International Journal of Mechanical Engineering

Diagnosing abnormal vibration in main steam turbines is one of the key technologies for ensuring the stable operation of power systems. To effectively identify vibration abnormalities during operation and improve diagnostic accuracy, this paper proposes a diagnosis technique based on multi-source signal fusion. By integrating vibration signals, temperature signals, and pressure signals, and employing signal processing and fusion algorithms, the robustness and accuracy of anomaly diagnosis can be enhanced. This paper investigates the advantages and disadvantages of various signal fusion methods, analyzes the complementarity of different signals in the diagnostic process, and proposes a novel multi-source signal fusion approach. Experimental results demonstrate that the proposed method can accurately identify abnormal vibrations in main steam turbines, providing effective support for the maintenance and fault prevention of power equipment.

Main steam turbine; Abnormal vibration; Multi-source signal; Signal fusion; Fault diagnosis