Early risk warning monitoring method and system based on video images

Abstract

The application provides an early risk warning monitoring method and system based on video images, and belongs to the technical field of remote video monitoring, and comprises the following steps: configuring an infrared camera and a plane camera; images of drilling fluid at an outlet groove of an oil well mud tank are acquired respectively, and the images are transmitted to a control host in real time; the control host obtains temperature change of the drilling fluid based on the infrared images; volume change of the drilling fluid at the outlet groove is also obtained; the control host analyzes to obtain a first analysis result and outputs warning information, or the control host further acquires infrared images and plane images of a second time length based on processing of the warning information, maintains or changes the first analysis result and outputs the warning information. Through real-time analysis on the temperature and flow of the drilling fluid, downhole conditions corresponding to the first time length are predicted, so that targeted intervention measures are proposed, and execution of the intervention measures is tracked, thereby realizing automatic monitoring and closed-loop feedback.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of remote video monitoring, in particular to an early risk warning monitoring method and system based on video images. BACKGROUND

[0002] At present, in the process of oil and gas drilling, the accidents of lost circulation and well kick in the wellbore can be reflected by the change of drilling fluid. When lost circulation occurs, the drilling fluid flows into the formation from the wellbore, and the flow of returned drilling fluid is lower than the pump-in amount, which may cause the liquid level in the wellbore to drop, and may cause the drilling fluid return to decrease and the well pressure to drop. When well kick occurs, the fluid in the formation will enter the wellbore, and the flow of returned drilling fluid is higher than the pump-in amount, and the well pressure will increase, and the properties of the drilling fluid may change, such as changes in color, viscosity, and bubble amount. Mud tank is mainly used for storing drilling fluid and continuously sending drilling fluid into the wellbore for lubrication and cooling of the drill bit, carrying of cuttings, stabilization of the well wall and control of the well pressure. When the drilling fluid returns to the mud tank, it will carry mud containing a large amount of cuttings and impurities, and the mud tank can remove solid particles in the drilling fluid, cool the drilling fluid, and realize the recycling of the drilling fluid.

[0003] The current drilling site basically adopts multi-person manual shift monitoring of outlet mud, and the operating personnel measures the mud depth of each mud tank at regular intervals, calculates the mud volume, and observes and monitors the relevant parameters of overflow. However, this manual monitoring method is a post-monitoring method, which lacks real-time performance and cannot achieve the function of in-process warning.

[0004] Therefore, it is necessary to provide an early risk warning monitoring method and system based on video images, which can judge whether an abnormal situation occurs in the wellbore according to the rising and falling of the liquid level returned in the mud tank and the temperature and flow of the liquid in the outlet tank, realize timely warning and intervention, and improve the timeliness of abnormal treatment. SUMMARY

[0005] Therefore, the present application provides an early risk warning monitoring method and system based on video images, which realizes quantitative detection of the temperature and volume of drilling fluid, judges whether the running condition of the wellbore is reliable, and timely proposes intervention measures and secondarily verifies the effect of the intervention measures.

[0006] The technical scheme of the present application is as follows:

[0007] On the one hand, the present application provides an early risk warning monitoring method based on video images, comprising the following steps:

[0008] S1: configure and calibrate the infrared camera and the plane camera;

[0009] S2: using an infrared camera and a plane camera to acquire images of drilling fluid at the outlet groove of the oil well mud tank respectively, and transmitting the images to the control host in real time;

[0010] S3: the control host obtains the temperature change of the drilling fluid based on the infrared images acquired by the infrared camera within a first time length; the control host also obtains the volume change of the drilling fluid at the outlet groove based on the infrared images and the plane images acquired by the plane camera within the first time length;

[0011] S4: the control host obtains a first analysis result based on the temperature change and the volume change of the drilling fluid within the first time length;

[0012] S5: the control host outputs warning information based on the first analysis result, or the control host further acquires infrared images and plane images within a second time length based on the processing of the warning information, maintains or changes the first analysis result and outputs the warning information.

[0013] On the basis of the above technical solutions, preferably, the infrared camera and the plane camera are calibrated so that the infrared camera and the plane camera can acquire the overall image of the outlet groove, the pose conversion matrix of the image coordinate system and the world coordinate system of the infrared camera and the plane camera is acquired respectively, and the corresponding relationship between the size of each pixel in the infrared camera and the plane camera and the real distance in the world coordinate system is obtained.

[0014] Preferably, the corresponding relationship between the size of each pixel in the infrared camera and the plane camera and the real distance in the world coordinate system is obtained by selecting an arbitrary plane in the vertical direction of the outlet groove of the mud tank, placing labels at different positions of the edge line in the vertical direction, acquiring a static image of the outlet groove of the mud tank through the infrared camera or the plane camera, identifying the pixel height difference of different labels in the static image, and obtaining the real proportional relationship between the size of the pixel and the world coordinate system. K 1、 K 2 and perspective transformation matrix H ; the positions of different edge lines of the outlet groove of the mud tank are determined in the infrared image or the plane image.

[0015] Further preferably, in step S3, the control host obtains the temperature change of the drilling fluid based on the infrared images acquired by the infrared camera within a first time length, which is based on the average pixel gray value of the surface layer of the drilling fluid flowing in the outlet groove of the mud tank within the first time length to estimate the actual return temperature of the drilling fluid , and calculate the theoretical return temperature of the drilling fluid ; wherein the actual return temperature of the drilling fluid is calculated according to the following formula: , wherein , is a polynomial coefficient, is the average gray value of the infrared image, is the emissivity of the drilling fluid, is the ambient temperature of the mud tank; the theoretical return temperature of the drilling fluid is calculated according to the following formula: , is the temperature of the drilling fluid at the bottom of the well, , is the formation temperature, is the friction heat generation coefficient, is the effective working time of the drill bit in this operation, is the average rotating speed corresponding to the effective working time of the drill bit, is the cumulative supply amount of the drilling fluid in this operation, is the temperature change caused by the circulation of the drilling fluid, , is the heat dissipation efficiency coefficient, is the circulation time of the drilling fluid.

[0016] Further preferably, the friction heat generation coefficient is calculated according to the following formula: wherein is the specific heat capacity of the drilling fluid, is the density of the drilling fluid in the first time period, is the temperature change of the drill bit caused by the circulation of the drilling fluid, , is the basic friction heat generation coefficient, , is the formation condition coefficient, , is the drilling pressure.

[0017] Further preferably, the control host further obtains the volume change of the drilling fluid in the outlet groove based on the infrared image and the planar image obtained by the planar camera in the first time period, including the following contents:

[0018] The histogram equalization is adopted, and then the contrast between the liquid surface and the background in the infrared image is extracted according to the RGB value of the pixel along the edge line of the outlet groove of the mud tank, that is, the pixel with R>240, G>100 and B<20 is fitted as the first straight line parallel to the upper edge of the outlet groove of the mud tank and intersecting with the vertical edge line, and the first pixel distance between the first straight line and the upper edge of the outlet groove of the mud tank is calculated.

[0019] In the planar image, the planar image is histogram equalized, if there is a reflection area in the planar image and the reflection area intersects with the vertical edge line of the outlet groove of the mud tank, a second straight line is fitted on the boundary of the reflection area, so that the included angle between the second straight line and the edge line of the outlet groove of the mud tank is minimum, and the second straight line is closed as the boundary of the drilling fluid in the mud tank; if there is no reflection area in the planar image, or there is a reflection area in the planar image, but the reflection area does not intersect with the vertical edge line of any outlet groove of the mud tank, the planar image is histogram equalized to eliminate the brightness difference, and then converted into a first gray image, a second gray image is converted from the still image in the drilling stop working stage, the first gray image and the second gray image are aligned based on the edge line of the outlet groove of the mud tank at the same position, the pixels with the gray scale not more than 50% of the overall gray scale of the image and the gray scale difference with the adjacent pixels not more than 5% are selected, a second straight line is fitted on the selected pixels, and the second pixel distance between each second straight line and the upper edge of the outlet groove of the mud tank is obtained; finally, the minimum value of the first straight line enclosed area or the second straight line enclosed area is selected, and the drilling fluid depth and the drilling fluid volume at the current time are converted from the first pixel distance or the second pixel distance, to obtain the drilling fluid volume change amount in the first time length.

[0020] Further preferably, the content of step S4 is: setting the real-time drilling fluid volume change amount in the mud tank in the first time length For , the volume of the drilling fluid pumped into the drilling in the first time length, the volume of the drilling fluid returned to the outlet groove in the first time length; based on the actual return temperature of the drilling fluid , the theoretical return temperature of the drilling fluid and the real-time drilling fluid volume change amount in the mud tank in the first time length , the following first analysis result is set:

[0021] 1) when , , it is determined that the drilling operation is low risk, and no warning information is issued;

[0022] 2) when , , it is determined that the drilling operation is at risk, it is prompted that there is fluid intrusion into the drilling, and corresponding measures are taken;

[0023] 3) when , , it is determined that the drilling operation is high risk, it is prompted to take plugging measures to isolate the fluid intruding into the wellbore;

[0024] 4) when , When the ratio of the volume of the gas bubble in the drilling fluid to the volume of the drilling fluid is greater than or equal to the first threshold value, it is determined that the drilling operation is at high risk, and it is prompted to perform well killing operation, shorten the cycle of the drilling fluid circulation cooling, increase the speed of the drilling fluid circulation, and supplement the drilling fluid to restore the liquid level balance.

[0025] 5) When the ratio of the volume of the gas bubble in the drilling fluid to the volume of the drilling fluid is greater than or equal to the first threshold value, it is determined that the drilling operation is at high risk, and it is prompted to perform well killing operation, shorten the cycle of the drilling fluid circulation cooling, increase the speed of the drilling fluid circulation, and supplement the drilling fluid to restore the liquid level balance. , When the ratio of the volume of the gas bubble in the drilling fluid to the volume of the drilling fluid is greater than or equal to the first threshold value, it is determined that the drilling operation is at high risk, and it is prompted to perform well killing operation, shorten the cycle of the drilling fluid circulation cooling, increase the speed of the drilling fluid circulation, and supplement the drilling fluid to restore the liquid level balance.

[0026] Further preferably, it is prompted that there is fluid intrusion into the well, and corresponding measures are taken, which is based on the number or density of the gas bubbles in the drilling fluid to confirm whether the fluid intruding into the well is gas or liquid, and then the density of the drilling fluid is increased to replace the intruding fluid. The adjustment formula of the drilling fluid density is: , is the adjusted drilling fluid density, is the shut-in standing pressure, is the drilling depth; the adjusted drilling fluid density is corrected based on the volume and density of the fluid intruding into the well: , is the correction result of the adjusted drilling fluid density, if the fluid intruding into the well is gas, the mixed density of the intruding gas and the drilling fluid is , is the volume flow rate of the gas intruding into the well, is the density of the gas intruding into the well; if the fluid intruding into the well is liquid, the mixed density of the intruding liquid and the drilling fluid is , is the volume of the liquid intruding into the well, is the density of the liquid intruding into the well.

[0027] More preferably, the content of step S5 is:

[0028] S51: immediately generate warning information to the well drilling management personnel according to the first analysis result of the medium risk and high risk obtained in step S4;

[0029] S52: after the corresponding treatment measures are taken, continue to use the infrared camera and the plane camera to continuously track the drilling fluid temperature change and the drilling fluid volume change in the drilling fluid outlet tank, and the second time length is not less than the first time length;

[0030] S53: according to the drilling fluid temperature change and the drilling fluid volume change in the second time length, if it is determined that the drilling operation state returns to low risk, the continuous state of the warning information is released, and it is returned to execute step S3 again, if it is determined that the drilling operation is still at medium risk or high risk, the continuous state of the warning information and the current first analysis result are maintained, and step S52 is repeatedly executed until the drilling operation state returns to low risk again, and then the continuous state of the warning information is released.

[0031] In another aspect, the present application provides an early risk warning monitoring system based on video images, for implementing the above method, comprising:

[0032] An image acquisition unit comprising an infrared camera and a plane camera, for acquiring infrared images and plane images of the drilling fluid at the outlet groove of the oil well mud tank respectively, and transmitting the images to the control host in real time;

[0033] The control host is in communication connection with the image acquisition unit, for obtaining the temperature change of the drilling fluid according to the infrared images obtained by the infrared camera within the first time length; the control host further obtains the volume change of the drilling fluid at the outlet groove based on the plane images of the first time length obtained by the plane camera; the control host predicts the first analysis result based on the temperature change and the volume change of the drilling fluid, and sends the first analysis result to the user of the control host to prompt the user to take disposal measures;

[0034] After the user takes disposal measures, the image acquisition unit further acquires infrared images and plane images for a second time length, and the control host further maintains the first analysis result unchanged or changes the first analysis result according to the infrared images and plane images obtained for the second time length.

[0035] The early risk warning monitoring method and system based on video images provided by the present application have the following beneficial effects compared with the prior art:

[0036] (1) The present application obtains the deviation of the real-time outlet temperature and the theoretical temperature of the drilling fluid through the fitting of the early infrared images, combined with the dynamic balance relationship between friction heat generation and drilling fluid circulation heat dissipation, and the accuracy and real-time performance are significantly improved compared with artificial post-measurement; the liquid level boundary is extracted by fusing infrared images and plane images, and the liquid level accuracy is higher, and even in the case of strong reflection and local shielding, the drilling fluid volume in the mud tank can still be accurately obtained;

[0037] (2) Based on the temperature deviation and the volume change, the self-adaptive first analysis result is graded by combining multiple thresholds, and the corresponding disposal suggestions and alarm information levels are predicted to remind the management personnel to intervene as soon as possible according to the prediction results; the post-maintenance is adjusted to in-process maintenance or preventive maintenance, and the timeliness of on-site maintenance is improved;

[0038] (3) Based on the prediction results, the corresponding disposal measures are proposed, and the secondary monitoring and verification based on the second time length are realized, realizing closed-loop control and automatic management of downhole risks. BRIEF DESCRIPTION OF DRAWINGS

[0039] In order to make the technical solutions in the embodiments of the present application or the prior art clearer, the accompanying drawings needed in the embodiments or prior art description will be briefly introduced. Obviously, the accompanying drawings in the following description only need to be some embodiments of the present application, and all other embodiments obtained by a person of ordinary skill in the art without creative work belong to the protection scope of the present application.

[0040] Figure 1 A flow chart of steps of a video image-based early risk warning monitoring method and system of the present application;

[0041] Figure 2 A schematic diagram of infrared images and plane images obtained by an infrared camera and a plane camera of a video image-based early risk warning monitoring method and system of the present application. DETAILED DESCRIPTION

[0042] The technical solutions in the embodiments of the present application will be described clearly and completely in combination with the embodiments of the present application. Obviously, the described embodiments only need to be some embodiments of the present application, and not all the embodiments. Based on the embodiments of the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work belong to the protection scope of the present application.

[0043] The conventional method is that the operating personnel measures the mud depth of each mud tank at regular time intervals, calculates the mud amount, and observes and monitors the overflow-related parameters. However, this manual monitoring method belongs to post-monitoring, and is not real-time, and cannot achieve the function of in-process early warning. In view of this, as shown in the drawings, on the one hand, the present application provides a video image-based early risk warning monitoring method, which comprises the following steps: Figure 1

[0044] S1: configuring and calibrating an infrared camera and a plane camera.

[0045] Calibrating the infrared camera and the plane camera is to enable the infrared camera and the plane camera to obtain the overall image of the outlet groove, to obtain the pose conversion matrix of the image coordinate system and the world coordinate system of the infrared camera and the plane camera respectively, and to obtain the corresponding relationship between the size of each pixel in the infrared camera and the plane camera and the real distance in the world coordinate system.

[0046] Specifically, in the drilling stoppage stage, an edge line of any plane in the vertical direction is selected in the outlet groove of the mud tank, labels are placed at different positions of the edge line, the static image of the outlet groove of the mud tank is obtained by the infrared camera or the plane camera, the pixel height difference of different labels in the static image is identified, and the real proportional relationship between the size of the pixel and the world coordinate system is obtained. K 1、 K 2 and perspective transformation matrix​H ; determine the position of different edges of the outlet groove of the mud tank in the infrared image or the planar image. When the actual size in the world coordinate system needs to be changed, if the homogeneous coordinates of a pixel point in the infrared image or the planar image are X , the corresponding homogeneous coordinates in the world coordinate system are X’ , X HX' ; convert the pixel distance of different pixel points in the image into the actual distance of the corresponding points in the world coordinate system, such as X 2- X 1|= K 1 H | X 2 ’ - X 1 ’ | , or X 2- X 1|= K 2 H | X 2 ’ - X 1 ’| , where the subscripts 1 and 2 represent different image pixel points or points in the world coordinate system.

[0047] If the infrared camera and the planar camera are perpendicular to the vertical inner surface of the outlet groove of the mud tank, the perspective transformation matrix H is not needed; if there is an inclination angle, the perspective transformation matrix H needs to be obtained. The perspective transformation matrix is a 3x3 matrix, which can be calculated by the function of the OPENCV library and is well known in the art, and will not be described here.

[0048] S2: Use the infrared camera and the planar camera to respectively acquire the images of the drilling fluid at the outlet groove of the oil well mud tank, and transmit the images to the control host in real time. The infrared camera and the planar camera are respectively connected to the remote control host through wired or wireless communication, and transmit real-time image information to the control host. As shown in Figure 2 , the left image is the infrared image of the drilling fluid in the outlet groove of the mud tank acquired by the infrared camera; Figure 2 and the right image is the planar image of the drilling fluid in the outlet groove of the mud tank acquired by the planar camera. Figure 2

[0049] S3: The control host obtains the temperature change of the drilling fluid based on the infrared images acquired by the infrared camera within a first time length; the control host also obtains the volume change of the drilling fluid at the outlet groove based on the infrared images and the planar images acquired by the planar camera within the first time length.

[0050] This step is divided into two parts: ​​

[0051] S31: The control host obtains the drilling fluid temperature change condition based on the infrared image obtained by the infrared camera within the first time length, that is, the average pixel gray value of the surface of the drilling fluid flowing in the outlet groove of the mud tank within the first time length based on the infrared image, to estimate the actual return temperature of the drilling fluid , and calculate the theoretical return temperature of the drilling fluid ; wherein the actual return temperature of the drilling fluid is calculated according to the following formula: , wherein , is a polynomial coefficient, is the average gray value of the gray image after the infrared image is converted into a gray image, is the emissivity of the drilling fluid, is the ambient temperature of the mud tank, and the theoretical return temperature of the drilling fluid is calculated according to the following formula: , is the temperature of the drilling fluid at the bottom of the well, , is the formation temperature, and the formation temperature is obtained based on the average surface temperature of the current season at the drilling site and the geothermal gradient corresponding to the drilling depth; is the friction heat generation coefficient, is the effective working time of the drill bit in this operation, is the average rotating speed corresponding to the effective working time of the drill bit, is the cumulative supply amount of the drilling fluid in this operation, is the temperature change caused by the circulation of the drilling fluid, , is the heat dissipation efficiency coefficient, is the circulation time of the drilling fluid. It should be noted that the effective working time of the drill bit in this operation and the circulation time of the drilling fluid are not less than the first time length, because the first time length is started after the drilling is stably operated for a period of time, and is not started at the same time as the start of the drill bit, so that the monitoring fluctuation at the start can be excluded. The polynomial coefficient is not fixed, and if there is a deviation between the actual return temperature of the drilling fluid and the measured value, the polynomial coefficient needs to be adjusted so that the cumulative value of the deviation between the drilling fluid temperature fitting curve and the actual drilling fluid temperature is minimized.

[0052] The average surface temperature of the current season is calculated using the following formula: , wherein k is a radiation-temperature conversion coefficient, is a base temperature, which is obtained by querying the meteorological data of the drilling site; Latitude of the drilling site, positive for north latitude, negative for south latitude, and 0 for equator; Solar declination, 23.5° for summer solstice, -23.5° for winter solstice, and 0 for spring equinox and autumn equinox; Solar constant; Seasonal average sunshine duration; Surface albedo, 0.34 for grassland, 0.6 for cement ground, and 0.93 for snow ground. The ground temperature is further calculated by the following formula: Ground temperature coefficient, Drilling depth.

[0053] In an embodiment, the friction heat generation coefficient is calculated according to the following formula: wherein Specific heat capacity of the drilling fluid, Density of the drilling fluid in the first time length, Temperature change of the drill bit caused by the drilling fluid circulation, Basic friction heat generation coefficient, Formation condition coefficient, Drilling pressure.

[0054] S32: The control host further obtains the volume change of the drilling fluid in the outlet groove based on the infrared image and the planar image acquired by the planar camera in the first time length, including the following contents:

[0055] The histogram equalization is adopted, and then the contrast between the liquid surface and the background in the infrared image is extracted according to the RGB value of the pixel along the edge line of the outlet groove of the mud tank, that is, the pixel with R>240, G>100, and B<20, which is fitted as a first straight line parallel to the upper edge of the outlet groove of the mud tank and intersecting with the vertical direction edge line, and the first pixel distance between the first straight line and the upper edge of the outlet groove of the mud tank is calculated.

[0056] ​​​​In the planar image, the planar image is histogram equalized, if there is a reflection area in the planar image and the reflection area intersects with the vertical edge of the outlet groove of the mud tank, a second straight line is fitted on the boundary of the reflection area, so that the included angle between the second straight line and the edge of the outlet groove of the mud tank is minimized, and the second straight line is closed as the boundary of the drilling fluid in the mud tank; if there is no reflection area in the planar image, or there is a reflection area in the planar image, but the reflection area does not intersect with the vertical edge of any outlet groove of the mud tank, the planar image is histogram equalized to eliminate the brightness difference, and then converted into a first gray image, a second gray image is converted from the still image in the drilling stop working stage, the first gray image and the second gray image are aligned based on the edge of the outlet groove of the mud tank at the same position, the pixels with a gray scale not more than 50% of the overall gray scale of the image and a gray scale difference with adjacent pixels not more than 5% are selected, and a second straight line is fitted on the selected pixels, and the second pixel distance between each second straight line and the upper edge of the outlet groove of the mud tank is obtained. If the reflection area can assist in obtaining the boundary of the drilling fluid, the straight edge of the reflection area is used, and if the reflection area does not help much in obtaining the boundary of the drilling fluid, the reflection area is ignored.

[0057] Finally, the minimum value of the first straight line enclosed area or the second straight line enclosed area is selected, and the drilling fluid depth and the drilling fluid volume at the current time are converted according to the first pixel distance or the second pixel distance, to obtain the drilling fluid volume change in the first time length.

[0058] The drilling fluid volumes obtained in different images may not be consistent, in order to be conservative, the drilling fluid volume is calculated by selecting the smaller enclosed area of the pixel area, which can improve the reliability of the subsequent first analysis result.

[0059] S4: The host obtains a first analysis result based on the drilling fluid temperature change and the volume change in the first time length.

[0060] The content of step S4 is: setting the real-time volume change of the drilling fluid in the mud tank in the first time length , , , the volume of the drilling fluid pumped into the drilling in the first time length, the volume of the drilling fluid returned to the outlet groove in the first time length; based on the actual return temperature of the drilling fluid , the theoretical return temperature of the drilling fluid , and the real-time volume change of the drilling fluid in the mud tank in the first time length , the following first analysis result is set:

[0061] 1) when , , it is determined that the drilling operation is low risk, and no warning information is issued;

[0062] 2) When , , it is identified as a risk in drilling operation, prompting fluid invasion into the wellbore, and corresponding measures are taken.

[0063] When gas invasion is confirmed, it is through fitting the number of bubbles in the planar image, whether it is significantly increased, that is, the area of the bubble region accounts for more than a certain proportion of the image pixel area, such as more than 5%, when it is identified as gas invasion. When liquid invasion is confirmed, it is through measuring whether the density or conductivity of the mixture changes significantly relative to the drilling fluid, such as a change in density of more than 5% of the initial density of the drilling fluid.

[0064] Here, corresponding measures are taken based on the number of bubbles or density in the drilling fluid to confirm that the fluid invading the wellbore is gas or liquid, and then the density of the drilling fluid is increased to replace the invading fluid. The adjustment formula for the drilling fluid density is: , is the adjusted drilling fluid density, is the shut-in well pressure, is the drilling depth; based on the volume and density of the fluid invading the wellbore, the adjusted drilling fluid density is corrected: , is the correction result of the adjusted drilling fluid density, if the fluid invading the wellbore is gas, the mixed density of the invading gas and the drilling fluid is , is the volume flow rate of the gas invading the wellbore, is the density of the gas invading the wellbore; if the fluid invading the wellbore is liquid, the mixed density of the invading liquid and the drilling fluid is , is the volume of the liquid invading the wellbore, is the density of the liquid invading the wellbore.

[0065] 3) When , , it is identified as a high risk in drilling operation, prompting to take plugging measures to isolate the fluid invading the wellbore; in this case, there may be shallow fluid invasion into the wellbore, such as a cave / fault, which needs to exclude the possibility of false positives, or confirm the risk and upgrade the risk level. If necessary, drilling needs to be stopped and high-concentration plugging materials need to be used for emergency plugging measures, and the stability of the wellbore needs to be detected.

[0066] 4) When , , it is identified as a high risk in drilling operation, which may exist well kick, prompting to carry out well killing operation, which should be immediately stopped, shut in and prevent blowout, and real-time monitor the wellhead pressure.

[0067] 5) When , At this time, it is determined that the drilling operation is high risk, and it is prompted to carry out plugging and drilling fluid cooling circulation at the same time. At this time, high temperature formation leakage may occur, which leads to insufficient drilling fluid and inability to balance the formation pressure, which is risky. Drilling should be stopped for inspection and plugging agent injection, or drilling fluid density and viscosity should be adjusted to assist plugging.

[0068] Real-time volume change of drilling fluid For positive, the volume of pumped drilling fluid is greater than the volume of returned drilling fluid, and the real-time volume change of drilling fluid For negative, the volume of pumped drilling fluid is less than the volume of returned drilling fluid; the above different combinations correspond to different levels of risk, and some cases need timely intervention.

[0069] S5: The control host outputs warning information based on the first analysis result, or the control host further acquires infrared images and plane images of a second time length based on the processing situation of the warning information, maintains or changes the first analysis result and outputs warning information.

[0070] The content of step S5 is;

[0071] S51: For the first analysis result of medium risk and high risk obtained in step S4, immediately generate warning information and feed back to the drilling management personnel;

[0072] S52: After taking corresponding treatment measures, continue to use the infrared camera and the plane camera to continuously track the drilling fluid temperature change and the drilling fluid volume change in the drilling fluid outlet tank, and make the second time length not less than the first time length;

[0073] S53: According to the drilling fluid temperature change and the drilling fluid volume change in the second time length, if it is determined that the drilling operation state returns to low risk, the continuous state of the warning information is released, and the step S3 is returned to be executed again, if it is determined that the drilling operation is still medium risk or high risk, the continuous state of the warning information and the current first analysis result are maintained, and the step S52 is repeated until the drilling operation state returns to low risk again, and the continuous state of the warning information is released.

[0074] On the other hand, the present application provides an early risk warning monitoring system based on video images, which is used to realize the above-mentioned method, comprising:

[0075] An image acquisition unit comprising an infrared camera and a plane camera, for acquiring infrared images and plane images of drilling fluid at the outlet tank of the oil well mud tank respectively, and feeding the images back to the control host in real time;

[0076] The control host is in communication connection with the image acquisition unit, is used for obtaining the drilling fluid temperature change condition according to the infrared image obtained by the infrared camera within the first time length, the control host is further based on the infrared image and the planar image of the first time length obtained by the planar camera, obtains the volume change condition of the outlet groove drilling fluid, the control host is based on the drilling fluid temperature change condition and the volume change condition, predicts the first analysis result and sends the first analysis result to the user of the control host, prompts the user to take disposal measures;

[0077] After the user takes disposal measures, the image acquisition unit further obtains the infrared image and the planar image according to the second time length, and the control host further maintains the first analysis result unchanged or changes the first analysis result according to the infrared image and the planar image obtained in the second time length.

[0078] The above only describes the preferred embodiments of the present application and is not used to limit the present application, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method for early risk warning and monitoring based on video images, characterized in that, Includes the following steps: S1: Configure and calibrate the infrared camera and the planar camera; S2: Use an infrared camera and a planar camera to acquire images of the drilling fluid at the outlet trough of the oil well mud tank, and transmit the images back to the control host in real time; S3: The control host obtains the drilling fluid temperature change based on the infrared image acquired by the infrared camera within the first time period; the control host also obtains the drilling fluid volume change in the outlet tank based on the infrared image and the planar image acquired by the planar camera within the first time period. In step S3, the control host obtains the drilling fluid temperature change based on the infrared images acquired by the infrared camera within a first time period. This is done by estimating the actual return temperature T of the drilling fluid based on the average grayscale value of the surface layer of the drilling fluid flowing in the mud tank outlet trough within the first time period, obtained from the infrared images. true And calculate the theoretical return temperature T of the drilling fluid. reture The actual return temperature T of the drilling fluid true Calculate according to the following formula: Where T = A(pixel) 3 -B (pixel) 2 +C(pixel)+D, where A, B, C, and D are polynomial coefficients, pixel is the average grayscale value of the infrared image, ε is the emissivity of the drilling fluid, and T amb The ambient temperature around the mud tank; the theoretical return temperature of the drilling fluid, T. reture Calculate T according to the following formula: reture =T down -ΔT loss T down The temperature of the drilling fluid at the bottom of the well. T formation Let t be the formation temperature, α be the coefficient of frictional heat generation, and t be the temperature of the formation. active The effective working time of the drill bit during this operation is represented by RPM, which is the average rotational speed of the drill bit during its effective working time. Q represents the effective working time of the drill bit. supply ΔT represents the cumulative amount of drilling fluid supplied during this operation. loss Temperature changes caused by drilling fluid circulation β is the heat dissipation efficiency coefficient, t cycle This refers to the drilling fluid circulation time. The coefficient of frictional heat generation, α, is calculated according to the following formula: Where C Q Let ρ be the specific heat capacity of the drilling fluid, ρ be the density of the drilling fluid during the first time interval, and ΔT be the temperature change of the drill bit caused by the circulation of the drilling fluid, where ΔT ≤ T. formation -T amb α0 is the basic friction heat generation coefficient, α0=0.02, f is the formation condition coefficient, f>0, and WOB is the drilling pressure. The control host also obtains the volume change of the drilling fluid in the outlet tank based on infrared images and planar images acquired by a planar camera for a first duration, including the following: Histogram equalization is used. Then, the contrast between the liquid surface and the background in the infrared image is calculated. Based on the RGB values ​​of the pixels, pixels with R>240, G>100, and B<20 are extracted along the edge of the mud tank outlet channel. These pixels are fitted to a first straight line parallel to the upper edge of the mud tank outlet channel and intersecting the vertical edge. The distance between the first straight line and the first pixel of the upper edge of the mud tank outlet channel is calculated. In the planar image, histogram equalization is performed. If a reflective area exists in the planar image and intersects the vertical edge of the mud tank outlet channel, a second straight line is fitted along the boundary of the reflective area to minimize the angle between the second straight line and the edge of the mud tank outlet channel. Several second straight lines are then used to enclose the boundary of the drilling fluid inside the mud tank. If no reflective area exists in the planar image, or if a reflective area exists but does not intersect the vertical edge of any mud tank outlet channel, histogram equalization is performed on the planar image to eliminate brightness differences. Then, the image is converted to a first grayscale image, and drilling is stopped. The still image during the working phase is converted into a second grayscale image. Using the edge of the mud tank outlet trough at the same location as a reference, the first and second grayscale images are aligned. Pixels with a grayscale value not exceeding 50% of the overall image grayscale and a grayscale difference of not more than 5% with adjacent pixels are fitted with a second straight line. The second pixel distance between each second straight line and the upper edge of the mud tank outlet trough is obtained. Finally, the minimum value between the area enclosed by the first straight line and the area enclosed by the second straight line is selected. The drilling fluid depth and volume at the current moment are calculated based on the first pixel distance or the second pixel distance to obtain the drilling fluid volume change within the first time period. S4: The control host obtains the first analysis result based on the changes in drilling fluid temperature and volume within the first time period; S5: The control host outputs a warning message based on the first analysis result, or the control host further acquires an infrared image and a planar image of a second duration based on the processing status of the warning message, maintains or changes the first analysis result and outputs a warning message.

2. The early risk warning and monitoring method based on video images according to claim 1, characterized in that, In step S1, calibrating the infrared camera and the planar camera enables them to acquire the overall image of the exit slot, obtain the pose transformation matrix between the image coordinate system and the world coordinate system of the infrared camera and the planar camera respectively, and obtain the correspondence between the size of each pixel in the infrared camera and the real distance in the world coordinate system.

3. The early risk warning and monitoring method based on video images according to claim 2, characterized in that, To obtain the correspondence between the size of each pixel in the infrared camera and the true distance in the world coordinate system, respectively, during the drilling shutdown phase, any plane is selected in the vertical direction of the mud tank outlet channel, and tags are placed at different positions on the edge. Static images of the mud tank outlet channel are acquired by the infrared camera or the planar camera. The pixel height difference of different tags is identified in the static image, and the proportional relationship between the pixel size and the true distance in the world coordinate system, K1, K2 and perspective transformation matrix H, are obtained. The positions of different edge lines of the mud tank outlet channel are determined in the infrared image or the planar image.

4. The early risk warning and monitoring method based on video images according to claim 1, characterized in that, Step S4 is as follows: Set the real-time volume change ΔV of the drilling fluid in the mud tank within the first time period as ΔV = V pump -V return V pump V represents the volume of drilling fluid pumped into the well during the first drilling period. return This represents the volume of drilling fluid returning to the outlet tank during the first time period; based on the actual return temperature T of the drilling fluid. true Theoretical return temperature T of drilling fluid reture The real-time volume change ΔV of the drilling fluid in the mud tank during the first time period is set as the following first analysis result: 1) When T true ≤T returen ±10℃, ΔV≤3%V pump At that time, the drilling operation was deemed low-risk, and no warning information was issued; 2) When T true <T returen -10℃, ΔV < -3%V pump At that time, it was identified as a risk in drilling operations, indicating that fluid had entered the well, and corresponding measures were taken; 3) When T true <T returen -10℃, ΔV>5%V pump At that time, the drilling operation was deemed to be of high risk, and measures were recommended to plug leaks and isolate the fluid that had entered the wellbore. 4) When T true >T returen +10℃, ΔV < -3%V pump When drilling operations are deemed high-risk, a well control operation is recommended, the drilling fluid circulation and cooling cycle is shortened, the drilling fluid circulation speed is increased, and drilling fluid is replenished to restore fluid level balance. 5) When T true >T returen +10℃, ΔV>5%V pump At that time, the drilling operation was deemed to be of high risk, and it was suggested that leakage plugging and drilling fluid cooling circulation be carried out simultaneously.

5. The early risk warning and monitoring method based on video images according to claim 1, characterized in that, The system indicates fluid intrusion into the wellbore and takes corresponding measures. This is based on the number or density of air bubbles in the drilling fluid, confirming whether the intruding fluid is gas or liquid. The system then increases the density of the drilling fluid to replace the intruding fluid. The formula for adjusting the drilling fluid density is: ρ1 is the adjusted drilling fluid density, P shut The shut-in stand pressure is given, and h is the drilling depth. The adjusted drilling fluid density is corrected based on the volume and density of the fluid entering the well. ρ correct To correct the drilling fluid density, if the fluid invading the well is gas, the mixed density of the invading gas and drilling fluid is: Q gas ρ is the volumetric flow rate of the gas entering the well. gas Let be the density of the gas that has entered the wellbore; if the fluid entering the wellbore is a liquid, the mixed density of the entering liquid and the drilling fluid is . V inv ρ is the volume of the fluid that enters the well. inv This refers to the density of the fluid that penetrates the well.

6. The early risk warning and monitoring method based on video images according to claim 4, characterized in that, The content of step S5 is as follows: S51: Based on the first analysis results of medium and high risk obtained in step S4, immediately generate warning information and feed it back to the drilling management personnel; S52: After taking corresponding measures, continue to use infrared cameras and planar cameras to continuously track the changes in drilling fluid temperature and volume in the drilling fluid outlet tank, and ensure that the second duration is not less than the first duration. S53: Based on the changes in drilling fluid temperature and volume during the second time period, if the drilling operation status is determined to have returned to low risk, the continuous status of the warning information is lifted, and the process returns to step S3. If the drilling operation is determined to still be at medium or high risk, the continuous status of the warning information and the current first analysis result are maintained, and step S52 is repeated until the drilling operation status returns to low risk again, at which point the continuous status of the warning information is lifted.

7. An early risk warning and monitoring system based on video images, used to implement the method according to any one of claims 1-6, characterized in that, include: The image acquisition unit includes an infrared camera and a planar camera, which are used to acquire infrared images and planar images of the drilling fluid at the outlet trough of the oil well mud tank, respectively, and transmit the images back to the control host in real time. The control host is connected in communication with the image acquisition unit and is used to obtain the drilling fluid temperature change based on the infrared images acquired by the infrared camera within a first time period; the control host also obtains the volume change of the drilling fluid in the outlet tank based on the infrared images and the planar images acquired by the planar camera within the first time period. The control host obtains the drilling fluid temperature change based on infrared images acquired by an infrared camera over a first time period. It estimates the actual return temperature T of the drilling fluid by obtaining the average grayscale value of the surface layer of the drilling fluid flowing in the mud tank outlet trough within the first time period from the infrared images. true And calculate the theoretical return temperature T of the drilling fluid. reture The actual return temperature T of the drilling fluid true Calculate according to the following formula: Where T = A(pixel) 3 -B (pixel) 2 +C(pixel)+D, where A, B, C, and D are polynomial coefficients, pixel is the average grayscale value of the infrared image, ε is the emissivity of the drilling fluid, and T amb The ambient temperature around the mud tank; the theoretical return temperature of the drilling fluid, T. reture Calculate T according to the following formula: reture =T down -ΔT loss T down The temperature of the drilling fluid at the bottom of the well. T formation Let t be the formation temperature, α be the coefficient of frictional heat generation, and t be the temperature of the formation. active The effective working time of the drill bit during this operation is represented by RPM, which is the average rotational speed of the drill bit during its effective working time. Q represents the effective working time of the drill bit. supply ΔT represents the cumulative amount of drilling fluid supplied during this operation. loss Temperature changes caused by drilling fluid circulation β is the heat dissipation efficiency coefficient, t cycle This refers to the drilling fluid circulation time. The coefficient of frictional heat generation, α, is calculated according to the following formula: Where C Q Let ρ be the specific heat capacity of the drilling fluid, ρ be the density of the drilling fluid during the first time interval, and ΔT be the temperature change of the drill bit caused by the circulation of the drilling fluid, where ΔT ≤ T. formation -T amb α0 is the basic friction heat generation coefficient, α0=0.02, f is the formation condition coefficient, f>0, and WOB is the drilling pressure. The control host also obtains the volume change of the drilling fluid in the outlet tank based on infrared images and planar images acquired by a planar camera for a first duration, including the following: Histogram equalization is used. Then, the contrast between the liquid surface and the background in the infrared image is calculated. Based on the RGB values ​​of the pixels, pixels with R>240, G>100, and B<20 are extracted along the edge of the mud tank outlet channel. These pixels are fitted to a first straight line parallel to the upper edge of the mud tank outlet channel and intersecting the vertical edge. The distance between the first straight line and the first pixel of the upper edge of the mud tank outlet channel is calculated. In the planar image, histogram equalization is performed. If a reflective area exists in the planar image and intersects the vertical edge of the mud tank outlet channel, a second straight line is fitted along the boundary of the reflective area to minimize the angle between the second straight line and the edge of the mud tank outlet channel. Several second straight lines are then used to enclose the boundary of the drilling fluid inside the mud tank. If no reflective area exists in the planar image, or if a reflective area exists but does not intersect the vertical edge of any mud tank outlet channel, histogram equalization is performed on the planar image to eliminate brightness differences. Then, the image is converted to a first grayscale image, and drilling is stopped. The still image during the working phase is converted into a second grayscale image. Using the edge of the mud tank outlet trough at the same location as a reference, the first and second grayscale images are aligned. Pixels with a grayscale value not exceeding 50% of the overall image grayscale and a grayscale difference of not more than 5% with adjacent pixels are fitted with a second straight line. The second pixel distance between each second straight line and the upper edge of the mud tank outlet trough is obtained. Finally, the minimum value between the area enclosed by the first straight line and the area enclosed by the second straight line is selected. The drilling fluid depth and volume at the current moment are calculated based on the first pixel distance or the second pixel distance to obtain the drilling fluid volume change within the first time period. Based on the changes in drilling fluid temperature and volume, the control host predicts the first analysis result and sends it to the user of the control host, prompting the user to take appropriate measures. After the user takes action, the image acquisition unit further acquires infrared images and planar images for a second duration. The control host further maintains the first analysis result unchanged or changes the first analysis result based on the acquired infrared images and planar images for the second duration.

Images