The compensation technique of tensile force effect on the electro-mechanical impedance method for structural health monitoring

In this article, the external axial tension applied on structure was considered in electro-mechanical impedance method. An experiment was performed to study the effect of external axial force on the electro-mechanical impedance–based structural health monitoring. The axial tensions were applied on both healthy and damaged steel beam pasted by surface-bonded piezoelectric transducers. The study results showed that the electrical admittance (the inverse of impedance) curves had an obvious tendency of decline with the increase in tension; thus, this effect would mislead the judgment of health status. Then, the artificial neural network based on radial basis function was introduced to compensate the effect of tension on EMI method. Numerical examples showed that artificial neural network method can prevent the root mean square deviation index from changing with increase in tension. An additional experiment was performed to verify the artificial neural network method. The same conclusion as the first experiment was obtained. The reasonable experiment result demonstrated that artificial neural network method has its generality for application.