Vibration signals of rolling bearings with labels are difficult to obtain under variable working conditions, which leads to low accuracy of fault diagnosis. Aiming at this problem, a new fault diagnosis method for rolling bearings was proposed based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and manifold embedding distribution alignment. Firstly, CEEMDAN was used to decompose the vibration signals of rolling bearings under different working conditions, and some intrinsic mode components (IMF) were obtained. Secondly, the time-domain and frequency-domain features of IMF components with larger kurtosis were extracted to construct a multi-features sample set. The extracted features were embedded into the manifold space for manifold feature transformation and the transformed manifold features were aligned dynamically. Finally, the classification model was trained with source data and target data to obtain the fault diagnosis results of rolling bearings with unknown labels. The experimental results show that the proposed method can minimize the difference of feature distribution between domains, and improve the accuracy of rolling bearings state recognition effectively.