Rolling optimization control method based on data-driven learning
A technology of rolling optimization and control method, applied in the field of automation, can solve the problem of simultaneous evaluation of difficult and multiple signal sources, and achieve the effect of improving anti-interference ability
Active Publication Date: 2020-11-06
HANGZHOU DIANZI UNIV
View PDF2 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Traditional signal source detection and location methods usually use radial basis function network, Kalman filter, or particle filter to complete the location evaluation of signal sources in simple environments based on signal strength and direction information, but these methods are difficult to complete in complex environments. Simultaneous evaluation of multiple source locations
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0044] The technical solution of the present invention will be further described below in conjunction with an embodiment.
[0045] Taking the wireless sensor network as an example, set the monitoring environment to be 10 meters long and 10 meters wide, establish a coordinate system, and divide the monitoring environment into small areas of 50×50. Among them, each sensor node sends a signal sequence in a short time, and it is assumed that the interval between two sendings is 5 seconds. The specific implementation steps are as follows:
[0046] The first step: establish the dynamic model of the quadrotor UAV, the specific steps are as follows:
[0047] a. The dynamic model of the quadrotor UAV is shown in formula (13).
[0048]
[0049] Among them: X, Y, and Z respectively represent the position of the quadrotor UAV in the inertial coordinate system. φ, θ, ψ represent the roll angle, pitch angle and yaw angle of the quadrotor UAV in the inertial coordinate system, respecti...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a rolling optimization control method based on data-driven learning. The method comprises the following steps: discretizing a continuous search environment, and predicting thepossible position of a signal source by Gaussian process regression according to a large number of collected signal intensity data; then, on the basis of the possible position of the signal source, designing a cost function, and generating an optimal control sequence of a quad-rotor unmanned aerial vehicle by adopting a rolling optimization method; finally, according to the optimal control sequence, acquiring the optimal motion trail of the quad-rotor unmanned aerial vehicle, inputting the first position into a controller of the quad-rotor unmanned aerial vehicle, and realizing searching and positioning of a signal source. According to the method, the defects in the prior art are overcome; through the rolling optimization control method based on data-driven learning, the quad-rotor unmanned aerial vehicle can predict the possible position of the signal source through the detected signal intensity information, the optimal reference track is generated, uncertain events can be well managed, and the signal source can be rapidly located.
Description
technical field [0001] The invention belongs to the technical field of automation, and in particular relates to a data-driven learning-based rolling optimization control method for signal source detection and positioning. Background technique [0002] Signal source detection and location are of great significance to human safety, such as environmental monitoring, sensor positioning, rescue of people in distress, and so on. In view of the above problems, quadrotor drones are usually used to complete the detection and positioning of signal sources. Traditional signal source detection and location methods usually use radial basis function network, Kalman filter, or particle filter to complete the location evaluation of signal sources in simple environments based on signal strength and direction information, but these methods are difficult to complete in complex environments. Simultaneous evaluation of multiple source locations. In addition, due to the possible occurrence of u...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G05B13/04
CPCG05B13/042
Inventor 吕强胡晨仲朝亮石厅林伟杰
Owner HANGZHOU DIANZI UNIV