Siemens Corporate Research, Inc.

Stephen J Hanson

Thomas Petsche

Angelo R Marcantonio

Robert W Schwanke

A computer-based system and method for ascertaining anomalies in an electric motor, includes computing and processing a set of Fast Fourier Transforms (FFT's) of the supply current waveforms for a motor known to be in a normal condition to create a feature set of input vectors. The input vector assignments for all possible cluster groupings 1 through n are derived using Ward's method. The method includes computing the Approximate Weight of Evidence (AWE) for each cluster grouping then selecting that count associated with a maximum AWE and designating this count as s. For each cluster in each grouping 1 through s, the method finds the member vector farthest from the cluster's centroid and defines this as the cluster's radius. A single input sample for a motor under supervision is read in, following by computing and processing an FFT based on the input sample for a newly generated feature vector and then checking whether the newly generated feature vector is inside any of the clusters 1 through s as defined for each cluster by its respective radius, and if not, outputting a warning signal.

Method and system for ascertaining anomalies in electric motors

A method for detecting a departure from normal operation of an electric motor comprises obtaining a set of normal current measurements for a motor being monitored; training a neural network auto-associator using the set of normal current measurements; making current measurements for the motor in operation; comparing the current measurements with the normal current measurements; and indicating abnormal operation whenever the current measurements deviate more than a predetermined amount from the normal current measurements. The method models a set of normal current measurements for the motor being monitored, and indicates a potential failure whenever measurements from the motor deviate significantly from a model. The model takes the form of an neural network auto-associator which is 'trained'--using current measurements collected while the motor is known to be in a normal operating condition--to reproduce the inputs on the output. A new set of current measurements are classified as 'good' or 'bad' by first transforming the measurement using a Fast Fourier Transform (FFT) and an internal scaling procedure, and then applying a subset of the transformed measurements as inputs to the neural network auto-associator. A decision is generated based on the difference between the input and output of the network.

Neural network auto-associator and method for induction motor monitoring

Given a set of objects (A, B, C, . . . ), each described by a set of attribute values, and given a classification of these objects into categories, a similarity function accounts well for this classification when only a small number of objects are not correctly classified. A method for modelling a similarity function using a neural network comprises the steps of: (a) inputting feature vectors to a raw input stage of a neural network respectively for object S in the given category, for other objects G in the same category being compared the object S, and for object B outside the given category; (b) coupling the raw inputs of feature vectors for S, G, and B to an input layer of the neural network performing respective set operations required for the similarity function so as to have a property of monotonicity; (c) coupling the input elements of the input layer to respective processing elements of an hidden layer of the neural network for computing similarity function results adaptively with different values of a coefficient w of the similarity function; (d) coupling the processing elements of the hidden layer to respective output elements of an output layer of the neural network for providing respective outputs of an error function measuring the extent to which object S is more similar to object G than to object B; and (e) obtaining an optimal coefficient w by back propagation through the neural network which minimizes the error outputs of the error function.

Growing community of inventors

Princeton, NJ, United States of America

Stephen J Hanson