Unmanned ship environment adjusting method based on OS-ELM algorithm
A technology for environmental regulation and unmanned ships, applied in the direction of neural learning methods, neural architecture, biological neural network models, etc., can solve the problem of in-depth research on big data processing technology, the stability of unmanned ships cannot be guaranteed, and single data conclusions and other problems, to achieve the effect of excellent generalization performance, fast information processing speed, and strong adaptability
Inactive Publication Date: 2017-11-07
WUHAN UNIV OF TECH
View PDF1 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] However, the amount of data received by the internal and external environment perception sensors is large and needs to be processed quickly, but the research on related big data processing technology needs to be further studied
At present, there are a small number of literatures on the data processing algorithm of unmanned ships, but most of the processed data is a single conclusion, and most of the algorithms are realized by increasing the number of nodes and increasing the cost, such as navigation state perception based on inertial navigation system method, research on MEMS gyroscope denoising based on wavelet analysis, etc.
However, if the cost is controlled and the number of nodes is reduced, the calculation amount will increase, and the calculation error will increase, and the stability of the unmanned ship cannot be guaranteed.
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] In order to have a clearer understanding of the technical features, purposes and effects of the present invention, the specific implementation manners of the present invention will now be described in detail with reference to the accompanying drawings.
[0045] Such as figure 1 Shown, the unmanned ship environment regulation method based on OS-ELM algorithm described in the present invention, comprises the following steps:
[0046] 101. Build an experimental environment for unmanned ships and collect navigation data of unmanned ships.
[0047] Install internal environmental sensors and external environmental sensors on unmanned ships;
[0048] The external environment sensor is connected to the external environment host computer;
[0049] The internal environment sensor is connected with the internal environment host computer through the experimental field bus;
[0050] The upper computer in the internal environment and the upper computer in the external environment ...
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 belongs to the unmanned ship artificial intelligence field, to be specific, relates to an unmanned ship environment adjusting method based on an OS-ELM algorithm. The unmanned ship environment adjusting method comprises steps that the experimental environment of the unmanned ship is constructed, and the shipping data of the unmanned ship is acquired; according to the shipping data of the unmanned ship, a sample set is formed; the sample set is processed based on the OS-ELM algorithm, a coupling relation between the inner environment and the outer environment of the unmanned ship is acquired; matching of data acquired by the unmanned ship during actual shipping according to the coupling relation is carried out, and the inner environment and the outer environment of the unmanned ship during the actual shipping are adjusted. The inner environment and the outer environment of the unmanned ship during the shipping are researched at the same time, and calculation is completed under a condition of limited samples, and in addition, learning speed is fast, and calculation accuracy is high.
Description
technical field [0001] The invention belongs to the field of unmanned ship artificial intelligence, in particular to an unmanned ship environment regulation method based on the OS-ELM algorithm. Background technique [0002] In recent years, artificial intelligence technology has been applied more and more in various fields. However, due to the limitation of application requirements and technical level, the research progress of domestic unmanned ships is relatively slow. Most unmanned ships are developed as unmanned remote control vehicles. Yes, the control method is also mostly remote control. Therefore, it is necessary to design an unmanned ship environment perception system that can accurately identify the marine environment, surrounding targets, and accurately judge the navigation status and motion posture of the unmanned ship, assist the unmanned ship to make independent decisions, and develop from remote control to intelligent. [0003] Most of today's environmental p...
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 IPC IPC(8): G06N3/04G06N3/08
CPCG06N3/08G06N3/048
Inventor 赵东明柳欣杨田田
Owner WUHAN UNIV OF TECH