A method for online optimization of drilling parameters
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SOUTHWEST PETROLEUM UNIV
- Filing Date
- 2024-10-25
- Publication Date
- 2026-07-14
Smart Images
Figure CN119312688B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of oil and gas drilling technology, and in particular to a method for online optimization of drilling parameters. Background Technology
[0002] During actual drilling, due to the uncertainty and time-varying nature of drilling conditions, the mechanical drilling rate prediction model exhibits dynamic characteristics. Constraints such as stick-slip vibration also exhibit dynamic changes. The objective function and constraints of the mechanical drilling rate optimization problem change over time. There are dynamic optimal solutions under different drilling conditions. The solution to the problem will expand or shrink over time, and the new solution may become better or worse in the process of problem evolution.
[0003] The characteristic of dynamic drilling parameter optimization problems is that drilling data is obtained gradually, and the algorithm makes real-time decisions based on currently known information at each time step. In contrast, static drilling parameter optimization design can obtain all information at the beginning of the solution, especially after drilling conditions change. Real-time drilling parameter optimization can only observe a portion of the drilling data at each time step and cannot know all the information in advance.
[0004] Therefore, this invention integrates drilling engineering with artificial intelligence algorithms and proposes an online optimization method for drilling parameters, which can dynamically optimize drilling parameters according to changes in drilling conditions, and is of great significance for realizing intelligent drilling. Summary of the Invention
[0005] The online optimization method for drilling parameters provided by this invention has the following specific technical solution:
[0006] The core idea of the online drilling parameter optimization method of this invention is to abstract the dynamic optimization problem of drilling parameters into a time-varying dynamic optimization problem. Its goal is to find x(t) over the entire time-varying process such that F(x,t) is minimized under given constraints, as expressed by the following formula:
[0007] minF(x,t)=(f1(x,t),...,f mt (x,t)) T
[0008] stg i (x,t)≤0,i=1,2,...,p
[0009] h j (x,t)=0,j=1,2,...,q
[0010] x∈Ω x ,t∈Ω t
[0011] In the formula: fmt (x,t) represents the mt-th objective function at time t, specifically representing the mechanical drilling rate prediction model.
[0012] x = (x1, x2, ... x) nt ) T The decision optimization variable representing dimension nt, x, has a range of values that varies over time, x = (x1, x2, ... x). nt ) T Specifically, these represent drilling parameters including drill pressure, rotation speed, and displacement.
[0013] F(x,t) represents the objective function vector for evaluating solution x at time t.
[0014] g i (x,t) represents the inequality constraints, which change over time; h j (x,t) represents the equality constraint, which changes with time; i and j represent multiple constraints, including but not limited to drill pressure constraint, rotation speed constraint, mechanical drilling speed constraint, and stick-slip vibration constraint.
[0015] Ω x This represents the space of feasible decision variables, specifically the space of decision variables for drilling parameter adjustments.
[0016] Ω t Represents time and space, specifically the time range for optimizing drilling parameters.
[0017] The online optimization method for drilling parameters of the present invention comprises the following steps:
[0018] S1. Obtain quasi-dynamic data from the drilling log and preprocess the real-time logging data from the drilling site.
[0019] Based on real-time logging data from the drilling site, fixed-frequency data such as drilling pressure, rotational speed, displacement, and mechanical drilling speed are obtained, and real-time drilling data is dynamically preprocessed, including the removal of data anomalies and data smoothing and noise reduction.
[0020] The quasi-dynamic data obtained from the drilling log includes drill string assembly data, wellbore structure data, wellbore trajectory data, and drilling fluid density data.
[0021] S2. Train the mechanical drilling rate prediction model and update the objective function based on the adaptive random forest algorithm; details are as follows:
[0022] Based on the adaptive random forest algorithm, with drilling pressure, rotational speed, and displacement as input feature variables, and mechanical drilling rate as output feature variable, the algorithm learns online from preprocessed real-time drilling data to train and update the mechanical drilling rate prediction model, i.e., updates the objective function f(x,t) in real time, as follows:
[0023] f(x,t m → f(x,t) n )
[0024] f(x,t m ) represents t m The objective function at time t; f(x,t) n ) represents t n The objective function at time t.
[0025] S3. Update drilling parameter constraints:
[0026] Considering quasi-dynamic data such as drill string assembly data, wellbore structure data, wellbore trajectory data, and drilling fluid density data, as well as changes in formation properties, update the constraint condition g. i (x,t) and h j (x,t), calculate the critical drilling pressure, critical mechanical drilling rate, and stick-slip vibration constraint conditions. Represented as follows:
[0027] g i (x,t m )≤0→g i (x,t n )≤0
[0028] h j (x,t m )=0→h j (x,t n ) = 0
[0029] In the formula, g i (x,t m ) represents t m Inequality constraints at time; g i (x,t n ) represents t n Inequality constraints at time; h j (x,t m ) represents t m Equality constraints at time; h j (x,t n ) represents t n Equality constraints at any given time.
[0030] S4. Update the decision variable space:
[0031] Considering the range of drilling parameters and potential errors in the computational model, the decision variable space is fine-tuned and updated within the range of existing data; as shown below:
[0032] x∈Ω xm →x∈Ω xn
[0033] In the formula, Ω xm Represents t m The space of decision variables at time Ω xn Represents t n The decision variable space at time.
[0034] S5, Particle Swarm Optimization
[0035] Based on the established mechanical drilling rate prediction model, the drilling parameter optimization problem is solved using the particle swarm optimization algorithm under the constraint of drilling parameters, and the optimized drilling parameters, namely drilling pressure, rotation speed and displacement, are obtained.
[0036] S6. Repeat steps S1 to S5, updating the objective function, drilling parameter constraints, and decision variable space in time and space, and solving for the optimal drilling parameter scheme under the current drilling conditions.
[0037] Compared with the prior art, the advantages of the present invention are:
[0038] (1) This invention integrates drilling engineering with artificial intelligence algorithms and proposes an online optimization method for drilling parameters, which can dynamically optimize drilling parameters according to changes in drilling conditions, and is of great significance for realizing intelligent drilling.
[0039] (2) This invention can be applied directly to existing conventional drilling equipment without the need for additional downhole measurement tools.
[0040] Other advantages, objectives and features of the present invention will be apparent in part from the following description, and in part from what those skilled in the art will understand through study and practice of the invention. Attached Figure Description
[0041] Figure 1 This is a flowchart of the online optimization method for drilling parameters according to the present invention.
[0042] Figure 2 This is a schematic diagram illustrating the principle of the online optimization method for drilling parameters according to the present invention.
[0043] Figure 3 The results of online optimization of drilling parameters are shown in the example. Detailed Implementation
[0044] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.
[0045] like Figure 1 and 2 As shown, the online optimization method for drilling parameters of the present invention comprises the following detailed steps:
[0046] S1. Data Acquisition and Preprocessing
[0047] (1) Obtain fixed-frequency drilling pressure, rotation speed, displacement and mechanical drilling speed based on real-time logging data at the drilling site, and dynamically preprocess real-time drilling data, including the removal of data anomalies and data smoothing and noise reduction; (2) Obtain quasi-dynamic data based on drilling logs, including drill string assembly data, wellbore structure data, wellbore trajectory data and drilling fluid density data.
[0048] S2, Objective Function Update
[0049] Based on the adaptive random forest algorithm, using drilling pressure, rotational speed, and displacement as input feature variables, and mechanical drilling rate as output feature variable, the algorithm learns online from preprocessed real-time drilling data to train and update the mechanical drilling rate prediction model, and updates the objective function in real time. This can be represented as:
[0050] f(x,t m → f(x,t) n )
[0051] f(x,t m ) represents t m The objective function at time t; f(x,t) n ) represents t n The objective function at time t.
[0052] S3, Constraint Update
[0053] Considering quasi-dynamic data such as drill string assembly data, wellbore structure data, wellbore trajectory data, and drilling fluid density data, as well as changes in formation properties, the constraints are updated, and the critical drilling pressure, critical mechanical drilling rate, and stick-slip vibration constraints are calculated. This can be expressed as:
[0054] g i (x,t m )≤0→g i (x,t n )≤0
[0055] h j (x,t m )=0→h j (x,t n ) = 0
[0056] In the formula, g i (x,t m ) represents t m Inequality constraints at time; g i (x,t n ) represents t n Inequality constraints at time; h j (x,t m ) represents t mEquality constraints at time; h j (x,t n ) represents t n Equality constraints at time points. i and j represent specific constraints.
[0057] Taking the stick-slip vibration constraint condition as an example, the stick-slip vibration constraint condition is related to the drill string assembly, wellbore trajectory, drilling fluid density, wellbore structure, etc. Assume t m The drill string assembly, wellbore trajectory, drilling fluid density, and wellbore structure at any given time can be represented as data. m , t m The stick-slip vibration constraint condition at time t is: g(x,data) m )≤0; in t n The drill string assembly, wellbore trajectory, drilling fluid density, and wellbore structure data changed at any given time, as per the data... m Transform into data n , then t n The stick-slip vibration constraint condition at time t is g(x,data) n )≤0.
[0058] From t m Time to t n The update of the stick-slip vibration constraint conditions at any given time can be expressed as:
[0059] g(x,data m )≤0→g(x,data n )≤0
[0060] S4. Decision Variable Space Update
[0061] Considering the adjustable range of drilling parameters and potential errors in the computational model, the adjustable range of decision variables should, in principle, be fine-tuned within the range of existing data. This can be expressed as:
[0062] x∈Ω xm →x∈Ω xn
[0063] In the formula, Ω xm Represents t m The space of decision variables at time Ω xn Represents t n The decision variable space at time.
[0064] S5, Particle Swarm Optimization
[0065] Based on the established mechanical drilling rate prediction model, the particle swarm optimization algorithm is used to solve the drilling parameter optimization problem under the constraint of drilling parameters, and the optimized drilling parameters, namely drilling pressure, rotation speed and displacement, are obtained.
[0066] S6. Repeat steps S1 to S5, updating the objective function, constraints, and decision variable space in time and space, and solving for the optimal drilling parameter scheme under the current drilling conditions.
[0067] Specific application cases
[0068] The online drilling parameter optimization method of the present invention was applied and tested in the 1740m-1750m section of the PLH2 well. The test results are as follows: Figure 3 As shown in the figure, in the 1740m-1743m well section, the mechanical drilling rate increases with the increase of drilling pressure; this method indicates that increasing drilling pressure is beneficial to increasing the mechanical drilling rate.
[0069] At this point, the mechanical drilling rate prediction model, i.e., the objective function, can be expressed as:
[0070] ROP = a * WOB α +b*RPM β +c*FLOW γ Clearly, a > 0;
[0071] In the formula, ROP is the mechanical drilling rate, m / h; WOB is the drilling pressure, kN; RPM is the rotational speed, r / min; FLOW is the displacement, L / s; a, b, and c are equation coefficients; and α, β, and γ are the drilling pressure index, rotational speed index, and flow rate index, respectively.
[0072] However, in the subsequent 1743m to 1750m section, the mechanical drilling rate increased significantly as the drilling pressure decreased.
[0073] At this point, the mechanical drilling rate prediction model, i.e., the objective function, can be expressed as:
[0074] ROP = a * WOB α +b*RPM β +c*FLOW γ Clearly, a < 0;
[0075] This is clearly because changes in formation or other downhole conditions cause changes in the rate of drilling equation. However, as can be seen from the figure, the recommended drilling pressure also shows a change from increasing to decreasing. In other words, the algorithm adapts to changes in drilling conditions by updating the mechanical rate of drilling model, and can optimize drilling parameters under dynamic drilling conditions.
[0076] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes, and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.
Claims
1. A method for online optimization of drilling parameters, characterized in that, The dynamic optimization problem of drilling parameters is abstracted into a time-varying dynamic optimization problem, the goal of which is to find the optimal parameters over the entire time period. , making Minimize under given constraints, as expressed by the following formula: In the formula: Represents time The next Each objective function specifically represents the mechanical drilling rate prediction model. represent Dimensional decision optimization variables The range of values for varies over time. Specifically, these represent drilling parameters including drill pressure, rotation speed, and displacement. Representing time Evaluation Solution The objective function vector; This represents the inequality constraints, which change over time. This represents the equality constraint, which changes over time. i and j This indicates that there are multiple constraints, including but not limited to drill pressure constraints, rotation speed constraints, mechanical drilling speed constraints, and stick-slip vibration constraints. This represents the decision variable space, specifically the decision variable space for adjusting the drill parameters; Represents time and space, specifically referring to the time range for drilling parameter optimization; The steps of this method are as follows: S1. Obtain quasi-dynamic data from the drilling log, and preprocess the real-time logging data from the drilling site. S2. Train the mechanical drilling rate prediction model based on the adaptive random forest algorithm and update the objective function: Based on the adaptive random forest algorithm, this method uses real-time well logging data as input feature variables and mechanical drilling rate as output feature variables. It trains and updates the mechanical drilling rate prediction model online using preprocessed real-time well data, thus updating the objective function in real time. , is represented as: represent The objective function at time t; represent The objective function at time t; S3. Update drilling parameter constraints: Considering quasi-dynamic data and changes in stratigraphic properties, update constraints. and Calculate the critical drilling pressure, critical mechanical drilling speed, and stick-slip vibration constraint conditions; S4. Update the decision variable space: Considering the range of drilling parameters and the errors in the calculation model, the decision variable space is adjusted and updated within the range of existing data. S5, Particle Swarm Optimization Based on the established mechanical drilling rate prediction model, the drilling parameter optimization problem is solved using the particle swarm optimization algorithm under the constraint of drilling parameters, and the optimized drilling parameters, namely drilling pressure, rotation speed and displacement, are obtained. S6. Repeat steps S1 to S5, updating the objective function, drilling parameter constraints, and decision variable space in time and space, and solving for the optimal drilling parameter scheme under the current drilling conditions.
2. The online optimization method for drilling parameters as described in claim 1, characterized in that, In step S1, drilling pressure, rotation speed, displacement, and mechanical drilling speed at a fixed frequency are obtained based on real-time logging data from the drilling site, and the real-time drilling data is dynamically preprocessed, including the removal of data anomalies and data smoothing and noise reduction.
3. The online optimization method for drilling parameters as described in claim 1, characterized in that, In step S1, the quasi-dynamic data includes drill string assembly data, wellbore structure data, wellbore trajectory data, and drilling fluid density data.
4. The online optimization method for drilling parameters as described in claim 2, characterized in that, In step S2, drilling pressure, rotation speed, and displacement are used as input feature variables, and mechanical drilling speed is used as output feature variable.
5. The online optimization method for drilling parameters as described in claim 1, characterized in that, In step S3, the constraints are updated as follows: In the formula, represent Inequality constraints at time points; represent Inequality constraints at time points; represent Equality constraints at any given time; represent Equality constraints at any given time.
6. The online optimization method for drilling parameters as described in claim 1, characterized in that, In step S4, the decision variable space is updated, as shown below: In the formula, represent The space of decision variables at any given time; represent The space of decision variables at any given time.