Yonghua Li, Beijing University of Posts and Telecommunications, China
Yonghua Li, male, professor, PHD supervisor, now teaches at the School of Information and Communication Engineering, Beijing University of Posts and Telecommunications. The main research directions are: Internet of Things technology, mobile communication technology, cloud computing and big data processing technology. He has many years of research and development experience in the key technical fields of intelligent hardware, Internet of Things and communication networks, undertaken more than 30 theoretical research and engineering projects, published more than 100 papers in academic journals and conferences, and applied for 50 patents. More than 30 monographs and textbooks have been published.
Speech Title: Identification of Wellbore Flow Abnormal Working Conditions Based on Deep Learning
Artificial intelligence is widely used in the oil industry. During the process of oil production, the parameters of oil wells will change under different working conditions, which may lead to abnormal operation of oil wells. Once the abnormal operation occurs, the whole production of the oil field will be affected, so it is very important to identify the abnormal operation of the production wellbore flow. To address this problem, an end-to-end deep learning fusion (EDF) model is proposed in this paper, which combines the advantages of deep neural network (DNN), convolutional neural network (CNN), and long short-term memory (LSTM) models to identify abnormal wellbore flow conditions. The experimental results show that the EDF model has higher accuracy and area under curve (AUC) value for identifying the abnormal working conditions of wellbore flow, which can perform the task of identifying the abnormal working conditions well.