Underground artificial chamber gas storage sealing layer leakage monitoring device and method

Abstract

The invention discloses an underground artificial chamber gas storage sealing layer leakage monitoring device and method, and belongs to the technical field of compressed air energy storage. Comprising a distributed optical fiber sensing network which is spirally wound on the outer surface of a sealing layer of an underground artificial chamber gas storage at an interval of 1m and is used for monitoring temperature distribution, the intelligent data processing unit integrates an AI algorithm and a GIS system and is used for analyzing temperature gradient abrupt change and positioning a leakage point, and the early warning and linkage module is used for triggering emergency response according to a positioning result. And the monitoring efficiency and safety are improved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of compressed air energy storage, and particularly relates to a sealing layer leakage monitoring device and method for an underground artificial cavern gas storage. BACKGROUND

[0002] In a compressed air energy storage power station, an underground artificial cavern gas storage is usually built in rock 100 meters deep underground, adopts a tunnel structure, and has a circular space with a diameter of 10-16 m and a length of 300-600 m, is composed of surrounding rock, reinforced concrete lining and a sealing layer (steel plate or glass steel), and stores high-pressure gas at 8-20 MPa. The existing leakage monitoring technology mainly arranges pressure gauges inside and outside the sealing layer to determine leakage by pressure change, but has the following defects:

[0003] Low positioning efficiency: only leakage occurrence can be determined, and the specific position cannot be quickly locked, manual point-by-point checking is required after the high-pressure gas is released, which is time-consuming and labor-intensive;

[0004] Poor monitoring accuracy: traditional point monitoring cannot form a surface area coverage, the leakage point positioning error is large, and the maintenance efficiency is low;

[0005] Insufficient real-time performance: the pressure change lags behind the leakage occurrence, early warning is difficult to achieve, and a large amount of gas leakage may occur, causing economic losses.

[0006] To solve the above problems, although there are attempts to use distributed sensing in the prior art, the sensing arrangement and data processing logic are not optimized in combination with the special environment (high pressure, humidity, rock vibration) of the underground cavern, and the high-precision positioning requirement cannot be met.

[0007] Therefore, there is a need for a sealing layer leakage monitoring device and method for an underground artificial cavern gas storage that can quickly and accurately position the leakage point of the sealing layer by optimizing the sensing network arrangement and intelligent data processing, and improve the monitoring efficiency and safety. SUMMARY

[0008] The purpose of the present application is to provide a sealing layer leakage monitoring device and method for an underground artificial cavern gas storage, which can quickly and accurately position the leakage point of the sealing layer by optimizing the sensing network arrangement and intelligent data processing, and improve the monitoring efficiency and safety.

[0009] To achieve the above purpose, the technical solution adopted by the present application is:

[0010] A leakage monitoring device for sealing layer of underground artificial cavern gas storage, comprising a distributed optical fiber sensing network for monitoring temperature distribution spirally wound on the outer surface of the sealing layer of the underground artificial cavern gas storage at an interval of 1 m, an intelligent data processing unit integrating an AI algorithm and a GIS system for analyzing temperature gradient mutation and locating a leakage point, and an early warning and linkage module for triggering emergency response according to the positioning result.

[0011] The further improvement of the technical scheme of the present application is that the distributed optical fiber sensing network comprises high-pressure resistant armored optical cable and uniformly spaced constant temperature compensation optical fiber segments, the outer layer of the high-pressure resistant armored optical cable is provided with a shear-resistant corrugated pipe, and an OTDR diagnostic optical fiber is integrated in the inside to monitor the on-off state of the optical fiber in real time.

[0012] The further improvement of the technical scheme of the present application is that the intelligent data processing unit adopts an LSTM neural network model to identify leakage characteristics, and the characteristics include a temperature gradient change rate > 0.3 DEG C / s and a DT >= 0.5 DEG C / m.

[0013] The further improvement of the technical scheme of the present application is that the LSTM neural network model synchronously analyzes time domain characteristics and spatial correlation, and can identify multi-point concurrent leakage events with an interval >= 1 m.

[0014] The further improvement of the technical scheme of the present application is that the early warning and linkage module comprises a three-level response mechanism: when DT = 0.5-1 DEG C / m, a local sound-light alarm is sounded, when DT > 1 DEG C / m and lasts for 10 s, the partition valve is automatically closed, and when DT > 2 DEG C / m, an explosion-proof ventilation system is started and positioning information is sent to a maintenance terminal.

[0015] A leakage monitoring method for sealing layer of underground artificial cavern gas storage, using a monitoring device to monitor, comprising the following steps:

[0016] Step S1: arranging a distributed optical fiber sensor to form a spiral monitoring network with an interval of 1 m;

[0017] Step S2: collecting temperature data along the optical fiber in real time, performing constant temperature compensation and interference filtering;

[0018] Step S3: analyzing the temperature gradient by using an AI algorithm, and locating the leakage point when detecting DT >= 0.5 DEG C / m;

[0019] Step S4: triggering early warning and linkage emergency disposal.

[0020] The further improvement of the technical scheme of the present application is that in step S3, the LSTM neural network model is used to compare real-time temperature with historical baseline, and the leakage point coordinates are calculated in combination with the optical fiber length, with an error <= 1 m.

[0021] The further improvement of the technical scheme of the present application is that the leakage point coordinate calculation adopts a space mapping algorithm:

[0022] (x,y,z)=f(L,R,θ)

[0023] Wherein, L represents the optical fiber length measurement value, R represents the chamber cross section radius, and 55°≤θ≤65°.

[0024] Further improvement of the technical scheme of the present application is that in step S4, the emergency treatment includes local sound-light alarm, closing the corresponding partition valve, starting the explosion-proof ventilation system and sending the positioning information to the maintenance terminal.

[0025] Due to the adoption of the above technical scheme, the present application has achieved the following technical progress:

[0026] The underground artificial chamber gas storage seal layer leakage monitoring device and method can realize rapid and accurate positioning of the seal layer leakage point, improve the monitoring efficiency and safety by optimizing the sensor network arrangement and intelligent data processing.

[0027] The present application adopts a distributed optical fiber sensor to monitor the temperature gradient change along the way, convert the optical signal into an electrical signal and transmit it to the processing unit. AI algorithm analyzes the temperature data in real time, compares the historical baseline and preset threshold, identifies the leakage characteristics and locates the specific position, and finally triggers the emergency response through the early warning and linkage module to realize the whole process automation of "monitoring, analysis, positioning and disposal". BRIEF DESCRIPTION OF DRAWINGS

[0028] Figure 1 is a layout schematic diagram of the underground artificial chamber gas storage seal layer leakage monitoring device of the present application. DETAILED DESCRIPTION

[0029] The present application will be further described in detail below in conjunction with the embodiments:

[0030] Embodiment 1

[0031] As shown in Figure 1 , the present embodiment provides an underground artificial chamber gas storage seal layer leakage monitoring device, which comprises a distributed optical fiber sensor network for monitoring temperature distribution spirally wound on the outer surface of the underground artificial chamber gas storage seal layer at an interval of 1m, an intelligent data processing unit integrating AI algorithm and GIS system for analyzing temperature gradient mutation and positioning the leakage point, and an early warning and linkage module for triggering emergency response according to the positioning result. Among them, the AI algorithm adopts NVIDIA Jetson AGX Orin chip as the AI algorithm core, and preinstalls the temperature feature recognition model based on TensorFlow. The GIS system imports the chamber three-dimensional CAD model, sets the coordinate mapping relationship, and realizes the visual labeling of the leakage point position.

[0032] The early warning and linkage module comprises a three-level response mechanism: when ΔT = 0.5-1℃ / m, local sound and light alarm, when ΔT > 1℃ / m and lasts for 10s, automatically closing the partition valve, when ΔT > 2℃ / m, starting the explosion-proof ventilation system and sending the positioning information to the maintenance terminal.

[0033] The distributed optical fiber sensing network comprises a high-pressure resistant armored optical cable and uniformly spaced constant temperature compensation optical fiber segments, the outer layer of the high-pressure resistant armored optical cable is provided with a shear-resistant corrugated pipe, and the inside is integrated with an OTDR diagnostic optical fiber to monitor the on-off state of the optical fiber in real time.

[0034] The intelligent data processing unit adopts an LSTM neural network model to identify leakage characteristics, and the characteristics include a temperature gradient change rate > 0.3℃ / s and ΔT≥0.5℃ / m. Among them, the LSTM neural network model synchronously analyzes the time domain characteristics and spatial correlation, and can identify multiple concurrent leakage events with a spacing of ≥1m.

[0035] Embodiment 2

[0036] The embodiment provides a leakage monitoring method for a sealing layer of an underground artificial cavern gas storage, and the monitoring device in embodiment 1 is used for monitoring, and the method comprises the following steps:

[0037] Step S1: arranging a distributed optical fiber sensor to form a spiral monitoring network with a spacing of 1m; specifically, an SMF-28e+ single-mode optical fiber is selected, which can withstand a temperature of-40℃-80℃ and has a tensile strength of ≥500MPa; after the sealing layer is constructed, the optical fiber is wound and fixed with a 1m pitch by using epoxy resin glue, and constant temperature compensation optical fiber segments are uniformly and spacedly arranged;

[0038] Step S2: collecting temperature data along the optical fiber in real time, performing constant temperature compensation and interference filtering;

[0039] Step S3: analyzing the temperature gradient by using an AI algorithm, and locating the leakage point when ΔT≥0.5℃ / m is detected; based on an LSTM neural network model, the real-time temperature is compared with a historical baseline, and the coordinates of the leakage point are calculated in combination with the length of the optical fiber, and the error is ≤1m; the coordinates of the leakage point are calculated by using a space mapping algorithm:

[0040] (x,y,z)=f(L,R,θ)

[0041] Wherein, L represents the length of the optical fiber, R represents the radius of the cavern section, and θ represents the spiral winding angle, 55°≤θ≤65°.

[0042] Step S4: triggering early warning and linkage emergency disposal, and the emergency disposal comprises local sound and light alarm, closing the corresponding partition valve, starting the explosion-proof ventilation system and sending the positioning information to the maintenance terminal.

[0043] When the sealing layer of underground artificial cavern gas storage leaks, the escape of high-pressure gas will cause the air near the leakage point to expand rapidly and absorb heat, forming a local temperature anomaly. The distributed optical fiber sensor converts the optical signal into an electrical signal by monitoring the temperature gradient along the way and transmitting it to the processing unit. AI algorithm analyzes temperature data in real time, compares historical baseline and preset threshold, identifies leakage characteristics and locates specific position, and finally triggers emergency response through early warning and linkage module to realize the whole process automation of "monitoring, analysis, positioning and disposal".

[0044] It can be understood that the present application is described by some embodiments, and those skilled in the art know that various changes or equivalent replacements can be made to these features and embodiments without departing from the spirit and scope of the present application. In addition, under the guidance of the present application, these features and embodiments can be modified to adapt to specific conditions and materials without departing from the spirit and scope of the present application. Therefore, the present application is not limited by the specific embodiments disclosed herein, and all embodiments falling within the scope of the claims of the present application are within the scope of the present application.

Claims

1. A device for monitoring leakage of the sealing layer of an underground artificial cavern gas storage reservoir, characterized in that: It includes a distributed fiber optic sensing network for monitoring temperature distribution, which is spirally wound on the outer surface of the sealing layer of the underground artificial chamber gas storage reservoir with a spacing of 1m; an intelligent data processing unit that integrates AI algorithms and GIS systems to analyze sudden changes in temperature gradients and locate leakage points; and an early warning and linkage module for triggering emergency responses based on the positioning results.

2. The underground artificial chamber gas storage sealing layer leakage monitoring device according to claim 1, characterized in that: The distributed optical fiber sensing network includes a high-voltage armored optical cable and evenly spaced constant-temperature compensation optical fiber segments. The outer layer of the high-voltage armored optical cable is provided with a shear-resistant corrugated tube, and an OTDR diagnostic optical fiber is integrated inside to monitor the on-off status of the optical fiber in real time.

3. The device for monitoring the sealing layer leakage of an underground artificial chamber gas storage according to claim 2, characterized in that: The intelligent data processing unit uses an LSTM neural network model to identify leakage characteristics, wherein the characteristics include a temperature gradient change rate greater than 0.3°C / s and ΔT greater than or equal to 0.5°C / m.

4. The device for monitoring the sealing layer leakage of an underground artificial chamber gas storage according to claim 3, characterized in that: The LSTM neural network model synchronously analyzes temporal features and spatial domain correlations, and can identify multi-point concurrent leakage events with a spacing of ≥1m.

5. The device for monitoring the sealing layer leakage of an underground artificial chamber gas storage according to claim 4, characterized in that: The early warning and linkage module includes a three-level response mechanism: when ΔT = 0.5-1℃ / m, local sound and light alarm will be triggered; when ΔT>1℃ / m and lasts for 10s, the partition valve will be automatically closed; when ΔT>2℃ / m, the explosion-proof ventilation system will be started and the positioning information will be sent to the maintenance terminal.

6. A method for monitoring leakage of a sealing layer of an underground artificial chamber gas storage, characterized in that: Monitoring using the monitoring device according to any one of claims 1 to 5 comprises the following steps: Step S1: Arrange distributed optical fiber sensors to form a spiral monitoring network with a spacing of 1m; Step S2: Real-time acquisition of temperature data along the optical fiber, and performing constant temperature compensation and interference filtering; Step S3: Analyze the temperature gradient using the AI ​​algorithm and locate the leak point when ΔT ≥ 0.5°C / m is detected; Step S4: trigger an early warning and initiate emergency response.

7. The method for monitoring leakage of the sealing layer of an underground artificial chamber gas storage according to claim 6, characterized in that: In step S3, the real-time temperature is compared with the historical baseline based on the LSTM neural network model, and the coordinates of the leakage point are calculated in combination with the optical fiber length, with an error of ≤1m.

8. The method for monitoring leakage of the sealing layer of an underground artificial chamber gas storage according to claim 7, characterized in that: The leakage point coordinates are calculated using a spatial mapping algorithm: (x,y,z)=f(L,R,θ) Wherein, L represents the measured value of the optical fiber length, R represents the cross-sectional radius of the chamber, and θ represents the spiral winding inclination angle, 55°≤θ≤65°.

9. The method for monitoring leakage of a sealing layer of an underground artificial chamber gas storage according to claim 6, characterized in that: In step S4, the emergency response includes local sound and light alarms, closing corresponding partition valves, starting the explosion-proof ventilation system, and sending positioning information to the maintenance terminal.

Images