Affiliation:
1. Saudi Aramco, Saudi Arabia
2. Baker Hughes, United States
Abstract
Abstract
The estimation of bit wear during real-time operation plays a crucial role in bit trip planning and drilling optimization. Estimates by human learnings can be highly subjective and convoluted by changes in formation and drilling data. Conventional methods using physics-based model and supervised machine learning are time consuming and accuracy is significantly limited by the labelled data available. Moreover, those approaches do not consider the entire real-time time/depth series. In this study, we present a real-time field-validated bit agnostic wear model using unsupervised deep learning method to overcome these challenges.
The framework is of unsupervised learning and representation of LWD sub-/surface drilling data) time/depth series data to lower-dimensional representation (latent) space with reconstruction ability and facilitating the downstream task e.g., bit wear estimation. Specifically, a bi-directional Long short-term Memory-based Variational Autoencoder (biLSTM-VAE) projects raw drilling data into a latent space in which the real-time bit-wear can be estimated through classification of the incoming real time data in the latent space. The deep neural network was trained in an unsupervised manner and the bit-wear estimation is an end-to-end process, and then implemented for evaluation in a real time lateral.
The model training results had significant separation of bit-wear states in the lower dimensional latent space projected by the trained model, suggesting the feasibility of the real-time monitoring and tracking of bit wear states in the latent space. We then employed the trained deep learning model to estimate the bit wear in the real-time drilling for seven runs in a lateral. The predicted bit wear for all evaluation field runs were closely match the actual dull grade with the error smaller than 1.0. Among the seven prediction values, five of them agreed exactly with the actual field dull grading. Moreover, real time data of bits from different manufacturers and their results demonstrate the model to be bit-agnostic.
To the best of our knowledge, this is the first field implementation of AI-assisted model for the real-time bit wear estimation that is both trained in an unsupervised manner in end-to-end process and AI predicted on completely unseen time/depth series data. Moreover, commonly available real time data is selected to ensure ease of applicability. Our approach also introduces a novel method of estimating bit wear based on the tracking of its trajectory in the latent space including the memory as opposed to isolated events. This helps improve the efficiency in drilling operations and can significantly affect economics of well engineering. As compared to traditional physic-based models that have been applied to estimate the bit wear, the proposed AI model is bit agnostic and is applicable to wide range of applications for drilling optimization
Reference10 articles.
1. Abadi, Martín, Barham, Paul, Chen, Jianmin. 2016. "Tensorflow: A system for large-scale machine learning. Proc.,12th USENIX symposium on operating systems design and implementation."
2. Probabilistic Neural Network with Bayesian-based,spectral torque imaging and Deep Convolutional Autoencoder for PDC bit wear monitoring;Agostini,2020
3. The python deep learning library;Chollet,2018
4. Bi-Directional Long Short-Term Memory Variational Autoencoder forReal-Time Bit-Wear Estimation;Luu,2021
5. Hybrid Physics-Field Data Approach Improves Prediction of ROP / Drilling Performance of Sharp and Worn PDC Bits;Zhan,2021
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献