Managing Operational Risk in Nuclear Facilities with TensorFlow

William Zywiec

Staff Scientist and Group Leader in the Nuclear Criticality Safety Division at Lawrence Livermore National Laboratory

Abstract:

Since the discovery of fission and subsequent first criticality of Chicago Pile-1, more than 60 criticality accidents have occurred throughout the world. These accidents are divided into two categories: those that occur during critical experiments or operations with nuclear reactors, and those that occur in production facilities, more commonly referred to as process criticality accidents. I will provide a brief overview of a few historical process criticality accidents and near misses that have occurred in the United States, and then I’ll discuss ongoing research that is being done to develop and implement machine learning tools to assess and manage operational risk in modern nuclear facilities. I’ll wrap up the presentation by discussing the overlap between nuclear criticality safety and emergency response.

Bio:

William Zywiec is a Staff Scientist and Group Leader in the Nuclear Criticality Safety Division at Lawrence Livermore National Laboratory. He currently leads several projects in California and Nevada that focus on radiation detection, nuclear threat assessment, and characterization of special nuclear material hold-up. He has a PhD in Systems Engineering from George Washington University, an MSE in Systems Engineering from Johns Hopkins University, and a BS in Nuclear Engineering from Rensselaer Polytechnic Institute.

Watch here

Webinar ID 972 3976 4948