Method and systems for provision of a simulation model of an electric rotating machine

Abstract

A computer-implemented method for providing a simulation model of an electric rotating machine is disclosed. The simulation model is defined by parameter values. Input data is obtained. The input data is collectable using the electric rotating machine when the electric rotating machine is not connected to an operating voltage and being characteristic of the electric rotating machine. The parameter values are determined from the input data using a trained function and the parameter values determined are provided.

What is claimed is: 
     
         1 . A computer-implemented method for provision of a trained function, the method comprising:
 obtaining training input data comprising shaft heights and a number of pole pairs, the training input data characteristic of an electric rotating machine, the training input data being collectable using electric rotating machines in a state in which the electric rotating machines are not connected to an operating voltage;   obtaining training output data comprising loss and stray coefficients of the electric rotating machines representative of parameter values that define simulation models of the electric rotating machines;   training a function based on the training input data and the training output data; and   providing the trained function.   
     
     
         2 . The method of  claim 1 , wherein the function is based on a neural network, or on a regression. 
     
     
         3 . The method of  claim 2 , wherein the function is based on a multivariate regression. 
     
     
         4 . The method of  claim 1 , further comprising preprocessing a training dataset, which comprises the training input data and the training output data, before the function is trained on the training dataset. 
     
     
         5 . The method of  claim 4 , wherein the preprocessing comprises bringing the training input data and the training output into a relative and normalized form. 
     
     
         6 . A computer-implemented method for provision of a simulation model of an electric rotating machine, the simulation model defined by parameter values, the method comprising:
 obtaining input data comprising a shaft height, a number of pole pairs and rating plate specifications of the electric rotating machine, the input data characteristic of the rotating electric machine, and the input data being collectable using the electric rotating machine in a state in which the electric rotating machine is not connected to an operating voltage;   determining the parameter values from the input data with the trained function provided by the method set forth in  claim 1 ;   determining with the trained function the loss and stray coefficients based on the shaft height and the number of pole pairs;   determining the parameter values from the loss and stray coefficients and the rating plate specifications; and   providing the determined parameter values.   
     
     
         7 . The method of  claim 6 , wherein the trained function is based on a neural network, or on a regression. 
     
     
         8 . The method of  claim 7 , wherein the trained function is based on a multivariate regression. 
     
     
         9 . The method of  claim 6 , wherein the input data is subjected to a plausibility check. 
     
     
         10 . The method as claimed of  claim 6 , wherein the input data consists of the rating plate specifications. 
     
     
         11 . The method of  claim 10 , wherein at least one part of the parameter values is defined by the rating plate specifications. 
     
     
         12 . The method of  claim 6 , wherein the input data consists of the shaft height and the number of pole pairs. 
     
     
         13 . The method of  claim 6 , wherein the simulation model is arranged as an equivalent circuit diagram. 
     
     
         14 . The method of  claim 13 , wherein the equivalent circuit diagram is an expanded equivalent circuit diagram. 
     
     
         15 . A computer program stored on a computer-readable medium, the computer program comprising commands that, when executed by a computer, cause said computer to carry out the method of  claim 1 . 
     
     
         16 . A computer program stored on a computer-readable medium, the computer program comprising commands that, when executed by a computer, cause said computer to carry out the method of  claim 6 . 
     
     
         17 . A data carrier signal stored on a computer-readable medium, that when transmitted, transmits the simulation model provided in accordance with the method of  claim 6 . 
     
     
         18 . A data carrier signal stored on a computer-readable medium, that when transmitted, transmits the computer program of  claim 15 . 
     
     
         19 . A data carrier signal stored on a computer-readable medium, that when transmitted, transmits the computer program of  claim 16 . 
     
     
         20 . A method for linkage of an electric rotating machine to a platform, the method comprising:
 collecting input data using the electric rotating machine in a state in which the electric rotating machine is not connected to an operating voltage, said input data comprising a shaft height, a number of pole pairs and rating plate specifications of the machine, and said input the input data characteristic of the machine;   entering the input data as input for configuration application software;   transmitting the input data to the platform with the configuration application software, wherein the platform comprises commands that cause the method of  claim 6  to be carried out by the platform in order to provide a simulation model of the electric rotating machine.   
     
     
         21 . The method of  claim 20 , further comprising transferring the simulation model to the configuration application software, wherein the configuration application software transmits the simulation model to a sensor apparatus arranged on the machine. 
     
     
         22 . The method of  claim 21 , wherein the sensor apparatus is fastened to the machine. 
     
     
         23 . The method of  claim 20 , wherein the platform is a software platform. 
     
     
         24 . The method of  claim 20 , wherein the platform is a cloud platform. 
     
     
         25 . A method for determining an operating behavior of an electric rotating machine connected to an operating voltage, the method comprising:
 detecting a stray magnetic field outside the machine;   calculating a slip frequency and a synchronous frequency from the stray magnetic field;   calculating a slip from the slip frequency and the synchronous frequency;   providing the simulation model according to the method of  claim 6 ; and   determining the operating behavior using the slip, the synchronous frequency, and the simulation model.   
     
     
         26 . The method of  claim 25 , further comprising determining an operating point of the electric rotating machine based on the slip, the synchronous frequency and simulation model. 
     
     
         27 . An arrangement for determining an operating behavior of an electric rotating machine connected to an operating voltage, the arrangement comprising:
 a processing facility;   a sensor apparatus embodied to detect a stray magnetic field outside the electric rotating machine and to calculate from the detected stray magnetic field a slip frequency and a synchronous frequency and to transfer the calculated slip frequency and synchronous frequency to the processing facility; and   the simulation model provided in accordance with the method of  claim 6  stored on the processing facility, wherein the processing facility is configured, using the calculated slip frequency and synchronous frequency, to determine a slip and subsequently to determine the operating behavior of the electric rotating machine by the simulation model.