Neural speed filtering for induction motors with anomalies and incipient faults

Effective sensorless speed estimation is desirable for both on-line condition monitoring and assessment, and for efficiency calculation of induction motors running off the power supply mains. In this paper, a sensorless neural adaptive speed filter is developed for induction motors operating under normal and anomalous conditions, such as supply imbalance, as well as incipient faults, such as electrical, electromechanical, and mechanical faults. The filter is demonstrated by comparisons with experimental speed measurements and spectral speed estimates. In addition to nameplate information required for the initial setup, the proposed neural speed filter uses only measured motor terminal currents and voltages. Initial training of the speed filter is accomplished off-line, using rotor slot harmonic-based speed estimates. The developed speed filter is scalable and it has been used for speed estimation of induction motors with varying power ratings. Incremental tuning is used to further improve filter performance and reduce filter development time significantly.