Browsing Texas A&M University Patents by Author "Parlos, Alexander G."

Now showing items 1-5 of 5

    • Condition assessment and life expectancy prediction for devices 
      Parlos, Alexander G. (United States. Patent and Trademark Office; Texas A&M University. Libraries, 2006-04-04)
      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 ...
    • Method and system for determining induction motor speed 
      Parlos, Alexander G.; Bharadwaj, Raj M. (United States. Patent and Trademark Office; Texas A&M University. Libraries, 2004-03-30)
      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, ...
    • Method and system for early detection of incipient faults in electric motors 
      Parlos, Alexander G.; Kim, Kyusung (United States. Patent and Trademark Office; Texas A&M University. Libraries, 2003-07-08)
      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 ...
    • Method and system for training a recurrent network 
      Parlos, Alexander G.; Atiya, Amir F. (United States. Patent and Trademark Office; Texas A&M University. Libraries, 2005-11-08)
      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 ...
    • Neural node network and model, and method of teaching same 
      Parlos, Alexander G.; Atiya, Amir F.; Fernandez, Benito; Tsai, Wei K.; Chong, Kil T. (United States. Patent and Trademark Office; Texas A&M University. Libraries, 1995-12-26)
      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 ...