WLWei Li

Wei Li

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Wei Li has a total of 18 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A Multi-Signal Fusion Method for Wet Gas Measurement Based on a Modified Swirl Flowmeter

    by Shiyu Yang, Chao Ma, Wei Li, Mengyu Li, Xiaoquan Gong, Lei Gong, Hanqing Chen, Ruiqi Wang, Zhongke Gao

    Accurate measurement of gas-liquid two-phase flow is critical for industrial production, yet traditional swirl flowmeters struggle to resolve the wet gas using a single frequency signal. To address this issue, we propose a multi-signal fusion measurement method based on a structurally refined swirl flowmeter. Firstly, single-phase water calibration experiments were conducted to investigate and select the structural parameters of the swirl generator (blade count, blade angle, and tail-cut angle) based on the instrument coefficient and effective measurement range. Secondly, numerical simulations were performed to reveal the physical mechanisms of liquid-phase interference by analyzing the evolution of internal static pressure and velocity fields under varying liquid volume fractions. Finally, extensive wet steam experiments were carried out using a condensation-weighing steam flow standard facility at the Yantai National Metrology Institute, covering gas-phase Froude numbers Frg from 0.71 to 3.33 and dryness fractions X from 0.9 to 1.0. The relationships among the under-reading UR coefficient, differential pressure ratio, dryness X, and gas Froude number Frg were systematically investigated. Consequently, a novel dual-parameter measurement model coupling UR and the differential pressure ratio was established. Experimental validation demonstrates that the proposed model achieves high accuracy: at a 95% confidence level, the relative errors for the dryness fraction and gas mass flow rate are controlled within 3.5% and 3.94%, respectively, with mean absolute percentage errors of 1.29% and 1.86%. This work provides an effective and highly precise approach for wet gas measurement.

  • Open Access

    A Multi-Signal Fusion Method for Wet Gas Measurement Based on a Modified Swirl Flowmeter

    by Shiyu Yang, Chao Ma, Wei Li, Mengyu Li, Xiaoquan Gong, Hanqing Chen, Ruiqi Wang, Zhongke Gao

    Accurate measurement of gas-liquid two-phase flow is critical for industrial production, yet traditional swirl flowmeters struggle to resolve the wet gas using a single frequency signal. To address this issue, we propose a multi-signal fusion measurement method based on an optimized swirl flowmeter. Firstly, single-phase water calibration experiments were conducted to optimize the structural parameters of the swirl generator (blade count, blade angle, and tail-cut angle) based on the instrumentation coefficient and effective measurement range. Secondly, numerical simulations were performed to reveal the physical mechanisms of liquid-phase interference by analyzing the evolution of internal static pressure and velocity fields under varying liquid volume fractions. Finally, extensive wet steam experiments were carried out using a condensation-weighing steam flow standard facility at the Yantai National Metrology Institute. The relationships among the under-reading UR coefficient, differential pressure ratio, dryness X, and gas Froude number Fr_g were systematically investigated. Consequently, a novel dual-parameter measurement model coupling UR and the differential pressure ratio was established. Experimental validation demonstrates that the proposed model achieves high accuracy: at a 95% confidence level, the relative errors for the dryness fraction and gas mass flow rate are controlled within 3.5% and 3.94%, respectively. This work provides an effective and highly precise approach for wet gas measurement.

  • Multiscale Cross-Channel Transformer for Parameter Measurement in Oil–Water Two-Phase Flow

    by Hanqing Chen, Mengyu Li, Ruiqi Wang, Wei Li, Bang Zhou, Zhiqiang Zhao, Zhongke Gao

    The accurate measurement of water cut and total flow rate in oil–water two-phase flow is crucial for effective oilfield management, particularly in high water-cut environments. The inherent complexity of oil–water flows, characterized by diverse flow patterns and significant nonlinear behaviors, poses substantial challenges for traditional measurement techniques. To address these challenges, we propose a multiscale cross-channel transformer (MSCC-Transformer) model designed to analyze high-frequency signals collected by a double-helix microwave sensor (DHMS). The MSCC-Transformer employs cross-channel multiscale embedding (CCME) and multiscale multihead self-attention (MMHSA) mechanisms to capture intricate interchannel dependencies and extract both fine-grained and long-term features. Moreover, a global average pooling (GAP) layer is used to integrate multiscale information, enhancing feature representation and improving measurement accuracy. The experiment determined 1.3 GHz as the optimal operating frequency for the DHMS. Additionally, dynamic experiments show that the MSCC-Transformer significantly outperforms the existing time-series models in measuring water cut and total flow rate, demonstrating its robustness and accuracy.


  • LAPNet: A lightweight adaptive patch network for measuring water cut in oil-water two-phase flow

    by Hanqing Chen, Mengyu Li, Wei Li, Bang Zhou, Zhiqiang Zhao, Ruiqi Wang, Weidong Cao, Jun Liu, Zhongke Gao


  • APMNet-Based Water-Cut Prediction Using Dual-Helical Microwave Sensing

    by Mengyu Li, Hanqing Chen, Ruiqi Wang, Bang Zhou, Wei Li, Weidong Cao, Meng Wu, Jun Liu, Zhongke Gao

    In industrial settings of high water-cut oil-water two-phase flow, accurately measuring wellhead parameters is essential for effective production monitoring and optimization in oilfields. The complexity of oil-water flow interactions and the limitations of current techniques pose significant challenges. We design a dual-helical microwave sensor, optimized through simulations for its structure and frequency. By integrating microwave transmission line technology with an innovative dual-helical design, the sensor enhances measurement stability and accuracy. Dynamic experiments are conducted to capture fluid signals under various conditions. We then propose an adaptive patch multi-feature fusion network (APMNet) for signal fusion and analysis. The dynamic patch module adjusts patch positions and sizes based on sequence variations, capturing more local changes and richer features, while the multi-feature fusion module integrates the features across the time, patch, and channel dimensions, effectively addressing issues of missing local features and noise interference. This approach achieves high-precision water cut prediction with a mean absolute percentage error (MAPE) of 2.08%. Comparative and ablation studies demonstrate the superior performance of our method in parameter prediction. Furthermore, field deployment in active oilfields confirms the practical effectiveness of the system in real-world applications.


  • A multi-task learning model with feature separation constraint for parameter prediction of gas–liquid two-phase flow

    by Xiaojing Jiang, Mengyu Li, Wei Li, Yuanzong Li, Ruiqi Wang, Hanqing Chen, Zhongke Gao

    Precise measurement of gas void fraction is crucial for the control and optimization of various industrial processes. However, due to the intricate dynamics inherent in two-phase flow, measuring gas void fraction remains a challenging task. In this work, we propose a novel deep learning model called Feature Separation Constraint Network (FSCN). First, we conduct gas–liquid two-phase flow experiments in vertical upward pipelines, where temporal and spatial signals about the fluid are collected using a four-sector distributed conductivity sensor. Second, a spatio-temporal convolutional neural network is employed to extract features, and flow pattern classification serves as an auxiliary task to provide global features for gas void fraction prediction. Subsequently, an expert network structure with a feature separation constraint is designed to enhance prediction performance. Finally, comparative analyses with competitive baselines demonstrate FSCN’s superior capability in gas void fraction estimation. A series of ablation experiments confirm the efficacy of each component.