Novel paralleled extreme learning machine networks for fault diagnosis of wind turbine drivetrain

With the increasing installed power of the wind turbines, the necessity of condition monitoring for wind turbine drivetrain cannot be neglected any longer. A reliable and rapid response fault diagnosis is vital for the wind turbine drivetrain system. The existing manual inspection-based methods are difficult to accomplish the real-time compound-fault monitoring task. To solve this problem, this paper proposes a novel dual extreme learning machines (Dual-ELMs) based fault diagnostic framework for feature extraction and fault pattern recognition. At the stage of feature learning, this paper applies the local mean decomposition (LMD) method to extract the production functions from the raw vibration signals. Compared with the traditional empirical mode decomposition method, the LMD method has a stronger ability to restrain the mode mixing and endpoints effect. At the stage of compound-fault classification, unlike the other widely-used classifiers, the proposed Dual-ELM networks inherit the advantages of the original extreme learning machines (ELMs), that employs two basic ELM networks for the compound-fault classification, and it does not need iterative fine-tuning of parameters. Thus the learning speed is faster than the other combinations of classifiers. The experimental validity of the proposed algorithm was conducted on a test rig for vibration analysis, which demonstrated that the proposed Dual-ELMs based fault diagnostic method provides an effective measure for the observed machinery than the other available fault diagnostic methods in aspects of feature extraction and compound-fault recognition.