In order to accurately achieve elevator fault diagnosis, an elevator fault diagnosis based on AO-VMD-BF and multi model fusion is proposed. Firstly, the variational mode decomposition(VMD) optimized by the aquila optimizer(AO) algorithm is used to decompose the signal into multiple modal components, and the Pearson correlation coefficient is used to remove false components. To address the problem of noise in the remaining signal, the butterworth filter(BF) is used for secondary denoising, The denoised vibration signal can be obtained by reconstructing the filtered modal sub quantum sequence. Then extract time-domain, frequency-domain, and entropy features to form a multi domain feature vector set. Finally, a Stacking ensemble learning elevator fault diagnosis model is established based on convolutional neural network(CNN), random forest(RF), support vector machine(SVM), and adaptive boosting(AdaBoost) models, with extreme gradient boosting(XGBoost) as the meta classifier. The analysis of experimental results shows that the proposed method can effectively extract fault features from elevator car vibration signals, and accurately and effectively diagnose elevator faults.