Method for Operating an Electric Drive System

Abstract

A method for operating an electrical drive system includes the steps of: acquiring a number of input variables pertaining to the electrical drive system; determining at least one state variable from the acquired input variables by way of an observer; determining at least one disturbance variable from the acquired input variables by way of the observer; controlling the electrical drive system on the basis of the at least one determined state variable; and monitoring the state of the electrical drive system by machine learning, the at least one disturbance variable forming input data for a machine learning model.

Claims

1.-7. (canceled)

8. A method for operating an electrical drive system, the method comprising the steps of: acquiring a number of input variables (e1, . . . , en) pertaining to the electrical drive system; determining at least one state variable (Z) from the acquired input variables (e1, . . . , en) via an observer; determining at least one disturbance variable (S) from the acquired input variables (e1, . . . , en) via the observer; controlling the electrical drive system based on the at least one determined state variable (Z); and monitoring a state of the electrical drive system via machine learning, the at least one disturbance variable (S) forming input data for a machine learning model.

9. The method according to claim 8, wherein the electrical drive system comprises: an electric motor and a phase-rotation indicator mechanically coupled to the electric motor; and a mechanical load moved by way of the electric motor, and a load sensor mechanically coupled to the mechanical load, wherein measured variables (m1, . . . , mm) ascertained for the observer are selected from: a phase-rotation indicator position (D1) generated by the phase-rotation indicator, a load sensor position (D2) generated by the load sensor, and a torque (D3) generated by the electric motor.

10. The method according to claim 9, wherein the at least one state variable (Z) is a position and/or a speed of the mechanical load.

11. The method according to claim 8, wherein the at least one disturbance variable (S) represents a friction occurring in the electrical drive system.

12. The method according to claim 8, wherein the at least one disturbance variable (S) represents a torque generated by the electric motor.

13. The method according to claim 8, wherein the observer is an extended Kalman filter.

14. The method according to claim 8, wherein the state of the electrical drive system determined by machine learning is evaluated for a purpose of preventive maintenance of the electrical drive system.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

[0019] FIG. 1 schematically shows a block diagram of an observer,

[0020] FIG. 2 schematically shows a block diagram of an electrical drive system, and

[0021] FIG. 3 shows a block diagram of a machine learning model for monitoring the condition of the electrical drive system.

DETAILED DESCRIPTION OF THE DRAWINGS

[0022] FIG. 2 shows a block diagram of an electrical drive system 100 with an electric motor 1 and a phase-rotation indicator, or encoder, 2 mechanically coupled to the electric motor 1. The electrical drive system 100 also comprises a mechanical load 3 moved by means of the electric motor 1 and a load sensor 4 mechanically coupled to the mechanical load 3.

[0023] FIG. 1 schematically shows a block diagram of an observer in the form of an extended Kalman filter 200, which uses a model 100 of the electrical drive system 100 to determine estimated measured variables m.sub.r1, . . . , m.sub.rm, at least one state variable Z and at least one disturbance variable S from a number of input variables e.sub.1, . . . , e.sub.n pertaining to the electrical drive system 100, inter alia. It holds that n=2, 3, . . . and m=2, 3, . . . .

[0024] The at least one disturbance variable S can represent a friction occurring in the electrical drive system 100 and/or a torque generated by means of the electric motor 1, for example.

[0025] In respect of the basic design and basic function of observers, or extended Kalman filters, reference will also be made to the relevant specialist literature.

[0026] Measured variables m.sub.1, . . . , m.sub.m ascertained for the observer 200 are for example selected from a phase-rotation indicator position D1 generated by means of the phase-rotation indicator 2, a load sensor position D2 generated by means of the load sensor 4, and a torque D3 generated by means of the electric motor 1, see also FIG. 2.

[0027] The state variable(s) Z may be a position and/or a speed of the mechanical load 3.

[0028] The electrical drive system 100 is controlled on the basis of the at least one determined state variable Z.

[0029] FIG. 3 shows a block diagram of a machine learning model 300 for condition monitoring and preventive maintenance of the electrical drive system 100, the at least one disturbance variable S forming input data for the model 300 and the model calculating a machine state MS on the basis of the at least one disturbance variable S.