Discovering patterns within the drilling reports using artificial intelligence for operation monitoring

• Autor(a) principal: Colombo, Danilo
• Data de Publicação: 2020
• Outros Autores: Pedronette, Daniel Carlos Guimarães [UNESP], Guilherme, Ivan Rizzo [UNESP], Papa, João Paulo [UNESP], Ribeiro, Luiz Carlos Felix [UNESP], Afonso, Luis Claudio Sugi [UNESP], Presotto, João Gabriel Camacho [UNESP], Sousa, Gustavo José [UNESP]
• Tipo de documento: Artigo de conferência
• Idioma: eng
• Título da fonte: Repositório Institucional da UNESP
• Texto Completo: http://hdl.handle.net/11449/201831

In well drilling activities, the execution of a sequence of operations defined in a well project is a central task. In order to provide proper monitoring, the operations executed during the drilling procedures are reported in Daily Drilling Reports (DDRs). Technologies capable of assisting the fulfillment of such reports represent valuable contributions. An approach using Machine Learning and Sequence Mining algorithms is proposed for predicting the next operation and classifying it based on textual descriptions. Nowadays, artificial intelligence (AI) applications play a key role in digital transformation process and is a very broad area, with various branches. Machine Learning techniques provide systems the ability to automatically learn and improve from experience without explicit instructions. Sequence Mining can be broadly defined as the task of finding statistical relevant patterns between samples modeled in a sequence. In our approach, the operations reported in DDRs are analyzed by Sequence Mining algorithms for predicting the next operation, whereas Machine Learning methods are used for automatically classifying the operations according to predefined ontologies based on textual descriptions. The proposed approach was experimentally validated using a real-world dataset composed of drilling reports with approximately 90K entries. Various sequence prediction algorithms are considered, more specifically: CPT+(Compact Prediction Tree+), DG (Dependency Graph), AKOM (All-k Order Markov), LZ78, PPM (Prediction by Partial Matching), and TDAG (Transitional Directed Acyclic Graph). For the classification tasks, approaches based on word embeddings and CRF (Conditional Random Fields) are exploited. Experimental results achieved high-accurate results, of 89% for the classification task. The promising results indicate that such strategies can be successfully exploited in the evaluated scenarios. Additionally, the positive results also encourage the investigation of its use in other oil and gas applications, since the reports organized through chronological order consists of a common scenario. The main contribution to the oil and gas industry consists of using artificial intelligence strategies in tasks associated with DDRs, saving human efforts and improving operational efficiency. Although the Sequence Mining and Machine Learning algorithms have been extensively used in different applications, the novelty of our work consists in the use of such approaches on the tasks of extracting useful information from the DDRs.