Automatic Imagery Data Analysis for Diagnosing Human Factors in the Outage of a Nuclear Plant

Tang, Pingbo; Zhang, Cheng; Yilmaz, Alper; Cooke, Nancy J.; Boring, Ronald L.; Chasey, Allan D.; Vaughn, Timothy; Jones, S.; Gupta, Ashish; Buchanan, Verica

doi:10.1007/978-3-319-40247-5_61

Cited by 5 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, it is also finding its way into the plant work process. For example, Tang (2016) developed an algorithm on tracking craft wait time at certain tasks by tracking the craft motion using image-processing methods. In the context of the nuclear power industry, dynamic image recognition can be used for:…”

Section: Motion Recognitionmentioning

confidence: 99%

Automation Technologies Impact on the Work Process of Nuclear Power Plants

Rashdan

Mortenson

2018

View full text Add to dashboard Cite

Nuclear power plants (NPPs) have been experiencing significant cost challenges to remain competitive with other power industries. This places a large burden on NPPs to minimize costs while sustaining excellent safety records. The Light Water Reactor Sustainability Program is a research and development program sponsored by the United States Department of Energy that supports the industry in overcoming this challenge. One of the main focus areas of the program is plant modernization, with automation as one of the key elements of modernization.NPPs costs are distributed primarily across operations and maintenance activities in the plant. Regulatory burdens, increased market costs for skilled labor, and increased surveillance and maintenance activities in pursuance of extended life cycles of the nuclear fleet are among the main cost drivers at play. Work processes at NPPs involve many reviews and layers of approval to ensure safe execution of operation and maintenance tasks. The work process is burdensome for maintenance activities and involves some disparate processes, systems, and departments across the organization. These activities add costs due to inefficiencies and manual processes. This makes the work process a great candidate for automation technologies.

show abstract

Section: Motion Recognitionmentioning

confidence: 99%

Automation Technologies Impact on the Work Process of Nuclear Power Plants

Rashdan

Mortenson

2018

View full text Add to dashboard Cite

show abstract

“…For example, the video stream or recording can be used to track human presence and waiting time at certain equipment locations. It thereby creates a stream of work-performance data (e.g., Tang et al 2016). The video stream or recording can also be used to track change actions performed on equipment, such as a breaker panel, and log status using change recognition (Menser 2017).…”

Section: Modern Statementioning

confidence: 99%

“…This can be achieved by implementing image-recognition methods on fixed or mobile cameras on helmets or glasses. Video recognition, coupled with facial recognition, can track people's movement in the plant for updating human-resources work progress (e.g., Tang et al 2016).…”

Section: State-of-the-artmentioning

confidence: 99%

Automation of Data Collection Methods for Online Monitoring of Nuclear Power Plants

Rashdan

Germain

2018

View full text Add to dashboard Cite

The workforce cost of operations and maintenance (O&M) in the United States nuclear power industry is mostly attributed to manual activities supplying information to a human decision-making process. Several manually-collected labor-intensive processes generate information that is not typically used beyond the intended target for collecting that information. The information is therefore expensive to collect, yet of limited use. This especially applies to surveillance activities and preventive maintenance, which represent most of the plant workforce activities.The industry has recognized the benefits of both reducing labor-intensive tasks by automating them and increasing the fidelity and uses of the data collected to enable advanced remote monitoring using data-driven decision making for O&M activities. These data-driven methods could include capabilities from performance trending to machine learning and advanced forms of artificial intelligence. This shift in O&M strategy results in significant cost savings, because it reduces labor requirements by automating the data-collection process and reduces the frequency of activities by using an on-need model. The frequency reduction results in additional cost savings by lowering labor and materials demand. This specific effort focuses on automation of monitoring data-collection processes. It is one in a series of efforts planned by the Department of Energy (DOE) Light-water Reactor Sustainability (LWRS) program to target multiple elements in migrating current O&M activities to a data-driven approach. These elements are data collection, data analytics, data management, visualization, value analysis, and change enablement. This effort will focus exclusively on data collection while the other five elements are explicitly researched in multiple ongoing efforts, or planned for future efforts. Out-of-the-box thinking was followed in this effort, which assumed no constraints from the other five elements.

show abstract