Disaster early warning method, system, equipment and storage medium based on multi-sensor
A multi-sensor, sensor technology, applied in neural learning methods, instruments, alarms, etc., can solve the problems of low efficiency of manual observation methods, measurement noise and gross error misjudgment, etc., to improve reliability, accuracy and effectiveness, The effect of improving accuracy
Active Publication Date: 2022-07-01
湖南北斗微芯产业发展有限公司
View PDF6 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0007] The efficiency of the manual observation method is too low, and the method of setting the threshold is very susceptible to the interference of sensor measurement noise and gross error, causing misjudgment
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
[0073] The following describes in detail the embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary, only used to explain the present invention, and should not be construed as a limitation of the present invention.
[0074] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", " Rear, Left, Right, Vertical, Horizontal, Top, Bottom, Inner, Outer, Axial, Radial, Circumferential The orientation or positional relationship indicated by etc. is based on the orientation or positional relationship shown in the accompanying drawings, and is only for the convenience of describing the p...
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 multi-sensor-based disaster early warning method, system, equipment and storage medium. First, the time series data collected by each sensor is denoised, which reduces the interference of sensor measurement noise on the one hand, and calculates the noise standard deviation on the other hand. , to improve the accuracy and effectiveness of subsequent migration judgment; the gross error, slow change speed and migration are used together as parameters to be estimated to build an estimation model to avoid the influence of gross error and slow change speed on migration judgment, which can greatly improve The accuracy of time series data migration judgment; the estimation model effectively estimates the migration parameters, slowly changing speed parameters and gross error parameters according to the method of stage iterative estimation, and tests the validity of the estimated parameters to improve the reliability of parameter estimation; Estimated time series data is obtained by checking the qualified parameters; finally, whether there is a significant deviation is judged according to the residual and noise standard deviation between the denoised time series data and the estimated time series data, and the present invention can improve the accuracy of disaster warning.
Description
technical field [0001] The invention relates to the technical field of disaster early warning, in particular to a multi-sensor-based disaster early warning method, system, equipment and storage medium. Background technique [0002] With the achievement of economic and social construction, the safety risks of geological disasters and engineering infrastructure have gradually become prominent. By laying out a sensor network, calculating the time series data collected by the sensor, and detecting abnormal changes in the time series data, disaster analysis and security early warning can be realized. [0003] When the disaster develops, the time series data collected by the sensor will shift. At present, the methods used for time series data offset detection of a single sensor mainly include: [0004] 1. Manually observe the data curve of each sensor, and identify abnormal data with the naked eye; [0005] 2. Set a threshold, when the sensor data exceeds the threshold, it is j...
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 Patents(China)
IPC IPC(8): G08B21/10G08B31/00G06F17/10G06F17/14G06N3/04G06N3/08
CPCG08B21/10G08B31/00G06F17/10G06F17/148G06N3/04G06N3/08
Inventor 甘雨赵星宇杨世忠
Owner 湖南北斗微芯产业发展有限公司