Patents by Inventor Siheng Chen

Siheng Chen has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 10351150
    Abstract: This invention relates to a vehicle-based infrastructure diagnostic apparatus to assist in the maintenance of rail networks. This is a complete system—from the acquisition of vibration signals in a moving vehicle, to the presentation of the infrastructure changes to the maintenance workers. This apparatus relies on novel techniques to account for the variable speed of the train (making it useful even on non-dedicated rail vehicles) and novel techniques to normalize for various environmental conditions. This system could help maintenance departments identify and remediate anomalies more rapidly, as well as trace network deterioration over time. The apparatus consists of low-cost unobtrusive sensors, software for data analysis, and hardware that makes it easy to deploy widely even on existing rail networks.
    Type: Grant
    Filed: May 31, 2016
    Date of Patent: July 16, 2019
    Assignee: Carnegie Mellon University
    Inventors: George Lederman, Jacobo Bielak, Hae Young Noh, James H Garrett, Siheng Chen, Jelena Kovacevic
  • Patent number: 10229533
    Abstract: Systems and methods for determining a pattern in time series data representing an operation of a machine. A memory to store and provide a set of training data examples generated by a sensor of the machine, wherein each training data example represents an operation of the machine for a period of time ending with a failure of the machine. A processor configured to iteratively partition each training data example into a normal region and an abnormal region, determine a predictive pattern absent from the normal regions and present in each abnormal region only once, and determine a length of the abnormal region. Outputting the predictive pattern via an output interface in communication with the processor or storing the predictive pattern in memory, wherein the predictive pattern is a predictive estimate of an impending failure and assists in management of the machine.
    Type: Grant
    Filed: November 22, 2016
    Date of Patent: March 12, 2019
    Assignee: Mitsubishi Electric Research Laboratories, Inc.
    Inventors: Dong Tian, Siheng Chen, Chen Feng, Anthony Vetro
  • Publication number: 20180122137
    Abstract: Systems and methods for determining a pattern in time series data representing an operation of a machine. A memory to store and provide a set of training data examples generated by a sensor of the machine, wherein each training data example represents an operation of the machine for a period of time ending with a failure of the machine. A processor configured to iteratively partition each training data example into a normal region and an abnormal region, determine a predictive pattern absent from the normal regions and present in each abnormal region only once, and determine a length of the abnormal region. Outputting the predictive pattern via an output interface in communication with the processor or storing the predictive pattern in memory, wherein the predictive pattern is a predictive estimate of an impending failure and assists in management of the machine.
    Type: Application
    Filed: November 22, 2016
    Publication date: May 3, 2018
    Inventors: Dong Tian, Siheng Chen, Chen Feng, Anthony Vetro