The University of Texas System

Alexander G Parlos

Amir F Atiya

Wei Kang Tsai

Benito Fernandez

Raj M Bharadwaj

Kil T Chong

Kyusung Kim

Gang Li

For determining rotation of a de-energized electric machine without accessing the machine, wherein the machine in the energized state rotates in a reference direction, a computer system determines, for at least one waveform of at least one set of multi-phase electrical power indicia measured remotely from the machine, that a first time segment of the at least one waveform corresponds to an energized state of the machine and that a second time segment of the at least one waveform corresponds to a de-energized state of the machine. The computer system also determines that the machine in the de-energized state has rotated in a direction reverse to the reference direction, wherein the determining that the machine in the de-energized state has rotated in a direction reverse to the reference direction includes comparing the first and second time segments of the at least one waveform.

Technology for sensorless detection of reverse rotation and speed estimation for electric machines

Assessing the condition of a device includes receiving signals from a sensor that makes electrical measurements of the device. An expected response of the device is estimated in accordance with the received signals, and a measured response of the device is established in accordance with the received signals. An output residual is calculated according to the expected response and the measured response. The condition of the device is assessed by identifying a fault of the device in accordance with the output residual.

Condition assessment and life expectancy prediction for devices

A method for training a recurrent network represented by x(k+1)=f(W x(k)), where W is a weight matrix, x is the output of the network, and K is a time index includes (a) determining the weight matrix at a first time increment, (b) incrementing the time increment associated with a received data point, and (c) determining a change in the weight matrix at the incremented time interval according to the formula:

Method and system for training a recurrent network

A non-linear, semi-parametric neural network-based adaptive filter is utilized to determine the dynamic speed of a rotating rotor within an induction motor, without the explicit use of a speed sensor, such as a tachometer, is disclosed. The neural network-based filter is developed using actual motor current measurements, voltage measurements, and nameplate information. The neural network-based adaptive filter is trained using an estimated speed calculator derived from the actual current and voltage measurements. The neural network-based adaptive filter uses voltage and current measurements to determine the instantaneous speed of a rotating rotor. The neural network-based adaptive filter also includes an on-line adaptation scheme that permits the filter to be readily adapted for new operating conditions during operations.

Method and system for determining induction motor speed

A method and system for early detection of incipient faults in an electric motor are disclosed. First, current and voltage values for one or more phases of the electric motor are measured during motor operations. A set of current predictions is then determined via a neural network-based current predictor based on the measured voltage values and an estimate of motor speed values of the electric motor. Next, a set of residuals is generated by combining the set of current predictions with the measured current values. A set of fault indicators is subsequently computed from the set of residuals and the measured current values. Finally, a determination is made as to whether or not there is an incipient electrical, mechanical, and/or electromechanical fault occurring based on the comparison result of the set of fault indicators and a set of predetermined baseline values.

Method and system for early detection of incipient faults in electric motors

The present invention is a fully connected feed forward network that includes at least one hidden layer 16. The hidden layer 16 includes nodes 20 in which the output of the node is fed back to that node as an input with a unit delay produced by a delay device 24 occurring in the feedback path 22 (local feedback). Each node within each layer also receives a delayed output (crosstalk) produced by a delay unit 36 from all the other nodes within the same layer 16. The node performs a transfer function operation based on the inputs from the previous layer and the delayed outputs. The network can be implemented as analog or digital or within a general purpose processor. Two teaching methods can be used: (1) back propagation of weight calculation that includes the local feedback and the crosstalk or (2) more preferably a feed forward gradient decent which immediately follows the output computations and which also includes the local feedback and the crosstalk. Subsequent to the gradient propagation, the weights can be normalized, thereby preventing convergence to a local optimum. Education of the network can be incremental both on and off-line. An educated network is suitable for modeling and controlling dynamic nonlinear systems and time series systems and predicting the outputs as well as hidden states and parameters. The educated network can also be further educated during on-line processing.

Growing community of inventors

College Station, TX, United States of America

Alexander G Parlos