As wind energy is experiencing an unprecedented development in today's world, the condition monitoring of wind turbine systems which can avoid serious accidents and economic losses are gathering more and more attentions. Considering the evaluation methods based on machine learning are complicated and unstable in terms of model training and parameter selection, this paper proposed a novel assessment algorithm based on similarity analysis of fuzzy k ‐principal curves (FKPCs) in manifold space. Initially, 38 fusion features containing time‐domain, frequency‐domain, and wavelet node energy features are extracted from the vibration signal of the wind turbine bearing. Then, the nonlinear local algorithm Laplacian eigenmaps was introduced to transform the original features to the projected lower dimensional space and obtain the more typical parameters. Combining fuzzy clustering with the k ‐principal curve creatively, smooth principal curves of the feature sets were then extracted according to point distribution in three‐dimensional manifold space. Finally, the Hausdorff distance algorithm was employed to calculate the similarity between the principal curves of healthy and test datasets to assess the running condition of wind turbine. To validate the present method, the experiments of accelerated bearing degradation were carried out. A series of comprehensive and persuasive comparisons and analysis with different feature conversion methods (principal component analysis [PCA] and Isomap), different distance analysis algorithms (Euclidean distance and Mahalanobis distance), and different assessment models (hidden Markov model [HMM] and deep belief network [DBN]) verified that the proposed FKPC technique can monitor the operating status of the machine more accurately without complex model training and parameter selection processes.