Multi-vibration signal fusion method based on fuzzy preference relation
A preference relationship and signal fusion technology, applied in character and pattern recognition, instruments, calculations, etc., can solve problems such as complex calculations, poor dynamics, and inability to adapt to influences, and achieve strong anti-interference ability, suppress noise, and good dynamic effect
Active Publication Date: 2019-03-15
SHANDONG COMP SCI CENTNAT SUPERCOMP CENT IN JINAN
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The average weighting method lacks dynamic adaptability and cannot adapt to the influence of random factors
The adaptive weighting algorithm requires prior knowledge of the sensor, the calculation is more complicated, and the dynamics are not very good
The Kalman filter algorithm has good signal tracking and estimation capabilities, but due to the influence of signal noise, the sensor signals provided by different sensors will produce certain deviations, which is not conducive to the prediction and estimation of real signals
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
[0035] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.
[0036] First, let’s explain how to obtain the fuzzy preference relationship:
[0037] In neural networks, the function expressed by formula (5) is commonly used to calculate the fuzzy preference relationship between two samples:
[0038]
[0039] Come in to characterize the ordered structure between samples. This paper draws on this idea, introduces the fuzzy preference relationship to represent the degree of preference between signals, and then determines the weight of each sensor in data fusion.
[0040] Suppose x(n) and y(n) are two deterministic signals, then the fuzzy preference relationship between the instantaneous values at time m can be expressed as formula (6), and the corresponding function curve is as figure 1 shown.
[0041]
[0042] Among them, k is a parameter greater than 0, controlling the degree of preference.
[0043] Depe...
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 multi-vibration signal fusion method based on the fuzzy preference relationship of the present invention includes: a). Acquiring the filtered signal; b). Calculating the fuzzy preference relationship; c). Calculating the comprehensive fuzzy preference relationship; d). Calculating the weight; e). Calculate the fusion signal value; f). Calculate the fusion signal value in the entire acquisition period; g). Obtain the ideal signal. The multi-vibration signal fusion method based on the fuzzy preference relationship of the present invention aims at how to comprehensively utilize the information of multiple sensors to improve the accuracy of fault diagnosis, studies the weighted fusion algorithm, proposes a data fusion algorithm based on the fuzzy preference relationship, and eliminates irrelevant information , to effectively fuse the data and provide more accurate information for feature extraction and identification of fault diagnosis.
Description
technical field [0001] The present invention relates to a multi-vibration signal fusion method, more specifically, to a multi-vibration signal fusion method based on a fuzzy preference relationship. Background technique [0002] In the fault diagnosis process, the reliability and accuracy of the diagnosis results are closely related to the data collection. However, due to the complexity of equipment operating conditions and fault information, it is difficult for a single sensor to obtain global information about equipment status, and the information provided is often incomplete, which will inevitably lead to low accuracy of fault diagnosis, and even missed detection and misdiagnosis. With the development of data fusion technology, multi-sensor data fusion technology is gradually applied in the field of fault diagnosis, which overcomes the limitation of single sensor. Data fusion can be divided into three levels according to its level of abstraction in the sensor processing ...
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): G06K9/62
CPCG06F18/251G06F18/25G06F18/253
Inventor 郝慧娟王茂励郝凤琦唐勇伟程广河李娟
Owner SHANDONG COMP SCI CENTNAT SUPERCOMP CENT IN JINAN