A new method is presented for prioritizing sensor locations for structural health monitoring (SHM). In view of the needs of SHM and damage detection, sensor locations are optimized for the purpose of both sensitivity for local damages and independence of the target mode. However, the two different optimization criterions lead to an inconsistency of the optimal result. Considering the structural response changes that result from damage, the relationship between the structural response and damage is deduced from the structural motion equation by a quasi-analytical mode. Based on the harmony between damage identifiability and mode observability, an object function is set up, including the information of mode independence and damage sensitivity. Utilizing the technique of singular value decomposition, an interior algorithm for the optimum sensor placement is proposed with the multiple objective criterions of minimizing the condition number of coefficient matrix and maximizing the fisher information matrix. A numerical example shows that this approach can effectively avoid the contradiction between the two different optimization criterions. Comparing with the result of single object, the result of damage detection from the optical sensor locations is much more accurate.