Unlock instant, AI-driven research and patent intelligence for your innovation.

A monitoring method for sensor data quality

A technology for data quality and data monitoring, applied in the fields of electrical digital data processing, digital data information retrieval, special data processing applications, etc., to achieve the effect of good versatility, strong robustness, and guaranteed reliability

Active Publication Date: 2021-01-29
XIDIAN UNIV
View PDF15 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The main purpose of the present invention is to propose a robust and versatile sensor data quality online and credible monitoring method to effectively solve the problems of real-time, complexity and credibility in the background technology, and to improve the online and credible monitoring of sensor data quality. Trusted Monitoring and its wide-ranging applications give guidance

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A monitoring method for sensor data quality
  • A monitoring method for sensor data quality
  • A monitoring method for sensor data quality

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] Such as figure 1 As shown, the sensor data quality online and trusted monitoring method includes algorithm initialization, reading sensor data and time stamp, detection and isolation of sensor data abnormal format, sensor data abnormal timing detection and isolation, sensor data abnormal format and abnormal timing Recovery and detection, isolation and recovery of outliers in sensor data.

Embodiment 2

[0049] Such as figure 2 As shown, the specific implementation of the above six steps is as follows:

[0050] step 1:

[0051] According to the real-time requirements of the sensor system, the requirements for computational complexity, and the theoretical basis and conditional assumptions of the algorithm, determine the initial monitoring window length L1 = 3, the maximum monitoring window length L2 = 50, and the length of each adjustment of the window size is Num = 1. The monitoring threshold Th, the absolute value of the front and rear data Var, the time stamp corresponding to the data to be monitored is t, the data is represented as data, the flag format is a space, the initial number of spaces Num1=0, and the two data and the corresponding the time stamp.

[0052] Step 2:

[0053] The read sensor data and time stamp are used as the input of the algorithm, and the sensor data and time stamp are data(t-2), data(t-1), data(t). Where data(t) is the data to be monitored. d...

Embodiment 3

[0064] Such as image 3 As shown, the data monitoring example of sensor abnormal format and abnormal timing, step1 is to convert all abnormal formats into blanks, and supplement the lost data according to the data timestamp, and the timestamp unit depends on the output frequency of the data; step2 is to make full use of Data around spaces Fill those spaces with appropriate data. Here is to use the interpolation method to take the average value of the data at both ends of the space and fill it into the space.

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

No PUM Login to View More

Abstract

The invention discloses a monitoring method for sensor data quality, including: algorithm theory basis and condition assumption, algorithm initialization, reading sensor data and time stamp, detection and isolation of sensor data abnormal format, detection and isolation of sensor data abnormal timing , Recovery of sensor data abnormal format and abnormal timing, detection, isolation and recovery of sensor data abnormal values. Through the classification and modeling of abnormal data, and based on several rules and double variable-length data monitoring windows, the detection, isolation and recovery of abnormal data are integrated, and relevant test platforms are built and a series of experiments are carried out to verify the results. The effectiveness of the proposed method, compared with the existing sensor data quality monitoring methods, the proposed method has strong robustness and good versatility, and can realize online and credible monitoring of sensor data quality, and has broad application prospects.

Description

technical field [0001] The invention belongs to the technical field of sensor data quality monitoring, and relates to a method for integrating detection, isolation and recovery of sensor abnormal data. Background technique [0002] A sensor is a device for detecting signals. It can perceive physical information and convert it into electrical signal output or other forms of output according to certain rules to meet the requirements of information processing and control. It has been widely used in industrial automation, agricultural Modernization, aerospace technology, military engineering, robotics, resource development, marine exploration, environmental monitoring, security, medical diagnosis, transportation, household appliances and other social development and various fields of human life. [0003] Sensor data is the cornerstone of sensor systems, and abnormal behavior of data will cause related systems to malfunction. Abnormal sensor data is caused by many factors such a...

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
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06F16/215G06F16/2458
CPCG06F16/215G06F16/2477
Inventor 刘公绪史凌峰辛东金
Owner XIDIAN UNIV