Sensor data noise reduction method based on multi-resolution wavelet

A multi-resolution, sensor technology, applied in the fields of genetic laws, instruments, genetic models, etc., can solve problems such as difficulty in self-adaptation, spectrum leakage, signal distortion, etc., and achieve self-adaptive window size, easy operation, and window size adjustment. Effect

Pending Publication Date: 2021-09-21
GUODIAN LONGYUAN ENERGY SAVING TECH
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] However, a large number of different sensors are used in the measurement of building information. Different sensors and sensors with different installation locations have different noise characteristics, and the above methods are difficult to achieve self-adaptive
For example, how large the sliding average window is is a very typical problem. If the sliding average window is large, it will lead to excessive averaging, and the slippage of the measured value in time and space will lead to data distortion; the short-time window Fourier The window size of the leaf transformation must be the same as the integer multiple of the data oscillation period, otherwise it will cause spectrum leakage and distort the reconstructed signal

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
  • Sensor data noise reduction method based on multi-resolution wavelet
  • Sensor data noise reduction method based on multi-resolution wavelet
  • Sensor data noise reduction method based on multi-resolution wavelet

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0068] Such as figure 1 as shown, figure 1 It shows a schematic flowchart of a multi-resolution wavelet-based sensor data noise reduction method provided by an embodiment of the present invention. The execution subject of the method in this embodiment is any computer or electronic device, and the noise reduction method may include the following step:

[0069] S01. Obtain the data of each sensor in the primary pipe network of the heating system within a specified period of time, and use the data of each sensor as the original signal.

[0070] For example, the data of each sensor within a specified period of time is acquired from the cloud device, and the acquired data of each sensor is used as the original signal.

[0071] In practical applications, the data of each sensor within a specified time period after abnormal data detection can also be acquired from the cloud device, and the acquired data of each sensor can be used as the original signal.

[0072] In this embodiment...

Embodiment 2

[0093] At present, when performing hydraulic calculations on the primary pipe network of the heating system, accurate pressure and flow sensor data are very important. These sensors are usually installed on various thermal stations, tube wells and some important pipelines, and continuously collect pressure and flow data at the installation point.

[0094] The sensor data is uploaded to the cloud database of the cloud device in real time for storage. When hydraulic calculation is required, the algorithm will first fetch the data of the corresponding time period from the database. At this time, start the method of the embodiment of the present invention to perform noise reduction processing on the data in the corresponding time period. Specifically, the following steps may be included:

[0095] The first step: take the data of a sensor target time period from the database as the original signal;

[0096] Step 2: Carry out Kolmogorov-Smirnov test (KS test) on the signal to obt...

Embodiment 3

[0129] This embodiment provides a data anomaly detection method, the data anomaly detection method can be applied before sensor data noise reduction, it is used to detect the anomaly of all sensor data at a certain time point, which includes the following steps :

[0130] P01. Obtain the data collected by each sensor during the water supply time period of the district heating operation system, and use the data of all sensors at each time point as a vector data to be measured.

[0131] For example, the electronic device in this embodiment can obtain the data collected by the sensors during the water supply time period of the district heating operation system from the cloud device. In this embodiment, the cloud device receives and stores the data collected by each sensor in the district heating operation system and uploaded by means of the relay device.

[0132] The data of the sensor in this embodiment includes: the data of the pressure sensor, the data of the temperature sens...

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 relates to a sensor data noise reduction method based on multi-resolution wavelets, and the method comprises the steps: S01, obtaining the data of each sensor in a primary pipe network of a heat supply system in a specified time period, and taking the data of each sensor as an original signal; S02, performing KS detection based on the original signal to obtain an optimal decomposition layer number J; and S03, adopting a pre-selected wavelet function and a primary function to process and reconstruct the original signal with the optimal decomposition layer number J, and obtaining a denoised target signal. The method provided by the invention solves the limitation of the existing method, realizes that the noise reduction of the original signal can be adaptively carried out under different resolutions, and avoids the problem caused by the need of setting the window size. The method is easy to use and high in universality.

Description

technical field [0001] The invention relates to the technical field of data noise reduction, in particular to a sensor data noise reduction method based on multi-resolution wavelets. Background technique [0002] In the field of smart buildings and smart municipalities, there are a large number of sensors, which are densely or sparsely distributed to collect various information data, such as temperature, pressure, flow, power, humidity and heat. The data collected by a large number of distributed sensors is the basis of big data analysis and intelligent processing. Due to the large number and wide distribution of sensors, it is inevitable that some of them will be abnormal. Especially in the space where a large number of wireless sensors are deployed, how to ensure the credibility and reliability of the basic data collected by the sensors is particularly critical. [0003] The data uploaded by the sensor can be considered to be composed of two parts: one is the deed value o...

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 Applications(China)
IPC IPC(8): G06K9/00G06K9/62G06N3/12
CPCG06N3/126G06F2218/06G06F2218/12G06F18/2411G06F18/214
Inventor 张源张同卫李硕张芬芳
Owner GUODIAN LONGYUAN ENERGY SAVING TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap