Inetec (Croatia)

Non-destructive ultrasonic analysis of materials is a method for assessing the integrity of the inspected components. It is commonly used in monitoring critical parts of the power plants, in aeronautics, oil and gas, and the automotive industry. Since most ultrasonic inspections rely on expert's previous experience they must constantly practice on new, unseen data. Acquiring enough data for training human experts on non-destructive ultrasonic scan analysis can be an expensive and time-consuming task. The only possibility to get new data for practicing is to implant synthetic defects in real metal blocks. Artificial defects are made by temperature strain, electrical discharge, and physical damage. All of those methods are very complicated and expensive to perform. Also metal blocks have to be taken from the components of the power plants to have the same structure and be realistic. In this work, some attempts have been made to generate 3D ultrasonic scans using computer vision and deep learning methods.

Non-destructive ultrasonic testing (UT) of materials is used for monitoring critical parts in power plants, aeronautics, oil and gas industry, and space industry. Due to a vast amount of time needed for a human expert to perform inspection it is practical for a computer to take over that task. Some attempts have been made to produce algorithms for automatic UT scan inspection mainly using older, non-flexible analysis methods. In this paper, two deep learning based methods for flaw detection are presented, YOLO and SSD convolutional neural networks. The methods' performance was tested on a dataset that was acquired by scanning metal blocks containing different types of defects. YOLO achieved average precision (AP) of 89.7% while SSD achieved AP of 84.5 %.

One of the technical issues addressed in Generic Letter 96-06 and its supplement by the U.S. NRC is related to the possibility of thermally induced over-pressurization (TIP) at isolated water-filled piping sections that penetrate the containment during design basis accident conditions such as a loss-of-coolant accident (LOCA) or a main-steam line break (MSLB)[1,2]. This is a safety-significant issue because TIP at an isolated water-solid piping section can threaten the containment integrity by causing a breach at the piping segment that penetrates through the containment and by in turn permitting bypass leakage at the containment. This constitutes a failure of the intended isolation function of the containment, which should be ensured during the conditions of a LOCA or MSLB for the health of the public in the vicinity of nuclear power plants. This issue is dealt with from a regulatory aspect in Periodic Safety Reviews (PSR) on operational NPPs in Korea. A methodology to evaluate the possibility and the effects of TIP has been established for application to Korean NPPs. In this paper, the assessment methodology is presented in a step by step manner and representative assessment results for a Korean NPP are also described.