A system and method for performing structural health monitoring on a structural element while it remains in service and experiences normal loading. The energy input to the element will be the normal and random energy inputs the element sees in service. The inventive system places an intelligent module at one or more points along the length of the structural element. The inventive system collects mass data from multiple modules on multiple elements. The system then applies machine learning or artificial intelligence techniques to detect changes in the measurements received from one or more modules. This approach reduces or eliminates the need to provide calibrated input energy. The invention preferably provides the ability to determine the condition of one element or sub-element under measurement relative to other elements.