Reconstruction method of missing data in dam monitoring system based on multi-task Gaussian process
A Gaussian process and missing data technology, which is applied in the field of missing data reconstruction of dam safety monitoring system based on multi-task Gaussian process, can solve the problems of sensor monitoring data missing, data acquisition system failure, etc., and achieve the goal of improving monitoring and management capabilities Effect
Active Publication Date: 2022-07-19
HOHAI UNIV
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, due to the harsh working environment of the dam, frequent natural disasters such as floods, cold waves, and earthquakes, as well as data acquisition system failures, noise, and human construction interference, the loss of sensor monitoring data is inevitable and even occurs frequently
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
[0049] The present invention will be further described below in conjunction with the accompanying drawings. The following examples are only used to illustrate the technical solutions of the present invention more clearly, and cannot be used to limit the protection scope of the present invention.
[0050] like figure 1 As shown, a multi-task Gaussian process-based missing data reconstruction framework for a dam safety monitoring system is implemented based on the python environment.
[0051] Firstly, the raw sensor data of each monitoring index is obtained from the dam safety monitoring system, and the sensor data and the lack of raw monitoring data are counted. According to whether they work normally, the sensors are divided into normal working sensors and sensors with missing data.
[0052] like figure 2 As shown, the method for reconstructing missing data in a dam monitoring system based on a multi-task Gaussian process of the present invention includes:
[0053] Step 1...
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 method for reconstructing missing data of a dam safety monitoring system based on a multi-task Gaussian process. By constructing a training learning framework based on multi-task Gaussian process, taking the existing data of normal working sensors and the corresponding date as input, learning and training multiple sensor data at the same time, obtaining the estimated value of the missing data of the faulty sensor, and realizing the re-analysis of the missing data of the sensor. structure. Aiming at the problem of the lack of original monitoring data generally existing in the dam safety monitoring system, the invention makes full use of the correlation of multiple sensors in time and space, and realizes the reconstruction of the missing data of the faulty sensor. The method has good applicability to the situation of missing data of single or multiple sensors, high computational efficiency and high accuracy of results. It can be applied to the reconstruction of missing data from sensors in the dam safety monitoring system, and has broad application prospects, which is of great help in improving the monitoring and management capabilities of the dam safety monitoring system.
Description
technical field [0001] The invention relates to the field of dam safety monitoring, in particular to a method for reconstructing missing data in a dam safety monitoring system based on a multi-task Gaussian process. Background technique [0002] China has more than 98,000 reservoirs and dams of various types built and under construction. These hydraulic structure projects have played a huge social and economic role in flood control, irrigation, water supply, power generation and shipping, and are an important basic guarantee for the national economy. Ensuring the safe operation of dams throughout their life cycle is of great significance for maintaining major infrastructure investments and ensuring the safety of people's lives and properties downstream. [0003] In recent years, a large number of sensors have been used in the safety monitoring of engineering systems. The sensor-based dam safety monitoring system can continuously collect physical monitoring indicators relat...
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): G06K9/62G01D18/00
CPCG01D18/00G06F18/241
Inventor 李扬涛包腾飞舒小颂高治鑫朱征胡雨涵龚建张康
Owner HOHAI UNIV