A Future with Machine Learning: Review of Condition Assessment of Structures and Mechanical Systems in Nuclear Facilities

Sandhu, Harleen Kaur; Bodda, Saran Srikanth; Gupta, Abhinav

doi:10.3390/en16062628

Cited by 20 publications

(3 citation statements)

References 118 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[20]. Incorporating sensor data into digital representations is critical for reliable and accurate health evaluations for technological advancements in sensor use in SHM [21]. The use of artificial intelligence (AI) in digital twins has shown tremendous potential for enhancing the precision and efficacy of SHM [22].…”

Section: Introductionmentioning

confidence: 99%

Current status and future challenges of digital twins for structural health monitoring in civil infrastructures

Parida,

Moharana

2024

Eng. Res. Express

View full text Add to dashboard Cite

Structural Health Monitoring (SHM) ensures the reliability, effectiveness, and performance of buildings and other structures. The introduction of digital twin technology in the last several decades has changed the field of SHM, allowing for real-time monitoring, analysis, and prediction of structural behavior. This research looks in depth at the usage of digital twins in the structural health monitoring of civil infrastructure developments. It analyzes the main features, benefits, challenges, and recent advancements in this rapidly increasing area. The review also discusses case studies and practical applications of digital twins for tracking and managing the health of civil infrastructures, providing insights into their potential for improving structural performance, lowering maintenance costs, and increasing the resilience of our built environment. This review paper provides a comprehensive overview of the usage of digital twins in critical infrastructure project structural health monitoring. It's an excellent tool for academics, scientists, and practitioners interested in utilizing digital twin technologies to improve our built environment's safety, performance, and resilience. This study aims to promote more significant research and innovation in developing and deploying digital twins for structural health monitoring by stressing the benefits, limits, and current advances in this field.

show abstract

Section: Introductionmentioning

confidence: 99%

Current status and future challenges of digital twins for structural health monitoring in civil infrastructures

Parida,

Moharana

2024

Eng. Res. Express

View full text Add to dashboard Cite

show abstract

“…AI enables condition-based maintenance strategies by continuously monitoring equipment health in real-time (Sharma et al, 2022). Sensors installed on subsea infrastructure collect data on parameters such as temperature, pressure, and vibration, which is then analyzed by AI algorithms to assess equipment condition (Sandhu et al, 2023). By detecting early signs of degradation or malfunction, it facilitates timely interventions, preventing costly breakdowns and ensuring optimal performance.…”

Section: Introductionmentioning

confidence: 99%

AI-enhanced subsea maintenance for improved safety and efficiency: Exploring strategic approaches

Oludayo Olatoye Sofoluwe,

Obinna Joshua Ochulor,

Ayemere Ukato

et al. 2024

Int. J. Sci. Res. Arch.

View full text Add to dashboard Cite

As the oil and gas industry increasingly explores deeper and more remote offshore sites, the maintenance of subsea infrastructure becomes paramount. The use of Artificial Intelligence (AI) in subsea maintenance offers promising solutions to enhance safety and efficiency in these challenging environments. This review explores strategic approaches to integrating AI into subsea maintenance operations. AI facilitates predictive maintenance by analyzing vast amounts of data collected from sensors and historical maintenance records. Machine learning algorithms can detect patterns and predict equipment failures before they occur, enabling proactive maintenance scheduling. This predictive capability reduces downtime and minimizes the risk of accidents by addressing potential issues before they escalate. AI-enabled autonomous underwater vehicles (AUVs) and remotely operated vehicles (ROVs) play a crucial role in subsea inspections and repairs. These AI-enhanced robots can navigate complex subsea environments, perform inspections, and execute maintenance tasks with greater precision and efficiency than human divers. By reducing the need for human intervention in hazardous environments, AI-driven AUVs and ROVs significantly improve safety. Furthermore, AI algorithms can optimize maintenance schedules based on factors such as equipment condition, environmental conditions, and operational requirements. By dynamically adjusting maintenance plans, operators can maximize equipment uptime while minimizing costs and risks. This proactive approach ensures that maintenance activities are conducted at the most opportune times, reducing the likelihood of unplanned downtime and improving overall efficiency. Moreover, AI facilitates condition-based maintenance strategies, where equipment health is continuously monitored in real-time. Sensors installed on subsea infrastructure collect data on factors such as temperature, pressure, and vibration, which is then analyzed by AI algorithms to assess equipment condition. By detecting early signs of degradation or malfunction, AI enables timely interventions, preventing costly breakdowns and ensuring optimal performance. In addition to predictive and condition-based maintenance, AI-driven analytics offer insights into operational performance and asset integrity. By analyzing data from various sources, including sensors, historical records, and operational logs, AI can identify trends, anomalies, and optimization opportunities. These insights enable operators to make data-driven decisions that enhance overall system reliability and efficiency. Strategic approaches to implementing AI in subsea maintenance require collaboration between technology providers, operators, and regulatory bodies. Establishing industry standards and guidelines for AI applications in subsea operations is crucial to ensure safety, reliability, and interoperability. Furthermore, investing in research and development to enhance AI algorithms and robotics technology is essential to unlock the full potential of AI in subsea maintenance. AI-enhanced subsea maintenance offers significant benefits in terms of safety and efficiency. By leveraging predictive analytics, autonomous robotics, and real-time monitoring, operators can optimize maintenance activities, reduce downtime, and minimize risks. Strategic approaches to integrating AI into subsea operations require collaboration, investment, and a commitment to advancing technology to meet the challenges of offshore environments.

show abstract

“…Recent applications of ML are also focused on the field of nuclear energy. Sandhu et al [16] review developments in condition assessment and AI applications of structural and mechanical systems in nuclear facilities. Tang et al [17] analyze the intelligent demand scenarios in the whole industrial chain of the nuclear industry, investigate the research status of deep learning in the application fields corresponding to different data types in the nuclear industry, and discuss the limitations and unique challenges of deep learning in the nuclear industry.…”

Section: Introductionmentioning

confidence: 99%

An Investigation of Efficiency Issues in a Low-Pressure Steam Turbine Using Neural Modelling

Bělohoubek,

Liška,

Kubín

et al. 2024

Sensors

View full text Add to dashboard Cite

This study utilizes neural networks to detect and locate thermal anomalies in low-pressure steam turbines, some of which experienced a drop in efficiency. Standard approaches relying on expert knowledge or statistical methods struggled to identify the anomalous steam line due to difficulty in capturing nonlinear and weak relations in the presence of linear and strong ones. In this research, some inputs that linearly relate to outputs have been intentionally neglected. The remaining inputs have been used to train shallow feedforward or long short-term memory neural networks using measured data. The resulting models have been analyzed by Shapley additive explanations, which can determine the impact of individual inputs or model features on outputs. This analysis identified unexpected relations between lines that should not be connected. Subsequently, during periodic plant shutdown, a leak was discovered in the indicated line.

show abstract

A Future with Machine Learning: Review of Condition Assessment of Structures and Mechanical Systems in Nuclear Facilities

Cited by 20 publications

References 118 publications

Current status and future challenges of digital twins for structural health monitoring in civil infrastructures

Current status and future challenges of digital twins for structural health monitoring in civil infrastructures

AI-enhanced subsea maintenance for improved safety and efficiency: Exploring strategic approaches

An Investigation of Efficiency Issues in a Low-Pressure Steam Turbine Using Neural Modelling

Contact Info

Product

Resources

About