Keo-Yuan Wu

Mr. Keo-Yuan Wu

University of California Los Angeles

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 October 2020 in Sensors
Verified
Journal Article
Open access
PDF file
ZMZahra Mahmoodzadeh
Zahra Mahmoodzadeh
Keo-Yuan WuKeo-Yuan Wu
Keo-Yuan Wu
Enrique DroguettEnrique Droguett
Enrique Droguett
AMAli Mosleh
Ali Mosleh
Gas pipeline systems are one of the largest energy infrastructures in the world and are known to be very efficient and reliable. However, this does not mean they are prone to no risk. Corrosion is a significant problem in gas pipelines that imposes large risks such as ruptures and leakage to the environment and the pipeline system. Therefore, various maintenance actions are performed routinely to ensure the integrity of the pipelines. The costs of the corrosion-related maintenance actions are a significant portion of the pipeline’s operation and maintenance costs, and minimizing this large cost is a highly compelling subject that has been addressed by many studies. In this paper, we investigate the benefits of applying reinforcement learning (RL) techniques to the corrosion-related maintenance management of dry gas pipelines. We first address the rising need for a simulated testbed by proposing a test bench that models corrosion degradation while interacting with the maintenance decision-maker within the RL environment. Second, we propose a condition-based maintenance management approach that leverages a data-driven RL decision-making methodology. An RL maintenance scheduler is applied to the proposed test bench, and the results show that applying the proposed condition-based maintenance management technique can reduce up to 58% of the maintenance costs compared to a periodic maintenance policy while securing pipeline reliability.

14 March 2015 in The International Journal of Advanced Manufacturing Technology
Verified
Journal Article
Closed access
PDF file
CLChun-Ming Lin
Chun-Ming Lin
TSTe-Li Su
Te-Li Su
Keo-Yuan WuKeo-Yuan Wu
Keo-Yuan Wu

1 September 2019 in Journal of Natural Gas Science and Engineering
Verified
Journal Article
Closed access
Keo-Yuan WuKeo-Yuan Wu
Keo-Yuan Wu
AMAli Mosleh
Ali Mosleh

11 November 2019
Verified
Conference Paper
Closed access
PDF file
WCWadie Chalgham
Wadie Chalgham
Mihai A. DiaconeasaMihai A. Diaconeasa
Mihai A. Diaconeasa
Keo-Yuan WuKeo-Yuan Wu
Keo-Yuan Wu
AMAli Mosleh
Ali Mosleh
The Pipeline Health Monitoring and Management web application is a risk-based pipeline integrity management support tool to support pipeline operators in decision-making and planning activities. The platform design is supported by a multi-disciplinary science and engineering approach for a comprehensive, state-of-the-art solution. The goal of the software platform is to integrate the data, methods, and technologies into a dynamic pipeline heath monitoring system supported by multiple probabilistic predictive models such as dynamic hybrid causal logic, corrosion prognosis, and sensor placement optimization models. This total system health management support tool provides online or offline updates on the reliability state of various segments of the pipeline system, and dynamically updates the recommendations on when and where to take mitigating actions, e.g., increase or decrease inspection frequency. The pipeline health monitoring system software platform under development provides the ability for (a) Integrity assessment based on comprehensive range of evidence from sensing, inspection, and real-time monitoring in addition to probabilistic integration of mechanistic models and data on failure mechanisms relating to various causal factors (e.g., uniform corrosion, pitting corrosion, etc.) for assessment of the pipe segment health (remaining life); (b) Dynamic pipeline network probabilistic health assessment model software for optimal risk-based prioritization of inspection and proactive management, and (c) Geographical mapping capabilities that will augment the interaction of the pipeline operators with the pipeline system such as viewing pipeline/sensor locations, and adding new pipelines if desired. The selected computational foundation for the assessment is the hybrid causal logic engine with a wide range of capabilities in terms of system model building and probabilistic analysis of various types of evidence for assessment of model parameters. On this foundation we are adding capabilities to integrate predictive corrosion models, sensor placement optimization, and computational modules to perform pipeline health assessment, and develop inspection and maintenance strategies. The resulting software will be deployed as a control room health dashboard and hand-held web-based field inspection support tool.

16 July 2021
Verified
Preprint
Open access
WCWadie Chalgham
Wadie Chalgham
Keo-Yuan WuKeo-Yuan Wu
Keo-Yuan Wu
AMAli Mosleh
Ali Mosleh
Pipeline failures continue to occur and are causing not only property damage but also human injuries and lives. Improving pipeline integrity management tools and techniques is becoming the main focus of owners and operators around the world. Quantifying the health state of the pipeline system is the main challenge facing the operators due to the limited sensor monitoring points