Decommissioning of nuclear facilities is an invasive process that presents industrial and chemical hazards as well as radiological ones, and indeed the non-radiological hazards generally represent the greater overall risk to workers. Even though workers are trained to stay away from potential dangers, there are still many types of risks that can occur within only a few minutes of carelessness. At present, a multitude of Tokyo Electric Power Company (TEPCO) workers, manufacturers of nuclear reactors, construction companies, and their contractors are engaged in the decommissioning project of Fukushima Daiichi nuclear power station and are consequently exposed to various health risks. According to contamination conditions, TEPCO indicates the workers shall be ensured to wear Personal Protective Equipment (PPE) (e.g. anorak bodysuits, helmet, full-face mask) in the plant’s most radioactive areas. However, TEPCO contracted various tasks to more than 20 companies (primary contractors), and each of them outsourced parts of tasks to multiple layers of subcontractors. This complex structure may hinder consistent implementation of occupational health rules. Thus, an automated monitoring approach is indispensable to be conducted to help to facilitate the safety monitoring task of decommissioning workers to ensure PPEs are appropriately used and ensure safety in the field.

This study proposes a deep learning-based system to automated detect helmets and masks and identifies whether workers on decommissioning sites are using PPE properly. Firstly, we deploy Yolov3 model to localize the helmets and masks in the observed frames via on-site surveillance cameras. Subsequently, we characterize the individual(s) postures by extracting the joint positions of the person in the image using OpenPose, which is the state-of-the-art method for detecting human body parts in images. Finally, we identify whether PPE(s) are appropriately used by analyzing the geometry relationships of detected PPE(s) and individual(s). The experimental results demonstrate that the high precision, high recall and fast speed of the system can effectively detect decommissioning workers' failure use of PPE and can facilitate improved safety inspection and supervision.


A Novel System for Automated Proper Use Identification of Personal Protective Equipment in Decommissioning Site of Fukushima Daiichi Nuclear Power Station

Division / Sponsors: 
Power Division & Nuclear Engineering Division (NED)

Power Conference
Paper Proceedings: https://asmedigitalcollection.asme.org/POWER/POWER2020/volume/83747

International Conference on Nuclear Engineering
Paper Proceedings: https://asmedigitalcollection.asme.org/ICONE/ICONE2020/volume/83761

POWER-ICONE - Virtual Conference

Supporting the need among researchers worldwide for additional online and multimedia content, ASME now offers the ASME Conference Video Collection. This platform will collect and provide long-term access to conference presentation videos, encompassing all technology areas within ASME's technical conference and events program. About 30,000-40,000 engineers across all mechanical engineering and related disciplines participate in ASME conferences each year. This includes authors of approximately 6,000 to 8,000 technical papers published by ASME, the majority of whom also submit video presentations for our virtual conferences. The video collection will be available as an add-on to existing product packages or as a separate subscription.