Back to results
US 12,742,906 B2Granted
Wind condition learning device, wind condition predicting device, and drone system
AssigneeMitsubishi Electric Corporation
InventorsMasaharu Imaki, Shumpei Kameyama, Yusuke Ito
Life of this patent
Estimating the term…
Abstract
A wind condition learning device according to the present disclosed technique includes: an input terminal to which a learning data set is input; and a calculator including AI to perform learning on the basis of the learning data set, in which one piece of the learning data set is a wind condition altitude distribution model value following a power law on an inflow side, and the other piece of the learning data set includes a wind speed average value, a wind speed maximum value, turbulence energy, or turbulence intensity in a wind condition distribution of an environmental space obtained by simulation.
Claims6
A drone system comprising:
- a drone configured to fly in an environmental space;
- a controller configured to pilot the drone;
- a wind condition measuring instrument;
- a wind condition learning device;
- and
- a wind condition predicting device comprising:
- an input terminal to which a learning data set is input;
- a calculator including artificial intelligence (AI) to perform learning by referring to the learning data set;
- and
- an output terminal to output a wind condition distribution predicted and calculated, wherein
- one piece of the learning data set is a wind condition altitude distribution model value following a power law on an inflow side, and the other piece of the learning data set includes turbulence energy, or turbulence intensity in a wind condition distribution of the environmental space obtained by simulation,
- the wind condition measuring instrument is a light detection and ranging (LiDAR) instrument, a radar, or a sonar, and
- wherein the wind condition learning device is configured to
- divide an environmental area around the drone into wire frame meshes defining a plurality of small areas and allocating vectors to the small areas, wherein each of the vectors represents a wind direction and wind speed for a respective small area among the plurality of small are as;
- and wherein the drone system is configured to
- predict the wind condition distribution using the vectors of the plurality of small areas and the AI;
- and
- transmit a warning message to the controller by referring to the predicted wind condition distribution of the environmental space and a current position of the drone in a case where it is determined that a warning is necessary for the drone.
15 more elements
A drone system comprising:
- a drone configured to fly in an environmental space;
- a controller configured to pilot the drone;
- a wind condition measuring instrument;
- a wind condition learning device;
- and
- a wind condition predicting device comprising:
- an input terminal to acquire actual measurement observation data of the wind condition measuring instrument;
- a calculator including a trained artificial intelligence (AI), to predict and calculate a wind condition distribution of the environmental space by referring to the actual measurement observation data;
- and
- an output terminal to output the wind condition distribution predicted and calculated;
- wherein, the wind condition distribution includes turbulence energy, or turbulence intensity,
- the wind condition measuring instrument is a light detection and ranging (LiDAR) instrument, a radar, or a sonar, and
- wherein the wind condition learning device is configured to
- divide an environmental area around the drone into wire frame meshes defining a plurality of small areas and allocating vectors to the small areas, wherein each of the vectors represents a wind direction and wind speed for a respective small area among the plurality of small areas, and wherein
- the drone system is configured to
- predict the wind condition distribution using the vectors of the plurality of small areas and the AI;
- and
- transmit a warning message to the controller by referring to the predicted wind condition distribution of the environmental space and a current position of the drone in a case where it is determined that a warning is necessary for the drone.
15 more elements
Dependencies are inferred from the claim text.