US Patent Application 18005897. ABNORMALITY DETECTION DEVICE AND ABNORMALITY DETECTION PROGRAM simplified abstract

From WikiPatents
Jump to navigation Jump to search

ABNORMALITY DETECTION DEVICE AND ABNORMALITY DETECTION PROGRAM

Organization Name

HONDA MOTOR CO., LTD.


Inventor(s)

Yuito Kubo of Minato-ku, Tokyo (JP)


Kyosuke Takekoshi of Minato-ku, Tokyo (JP)


Eiji Oshima of Minato-ku, Tokyo (JP)


ABNORMALITY DETECTION DEVICE AND ABNORMALITY DETECTION PROGRAM - A simplified explanation of the abstract

  • This abstract for appeared for US patent application number 18005897 Titled 'ABNORMALITY DETECTION DEVICE AND ABNORMALITY DETECTION PROGRAM'

Simplified Explanation

The abstract describes an abnormality detection device that can analyze vehicle signals to identify abnormalities. The device divides the vehicle signals into time windows and extracts the data within each window. It then uses this data to create learned information through a learning process. The device can reconstruct the time-series data in the vehicle signal based on the learned information and calculate the error between the original and reconstructed data. Using this error and the learned information, the device can determine the degree of abnormality in the vehicle signal.


Original Abstract Submitted

An abnormality detection device includes: a time window process part configured to divide, by time windows, each of a plurality of vehicle signals each including a time-series data and to extract the data included in the time window; a learning part configured to create learned information by means of learning using the time-series data in the vehicle signal divided by the time windows; and an abnormality degree calculation part configured to reconstruct the time-series data in the vehicle signal divided by the time windows, based on the learned information, thereby calculate an error between before and after the reconstruction, and further calculate an abnormality degree of the vehicle signal based on the calculated error and the learned information.