Stuck pipe is one of the leading causes of non-productive time (NPT) while drilling. Machine learning (ML) techniques can be used to predict and avoid stuck pipe issues. In this paper, a model based on ML to predict and prevent stuck pipe related to differential sticking (DS) is presented. The stuck pipe indicator is established by detecting and predicting abnormalities in the drag signatures during tripping and drilling activities. The solution focuses on detecting differential sticking risk via assessing hookload signatures, based on previous experience from historical wells. Therefore, selecting the proper training set has proven to be a crucial stage of model development, especially considering the challenges in data quality. The model is trained with historical wells with and without differential sticking issues. The solution is based on the Artificial Neural Network (ANN) approach. The model is designed to provide users, i.e., driller or monitoring specialist, a warning whenever a risk is identified. Since multi-step forecasting is used, the warning is given with enough time for the driller or monitoring specialist to evaluate which preventative action or intervention is necessary. The warnings are provided typically between 30 minutes and 4 hours ahead. The model validation includes the performance metrics and a confusion matrix. Practical cases with real-time wells are also provided. The ML model was proven robust and practical with our data sets, for both historical and live wells. The huge amount of data produced while drilling holds valuable information and when smartly fed into an Artificial Intelligence (AI) model, it can prevent NPT such as stuck pipe events as demonstrated in this paper.

Petroliam Nasional Berhad (PETRONAS) has long realized the importance of real-time drilling data. The company utilizes the technology to monitor rig site operations. An in-house real-time surveillance-monitoring centre, called the Smart Drilling Optimization Monitoring Centre (Smart DOMC), was established in 2010 within the company’s headquarters. The centre’s real-time environment was fully managed by a single service-company: data aggregated on the rig site was kept in the service company’s server, in the service company’s proprietary format, and only accessible to the drilling engineering team via the service company’s web-based application. This approach forced PETRONAS to be wholly reliant on the service-company’s own technical application and service, with no ownership or control of (the company’s) real-time data architectures, and only nominal visibility of dataflow and management. In line with the company’s Integrated Operations (IO) initiative and driven by the company’s increasing amount of operations, the availability of a standardized independent real-time data management infrastructure became a critical component in order to facilitate seamless flow of real-time technical data transparently throughout the organization, particularly within the Smart DOMC and the operation team’s disbursed workplaces. Thus, in 2014, the Real Time Well Solution was implemented. The new solution is an enterprise real-time data management solution with web-based delivery, which leverages the Wellsite Information Transfer Standard Markup Language (WITSML) as the standard format for the exchange of data. It is a secure infrastructure wholly resident within PETRONAS IT environment, which consists of clustered database servers with load balancing and failover backup servers ensuring high-availability, and capable of facilitating the flow of real-time drilling data from multiple rig sites, for the company’s domestic and international operations. It offers advanced customizable web-based features for domain experts to view real-time drilling data, through the standard web-browser and mobile devices. This paper will describe PETRONAS Real Time Well Solution and the three main challenges faced in implementing the new solution. Four case histories detailing the utilization of the WITSML infrastructure during critical well construction operations will also be reviewed. With the new System, PETRONAS is able to implement industry-accepted and non-proprietary standard in accessing real-time information, take immediate ownership and better control of data aggregated on rig sites, and integrate real-time information with existing corporate third-party applications.

PETRONAS Carigali Sdn. Bhd. (PCSB) Wells Department (formerly known as Drilling Division) has long realized the importance of drilling and delivering most cost-effective Wells for the Exploration and Development segment, by establishing the PETRONAS Digital Collaboration Centre (PDCC), which serves as a decision support platform for stakeholders to monitor, reduce, and eliminate operational and safety problems during drilling, but a piece of the puzzle is still missing - to measure the well activity performance. The earlier arrangement heavily relied on human factors such as the time-consuming logs that were completed manually by the PDCC personnel within 7 days after each completed well section. The analysis was done manually using excel spreadsheets, only focusing on major well activities, for example running the casing/liner and connection time. However, no pro-active action was taken during the operations to improve the performance. Furthermore, there is no ability to intervene with the rig performance in real time and adapt a technical limit approach. The Operational Excellence coach has limited experience and no tools to measure the technical limit, which also leads to a knowledge gap in wells performance and benchmarking areas of the drilling engineer's portfolio. The implementation of the new artificial intelligent tool, presents revolutionary management challenges for people, process, and technology within the PCSB, aligning with Well's House vision to be "World Class Well Delivery – Preferred Solutions Partner". This paper presents the business requirements and implementation of the PETRONAS Wells Performance Tool, and also describes the comparison between the previous approach and the challenges faced with implementing the new solution.

Despite many drilling technology improvements during recent years, hole cleaning remains a significant challenge. The variation of equivalent circulation density (ECD) is a symptom of borehole instability. Therefore, the ability to accurately estimate ECD is a key consideration for preventing hole cleaning problems that may lead to a stuck pipe, and well pressure management more generally. In this work, we demonstrate a Machine Learning approach to estimating downhole ECD in real-time using a deep neural network. Surface measurements that are widely available from most rigs are used as the model inputs, hence less configuration information is required relative to hydraulic simulations for pressure loss. Mean Absolute Errors of ~0.3-0.4 ppg were achieved on 16 validation wells and 7 holdout wells (blind test); these wells were independent of those in the training data. Prediction errors often reflect offsets between reference and predicted values; however, even with these offsets, trends in ECD behavior can still be captured correctly. The model shows promise for real-time ECD monitoring purposes to complement existing numerical methods and downhole tools. Beyond real-time estimation, other applications could include forecasting ECD a short time ahead to provide early indications of hole cleaning issues; case studies obtained from a real-time monitoring centre where this approach is used are presented as part of this work. The software tool was capable of detecting such symptoms in advance, giving the driller opportunity to take preventive actions to avoid a potential stuck pipe.

Drilling rate of penetration (ROP) is a major contributor to drilling costs. ROP is influenced by many different controllable and uncontrollable factors that are difficult to distinguish with the naked eye. Thus, machine learning (ML) models such as neural networks (NN) have gained momentum in the drilling industry. Existing models were either field-based or tool-based, which impacted the accuracy outside of the trained field. This work aims to develop one generally applicable global ROP model, reducing the effort needed to re-develop models for every application. A drilling dataset was gathered from exploration and development wells in both onshore and offshore operations from a variety of fields and regions. The wells were curated to have different water depths, down hole drive such as Rotary Steerable System (RSS), PDM, Standard Rotary, bit types (Mill Tooth, TCI, PDC) and inclinations (vertical or deviated). A deep neural network was used for modelling the relationship between ROP and inputs taken from real-time surface data, such as Torque, Weight-on-Bit (WOB), rotary speed (RPM), flow and pressure measurements. The performance of the ROP model was analyzed using historical data via summary statistics such as Mean Absolute Percentage Error, as well as graphical results such as residuals distributions, cumulative distribution functions of errors, and plots of ROP vs depth for independent holdout testing wells not included in the model fitting process. Analysis was done both in aggregate, and for each specific well. The ROP model was demonstrated to generalize effectively in all cases, with only minor increases in error metrics for the holdout test wells, where the Mean Absolute Percentage Error averaged across wells was ~20%, compared to 17.5% averaged across training wells. Furthermore, residuals distributions were centered close to zero, indicating low systematic error. This work proves the case for a "global" ROP prediction model applicable "out-of-the-box" to a broad set of drilling operations. A global ROP model has the potential to eliminate learning curves, reducing time and costs associated with having to develop a new model for every field. Furthermore, a model that effectively captures the relationships between parameters controllable by drillers and ROP can be used for automatically identifying drilling parameters that improve ROP. Preliminary field-testing of the ROP optimization system yielded positive results, with many examples of increased ROP realized after following drilling parameter recommendations provided by the software.