Artificial Intelligence Strategy Minimizes Lost Circulation Non-Productive Time in Brazilian Deep Water Pre-Salt

Abstract

Fluid losses are still today one of the most challenging problems in well construction. The scenarios faced by operators during development and exploratory campaigns in the deep water pre-salt area are characterized by natural fractures, vugs and caves. Therefore, problems related to loss of circulation are critical, increasing the non-productive time and consequently, well construction costs. Additionally, in several situations, conventional drilling limitations prevent the reaching of the well target. The present study proposes the application of a methodology to define optimum loss control material (cross-linked pills, fluid loss squeeze, bridging agents, cement), among those available for each situation, to minimize lost circulation events during drilling operations. An Artificial Intelligence strategy based on Supervised Learning was defined to generalize data collected from five hundred lost circulation events over a three years period. Human Computer Interaction principles were used on the development of an interface where the field engineer can interact with training data while having little to no Machine Learning knowledge. The use of empirical analysis and learning strategies as tools to assist the decision making process in the form of lost circulation countermeasures is described by this paper. The method was validated on data collected from several different wells in the Santos Basin, Brazil, pre-salt area. The strategy was already applied in two real cases resulting in a six days well construction time saving.

The application of deep learning algorithms to classify subsurface drilling lost circulation severity in large oil field datasets

“…Toreifi et al [36] identified the advantages of the SVM algorithm in comparison with multi-layer perceptron (MLP) for prediction of loss events in fractured formations. Cristofaro et al [37] implemented several machine learning algorithms to classify the success in applying different LCMs in a deep-water pre-salt basin offshore Brazil. They showed that by combining neural networks with an instance-based algorithm better prediction performance could be achieved.…”

Application of Artificial Intelligence Techniques in Predicting the Lost Circulation Zones Using Drilling Sensors

“…Therefore, it is arduous to predict. Therefore, many researchers applied the artificial intelligence to solve problems related to lost circulation such as Anifowose et al [32], Castillo [33], Moazzeni et al [34], Toreifi et al [35], Efendiyev et al [36], Far and Hosseini [37], Solomon et al [38], Manshad et al [39], Al-Hameedi et al [40], Alkinani et al [41], Abbas et al [42], Cristofaro et al [43], and Jahanbakhshi and Keshavarzi [44]. All these studies applied a single technique of AI to predict either the type of losses, the amount of losses, or the loss treatment, besides using many input parameters that are difficult to access in every well.…”

Artificial neural network models to predict lost circulation in natural and induced fractures

“…Lost circulation estimation is a limited topic in the literature; only a few papers were published about this topic. Some shortcomings were identified in the previous work as follows [34,36,[39][40][41][42]]:…”

“…Collected data from the literature Al-Azani et al [31] Elkatatny et al [32],Abdelgawad et al [33] Drilling fluid rheological properties Estimating rheological properties of drilling fluid Cristofaro et al [34] Mud loss Used multiple artificial intelligence methods to find the best treatment for mud losses Hoffimann et al [35] Drilling reports sentence classifications Used ANNs to develop a methodology for automating sentences in drilling reports Li et al [36] Lost circulation Used ANNs to predict lost circulation risk during drilling Al-AbdulJabbar et al [37] Formation top prediction while drilling Used ANNs to predict formation tops while drilling Elzenary et al [38] Equivalent circulation density (ECD) prediction Used ANNs to predict ECD while drilling used to verify the model, and testing data are used to test the network and assess the outcomes. Feedforward backpropagation is the process where the data are imported to the model and obtaining a desired output, then the output of the network will be compared with the actual output, the error will backpropagate, and the weights are adjusted until calibration is reached.…”