计算机科学
循环(流体动力学)
领域(数学)
人工智能
井漏
体积热力学
抖动
模式识别(心理学)
数据挖掘
机器学习
计算机视觉
数学
工程类
噪声整形
纯数学
量子力学
物理
航空航天工程
钻井液
钻探
机械工程
作者
Weifeng Sun,Weihua Li,Dezhi Zhang,Kai Liu,Wang Chen,Yongshou Dai,Weimin Huang
标识
DOI:10.1016/j.geoen.2023.211660
摘要
In order to improve the lost circulation risk recognition accuracy of artificial intelligence (AI) based models using limited number of data samples, a lost circulation monitoring method involving data augmentation and Bi-directional Long Short-Term Memory (Bi-LSTM) network is proposed. Firstly, the collected lost circulation data samples including pit volume (PIT), flow-out rate (FOR), pump speed (PS) and standpipe pressure (SPP) data sequences as elements are augmented using percentage scaling and random dithering to produce a dataset with increased number of samples. Then, a Bi-LSTM-based lost circulation monitoring model, which can explore both the past and future information of the input data, is established and trained with the augmented dataset. Finally, the obtained lost circulation monitoring model is applied to the PIT, FOR, PS, and SPP field data sequences for risk monitoring. A collected field lost circulation dataset with 2000 sample points was used to train and test the recognition performance of the proposed method, the test results demonstrate that the recognition accuracies of the LSTM model and Bi-LSTM model without data augmentation are 84% and 89%, respectively. After data augmentation is applied, the recognition accuracy of the Bi-LSTM model is improved to 93%.
科研通智能强力驱动
Strongly Powered by AbleSci AI