A Novel Bearing Fault Diagnosis Method Based on Singular Spectrum Decomposition and a Multi-Strategy Enhanced Cuckoo Search-Optimized Extreme Learning Machine

Large background noise, difficulty in feature extraction, and low parameter-optimization efficiency of diagnosis models are key challenges in rolling bearing fault diagnosis. To address these issues, this paper proposes a fault diagnosis framework that combines Singular Spectrum Decomposition (SSD) with a Multi-Strategy Enhanced Cuckoo Search (MS-CS) algorithm to optimize an Extreme Learning Machine (ELM). First, the raw vibration signal is decomposed via SSD and each intrinsic component’s energy contribution is computed; components whose cumulative energy exceeds 90% are retained and reconstructed, thereby effectively suppressing noise while preserving critical fault features. Next, Multiscale Permutation Entropy (MPE) is extracted from the reconstructed signal to form a high-discriminability feature set. To overcome the traditional Cuckoo Search algorithm’s tendency to become trapped in local optima and its slow convergence, Cauchy mutation and adaptive Levy flight strategies are introduced to enhance global exploration and local exploitation. Finally, the improved MS-CS algorithm is employed to optimize the ELM’s input weights and hidden-layer biases, yielding a high-precision diagnostic model. Experimental results on benchmark bearing data demonstrate an average fault recognition rate of 96%, representing improvements of 6.67% over the conventional CS-ELM and 18% over the unoptimized ELM. These findings confirm the proposed method’s effectiveness and robustness in practical engineering applications.