Attitude prediction method for wave compensation system
A technology of compensation system and prediction method, applied in neural learning method, navigation through velocity/acceleration measurement, biological neural network model, etc., can solve problems such as difficult to obtain state equation, and achieve the effect of short time and low cost
Inactive Publication Date: 2019-05-10
NANJING UNIV OF SCI & TECH
View PDF6 Cites 12 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The frequency domain analysis method needs to know the state equation of the ship's motion, but due to the complexity of the ship's motion, it is difficult to obtain an accurate state equation
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
[0052] In this embodiment, during the operation of the ship, 6400 sets of data corresponding to a duration of 32 s are read from the inertial navigation system installed on the hull with an output frequency of 200 Hz. When installing the inertial navigation system, make sure that the X-axis points positively to the starboard side, the Y-axis points positively towards the bow, and the Z-axis points vertically upwards.
[0053] 6400 sets of data including 3-axis attitude angle θ α , θ β , θ γ and 3-axis acceleration information a x ,a y ,a z ,Such as figure 2 shown. In order to remove the burr signal in the attitude angle signal and the acceleration signal, the average value of every 4 data is taken as the data to be processed. Then use the sliding weighted average filtering method to filter the acceleration signal as follows:
[0054]
[0055] In the formula, a x ,a y ,a z For the acceleration value that obtains, h is the weighted average factor, adopts five-poin...
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 an attitude prediction method for a wave compensation system. The attitude prediction method comprises the following steps that first an attitude angle and acceleration data ofa hull are collected from an inertial navigation system fixed to the hull by the sampling frequency f, an attitude angle signal and an acceleration signal are obtained, and the attitude angle is converted into an Euler angle form; then the acceleration signal is filtered; then the spectrum of the acceleration signal is analyzed, and the spectrum is subjected to bandpass filtering to obtain an acceleration signal of an effective frequency band; then the acceleration signal of the effective frequency band is subjected to frequency domain integration, and a speed and displacement are obtained; and finally, the attitude angle and displacement are trained as the input of a neural network to obtain an attitude prediction model, and the attitude prediction can be completed according to the attitude prediction model. The attitude prediction method does not depend on the equation of a motion state of a ship, only needs to use the historical data of the motion of the ship to complete the real-time forecasting, and is simple and low in cost.
Description
technical field [0001] The invention belongs to the field of sea-based platform wave compensation systems, in particular to an attitude prediction method of the sea-wave compensation system. Background technique [0002] Due to the action of wind, waves and currents, the offshore floating production system inevitably produces swaying and heaving movements, which brings a lot of inconvenience and danger to offshore operations. Although there are currently professional attitude detection sensors, due to the delay of the sensor itself, the data processing time of the control algorithm and the hysteresis of the large inertia link, the accuracy of the compensation is seriously affected. Therefore, it is necessary to introduce a prediction algorithm to predict the attitude in advance. [0003] There are six degrees of freedom in the movement of the ship, and the angle information can be directly obtained through the inertial measurement system, while the displacement is generally ...
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): G01C21/16G06N3/04G06N3/08
Inventor 单梁符海涛徐海洋戴跃伟李军项文波苏智勇
Owner NANJING UNIV OF SCI & TECH