Structural fire testing is experiencing a renaissance. Both the research and regulatory communities are currently confronting the inherent problems associated with using simplified, single element tests on isolated structural members subjected to standard temperature-time curves to demonstrate adequate structural performance of buildings in fires. Indeed, this international symposium on "Fire Testing and Experimental Validation" is an indication of renewed interest in this area. This involves a shift in testing philosophy from prescriptive standard fire testing to large-scale non-standard fire testing using real fires. This follows more than a century during which the standard fire resistance test has been the predominant means of characterizing the response of structural elements and materials in fires. Large-scale nonstandard tests performed around the world during the past three decades have identified numerous shortcomings in our understanding of real building behaviour in real fires; these could not have been observed through standard tests. However, while identifying many of these shortcomings appears as novel insight, many such insights have been well known for decades but have remained largely unaddressed due to the pervasive use of the standard fire test. Only now, with a keen interest in understanding and a willingness to change our testing, design, and regulatory approaches, can these shortcomings be addressed. This paper briefly reviews the available data and knowledge from large scale non-standard fire tests conducted in the past thirty years, and defines current gaps in knowledge and research needs for rational and holistic fire-safe structural design of buildings.
