Early warning method for third-party construction of oil and gas pipelines based on emd decomposition and lstm

A technology for oil and gas pipelines and classification models, applied in neural learning methods, instruments, biological neural network models, etc., can solve problems such as waveform data interference, low precision, and inability to accurately identify third-party construction, and achieve classification errors, The effect of rapid classification recognition, strong universality and portability

Active Publication Date: 2020-10-09
浙江浙能天然气运行有限公司 +2
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Due to the complexity of disturbing activities along the oil and gas pipeline, it is easy to detect the data collected by distributed optical fiber vibration sensors. Waveform data causes interference, which makes it impossible to accurately identify third-party construction, resulting in low precision of early warning

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
  • Early warning method for third-party construction of oil and gas pipelines based on emd decomposition and lstm
  • Early warning method for third-party construction of oil and gas pipelines based on emd decomposition and lstm
  • Early warning method for third-party construction of oil and gas pipelines based on emd decomposition and lstm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] In this embodiment, a distributed optical fiber sensor is laid along the long-distance oil and gas pipeline, which is buried about 3-5 meters deep underground like the oil and gas pipeline. The back Rayleigh scattered light intensity along the axial direction in the optical fiber is detected by technology, and the specific position of the disturbance event is located according to the coherent interference result of the returned back Rayleigh scattered light, and according to the difference of the interference waveform, the Accurate classification and identification of vibration sources.

[0045] Specifically, such as figure 1 As shown, in this example the The distributed optical fiber system consists of three major parts, including distributed optical fiber vibration sensors, data acquisition modules and computers.

[0046] Distributed optical fiber vibration sensors specifically include: ultra-narrow linewidth lasers, acousto-optic modulators, erbium-doped optical ...

Embodiment 2

[0115] The difference between the third-party construction early warning method for oil and gas pipelines based on EMD decomposition and LSTM in this embodiment and Embodiment 1 is that:

[0116] The threshold for early warning triggering is not limited to the three consecutive forecast results described in Example 1, which are bands of third-party construction danger signals such as excavators. It can also be only once, or twice, four times, or five times to meet different application needs.

[0117] Other steps can refer to embodiment 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

No PUM Login to view more

Abstract

The present invention relates to a third-party early warning method for oil and gas pipeline construction based on EMD decomposition and LSTM, including: S1, collecting waveform data in real time through a distributed optical fiber system laid along the pipeline, and performing threshold triggering on the waveform data to obtain suspicious bands; S2, Perform wavelet denoising on the signals in the suspicious band in turn to obtain the denoising signal in the suspicious band; S3, extract the corresponding time series features from the denoising signal in the suspicious band, and perform EMD decomposition on the denoising signal in the suspicious band to obtain the IMF energy spectrum ; S4, carry out normalization process to timing feature, IMF energy spectrum, to input LSTM classification model, judge in real time whether the vibration source corresponding to the signal of suspicious band is a third-party construction; S5, if so, then execute alarm; if not, then Go to step S1. The invention realizes accurate and rapid classification and identification of optical fiber sensing disturbance signals, and solves the shortcomings of security alarms at the perimeter of pipelines.

Description

technical field [0001] The invention belongs to the technical field of early warning for oil and gas pipelines, and in particular relates to a third-party construction early warning method for oil and gas pipelines based on EMD decomposition and LSTM. Background technique [0002] Construction by third parties within the safe scope of the pipeline is collectively referred to as "third-party construction". For a long time, huge manpower and financial resources have been invested to maintain the integrity of oil and gas pipelines and prevent third-party construction damage. However, third-party construction of oil and gas pipelines is highly random, difficult to predict and control, and makes monitoring difficult. [0003] Distributed fiber optic vibration sensor is a fiber optic sensing system developed in recent years for real-time measurement of spatial vibration distribution. The optical cable laid in the same trench as the pipeline is used as the sensing medium to sense ...

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): G06K9/00G06N3/04G06N3/08
CPCG06N3/049G06N3/08G06N3/045G06F2218/06G06F2218/08G06F2218/12
Inventor 陈积明滕卫明解剑波钱济人杨秦敏范海东沈佳园张国民李清毅周元杰丁楠周君良
Owner 浙江浙能天然气运行有限公司
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