Machine Learning Microservice for Identification of Accident Predecessors

Abstract

Drilling accidents prediction is the important task in well construction. Drilling support software allows observing the drilling parameters for multiple wells at the same time and artificial intelligence helps detecting the drilling accident predecessor ahead the emergency situation. We present machine learning (ML) algorithm for prediction of such accidents as stuck, mud loss, fluid show, washout, break of drill string and shale collar. The model for forecasting the drilling accidents is based on the "Bag-of-features" approach, which implies the use of distributions of the directly recorded data as the main features. Bag-of-features implies the labeling of small parts of data by the particular symbol, named codeword. Building histograms of symbols for the data segment, one could use the histogram as an input for the machine learning algorithm. Fragments of real-time mud log data were used to create the model. We define more than 1000 drilling accident predecessors for more than 60 real accidents and about 2500 normal drilling cases as a training set for ML model. The developed model analyzes real-time mud log data and calculates the probability of accident. The result is presented as a probability curve for each type of accident; if the critical probability value is exceeded, the user is notified of the risk of an accident. The Bag-of-features model shows high performance by validation both on historical data and in real time. The prediction quality does not vary field to field and could be used in different fields without additional training of the ML model. The software utilizing the ML model has microservice architecture and is integrated with the WITSML data server. It is capable of real-time accidents forecasting without human intervention. As a result, the system notifies the user in all cases when the situation in the well becomes similar to the pre-accident one, and the engineer has enough time to take the necessary actions to prevent an accident.

Making the black-box brighter: Interpreting machine learning algorithm for forecasting drilling accidents

“…Step 4. Plot the highlighted 𝜏 segments and accident probabilities Figure 2: General scheme for interpretation of Bag-of-features model, used for drilling accident forecasting problem (Gurina et al, 2022b(Gurina et al, , 2021.…”

“…Since the current study is mostly aimed at studying the interpretability techniques for black-box machine learning models, in this section we describe methods that are used nowadays to interpret forecasting black-box models and assess the quality of obtained interpretability. The full literature review related to the forecasting of drilling accidents can be found in papers (Gurina et al, 2021(Gurina et al, , 2022b, while here we mostly focus on the review of the system that provides forecast and explanation why it was made.…”

“…This section provides a brief overview of the Bag-of-features model, used for forecasting drilling accidents in realtime and based on the Bag-of-features approach. As was mentioned in Section 1, the full description of the Bag-of-features model can be found in papers (Gurina et al, 2022b(Gurina et al, , 2021, while the general scheme of the model is presented in Figure 1.…”

“…Figure 1: General scheme of Bag-of-features model, used for drilling accident forecasting problem solving (Gurina et al, 2022b(Gurina et al, , 2021.…”