This paper outlines the essential steps taken in performing structural reliability calculations during the process of laying out a risk-based inspection program. The structural reliability analysis described in this paper essentially takes the deterministic finite element method (FEM) stress/fatigue analysis results, coupled with uncertain degradation mechanisms (e.g. corrosion rate, crack propagating parameters, etc.), and tracks the time-varying structural reliability index of the structural components under consideration. This can then be used to determine the timing for inspection of structural components. For the assessment of structural strength, an efficient and straightforward method is proposed to calculate the time-variant reliability index. This method is verified by an example problem and compared to the random process first-passage reliability solutions. Load combination issue is briefly discussed, in which an approach stems from the ABS Dynamic Loading Approach (DLA) coupled with concepts from Turkstra’s rule. This proposed simplistic load combination approach is verified through an example problem in which the result is compared to the solution calculated from a more sophisticated approach. Establishment of target reliability levels is also briefly discussed. For the assessment of fatigue behavior for welded connections, both S-N curve based and fracture mechanics based reliability methods are discussed. Their usefulness will be discussed in terms of both inspection interval as well as selecting the proper sampling percentage of connections to inspect. Statistical correlation among a group of similar connections is discussed to assist the selection of appropriate locations in the population of the aforementioned sampling. The usefulness of fatigue reliability analysis is also demonstrated by an example problem.

This paper describes a holistic, risk-based approach to asset integrity management (AIM). The approach outlined in this paper is referred to as risk-based maintenance. This approach is based on proven risk assessment and reliability analysis methodologies, as well as the need to have appropriate management systems. Combining these tools and management systems provides a holistic approach to managing asset integrity, rather than a seemingly random application of analysis approaches and improvement initiatives. The information in this paper will benefit plant personnel interested in implementing an integrated AIM program or advancing their current AIM program to the next level.

No abstract

Accurate prediction of machinery failure is a challenging and important task for the offshore industry. Early diagnosis and prognosis of machinery failure has become a necessity to drive high levels of safety and performance in oil and gas operations. Prognostics enabled by data-driven machine learning techniques offers new insights into the health and performance of machinery and thereby improves operational efficiency. Advances in this topic are important because of the challenging nature of prognostics and the large degree of uncertainty that is associated. In this work, we demonstrate a practical approach to build and perform robust predictive machine learning models that are capable of detecting critical machinery failure early. In addition, a review of recent state-of-art machine learning approaches employed in modeling of machinery failure prediction is presented. Predictive models discussed here are based on various supervised machine learning techniques as well as on different input features. A variety of these newer algorithms include baggings, boosting, support vector machines, ramdon forest, etc., all of which have been widely applied in predictive models. Although it is evident that machine learning methods can improve our understanding of failure progression, appropriate validation schemes are necessary to evaluate machine learning models to assist in effective and accurate decision making. Therefore, we illustrate different levels of evaluation methodologies that can be trusted for these methods to be considered in the everyday operational practice. The machine learning models mentioned in this manuscript is then applied to a case of bearing failure on wind turbine gearbox. A machine learning model by utilizing XGBoost is proposed for prediction of remaining useful life with improved accuracy. This paper could also serve as a guidline to assess machine learning data analytic methods for prognostics relevant to common machinery types on offshore assets.

fax 01-972-952-9435. AbstractAs the FPSO fleet matures, the challenge of how to more rationally and efficiently manage the life-cycle integrity of an FPSO attracts more attention. Risk and reliability based approaches are regarded as very powerful tools to help optimize an integrity program and offer flexibility in helping better manage the integrity management regime.ABS has developed a multi-level risk-based inspection methodology ranging from simplified deterministic approaches using standard design analysis up to sophisticated probabilistic approaches. Each approach has various levels of usefulness ranging from the definition of critical areas for a single inspection campaign up to the generation of an optimized inspection schedule and work scope covering the entire lifecycle of a particular unit. These RBI methodologies have been successfully applied in inspection planning for several FPSO installations. A wide range of engineering analyses were involved, depending on the needs of individual projects and client requests, inspection objectives, condition of the asset, availability of design analysis information, etc.In line with the various levels of assessment defined above, ABS has also started developing an automated RBI assessment tool which is discussed at the end of this paper.