Objectives/Scope: Traditionally Daily Drilling Reports were used as the main source of the data input for Invisible Lost Time calculations with great success. One observed drawback was that the hidden causes that lead to invisible lost time were not identified. This paper outlines the framework to incorporate Real-Time high frequency rig-floor sensor data in the invisible lost time calculation, identification, and reduction exercises. This approach breaks down, downhole activities into smaller, measurable, discrete sub-activities that are measured, benchmarked, and targeted for improvement. Methods, Procedures, Process: This paper covers three major downhole activities: Drilling, Tripping, and Running Casing, breaking them down into thirty-three sub-activities. A three-year drilling activities dataset is categorized into comparable groups based on drilling rig capabilities and formation characteristics. The sub-activities are then presented on a histogram with the average, P10, P50, and P95 values of each sub-activity determined based on a pre-accepted category. This benchmarking process enabled the generation of the targets that are currently being used for calculating and understanding the invisible lost time causes in the operation. Results, Observations, Conclusions: revious reporting would simply identify the phase of operation that is creating the invisible lost time. Complementing the existing Invisible Lost Time calculation model with Real-Time data has enabled the understanding of the operational steps that lead to sub-optimal performance. A good example of this would be the drilling phase. The new approach is able to pinpoint the steps in the drilling phase that generates the invisible lost time, for example when post-connection times are excessively exceeding historical norms. Another advantage is the ability to run the report in the middle of the activity and highlight that the current rate of execution is not optimal. This enables the supervisor to investigate the situation and propose solutions to improve performance on the ongoing activity. In addition, this approach has been used successfully for ranking the performance of casing running service companies and helping in the decision-making process for awarding new contracts.

Drilling, tripping and running casing represents approximately fifty percent of the total well time, where the connection time KPI is the common performance indicator for those operations. Therefore, enabling real-time monitoring on drilling weight to weight and tripping connection time KPI's will add significant value through well time saving. The objective of this paper is to discuss the detailed implementation of machine learning to automate the detection and computation of the KPI's in real-time. The existing method for drilling performance monitoring requires extensive human data interpretation to calibrate the parameters required in this process. To overcome the complexity and reduce the human interaction, the automated Rig state and Drill state activity level were implemented based on Machine Learning (ML). The algorithm learns from the previous connections, drilling stand or tripping conditions to define the thresholds necessary to determine the current rig operation. With automatic rig activity detection, statistics to monitor the performance can be done in a systematic way. As a result, consistency of computation allows to compare performance and to improve it. The automated process using Machine Learning (ML) delivered consistent and powerful real time KPI computation, this helped to eliminate any human interpretation. This enabled real-time performance analysis delivery to rig site operations team. The machine learning model results were compared with the existing performance engine output and the comparison showed accurate and identical rig state/drill state detection and KPI's computation. The initial potential time saving with the implementation of this methodology is estimated around 15%, this was achieved through performance improvement on drilling and tripping connection KPI's. Further potential time saving can be achieved by extending the concept to track casing and liner running performance monitoring and other relevant drilling activities. This project introduces novel Rig state detection and KPI computation based on automated machine leaning model, demonstrating the benefits through improvement in drilling performance. The approach allows operators to mitigate data issues related with human interpretation and demonstrate real-time, high frequency and high-accuracy KPI's to significantly improve the drilling performance.