The early detection of a stuck pipe event is crucial as it is one of the major incidents resulting in nonproductive time. An ordinary supervised machine learning approach has been adopted to achieve the detection of stuck pipe in some previous studies. However, for early detection before stuck occurs with this approach, there are challenging issues such as limited stuck pipe data, various causes of stuck, and the lack of a prior exact "stuck sign" which should be a label in the training dataset. In this study, the surface drilling data is first collected from multiple agencies to enhance the training dataset. Subsequently, a supervised machine learning algorithm with ordinary binary classification methodologies, such as support vector machines and neural networks is adopted. The supervised machine learning approach presents good performance for stuck pipe event detection. However, it detects "stuck has already occurred", and it cannot effectively predict the stuck pipe because there is no exact sign for stuck pipe which is mandatory as label for training data. This study also adopts an unsupervised machine learning algorithm which employs architectures that include an autoencoder with long short-term memory, as well as a multiple prediction model to improve the expressiveness. The unsupervised machine learning process typically involves learning the features of normal activities, whereby the created model can represent only these activities. When stuck occurs or will occur, as such data are not represented by the created model, it should be detected. The performance of the early stuck pipe event detection using supervised and unsupervised machine learning approaches is analyzed, and the results demonstrate that the unsupervised machine learning approach presents a better early stuck pipe detection capability. The proposed machine learning algorithm will be further improved in the future and the prediction result will be validated through actual operation.

Abstract Pipe-sticking during drilling operations causes severe difficulties, including economic losses and safety issues. Therefore, real-time stuck-pipe predictions are an important tool to preempt this problem and avoid the aforementioned troubles. In this study, we have developed a prediction technique based on artificial intelligence, in collaboration with industry, the government, and academia. This technique was developed by combining an unsupervised learning model built using an encoder-decoder, long short-term memory architecture, with a relative error function. The model was trained with the time series data of normal drilling operations and based on an important hypothesis: reconstruction errors between observed and predicted values are higher around the time of pipe sticking than during normal drilling operations. An evaluation method of stuck-pipe possibilities using a relative error function reduced false predictors caused by large variations of drilling parameters. The prediction technique was then applied to 34 actual stuck-pipe events, where it was found that reconstruction errors calculated with the relative error function increased 0.5-10 hours prior to the pipe sticking for 17 out of 34 stuck-pipe events (thereby partly confirming our hypothesis).

Digital technology has a strong potential to transform our business process and enhance the operational efficiencies in oil and gas industries. INPEX has been exploring the applicability of various digital technologies, such as machine learning, deep learning, big data analytics, internet of things （IoT） and robotics etc. since early 2018 as part of 2018-2022 Technology roadmap strategy. This paper describes the one of current domestic projects, which aim is the visualization & optimization of the production well performance. This project has been executed to the oldest oil field in Japan, located in the Akita prefecture. The passion of the project is not only to increase hydrocarbon productivities, but also to reduce the operating expense （OPEX）/bbl. In addition, the paper includes INPEX digital transformation（DX） strategy & lessons learnt from various proof of concept （PoC） projects, which we have also conducted since the beginning of 2018.