As today's oil and gas projects are becoming larger and more complex, project managers are constantly faced with a number of concerns about schedules, budgets, productivity and safety. Operating an oil and gas facility is a process where workers refer to technical specifications to obtain the right information, identify the components, and then make a decision as to the adjustment or correctness. This entire process is iterative and triggers a learning process which may lead to improved proficiency as the cycle is repeated. The inability to find the right information or sequence within a cycle can contribute to efficiency losses. Jobsite training offered by qualified organisations and associations for the oil and gas industry is very limited, and the relevant training facilities and centres that have been established or considered in the construction agenda are far from sufficient to the growing standard of operators and industry expansion. This paper, underpinned by advanced innovative visualisation technologies, proposes a framework to improve efficiency and expedite the process of developing the complex procedural skills in operating and maintaining oil and gas facilities, through identifying scientific principles of enabling complex procedural learning approaches, developing proficiency-based learning approaches and corresponding learning curricula, and appraising learning outcomes according to developed skillset taxonomy. The proposed framework is tested under the development of an innovative and immersive Augmented Reality/Virtual Reality training system, which reveals significantly pragmatic benefits in terms of boosting up workforce productivity while bringing down rework. It is also demonstrated that embedding paradigms of transformative learning process while pedagogically adopting Information Communication Technologies (ICT) in curricula development and assessment regimes can help the sector significantly improve workforce safety.

Site operations usually contain potential safety issues and an effective monitoring strategy for operations is essential to predict and prevent risk. Regarding the status monitoring among material, equipment and personnel during site operations, much work is conducted on localization and tracking using Radio Frequency Identification (RFID) technology. However, existing RFID tracking methods suffer from low accuracy and instability, due to severe interference in industrial sites with many metal structures. To improve RFID tracking performance in industrial sites, a RFID tracking method that integrates Multidimensional Support Vector Regression (MSVR) and Kalman filter is developed in this paper. Extensive experiments have been conducted on a Liquefied Natural Gas (LNG) facility site with long range active RFID system to evaluate the performance of this approach. The results demonstrate the effectiveness and stability of the proposed approach with severe noise and outliers. It is feasible to adopt the proposed approach which satisfies intrinsically-safe regulations for monitoring operation status in current practice.

Radio frequency identification (RFID) is widely used for item identification and tracking. Due to the limited communication range between readers and tags, how to configure a RFID system in a large area is important but challenging. To configure a RFID system, most existing results are based on cost minimization through using 0/1 identification model. In practice, the system is interfered by environment and probabilistic model would be more reliable. To make sure the quality of the system, more objectives, such as interference and coverage, should be considered in addition to cost. In this paper, we propose a probabilistic-based multi-objective optimization model to address these challenges. The objectives to be optimized include number of readers, interference level and coverage of tags. A decomposition based firefly algorithm is designed to solve this multi-objective optimization problem. Virtual force is integrated into random walk to guide readers moving in order to enhance exploitation. Numerical simulations are introduced to demonstrate and validate our proposed method. Comparing with existing methods, such as Non-dominated Sorting Genetic Algorithm-II and Multi-objective Particle Swarm Optimization approaches, our proposed method can achieve better performance in terms of quality metric and generational distance under the same computational environment. However, the spacing metric of the proposed method is slightly inferior to those compared methods. (C) 2017 Elsevier B.V. All rights reserved.

Scaffolding tasks are the most significant workitems in Liquefied Nature Gas (LNG) plant maintenance projects and an effective progress monitoring approach can be beneficial to stakeholders through the better control to the budget and schedule of the entire project. This research is focused on discussing findings and lesson learnt from the scaffolding progress monitoring case study of a LNG plant maintenance project. A novel approach by using Building Information Modelling (BIM) and image processing technologies to automatically estimate scaffolding progress through site photos is being developing. The case study by adopting the developing approach at a real LNG plant is currently carried on. The collected scaffolding photos have been used to iteratively improve the developing approach. The plan of the case execution is outlined and introduced in the paper including the development of an image recognition algorithm for scaffolding progress estimations and a Navisworks plug-in for productivity analysis in terms of cost and schedule. By going through site data collections, observations, data analysis and discussions with related contractors and the operator at site, the feasibility of the approach adoption and related implementation issues are identified. The feedback from industry partners can be summarized into five perspectives: (1) the complexity of scaffolding structure affects the performance of the proposed recognition algorithm a lot; (2) the proposed approach is considered reliable if the average accuracy of the progress estimation can be slightly higher than that of the conventional way; (3) a guideline for data collection process is necessary; (4) reduce site work and shift the work load back to the office is preferred and; (5) the proposed approach benefits implementation contractors the most. It is expected that these findings among the ongoing study can further adjust the development direction and identify following studies for the proposed approach in the future.

The Development of a BIM-enabled Inspection Management System for Maintenance Diagnoses of Oil and Gas Plants Hung-Lin Chi, Jun Wang, Jian Chai and Xiangyu Wang Pages 1016-1024 (2016 Proceedings of the 33rd ISARC, Auburn, USA, ISBN 978-1-5108-2992-3, ISSN 2413-5844) Abstract: Current inspection process has productivity issues, such as double handing information, time-consuming data aggregation, lack of information transparency and so on. About inspections for plant maintenance, site managers encounter difficulties in getting global pictures tracing a significant amount of inspection information at management perspective. The decision-making is based on paper-based schedules and updated progress of them, which lacks information reliability and change flexibility. The purpose of the research-industry cooperation is to determine how the integration of inspection management and Building Information Modelling (BIM) influences the performance of the plant inspection and maintenance processes. The research team developed the integration among an online inspection management portal, a mobile client application and an existing BIM platform, NavisworksTM, in this study. By using the developed system, the information of inspection tasks, including daily status reports, schedules, and task assignments, can be linked with BIM for better visualization, communication and asset life cycle management. Site managers are able to view the inspection processes through 4D simulation identifying particular inspection tasks and time duration of their interests. The outcomes of a pilot study conducted through industrial partners shows positive comments, such as reducing time spent on aggregating inspection information, going paperless and increasing real-time inspection visibility for managers to make corresponding decisions. Keywords: Building Information Modelling, Inspection, Plant life extension, Maintenance DOI: https://doi.org/10.22260/ISARC2016/0122 Download fulltext Download BibTex Download Endnote (RIS) TeX Import to Mendeley

The application of automatic as-built modeling based on laser scanning can potentially facilitate progress tracking and control in industrial plant construction. Although notable work has been conducted in the as-built modeling field, the level of automation and ability for programs to recognize semantic information is low. Semantic information, such as an installation schedule for industrial components, is vital for identifying actual construction progress. Unfortunately, as the current practices lack the ability to use robust process mapping to turn such information into corresponding as-built models, the current successful rate of recognition remains low. To fill these gaps, this article describes a new as-built modeling process for industrial components by incorporating segmentation and three-dimensional object recognition techniques from computer vision fields. Following the generation of the as-built model, the tracking process is able to identify schedule delays through deviation analysis between the as-built and four-dimensional as-designed models. The modeling process can be integrated in a concurrent construction environment, which provides precise feedback for planners and site managers to simultaneously maintain the quality of construction plans. A case study is conducted, which demonstrates that the developed process enables as-built modeling with semantic information and automatic construction progress tracking. With a certain number of as-built components of a dehydration module being captured, a successful recognition rate of over 90% is achieved. Furthermore, the processing time of the case study lies within an acceptable time period, which supports efficient progress tracking. The results show the feasibility of the developed process, which promises to save time and labor costs during construction.

As-built modelling has potentials in progress tracking and quality control in industrial plants construction. Although noted work has been conducted, there remain gaps in sophistication of automation and the extent of recognition for semantic information during the process is low. This paper developed a new modelling process for industrial components to fill in these gaps by incorporating 3D object recognition and graph matching techniques. The new process firstly groups the point cloud data of industrial components into geometric primitives. The process is also developed to recognize industrial components by matching connection graph, which is retrieved from geometric primitives, of as-built model with that of as-designed model. Furthermore, the tracking process is able to identify schedule delays by deviation analysis between as-built and as-designed model. A pilot study is carried out and proves that the developed process enables as-built modelling with semantic information and automatic construction progress tracking. Results show that the developed method is promising in saving time and labor cost during construction.