Artificial neural network model based on improved VMD algorithm to monitor sand mass flow rate in natural gas pipeline

• Published in: Measurement : journal of the International Measurement Confederation Vol. 254; p. 117887
• Main Authors: Jia, Huiqin, Jiang, Jingui, Li, Fei, Si, Zechen, Zhang, Yuhao, Zhao, Jiaxuan, Sun, Zhimeng
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.10.2025
• Subjects: Artificial neural network (ANN); Improved slime mould algorithm (ISMA); Kernel principal component analysis (KPCA); Sand mass flow rate; Variational modal decomposition (VMD); Variational modal decomposition (VMD); Artificial neural network (ANN); Kernel principal component analysis (KPCA); Improved slime mould algorithm (ISMA); Sand mass flow rate
• ISSN: 0263-2241
• DOI: 10.1016/j.measurement.2025.117887

•Improved slime mould algorithm improves search, speeds signal denoising convergence.•Improved variational modal decomposition algorithm enhances the denoising effect and adaptability of sand signals.•Kernel principal component analysis selects features for sand flow rate prediction.•Improved slime mould algorithm optimized artificial neural network effectively predicts sand flow rate in natural gas pipeline. Sand production has caused serious harm to the long-term production of oil and gas wells. In order to accurately monitor the sand production, this paper proposes an ANN model based on the improved VMD algorithm to monitor sand mass flow rate. In the monitoring of sand mass flow rate in natural gas pipelines, this paper begins by employing the wavelet time–frequency analysis method to analyze the sand signal. Subsequently, the improved VMD method is utilized to denoise and extract features from the sand signal. Finally, KPCA is applied to reduce the dimensionality of the sand signal features. The results from the laboratory platform demonstrate that the fuzzy entropy, mean square frequency, and peak factor can effectively predict sand mass flow rate as feature inputs to the ISMA-ANN model. This experimental result provides a reliable and efficient method for real-time monitoring of sand mass flow rate in real gas well production.