Most of identification methods are eventually converted to a linear algebraic equation set. Different ways to solve the equation set will result in solutions with completely different levels of accuracy. Based on the frequencytime domain method (FTDM),the moving vehicleaxle loads are identified from the measured responses induced by the vehicles crossing a bridge.The focus is on evaluation of two solutions,i.e.,direct calculation of pseudo inverse (PI) and calculation of pseudo inverse via the singular value decomposition (SVD) technique,to the equation set established in the FTDM.The effects of various parameters on identified results also are discussed.Assessment results show that the SVD technique can obviously improve identification accuracy as compared to the PI solution