An online hybrid prediction model for mud pit volume in the complex geological drilling process. (June 2021)

• Record Type: Journal Article
• Authors: Zhou, Yang; Chen, Xin; Fukushima, Edwardo F.; Wu, Min; Cao, Weihua; Terano, Takao
• Is Part Of: Control engineering practice. Volume 111(2021)
• Publication Date: 2021-06
• Subjects: Mud pit volume -- Time series -- Support vector regression -- Back propagation neural network -- Long short-term memory neural network; Automatic control -- Periodicals; 629.89
• DOI: 10.1016/j.conengprac.2021.104793
• Languages: English
• ISSNs: 0967-0661

Abstract

Abstract: The mud pit volume (MPV) model is of great importance in evaluating the bottom hole pressure (BHP). In this paper, an online hybrid model is developed to predict MPV considering the drilling characteristics of data pollution, multi-variable, strong nonlinearity, and time series characteristics. First, the mutual information and fast Fourier transform method are introduced to filter data noises and determine the model inputs. Then, back propagation neural network (BPNN) method and support vector regression (SVR) method are used to establish the submodels, and the submodels are combined based on three evaluation criteria. After that, the combination model is fine-tuned according to the time series trends of MPV based on the long short-term memory neural network (LSTMNN). Finally, a modified sliding window method is developed to update the hybrid model constructed by SVR, BPNN and LSTMNN. The simulation results based on actual drilling data show that the online hybrid model has higher accuracy than other prediction models, and the online hybrid model can follow the time series characteristics of MPV, which validates the effectiveness of the developed model. Highlights: High frequency noises in drilling data are filtered. An online hybrid model with time series characteristics is developed to predict mud pit volume. A modified sliding window method is developed to update the hybrid prediction model. The developed prediction model lays a foundation for the optimization of drilling process.