To achieve real-time monitoring and accurate evaluation of the operating state of permanent magnet motor system

this paper proposes a state perception and evaluation method based on the intrinsic state quantity. Key system state variables

including rotational speed

dq-axis voltage

and dq-axis current

are selected. A hybrid sensing model that integrates Long short-term memory network and bidirectional long short-term memory networks is constructed to capture the intrinsic relationships among features. A multi-dimensional error metric system comprising peak error

difference error

and absolute error is designed based on the dq-axis current

where the weights are determined by the analytic hierarchy process (AHP). The system’s operating state is quantitatively evaluated through the modulus of the error vector. Experimental results show that the proposed method has good prediction accuracy and generalization capability under various operating conditions

validating the effectiveness of the proposed method.