)-based soft actor-critic (SAC) to handle constraints in complex, high-dimensional state spaces. Our method features a worst-case actor to ensure strict compliance with safety requirements, even in unpredictable scenarios. The policy optimization leverages the augmented Lagrangian method and leverages latent diffusion models to forecast and simulate future trajectories. This dual strategy ensures safe navigation through environments and enhances policy performance by incorporating distribution modeling to address environmental uncertainties. Empirical evaluations conducted in both simulated and real environments demonstrate that our approach surpasses existing methods in terms of safety, efficiency, and decision-making capabilities.


  • Open Access

    A Lightweight Border Patrol Object Detection Network for Edge Devices

    by Lei Yue, Haifeng Ling, Jianhu Yuan, Linyuan Bai

    Border patrol object detection is an important basis for obtaining information about the border patrol area and for analyzing and determining the mission situation. Border Patrol Staffing is now equipped with medium to close range UAVs and portable reconnaissance equipment to carry out its tasks. In this paper, we designed a detection algorithm TP-ODA for the border patrol object detection task in order to improve the UAV and portable reconnaissance equipment for the task of border patrol object detection, which is mostly performed in embedded devices with limited computing power and the detection frame imbalance problem is improved; finally, the PDOEM structure is designed in the neck network to optimize the feature fusion module of the algorithm. In order to verify the improvement effect of the algorithm in this paper, the Border Patrol object dataset BDP is constructed. The experiments show that, compared to the baseline model, the TP-ODA algorithm improves mAP by 2.9%, reduces GFLOPs by 65.19%, reduces model volume by 63.83% and improves FPS by 8.47%. The model comparison experiments were then combined with the requirements of the border patrol tasks, and it was concluded that the TP-ODA model is more suitable for UAV and portable reconnaissance equipment to carry and can better fulfill the task of border patrol object detection.


  • Open Access

    Autonomous Trajectory Planning and Control of Anti-Radiation Loitering Munitions under Uncertain Conditions

    by Linyuan Bai, Hongchuan Luo, Haifeng Ling

    As an autonomous system, an anti-radiation loitering munition (LM) experiences uncertainty in both a priori and sensed information during loitering because it is difficult to accurately know target radar information in advance, and the sensing performance of the seeker is affected by disturbance and errors. If, as it does in the state of the art, uncertainties are ignored and the LM travels its planned route, its battle effectiveness will be severely restricted. To tackle this problem, this paper studies the method of autonomous planning and control of loitering routes using limited a priori information of target radar and real-time sensing results. We establish a motion and sensing model based on the characteristics of anti-radiation LMs and use particle filtering to iteratively infer the target radar information. Based on model predictive control, we select a loitering path to minimize the uncertainty of the target information, so as to achieve trajectory planning control that is conducive to the acquisition of target radar information. Simulation results show that the proposed method can effectively complete the autonomous trajectory planning and control of anti-radiation LMs under uncertain conditions.