Honda Research Institute Europe Gmbh

Sebastian Schmitt

Hideaki Shimamura

Markus Olhofer

Yuki Matsui

Tobias Rodemann

Stefano Squartini

Andrea Castellani

A computer-implemented method for detecting an anomalous operating status of a technical system. A training phase obtains a first set of time-series values generated by a digital twin simulation of the technical system for a regular operating status and a second set of time-series values measured by sensors in an anomalous operating status, and adjusts parameters of a machine learning model for detecting the regular operating status and for discriminating data samples of the regular operating status from data samples of the anomalous operating status to generate a trained machine learning model. A monitoring phase obtains a set of multivariate time-series values measured by the sensors, calculates an anomaly score value for determining whether the technical system is in an anomalous operating status based on the obtained set of multi-variate time-series values and the trained machine learning model, and outputs a signal including information on the determined anomalous operating status.

Method and system for semi-supervised deep anomaly detection for large-scale industrial monitoring systems based on time-series data utilizing digital twin simulation data

A method for determining an anomalous operating state in a charging infrastructure system for batteries is proposed. For a charging process at a charging station, the method includes obtaining target characteristics of the charging process, determining process parameters for the charging process, performing the charging process, determining a performance metric for the performed charging process, generating and storing a data set for the performed charging process in a database. For multiple charging processes, the method includes calculating and storing at least one first set of statistic data for a first time interval and at least one second set of statistic data for a second time interval, comparing the first set of statistic data with the second set of statistic data to compute a set of difference values for each stored data set, and determining whether the charging infrastructure system operates in an anomalous operating state.

Method and system for detecting faults in a charging infrastructure system for electric vehicles

A system and method are provided for setting parameters in an autonomous working device. The autonomous working device can be controlled based on a plurality of parameters. For each of a plurality of different working environments a set of sensor values is generated. The plurality of sets is partitioned into categories, each category corresponding to a prototypical working environment. The parameters for each category are optimized to find an optimized parameter set for each prototypical working environment. For an individual working environment, an individual set of sensor values that the sensors of the autonomous working device produce is generated. Based at least on the individual set of sensor values, the prototypical working environment showing highest similarity to the individual environment is determined, and the parameters in the autonomous working device are set according to the optimized parameter set corresponding to the determined prototypical working environment.

Growing community of inventors

Offenbach, Germany

Sebastian Schmitt