{"id":11056,"date":"2022-02-25T08:39:47","date_gmt":"2022-02-25T07:39:47","guid":{"rendered":"https:\/\/www.revistanuclear.es\/uncategorized\/application-of-deep-neural-networks-in-automatic-visual-inspection-of-uo2-pellets\/"},"modified":"2023-02-01T12:31:33","modified_gmt":"2023-02-01T11:31:33","slug":"application-of-deep-neural-networks-in-automatic-visual-inspection-of-uo2-pellets","status":"publish","type":"post","link":"https:\/\/www.revistanuclear.es\/en\/fuel-cycle\/application-of-deep-neural-networks-in-automatic-visual-inspection-of-uo2-pellets\/","title":{"rendered":"Application of deep neural networks in automatic visual inspection of UO2 pellets"},"content":{"rendered":"
BEST TECHNICAL ARTICLE 2022<\/div><\/div><\/div><\/div>\n
\"\"<\/span>SEE FULL VERSION<\/span><\/a>
<\/div>N<\/span>eural Networks are an incipient technology and its use in real applications, including industrial ones, is ever increasing. The current computational power and the evolution of machine learning techniques allow the implementation of systems based on neural networks that a few years ago only were used at laboratory and for theoretical applications.<\/p>\n

ENUSA, as nuclear fuel manufacturer, must comply with high quality standards for the manufacturing process. An example of it applied to nuclear fuel pellets manufacturing are the automatic visual inspection equipment for defect detection and pellet rejection at ENUSA factory. This equipment has been developed by ENUSA since 2000; two of them have been exploited at ENUSA\u2019s factory, and, in 2019, a third one was supplied to Jianzhong Nuclear Fuel Co., Ltd. (CJNF) at Yibin (China).<\/p>\n

Automatic Pellet Inspection Equipment (API) uses traditional image analysis techniques. Thanks to the effectiveness shown by this equipment, ENUSA continued working on its technical evolution, more so considering the improvements image acquisition systems and image analysis techniques over the last years.<\/p>\n

The use of deep neural networks (DNN) for image pellet analysis provides more reliable results and superior capacity to discriminate small changes in the image compared to traditional techniques. Based on all this, ENUSA decided to investigate DNN and its use in API equipment, within a collaboration project with AUDIAS (Audio, Data Intelligence and Speech) research group of \u201cUniversidad Aut\u00f3noma de Madrid<\/i>\u201d. This research group has considerable experience in neural networks and signal processing for real applications.<\/p>\n

\"\"