Gas well production optical fiber monitoring simulation experiment system and gas production contribution rate calculation method

Abstract

The invention relates to the technical field of petroleum and natural gas development, in particular to a gas well production optical fiber monitoring simulation experiment system and a gas production contribution rate calculation method.The gas well production optical fiber monitoring simulation experiment system comprises a full-size pipe column simulation system; the simulation device is used for simulating the process that gas enters a shaft from a reservoir and flows in the shaft in different well completion modes and is provided with a gas injection pipeline; the gas injection system is used for injecting gases with different pressures and / or different temperatures into the full-size tubular column simulation system and is connected with the gas injection pipeline through an inlet injection pipeline; and the optical fiber monitoring system is used for acquiring temperature characteristics and sound wave characteristics of gas in the full-size tubular column simulation system under different gas flows, different pressures and different temperatures, forming a data set and being connected with the full-size tubular column simulation system through an in-well optical cable. According to the method, production layer identification and accurate calculation of the gas production contribution rate can be realized by utilizing a distributed optical fiber monitoring technology.

Description

Technical Field

[0001] The present invention relates to the technical field of oil and natural gas development, and more specifically, to a gas well production optical fiber monitoring simulation experimental system and a gas production contribution rate calculation method. Background Art

[0002] With the gradual increase in domestic gas demand, efficient production of gas wells has become an important part of ensuring energy security. Accurately understanding the gas production status of gas wells is the key to optimizing development plans and improving production efficiency, and it is urgent to carry out gas well production profile testing. At present, it is difficult to test each production layer using conventional gas production profile testing technology. The following shortcomings exist: conventional testing technology involves operations such as dragging and lowering the test pipe string and sealing the layer during the test process, which has high construction risks and affects the flow state of the wellbore fluid, resulting in inaccurate measurement results; conventional instruments have poor response under small flow rates; and the life of the test instrument is limited under high temperature environments. Therefore, it cannot meet the needs of accurate prediction of gas well production. Summary of the invention

[0003] The purpose of the present invention is to overcome the deficiency of the existing technology that cannot meet the demand for accurate prediction of gas production in gas wells, and to provide a gas well production optical fiber monitoring simulation experimental system and a gas production contribution rate calculation method, which can realize the accurate calculation of production layer identification and gas production contribution rate by using distributed optical fiber monitoring technology.

[0004] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0005] Provided is a gas well production optical fiber monitoring simulation experiment system, including

[0006] Full-scale string simulation system, used to simulate the process of gas entering the wellbore from the reservoir and flowing in the wellbore under different completion methods, with gas injection pipeline;

[0007] A gas injection system, used to inject gases of different pressures and / or temperatures into the full-scale string simulation system, connected to the gas injection pipeline via an inlet injection line;

[0008] The optical fiber monitoring system is used to obtain the temperature characteristics and acoustic wave characteristics of the gas in the full-scale tubing simulation system at different gas flow rates, different pressures, and different temperatures, and form a data set, which is connected to the full-scale tubing simulation system through a downhole optical cable.

[0009] The present invention injects gases of different pressures and / or temperatures into the full-size tubing simulation system through a gas injection system to simulate situations under different gas pressures and temperatures in different gas wells; the full-size tubing simulation system can realistically simulate the process of gas entering the wellbore from the reservoir and flowing in the wellbore, and can also select different completion methods, which can be a screen tube completion method, a perforated tube completion method, or a bare hole completion without a completion tubing; and then use an optical fiber monitoring system to extract the acoustic wave and temperature response characteristics of each flow process for calculating the gas production contribution rate.

[0010] Preferably, the full-size tubing simulation system comprises an inlet high-pressure rubber hose, a completion tubing, a flow steel pipe, and an outlet high-pressure rubber hose which are connected in sequence, an inlet gate valve is provided at the end of the inlet high-pressure rubber hose, an outlet gate valve is provided at the end of the outlet high-pressure rubber hose, a steel pipe is provided outside the completion tubing, both ends of the steel pipe are sealed to the outer wall of the completion tubing by a seal, the gas injection pipeline is connected to the side of the steel pipe, the downhole optical cable passes through the inlet gate valve, the inlet high-pressure rubber hose, the completion tubing, the flow steel pipe, and the outlet high-pressure rubber hose in sequence, an internal temperature and pressure sensor is provided in the completion tubing, an external temperature and pressure sensor is provided outside the completion tubing and located in the steel pipe, and a plurality of temperature and pressure sensors are provided in sequence along the length direction of the flow steel pipe to form a temperature and pressure sensor array.

[0011] Preferably, a flow divider is provided inside the steel pipe and between the steel pipe and the completion string, the end of the gas injection pipeline abuts against the flow divider, and a flow annulus is formed between the flow divider and the completion string. The flow divider serves to evenly distribute the flow.

[0012] Preferably, the completion string is located in the middle of the steel pipe, ensuring that the gaps around the completion string and the steel pipe are the same in size, so that the gas flows evenly around the completion string.

[0013] Preferably, the length of the completion string is equal to the length of the steel pipe.

[0014] Preferably, the inner diameters of the inlet high-pressure rubber hose, the completion string, the flow steel pipe, and the outlet high-pressure rubber hose are all equal. The equal inner diameter setting can reduce the throttling effect caused by the change in pipe diameter and reduce the impact on the acoustic wave signal.

[0015] Preferably, the gas injection system includes a high-pressure air pump, a heater, and an injected gas temperature, pressure, and flow integrated sensor which are arranged in sequence. The high-pressure air pump is connected to the heater through an air pump outlet pipeline. One end of the injected gas temperature, pressure, and flow integrated sensor is connected to the heater through a heating outlet pipeline, and the other end is connected to the gas injection pipeline through the inlet injection pipeline.

[0016] Preferably, the completion string is a screen pipe or a perforated pipe.

[0017] The present invention also provides a method for calculating gas production contribution rate, which is applied to the gas well production optical fiber monitoring simulation experimental system as described above, and specifically comprises the following steps:

[0018] S1: Conduct gas flow monitoring experiment using the gas well production optical fiber monitoring simulation experimental system;

[0019] S2: extracting experimental temperature characteristics and experimental sound wave characteristics in the experiment;

[0020] S3: Establishing a production layer automatic identification and layer gas production contribution rate calculation model, and inputting the experimental temperature characteristics and experimental acoustic wave characteristics into the model for training;

[0021] S4: Extract the measured temperature characteristics and measured acoustic wave characteristics from the field measured data, and input them into the model for evaluation and calculation to obtain the gas production location and gas production contribution rate.

[0022] The present invention is based on the established gas well production optical fiber monitoring simulation experimental system to obtain the temperature and acoustic wave response characteristics under different gas production conditions, and can calculate the gas production contribution rate of the gas well by combining the physical model and the machine learning model.

[0023] Preferably, when conducting a gas flow monitoring experiment, there are at least 300 experimental combination schemes with different gas flow rates, different pressures, and different temperatures, and the experimental duration of each experimental scheme is not less than 10 seconds.

[0024] Compared with the prior art, the present invention has the following beneficial effects:

[0025] 1. The full-scale gas well production optical fiber monitoring simulation experimental system constructed by the present invention can truly simulate the process of gas entering the wellbore from the reservoir and flowing in the wellbore, and then extract the acoustic wave and temperature response characteristics of each flow process, laying a data foundation for the establishment of a machine learning interpretation model, and effectively solving the problem that insufficient field test data can hardly meet the requirements of training samples;

[0026] 2. Incorporate the Joule-Thomson effect model based on thermodynamic principles as a physical model constraint into the machine learning model to reduce dependence on data quality and data volume;

[0027] 3. The interpretation method no longer relies on manual experience, and can efficiently realize the automatic identification of gas well production layers and the calculation of layer gas production contribution rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 A schematic diagram of a gas well production optical fiber monitoring simulation experimental system;

[0029] Figure 2 The figure is a flow chart of a method for calculating gas production contribution rate.

[0030] In the attached figure: 601, high-pressure air pump; 602, heater; 603, injection gas temperature, pressure and flow integrated sensor; 604, DAS-DTS demodulator; 605, inlet high-pressure rubber hose; 606, steel pipe; 607, completion string; 608, gas injection pipeline; 609, flow steel pipe; 610, outlet high-pressure rubber hose; 611, well-entry optical cable; 612, flow annulus; 613, diverter; 614, outlet gate valve; 615, inlet gate valve; 701, air pump outlet pipeline; 702, heating outlet pipeline; 703, inlet injection pipeline; P1, internal temperature and pressure sensor; P2, external temperature and pressure sensor; R1, the first temperature and pressure sensor; Rn, the nth temperature and pressure sensor. DETAILED DESCRIPTION

[0031] The present invention is further described below in conjunction with specific implementation methods. The accompanying drawings are only used for exemplary descriptions and are only schematic diagrams, not actual drawings, and cannot be understood as limiting this patent; in order to better illustrate the embodiments of the present invention, some parts of the accompanying drawings may be omitted, enlarged or reduced, and do not represent the size of the actual product; for those skilled in the art, it is understandable that some well-known structures and their descriptions in the accompanying drawings may be omitted.

[0032] The same or similar numbers in the drawings of the embodiments of the present invention correspond to the same or similar parts; in the description of the present invention, it should be understood that if the terms "upper", "lower", "left", "right" and the like indicate directions or positional relationships based on the directions or positional relationships shown in the drawings, it is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction. Therefore, the terms describing the positional relationship in the drawings are only used for illustrative purposes and cannot be understood as limitations on this patent. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.

[0033] Embodiment 1

[0034] This embodiment is a first embodiment of a gas well production optical fiber monitoring simulation experimental system. Figure 1 Shown, including

[0035] A full-scale string simulation system is used to simulate the process of gas entering the wellbore from the reservoir and flowing in the wellbore under different completion methods, and is provided with a gas injection pipeline 608;

[0036] A gas injection system, used to inject gases of different pressures and / or temperatures into the full-scale string simulation system, connected to the gas injection pipeline 608 via an inlet injection line 703;

[0037] The optical fiber monitoring system is used to obtain the temperature characteristics and acoustic wave characteristics of the gas in the full-scale string simulation system at different gas flow rates, different pressures, and different temperatures, and form a data set, which is connected to the full-scale string simulation system through the downhole optical cable 611.

[0038] The optical fiber monitoring system is composed of a DAS-DTS demodulator 604 and a downhole optical cable 611; at least one single-mode optical fiber and one multi-mode optical fiber are packaged in the downhole optical cable 611; preferably, the downhole optical cable 611 can be a steel armored optical cable, a continuous oil pipe encapsulated optical cable, or an optical cable encapsulated in other forms; the downhole optical cable 611 can be a steel armored optical cable directly laid in a full-size tubular simulation system to simulate the process of lowering the optical cable into the well using a crawler in actual production; it can also be a continuous oil pipe encapsulated optical cable directly laid in a full-size tubular simulation system to simulate the process of lowering the optical cable using a continuous oil pipe in actual production; it can also be a steel armored optical cable bundled with a small oil pipe and then laid in a full-size tubular simulation system along with the small oil pipe, simulating the process of lowering the optical cable in actual production using a small oil pipe bundled method;

[0039] The DAS-DTS demodulator 604 includes a DTS demodulator for temperature monitoring and a DAS demodulator for acoustic wave monitoring; the DTS demodulator in the DAS-DTS demodulator 604 is connected to a single-mode optical fiber in the downhole optical cable 611 to monitor temperature changes along the pipeline in the full-scale pipe string simulation system; the DAS demodulator in the DAS-DTS demodulator 604 is connected to a multi-mode optical fiber in the downhole optical cable 611 to monitor acoustic wave changes along the pipeline in the full-scale pipe string simulation system;

[0040] The full-scale tubing simulation system includes an inlet high-pressure rubber hose 605, a completion tubing 607, a flow steel pipe 609, and an outlet high-pressure rubber hose 610 which are connected in sequence. An inlet gate valve 615 is provided at the end of the inlet high-pressure rubber hose 605, and an outlet gate valve 614 is provided at the end of the outlet high-pressure rubber hose 610. A steel pipe 606 is provided on the outer sleeve of the completion tubing 607. Both ends of the steel pipe 606 are sealed with the outer wall of the completion tubing through seals. A gas injection pipeline 608 is connected to the side of the steel pipe 606. An optical cable 611 penetrates the inlet gate valve 615, the inlet high-pressure rubber hose 605, the completion tubing 607, the flow steel pipe 609, and the outlet high-pressure rubber hose 610 in sequence. An internal temperature and pressure sensor P1 is provided in the completion tubing 607, an external temperature and pressure sensor P2 is provided outside the completion tubing 607 and located in the steel pipe 606, and a plurality of temperature and pressure sensors are provided in sequence along the length direction of the flow steel pipe 609 to form a temperature and pressure sensor array.

[0041] A flow divider 613 is provided inside the steel pipe 606 and between the steel pipe 606 and the completion string 607 . The end of the gas injection pipe 608 abuts against the flow divider 613 , forming a flow annulus 612 between the flow divider 613 and the completion string 607 . The flow divider 613 serves to evenly distribute the flow; the completion string 607 is centrally placed inside the steel pipe 606, and the two ends of the steel pipe 606 are sealed to the outer wall of the completion string 607 through sealing connectors to form a flow annulus 612; the size of the gap space around the completion string 607 and the steel pipe 606 is ensured to be the same, and the gas flows evenly around the completion string 607; the length of the completion string 607 is equal to the length of the steel pipe 606; one end of the high-pressure rubber hose 605 at the inlet end is connected to one end of the completion string 607, and the other end of the completion string 607 is connected to one end of the flow steel pipe 609, and the other end of the flow steel pipe 609 is connected to one end of the outlet high-pressure rubber hose 610, forming a flow channel of the full-size string simulation system;

[0042] The other end of the inlet high-pressure rubber hose 605 is connected to the inlet gate valve 615, and the other end of the outlet high-pressure rubber hose 610 is connected to the outlet gate valve 614; preferably, the inlet high-pressure rubber hose 605, the completion string 607, the flow steel pipe 609, and the outlet high-pressure rubber hose 610 have the same inner diameter; the setting of equal inner diameter can reduce the throttling effect caused by the change of pipe diameter and reduce the influence on the acoustic wave signal; moreover, the size and material of the completion string 607 and the flow steel pipe 609 are the same as the size and material of the completion string 607 and the casing used in the field measurement;

[0043] In this embodiment, the completion string 607 uses a screen pipe to simulate the screen pipe completion method. Preferably, the screen pipe in the experiment uses the screen pipe actually used on site, and the screen pipe is distributed with gaps; the downhole optical cable 611 passes through the inlet gate valve 615 and enters the flow channel of the full-scale string simulation system;

[0044] The length of the completion string 607 is not less than the spatial resolution of the DAS demodulator;

[0045] The gas injection pipeline 608 provides an inflow channel for gas to enter the full-scale tubing simulation system; the gas enters the flow divider 613 after passing through the gas injection pipeline 608, and enters the flow annulus 612 after the flow is evenly distributed by the flow divider 613, filling the surroundings of the completion string 607, and flows into the completion string 607 from all holes or gaps on the completion string 607 under the pressure difference between the inside and outside of the completion string 607, and then acts on the downhole optical cable 611, simulating the actual process of gas entering the wellbore from the reservoir, thereby avoiding the gas from directly acting on the downhole optical cable 611 after passing through the gas injection pipeline 608;

[0046] The inlet high-pressure rubber hose 605 and the outlet high-pressure rubber hose 610 are high-pressure and high-temperature resistant rubber hoses made of the same material, and their function is to reduce the influence of the end effect generated when the gas enters and flows out of the flow channel in the full-size string simulation system; the end effect refers to the vibration effect caused by the closing or throttling of the gate valve when the gas passes through the inlet gate valve 615 and the outlet gate valve 614, which will interfere with the vibration signal collected by the DAS demodulator, and in severe cases, will annihilate the useful vibration signal generated when the gas flows through the completion string 607 and the flow steel pipe 609;

[0047] The gas injection system includes a high-pressure air pump 601, a heater 602, and an injected gas temperature, pressure, and flow integrated sensor 603, which are arranged in sequence. The high-pressure air pump 601 is connected to the heater 602 through an air pump outlet pipeline 701. One end of the injected gas temperature, pressure, and flow integrated sensor 603 is connected to the heater 602 through the heating outlet pipeline 702, and the other end is connected to the gas injection pipeline 608 through the inlet injection pipeline 703.

[0048] The high-pressure gas pump 601 can provide high-pressure gas of different pressures by adjusting the pressure valve thereon; the high-pressure gas from the high-pressure gas pump 601 first enters the heater 602 through the gas pump outlet pipeline 701 to be heated to different temperatures, and then flows through the injection gas temperature, pressure and flow integrated sensor 603 through the heating outlet pipeline 702 to measure the corresponding temperature, pressure and flow, and then flows into the gas injection pipeline 608 through the inlet injection pipeline 703, enters the flow annulus 612 after the flow is evenly distributed by the diverter 613, and finally flows through the completion string 607 to enter the flow channel of the full-scale string simulation system; the DAS-DTS demodulator 604 measures the temperature and acoustic wave signals of the high-temperature and high-pressure gas flowing through the completion string 607 and the flow steel pipe 609 through the downhole optical cable 611;

[0049] The temperature and pressure sensor P1 inside the completion string 607 is arranged inside the completion string 607 to monitor the temperature and pressure data of the gas after it flows into the completion string 607; the temperature and pressure sensor P2 outside the completion string 607 is arranged in the flow annulus 612 outside the completion string 607 to monitor the temperature and pressure data of the gas before it flows into the completion string 607; the temperature and pressure sensor array, hereinafter referred to as the temperature and pressure array, is arranged in the flow steel pipe 609 to monitor the temperature and pressure data of the gas along the flow steel pipe 609 toward the high-pressure rubber hose 610 at the outlet end after the gas enters the completion string 607; the temperature and pressure array is composed of the first temperature and pressure sensor R1 and the nth temperature and pressure sensor Rn arranged at equal intervals; the nth temperature and pressure sensor Rn can be the second, third, tenth, or any number of them, but at least the second; the distance between two adjacent temperature and pressure sensors in the temperature and pressure array is not less than the spatial resolution of the DAS demodulator; the spatial resolution refers to the size or size of the smallest unit that the instrument can distinguish in detail. Spatial resolution is one of the most important performance indicators of OFDR technology, which determines the positioning accuracy of the system and the distribution density of the measurement points. For example, if the spatial resolution of DAS is 2 meters, the distance between adjacent temperature and pressure sensors must not be less than 2 meters.

[0050] The gas well production optical fiber monitoring simulation experiment system of the present invention can truly simulate the on-site gas well environment and is used to accurately predict the gas production of the gas well.

[0051] Embodiment 2

[0052] The present embodiment is the second embodiment of a gas well production optical fiber monitoring simulation experiment system. The present embodiment is similar to the first embodiment, except that the completion string 607 uses a perforated pipe to simulate the perforated pipe completion method. The material and size of the perforated pipe are the same as those of the perforated pipe actually used on site. The perforated pipe is distributed with holes. The gas enters the diverter 613 after passing through the gas injection pipeline 608, and enters the flow annulus 612 after the flow is evenly distributed by the diverter 613, filling the completion string 607. Under the action of the pressure difference between the inside and outside of the completion string 607, the gas flows into the completion string 607 from all the holes or gaps on the completion string 607, and then acts on the downhole optical cable 611, simulating the actual process of gas entering the wellbore from the reservoir, thereby avoiding the gas directly acting on the downhole optical cable 611 after passing through the injection hole.

[0053] Embodiment 3

[0054] This embodiment is a second embodiment of a gas well production optical fiber monitoring simulation experimental system. This embodiment is similar to the first embodiment, except that the completion string 607 is omitted to simulate the situation of open hole completion.

[0055] There is no completion string 607 to simulate the open hole completion situation. The gas entering from the gas injection pipe 608 on the steel pipe 606 enters the flow annulus 612 after the flow is evenly distributed by the diverter 613, and then acts on the downhole optical cable 611; the high-pressure rubber hose 605 at the inlet end is connected to the steel pipe 606 through a sealing connector, one end of the flow steel pipe 609 is connected to the steel pipe 606 through a sealing connector, and the other end of the flow steel pipe 609 is connected to the high-pressure rubber hose 610 at the outlet end.

[0056] Embodiment 4

[0057] This embodiment is an embodiment of a method for calculating gas production contribution rate, which is applied to the above-mentioned gas well production optical fiber monitoring simulation experiment system. Figure 2 As shown, the specific steps include:

[0058] S1: Conduct gas flow monitoring experiment using the gas well production optical fiber monitoring simulation experimental system;

[0059] Conduct a full-scale pipe gas flow DTS / DAS monitoring experiment to obtain the temperature and acoustic response signals of the gas flowing in the pipeline, including the following steps:

[0060] S11: According to the completion string 607 and casing used on site, the downhole optical cable 611 and the DAS-DTS demodulator 604 used Figure 1 As shown in the figure, a full-scale gas well production optical fiber monitoring simulation experimental system is built;

[0061] S12: Conduct gas flow DAS-DTS monitoring experiments at different gas flow rates, pressures and temperatures on the experimental system, and use the downhole optical cables 611611 to collect the temperature and acoustic wave response of the gas flowing through the completion string 607 and the flow steel pipe 609 in real time during the experiments at different gas flow rates, pressures and temperatures. At the same time, use the temperature and pressure data of the corresponding positions of the temperature and pressure sensors P1 inside the completion string 607, the temperature and pressure sensors P2 outside the completion string 607, and the temperature and pressure data of each temperature and pressure sensor in the temperature and pressure array D. In order to ensure the data sample size, there are no less than 300 experimental combination schemes with different gas flow rates, pressures and temperatures, and the experimental duration of each experimental scheme is no less than 10 seconds.

[0062] S2: Extract experimental temperature features and experimental acoustic wave features in the experiment;

[0063] Extracting temperature and acoustic wave characteristics from the experimental data, extracting acoustic wave characteristic signals and temperature characteristic signals related to flow and flow rate generated when the gas flows through the completion string 607 and in the flow steel pipe 609 from the temperature and acoustic wave response signals of the gas flowing in the pipeline obtained from the full-scale pipe string gas flow DTS / DAS monitoring experiment, and forming a data set, including the steps of:

[0064] S21: For each set of experimental data, all acoustic wave response signals A1 of the gas flowing through the completion string 607 and entering the flow channel within the duration of the experiment are extracted at the completion string 607, and the extracted acoustic wave response signal SA1 is subjected to noise reduction processing by using the median filtering method, and the spectrum is analyzed by using the modern signal analysis method to extract the frequency band energy feature SA(1,1), the root mean square feature SA(1,2), the low variance scattering feature SA(1,3), and the short-time frequency feature SA(1,4) of the response signal;

[0065] S22: for each set of experimental data, extract all temperature response signals ST1 of the gas flowing through the completion string 607 and entering the flow channel within the duration of the experiment at the completion string 607, process the extracted temperature response signals ST1, and calculate the average change rate characteristic of the temperature over time within the duration of the experiment STTA(1,1); the average change rate characteristic over time refers to calculating the temperature change rate within adjacent time for the temperature data extracted within the duration of the experiment, and then calculating the average change rate using the arithmetic mean method;

[0066] S23: For each group of experimental data, all acoustic wave response signals SR1, ..., SRn corresponding to the positions of the temperature and pressure sensors in the temperature and pressure array D are extracted, and the extracted acoustic wave response signals SR1, ..., SRn are subjected to noise reduction processing by using the median filtering method. The spectrum is analyzed by using the modern signal analysis method to extract the frequency band energy characteristics SAR1(1,1), ..., SARn(1,1), the root mean square characteristics SAR1(1,2), ..., SARn(1,2), the low variance scattering characteristics SAR1(1,3), ..., SARn(1,3), and the short-time time-frequency characteristics SAR1(1,4), ..., SARn(1,4) of the response signals;

[0067] S24: For each set of experimental data, all temperature response signals STR1, ..., STRn corresponding to the positions of the temperature and pressure sensors in the temperature and pressure array D are extracted respectively, and the extracted temperature response signals STR1, ..., STRn are processed to calculate the average spatial change rate characteristics STTAR1(1,1), ..., STTAR1(1,n) of the temperature at each temperature and pressure sensor within the experimental duration, and the average spatial change rate characteristics STTAPR1(1,1), ..., STTAPR1(1,n) of the pressure at each temperature and pressure sensor within the experimental duration; the average spatial change rate characteristics refer to taking the arithmetic average of the temperature and pressure data extracted within the experimental duration, and then dividing by the distance between two adjacent temperature and pressure sensors to calculate the average change rate;

[0068] S25: For each set of experimental data, extract the temperature data P1T and P2T and the pressure data P1P and P2P of the temperature and pressure sensor P1 inside the completion string 607 and the temperature and pressure sensor P2 outside the completion string 607 within the duration of the experiment, calculate the average values ​​AP1T, AP2T, AP1P and AP2P of each temperature and pressure parameter, and then calculate the temperature-pressure coefficient PT(1) using formula (E1);

[0069]

[0070] S3: Establish a model for automatic identification of production layers and calculation of layer gas production contribution rate, and input the experimental temperature characteristics and experimental acoustic wave characteristics into the model for training;

[0071] The model is a machine learning model, which can be a BP neural network, random forest, decision tree, convolutional neural network, or other models;

[0072] The establishment of the production layer automatic identification model includes the following steps:

[0073] S31: The acoustic wave and temperature features extracted from each experimental scheme are combined into several data sets. The first data set D(1,1) of the first experimental scheme is {SA(1,1), SA(1,2), SA(1,3), SA(1,4), STTA(1,1), PT(1)}, the second data set D(1,2) is {SAR1(1,1), SAR1(1,2), SAR1(1,3), SAR1(1,4), STTAR1(1,1), STTAPR1(1,1)}..., the n+1th data set D(1,n+1) is {SARn(1,1), SARn(1,2), SARn(1,3), SARn(1,4), STTAR1(1,1), STTAPR1(1,1)}. n), STTAPR1(1,n)}; the first data set D(n,1) of the nth experimental scheme is {SA(n,1), SA(n,2), SA(n,3), SA(n,4), STTA(n,1), PT(n)}, the second data set D(n,2) is {SAR1(n,1), SAR1(n,2), SAR1(n,3), SAR1(n,4), STTAR1(n,1), STTAPR1(n,1)}, ..., the n+1th data set D(n,n+1) is {SARn(n,1), SARn(n,2), SARn(n,3), SARn(n,4), STTAR1(n,n), STTAPR1(n,n)};

[0074] S32: The first data set of each experimental scheme is marked as 1, representing the gas-producing layer; the second data set ... the n+1th data set are all marked as 0, representing the non-gas-producing layer;

[0075] S33: The first data set of each experimental scheme is randomly sampled and divided into a training set sample TR1 and a test set sample TS1 according to a ratio of 8:2; the data sets other than the first data set of each experimental scheme are randomly sampled and divided into a training set sample TR2 and a test set sample TS2 according to a ratio of 8:2, TR1 and TR2 are used as the total training set samples, and TS1 and TS2 are used as the total test set samples;

[0076] S34: taking the total training set samples, the total test set samples and the labels corresponding to each data set in the samples as machine learning model parameters, and bringing them into the machine learning model for training and verification, so as to obtain a production layer segment automatic identification model;

[0077] The steps of establishing the gas production contribution rate model include:

[0078] S35: The acoustic wave and temperature features extracted from each experimental scheme are combined into a data set. The first data set DQ(1) of the first experimental scheme is {SA(1,1), SA(1,2), SA(1,3), SA(1,4), STTA(1,1), PT(1), SAR1(1,1), SAR1(1,2), SAR1(1,3), SAR1(1,4), STTAR1(1,1), STTAPR1(1,1), …, SARn(1,1), SARn(1,2), SARn(1,3), SARn(1,4), STTAR1(1,n) ,STTAPR1(1,n)}; The first data set DQ(n) of the nth experimental scheme is {SA(n,1), SA(n,2), SA(n,3), SA(n,4), STTA(n,1), PT(n), SAR1(n,1), SAR1(n,2), SAR1(n,3), SAR1(n,4), STTAR1(n,1), STTAPR1(n,1), …, SARn(n,1), SARn(n,2), SARn(n,3), SARn(n,4), STTAR1(n,n), STTAPR1(n,n)};

[0079] S36: normalize the flow rates of all experimental schemes using formula (E2), and use the calculated result as the flow rate label of the experimental scheme;

[0080]

[0081] Among them, R normis the normalized gas flow rate; R is the flow rate for each experimental scheme; R max is the maximum flow rate in all experimental schemes.

[0082] S37: All data sets of the above experimental schemes are randomly sampled and divided into training set samples TRQ and test set samples TSQ in a ratio of 8:2;

[0083] S38: The TRQ of the training set sample, the TSQ of the test set sample and the flow labels corresponding to each data set in the sample are taken as machine learning model parameters, and brought into the machine learning model for training and verification to obtain a layer gas production contribution rate model; the machine learning model is a Ridge regression model;

[0084] S4: Extract the measured temperature characteristics and measured acoustic wave characteristics from the field measured data, and input them into the model for evaluation and calculation to obtain the gas production location and gas production contribution rate.

[0085] S41: Depth correction of DAS and DTS measured data;

[0086] S42: dividing the DAS and DTS measured data after depth correction into a plurality of data segments along the wellbore with the spatial resolution of the DAS demodulator as the length interval;

[0087] S43: Processing the data segments divided in step S42 according to the temperature and acoustic wave feature extraction method in the production layer automatic identification and layer gas production contribution rate machine learning model to extract the temperature and acoustic wave features of each data segment;

[0088] S44: The temperature and acoustic wave characteristics of each data segment extracted in step S43 are brought into the production layer segment automatic identification model and the layer segment gas production contribution rate model established by the production layer segment automatic identification and layer segment gas production contribution rate machine learning model. By calculating the corresponding actual temperature and pressure coefficients and actual flow labels, the gas production contribution rates of the gas-producing layer and non-gas-producing layer and each gas-producing layer can be finally obtained.

[0089] In the gas well production optical fiber monitoring simulation experiment system of this embodiment, the completion string 607 involved can be a screen tube to simulate the screen tube completion method, or a perforated tube to simulate the perforated tube completion method, or there can be no completion string 607 to simulate the open hole completion.

[0090] In the specific contents of the above-mentioned specific implementation methods, the various technical features can be combined in any non-contradictory manner. In order to make the description concise, not all possible combinations of the above-mentioned technical features are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0091] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the embodiments here. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the claims of the present invention.

Claims

1. A gas well production optical fiber monitoring simulation experimental system, characterized in that: include A full-scale string simulation system, used to simulate the process of gas entering the wellbore from the reservoir and flowing in the wellbore under different completion methods, and provided with a gas injection pipeline (608); A gas injection system, used to inject gases of different pressures and / or temperatures into the full-scale string simulation system, connected to the gas injection pipeline (608) via an inlet injection line (703); The optical fiber monitoring system is used to obtain the temperature characteristics and acoustic wave characteristics of the gas in the full-scale tubing simulation system at different gas flow rates, different pressures and different temperatures, and form a data set, which is connected to the full-scale tubing simulation system through a downhole optical cable (611).

2. The gas well production optical fiber monitoring simulation experimental system according to claim 1 is characterized in that: The full-scale tubular string simulation system comprises an inlet high-pressure rubber hose (605), a completion tubular string (607), a flow steel pipe (609), and an outlet high-pressure rubber hose (610) which are connected in sequence. The end of the inlet high-pressure rubber hose (605) is provided with an inlet gate valve (615), and the end of the outlet high-pressure rubber hose (610) is provided with an outlet gate valve (614). The completion tubular string (607) is covered with a steel pipe (606). Both ends of the steel pipe (606) are sealed with the outer wall of the completion tubular string through a seal. The gas injection pipeline (608) is connected to the gas injection pipeline (608). The side of the steel pipe (606) is connected, and the downhole optical cable (611) sequentially passes through the inlet gate valve (615), the inlet high-pressure rubber hose (605), the completion string (607), the flow steel pipe (609), and the outlet high-pressure rubber hose (610). An internal temperature and pressure sensor P1 is provided in the completion string (607), and an external temperature and pressure sensor P2 is provided outside the completion string (607) and located in the steel pipe (606). A plurality of temperature and pressure sensors are sequentially provided along the length direction of the flow steel pipe (609) to form a temperature and pressure sensor array.

3. The gas well production optical fiber monitoring simulation experimental system according to claim 2 is characterized in that: A flow diverter (613) is provided inside the steel pipe (606) and between the steel pipe (606) and the completion string (607). The end of the gas injection pipeline (608) abuts against the flow diverter (613), forming a flow annulus (612) between the flow diverter (613) and the completion string (607).

4. The gas well production optical fiber monitoring simulation experimental system according to claim 2 is characterized in that: The completion string (607) is located in the middle of the steel pipe (606).

5. The gas well production optical fiber monitoring simulation experimental system according to claim 2 is characterized in that: The length of the completion string (607) is equal to the length of the steel pipe (606).

6. The gas well production optical fiber monitoring simulation experimental system according to any one of claims 2 to 5, characterized in that: The inner diameters of the inlet high-pressure rubber hose (605), the completion string (607), the flow steel pipe (609), and the outlet high-pressure rubber hose (610) are all equal.

7. The gas well production optical fiber monitoring simulation experimental system according to claim 1 is characterized in that: The gas injection system comprises a high-pressure air pump (601), a heater (602), and an injection gas temperature, pressure and flow integrated sensor (603) which are arranged in sequence. The high-pressure air pump (601) is connected to the heater (602) via an air pump outlet pipeline (701); one end of the injection gas temperature, pressure and flow integrated sensor (603) is connected to the heater (602) via a heating outlet pipeline (702), and the other end is connected to the gas injection pipeline (608) via the inlet injection pipeline (703).

8. The gas well production optical fiber monitoring simulation experimental system according to claim 2 is characterized in that: The completion string (607) is a screen tube or a perforated tube.

9. A method for calculating gas production contribution rate, characterized in that: The gas well production optical fiber monitoring simulation experiment system as claimed in any one of claims 1 to 7 specifically comprises the following steps: S1: Conduct gas flow monitoring experiment using the gas well production optical fiber monitoring simulation experimental system; S2: extracting experimental temperature characteristics and experimental sound wave characteristics in the experiment; S3: Establishing a production layer automatic identification and layer gas production contribution rate calculation model, and inputting the experimental temperature characteristics and experimental acoustic wave characteristics into the model for training; S4: Extract the measured temperature characteristics and measured acoustic wave characteristics from the field measured data, and input them into the model for evaluation and calculation to obtain the gas production location and gas production contribution rate.

10. The method for calculating gas production contribution rate according to claim 9, characterized in that: When conducting gas flow monitoring experiments, there are no less than 300 experimental combination schemes with different gas flow rates, different pressures, and different temperatures, and the experimental duration of each experimental scheme is no less than 10 seconds.

Images