Adaptive parameter-optimized NLM algorithm to denoise vibration signals of hydropower units

Monitoring and diagnosing the operating state of hydropower units is crucial, which becomes a hot research topic in the industry. the vibration signals provide a reliable indication to detect the abnormal working conditions of hydropower units. however, the vibration signals is affected by the environment noise inevitably, making it difficult to truly reflect the operating state of hydropower units. the non-local means (NLM) algorithm is proved to be effective in denoising the vibration signals, however, whose parameters depend on the human experience, which hinders its application and development. in the present work, based on the Bayesian parameter optimization (BPO), the parameters of NLM are set adaptively, the BPO-NLM denoising algorithm is proposed. by conducting the simulation, the denoising effectiveness of BPO-NLM is improved remarkably than that of the traditional NLM. at different snr, RMSE of the signal denoised by BPO-NLM is much smaller than that of the traditional NLM, while snr of the signal denoised by BPO-NLM is much larger, namely, the effective component of the signal is enhanced, while the noise component is suppressed.