Cable tunnel intrusion monitoring method based on optical fiber sensor signals and abnormal codes

Abstract

The invention relates to a cable tunnel intrusion monitoring method based on optical fiber sensor signals and abnormal codes, and the method can achieve the coding of the abnormal condition of the inputted optical fiber sensor signal, obtains a regression model based on the code, and achieves the monitoring of the cable tunnel intrusion condition. By means of the method, a regression prediction model based on abnormal condition codes rather than specific numerical values can be obtained, the problem that long-time stable operation cannot be achieved due to the fact that a traditional prediction method is bound with specific experimental numerical values can be avoided, and the cable tunnel invasion condition can be effectively monitored within a long time range.

Description

Technical field: [0001] The invention relates to a cable tunnel intrusion monitoring method based on optical fiber sensor signals and abnormal codes, which is used for monitoring cable tunnel intrusion and belongs to the technical field of cable tunnel state safety monitoring. Background technique: [0002] Power cables are an important carrier of power transmission, and cable tunnel faults affect the effectiveness of power grid construction. Criminals often invade cable tunnels, and the internal cross-connection wires, grounding wires, and grounding copper bars in the tunnel are often stolen and stolen, which not only causes huge economic losses, but also seriously affects the safe and effective operation of the power system. Therefore, It is very necessary to monitor the cable tunnel intrusion. [0003] There are currently two ways to monitor cable tunnel intrusions: one is to directly have special personnel inspect the tunnels at fixed intervals. There will be situation...

AI Technical Summary

Problems solved by technology

Criminals often invade cable tunnels, and the internal cross-connection wires, grounding wires, and grounding copper bars in the tunnel are often stolen, which not only causes huge economic losses, but also seriously affects the safe and effective operation of the power system. Therefore, It is very necessary to monitor the cable tunnel intrusion

[0003] There are currently two ways to monitor cable tunnel intrusions: one is to directly have special personnel inspect the tunnels at fixed intervals. There will be situations where the detection is not timely or missed; the second is to use the optical fiber sensor signal to reflect the situation in the tunnel, and establish a corresponding artificial intelligence model to predict possible intrusions. These models are usually based on laboratory data or cable tunnels. The data obtained at the initial stage is constructed, and its characteristic is that it is bound to a specific value and the accuracy will be very high in the initial stage of system operation; however, due to the fact that tunnels with large regional distribution will inevitably experience settlement and deformation during long-term use, So these numerical-based models will become more and more inaccurate, and the false positive rate will continue to increase after running for a period of time

[0004] Therefore, it is necessary to propose a method that can avoid the problem of binding the traditional method and the specific experimental value, and monitor the cable tunnel intrusion in a longer time range.

Images