arXiv subjects

Zhongliang Li

Publications and source records attributed to Zhongliang Li.

8 recordsLinked to original sources

arXiv2026

Unlocking Directional Radiation in Pinching-Antenna Systems: Geometry-Aware Design and Experimental Verification

Pinching-antenna systems (PASS) have recently attracted growing interest as a flexible architecture for creating "last-meter" line-of-sight wireless links through dielectric waveguides and reconfigurable radiation points. While modeling pinching antennas (PAs) as isotropic point radiators has enabled tractable analyses and demonstrated the performance gains of PASS, their practical radiation characteristics remain underexplored. This article investigates PASS from the perspective of PA geometry. Starting from the physical coupling principle, we explain why PA shape affects the induced polarization current and incorporate directional gain into the channel model. The full-wave simulations are conducted to show how different PA geometries and orientations reshape the internal field distribution and far-field radiation pattern. A 60 GHz prototype video transmission experiment is further presented to demonstrate the link-level impact of changing PA states. Finally, promising applications enabled by geometry-aware directional PASS are highlighted.

eess.SY↗

arXiv2026

An advanced 1D physics-based model for PEM hydrogen fuel cells with enhanced overvoltage prediction

A one-dimensional, dynamic, two-phase, isothermal model of proton exchange membrane fuel cell systems using a finite-difference approach has been developed. This model balances the simplicity of lumped-parameter models with the detailed accuracy of computational fluid dynamics models, offering precise internal state descriptions with low computational demand. The model's static behavior is validated experimentally using polarization curves. In addition, a novel physical parameter, the limit liquid water saturation coefficient ($s_{\rm lim}$), is introduced in the overvoltage calculation, replacing the traditional limit current density coefficient ($i_{\rm lim}$). This new parameter links the voltage drop at high current densities to the amount of liquid water present in the catalyst layers and the operating conditions of the fuel cell. Additionally, it has been observed that $s_{\rm lim}$ is influenced at least by the gas pressure applied by the operator. This newly established link is promising for optimizing the control and thereby improving the performance of fuel cells.

eess.SY↗

arXiv2026

AlphaPEM: an open-source dynamic 1D physics-based PEM fuel cell model for embedded applications

The urgency of the energy transition requires improving the performance and longevity of hydrogen technologies. AlphaPEM is a dynamic one-dimensional (1D) physics-based PEM fuel cell system simulator, programmed in Python and experimentally validated. It offers a good balance between accuracy and execution speed. The modular architecture allows for addition of new features, and it has a user-friendly graphical interface. An automatic calibration method is proposed to match the model to the studied fuel cell. The software provides information on the internal states of the system in response to any current density and can produce polarization and EIS curves. AlphaPEM facilitates the use of a model in embedded conditions, allowing real-time modification of the fuel cell's operating conditions.

eess.SY↗

arXiv2024

A Critical Review of Proton Exchange Membrane Fuel Cells Matter Transports and Voltage Polarisation for Modelling

Technologies based on the use of hydrogen are promising for future energy requirements in a more sustainable world. Consequently, modelling fuel cells is crucial, for instance, to optimize their control to achieve excellent performance, to test new materials and configurations on a limited budget, or to consider their degradation for improved lifespan. To develop such models, a comprehensive study is required, encompassing both well-established and the latest governing laws on matter transport and voltage polarisation for Proton Exchange Membrane Fuel Cells (PEMFCs). Recent articles often rely on outdated or inappropriate equations, lacking clear explanations regarding their background. Indeed, inconsistent understanding of theoretical and experimental choices or model requirements hinders comprehension and contributes to the misuse of these equations. Additionally, specific researches are needed to construct more accurate models. This study aims to offer a comprehensive understanding of the current state-of-the-art in PEMFC modeling. It clarifies the corresponding governing equations, their usage conditions, and assumptions, thus serving as a foundation for future developments. The presented laws and equations are applicable in most multi-dimensional, dynamic, and two-phase PEMFC models.

eess.SY↗

arXiv2023

A Lifetime Extended Energy Management Strategy for Fuel Cell Hybrid Electric Vehicles via Self-Learning Fuzzy Reinforcement Learning

Modeling difficulty, time-varying model, and uncertain external inputs are the main challenges for energy management of fuel cell hybrid electric vehicles. In the paper, a fuzzy reinforcement learning-based energy management strategy for fuel cell hybrid electric vehicles is proposed to reduce fuel consumption, maintain the batteries' long-term operation, and extend the lifetime of the fuel cells system. Fuzzy Q-learning is a model-free reinforcement learning that can learn itself by interacting with the environment, so there is no need for modeling the fuel cells system. In addition, frequent startup of the fuel cells will reduce the remaining useful life of the fuel cells system. The proposed method suppresses frequent fuel cells startup by considering the penalty for the times of fuel cell startups in the reward of reinforcement learning. Moreover, applying fuzzy logic to approximate the value function in Q-Learning can solve continuous state and action space problems. Finally, a python-based training and testing platform verify the effectiveness and self-learning improvement of the proposed method under conditions of initial state change, model change and driving condition change.

cs.AI↗

arXiv2023

Data-driven prognostics based on time-frequency analysis and symbolic recurrent neural network for fuel cells under dynamic load

Data-centric prognostics is beneficial to improve the reliability and safety of proton exchange membrane fuel cell (PEMFC). For the prognostics of PEMFC operating under dynamic load, the challenges come from extracting degradation features, improving prediction accuracy, expanding the prognostics horizon, and reducing computational cost. To address these issues, this work proposes a data-driven PEMFC prognostics approach, in which Hilbert-Huang transform is used to extract health indicator in dynamic operating conditions and symbolic-based gated recurrent unit model is used to enhance the accuracy of life prediction. Comparing with other state-of-the-art methods, the proposed data-driven prognostics approach provides a competitive prognostics horizon with lower computational cost. The prognostics performance shows consistency and generalizability under different failure threshold settings.

cs.LG↗

arXiv2021

Learning from Pseudo Lesion: A Self-supervised Framework for COVID-19 Diagnosis

The Coronavirus disease 2019 (COVID-19) has rapidly spread all over the world since its first report in December 2019 and thoracic computed tomography (CT) has become one of the main tools for its diagnosis. In recent years, deep learning-based approaches have shown impressive performance in myriad image recognition tasks. However, they usually require a large number of annotated data for training. Inspired by Ground Glass Opacity (GGO), a common finding in COIVD-19 patient's CT scans, we proposed in this paper a novel self-supervised pretraining method based on pseudo lesions generation and restoration for COVID-19 diagnosis. We used Perlin noise, a gradient noise based mathematical model, to generate lesion-like patterns, which were then randomly pasted to the lung regions of normal CT images to generate pseudo COVID-19 images. The pairs of normal and pseudo COVID-19 images were then used to train an encoder-decoder architecture based U-Net for image restoration, which does not require any labelled data. The pretrained encoder was then fine-tuned using labelled data for COVID-19 diagnosis task. Two public COVID-19 diagnosis datasets made up of CT images were employed for evaluation. Comprehensive experimental results demonstrated that the proposed self-supervised learning approach could extract better feature representation for COVID-19 diagnosis and the accuracy of the proposed method outperformed the supervised model pretrained on large scale images by 6.57% and 3.03% on SARS-CoV-2 dataset and Jinan COVID-19 dataset, respectively.

eess.IV↗

arXiv2017

Slim Embedding Layers for Recurrent Neural Language Models

Recurrent neural language models are the state-of-the-art models for language modeling. When the vocabulary size is large, the space taken to store the model parameters becomes the bottleneck for the use of recurrent neural language models. In this paper, we introduce a simple space compression method that randomly shares the structured parameters at both the input and output embedding layers of the recurrent neural language models to significantly reduce the size of model parameters, but still compactly represent the original input and output embedding layers. The method is easy to implement and tune. Experiments on several data sets show that the new method can get similar perplexity and BLEU score results while only using a very tiny fraction of parameters.

cs.CL↗