Method for predicting drill jamming of permian igneous rock and application of method

Abstract

The invention provides a method for predicting drill jamming of permian igneous rocks and application of the method, and belongs to the technical field of oil exploration and development. The method comprises the following steps: collecting drilled well data and seismic data in a work area; performing well-seismic calibration based on the collected drilling data and seismic data; on the basis of well seismic calibration, calibrating the position of the permian igneous rock on the seismic section; based on the positions of the calibrated permian system and carboniferous system interfaces on the seismic section, summarizing reflection characteristics of permian system igneous rocks; and comparing the summarized reflection characteristics of the permian igneous rock with the reflection characteristics of the to-be-drilled well, and predicting the permian igneous rock stuck drilling section of the to-be-drilled well. The invention further provides application of the method in well drilling. Compared with the prior art, the method is suitable for well drilling jamming prediction of areas with geologic structures containing permian igneous rocks.

Description

Technical Field

[0001] The invention relates to the technical field of petroleum exploration and development, and mainly to a method for predicting pipe sticking in Permian igneous rocks and its application. Background Art

[0002] Drilling stuck drill refers to a phenomenon in which the drill tool is trapped in the well and cannot move freely due to various reasons during the drilling process. This may be caused by geological factors, poor drilling fluid performance, improper technical measures and other reasons. The hazards of drilling stuck drill include but are not limited to: the drill tool cannot be lifted or lowered, and it may get stuck in serious cases; the tension torque of the drill tool increases, the rock cuttings returned by the vibrating screen decreases, the pump pressure / ECD increases, it is difficult to transmit the drilling pressure to the drill bit, the rock cuttings are repeatedly broken, the tool face is difficult to stabilize, the tension increases when lifting the drill, and there is excessive tension in the casing; if the drill is stuck seriously, it may also cause serious consequences such as damage to the drill tool, scrapping of the oil well, and casualties.

[0003] Currently, the commonly used drill bit stuck warning methods include but are not limited to: observing the changes in parameters such as the pulling torque of the drill bit, pump pressure, and the returned cuttings from the vibrating screen, as well as whether the drill bit encounters resistance when it is lifted and lowered. During the drilling process, the formation conditions are regularly tested, such as the lithology, hardness, cracks, etc. of the formation, as well as the absorption of drilling fluid by the formation. However, this kind of drill bit stuck warning method that needs to be combined with the actual situation often relies on the experience of the warning analyst, so it is difficult to implement as a controllable technical solution with small differences in operation between different personnel.

[0004] The risk of drilling stuck caused by Permian igneous rocks mainly comes from their special lithological characteristics. Permian igneous rocks are usually hard, brittle and abrasive, which makes it easy to generate rock cuttings during drilling and may cause severe wear of the drill bit. When the drill bit is severely worn, the shape and size of its cutting edge will change, which will affect the stability of the drill tool in the wellbore and may cause the drill tool to deviate in the well. In addition, due to the high abrasiveness of Permian igneous rocks, the drill tool may encounter greater resistance when moving up and down in the well, which also increases the risk of drill stuck. Therefore, a computer early warning method for drill stuck suitable for Permian igneous rocks is needed.

[0005] CN115640759A discloses a drill stuck warning method and system based on machine learning, belonging to the technical field of drill stuck warning, the method comprises the following steps: obtaining cuttings data distributed along the borehole trajectory, and constructing a real-time cuttings migration model; obtaining the real-time dynamic distribution of the cuttings bed in the borehole based on the real-time cuttings migration model; constructing a friction torque balance model when the drill pipe rotates in the borehole; obtaining the friction torque value on the drill pipe based on the real-time dynamic distribution of the cuttings bed in the borehole and the friction torque balance model; optimizing the friction torque balance model based on the friction torque value on the drill pipe using a Bayesian optimization algorithm and a Nash efficiency coefficient; performing real-time drill stuck warning using a time series data analysis method based on the optimized friction torque balance model; the invention solves the problem that it is difficult to accurately and quickly predict the risk of drill stuck in real time under different working conditions; however, the effect part of the invention only records that the established well test interpretation model can reliably interpret abnormally high-pressure carbonate volatile oil reservoirs, lacks targeted adaptation for drill stuck warning of Permian igneous rocks, and its accuracy is difficult to confirm.

[0006] CN115204046A discloses a method for predicting stuck drill based on machine learning, including collecting relevant logging data and preprocessing the logging data; screening out parameter data related to stuck drill according to the preprocessing results; establishing a stuck drill prediction model using a BP neural network algorithm optimized by GA based on the parameter data related to stuck drill; using the stuck drill prediction model to make predictions and issue early warnings; using a neural network algorithm optimized by a genetic algorithm to predict stuck drill accidents, and using visual analysis of a machine learning algorithm to enable management personnel to take corresponding treatment measures in time before accidents occur, thereby reducing risks and greatly improving the safety performance of drilling; however, the invention still does not involve the content of predicting the risks of drilling in Permian basalt and lacks clear applicability.

[0007] CN113129157A discloses a real-time early warning method for drill stuck fault in downhole suitable for shale gas long water section, characterized in that it includes: step 100, constructing a drill stuck fault database; step 200, constructing a BP neural network intelligent algorithm; step 300, creating a drill stuck fault early warning model based on the BP neural network intelligent algorithm in step 200; step 310, designing a BP neural network; step 311, designing an input layer: according to the drill stuck fault database in step 100, selecting a characterization parameter with a strong correlation with the drill stuck fault and setting it as an input neuron; step 312, designing an output layer: setting two output neurons, which are the expected output vector q1=(1,0) when the drill stuck fault occurs and the expected output vector q2=(0,1) when the drill stuck fault does not occur; step 313, designing a hidden layer: calculating the number of hidden layers by a classical formula, and the number of hidden layers is 1-10; the beneficial effects recorded include:

[0008] A real-time early warning method for drill stuck faults based on particle swarm algorithm optimized BP neural network was developed, and a drill stuck fault early warning model was created, which realized intelligent and real-time quantitative judgment of drill stuck faults and solved the problems of poor comprehensive utilization of monitoring information, insufficient risk warning, and strong subjectivity in traditional prediction methods.

[0009] However, the real-time warning method for downhole stuck drill failures proposed in the prior art for shale gas long water sections does not involve predicting the distribution of Permian basalt based on the reflection characteristics of the well to be drilled, making it difficult to accurately predict the Permian igneous rock stuck drill section.

[0010] The real-time early warning method for downhole drill stuck faults applicable to shale gas long water sections proposed in the prior art does not involve predicting the distribution of Permian basalt based on the reflection characteristics of the well to be drilled, thereby predicting the Permian igneous rock drill stuck section, which is different from the method and purpose of the present invention.

[0011] Permian igneous rocks are well developed in Shunbei area. When encountering basalt during the actual drilling process, the drill often gets stuck, which will cause drilling well control risks. In the early stage, the drilling situation of adjacent wells was mainly predicted; however, the prediction effect was poor due to the large lateral changes of igneous rocks, so there is an urgent need to develop a method to solve this problem.

[0012] In order to solve this problem, Sinopec North China Petroleum Engineering Co., Ltd. Western Branch published the "Permian Optimal Fast Drilling Plan for Fault Zone No. 5 in Shunbei Block" in 2022. The research objectives of the paper are that basalt is hard, abrasive, poor drillability, poor stability, prone to block drop, and cracks at the junction of intrusive bodies are prone to well leakage, which is a construction difficulty in Fault Zone No. 5. When drilling to a depth of 4932.30m, the top drive frequently stopped. After releasing the torque, the lifting and lowering of the active drilling tool encountered resistance. The jar was jarred for the 205th time, and it was lifted to 258t (original hanging weight 208t), and the jar was successfully unblocked. The cause of the stuck drill was analyzed to be the Permian basalt and basalt cuttings that were not returned in time and fell to the drill bit at the bottom of the well. The well team summarized the experience, formulated a downhole risk assessment, and combined the existing well data to start from the drill bit, drilling fluid performance, and drilling parameters. The team summarized the progressive pressure-bearing plugging method, the roller drill bit pressure stabilization and parameter control method, and the mud performance optimization method to deal with the risk of well collapse and leakage in the Permian formation. During the secondary construction process of the well, the Permian formation was safely drilled through and the second drilling depth of 5186m was successfully reached. A set of optimized and fast drilling construction plans suitable for the Permian formation in the No. 5 fault zone of Shunbei Block were summarized.

[0013] However, the main content and innovation of this paper is the Permian basalt drilling method, and no warning or prediction of possible drill sticking is made. It still needs a method to predict the drill sticking situation and solve the problem of drill sticking in Permian igneous rocks from both construction and design aspects.

[0014] Therefore, how to accurately predict the drill bit sticking situation in Permian igneous rocks and improve the guidance mechanism of horizontal wells during drilling is one of the issues that technicians in this field are studying. Summary of the invention

[0015] The present invention aims at the problem that the prior art lacks the accurate prediction of the drill stuck section of Permian igneous rock using a machine learning method, and provides a method for predicting the drill stuck section of Permian igneous rock and its application.

[0016] To achieve the above purpose, the technical solution adopted by the present invention is as follows:

[0017] A method for predicting pipe sticking in Permian igneous rocks comprises the following steps:

[0018] S1. Collect the drilling data and seismic data in the work area;

[0019] S2. Based on the drilling data and seismic data collected in step S1, perform well seismic calibration;

[0020] S3. Based on the well-seismic calibration performed in step S2, calibrate the position of the Permian igneous rock on the seismic profile;

[0021] S4. Based on the position of the Permian-Carboniferous interface on the seismic profile calibrated in step S3, summarize the reflection characteristics of the Permian igneous rocks;

[0022] S5. Compare the reflection characteristics of the Permian igneous rock summarized in step S4 with the reflection characteristics of the well to be drilled, and predict the stuck section of the Permian igneous rock of the well to be drilled.

[0023] Preferably, the drilling data in step S1 include acoustic wave time difference, density logging curve, Permian interface depth, Carboniferous interface depth, Silurian interface depth, Permian igneous rock lithology and Permian igneous rock depth data.

[0024] Preferably, the seismic data in step S1 include seismic time migration data, interpreted Permian top surface stratum data and interpreted Carboniferous top surface stratum data.

[0025] Preferably, synthetic seismic records need to be produced before the well seismic calibration in step S2.

[0026] Further preferably, the synthetic seismic record is performed using Landmark software.

[0027] Most preferably, the data required for the synthetic seismic record includes: the acoustic wave time difference and density curve in the drilling data in step S1.

[0028] Preferably, the data required for the well seismic calibration in step S2 includes: the drilling data and seismic data described in step S1.

[0029] Further preferably, the drilling data include sonic time difference, density logging curve, Permian interface depth, Carboniferous interface depth, Silurian interface depth, Permian igneous rock lithology and Permian igneous rock depth data.

[0030] More preferably, the seismic data include seismic time migration data, interpreted Permian top surface stratum data and interpreted Carboniferous top surface stratum data.

[0031] Preferably, the basis for the summary in step S4 is: reflection intensity, continuity and the depth of the Permian igneous rock actually drilled.

[0032] Preferably, the reflection features referenced by the comparison in step S5 are specifically: reflection intensity and continuity.

[0033] Preferably, the prediction method in step S5 is: the higher the degree of similarity between the reflection characteristics of the Permian igneous rock summarized in step S4 and the reflection characteristics of the well to be drilled, the higher the risk of pipe sticking caused by the Permian igneous rock.

[0034] The present invention also provides application of the above method for predicting pipe sticking in Permian igneous rocks in drilling.

[0035] Compared with the prior art, the present invention has the following beneficial effects:

[0036] The present invention uses the reflection characteristics of Permian igneous rocks through the drilling data and seismic data of the wells that have been drilled to predict the pipe sticking situation of Permian igneous rocks during the drilling process, thereby improving the utilization rate of data. The method is simpler and more intuitive, and can effectively improve the timeliness and efficiency of pipe sticking warning when a horizontal well encounters a convex structure or a concave structure under complex geological conditions containing Permian igneous rocks, thereby ensuring the normal progress of the project. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 A flow chart of a method for predicting stuck pipe in Permian igneous rocks according to the present invention;

[0038] Figure 2 Schematic diagram of predicted distribution of Permian igneous rocks according to an embodiment of the present invention. DETAILED DESCRIPTION

[0039] The following will describe the implementation methods of the present invention in detail in conjunction with the accompanying drawings and embodiments, so that the implementers of the present invention can fully understand how the present invention applies technical means to solve technical problems and achieve the implementation process of technical effects and implement the present invention specifically according to the above implementation process. It should be noted that as long as there is no conflict, the various embodiments and various features of the embodiments in the present invention can be combined with each other, and the technical solutions formed are all within the protection scope of the present invention.

[0040] Unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "including" or "comprising" and the like used in the present disclosure mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0041] Embodiment A method for predicting stuck pipe in Permian igneous rocks

[0042] S1. Collect the drilling data and seismic data in the work area;

[0043] The drilling data include acoustic wave time difference, density logging curve, Permian interface depth, Carboniferous interface depth, Silurian interface depth, Permian igneous rock lithology and Permian igneous rock depth data;

[0044] The seismic data include seismic time migration data, interpreted Permian top surface horizon data and interpreted Carboniferous top surface horizon data;

[0045] S2. Complete well-seismic calibration based on the collected drilling data and seismic data in the work area;

[0046] Using the logging acoustic time difference and density data curves on the conventional seismic comprehensive interpretation software Landmark, synthetic seismic records are produced;

[0047] On the basis of the synthetic seismic record that has been produced, well seismic calibration is performed according to the drilled well data and seismic data in step S1;

[0048] The drilling data include acoustic wave time difference, density logging curve, Permian interface depth, Carboniferous interface depth, Silurian interface depth, Permian igneous rock lithology and Permian igneous rock depth data;

[0049] The seismic data include seismic time migration data, interpreted Permian top surface horizon data and interpreted Carboniferous top surface horizon data;

[0050] S3. Based on well-seismic calibration, calibrate the position of the Permian-Carboniferous interface on the seismic profile;

[0051] S4. Based on the position of the Permian-Carboniferous interface on the seismic profile calibrated in step S3, summarize the reflection characteristics of the Permian igneous rocks;

[0052] After completing synthetic seismic records and well seismic calibration, it is concluded that the seismic reflection characteristics of basalt are high reflection intensity and strong continuity;

[0053] The summary process also needs to be combined with the lithology data obtained from the actual drilling corresponding to the reflection characteristics;

[0054] S5. comparing the reflection characteristics of the Permian igneous rock summarized in step S4 with the reflection characteristics of the well to be drilled, and predicting the drilling section of the Permian igneous rock to be drilled;

[0055] By pulling the seismic profile of the well to be drilled and observing the reflection characteristics, if it is continuous and strong, it is predicted that the Permian system of the well to be drilled has basalt. Basalt is hard and brittle, and it is easy for blocks to fall off and the drill to get stuck during the drilling process. It is predicted that the Permian basalt section of the well to be drilled is prone to drill sticking.

[0056] Figure 2 The distribution diagram of the Permian igneous rock of the present invention is shown to illustrate the distribution of the Permian igneous rock and the relationship between the distribution of the Permian basalt and the drilling section stuck by the Permian igneous rock.

[0057] As can be seen from the figure, the range where the stuck drill may occur is preliminarily determined by the top surface of the Permian and Carboniferous systems, i.e., the range between the top surfaces of the Permian and Carboniferous systems;

[0058] Further, according to the reflection characteristics in step S4 and the lithology data of the actual drilling, the reflection characteristics corresponding to the actual drilling lithology of basalt are determined; and then the position of basalt (Permian igneous rock) is determined by similar reflection characteristics, and the reflection characteristics of basalt are summarized;

[0059] Then determine the location of the well to be drilled on the seismic profile, compare the reflection characteristics in the drilling route with the reflection characteristics summarized in S4, and complete the prediction of the possible distribution range of basalt.

[0060] Finally, it should be noted that the above content is only used to illustrate the technical solution of the present invention, rather than to limit the scope of protection of the present invention. Simple modifications or equivalent substitutions of the technical solution of the present invention by ordinary technicians in this field do not deviate from the essence and scope of the technical solution of the present invention.

Claims

1. A method for predicting stuck pipe in Permian igneous rocks, It is characterized in that The following steps are involved: S1. Collect the drilling data and seismic data in the work area; S2. Based on the drilling data and seismic data collected in step S1, well seismic calibration and production of synthetic seismic records; S3. Based on the well seismic calibration and synthetic seismic records produced in step S2, calibrate the position of the Permian and Carboniferous interfaces on the seismic profile; S4. Based on the position of the Permian-Carboniferous interface on the seismic profile calibrated in step S3, summarize the reflection characteristics of the Permian igneous rocks; S5. Compare the reflection characteristics of the Permian igneous rock summarized in step S4 with the reflection characteristics of the well to be drilled, and predict the stuck section of the Permian igneous rock of the well to be drilled.

2. The method according to claim 1, Features: The drilling data in step S1 include acoustic wave time difference, density logging curve, Permian interface depth, Carboniferous interface depth, Silurian interface depth, Permian igneous rock lithology and Permian igneous rock depth data.

3. The method according to claim 1, Features: The seismic data in step S1 include seismic time migration data, interpreted Permian top surface stratum data and interpreted Carboniferous top surface stratum data.

4. The method according to claim 1, Features: Before the well-seismic calibration described in step S2, synthetic seismic records need to be produced.

5. The method according to claim 4, Features: The synthetic seismic record is performed using Landmark software.

6. The method according to claim 5, Features: The data required for synthesizing seismic records include: the acoustic wave time difference and density curve in the drilling data in step S1.

7. The method according to claim 1, Features: The data required for the well seismic calibration in step S2 include: the drilling data and seismic data described in step S1.

8. The method according to claim 7, Features: The drilling data include acoustic wave time difference, density logging curve, Permian interface depth, Carboniferous interface depth, Silurian interface depth, Permian igneous rock lithology and Permian igneous rock depth data.

9. The method according to claim 7, Features: The seismic data includes seismic time migration data, interpreted Permian top surface horizon data, and interpreted Carboniferous top surface horizon data.

10. The method according to claim 1, Features: The basis for the summary in step S4 is: reflection intensity, continuity and the depth of the Permian igneous rock actually drilled.

11. The method according to claim 1, Features: The reflection features referenced by the comparison in step S5 are specifically: reflection intensity and continuity.

12. The method according to claim 1, Features: The prediction method in step S5 is: the higher the degree of similarity between the reflection characteristics of the Permian igneous rock summarized in step S4 and the reflection characteristics of the well to be drilled, the higher the risk of pipe sticking caused by the Permian igneous rock.

13. Use of the method according to any one of claims 1 to 12 in drilling.

Images