Fault positioning method for predicting traveling-wave range arrival time based on NARNN model
A technology of fault location and model prediction, which is applied in the direction of fault detection, fault location, and electrical measurement according to conductor type, which can solve problems such as interference by noise and inaccurate identification of wave heads, and achieve high precision and reliability.
Active Publication Date: 2019-11-29
新沂茂源实业发展有限公司
View PDF9 Cites 6 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] In order to solve the technical problems proposed by the above-mentioned background technology, the present invention aims to provide a fault location method based on the NARNN (non-linear autoregressive neural network) model to predict the arrival time of the traveling wave head, which overcomes the inaccurate recognition of the wave head of the traditional traveling wave method and is disturbed by noise. and other defects
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
[0039] The present invention will be further described below in conjunction with the accompanying drawings.
[0040] The topology of a two-terminal ranging transmission line is as follows: figure 2 As shown, the present invention proposes a fault location method based on the NARNN (non-linear autoregressive neural network) model to predict the arrival time of the traveling wave head, and its overall process is as follows figure 1 shown, including the following steps:
[0041] (1) Set measurement points at the first and last ends of the transmission line, denoted by m and n respectively, and the fault point is denoted by f. After a fault occurs on the transmission line, the original voltage traveling wave signals at the first point m and the end n points are extracted respectively, and then phase-mode transformed to obtain the original line-mode voltage traveling wave signal, respectively denoted as and Among them, the subscript indicates m point and n point, and the supe...
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 fault positioning method for predicting traveling-wave range arrival time based on a NARNN model. The method comprises the following steps: firstly processing an acquired initial voltage traveling-wave signal by utilizing a derivative method, and initially determining the traveling-wave range arrival time; and then selecting a piece of data before the traveling-wave rangearrival time as a training set, and predicting on the traveling-wave waveform by utilizing the NARNN model; and finally making difference between the waveform predicted by the NARNN model and the actual waveform, and checking the obtained difference by utilizing KPSS to obtain the wave range arrival precise time; and performing fault positioning by utilizing a double-end ranging method. The influence on the fault precise positioning by the high-frequency noise is avoided, and the influence by the fault resistance and the fault initial phase angel can be avoided, and the method is suitable forthe grid fault positioning containing the high-frequency noise, and has high precision and reliability.
Description
technical field [0001] The invention belongs to the technical field of power grid fault location, and in particular relates to a fault location method based on NARNN model prediction type wave head arrival time. Background technique [0002] With the advancement of smart distribution network construction, fault location technology is of great significance for quickly finding faults, quickly restoring power supply time, and reducing economic losses for all parties. The topology of the distribution network is relatively complex, and its line connection methods are also varied. A large number of high-frequency noise signals exist in various power equipment. These factors have brought many challenges to the accurate location of faults. [0003] At present, the traveling wave method of fault location in the power grid generally detects the moment when the head of the initial transient traveling wave arrives at each measurement point in the power grid, and uses the internal logica...
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 Applications(China)
IPC IPC(8): G01R31/08
CPCG01R31/086G01R31/088Y04S10/52
Inventor 刘波王丹梁睿滕松郭振华
Owner 新沂茂源实业发展有限公司