Hybrid method based on particle filter and NARX for real-time flow rate estimation in multi-product pipelines. (April 2020)

• Record Type: Journal Article
• Authors: He, Lei; Wen, Kai; Wu, Changchun; Gong, Jing; Ping, Xie
• Is Part Of: Journal of process control. Volume 88(2020)
• Page Start: 19
• Page End: 31
• Publication Date: 2020-04
• Subjects: Multi-product pipelines -- Friction coefficient calibration -- Particle filter -- NARX -- Multi-objective optimisation; Process control -- Periodicals; Fabrication -- Contrôle -- Périodiques; Process control; Periodicals; Electronic journals; 660.281
• DOI: 10.1016/j.jprocont.2020.02.004
• Languages: English
• ISSNs: 0959-1524

Abstract

Highlights: A hybrid method integrating data driven method and model driven method is proposed to improve the estimation performance of on line flow rate. A lumped parameter method to reduce the difference between the actual operation state and theoretical model has been proposed. T he particle filter method combing with on line parameter calibration technique based on multi objective optimization model has been adopted to deal with measurement noise and asynchrony of sampling period. The proposed approach successfully estimate the real time flow rate in both normal an d abnormal operation conditions by adopted on line friction calibration method and local NARX model The robustness and effective ness of proposed hybrid method is verified by comparing with data driven methods and model driven methods in different operation conditions. Abstract: Real-time flow estimation plays a vital role in multi-product pipeline operations, and the accuracy of real-time flow estimation is affected by noise interference and instrument accuracy and cannot be performed by direct observation of flow meter. Pipeline flow models based on the first principle method are established and employed as soft sensors of pipeline real-time flow rate. However, these models are validated by the controlled experimental pipeline, which may be ineffective regarding actual pipelines with uncertain physical parameters. In this paper, a novel approach integrating data-driven and model-driven method is proposed to estimate the flow rate of petroleum products on-line. The difference between the theoretical model and actual state of a pipeline is accounted for by the friction coefficient, and on-line calibration is achieved by solving multi-objective optimisation problems with asynchronous operation data. The flow state of the pipeline is obtained in real time by the particle filter when new pressure observations with noise become available. The estimation performance of local pressure mutation points is improved by adopting the recurrent nonlinear autoregressive neural network modelling blue of the data-driven method. The effectiveness of the proposed method is evaluated blue by examining actual data of the pipeline over a period of time. The prediction results of some other model-driven and data-driven methods are also compared to blue that of the proposed method. The results blue indicate that the proposed method improves the accuracy and reliability of the product flow rate estimations even under unforeseen operation conditions.