Optimization of cyber-physical systems
AssigneeNEC Corporation
InventorsShuchu Han, LuAn Tang, Haifeng Chen
Life of this patent
Estimating the term…
Abstract
Methods and systems for optimizing performance of a cyber-physical system include training a machine learning model, according to sensor data from the cyber-physical system, to generate one or more parameters for controllable sensors in the cyber-physical system that optimize a performance indicator. New sensor data is collected from the cyber-physical system. One or more parameters for the controllable sensors are generated using the trained machine learning module and the new sensor data. The one or more parameters are applied to the controllable sensors to optimize the performance of the cyber-physical system.
Claims19
A method for optimizing performance of a cyber-physical system, comprising:
- training a machine learning model, according to sensor data from the cyber-physical system, to generate one or more parameters for controllable sensors in the cyber-physical system that optimize a performance indicator;
- collecting new sensor data from the controllable sensors the cyber-physical system, wherein the controllable sensors measure controllable properties of the cyber-physical system;
- generating one or more parameters for the controllable sensors using the trained machine learning model and the new sensor data;
- and
- applying the one or more parameters to the controllable sensors to change the controllable properties of the cyber-physical system to optimize the performance of the cyber-physical system.
A method for optimizing performance of a cyber-physical system, comprising:
- training an artificial neural network, according to sensor data from the cyber-physical system, to generate one or more parameters for controllable sensors in the cyber-physical system that optimize a performance indicator, wherein the artificial neural network includes a hidden layer that has a plurality of radial basis function neurons that accept sensor data inputs from a plurality of sensors and that further has a constant value neuron;
- collecting new sensor data from the controllable sensors of the cyber-physical system, wherein the controllable sensors measure controllable properties of the cyber-physical system;
- generating one or more parameters for the controllable sensors using the trained artificial neural network and the new sensor data;
- and
- applying the one or more parameters to the controllable sensors to change the controllable properties of the cyber-physical system to optimize the performance of the cyber-physical system.
A system for optimizing performance of a cyber-physical system, comprising:
- model trainer configured to train a machine learning model, according to sensor data from the cyber-physical system, to generate one or more parameters for controllable sensors in the cyber-physical system that optimize a performance indicator;
- an optimizer configured to generate one or more parameters for the controllable sensors using the trained machine learning model and new sensor data, wherein the controllable sensors measure controllable properties of the cyber-physical system;
- and
- a sensor interface configured to collect the new sensor data from the controllable sensors of the cyber-physical system and to apply the one or more parameters to the controllable sensors to change the controllable properties of the cyber-physical system to optimize the performance of the cyber-physical system.
Dependencies are inferred from the claim text.