A machine learning apparatus for learning a correction parameter used in correction of a command value that controls a motor in a motor drive system including a plurality of kinds of correction functions includes: a state observation unit that observes, as a state variable, each of a feature calculated on the basis of drive data and the kind of any of the correction functions of the motor drive system and the correction parameter; and a learning unit that learns the correction parameter for each of the correction functions according to a training data set created on the basis of the state variable.

The controller comprises a displacement controller and a rotating speed controller. The displacement controller includes a vibration force compensation control module and a dead-time vibration compensation module. The vibration force compensation control module receives actual displacements and a rotor mechanical angle and outputs corresponding vibration compensation forces. The vibration force compensation control module comprises a first neural network band-pass filter, a second neural network band-pass filter, a third PID controller, and a fourth PID controller. The dead-time vibration compensation module receives a rotor electrical angle and an actual quadrature-direct axis currents and an actual direct axis current and outputs a quadrature-direct axis compensation voltages and a direct axis compensation voltage. The dead-time vibration compensation module consists of a third neural network band-pass filter in a direct axis direction, a fourth neural network band-pass filter in a quadrature axis direction, a sixth PI controller, and a seventh PI controller.

The controller comprises a displacement controller and a rotating speed controller. The displacement controller includes a vibration force compensation control module and a dead-time vibration compensation module. The vibration force compensation control module receives actual displacements and a rotor mechanical angle and outputs corresponding vibration compensation forces. The vibration force compensation control module comprises a first neural network band-pass filter, a second neural network band-pass filter, a third PID controller, and a fourth PID controller. The dead-time vibration compensation module receives a rotor electrical angle and an actual quadrature-direct axis currents and an actual direct axis current and outputs a quadrature-direct axis compensation voltages and a direct axis compensation voltage. The dead-time vibration compensation module consists of a third neural network band-pass filter in a direct axis direction, a fourth neural network band-pass filter in a quadrature axis direction, a sixth PI controller, and a seventh PI controller.

A motor control device includes a motor that generates torque corresponding to a current for energizing multi-phase coils, a current sensor that detects a current value of the current for energizing the multi-phase coils, and a controller that obtains a current value of a current flowing through a predetermined coil by adding an origin learning value to a signal input from the current sensor and that controls a current for energizing the predetermined coil based on the current value. The motor control device obtains, each time the origin learning value is changed by a predetermined value, an amplitude of a predetermined order in a q-axis current of the motor based on the changed origin learning value and the signal input from the current sensor, and performs correction based on the origin learning value at the time when the amplitude switches from a decreasing tendency to an increasing tendency.

A motor control device includes a motor that generates torque corresponding to a current for energizing multi-phase coils, a current sensor that detects a current value of the current for energizing the multi-phase coils, and a controller that obtains a current value of a current flowing through a predetermined coil by adding an origin learning value to a signal input from the current sensor and that controls a current for energizing the predetermined coil based on the current value. The motor control device obtains, each time the origin learning value is changed by a predetermined value, an amplitude of a predetermined order in a q-axis current of the motor based on the changed origin learning value and the signal input from the current sensor, and performs correction based on the origin learning value at the time when the amplitude switches from a decreasing tendency to an increasing tendency.

An apparatus for driving a motor includes motor circuitry and neural network circuitry. The motor circuitry is configured to generate, based on an error compensated rotor angle and current at a plurality of phases of the motor, a d-axis instant current value and generate a d-axis instant voltage value based on the d-axis instant current value. The motor circuitry is further configured to generate voltage at the plurality of phases based on the d-axis instant voltage value. The neural network circuitry is configured to generate a rotor angle offset based on an instant rotor speed at the motor. The neural network circuitry has been trained to generate the rotor angle offset to minimize the d-axis instant voltage value for each of a plurality of rotor speeds at the motor. The error compensated rotor angle is based on the rotor angle offset.

A fuzzy finite-time optimal synchronization control method for a fractional-order permanent magnet synchronous generator, and belongs to the technical field of generators. A synchronization model between fractional-order driving and driven permanent magnet synchronous generators with capacitance-resistance coupling is established. The dynamic analysis fully reveals that the system has rich dynamic behaviors including chaotic oscillation, and a numerical method provides stability and instability boundaries. Then, under the framework of a fractional-order backstepping control theory, a fuzzy finite-time optimal synchronous control scheme which integrates a hierarchical type-2 fuzzy neural network, a finite-time command filter and a finite-time prescribed performance function is provided.

This power conversion device includes: a current detection unit for detecting current flowing through a rotary electric machine; a switching pattern determination unit for determining a switching pattern on the basis of the detected current, a current prediction value, a current command value, and a current harmonic command value; and a power conversion unit for outputting AC power to the rotary electric machine in accordance with the switching pattern, wherein the switching pattern determination unit determines the switching pattern so that the current value follows the current command value and the current harmonic becomes equal to or smaller than a limit value.

The disclosure discloses a motor driving system converter fault diagnosis method based on adaptive sparse filtering, and belongs to the field of driving system fault diagnosis. The disclosure applies an unsupervised learning algorithm to an application scene of converter fault diagnosis. Effective features are automatically extracted from original data, and the problem of manual feature design based on expert knowledge is solved. Meanwhile, in consideration of current fundamental period change caused by different rotation speed working conditions, rotation speed feedback is introduced, secondary sampling is carried out on current sampled at a constant frequency, it is ensured that the length of a signal input into the deep sparse filtering network is one fundamental wave period, redundant information is better removed from original data, the calculation burden is relieved, and the accuracy and rapidity of the diagnosis algorithm are improved to a certain extent.

A motor control unit (10) includes, for example, a motor control block (11) that performs feedback control of a drive current that flows through a motor (20) and a machine learning block (14) that analyzes input data including at least the drive current so as to detect a failure level of the motor (20). The motor control block (11) could be configured to dynamically switch a control parameter or a control method in accordance with the failure level. The input data may further include, for example, a drive voltage applied to the motor (20). Furthermore, the input data may further include, for example, at least one of vibrations and a temperature of the motor (20) or a motor device (1) mounting the motor (20) therein.