Optical fiber coiled tubing underground fluid monitoring system and method based on AI large model

Abstract

The invention discloses an optical fiber coiled tubing underground fluid monitoring system and method based on an AI large model, the system comprises an optical fiber sensing composite modem, a coiled tubing body and an underground fluid monitoring data processor, the optical fiber sensing composite modem is installed near a ground wellhead, the coiled tubing body is arranged underground, and the underground fluid monitoring data processor is connected with the optical fiber sensing composite modem. The underground fluid monitoring data processor is arranged near a ground wellhead; according to the invention, the function of long-term real-time dynamic monitoring of an oil and gas production well is realized, and analysis, processing and statistics can be carried out on underground fluid optical fiber monitoring data based on an AI big data model for a long time, so that an indispensable means, system and method are provided for scientific management of oil and gas reservoirs and improvement of the recovery ratio; the device also has a well-ground time-shifting combined three-dimensional exploration function, realizes time-shifting monitoring of dynamic changes of underground oil-water two-phase and oil-gas-water three-phase fluid interfaces in the oil-gas production process, and is suitable for wide popularization and application.

Description

Technical Field

[0001] The present invention relates to the technical field of underground fluid monitoring of fiber optic coiled tubing, and particularly relates to a fiber optic coiled tubing underground fluid monitoring system and method based on an AI large model. Background Technique

[0002] Artificial Intelligence (AI) is an important driving force for the new round of scientific and technological revolution and industrial transformation. It is a new technical science that studies, develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. Artificial Intelligence (AI) is an interdisciplinary and emerging discipline based on computer science, integrating multiple disciplines such as computer science, psychology, and philosophy. It is a new technical science that studies, develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence, attempting to understand the essence of intelligence and produce a new intelligent machine that can respond in a way similar to human intelligence. The research in this field includes robots, speech recognition, image recognition, natural language processing, and expert systems, etc. Artificial Intelligence is an important part of the intelligent discipline, attempting to understand the essence of intelligence and produce a new intelligent machine that can respond in a way similar to human intelligence. Artificial Intelligence is a very broad science, including robots, speech recognition, image recognition, natural language processing, expert systems, machine learning, computer vision, etc.

[0003] A large model refers to a machine learning model with a large number of parameters and a complex computing structure. These models are usually constructed by deep neural networks and have billions or even hundreds of billions of parameters. The design purpose of large models is to improve the expressive ability and prediction performance of the models, and they can handle more complex tasks and data. Large models have a wide range of applications in various fields, including natural language processing, computer vision, speech recognition, and recommendation systems, etc. Large models learn complex patterns and features by training massive amounts of data, and have stronger generalization ability, and can make accurate predictions on unseen data. Big data analysis refers to the process of processing, analyzing and mining large, high-speed, multi-source, and multi-type data to discover valuable information and knowledge. The core technologies of big data analysis include data storage, data processing, data mining, data analysis, and data visualization, etc. With the development of technologies such as the Internet, artificial intelligence, and the Internet of Things, the scale and complexity of data are increasing continuously, and big data analysis technology has become an indispensable part of enterprises and organizations.

[0004] At present, laying a permanent armored optical cable outside the metal casing faces difficulties in construction operations, high costs, difficulties in detecting the orientation of the optical cable, and immature underground radiation avoidance technology, resulting in the armored optical cable being shot and broken during perforation operations. Moreover, the armored optical cable laid inside the casing can only be used for temporary data collection because the armored optical cable laid inside the casing will affect or interfere with other underground operations, making it impossible to lay the armored optical cable inside the casing for long-term monitoring operations. At the same time, although laying an armored optical cable inside a coiled tubing can be used for microseismic monitoring and liquid production profile measurement in the horizontal well section, it can only be temporary and cannot lay the coiled tubing with the built-in armored optical cable in the horizontal well for a long time without affecting the underground oil and gas production. Therefore, it is necessary to design an AI large model-based optical fiber coiled tubing underground fluid monitoring system and method. Summary of the Invention

[0005] The main object of the present invention is to solve the problems that currently laying a permanent armored optical cable outside the metal casing faces difficulties in construction operations, high costs, difficulties in detecting the orientation of the optical cable, and immature underground radiation avoidance technology, resulting in the armored optical cable being shot and broken during perforation operations. The present invention provides an AI large model-based optical fiber coiled tubing underground fluid monitoring system and method, which realizes the function of long-term real-time dynamic monitoring of oil and gas production wells, and can long-term analyze, process, and statistically analyze the underground fluid optical fiber monitoring data based on the AI big data model, thereby providing indispensable means, systems, and methods for the scientific management of oil and gas reservoirs and improving oil recovery. It also has the function of well-ground time-lapse joint three-dimensional exploration, and realizes the function of time-lapse monitoring of the dynamic changes of the underground oil-water two-phase and oil-gas-water three-phase fluid interfaces during the oil and gas production process.

[0006] To achieve the above object, the technical solution adopted by the present invention is as follows: An AI large model-based optical fiber coiled tubing underground fluid monitoring system, comprising an optical fiber sensing composite modulation and demodulation instrument, a coiled tubing body, and an underground fluid monitoring data processor. The optical fiber sensing composite modulation and demodulation instrument is installed near the surface wellhead, the coiled tubing body is laid underground, and the underground fluid monitoring data processor is arranged near the surface wellhead; A straight optical unit and a spiral optical unit are inlaid on the outer side wall of the coiled tubing body. The optical fiber sensing composite modulation and demodulation instrument is connected to the optical fibers in the straight optical unit and the spiral optical unit. The underground fluid monitoring data processor is connected to the optical fiber sensing composite modulation and demodulation instrument. The straight optical unit is used to real-time monitor and measure the fluid noise data, strain data, temperature data, seismic data, microseismic data, and time-lapse vertical ground profile data outside the underground coiled tubing body; The spiral optical unit is used for real-time monitoring and measurement of fluid noise data, three-component strain data, temperature data, three-component seismic data, three-component microseismic data, and three-component time-lapse vertical surface profile data outside the coiled tubing body; Inside the underground fluid monitoring data processor, there are an underground fluid distribution change data processing unit and an underground fluid monitoring data processing unit. The underground fluid monitoring data processing unit is distilled from the underground fluid distribution change data processing unit; The underground fluid distribution change data processing unit includes an underground three-phase fluid static distribution model, a three-dimensional viscoelastic medium anisotropic longitudinal wave velocity model, and a three-dimensional viscoelastic medium anisotropic shear wave velocity model. The underground three-phase fluid static distribution model is made by an underground three-dimensional reservoir model building software using a three-dimensional geological model, a three-dimensional structural model, a three-dimensional porosity model, and a three-dimensional permeability model. The three-dimensional viscoelastic medium anisotropic longitudinal wave velocity model and the three-dimensional viscoelastic medium anisotropic shear wave velocity model are both generated by an underground three-dimensional velocity building software using a three-dimensional geological structure model, a three-dimensional seismic velocity model, acoustic logging data, vertical surface profile data, rock physics measurement data, anisotropy coefficient, and attenuation coefficient Q value; The underground fluid monitoring data processing unit is used for processing fluid noise data, strain data, temperature data, seismic data, microseismic data, and time-lapse vertical surface profile data outside the underground coiled tubing body that are real-time monitored and measured by the straight optical unit, as well as fluid noise data, three-component strain data, temperature data, three-component seismic data, three-component microseismic data, and three-component time-lapse vertical surface profile data outside the coiled tubing body that are real-time monitored and measured by the spiral optical unit.

[0007] For the aforementioned fiber optic coiled tubing underground fluid monitoring system based on the AI large model, inside the fiber optic sensing composite modulation and demodulation instrument, there are a DAS signal input module, a DTS signal input module, a DSS signal input module, and a DPS signal input module; the straight optical unit includes a straight single-mode optical fiber, a straight multimode optical fiber, a straight single-mode strain optical unit, and a straight continuous grating optical fiber or a straight microstructure optical fiber. The straight single-mode optical fiber is connected to the signal input end of the DAS signal input module, the straight multimode optical fiber is connected to the signal input end of the DTS signal input module, the straight single-mode strain optical unit is connected to the signal input end of the DSS signal input module, and the straight continuous grating optical fiber or the straight microstructure optical fiber is connected to the signal input end of the DPS signal input module; the straight single-mode optical fiber, the straight multimode optical fiber, the straight single-mode strain optical unit, and the straight continuous grating optical fiber or the straight microstructure optical fiber inside the straight optical unit are all high-temperature resistant, hydrogen loss resistant, and high-reflection coefficient type optical fibers.

[0008] The aforementioned fiber optic coiled tubing underground fluid monitoring system based on an AI large model, wherein the spiral optical unit includes a spiral single-mode optical fiber, a spiral multi-mode optical fiber, a spiral single-mode strain optical unit, and a spiral continuous grating optical fiber or a spiral microstructure optical fiber, and the optimized spiral winding angle of the spiral optical unit is 60 degrees; the spiral single-mode optical fiber is connected to the signal input end of the DAS signal input module, the spiral multi-mode optical fiber is connected to the signal input end of the DTS signal input module, the spiral single-mode strain optical unit is connected to the signal input end of the DSS signal input module, and the signal output end of the spiral continuous grating optical fiber or the spiral microstructure optical fiber is in data communication connection with the DPS signal input module; the spiral single-mode optical fiber, the spiral multi-mode optical fiber, the spiral single-mode strain optical unit, and the spiral continuous grating optical fiber or the spiral microstructure optical fiber in the spiral optical unit are all high-temperature resistant, hydrogen loss resistant, and high-reflection coefficient type optical fibers.

[0009] The aforementioned fiber optic coiled tubing underground fluid monitoring system based on an AI large model, wherein both the straight single-mode strain optical unit and the spiral single-mode strain optical unit are made by coating a high-temperature resistant and high-strength flexible composite material on the outer side walls of the straight single-mode optical fiber and the spiral single-mode optical fiber and making the diameters of the straight single-mode optical fiber and the spiral single-mode optical fiber 1 mm to 2 mm, and then placing them in stainless steel tubes with corresponding inner diameters. Both the straight single-mode strain optical unit and the spiral single-mode strain optical unit are used to sense the stress and strain outside the stainless steel tube.

[0010] The aforementioned fiber optic coiled tubing underground fluid monitoring system based on an AI large model, wherein grooves are formed on the outer side wall of the coiled tubing body. The straight optical unit is entirely embedded in the middle position of the weld of the coiled tubing body or symmetrically embedded in the middle positions of the weld and the groove of the coiled tubing body before the coiled tubing body is welded into a pipe. The straight optical unit is embedded and welded with the coiled tubing body when the coiled tubing body is welded and formed; after the straight optical unit and the spiral optical unit are embedded on the outer side wall of the coiled tubing body, they are filled and fixed with a high-temperature resistant flexible composite material and covered with a thin stainless steel sleeve after fixation.

[0011] The aforementioned fiber optic coiled tubing underground fluid monitoring system based on an AI large model further includes a ground artificial seismic source, which is arranged on the ground near the wellhead. The fiber optic sensing composite modulation and demodulation instrument uses a straight single-mode optical fiber and a spiral single-mode optical fiber to collect vertical ground profile data and time-lapse vertical ground profile data excited by the ground artificial seismic source.

[0012] The aforementioned fiber optic coiled tubing underground fluid monitoring system based on an AI large model further includes a surface geophone, which is used to collect surface seismic data excited by a surface artificial seismic source. While collecting the surface seismic data, the geophone collects vertical ground profile data in the well through a straight single-mode optical fiber and a helical single-mode optical fiber, realizing well-ground joint seismic data acquisition and well-ground three-dimensional exploration.

[0013] For the aforementioned fiber optic coiled tubing underground fluid monitoring system based on an AI large model, the underground fluid distribution change data processing unit is specifically trained by an AI data large model using an underground three-phase fluid static distribution model, a three-dimensional viscoelastic anisotropic longitudinal wave velocity model, and a three-dimensional viscoelastic anisotropic shear wave velocity model. The underground three-phase fluid static distribution model uses a three-dimensional geological model, a three-dimensional structural model, a three-dimensional porosity model, and a three-dimensional permeability model as input data for underground three-dimensional reservoir model modeling software. The three-dimensional geological structure model, the three-dimensional seismic velocity model, acoustic logging data, vertical ground profile data, rock physics measurement data, anisotropy coefficient, and attenuation coefficient Q value are input data for underground three-dimensional velocity modeling software.

[0014] A fiber optic coiled tubing underground fluid monitoring method based on an AI large model includes the following steps: Step 1: During oil and gas production, the fiber optic sensing composite modulation and demodulation instrument is used to monitor and measure the DSS signal outside the coiled tubing body in real time through the straight single-mode strain optical unit and the helical single-mode strain optical unit embedded on the outer sidewall of the multi-well coiled tubing body. Then, the fiber optic sensing composite modulation and demodulation instrument is used to monitor and measure the DAS signal, DTS signal, and DPS signal on both the inner and outer sides of the coiled tubing body in real time through the straight optical unit and the helical optical unit. Step 2: The fiber optic sensing composite modulation and demodulation instrument is used to modulate and demodulate the multi-well DTS signal and DSS signal measured in Step 1. Among them, the DSS signal transmitted through the straight single-mode strain optical unit can obtain underground stress data at different depths outside the coiled tubing body through modulation and demodulation. The DSS signal transmitted through the helical single-mode strain optical unit can obtain underground three-component stress data at different depths and different azimuths outside the coiled tubing body through modulation and demodulation. Then, the DTS signal transmitted through the straight multi-mode optical fiber and the helical multi-mode optical fiber can obtain real-time temperature data of the entire well section of the coiled tubing body and correct the measured underground stress data for temperature drift, so as to obtain the true underground stress data corrected at different depths and different azimuths of the underground coiled tubing body. Step 3: Based on the underground three-component stress data at different depths and different azimuths outside the coiled tubing body obtained in Step 2, a three-dimensional distribution map of the underground three-component stress field at each depth and each azimuth is drawn, so as to obtain the distribution change characteristics of the underground three-component stress field along the trajectory of the coiled tubing body. Step 4: Based on the distribution and variation characteristics of the underground three-component stress field along the trajectory of the coiled tubing body, conduct real-time long-term monitoring on the well sections with high underground three-component stress of the coiled tubing body, so as to prevent the damage of the local coiled tubing body. Step 5: By using the fiber optic sensing composite modulation and demodulation instrument to modulate and demodulate the DAS signals transmitted by the helical single-mode optical fiber, the distribution of the three-component microseismic data in the three-dimensional space around the well trajectory can be obtained, so as to monitor the distribution of the microseismic events induced by underground fluid migration in the underground three-dimensional space and its fracture mechanism at the source point location.

[0015] The aforementioned fiber optic coiled tubing underground fluid monitoring method based on the AI large model can also obtain the underground distributed noise data, temperature data, underground stress data, and fluid pressure data in the pores of the underground reservoir by using the fiber optic sensing composite modulation and demodulation instrument to modulate and demodulate the obtained DSS signals, DAS signals, DTS signals, and DPS signals in Step 1. Thus, the changes in the oil-water two-phase fluid interface and the oil-gas-water three-phase fluid interface underground and around the well can be measured and monitored in real time, and then the exploitation mode and development process of underground oil and gas resources can be optimized, thereby improving the recovery rate of underground oil and gas resources. The specific steps are as follows. Step A: Use the fiber optic sensing composite modulation and demodulation instrument to modulate and demodulate the input DSS signals, DAS signals, DTS signals, and DPS signals, and obtain the fluid noise data, formation temperature data, ground stress data, and fluid pressure data in the pores of the rock distributed around multiple wells underground. Step B: Input the fluid noise data, formation temperature data, ground stress data, and fluid pressure data in the pores of the rock distributed underground obtained in Step A into the underground fluid distribution change data processing unit as multiple parameters, and calculate through the joint inversion method based on AI artificial intelligence, so as to obtain the liquid production or gas production profile of each underground oil and gas production well and the water absorption or gas absorption profile data of each water injection or gas injection well. Step C: Based on the three-component ground stress field data distributed underground obtained in Step A, conduct real-time monitoring on the distribution and variation of the ground stress field along the outer wall of the coiled tubing body, so as to prevent the damage of the high ground stress concentration pipe sections. Step D: Regularly activate the surface artificial seismic source set on the ground, and then collect the time-lapse variable offset fiber optic vertical ground profile data and the time-lapse three-dimensional fiber optic vertical ground profile data through the straight single-mode optical fiber and the helical single-mode optical fiber on the outer wall of the coiled tubing body. Step E: Perform surface-consistent amplitude compensation processing, surface-consistent deconvolution processing, and wavefield separation processing with relative amplitude preservation based on AI artificial intelligence on the time-lapse variable-offset fiber-optic vertical surface profile data and time-lapse 3D fiber-optic vertical surface profile data collected in different periods in Step D, so as to obtain the processed time-lapse variable-offset fiber-optic vertical seismic profile data and time-lapse 3D fiber-optic vertical seismic profile data; Step F: Perform amplitude-preserved prestack depth migration processing based on AI artificial intelligence on the processed time-lapse variable-offset fiber-optic vertical seismic profile data and time-lapse 3D fiber-optic vertical seismic profile data obtained in Step E to obtain the migrated vertical seismic profile data, then extract the fluid-sensitive attribute parameters in the migrated vertical seismic profile data, then obtain the highlight body data in combination with the S transform, and then calculate and monitor the three-dimensional spatial distribution range and the change over time of the oil-water two-phase and oil-gas-water three-phase fluid boundaries around the well, so as to obtain the utilization status of underground oil and gas resources and the distribution status and characteristics of remaining oil and gas resources around the well, and further improve the oil and gas recovery rate; Step G: Input the liquid production or gas production profile of each production well underground, the water injection or gas injection profile data of each injection well, and the three-dimensional spatial distribution range and the change over time data of the oil-water two-phase and oil-gas-water three-phase fluid boundaries around the well obtained in Step F into the AI real-time underground fluid monitoring data processing model, and combine the distribution of microseismic events induced by underground fluid migration in the three-dimensional underground space and the fracture mechanism at the source point position to realize real-time measurement and monitoring of the changes in the oil-water two-phase fluid interface and oil-gas-water three-phase fluid interface underground and around the well, so as to obtain the utilization status of underground oil and gas resources and the distribution status and characteristics of remaining oil and gas resources around the well, and then timely optimize and adjust the development plan and production system and achieve the purpose of improving the oil and gas recovery rate.

[0016] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention uses an optical fiber sensing composite modulation and demodulation instrument to continuously monitor and measure the DSS signals on the outer sidewall of the coiled tubing body through the straight single-mode strain optical units and helical single-mode strain optical units embedded on the outer sidewall of the multi-well coiled tubing body. Then, the optical fiber sensing composite modulation and demodulation instrument is used to continuously monitor and measure the DAS signals, DTS signals, and DPS signals on both the inner and outer sides of the coiled tubing body through the straight optical units and helical optical units. Next, the optical fiber sensing composite modulation and demodulation instrument can modulate and demodulate the measured multi-well DTS signals and DSS signals. Among them, by modulating and demodulating the DSS signals transmitted by the straight single-mode strain optical units, the underground stress data at different depths on the outer side of the coiled tubing body can be obtained. By modulating and demodulating the DSS signals transmitted by the helical single-mode strain optical units, the underground three-component stress data at different depths and different azimuths on the outer side of the coiled tubing body can be obtained. Then, by modulating and demodulating the DTS signals transmitted by the straight multi-mode optical fibers and helical multi-mode optical fibers, the real-time temperature data of the entire well section of the coiled tubing body can be obtained and the temperature drift correction of the measured underground stress data can be performed, so as to obtain the true underground stress data corrected at different depths and different azimuths of the underground coiled tubing body. The present invention effectively realizes the function of obtaining the underground stress data at different depths on the outer side of the coiled tubing body, and also has the function of obtaining the underground three-component stress data at different depths and different azimuths on the outer side of the coiled tubing body, and also has the function of obtaining the true underground stress data corrected at different depths and different azimuths of the underground coiled tubing body.

[0017] 2. The present invention can obtain the distribution change characteristics of the underground three-component stress field along the trajectory of the coiled tubing body by drawing a three-dimensional distribution map of the underground three-component stress field at each depth and each azimuth based on the obtained underground three-component stress data at different depths and different azimuths on the outer side of the coiled tubing body. Then, according to the distribution change characteristics of the underground three-component stress field along the trajectory of the coiled tubing body, real-time long-term monitoring can be carried out on the well sections with high underground three-component stress of the coiled tubing body, so as to prevent the occurrence of damage to the local coiled tubing body. Next, by using the optical fiber sensing composite modulation and demodulation instrument to modulate and demodulate the DAS signals transmitted by the helical single-mode optical fibers, the distribution of the three-component microseismic data in the three-dimensional space around the well trajectory can be obtained, so as to monitor the distribution of microseismic events induced by underground fluid migration in the underground three-dimensional space and its fracture mechanism at the source point position. The present invention effectively realizes the function of obtaining the distribution change characteristics of the underground three-component stress field along the trajectory of the coiled tubing body, and can carry out real-time long-term monitoring on the well sections with high underground three-component stress of the coiled tubing body, and can also prevent the occurrence of damage to the local coiled tubing body. At the same time, it can also monitor the distribution of microseismic events induced by underground fluid migration in the underground three-dimensional space and its fracture mechanism at the source point position.

[0018] 3. The present invention modulates and demodulates the input DSS signal, DAS signal, DTS signal, and DPS signal by using an optical fiber sensing composite modulation and demodulation instrument to obtain fluid noise data, formation temperature data, in-situ stress data, and pressure data of the fluid in the rock pores distributed around multiple underground wells. Then, the obtained fluid noise data, formation temperature data, in-situ stress data, and pressure data of the fluid in the rock pores distributed underground are input into the underground fluid distribution change data processing unit as multi-parameters and calculated through a joint inversion method based on AI artificial intelligence, so as to obtain the liquid production or gas production profile of each underground oil and gas production well and the water absorption or gas absorption profile data of each water injection or gas injection well. Then, according to the obtained three-component in-situ stress field data distributed underground, the distribution change of the in-situ stress field on the outer side wall of the coiled tubing body is monitored in real time, so as to prevent the damage of the high in-situ stress concentration pipe section. Furthermore, the time-lapse variable offset fiber optic vertical seismic profile data and the time-lapse three-dimensional fiber optic vertical seismic profile data collected in different periods are subjected to surface-consistent amplitude compensation processing, surface-consistent deconvolution processing, and wavefield separation processing with relative amplitude preservation based on AI artificial intelligence, so as to obtain the processed time-lapse variable offset fiber optic vertical seismic profile data and the time-lapse three-dimensional fiber optic vertical seismic profile data, effectively realizing the function of the present invention to obtain the processed time-lapse variable offset fiber optic vertical seismic profile data and the time-lapse three-dimensional fiber optic vertical seismic profile data, and having a relatively fast data processing speed and accurate processing results.

[0019] 4. In the present invention, the obtained processed time-lapse variable-offset fiber optic vertical seismic profile data and time-lapse three-dimensional fiber optic vertical seismic profile data are subjected to amplitude-preserving prestack depth migration processing based on AI artificial intelligence to obtain the vertical seismic profile data after migration processing. Then, the fluid-sensitive attribute parameters in the vertical seismic profile data after migration processing are extracted. Next, in combination with the S transform, highlight body data is obtained. Then, the three-dimensional spatial distribution range and the change over time of the oil-water two-phase and oil-gas-water three-phase fluid boundaries around the well are calculated and monitored, so as to obtain the utilization status of underground oil and gas resources and the distribution status and characteristics of the remaining oil and gas resources around the well. Furthermore, the oil and gas recovery rate can be increased. Then, the liquid production or gas production profile of each production well underground, the water absorption or gas absorption profile of each injection well, and the data of the three-dimensional spatial distribution range and the change over time of the oil-water two-phase and oil-gas-water three-phase fluid boundaries around the well are input into the AI real-time underground fluid monitoring data processing model. In combination with the distribution of microseismic events induced by underground fluid migration in the three-dimensional underground space and the fracture mechanism at the source point position, the real-time measurement and monitoring of the changes in the oil-water two-phase fluid interface and the oil-gas-water three-phase fluid interface underground and around the well are realized, so as to obtain the utilization status of underground oil and gas resources and the distribution status and characteristics of the remaining oil and gas resources around the well. Furthermore, the development plan and production system are optimized and adjusted in a timely manner to achieve the purpose of increasing the oil and gas recovery rate. The present invention effectively realizes the function of real-time measurement and monitoring of the changes in the oil-water two-phase fluid interface and the oil-gas-water three-phase fluid interface underground and around the well, and also has the function of obtaining the utilization status of underground oil and gas resources and the distribution status and characteristics of the remaining oil and gas resources around the well, which enables the timely optimization and adjustment of the development plan and production system and achieves the purpose of increasing the oil and gas recovery rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 is a schematic diagram of the overall structure of the present invention; Figure 2 is a schematic diagram of the coiled tubing body structure of the present invention; Figure 3 is a schematic diagram of the straight optical unit structure of the present invention; Figure 4 is a schematic diagram of the spiral optical unit structure of the present invention; Figure 5 is a schematic diagram of the construction of the underground fluid monitoring data processing unit of the present invention.

[0021] In the figure: 1. Fiber optic sensing composite modulation and demodulation instrument; 2. Coiled tubing body; 3. Straight optical unit; 301. Straight single-mode optical fiber; 302. Straight multimode optical fiber; 303. Straight single-mode strain optical unit; 304. Straight continuous grating optical fiber; 4. Helical optical unit; 401. Helical single-mode optical fiber; 402. Helical multimode optical fiber; 403. Helical single-mode strain optical unit; 404. Helical continuous grating optical fiber; 5. Surface artificial seismic source; 6. Surface geophone; 7. Underground fluid monitoring data processor. Detailed implementation mode

[0022] In order to make the technical means, creative features, achieved purposes and effects of the present invention easy to understand, the present invention will be further described below in conjunction with the detailed implementation mode.

[0023] Such as Figures 1-5As shown in the figure, an underground fluid monitoring system and method based on an AI large model includes an optical fiber sensing composite modulation and demodulation instrument 1, a coiled tubing body 2, and an underground fluid monitoring data processor 7. The optical fiber sensing composite modulation and demodulation instrument 1 is installed near the surface wellhead. The coiled tubing body 2 is laid underground. The underground fluid monitoring data processor 7 is set near the surface wellhead. On the outer sidewall of the coiled tubing body 2, a straight optical unit 3 and a spiral optical unit 4 are inlaid. The optical fiber sensing composite modulation and demodulation instrument 1 is connected to the optical fibers in the straight optical unit 3 and the spiral optical unit 4. The underground fluid monitoring data processor 7 is connected to the optical fiber sensing composite modulation and demodulation instrument 1. The straight optical unit 3 is used to monitor and measure in real time the fluid noise data, strain data, temperature data, seismic data, micro-seismic data, and time-lapse vertical surface profile data in the formation around the wellbore outside the underground coiled tubing body 2. The spiral optical unit 4 is used to monitor and measure in real time the fluid noise data, three-component strain data, temperature data, three-component seismic data, three-component micro-seismic data, and three-component time-lapse vertical surface profile data outside the coiled tubing body 2. Inside the underground fluid monitoring data processor 7, there are an underground fluid distribution change data processing unit and an underground fluid monitoring data processing unit. The underground fluid monitoring data processing unit is distilled by the underground fluid distribution change data processing unit. The underground fluid distribution change data processing unit includes an underground three-phase fluid static distribution model, a three-dimensional viscoelastic medium anisotropic longitudinal wave velocity model, and a three-dimensional viscoelastic medium anisotropic shear wave velocity model. The underground three-phase fluid static distribution model is made by an underground three-dimensional reservoir model modeling software using a three-dimensional geological model, a three-dimensional structural model, a three-dimensional porosity model, and a three-dimensional permeability model. The three-dimensional viscoelastic medium anisotropic longitudinal wave velocity model and the three-dimensional viscoelastic medium anisotropic shear wave velocity model are both generated by an underground three-dimensional velocity modeling software using a three-dimensional geological structure model, a three-dimensional seismic velocity model, acoustic logging data, vertical surface profile data, rock physics measurement data, anisotropy coefficient, and attenuation coefficient Q value. The underground fluid monitoring data processing unit is used to process the fluid noise data, strain data, temperature data, seismic data, micro-seismic data, and time-lapse vertical surface profile data in the formation around the wellbore outside the underground coiled tubing body 2 monitored and measured in real time by the straight optical unit 3, and the fluid noise data, three-component strain data, temperature data, three-component seismic data, three-component micro-seismic data, and three-component time-lapse vertical surface profile data outside the coiled tubing body 2 monitored and measured in real time by the spiral optical unit 4. Through the set underground fluid monitoring data processing unit, the data collected by the underground coiled tubing body 2 and the spiral optical unit 4 can be monitored and measured in real time.

[0024] Specifically, the fiber optic sensing composite modulation and demodulation instrument 1 internally includes a DAS signal input module, a DTS signal input module, a DSS signal input module, and a DPS signal input module; the straight optical unit 3 includes a straight single-mode optical fiber 301, a straight multimode optical fiber 302, a straight single-mode strain optical unit 303, and a straight continuous grating optical fiber or a straight microstructured optical fiber 304. The straight single-mode optical fiber 301 is connected to the signal input end of the DAS signal input module, the straight multimode optical fiber 302 is connected to the signal input end of the DTS signal input module, the straight single-mode strain optical unit 303 is connected to the signal input end of the DSS signal input module, and the straight continuous grating optical fiber or the straight microstructured optical fiber 304 is connected to the signal input end of the DPS signal input module; the straight single-mode optical fiber 301, the straight multimode optical fiber 302, the straight single-mode strain optical unit 303, and the straight continuous grating optical fiber or the straight microstructured optical fiber 304 in the straight optical unit 3 are all high-temperature resistant, hydrogen loss resistant, and high-reflection coefficient type optical fibers. Through the fiber optic sensing composite modulation and demodulation instrument 1, the DSS signal outside the continuous tubing body 2 can be monitored and measured in real time through the straight single-mode strain optical unit 303 and the helical single-mode strain optical unit 403 embedded in the outer sidewall of the multi-well coiled tubing body 2.

[0025] Specifically, the helical optical unit 4 includes a helical single-mode optical fiber 401, a helical multimode optical fiber 402, a helical single-mode strain optical unit 403, and a helical continuous grating optical fiber or a helical microstructured optical fiber 404. The optimized helical winding angle of the helical optical unit 4 is 60 degrees; the helical single-mode optical fiber 401 is connected to the signal input end of the DAS signal input module, the helical multimode optical fiber 402 is connected to the signal input end of the DTS signal input module, the helical single-mode strain optical unit 403 is connected to the signal input end of the DSS signal input module, and the signal output end of the helical continuous grating optical fiber or the helical microstructured optical fiber 404 is data communication connected to the DPS signal input module; the helical single-mode optical fiber 401, the helical multimode optical fiber 402, the helical single-mode strain optical unit 403, and the helical continuous grating optical fiber or the helical microstructured optical fiber 404 in the helical optical unit 4 are all high-temperature resistant, hydrogen loss resistant, and high-reflection coefficient type optical fibers. Through the fiber optic sensing composite modulation and demodulation instrument 1, the DAS signal, DTS signal, and DPS signal on both the inner and outer sides of the continuous tubing body 2 can be monitored and measured in real time through the straight optical unit 3 and the helical optical unit 4.

[0026] Specifically, both the straight single-mode strain optical fiber unit 303 and the helical single-mode strain optical fiber unit 403 are made by coating a high-temperature resistant and high-strength flexible composite material on the outer sidewalls of the straight single-mode optical fiber 301 and the helical single-mode optical fiber 401 to make the diameters of the straight single-mode optical fiber 301 and the helical single-mode optical fiber 401 be 1 mm to 2 mm, and then placing them in stainless steel tubes with corresponding inner diameters. Both the straight single-mode strain optical fiber unit 303 and the helical single-mode strain optical fiber unit 403 are used to sense the stress and strain outside the stainless steel tubes. By modulating and demodulating the DTS signals transmitted by the straight multimode optical fiber 302 and the helical multimode optical fiber 402, the real-time temperature data of the entire well section of the coiled tubing body 2 can be obtained, and the temperature drift correction of the measured underground stress data can be performed, so as to obtain the true underground stress data of the underground coiled tubing body 2 corrected at different depths and different orientations.

[0027] Specifically, grooves are provided on the outer sidewall of the coiled tubing body 2. Before the coiled tubing body 2 is welded into a pipe, the straight optical fiber unit 3 is entirely embedded in the middle position of the weld of the coiled tubing body 2 or symmetrically embedded in the middle positions of the weld and the groove of the coiled tubing body 2 respectively. When the coiled tubing body 2 is welded and formed, the straight optical fiber unit 3 is embedded and welded with the coiled tubing body 2; after the straight optical fiber unit 3 and the helical optical fiber unit 4 are embedded on the outer sidewall of the coiled tubing body 2, they are filled and fixed with a high-temperature resistant flexible composite material and covered with a thin stainless steel sleeve after fixation. By filling and fixing with a high-temperature resistant flexible composite material and covering with a thin stainless steel sleeve after fixation, the straight optical fiber unit 3 and the helical optical fiber unit 4 can be protected.

[0028] Specifically, the surface artificial seismic source 5 is arranged on the ground near the wellhead. The fiber optic sensing composite modulation and demodulation instrument 1 uses the straight single-mode optical fiber 301 and the helical single-mode optical fiber 401 to collect the vertical ground profile data and time-lapse vertical ground profile data excited by the surface artificial seismic source 5. By using the straight single-mode optical fiber 301 and the helical single-mode optical fiber 401, the vertical ground profile data and time-lapse vertical ground profile data excited by the surface artificial seismic source 5 can be collected.

[0029] Specifically, the surface geophone 6 is used to collect the surface seismic data excited by the surface artificial seismic source 5. While collecting the surface seismic data, the geophone 6 collects the vertical ground profile data in the well through the straight single-mode optical fiber 301 and the helical single-mode optical fiber 401, realizing well-ground joint seismic data acquisition and well-ground three-dimensional exploration. By collecting the vertical ground profile data in the well through the straight single-mode optical fiber 301 and the helical single-mode optical fiber 401, well-ground joint seismic data acquisition and well-ground three-dimensional exploration are thus realized.

[0030] Specifically, the underground fluid distribution change data processing unit is specifically trained by an AI data large model using an underground three-phase fluid static distribution model, a three-dimensional viscoelastic medium anisotropic longitudinal wave velocity model, and a three-dimensional viscoelastic medium anisotropic shear wave velocity model; the underground three-phase fluid static distribution model uses a three-dimensional geological model, a three-dimensional structural model, a three-dimensional porosity model, and a three-dimensional permeability model as input data for an underground three-dimensional reservoir model building software, and the three-dimensional geological structure model, the three-dimensional seismic velocity model, acoustic logging data, vertical ground profile data, rock physics measurement data, anisotropy coefficient, and attenuation coefficient Q value are input data for an underground three-dimensional velocity model building software.

[0031] An optical fiber coiled tubing underground fluid monitoring method based on an AI large model includes the following steps: Step 1, during oil and gas production, the optical fiber sensing composite modulation and demodulation instrument 1 is used to monitor and measure the DSS signal on the outer side of the coiled tubing body 2 in real time through the straight single-mode strain optical unit 303 and the helical single-mode strain optical unit 403 embedded in the outer sidewall of the multi-well coiled tubing body 2, and then the optical fiber sensing composite modulation and demodulation instrument 1 is used to monitor and measure the DAS signal, DTS signal, and DPS signal on both the inner and outer sides of the coiled tubing body 2 through the straight optical unit 3 and the helical optical unit 4, so that the present invention has the function of monitoring and measuring the DAS signal, DTS signal, and DPS signal on both the inner and outer sides of the coiled tubing body 2 in real time. Step 2, the optical fiber sensing composite modulation and demodulation instrument 1 is used to modulate and demodulate the multi-well DTS signal and DSS signal measured in Step 1. Among them, the DSS signal transmitted through the straight single-mode strain optical unit 303 can be modulated and demodulated to obtain the underground stress data at different depths on the outer side of the coiled tubing body 2, and the DSS signal transmitted through the helical single-mode strain optical unit 403 can be modulated and demodulated to obtain the underground three-component stress data at different depths and different azimuths on the outer side of the coiled tubing body 2. Then, the DTS signal transmitted through the straight multimode optical fiber 302 and the helical multimode optical fiber 402 can be modulated and demodulated to obtain the real-time temperature data of the entire well section of the coiled tubing body 2 and correct the measured underground stress data for temperature drift, so as to obtain the true underground stress data corrected at different depths and different azimuths of the underground coiled tubing body 2, so that the present invention has the function of obtaining the true underground stress data corrected at different depths and different azimuths of the underground coiled tubing body 2. Step 3, based on the underground three-component stress data at different depths and different azimuths on the outer side of the coiled tubing body 2 obtained in Step 2, a three-dimensional distribution map of the underground three-component stress field at each depth and each azimuth is drawn, so as to obtain the distribution change characteristics of the underground three-component stress field along the trajectory of the coiled tubing body 2, so that the present invention has the function of obtaining the distribution change characteristics of the underground three-component stress field along the trajectory of the coiled tubing body 2. Step 4: Based on the distribution change characteristics of the underground three-component stress field along the trajectory of the coiled tubing body 2, conduct real-time long-term monitoring on the well sections with high underground three-component stress of the coiled tubing body 2, so as to prevent the damage of the local coiled tubing body 2, that is, the present invention has the function of preventing the damage of the local coiled tubing body 2; Step 5: By using the fiber optic sensing composite modulation and demodulation instrument 1 to modulate and demodulate the DAS signals transmitted by the helical single-mode optical fiber 401, the distribution of three-component microseismic data in the three-dimensional space around the well trajectory can be obtained, so as to monitor the distribution of microseismic events induced by underground fluid migration in the underground three-dimensional space and its fracture mechanism at the source point position, that is, the present invention has the function of monitoring the distribution of microseismic events induced by underground fluid migration in the underground three-dimensional space and its fracture mechanism at the source point position.

[0032] Specifically, in Step 1, by using the fiber optic sensing composite modulation and demodulation instrument 1 to modulate and demodulate the obtained DSS signals, DAS signals, DTS signals and DPS signals, the underground distributed noise data, temperature data, underground stress data and fluid pressure data in the pores of the underground reservoir can also be obtained, so as to be able to measure and monitor the changes of the oil-water two-phase fluid interface and the oil-gas-water three-phase fluid interface underground and around the well in real time, and further optimize the exploitation mode and development process of underground oil and gas resources, thereby improving the recovery rate of underground oil and gas resources. The specific steps are as follows. Step A: Use the fiber optic sensing composite modulation and demodulation instrument 1 to modulate and demodulate the input DSS signals, DAS signals, DTS signals and DPS signals, and obtain the fluid noise data, formation temperature data, in-situ stress data and fluid pressure data in the pores of the rock distributed around multiple underground wells, that is, the present invention has the function of obtaining the fluid noise data, formation temperature data, in-situ stress data and fluid pressure data in the pores of the rock distributed around multiple underground wells; Step B: Input the fluid noise data, formation temperature data, in-situ stress data and fluid pressure data in the pores of the rock obtained in Step A into the underground fluid distribution change data processing unit as multiple parameters, and calculate through the joint inversion method based on AI artificial intelligence, so as to obtain the liquid production or gas production profile of each underground oil and gas production well and the water absorption or gas absorption profile data of each water injection or gas injection well, that is, the present invention has the function of obtaining the liquid production or gas production profile of each underground oil and gas production well and the water absorption or gas absorption profile data of each water injection or gas injection well; Step C: Based on the three-component in-situ stress field data obtained in Step A, conduct real-time monitoring on the distribution change of the in-situ stress field on the outer wall of the coiled tubing body 2, so as to prevent the damage of the high in-situ stress concentration pipe section, that is, the present invention has the function of preventing the damage of the high in-situ stress concentration pipe section; Step D: Regularly activate the surface artificial seismic source 5 set on the ground, and then collect time-lapse variable-offset fiber-optic vertical seismic profile data and time-lapse three-dimensional fiber-optic vertical seismic profile data through the straight single-mode optical fiber 301 and the helical single-mode optical fiber 401 on the outer wall of the coiled tubing body 2, so that the present invention has the function of collecting time-lapse variable-offset fiber-optic vertical seismic profile data and time-lapse three-dimensional fiber-optic vertical seismic profile data; Step E: Perform surface-consistent amplitude compensation processing, surface-consistent deconvolution processing, and wavefield separation processing with relative amplitude preservation based on AI artificial intelligence on the time-lapse variable-offset fiber-optic vertical seismic profile data and time-lapse three-dimensional fiber-optic vertical seismic profile data collected in different periods in Step D, so as to obtain processed time-lapse variable-offset fiber-optic vertical seismic profile data and time-lapse three-dimensional fiber-optic vertical seismic profile data, so that the present invention has the function of obtaining processed time-lapse variable-offset fiber-optic vertical seismic profile data and time-lapse three-dimensional fiber-optic vertical seismic profile data; Step F: Perform amplitude-preserving prestack depth migration processing based on AI artificial intelligence on the processed time-lapse variable-offset fiber-optic vertical seismic profile data and time-lapse three-dimensional fiber-optic vertical seismic profile data obtained in Step E to obtain migrated vertical seismic profile data, then extract fluid-sensitive attribute parameters from the migrated vertical seismic profile data, then combine with the S transform to obtain highlight body data, and then calculate and monitor the three-dimensional spatial distribution range and its change over time of the oil-water two-phase and oil-gas-water three-phase fluid boundaries around the well, so as to obtain the utilization status of underground oil and gas resources and the distribution state and characteristics of remaining oil and gas resources around the well, and further improve the oil and gas recovery rate, so that the present invention has the function of improving the oil and gas recovery rate; Step G: Input the liquid production or gas production profile of each production well underground obtained in Step B, the water absorption or gas absorption profile data of each injection well, and the three-dimensional spatial distribution range and its change over time data of the oil-water two-phase and oil-gas-water three-phase fluid boundaries around the well obtained in Step F into the AI real-time underground fluid monitoring data processing model 12, and combine the distribution of microseismic events induced by underground fluid migration in the underground three-dimensional space and its fracture mechanism at the seismic source point position to realize real-time measurement and monitoring of the changes in the oil-water two-phase fluid interface and oil-gas-water three-phase fluid interface underground and around the well, so as to obtain the utilization status of underground oil and gas resources and the distribution state and characteristics of remaining oil and gas resources around the well, and then timely optimize and adjust the development plan and production system and achieve the purpose of improving the oil and gas recovery rate, so that the present invention has the function of timely optimizing and adjusting the development plan and production system and achieving the improvement of the oil and gas recovery rate.

[0033] All the electronic components used in the present invention are common standard components or components known to those skilled in the art, and their structures and principles can all be learned by those skilled in the art through technical manuals or through conventional experimental methods.

[0034] The basic principles, main features and advantages of the present invention have been shown and described above. Those skilled in the art should understand that the present invention is not limited by the above embodiments. What is described in the above embodiments and the specification only illustrates the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. An optical fiber coiled tubing underground fluid monitoring system based on an AI large model, comprising an optical fiber sensing composite modem (1), a coiled tubing body (2) and an underground fluid monitoring data processor (7), characterized in that: The optical fiber sensing composite modem (1) is installed near the surface wellhead, the coiled tubing body (2) is laid underground, and the underground fluid monitoring data processor (7) is arranged near the surface wellhead; The outer side wall of the coiled tubing body (2) is inlaid with a straight light unit (3) and a spiral light unit (4); the optical fiber sensing composite modem (1) is connected to the optical fibers in the straight light unit (3) and the spiral light unit (4); and the underground fluid monitoring data processor (7) is connected to the optical fiber sensing composite modem (1); The straight optical unit (3) is used to monitor and measure in real time the fluid noise data, strain data, temperature data, seismic data, microseismic data and time-shifted vertical ground profile data outside the underground coiled tubing body (2); The spiral optical unit (4) is used to monitor and measure in real time the fluid noise data, three-component strain data, temperature data, three-component seismic data in the formation around the wellbore, three-component microseismic data and three-component time-lapse vertical ground profile data outside the coiled tubing body (2); The underground fluid monitoring data processor (7) is internally provided with an underground fluid distribution change data processing unit and an underground fluid monitoring data processing unit, wherein the underground fluid monitoring data processing unit is distilled from the underground fluid distribution change data processing unit; The underground fluid distribution change data processing unit comprises an underground three-phase fluid static distribution model, a three-dimensional viscoelastic medium anisotropic longitudinal wave velocity model and a three-dimensional viscoelastic medium anisotropic shear wave velocity model. The underground three-phase fluid static distribution model is made by using a three-dimensional geological model, a three-dimensional structural model, a three-dimensional porosity model and a three-dimensional permeability model through an underground three-dimensional reservoir modeling software. The three-dimensional viscoelastic medium anisotropic longitudinal wave velocity model and the three-dimensional viscoelastic medium anisotropic shear wave velocity model are both generated by using a three-dimensional geological structural model, a three-dimensional seismic velocity model, sonic logging data, vertical ground profile data, rock physical measurement data, anisotropy coefficient and attenuation coefficient Q value through an underground three-dimensional velocity modeling software. The underground fluid monitoring data processing unit is used to process the fluid noise data, strain data, temperature data, seismic data, microseismic data and time-shifted vertical ground profile data outside the underground continuous oil pipe body (2) monitored and measured in real time by the straight light unit (3) and the fluid noise data, three-component strain data, temperature data, three-component seismic data, three-component microseismic data and three-component time-shifted vertical ground profile data outside the continuous oil pipe body (2) monitored and measured in real time by the spiral light unit (4).

2. According to claim 1, an optical fiber coiled tubing underground fluid monitoring system based on an AI large model is characterized by: The optical fiber sensing composite modem (1) internally comprises a DAS signal input module, a DTS signal input module, a DSS signal input module and a DPS signal input module; The straight optical unit (3) comprises a straight single-mode optical fiber (301), a straight multi-mode optical fiber (302), a straight single-mode strain optical unit (303) and a straight continuous grating optical fiber or a straight microstructure optical fiber (304); the straight single-mode optical fiber (301) is connected to a signal input end of a DAS signal input module, the straight multi-mode optical fiber (302) is connected to a signal input end of a DTS signal input module, the straight single-mode strain optical unit (303) is connected to a signal input end of a DSS signal input module, and the straight continuous grating optical fiber or the straight microstructure optical fiber (304) is connected to a signal input end of a DPS signal input module; The straight single-mode optical fiber (301), the straight multi-mode optical fiber (302), the straight single-mode strain optical unit (303), and the straight continuous grating optical fiber or the straight microstructure optical fiber (304) in the straight optical unit (3) are all high-temperature resistant, hydrogen-loss resistant, and high-reflection coefficient optical fibers.

3. The optical fiber coiled tubing underground fluid monitoring system based on AI large model according to claim 2 is characterized by: The spiral optical unit (4) comprises a spiral single-mode optical fiber (401), a spiral multimode optical fiber (402), a spiral single-mode strain optical unit (403) and a spiral continuous grating optical fiber or a spiral microstructure optical fiber (404); the spiral winding optimization angle of the spiral optical unit (4) is 60 degrees; the spiral single-mode optical fiber (401) is connected to the signal input end of the DAS signal input module, the spiral multimode optical fiber (402) is connected to the signal input end of the DTS signal input module, the spiral single-mode strain optical unit (403) is connected to the signal input end of the DSS signal input module, and the signal output end of the spiral continuous grating optical fiber or the spiral microstructure optical fiber (404) is connected to the DPS signal input module for data communication; The spiral single-mode optical fiber (401), the spiral multi-mode optical fiber (402), the spiral single-mode strain optical unit (403), and the spiral continuous grating optical fiber or the spiral microstructure optical fiber (404) in the spiral optical unit (4) are all high-temperature resistant, hydrogen-loss resistant, and high-reflection coefficient optical fibers.

4. The optical fiber coiled tubing underground fluid monitoring system based on AI large model according to claim 3 is characterized by: The straight single-mode strain light unit (303) and the spiral single-mode strain light unit (403) are both made by coating the outer side walls of the straight single-mode optical fiber (301) and the spiral single-mode optical fiber (401) with a high-temperature resistant and high-strength flexible composite material, and placing the straight single-mode optical fiber (301) and the spiral single-mode optical fiber (401) in a stainless steel tube with a corresponding inner diameter after the diameters of the straight single-mode optical fiber (301) and the spiral single-mode optical fiber (401) are made to be 1 mm to 2 mm. The straight single-mode strain light unit (303) and the spiral single-mode strain light unit (403) are both used to sense stress and strain outside the stainless steel tube.

5. The optical fiber coiled tubing underground fluid monitoring system based on AI large model according to claim 4 is characterized by: The outer wall of the coiled tubing body (2) is provided with a groove. Before the coiled tubing body (2) is welded into a pipe, the straight light unit (3) is completely embedded in the middle of the weld of the coiled tubing body (2) or is symmetrically embedded in the weld and the middle of the groove of the coiled tubing body (2). The straight light unit (3) is embedded and welded with the coiled tubing body (2) when the coiled tubing body (2) is welded into shape. After the straight light unit (3) and the spiral light unit (4) are embedded in the outer wall of the coiled tubing body (2), they are filled and fixed with a high-temperature resistant flexible composite material and then covered with a thin layer of stainless steel sleeve.

6. The optical fiber coiled tubing underground fluid monitoring system based on AI large model according to claim 1, further comprising a ground artificial seismic source (5), characterized in that: The ground artificial seismic source (5) is arranged on the ground near the wellhead, and the optical fiber sensing composite modem (1) uses a straight single-mode optical fiber (301) and a spiral single-mode optical fiber (401) to collect vertical ground profile data and time-shifted vertical ground profile data stimulated by the ground artificial seismic source (5).

7. The optical fiber coiled tubing underground fluid monitoring system based on the AI ​​large model according to claim 6 further comprises a ground detector (6), characterized in that: The ground detector (6) is used to collect ground seismic data stimulated by a ground artificial seismic source (5). While collecting the ground seismic data, the detector (6) collects vertical ground profile data in the well through a straight single-mode optical fiber (301) and a spiral single-mode optical fiber (401), thereby realizing well-ground combined seismic data collection and well-ground three-dimensional exploration.

8. The optical fiber coiled tubing underground fluid monitoring system based on AI large model according to claim 7 is characterized by: The underground fluid distribution change data processing unit is specifically formed by using an underground three-phase fluid static distribution model, a three-dimensional viscoelastic medium anisotropic longitudinal wave velocity model and a three-dimensional viscoelastic medium anisotropic shear wave velocity model through AI data large model training; The underground three-phase fluid static distribution model uses a three-dimensional geological model, a three-dimensional structural model, a three-dimensional porosity model and a three-dimensional permeability model as input data for the underground three-dimensional oil reservoir modeling software, and the three-dimensional geological structural model, three-dimensional seismic velocity model, sonic logging data, vertical ground profile data, rock physics measurement data, anisotropy coefficient and attenuation coefficient Q value are input data for the underground three-dimensional velocity modeling software.

9. A method for monitoring underground fluid in optical fiber coiled tubing based on AI large model, wherein the specific monitoring process of the method for monitoring underground fluid in optical fiber coiled tubing is based on the optical fiber coiled tubing underground fluid monitoring system according to any one of claims 1 to 9, characterized in that: The following steps are involved: Step 1: During oil and gas production, the optical fiber sensing composite modem (1) monitors and measures the DSS signal on the outside of the coiled tubing body (2) in real time via the straight single-mode strain optical unit (303) and the spiral single-mode strain optical unit (403) embedded in the outer wall of the multi-well coiled tubing body (2), and then monitors and measures the DAS signal, DTS signal and DPS signal on both sides of the inside and outside of the coiled tubing body (2) in real time via the optical fiber sensing composite modem (1) via the straight optical unit (3) and the spiral optical unit (4); Step 2: Using an optical fiber sensing composite modulator (1) to modulate and demodulate the multi-well DTS signals and DSS signals measured in step 1, wherein the underground stress data at different depths outside the coiled tubing body (2) can be obtained by modulating and demodulating the DSS signal transmitted by the straight single-mode strain light unit (303), and then the underground three-component stress data at different depths and different orientations outside the coiled tubing body (2) can be obtained by modulating and demodulating the DSS signal transmitted by the spiral single-mode strain light unit (403). Then, by modulating and demodulating the DTS signal transmitted by the straight multimode optical fiber (302) and the spiral multimode optical fiber (402), the real-time temperature data of the coiled tubing body (2) of the entire well section can be obtained, and the measured underground stress data can be corrected for temperature drift, thereby obtaining the corrected real underground stress data of the underground coiled tubing body (2) at different depths and different orientations; Step 3: based on the underground three-component stress data at different depths and different directions outside the coiled tubing body (2) obtained in step 2, a three-dimensional distribution diagram of the underground three-component stress field at each depth and direction is drawn, so as to obtain the distribution change characteristics of the underground three-component stress field along the trajectory of the coiled tubing body (2); Step 4: Based on the distribution change characteristics of the underground three-component stress field along the trajectory of the coiled tubing body (2), the well section with high underground three-component stress of the coiled tubing body (2) is monitored in real time and for a long time, so as to prevent the local coiled tubing body (2) from being damaged; Step 5: Using the optical fiber sensing composite modulator (1) to modulate and demodulate the DAS signal transmitted by the spiral single-mode optical fiber (401), the distribution of three-component microseismic data in the three-dimensional space around the well trajectory can be obtained, thereby monitoring the distribution of microseismic events induced by underground fluid migration in the underground three-dimensional space and their rupture mechanism at the source point.

10. The optical fiber coiled tubing underground fluid monitoring method based on AI large model according to claim 9 is characterized by: In step 1, by using the optical fiber sensing composite modulator (1) to modulate and demodulate the obtained DSS signal, DAS signal, DTS signal and DPS signal, it is also possible to obtain underground distributed noise data, temperature data, underground stress data and fluid pressure data in underground reservoir pores, so as to measure and monitor the changes of the oil-water two-phase fluid interface and the oil-gas-water three-phase fluid interface underground and around the well in real time, thereby optimizing the mining method and development process of underground oil and gas resources, thereby improving the recovery rate of underground oil and gas resources. The specific steps are as follows: Step A, using a fiber optic sensor composite modulator (1) to modulate and demodulate the input DSS signal, DAS signal, DTS signal and DPS signal and obtain fluid noise data distributed around multiple underground wells, formation temperature data, ground stress data and pressure data of fluid in rock pores; Step B, the underground distributed fluid noise data, formation temperature data, ground stress data and pressure data of fluid in rock pores obtained in step A are input into the underground fluid distribution change data processing unit by using multi-parameters and calculated by a joint inversion method based on AI artificial intelligence, so as to obtain the liquid production or gas production profile of each underground oil and gas production well and the water or gas absorption profile data of each water injection or gas injection well; Step C, monitoring the distribution change of the ground stress field along the outer wall of the coiled tubing body (2) in real time based on the three-component ground stress field data of the underground distribution obtained in step A, so as to prevent damage to the pipe section with high ground stress concentration; Step D, regularly exciting a ground artificial seismic source (5) disposed on the ground, and then collecting time-shifted variable offset optical fiber vertical ground profile data and time-shifted three-dimensional optical fiber vertical ground profile data through a straight single-mode optical fiber (301) and a spiral single-mode optical fiber (401) on the outer wall of the coiled tubing body (2); Step E, performing AI-based surface consistent amplitude compensation processing, surface consistent deconvolution processing, and relatively amplitude-preserving wavefield separation processing on the time-shifted variable offset fiber vertical ground profile data and the time-shifted three-dimensional fiber vertical ground profile data acquired at different periods obtained in step D, so as to obtain the processed time-shifted variable offset fiber vertical seismic profile data and the time-shifted three-dimensional fiber vertical seismic profile data; Step F, the processed time-shifted variable offset fiber vertical seismic profile data and the time-shifted three-dimensional fiber vertical seismic profile data obtained in step E are processed by amplitude-preserving prestack depth migration based on AI artificial intelligence to obtain vertical seismic profile data after migration processing, and then the fluid sensitive attribute parameters in the vertical seismic profile data after migration processing are extracted, and then the highlight data is obtained by combining S transformation, and then the three-dimensional spatial distribution range and time change of the oil-water two-phase and oil-gas-water three-phase fluid boundaries around the well are calculated and monitored, so as to obtain the utilization status of underground oil and gas resources and the distribution status and characteristics of the remaining oil and gas resources around the well, thereby improving the oil and gas recovery rate; Step G, input the liquid production or gas production profile of each underground production well obtained in step B, the water absorption or gas absorption profile data of each injection well, and the three-dimensional spatial distribution range and time change data of the oil-water two-phase and oil-gas-water three-phase fluid boundaries around the wells obtained in step F into the AI ​​real-time underground fluid monitoring data processing model (12), combined with the distribution of microseismic events induced by underground fluid migration in the underground three-dimensional space and its rupture mechanism at the source point, to achieve real-time measurement and monitoring of the changes in the oil-water two-phase fluid interface and the oil-gas-water three-phase fluid interface underground and around the wells, so as to obtain the utilization status of underground oil and gas resources and the distribution status and characteristics of the remaining oil and gas resources around the wells, and then timely optimize and adjust the development plan and production system to achieve the purpose of improving oil and gas recovery.

Images