Concerning the problems that the parameters of the state of the aluminum reduction cells are multivariate and with strong coupling, the calculation of established diagnosis model is large and the precision of diagnosis is limited, this paper proposed Optimized Relative Principal Component Analysis (ORPCA) method to diagnose the status of aluminum reduction cells. An effective principle of determining the relative weight was put forward, which took advantage of Relative Principal Component Analysis (RPCA) in reducing dimensions. In the method, Genetic Algorithm (GA) was used to optimize the fitness function about false alarm rate. The diversification of the sample project in principal component space and residual space was observed to acquire the best relative transforming matrix, so the false alarm rate of Hotelling's T2 test and Squared Prediction Error (SPE) were reduced to the least. By using a group data of 170kA operating aluminum smelter from a factory, the experimental results show that, when the confidence coefficients are 95% and 97.5%, the false alarm rates of T2 test are 16.79% and 9.77% respectively, meanwhile, the false alarm rates of SPE test are 4.01% and 1.75% respectively. Compared with other similar algorithms, the proposed method can test the abnormal condition of aluminum reduction cells and obviously reduce the false alarm rate of Hotelling's T2 test and SPE test.