Many aerospace, civil and mechanical systems continue to be used despite ageing and the associated potential for damage accumulation. Therefore, the ability to monitor the structural health of these systems is becoming increasingly important. A wide variety of highly effective local non–destructive evaluation tools is available. However, damage identification based upon changes in vibration characteristics is one of the few methods that monitor changes in the structure on a global basis. A summary of developments in the field of global structural health monitoring that have taken place over the last thirty years is first presented. Vibration–based damage detection is a primary tool that is employed for this monitoring. Next, the process of vibration based damage detection will be described as a problem in statistical pattern recognition. This process is composed of three portions: (i) data acquisition and cleansing; (ii) feature selection and data compression; and (iii) statistical model development. Current research regarding feature selection and statistical model development will be emphasized with the application of this technology to a large–scale laboratory structure.