The challenges with life-cycle management of an offshore asset, coupled with multi-discipline system engineering, and multiple competing project objectives provide an opportunity to seek a disruptive approach for maximizing value. The objective of this paper is to introduce ExxonMobil's new approach called intelligent Deepwater Advanced Solutions Hub (iDASH) where various engineering tools are strategically integrated to maximize value and improve decision quality utilizing advantages of latest digital technologies. Establishing a cloud-based centralized hub with engineering tools that can generate holistic solutions is a novel and disruptive approach given the unique and complex nature of large-scale development and management of deepwater resources. As the energy industry goes through a challenging situation where more complex and competing objectives exist, the proposed iDASH can provide a new and unique approach to move in the right direction by leveraging integrated tools and data-driven technologies. Offshore developments require a wide range of expertise areas including reservoir, wells, flow assurance, subsea, flowlines, risers, topsides, marine, geotechnical, costing, and project economics. Key challenges to asset life-cycle management include uncertainty from subsurface, limited number of alternative concepts, slow evaluation turn-around time, inability to integrate processes across multiple disciplines, and non-streamlined data transfer among different stages of a project. The iDASH approach proposes solutions by emphasizing the integration of tools, continuity among different stages of a project, and cross-discipline connectivity. Logically following typical project stages, iConcept, iDesign, iOperate, and iDecom are addressed as four pillars of iDASH to ensure value maximization. Locating and integrating various engineering tools in a cloud-based centralized hub allows for cross-discipline collaboration, optimization, and faster cycles with either better solutions or multiple alternative options. Progress in this space can decrease capital expenditure (CAPEX) or increase net present value (NPV), resulting in faster monetization of an asset or a shorten payback time. Specific use cases and proofs of concept with different engineering tools demonstrate the feasibility of iDASH and value maximization. Specifically, a trade-space analysis for improving decision quality seeking an optimal concept is demonstrated as an iConcept tool. A riser optimization case is demonstrated as an iDesign tool. A mooring integrity checker is illustrated as an iOperate tool. Results validate that challenges in asset life-cycle management can be overcome and that the proposed disruptive approach offers quick, logical, strategic, and insightful means for managing the value maximization of an asset.

The objective of this study is to develop a data-driven machine learning based tool to estimate the FPSO topsides weight. The data were collected from public sources including IHS, news and magazines, covering world-wide active FPSO geographic locations, topsides weights, and their production throughput. One of the challenges is that the size of the dataset is less than 200 data points, largely due to the limited total number of FPSOs worldwide. Another challenge is that there are missing values for gas production, as such, imputation of missing values becomes necessary. In this study, data imputation was conducted by incorporating geographic information and physics guided feature engineering, through which the imputation is more accurate compared to simple imputers. For machine learning algorithms, polynomial regression was first evaluated as the baseline model and various machine learning models were built and compared with the baseline, such as Gaussian process regressor, random forest, neural network, and natural gradient boosting, with the purpose of identifying the most accurate one. To solve the overfitting issue caused by the small size of the dataset, several strategies have been investigated and compared, such as k-fold cross validation, regularization and extensive hyper-parameter tuning via Bayesian optimization algorithm based on the Hyperopt library. Among all the machine learning models, it is found that the natural gradient boosting method is the best performer with a mean absolute percentage error (MAPE) of 24% on the blind testing data, which is 35% lower than the baseline model. Shapley Additive exPlanations (SHAP) analysis was also implemented for model interpretation and gas production was found to be the most influential feature. The trained gradient boosting model was deployed to an internal web application in which users could get a quick estimation of FPSO topsides weight by providing three features: gas production, oil production and water depth. The 2D and 3D cross plots with historic data and predicted value are also provided in the web-app for better results visualizations. The novelty of this paper is to develop a data-driven machine learning tool for FPSO topsides weight estimation on an early stage of a project, which can serve as an independent alternative to the traditional empirical based approaches to help pre-design the facilities and estimate the cost. In the back-end, the best machine learning model was identified, along with the best imputation strategy based on a physics guided feature engineering approach. In the front-end, a web application was developed for an interactive estimation of FPSO topsides weight. With continuous enrichment and validation of the collected data, the machine learning approach can serve as a trustworthy fast and early estimation for FPSO topsides weight.

The key to finding the highest-value concept in deepwater full-field development is by making high-quality decisions during the Concept Select stage of a project. One of the critical elements to achieve this is by considering a broad range of conceptual alternatives and evaluating them rapidly, providing timely feedback, and facilitating an exploratory learning process. However, concept-select decisions are challenged by competing objectives, significant uncertainties, and many possible concepts. Further, deepwater full-field developments require strong connectivity and interfaces across multiple disciplines, which include reservoir, wells, drilling, flow assurance, subsea, flowlines, risers, topsides, metocean, geotechnical, marine, costing, and project economics. Key challenges to the current methodology include a lack of capacity to consider multiple concepts, slow evaluation turn-around for each concept generated, continuous evaluation and revisions with new data and information, lack of ability to integrate processes across multiple disciplines, and poor risk management driven by technical/commercial uncertainties and unavailable data. This paper addresses these challenges by combining concepts from the Decision Quality (DQ) framework and FLOCO® (Field Layout Concept Optimizer), which is a metaheuristic model-based system-engineering software, to efficiently identify the highest value field development concepts among several possible alternatives. This novel approach applies a new framework to an offshore deepwater full-field development. Specifically, we explore the trade-space, evaluate the trade-offs between risk and reward, perform integrated techno-economic analysis, and identify the best concepts. Key outputs are the identification of development concepts that meet the given constraints and functional requirements for further optimization, while eliminating those that do not meet such requirements. The results demonstrate that the challenges in the current Concept Select phase can be simplified and that the proposed approach offers a quick, logical, and insightful means of selecting the highest-value concept. The case study demonstrates that the proposed improvement to the concept-select stage of deepwater full-field development process can lead to significantly improved project economics, as it fully explores the decision-space, key uncertainties, multiple technically feasible concepts, and key performance indicators such as net present value (NPV) and capital expenditures (CAPEX). This paper addresses the development of economic oil and gas projects through decision making enhanced by rapid digital prototyping and analysis. The integration of Decision Quality methodologies with systems-engineering decision-support tools is novel and is likely to become more important as the industry explores and develops more complicated targets in the future.

To facilitate development of future deeper water assets, riser and pipeline designs using current X65 carbon steel requires increased wall thicknesses to manage the demand from large tensile loads. This increase in wall thickness is due to the weight of the pipe body and the fatigue performance at the hang-off and the touch-down point for steel catenary risers (SCR) and steel lazy wave risers (SLWR). The increased wall thickness poses challenges for fabrication, design, installation and project execution due to the single side welding of thick pipe. Increasing the steel grade from the current X65 to X80 or higher strength grade could reduce the pipe wall thickness and provide potential cost savings from total tonnage and is therefore considered as a potential alternative for deeper water steel riser applications. However, it is challenging to meet the hardness acceptance criteria (i.e. 250 HV10) as per DNV-ST-F101 for the higher strength steel weldment, particularly for sour service. The objective of this study was to understand the effect of hardness on sulfide stress cracking (SSC) resistance of X80 line pipe base material and weldment in sour service environments. A 323.9 mm OD × 25.4 mm WT seamless quenched and tempered X80 line pipe was used for this study. Coupons were extracted from the pipe and then heat-treated by welding simulator (Gleeble™). Implementing controlled cooling, hardness values ranging from 270 to 350 HV10 were achieved, and representing the heat affected zone (HAZ) hardness. Four point bend SSC test were performed on coupon halves as per NACE TM-0316, loaded to 80% actual yield strength (AYS) and tested for 30 days in selected NACE Region 2 and 3 environments as specified in NACE MR0175/ISO 15156-2. Coupons showed no indication of SSC cracking for the samples with measured hardness values of ∼320 HV10 in the selected NACE Region 2 and 3 environments.