| 郭素娜,王千慧,韩佳文,方立德.基于时空序列模型的流量计计量性能预测方法[J].电子测量与仪器学报,2026,40(6):283-289 |
| 基于时空序列模型的流量计计量性能预测方法 |
| Measurement performance prediction method for flowmetersbased on spatio-temporal sequence model |
| |
| DOI： |
| 中文关键词: 时空序列模型 性能预测 单边文丘里流量计 CFD仿真 |
| 英文关键词:spatio-temporal sequence model performance prediction unilateral venturi flowmeter CFD simulation |
| 基金项目:国家自然科学基金项目(62173122)资助 |
|
|
| Author | Institution |
| Guo Suna | 1.College of Quality and Technical Supervision, Hebei University, Baoding 071002, China; 2.Engineering Research Center of
Zero-carbon Energy Buildings and Measurement Techniques, Ministry of Education, Baoding 071002, China |
| Wang Qianhui | 1.College of Quality and Technical Supervision, Hebei University, Baoding 071002, China; 2.Engineering Research Center of
Zero-carbon Energy Buildings and Measurement Techniques, Ministry of Education, Baoding 071002, China |
| Han Jiawen | 1.College of Quality and Technical Supervision, Hebei University, Baoding 071002, China; 2.Engineering Research Center of
Zero-carbon Energy Buildings and Measurement Techniques, Ministry of Education, Baoding 071002, China |
| Fang Lide | 1.College of Quality and Technical Supervision, Hebei University, Baoding 071002, China; 2.Engineering Research Center of
Zero-carbon Energy Buildings and Measurement Techniques, Ministry of Education, Baoding 071002, China |
|
| 摘要点击次数: 48 |
| 全文下载次数: 17 |
| 中文摘要: |
| 针对传统计算流体力学(computational fluid dynamics, CFD)方法在流量计计量性能分析中计算效率低、网格依赖性强、实时性不足等问题,引入深度学习技术,构建了一种基于时空序列模型PredRNN_V2的流量计计量性能预测方法。在单边文丘里流量计内部流场预测任务中，将稳态CFD求解过程中的迭代流场演化建模为时空序列预测问题，构建了从数据获取、预处理到模型训练与评估的完整流程。选取ConvLSTM、PredRNN与PredRNN_V2进行对比，并采用均方误差(mean squared error, MSE)、结构相似性(structural similarity index, SSIM)、感知损失(learned perceptual image patch similarity, LPIPS)和峰值信噪比(peak signal-to-noise ratio, PSNR)作为评价指标对预测性能进行定量评估。结果表明，PredRNN_V2输出的MSE增长最缓，平均PSNR达36.8，显著高于PredRNN和ConvLSTM，PredRNN_V2的平均SSIM为0.92、LPIPS为0.069，表明其预测结果噪声更低、速度云图边界更加清晰，在保持较高计算效率的同时，其预测精度显著优于其他两个模型。PredRNN_V2的预测结果与仿真结果的相对误差在±5%以内，表明其在流场预测中具有可靠性和准确性。 |
| 英文摘要: |
| To the problems of low computational efficiency, strong grid dependence, and insufficient real-time performance in the traditional computational fluid dynamics (CFD) method for flowmeter performance analysis, deep learning technology was introduced to construct a flowmeter performance prediction method based on a spatiotemporal sequence model PredRNN_V2. In the task of predicting the internal flow field of a unilateral Venturi flowmeter, the iterative flow field evolution during the steady-state CFD solution process was modeled as a spatiotemporal sequence prediction problem, and a complete process from data acquisition, preprocessing to model training and evaluation was constructed. ConvLSTM, PredRNN, and PredRNN_V2 were selected for comparison, and mean squared error (MSE), structural similarity index (SSIM), learned perceptual image patch similarity (LPIPS), and peak signal-to-noise ratio (PSNR) were used as evaluation indicators to quantitatively assess the prediction performance. The results showed that the MSE output by the PredRNN_V2 model increased the most slowly, with an average PSNR of 36.8, significantly higher than PredRNN and ConvLSTM. The average SSIM of PredRNN_V2 was 0.92, and the LPIPS was 0.069, indicating that its prediction results had lower noise and clearer cloud boundary, and its prediction accuracy was significantly superior to the other two models while maintaining a high computational efficiency. The relative error between the prediction results of the PredRNN_V2 model and the simulation results was within ±5%, indicating the reliability and accuracy of the model in predicting the flow field. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
