Method and device for detecting gas well annulus and storage medium

Abstract

The embodiment of the invention provides a gas well annulus detection method and device and a storage medium, and the method comprises the steps: obtaining the annulus pressure of a to-be-detected gas well, and determining an annulus pressure curve according to the annulus pressure; the annulus pressure curve is substituted into an annulus pressure curve prediction model, whether the gas well to be detected leaks or not is determined, if the gas well to be detected leaks, basic parameters of the gas well to be detected are obtained, the basic parameters are substituted into an annulus leakage prediction model, and leakage point parameters of the gas well to be detected are determined. The method can accurately detect the gas well annulus leakage point.

Description

Technical Field

[0001] The invention relates to the field of oil and gas field well development, and in particular to a method, a device and a storage medium for detecting the annulus of a gas well. Background Art

[0002] As the gas production period is extended, some corrosive media corrode gas wells, causing gas well string leakage, packer failure and other faults. Determining the location of the leak, the size of the leak rate and the gas composition is of great significance for evaluating the abnormal annular pressure. In order to meet the evaluation standards, the existing technology mainly uses sonic logging equipment and skid-mounted integral detection devices to detect annular pressure, temperature and leaks. Each time the existing equipment is installed, it needs to be modified according to different on-site conditions, and the construction process is cumbersome and complicated. Moreover, for the detection of high-pressure gas wells, the detection setting is in a high-pressure state for a long time, which makes close-range detection work have certain safety hazards. Summary of the invention

[0003] The purpose of the embodiments of the present invention is to provide a method, device and storage medium for detecting the annulus of a gas well, wherein the method can accurately detect the leakage point of the annulus of the gas well.

[0004] In order to achieve the above-mentioned purpose, an embodiment of the present invention provides a method for detecting the annulus of a gas well, the method comprising: obtaining the annulus pressure of the gas well to be tested, and determining an annulus pressure curve according to the annulus pressure; bringing the annulus pressure curve into an annulus pressure curve prediction model to determine whether the gas well to be tested is leaking; if the gas well to be tested is leaking, obtaining basic parameters of the gas well to be tested, bringing the basic parameters into an annulus leakage prediction model to determine the leakage point parameters of the gas well to be tested.

[0005] Optionally, the annular pressure curve prediction model is obtained through the following process:

[0006] Determine the annular pressure curve according to the type of annular pressure;

[0007] Establishing a database according to the annular pressure curve;

[0008] The database is standardized and denoised, and a convolutional neural network is used to train the database to obtain an annular pressure curve prediction model.

[0009] Optionally, the annulus pressure curve prediction model is used to determine whether the gas well to be tested is leaking according to the changing trend of the annulus pressure curve, wherein if the annulus pressure curve shows an upward trend after decreasing for a period of time, it is determined that the gas well to be tested is leaking.

[0010] Optionally, the step of bringing the basic parameters into an annulus leakage prediction model to determine the leakage point parameters of the gas well to be tested includes:

[0011] Bringing the basic parameters into the annulus leakage prediction model;

[0012] Dividing the annular space leakage prediction model into time and space grids to establish nodes of the tubing, casing, fluid in the tubing, and fluid in the annular space;

[0013] Determine initial conditions and boundary conditions, and determine the pressure, density and boundary node temperature of the fluid at each node in the oil pipe according to the basic parameters;

[0014] Determine the leakage depth and the annular pressure at the leakage point according to the pressure, density and boundary node temperature of the fluid at each node in the oil pipe;

[0015] The flow rate at the leakage point is determined according to the leakage depth and the annular pressure at the leakage point.

[0016] Optionally, the basic parameters are at least one of wellbore structure parameters, thermodynamic parameters, gas physical property parameters, annulus pressure relief / recovery data, wellhead pressure, wellhead temperature, annulus wellhead pressure, annulus wellhead temperature, liquid level depth and annulus leakage rate.

[0017] In another aspect, the present invention provides a device for detecting annulus of a gas well, the device comprising:

[0018] An acquisition module is used to acquire the annular pressure of the gas well to be tested and determine the annular pressure curve according to the annular pressure;

[0019] The processing module is used to bring the annulus pressure curve into the annulus pressure curve prediction model to determine whether the gas well to be tested is leaking. If the gas well to be tested is leaking, the basic parameters of the gas well to be tested are obtained, and the basic parameters are brought into the annulus leakage prediction model to determine the leakage point parameters of the gas well to be tested.

[0020] Optionally, an annular pressure curve is determined according to the category of annular pressure;

[0021] Establishing a database according to the annular pressure curve;

[0022] The database is standardized and denoised, and a convolutional neural network is used to train the database to obtain an annular pressure curve prediction model.

[0023] Optionally, the annulus pressure curve prediction model is used to determine whether the gas well to be tested is leaking according to the changing trend of the annulus pressure curve, wherein if the annulus pressure curve shows an upward trend after decreasing for a period of time, it is determined that the gas well to be tested is leaking.

[0024] Optionally, the step of bringing the basic parameters into an annulus leakage prediction model to determine the leakage point parameters of the gas well to be tested includes:

[0025] Bringing the basic parameters into the annulus leakage prediction model;

[0026] Dividing the annular space leakage prediction model into time and space grids to establish nodes of the tubing, casing, fluid in the tubing, and fluid in the annular space;

[0027] Determine initial conditions and boundary conditions, and determine the pressure, density and boundary node temperature of the fluid at each node in the oil pipe according to the basic parameters;

[0028] Determine the leakage depth and the annular pressure at the leakage point according to the pressure, density and boundary node temperature of the fluid at each node in the oil pipe;

[0029] The flow rate at the leakage point is determined according to the leakage depth and the annular pressure at the leakage point.

[0030] In another aspect, the present invention provides an electronic device, comprising:

[0031] at least one processor;

[0032] a memory connected to the at least one processor;

[0033] The memory stores instructions that can be executed by the at least one processor, and the at least one processor implements the above-mentioned method for detecting the annulus of a gas well by executing the instructions stored in the memory.

[0034] On the other hand, the present invention provides a machine-readable storage medium storing machine instructions. When the machine instructions are executed on a machine, the machine executes the above-mentioned method for detecting the annulus of a gas well.

[0035] A method for detecting the annulus of a gas well of the present invention comprises: obtaining the annulus pressure of the gas well to be tested, and determining the annulus pressure curve according to the annulus pressure; bringing the annulus pressure curve into the annulus pressure curve prediction model to determine whether the gas well to be tested is leaking, and if the gas well to be tested is leaking, obtaining the basic parameters of the gas well to be tested, bringing the basic parameters into the annulus leakage prediction model to determine the leakage point parameters of the gas well to be tested. The method automatically identifies the annulus pressure curve, eliminates the influence of subjective factors, and calculates the leakage point parameters of the completion string according to the detection data, and quantifies the leakage degree. And through year-by-year comparative detection, the leakage point of the gas well annulus can be accurately detected.

[0036] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings:

[0038] Figure 1 It is a schematic flow chart of a method for detecting annulus of a gas well according to the present invention;

[0039] Figure 2 is a schematic diagram of an annular pressure curve of the present invention;

[0040] Figure 3 It is a schematic diagram of the flow of annular pressure curve identification of the present invention;

[0041] Figure 4 It is a schematic flow diagram of the annular pressure curve prediction model of the present invention;

[0042] Figure 5 It is a schematic diagram of an embodiment of a device for detecting annulus of a gas well according to the present invention.

[0043] Description of Reference Numerals

[0044] 1- Temperature and pressure detection model;

[0045] 2- Leakage and flow detection module;

[0046] 3- Gas component detection module;

[0047] 11-first pipe section; 12-temperature transmitter;

[0048] 13-pressure transmitter; 14-first stop valve;

[0049] 15-needle valve; 16-first heating unit;

[0050] 17-gas-liquid separator;

[0051] 21- second pipe section; 22- third pipe section;

[0052] 23-first pressure gauge; 24-flow meter;

[0053] 25-first throttle valve; 26-second throttle valve;

[0054] 27- second stop valve; 28- fourth pipe section;

[0055] 29-third stop valve; 30-fifth pipe section;

[0056] 31- fourth stop valve; 32- one-way valve;

[0057] 33-Hydrogen sulfide detector; 34-Carbon dioxide detector;

[0058] 35-alkane detector; 36-fifth stop valve;

[0059] 37-seventh pipe section; 38-second heating unit;

[0060] 39- second pressure gauge;

[0061] 40-pressure reducing valve; 41-third pressure gauge;

[0062] 42-Desiccant. DETAILED DESCRIPTION

[0063] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present invention, and is not used to limit the embodiment of the present invention.

[0064] Figure 1 Schematic diagram of a method for detecting annular space of a gas well according to the present invention. Figure 1 As shown, a method for detecting the annulus of a gas well of the present invention comprises: step S101 is to obtain the annulus pressure of the gas well to be tested, and determine the annulus pressure curve according to the annulus pressure. The annulus pressure is the casing pressure, that is, the casing annulus pressure. Preferably, the present application obtains the annulus pressure by detecting a pressure sensor. The annulus pressure curve is determined by obtaining multiple data of the annulus pressure within a certain period of time, and the annulus pressure curve is used to represent the change trend of the annulus pressure within a certain period of time.

[0065] Step S102 is to bring the annular pressure curve into the annular pressure curve prediction model to determine whether the gas well to be tested is leaking. If the gas well to be tested is leaking, the basic parameters of the gas well to be tested are obtained, and the basic parameters of the ring are brought into the annular leakage prediction model to determine the leakage point parameters of the gas well to be tested. The basic parameters are at least one of wellbore structure parameters, thermodynamic parameters, gas physical property parameters, annular pressure relief\recovery data, wellhead pressure, wellhead temperature, annular wellhead pressure, annular wellhead temperature, liquid level depth and annular leakage rate.

[0066] According to a specific implementation, the annular pressure curve prediction model is obtained through the following process: determining the annular pressure curve according to the type of annular pressure; establishing a database according to the annular pressure curve; standardizing and denoising the database, and training the database using a convolutional neural network to obtain the annular pressure curve prediction model. Specifically, the annular pressure types include continuous annular pressure, thermal effect annular pressure, and physical effect annular pressure.

[0067] The annular pressure curve prediction model is used to determine whether the gas well to be tested is leaking according to the change trend of the annular pressure curve, wherein, if the annular pressure curve shows an upward trend after falling for a period of time, it is determined that the gas well to be tested is leaking. The thermal effect annular pressure and the physical effect annular pressure are annular pressures due to production conditions or artificially applied. Once they are released, they will not be generated autonomously. Therefore, the annular pressure curves (annular pressure relief\recovery curves) of the thermal effect annular pressure and the physical effect annular pressure will show a trend of falling to a stable state in the end.

[0068] The sustained annular pressure is the pressure generated by the fluid from the production layer or bottom layer entering the annular space due to the damage of the well barrier. After the sustained annular pressure is released, the annular space will continue to recover and rise due to the leakage channel caused by the damaged barrier. Different degrees of barrier damage will affect the degree of pressure recovery.

[0069] If the annulus pressure type is thermal effect annulus pressure or physical effect annulus pressure, the gas well to be tested has no leakage; if the annulus pressure type is continuous annulus pressure, the gas well to be tested has leakage.

[0070] Figure 2 It is a schematic diagram of an annular pressure curve of the present invention, such as Figure 2 As shown, if the annular pressure curve is curve 1, the annular pressure type is thermal effect annular pressure and physical effect annular pressure, and the gas well to be tested has no leakage. If the annular pressure curve is curve 2 or 3, the annular pressure type is continuous annular pressure, the gas well to be tested has leakage, and the barrier damage degrees of curves 2 and 3 are different.

[0071] Specifically, when the annulus pressure curve does not rebound in 24 hours, the annulus pressure is the annulus pressure caused by the physical effect of the wellbore, which is represented by curve 1; when the pressure rebounds, but the trend is slow and finally stabilizes at a certain allowable value, it means that there is a slight leakage in the oil pipe or the packer, which is represented by curve 2; when the pressure does not rise or rises slightly after pressure relief, the annulus pressure is caused by the physical effect, which is represented by curve 3.

[0072] Figure 3 It is a schematic diagram of the flow of annular pressure curve identification of the present invention, such as Figure 3 As shown, the steps of the annular pressure curve prediction model include: Step 1 is to establish a database according to the annular pressure curve, and divide the annular pressure curve data according to different categories. Among them, the abscissa of the annular pressure curve is time (s), and the ordinate is pressure (MPa).

[0073] Step 2 is to standardize and reduce noise on the database, specifically to pre-process the annular pressure curve. The annular pressure curve is subjected to noise reduction by a one-dimensional Gaussian filter; the annular pressure curve is standardized based on a standardized processing method, and the pressure data is converted to the [0,1] interval.

[0074] Step 3 is to use a convolutional neural network to train the database to obtain an annular pressure curve prediction model. Specifically, the annular pressure curve is input into the annular pressure curve database, the loss function is calculated through the convolutional neural network model, and the weight parameters in each convolution layer are updated by back propagation of the loss function, and repeated training can be performed multiple times. Preferably, small batches of data are input into the annular pressure curve database, for example, 16 annular pressure curve samples are input at a time, and their average loss function is calculated. The convolutional neural network model includes an input layer, a feature extraction layer, and an output layer.

[0075] Preferably, the feature extraction layer includes three convolutional layers, and the output layer includes two fully connected layers and one output layer, such as Figure 4 As shown. The input data of the input layer is the annular pressure curve, and the data dimension is 200×200×3. The feature extraction layer consists of 3 groups of convolutional layers, each of which contains a convolution operation layer, a pooling layer and an activation function layer. The convolution kernel size of the first convolutional layer is 5×5, the number of channels is 3, and the step size is 2. The pooling layer adopts the maximum max-pooling method (maximum pooling), the size is 3×3, the step size is 2, and it contains 1 Leaky-ReLU activation function layer; the convolution kernel size of the second convolutional layer is 5×5, the number of channels is 3, and the step size is 2. The pooling layer adopts the maximum max-pooling method, the size is 3×3, the step size is 2, and it contains 1 Leaky-ReLU activation function layer; the convolution kernel size of the third convolutional layer is 5×5, the number of channels is 3, and the step size is 2. The pooling layer adopts the maximum max-pooling method, the size is 3×3, the step size is 2, and it contains 1 Leaky-ReLU activation function layer. The output layer consists of a fully connected layer and a Softmax layer (normalized exponential function). The forward propagation framework of the convolutional neural network model includes three convolutional layers, two fully connected layers and an output layer. The size of the first fully connected layer is 128, and the size of the second fully connected layer is 32. The output layer and the fully connected layer can be connected using the Softmax activation function, and the final result is the probability distribution of the input curve belonging to curves 1, 2, and 3. The loss function is to compare the output result of the network with the true label, calculate the value of the loss function, and measure the error degree of the network output.

[0076] The weight update refers to starting from the loss function, calculating the gradient (derivative) of each layer according to the chain rule, propagating the gradient from the output layer to the input layer, and using an optimization algorithm (such as the gradient descent method) to update the weights in the network based on the gradient information obtained by back propagation. This model uses the stochastic gradient descent method to update the weights, and the learning rate is 0.001.

[0077] Step 4 is to use the trained convolutional neural network to automatically identify the annular pressure curve. Different annular pressure curves are calculated by the convolutional neural network and the output results are 1, 2 and 3. Among them, 0 represents curve 1, 1 represents curve 2, and 2 represents curve 3. Finally, it is judged whether the gas well to be tested has leakage according to the change trend of the curve.

[0078] The method of bringing the basic parameters into the annulus leakage prediction model to determine the leakage point parameters of the gas well to be tested includes: bringing the basic parameters into the annulus leakage prediction model; dividing the annulus leakage prediction model into time and space grids to establish nodes of the oil pipe, casing, fluid in the oil pipe, and fluid in the annulus; determining initial conditions and boundary conditions, and determining the pressure, density and boundary node temperature of the fluid at each node in the oil pipe according to the basic parameters; determining the leakage depth and the annulus pressure at the leakage point according to the pressure, density and boundary node temperature of the fluid at each node in the oil pipe; and determining the leakage point flow rate according to the leakage depth and the annulus pressure at the leakage point.

[0079] According to a specific implementation, the annulus leakage prediction model includes a temperature and pressure distribution model, a fluid leakage model and annulus volume change model. Specifically, the temperature and pressure distribution model is mainly determined by the law of conservation of power and energy in the oil pipe.

[0080] The equivalent diameter of the gas leakage point is very small compared to the oil pipe diameter, so the gas leakage rate can be calculated by constructing a small hole model

[0081] The annular volume change model is as follows: Due to the low density of the fluid in the annular space, the leaked gas gathers into a column at the top of the casing-tubing annular space, thereby generating a higher continuous annular pressure. At the same time, the liquid column in the annular space is compressed by the continuous annular pressure. According to the law of conservation of volume, the total volume of the annular gas column and liquid column is equal to the annular volume, as shown in formula (20):

[0082] V an +ΔV in =V ag +V aL +ΔV aL

[0083] Where Van is the initial annulus volume (m 3 ); ΔVan is the change in annular volume (m 3), when the annulus is regarded as a rigid space, ΔVan is zero; Vag is the volume of the annular air column (m 3 ); VaL is the volume of the initial annular liquid column (m 3 );ΔVaL is the change in the volume of the liquid column (m 3 ).

[0084] Leakage is a factor that changes the volume of the annular gas and liquid columns. There is an interactive relationship between the leakage rate, leakage volume and annular pressure. The annular pressure reduces the gas leakage rate and increases the liquid leakage rate. Therefore, the leakage rate is a function of the annular pressure. The fluid leakage volume is the integral of the leakage rate and time.

[0085] Temperature and pressure distribution are key parameters for solving this model. By calculating the pressure and temperature distribution of the wellbore, the average temperature of the annular fluid is obtained, and the temperature and pressure of each leakage point are provided according to the location of the leakage point. Then the leakage process is determined by the three parameters of the leakage point type, liquid level and the tubing and annular pressure at the leakage location, and the continuous annular pressure and liquid level are obtained (continue the process for the next time period until the set time is reached). The above operations can obtain the change law of characteristic parameters, including pressure, annular gas volume, pressure balance point position and liquid level. Therefore, the annular leakage prediction model of this application can be used to analyze the characteristics of relevant parameters under any number and type of leakage points.

[0086] The present invention also provides a device for detecting the annulus of a gas well, comprising: an acquisition module, used to acquire the annulus pressure of the gas well to be tested, and determine the annulus pressure curve according to the annulus pressure; a processing module, used to bring the annulus pressure curve into an annulus pressure curve prediction model to determine whether the gas well to be tested is leaking; if the gas well to be tested is leaking, basic parameters of the gas well to be tested are acquired, the basic parameters are brought into the annulus leakage prediction model, and the leakage point parameters of the gas well to be tested are determined.

[0087] For example, a three-way joint is installed at the wellhead oil layer casing cock, and the three-way joint connection is used to detect the liquid level and pressure and temperature; the outlet end of the pressure and temperature detection module is connected in series with the inlet end of the flow detection module through a high-pressure hose; the outlet end of the flow detection module is connected in series with the inlet end of the gas component detection module through a high-pressure hose. The liquid level monitoring module is used to connect the sonic generator and the three-way joint of the casing cock; the three-way joint is connected to the sonic generator through a high-pressure hose.

[0088] The pressure and temperature detection module includes a gas-liquid separator for separating the gas and liquid of the annulus, a stop valve for closing the pipeline channel, a needle valve for controlling the flow rate, a pressure sensor for detecting the annulus pressure, a temperature sensor for real-time detection of the annulus fluid temperature, a connecting pipeline for connecting the pressure sensor and the temperature sensor, a heater for heating the pipeline, and a signal transmission assembly for transmitting the annulus pressure and temperature signals to a ground remote control computer.

[0089] Figure 5 Schematic diagram of an embodiment of a device for detecting annular space of a gas well according to the present invention, Figure 5 As shown, the device includes a temperature and pressure detection module 1, a leakage and flow detection module 2 and a gas component detection module 3. The temperature and pressure detection module 1, the leakage and flow detection module 2 and the gas component detection module 3 are connected in sequence through a hose. The temperature and pressure detection module 1 includes: a first pipe section 11, a temperature transmitter 12, a pressure transmitter 13, a first stop valve 14, a needle valve 15, a first heating unit 16 and a gas-liquid separator 17. The gas-liquid separator 17, the first stop valve 14, the pressure transmitter 13 and the temperature transmitter 12 are connected to the first pipe section 11 in sequence along the fluid flow direction. The first heating unit 16 is sleeved on the first pipe section 11 between the temperature transmitter 12 and the needle valve 15.

[0090] The flow detection module 2 includes: a second pipe section 21, a third pipe section 22, a fourth pipe section 28, a pressure gauge 23, a flow meter 24, a first throttle valve 25, a second throttle valve 26, a second stop valve 27 and a third stop valve 29. The third pipe section 22 is located on the second pipeline 21, the inlet is the front end of the third stop valve 29, and the outlet is the rear end of the third stop valve 29. The pressure gauge 23, the flow meter 24, the first throttle valve 25 and the second throttle valve 26 are sequentially connected to the third pipe section along the fluid flow direction. The fourth pipe section 28 is located on the third pipe section 22, the inlet is located between the flow meter 24 and the first throttle valve 25, and the outlet is located between the second throttle valve 26 and the outlet of the second pipe section.

[0091] The gas component detection module 3 includes: a fifth pipe section 30, a sixth pipe section, a seventh pipe section 37, a fourth stop valve 31, a one-way valve 32, a hydrogen sulfide detector 33, a carbon dioxide detector 34, a methane detector 35, a fifth stop valve 36, a sixth stop valve, a second heating unit 38, a pressure gauge 39, a pressure reducing valve 40, a pressure gauge 41 and a desiccant 42. The fifth pipe section 30 and the seventh pipe section 37 are connected in parallel to form two passages, the sixth pipe section is located on the seventh pipe section 37; the fourth stop valve 31 is located on the fifth pipe section 30; the desiccant 42, the pressure gauge 41, the pressure reducing valve 40, the pressure gauge 39, the second heating unit 38, the fifth stop valve 36, the methane detector 35, the carbon dioxide detector 34, the hydrogen sulfide detector 33, and the one-way valve 32 are sequentially arranged on the seventh pipe section 37 along the fluid flow direction. The inlet of the seventh pipe section is located between the second heating unit 38 and the fifth stop valve 36, and the outlet is located behind the one-way valve 32; the sixth stop valve is located on the seventh pipe section 37. Among them, the hose, the first pipe section 11, the second pipe section 21, the third pipe section 22, the fourth pipe section 28, the fifth pipe section 30, the sixth pipe section and the seventh pipe section 37 can all withstand the preset pressure and preset temperature, and the diameter of the hose is smaller than the diameter of any pipe section among the first pipe section 11, the second pipe section 21, the third pipe section 22, the fourth pipe section 28, the fifth pipe section 30, the sixth pipe section and the seventh pipe section 37.

[0092] Specifically, the device for detecting the annulus of a gas well is installed on the wellhead Christmas tree, and the outlet of the oil casing annulus is connected to the port of the temperature and pressure detection module 1 close to the temperature transmitter 12, so that the gas discharged from the oil casing annulus can be directly transported to the device.

[0093] The temperature and pressure detection module 1 is used to detect the temperature and pressure of the gas, the leakage and flow detection module 2 is used to detect the flow of the gas and the annular leakage rate, and the gas component detection module 3 is used to detect the components of the gas. In order to perform multiple tests on the gas, it is necessary to change the flow of the gas in the device to form a pressure reduction. The reduction in gas pressure will lead to a decrease in temperature, and the temperature reduction will cause hydrates to be produced in the gas. The formation of the above hydrates will hinder the detection. In order to avoid the occurrence of the above situation, the device is provided with a first heating unit 16 and a second heating unit 38 to compensate for the temperature of the gas.

[0094] Since it is necessary to install various parts on the first pipe section 11, the second pipe section 21, the third pipe section 22, the fourth pipe section 28, the fifth pipe section 30, the sixth pipe section and the seventh pipe section 37, the first pipe section 11, the second pipe section 21, the third pipe section 22, the fourth pipe section 28, the fifth pipe section 30, the sixth pipe section and the seventh pipe section 37 are hard pipe sections with relatively large diameters, and the diameters of the above pipe sections are not less than 0.0127 meters (1 / 2 inches). The hose can withstand the high pressure and high temperature of the gas in the oil casing annulus, but its diameter is relatively small. Preferably, the diameter of the hose is not less than 0.0127 meters (1 / 2 inches), and it is soft and deformable. The presence of the first heating unit 16 and the second heating unit 38 in the device can supplement the heat loss caused by the use of the hose to transport the gas. The hose also has sulfur resistance, thereby avoiding corrosion by sulfur in the gas discharged from the above gas well, and has a relatively high service life.

[0095] The first throttle valve 25 is used to reduce the flow rate of the passing gas, so as to determine the annular space leakage rate, wherein the first throttle valve 25 is a large-range flow adjustment. The second throttle valve 26 is used to reduce the flow rate of the passing gas, accurately adjust the flow rate, and stabilize the pressure area after adjustment, and the second throttle valve 26 is a small-range flow adjustment. The pressure reducing valve 40 is used to reduce the pressure of the passing gas, so as to facilitate the detection of the gas components.

[0096] The present application connects the temperature and pressure detection module 1, the leakage and flow detection module 2 and the gas component detection module 3 in sequence with a hose, and the hose can withstand the high pressure and high temperature of the gas in the oil casing annulus. Due to its small diameter and softness and deformability, the overall volume of the device becomes smaller and the weight becomes lighter. The device is also provided with a heating unit, so that the device can heat the gas in the first pipe section 11 and the third pipe section 31 respectively through the first heating unit 15 and the second heating unit 35 on the basis of being able to complete the temperature, pressure, flow and component measurements, so as to compensate for the temperature loss caused by the decrease in air pressure due to friction energy consumption during the flow of gas in the pipe section and the hose, and avoid the formation of hydrates due to the decrease in temperature of the gas, thereby ensuring the smooth progress of the detection process.

[0097] The hose, the first pipe section 11, the second pipe section 21, the third pipe section 22, the fourth pipe section 28, the fifth pipe section 30, the sixth pipe section and the seventh pipe section 37 can all withstand a preset pressure and a preset temperature, the preset pressure can be 50MPa-60MPa, and the preset temperature can be -10°C-100°C. The temperature and pressure detection module 1 has a first annular space cock 5 between the port close to the temperature transmitter 12 and the oil casing annulus, wherein the cock refers to a small plug-type valve, which is mainly used to open and close the pipeline and equipment medium.

[0098] The temperature and pressure detection module 1 also includes: a needle valve 1; the needle valve 15 is located on the first pipe section 11 downstream of the first stop valve 14, and the flow rate of the gas is changed by changing the opening of the needle valve 15; during the pressure test of the pipeline, the first stop valve 14 can be closed to seal the pipeline upstream of the first stop valve 14, and the pressure in the pipeline can be measured to detect whether the pipeline meets the sealing requirements.

[0099] The leakage rate and flow detection module 2 also includes closing the stop valve 29 and the stop valve 28, and the gas will pass through the pipe section 22 for leakage rate detection. After adjusting the throttle valve 25 and the throttle valve 26, the pressure shown in the pressure gauge 23 no longer changes. At this time, the flow rate recorded by the flow detector 24 is the annular space leakage rate. The leakage rate and flow detection module 2 also includes closing the stop valve 27 and opening the stop valve 29, so that the fluid does not pass through the throttle valve and directly enters the gas quality analysis module 3. The leakage rate and flow detection module 2 also includes closing the stop valve 29 and opening the stop valve 28, so that the fluid does not pass through the throttle valves 25 and 26, and directly detects the pressure relief flow of the annulus.

[0100] The gas component detection module 3 also includes: a pressure reducing valve 40; the pressure reducing valve 40 is located upstream of the methane detector 35, on the pipe section 37. The pressure reducing valve 40 is used to further reduce the pressure of the gas flowing through and adjust the pressure of the gas, so that the pressure of the gas flowing into the methane detector 35, the carbon dioxide detector 34 and the hydrogen sulfide detector 33 meets the detection requirements. The gas component detection module 3 also includes: a pipe section 30 and a blowout pool; after opening the stop valve 31, closing the pressure reducing valve 40 and the stop valve 36, the fluid well pipe section 30 enters the blowout pool. The inlet end of the pipe section 30 is connected to the outlet end of the leakage and flow detection module 2 through a hose, and the outlet end of the pipe section 30 is connected to the annulus cock 6 through a hose. The use of the wellhead pipe section can reduce the amount of hose used in the device, thereby further reducing the volume and weight of the device while ensuring the detection effect, forming an internal circulation blowout. Since the gas is flammable and may contain toxic and harmful components such as sulfur, it needs to be burned before it can be discharged. The blowdown pool is used to ignite the gas and treat the post-burnt substances to avoid direct discharge of the gas, which may pollute the environment or even cause dangerous accidents.

[0101] The fluid can change its flow direction through the stop valve 31 and the stop valve 36. First, close the stop valve 31 to allow the fluid to enter the pipe section 37; after completing the gas component detection, close the stop valve 36 and open the stop valve 31. The device also includes: a data processing module 18; the temperature and pressure detection module 1, the leakage and flow detection module 2, and the gas component detection module 3 respectively send the measured data to the data processing module 18 through the signal transmission unit. Specifically, the data processing module 18 performs a comprehensive analysis after receiving the temperature, pressure, flow and component signals, and then obtains the leakage point location, leakage rate, etc. in the annulus, intelligently determines the annulus pressure type, and provides data for subsequent research on the annulus.

[0102] A method for detecting the annulus of a gas well of the present invention comprises: obtaining the annulus pressure of the gas well to be tested, determining the annulus pressure curve according to the annulus pressure; bringing the annulus pressure curve into the annulus pressure curve prediction model to determine whether the gas well to be tested is leaking, and if the gas well to be tested is leaking, obtaining the basic parameters of the gas well to be tested, bringing the basic parameters into the annulus leakage prediction model to determine the leakage point parameters of the gas well to be tested. The method automatically identifies the annulus pressure curve, eliminates the influence of subjective factors, and calculates the leakage point parameters of the completion string according to the detection data, quantifies the leakage degree, and can accurately detect the leakage point of the gas well annulus through year-by-year comparative detection.

[0103] On the other hand, the present invention also provides an electronic device, which includes: at least one processor; a memory connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the at least one processor implements the above-mentioned method for detecting the annulus of a gas well by executing the instructions stored in the memory.

[0104] The processor includes a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and the leakage point of the gas well annulus can be detected by adjusting the kernel parameters.

[0105] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0106] An embodiment of the present invention provides a storage medium on which a program is stored. When the program is executed by a processor, the method for detecting the annulus of a gas well is implemented.

[0107] An embodiment of the present invention provides a processor, which is used to run a program, wherein the method for detecting the annulus of a gas well is executed when the program is run.

[0108] The embodiment of the present invention provides a device, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, the following steps are implemented: (method claim steps, sole right + subordinate right). The device in this article can be a server, a PC, a PAD, a mobile phone, etc.

[0109] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0110] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0111] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0112] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0113] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0114] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0115] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0116] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0117] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for detecting the annulus of a gas well, characterized in that: The method includes: Obtain the annular pressure of the gas well to be tested, and determine the annular pressure curve according to the annular pressure; The annulus pressure curve is brought into the annulus pressure curve prediction model to determine whether the gas well to be tested is leaking. If the gas well to be tested is leaking, the basic parameters of the gas well to be tested are obtained, and the basic parameters are brought into the annulus leakage prediction model to determine the leakage point parameters of the gas well to be tested.

2. The method according to claim 1, characterized in that The annular pressure curve prediction model is obtained through the following process: Determine the annular pressure curve according to the type of annular pressure; Establishing a database according to the annular pressure curve; The database is standardized and denoised, and a convolutional neural network is used to train the database to obtain an annular pressure curve prediction model.

3. The method according to claim 1, characterized in that The annular pressure curve prediction model is used to determine whether the gas well to be tested is leaking according to the changing trend of the annular pressure curve, wherein if the annular pressure curve shows an upward trend after decreasing for a period of time, it is determined that the gas well to be tested is leaking.

4. The method according to claim 1, characterized in that: The step of bringing the basic parameters into the annulus leakage prediction model to determine the leakage point parameters of the gas well to be tested includes: Bringing the basic parameters into the annulus leakage prediction model; Dividing the annular space leakage prediction model into time and space grids to establish nodes of the tubing, casing, fluid in the tubing, and fluid in the annular space; Determine initial conditions and boundary conditions, and determine the pressure, density and boundary node temperature of the fluid at each node in the oil pipe according to the basic parameters; Determine the leakage depth and the annular pressure at the leakage point according to the pressure and density of the fluid at each node in the oil pipe and the boundary node temperature; The flow rate at the leakage point is determined according to the leakage depth and the annular pressure at the leakage point.

5. The method according to claim 1 or 4, characterized in that: The basic parameters are at least one of wellbore structure parameters, thermodynamic parameters, gas physical property parameters, annulus pressure relief\recovery data, wellhead pressure, wellhead temperature, annulus wellhead pressure, annulus wellhead temperature, liquid level depth and annulus leakage rate.

6. A device for detecting the annulus of a gas well, characterized in that: The device includes: An acquisition module is used to acquire the annular pressure of the gas well to be tested and determine the annular pressure curve according to the annular pressure; The processing module is used to bring the annulus pressure curve into the annulus pressure curve prediction model to determine whether the gas well to be tested is leaking. If the gas well to be tested is leaking, the basic parameters of the gas well to be tested are obtained, and the basic parameters are brought into the annulus leakage prediction model to determine the leakage point parameters of the gas well to be tested.

7. The device according to claim 6, characterized in that Determine the annular pressure curve according to the type of annular pressure; Establishing a database according to the annular pressure curve; The database is standardized and denoised, and a convolutional neural network is used to train the database to obtain an annular pressure curve prediction model.

8. The device according to claim 6, characterized in that The annular pressure curve prediction model is used to determine whether the gas well to be tested is leaking according to the changing trend of the annular pressure curve, wherein if the annular pressure curve shows an upward trend after decreasing for a period of time, it is determined that the gas well to be tested is leaking.

9. The device according to claim 6, characterized in that The step of bringing the basic parameters into the annulus leakage prediction model to determine the leakage point parameters of the gas well to be tested includes: Bringing the basic parameters into the annulus leakage prediction model; Dividing the annular space leakage prediction model into time and space grids to establish nodes of the tubing, casing, fluid in the tubing, and fluid in the annular space; Determine initial conditions and boundary conditions, and determine the pressure, density and boundary node temperature of the fluid at each node in the oil pipe according to the basic parameters; Determine the leakage depth and the annular pressure at the leakage point according to the pressure and density of the fluid at each node in the oil pipe and the boundary node temperature; The flow rate at the leakage point is determined according to the leakage depth and the annular pressure at the leakage point.

10. An electronic device, characterized in that: The electronic device includes: at least one processor; a memory connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the at least one processor implements the method for detecting the annulus of a gas well as described in any one of claims 1 to 5 by executing the instructions stored in the memory.

11. A machine-readable storage medium, characterized in that: Machine instructions are stored, and when the machine instructions are executed on the machine, the machine executes the method for detecting the annulus of a gas well as claimed in any one of claims 1 to 5.

Images