Method and apparatus for determining jetting displacement for deep water surface conductor well construction

Abstract

The specification relates to the technical field of deepwater oil and gas field development, and particularly discloses a method and device for determining the jet displacement of a deepwater surface conduit well construction process, wherein the method comprises: obtaining drilling parameters and formation property parameters of a deepwater surface jet well construction operation; determining the correlation between the jet displacement and the rate of penetration based on the drilling parameters and the formation property parameters by using a target BP neural network; establishing a surface bearing capacity recovery curve according to the drilling parameters and the formation property parameters by using a target long short-term memory neural network; the surface bearing capacity recovery curve is a curve of the surface bearing capacity changing with time; and calculating the target jet displacement based on the correlation between the jet displacement and the rate of penetration and the surface bearing capacity recovery curve by using a particle swarm optimization algorithm. The above scheme can determine the optimal jet displacement of the deepwater surface conduit well construction, has reference significance for deepwater surface well construction design, and improves the safety and efficiency of deepwater surface efficient drilling.

Description

TECHNICAL FIELD

[0001] The present specification relates to the technical field of deepwater oil and gas field development, in particular to a method and device for determining the jet displacement of a surface conductor installation process of a deepwater surface conductor. BACKGROUND

[0002] Deep-sea oil and gas is an important energy source and has received increasing attention worldwide. The development and exploitation of deepwater oil and gas fields not only have significant economic benefits, but also have very broad resource potential. With the continuous progress of marine engineering operation technology and offshore oil and gas exploration and development technology, the development of deepwater oil and gas resources has become more feasible and economical. The development of these technologies not only improves the efficiency of exploration and development and reduces greenhouse gas emissions, but also reduces input costs, making the development of deepwater oil and gas resources more attractive.

[0003] The surface conductor is the first layer of pipe column on the seabed of deep-sea oil and gas development, and subsequent drilling operations provide a stable starting point, ensuring the passage of drilling fluid, drilling tools, production, testing, and oil and gas. Surface conductor installation is an important process of deepwater drilling. In the surface conductor installation, the drilling and cementing method, suction pile, and jet method are usually used to install the surface conductor. The drilling and cementing method requires complex drilling tools and a long operation cycle, and the cementing cement is very easy to pollute the seabed environment. The suction pile method is subject to soil properties and topographic conditions, and the stability is seriously affected in strong sea currents. The jet method installs the surface conductor in place without cementing, relying on the surrounding seabed soil backfill and compaction to provide bearing capacity to maintain stability. The jet method can quickly complete the wellhead installation and produce less waste, with the advantages of adapting to various seabed soil types, environmental protection, and efficient operation, and is widely welcomed in deepwater surface installation.

[0004] The principle of the jet method for installing the surface conductor is to use water jet to break the soil and form a borehole. After the surface conductor is installed in place, it relies on the soil to provide bearing capacity to maintain stability. If the jet hydraulic parameters are too small, the jet forms a borehole diameter smaller than the surface conductor diameter, which seriously affects the jet operation efficiency, as shown in (a) of Figure 1 If the jet hydraulic parameters are too large, the jet forms a borehole diameter significantly larger than the surface conductor diameter, and a longer standing time is needed to ensure that the soil can stably bear the conductor, as shown in (b) of Figure 1After the installation of the conduit, a waiting time is required, which is usually obtained by experience and lacks specific guidance. Too long waiting time increases the engineering cost, and too long platform positioning wastes fuel and produces greenhouse gas. Too short waiting time will cause the conduit to sink, resulting in a failed operation. Therefore, accurately controlling the drilling jet flow rate is the key to safe, efficient and environmentally friendly drilling. However, the prior art cannot accurately control the drilling jet flow rate to balance the efficient conduit installation operation and the shortest safe waiting time in the deep water surface conduit well construction process.

[0005] At present, there is no effective solution to the above problems. SUMMARY

[0006] The embodiments of the present specification provide a method and device for determining the jet flow rate of a deep water surface conduit well construction process, to solve the problem that the prior art cannot accurately control the drilling jet flow rate to balance the efficient conduit installation operation and the shortest safe waiting time in the deep water surface conduit well construction process.

[0007] The embodiments of the present specification provide a method for determining the jet flow rate of a deep water surface conduit well construction process, comprising:

[0008] Obtaining drilling parameters and formation property parameters of a deep water surface jet well construction operation;

[0009] Using a target BP neural network, determining the correlation between the jet flow rate and the rate of penetration based on the drilling parameters and the formation property parameters;

[0010] Using a target long short-term memory neural network, establishing a surface bearing capacity recovery curve according to the drilling parameters and the formation property parameters; the surface bearing capacity recovery curve is a curve of the change of the surface bearing capacity with time;

[0011] Using a particle swarm optimization algorithm, calculating a target jet flow rate based on the correlation between the jet flow rate and the rate of penetration and the surface bearing capacity recovery curve.

[0012] In one embodiment, the target BP neural network is constructed by the following method:

[0013] According to the physical relationship between the jet flow rate and the rate of penetration, the structure of the BP neural network and the number of neurons of the input layer, the hidden layer and the output layer included in the BP neural network are determined;

[0014] Collect drilling parameters and geological parameters; train the BP neural network using the collected data to obtain the target BP neural network; in the training process, the network weight of the BP neural network is adjusted through iterative optimization, so that the correlation between the jet discharge and the penetration rate output by the BP neural network is close to the actual relationship between the jet discharge and the penetration rate.

[0015] In one embodiment, the target long short-term memory neural network is constructed by:

[0016] determining the structure of the long short-term memory neural network and the number and layers of long short-term memory units;

[0017] Collect jet drilling parameters and waiting time; train the long short-term memory neural network using the collected jet drilling parameters and waiting time to obtain the target long short-term memory neural network; in the training process, the network weight of the long short-term memory neural network is adjusted through iterative optimization, so that the output of the long short-term memory neural network is close to the actual bearing capacity data.

[0018] In one embodiment, a target long short-term memory neural network is used to establish a surface bearing capacity recovery curve according to the drilling parameters and formation property parameters, including:

[0019] According to the bearing capacity data output by the target long short-term memory neural network, a surface bearing capacity recovery curve is established;

[0020] According to the surface bearing capacity recovery curve, the static waiting time during the jet drilling waiting period is determined, which is the shortest waiting time to ensure the safety of deep water surface jet well construction operation.

[0021] In one embodiment, a particle swarm optimization algorithm is used to calculate the target jet discharge based on the correlation between the jet discharge and the penetration rate and the surface bearing capacity recovery curve, including:

[0022] A group of randomly generated particles is initialized, and the fitness of each group of particles is calculated according to the performance index; each particle is used to represent a jet drilling scheme, which includes the combination of corresponding jet discharge and static waiting time;

[0023] According to the historical best position and global best position of each particle, its speed and position are updated, the new position of each particle is evaluated, and its fitness is calculated; if the fitness of the current particle is better than its historical best position, the individual best position is updated; if the fitness of the current particle is better than the global best position, the global best position is updated, and the iteration is continuously performed until the preset number of iterations is met or the fitness threshold is reached;

[0024] The global optimal position is output, and optimal solutions for a jetting drilling installation stage and a static waiting stage are obtained.

[0025] In one embodiment, after the target jetting discharge is calculated based on the correlation between the jetting discharge and the rate of penetration and the surface load capacity recovery curve by using the particle swarm optimization algorithm, the method further includes:

[0026] According to the target jetting discharge and the correlation between the jetting discharge and the rate of penetration, a corresponding target rate of penetration is determined.

[0027] Based on the target jetting discharge, the target rate of penetration and the surface load capacity recovery curve, a shortest well construction time and a real-time load capacity of the conduit during the waiting period are calculated.

[0028] The embodiments of the present specification also provide a device for determining a jetting discharge in a deep water surface conduit well construction process, comprising:

[0029] An acquisition module is configured to acquire drilling parameters and formation property parameters of a deep water surface jetting well construction operation.

[0030] A determination module is configured to determine a correlation between a jetting discharge and a rate of penetration based on the drilling parameters and the formation property parameters by using a target BP neural network.

[0031] An establishment module is configured to establish a surface load capacity recovery curve according to the drilling parameters and the formation property parameters by using a target long short-term memory neural network; the surface load capacity recovery curve is a curve of the surface load capacity changing with time.

[0032] A calculation module is configured to calculate a target jetting discharge based on the correlation between the jetting discharge and the rate of penetration and the surface load capacity recovery curve by using a particle swarm optimization algorithm.

[0033] The embodiments of the present specification also provide a computer device, comprising a processor and a memory for storing processor-executable instructions, wherein the processor executes the instructions to implement the steps of the method for determining a jetting discharge in a deep water surface conduit well construction process according to any of the above embodiments.

[0034] The embodiments of the present specification also provide a computer-readable storage medium having computer instructions stored thereon, wherein the instructions are executed to implement the steps of the method for determining a jetting discharge in a deep water surface conduit well construction process according to any of the above embodiments.

[0035] The embodiments of the present specification also provide a computer program product comprising computer programs / instructions, wherein the computer programs / instructions are executed by a processor to implement the steps of the method for determining a jetting discharge in a deep water surface conduit well construction process according to any of the above embodiments.

[0036] In an embodiment of the present specification, a method for determining the jet discharge capacity in the process of building a deep water surface string is provided, a target BP neural network is used to determine the correlation between the jet discharge capacity and the rate of penetration based on the drilling parameters and the formation property parameters, a target long short-term memory neural network is used to establish a surface string bearing capacity recovery curve according to the drilling parameters and the formation property parameters; the surface string bearing capacity recovery curve is a curve of the surface string bearing capacity changing with time, and a particle swarm optimization algorithm is used to calculate the target jet discharge capacity based on the correlation between the jet discharge capacity and the rate of penetration and the surface string bearing capacity recovery curve. In the above scheme, in the process of building a deep water surface string, the jet discharge capacity of the surface string is optimized by using the BP neural network to control the rate of penetration, the long short-term memory neural network is used to predict the surface string bearing capacity recovery with a confidence interval, the particle swarm optimization algorithm is used to optimize the discharge capacity to obtain the optimal flow rate of the deep water surface string building, and the actual drilling case is verified, which effectively balances the efficient string installation operation and the shortest safe waiting time in the process of building a deep water surface string, provides a new method for the traditional deep water surface string building relying on experience, has reference significance for the design of deep water surface string building, and improves the safety and efficiency of deep water surface string building. BRIEF DESCRIPTION OF DRAWINGS

[0037] The drawings described herein are used to provide further understanding of the present specification, constitute a part of the present specification, and do not constitute a limitation to the present specification. In the drawings:

[0038] Figure 1 A schematic diagram of a jet method for installing a surface string is shown;

[0039] Figure 2 A flowchart of a method for determining the jet discharge capacity in the process of building a deep water surface string in an embodiment of the present specification is shown;

[0040] Figure 3 A flowchart of determining the upper limit and the lower limit of the jet discharge capacity based on the principles of fluid mechanics and soil mechanics in an embodiment of the present specification is shown;

[0041] Figure 4 A schematic diagram of a BP neural network in an embodiment of the present specification is shown;

[0042] Figure 5 A calculation principle diagram of a particle swarm optimization algorithm in an embodiment of the present specification is shown;

[0043] Figure 6 A whole flowchart of a method for determining the jet discharge capacity in the process of building a deep water surface string in an embodiment of the present specification is shown;

[0044] Figure 7 FIG. 1 shows a schematic diagram of an apparatus for determining the jetting displacement of a deep water surface conductor well construction process according to an embodiment of the present specification;

[0045] Figure 8 FIG. 2 shows a schematic diagram of a computer device according to an embodiment of the present specification. DETAILED DESCRIPTION

[0046] The principles and spirits of the present specification will be described below with reference to several exemplary embodiments. It should be understood that the embodiments are given only so that those skilled in the art can better understand and implement the present specification, and do not limit the scope of the present specification in any way. On the contrary, the embodiments are provided so that the present specification disclosure is more thorough and complete, and the scope of the present disclosure is fully conveyed to those skilled in the art.

[0047] Those skilled in the art understand that the embodiments of the present specification can be implemented as a system, apparatus device, method or computer program product. Therefore, the present specification disclosure can be specifically implemented in the following forms, i.e., complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0048] The embodiments of the present specification provide a method for determining the jetting displacement of a deep water surface conductor well construction process. Figure 2 FIG. 1 shows a flow chart of a method for determining the jetting displacement of a deep water surface conductor well construction process according to an embodiment of the present specification. Although the present specification provides method operation steps or apparatus structures as described in the following embodiments or drawings, more or less operation steps or module units can be included in the method or apparatus based on convention or without creative labor. The execution order of the steps or the module structure of the apparatus is not limited to the execution order or module structure described in the embodiments of the present specification and shown in the drawings in the steps or structures without necessary causal relationship in logic. When the method or module structure is applied to the actual apparatus or terminal product, it can be sequentially executed or executed in parallel (for example, parallel processor or multi-thread processing environment, even distributed processing environment) according to the method or module structure shown in the embodiments or drawings.

[0049] Specifically, as shown in FIG. 1, the method for determining the jetting displacement of a deep water surface conductor well construction process according to an embodiment of the present specification can include the following steps: Figure 2

[0050] Step S201, obtaining drilling parameters and formation property parameters of a deep water surface jetting well construction operation.

[0051] ​The surface conduit is the first string of the subsea in the deepwater oil and gas development, and subsequent drilling operations provide a stable starting point, which is a channel to ensure the passage of drilling fluid, drilling tools, production, testing and oil and gas. The surface conduit installation is an important process of deepwater drilling. In the embodiment, the surface conduit is installed by using the jet method.

[0052] In the deepwater surface jet well construction operation to be studied, drilling parameters and formation property parameters can be obtained. The drilling parameters can include at least one of the following: drilling pressure, bit sticking out amount, jet displacement, drill bit water hole, etc. The formation property parameters can include at least one of the following: shear strength, recovery ability, friction property and fracture pressure, etc.

[0053] In step S202, a target BP neural network is used to determine the correlation between the jet displacement and the mechanical drilling speed based on the drilling parameters and the formation property parameters.

[0054] In the jet installation stage of the surface well construction, drilling parameters and geological conditions are affected by many factors, and the BP (Back Propagation) neural network has an advantage in fusing the influence of multiple factors and calculating the relationship between displacement and mechanical drilling speed. Therefore, after obtaining the drilling parameters and the formation property parameters of the deepwater surface jet well construction operation, a target BP neural network can be used to determine the correlation between the jet displacement and the mechanical drilling speed based on the drilling parameters and the formation property parameters. The target BP neural network can be a pre-trained BP neural network.

[0055] In some embodiments of the present specification, the target BP neural network is constructed by: determining the structure of the BP neural network and the number of neurons of the input layer, the hidden layer and the output layer included in the BP neural network according to the physical relationship between the jet displacement and the mechanical drilling speed; collecting drilling parameters and geological parameters; training the BP neural network using the collected data to obtain the target BP neural network; and adjusting the network weight of the BP neural network through iterative optimization during the training process, so that the correlation between the jet displacement and the mechanical drilling speed output by the BP neural network is close to the actual relationship between the jet displacement and the mechanical drilling speed.

[0056] Specifically, in drilling operations, the flow rate of the drilling fluid and the rate of penetration are interdependent and influence each other. Generally, the flow rate of the drilling fluid and the rate of penetration are positively correlated and nonlinear, because different geological conditions and drilling parameters and other factors will affect this relationship. The formation characteristics can include, for example, the hardness of the seabed map, the undrained shear strength, the porosity, the permeability, and the like. The drilling parameters can include the drilling fluid characteristics, the drill bit type and size, the drilling process parameters. The drilling fluid characteristics include the density, the viscosity, the flow rate, and the like. The drilling process parameters include the weight on bit, the rotation speed, the jet angle, and the like.

[0057] In the design of a deep water surface injection phase, a model based on a BP neural network is established to predict the relationship between the flow rate of the drilling fluid and the rate of penetration of the injection drilling. The drilling parameters and the geological parameters are collected, and the structure of the BP neural network is designed according to the relationship between the flow rate of the drilling fluid and the rate of penetration, including the number of neurons in the input layer, the hidden layer, and the output layer. The design of these layers takes into account the complexity of the input data and the nonlinear characteristics of the output relationship. The BP neural network is trained using the collected data.

[0058] Specifically, the number of neurons in the input layer of the BP neural network usually corresponds to the number of input features. The BP neural network mainly studies the influence of engineering operation parameters and geological parameters during drilling on the rate of penetration, and the drilling parameters represent the difficulty of drilling into and damaging the formation, and the formation parameters represent whether the formation is difficult to drill. In this embodiment, the input features can include formation parameters (such as rock hardness, porosity), drilling fluid parameters (such as density, viscosity), drill bit parameters (such as type, size), and other process parameters (such as weight on bit, flow rate), and the like. Each input feature corresponds to an input neuron, and these neurons pass data to the hidden layer.

[0059] The number of neurons in the hidden layer has no fixed rule and usually needs to be determined through experiments. The hidden layer can have one or more, and the number of neurons in each hidden layer can be different. The hidden layer is responsible for extracting features and patterns from the input data and processing the data through a nonlinear activation function (such as Sigmoid, ReLU, or Tanh) to capture the complex relationship between the input and the output. In theory, more hidden layers and neurons can capture more complex patterns, but can also cause overfitting, so it needs to be determined through experiments.

[0060] The output of the BP neural network is the rate of penetration. The BP neural network obtains the corresponding rate of penetration according to the input of different jet discharge capacities, so as to obtain the correlation between the discharge capacity and the drilling speed. According to the drilling speed, the drilling time of the jet drilling installation stage can be obtained. The output layer converts the data processed by the hidden layer into the final prediction result. For regression problems (such as predicting the rate of penetration), the output layer usually uses a linear activation function. In this way, a BP neural network can be designed which can not only handle the complexity of input data but also capture the nonlinear characteristics of the output relationship. This process requires some experience and multiple experiments to achieve the optimal network structure.

[0061] Through iterative optimization, the network weights are adjusted to make the output of the network close to the actual relationship between the drilling discharge capacity and the rate of penetration. Then, the trained BP neural network is tested using test data to verify the prediction performance of the network. This helps to evaluate the reliability and accuracy of the model. Finally, in the optimization network stage, the network structure or training parameters are adjusted according to the test results to further improve the prediction accuracy of the network and better adapt to the needs of actual drilling operations.

[0062] In step S203, a target long short-term memory neural network is used to establish a surface bearing capacity recovery curve according to the drilling parameters and the formation property parameters. The surface bearing capacity recovery curve is a curve of the surface bearing capacity changing with time.

[0063] A target long short-term memory (LSTM) neural network can be used to establish a surface bearing capacity recovery curve according to the drilling parameters and the formation property parameters. The surface bearing capacity recovery curve is a curve of the surface bearing capacity changing with time. The LSTM model can consider the influence of time series and accurately calculate the recovery of bearing capacity during the static waiting process, and determine the shortest waiting time to avoid excessive waiting, waste of energy and excessive emission of greenhouse gases, and too short waiting to cause safety accidents during the operation.

[0064] The BP neural network can be used to calculate the drilling time by the rate of penetration, and the LSTM neural network can be used to calculate the fine waiting time, so as to calculate the time of the entire jet drilling installation stage and the static waiting stage.

[0065] In some embodiments of the present specification, the target long short-term memory neural network is constructed by determining the structure of the long short-term memory neural network and the number and layers of long short-term memory units; collecting jet drilling parameters and waiting time; training the long short-term memory neural network using the collected jet drilling parameters and waiting time to obtain the target long short-term memory neural network; and in the training process, adjusting the network weights of the long short-term memory neural network through iterative optimization, so that the output of the long short-term memory neural network is close to the actual bearing capacity data.

[0066] In the calculation of the bearing force in real time during the waiting period of jet drilling, a surface bearing force recovery curve considering the confidence interval is established by the LSTM method to calculate the static waiting time during the waiting period of jet drilling. After the jet drilling parameters and the waiting time are collected, the structure of the LSTM network is designed, including the input layer, the LSTM layer, and the output layer. The number of LSTM units and the number of layers in the LSTM layer need to be adjusted according to the specific problem to adapt to the complexity of the data. The LSTM network is trained using engineering data, and the network weights are adjusted through iterative optimization to make the output of the network close to the actual bearing force data. According to the prediction results of the LSTM network, the confidence interval of the recovery curve of the surface bearing force changing with time is established to reflect the trend of the bearing force.

[0067] Specifically, the number of LSTM units usually corresponds to the number of input features. LSTM mainly studies the bearing force recovery during the static waiting period, which is mainly affected by geological parameters. Only the drilling discharge during drilling affects the recovery during the waiting period, which is manifested as excessive damage to the formation and slow recovery. The number of layers usually needs to be adjusted through experiments to find the best performance and balance of computing resources. The design of LSTM needs to consider the time dependence of the data. For example, the influence of drilling discharge on soil recovery (backfilling) may need to consider information at different time scales. Determine the input feature dimension, set the number of LSTM units. Determine the number of LSTM layers, each layer can have a different number of units. Determine the output layer structure, which is usually one or more neurons, used to predict the impact of discharge on soil recovery. Use time series data (discharge data) as input to train the LSTM model. Apply appropriate loss functions to optimize model parameters through backpropagation and gradient descent. Use the validation set to evaluate the performance of the model. Adjust the number of LSTM units and layers based on performance indicators such as prediction accuracy and overfitting.

[0068] In some embodiments of the present specification, a target long short-term memory neural network is used to establish a surface bearing force recovery curve based on the drilling parameters and formation property parameters, including: establishing a surface bearing force recovery curve based on the bearing force data output by the target long short-term memory neural network; determining the static waiting time during the waiting period of jet drilling based on the surface bearing force recovery curve, the static waiting time being the shortest waiting time to ensure the safety of deep water surface jet well construction operation. According to the bearing force recovery curve, the shortest waiting time during the waiting period of jet drilling is determined to ensure that the bearing capacity of the guide pipe is safe and not to waste the positioning of the operation platform by excessive waiting, ensuring the safety and efficiency of deep water surface well construction operation.

[0069] Step S204, using a particle swarm optimization algorithm, based on the correlation between the jet displacement and the mechanical drilling speed and the surface bearing capacity recovery curve, the target jet displacement is calculated.

[0070] After obtaining the correlation between the jet displacement and the mechanical drilling speed and the surface bearing capacity recovery curve, the particle swarm optimization algorithm can be used to calculate the target jet displacement based on the correlation between the jet displacement and the mechanical drilling speed and the surface bearing capacity recovery curve. The particle swarm optimization (PSO) algorithm can optimize the coupling effect of displacement on the installation and standby waiting stages of jet drilling, and calculate the optimal solution of the entire installation and standby waiting stages of jet drilling. The optimal solution includes the target jet displacement, target mechanical drilling speed, target drilling duration, target standby duration and target surface conduit bearing capacity of the installation stage of jet drilling.

[0071] In some embodiments of the present specification, the particle swarm optimization algorithm is used to calculate the target jet displacement based on the correlation between the jet displacement and the mechanical drilling speed and the surface bearing capacity recovery curve, including: initializing a group of randomly generated particles, and calculating the corresponding fitness according to the performance index of each group of particles; each particle is used to represent a jet drilling scheme, which includes the combination of corresponding jet displacement and standby waiting time; according to the historical best position and the global best position of each particle, its speed and position are updated, the new position of each particle is evaluated, and its fitness is calculated; if the fitness of the current particle is better than its historical best position, the individual best position is updated; if the fitness of the current particle is better than the global best position, the global best position is updated, and the iteration is continuously performed until the preset iteration number is met or the fitness threshold is reached; the global best position is output, and the optimal solution of the installation and standby waiting stages of jet drilling is obtained.

[0072] In this embodiment, in order to improve the overall efficiency and safety of jet drilling, the particle swarm optimization (PSO) algorithm is used to optimize the displacement combination of the installation and standby waiting stages of jet drilling. The particle swarm algorithm starts from a random solution, finds the optimal solution through iteration, uses fitness to evaluate the quality of the solution, and follows the current optimal value to find the global optimum. The optimal solution of the entire installation and standby waiting stages of jet drilling includes the optimal solution of the following parameters: jet displacement and mechanical drilling speed during drilling, drilling duration, standby duration and surface conduit bearing capacity.

[0073] According to the target of jet drilling, a fitness function is defined to evaluate the pros and cons of each particle. This fitness function takes into account factors such as jet efficiency, safety, environmental impact, etc., to ensure that the optimization result can meet the actual demand.

[0074] According to the historical optimal position and the global optimal position of each particle, the speed and position of each particle are updated, the new position of each particle is evaluated, and the fitness of each particle is calculated. If the fitness of the current particle is better than the historical optimal position, the individual optimal position is updated; if the fitness of the current particle is better than the global optimal position, the global optimal position is updated. This process is iterated continuously until a preset number of iterations or a fitness threshold is met.

[0075] Finally, the global optimal position, i.e. the optimal solution of the entire jet drilling installation stage and the static waiting stage, is output. This optimal solution can guide the actual jet drilling operation to improve efficiency and safety.

[0076] In the above embodiment, in the process of building a well for a deepwater surface conduit, the jet discharge of the surface conduit is controlled to optimize the drilling speed by using a BP neural network, the surface conduit bearing capacity recovery is predicted with a confidence interval by using a long short-term memory neural network, the optimal flow rate for building a well for a deepwater surface conduit is obtained by optimizing the discharge using a particle swarm optimization algorithm, and the actual drilling case is verified, effectively balancing the efficient conduit installation operation and the shortest safe waiting time during the deepwater surface well building process, providing a new method for the traditional deepwater surface conduit well building based on experience, having reference significance for deepwater surface well building design, and improving the safety and efficiency of deepwater surface efficient drilling.

[0077] In some embodiments of the present specification, after calculating the target jet discharge based on the correlation between the jet discharge and the mechanical drilling speed and the surface bearing capacity recovery curve using the particle swarm optimization algorithm, the method further comprises: determining the corresponding target mechanical drilling speed according to the target jet discharge and the correlation between the jet discharge and the mechanical drilling speed; and calculating the shortest well building time and the real-time conduit bearing capacity during the waiting period based on the target jet discharge, the target mechanical drilling speed and the surface bearing capacity recovery curve.

[0078] In the result analysis and decision support stage, the shortest well building time and the real-time conduit bearing capacity during the waiting period are calculated based on the optimized jet discharge and mechanical drilling speed. These results are fed back to the actual production process to guide the implementation of drilling operations to achieve the purpose of improving efficiency and reducing cost.

[0079] Each embodiment in the present specification is described in a progressive manner, and the same or similar parts between each embodiment can be referred to each other. Each embodiment mainly describes the difference from other embodiments. For specific details, refer to the description of the related processing and related embodiments described above, which will not be repeated here.

[0080] The above described particular embodiments of the present specification. Other embodiments are within the scope of the appended claims. In some cases, the acts or steps recited in the claims can be performed in a different order than those in the embodiments and still achieve desirable results. Additionally, the processes depicted in the figures do not necessarily require the particular order shown or sequential order to achieve desirable results. In some embodiments, multitasking and parallel processing can be advantageous or possible.

[0081] The above method is described below in conjunction with a specific embodiment, however, it is worth noting that the specific embodiment is only for better illustration of the present specification, and does not constitute an improper limitation on the present specification.

[0082] A method for determining the jet displacement of a deep water surface conduit well construction process is provided in the specific embodiment. In the deep water surface jet well construction operation, it includes the installation of the surface conduit stage and the installation in place and waiting stage. In the construction process of jetting to install the surface conduit, the jet displacement is a crucial factor. This jet displacement not only determines the carrying capacity of the surface conduit, but also is directly related to the running speed of the jet operation. If the jet displacement does not reach the minimum soil breaking displacement, the running speed of the conduit will become very slow. However, if the jet displacement exceeds this minimum value, increasing the displacement can significantly improve the efficiency of the jet. However, with the increase of the displacement, the interference of the water jet to the soil around the conduit will also increase, resulting in a greater decrease in the carrying capacity of the surface conduit, and a longer waiting time after installation in place, even leading to sinking operation accidents. Therefore, accurate control of the jet displacement of the jet drilling needs to consider both the hydraulic soil breaking capacity and the conduit carrying capacity as two constraint factors, which is crucial for improving the efficiency and safety of surface well construction.

[0083] The seabed shallow soil is soft, in order to ensure the jet efficiency and prevent wellbore inclination and clay sticking drill bit, the water jet breaking soil is mainly used and the drill bit mechanical breaking soil is supplemented in principle. In order to ensure the efficiency of jetting down the conduit, the minimum displacement satisfying the rock breaking capacity is taken as the lower limit of the jet displacement in the design. In the process of installing the surface conduit for well construction by using the jet method, the influence of the soil body can be regarded as the expansion problem of the cylindrical hole in the infinite soil body. The wellbore radius formed by the water jet corresponds to the initial radius of the cylindrical hole, and the radius of the surface conduit is the radius after the expansion of the circular hole.

[0084] Before the water jet acts on the soil body, its momentum is ρQu, and after it acts on the soil body, its momentum becomes ρQucosθ. According to the momentum theorem, the force of the jet water jet acting on the seabed soil surface is:

[0085] F=ρQu(1-cosθ) (1)

[0086] wherein ρ is the density of the jet drilling fluid, unit kg / m3 Q is the jet discharge, unit m 3 / s; u is the jet flow rate, unit m / s; θ is the jet return angle, unit °; F is the total jet force, unit N.

[0087] If the water jet angle is constant, the total jet force F also remains unchanged.

[0088] In the process of jet, the jet along the way momentum is equal to the initial total momentum of the jet,

[0089]

[0090] Where R0 is the nozzle radius, unit m; u0 is the initial jet flow rate of nozzle position, unit m / s; J is the fluid momentum, unit kg·m / s.

[0091] According to Bernoulli's theorem, the pressure at the nozzle outlet is:

[0092]

[0093] The force within the jet half-width range is:

[0094]

[0095] Where p0 is the pressure at the nozzle outlet, unit pa; F b is the jet force along the cross section, unit N; λ is the jet force reduction coefficient.

[0096] From equation (4), the average force per unit area is:

[0097]

[0098] Where p b is the force acting on the unit area of soil, unit pa; S b is the nozzle action area, unit m 2 ; α is the jet diffusion angle, unit °; x is the jet striking range, unit m.

[0099] In the process of jet, the jet flow acts on the soil surface, and when the jet force is greater than the critical failure pressure of the soil, the soil is damaged:

[0100] p b ≥ p cr (6)

[0101] Where p cr is the critical failure pressure of the soil, which can be approximately equal to the shear strength of the soil, unit pa;

[0102] The diameter and overhang of the drill bit are determined according to the diameter of the conduit; the relative position of the drill bit nozzle to the bottom of the conduit and the equivalent diameter d of the nozzle are determined according to the structure characteristics of the jetting drill bit ne and the water jet striking range x.

[0103] The minimum jetting discharge that meets the soil breaking condition is:

[0104]

[0105] wherein Q0 is the minimum discharge value for hydraulic soil breaking; d ne is the equivalent diameter of the nozzle, in m; k f is the nozzle flow coefficient; and Z is the number of nozzles. u is the jetting impact force on soil, in Pa.

[0106] The relationship between the running speed of the conduit and the jetting discharge is:

[0107]

[0108] wherein v is the conduit installation speed when the discharge is Q, in m / s; Q is the actual jetting discharge, in m 3 / min; Q0 is the minimum discharge value for hydraulic soil breaking, in m 3 / min; v max is the fastest conduit running speed, in m / s; a and b are influence factors, which depend on the stratum; R 2 is the regression factor, which depends on the stratum.

[0109] The minimum discharge required to meet the rock breaking condition is related to multiple factors, including the equivalent diameter of the nozzle, the density of the drilling fluid, the structure of the nozzle, the damage range of the jet, and the shear strength of the soil, etc. These parameters can be determined through the design of the drill bit structure and the nozzle structure and the analysis of soil sampling.

[0110] While ensuring the efficient operation of jetting drilling, the influence of excessively high discharge on the bearing capacity of the conduit needs to be considered to avoid long waiting time or sinking accidents of the conduit. The jetting discharge, the surface conduit running speed model, and the relationship model between the jetting discharge and the bearing capacity of the surface conduit determine the upper limit of the jetting discharge and the surface conduit static time window at the same time.

[0111] According to the soil data and the size of the surface conduit, the limit bearing capacity profile of the surface conduit is established by using the limit bearing capacity calculation model formula (9) of the surface conduit.

[0112]

[0113] Considering the impact of jetting disturbance, and introducing a coefficient to reduce the bearing capacity of the surface conduit, the real-time bearing capacity calculation model after the surface conduit is in place can be expressed as:

[0114] F ut =KF u (10)

[0115] Among them, F ut The real-time load-bearing capacity of the surface conduit is expressed in N; F. u d represents the ultimate bearing capacity of the surface guide pipe, in N; L represents the depth of the surface guide pipe into the mud, in m; o f is the outer diameter of the surface conduit, in meters (m). u — Frictional force per unit area between the surface guide pipe and the soil, in Pa; A—Cross-sectional area of ​​the lower end of the surface guide pipe, in m² 2 ;q u —Ultimate resistance per unit area at the lower end of the surface catheter, in N / m 2 F ut is the real-time bearing capacity of the surface conduit, in N; K is the reduction coefficient of the surface conduit's jet bearing capacity, dimensionless.

[0116] The water jet during the spraying process disturbs the soil, which leads to a decrease in the bearing capacity of the surface guide pipe. Based on the spraying discharge and the drill bit extension, the real-time bearing capacity of the surface guide pipe is determined using the real-time bearing capacity calculation model (9), and a real-time bearing capacity profile of the surface guide pipe is established.

[0117]

[0118] In the vertically downward direction, the guide tube is subjected to its own weight, as well as the weight of the anti-sinking plate, the low-pressure wellhead, and the lower connector of the insertion tool. The vertical load on the surface guide tube when the insertion tool is released is as shown in equation (12):

[0119] G r =λk b L c +W LPWH +W m +W CADA (12)

[0120] Where Q0 is the minimum jet blasting and rock-carrying capacity, in meters. 3 / min; Q is the injection displacement, d o f is the outer diameter of the surface duct. u —Frictional force per unit area between the surface guide pipe and the soil, q u —The ultimate resistance per unit area at the lower end of the surface catheter, t2 is the static waiting time of the surface catheter, in hours. iD is the inner diameter of the surface conduit, in m; l is the protruding length of the drill bit during the jet installation surface conduit process, in m. S is the length from the nozzle to the end of the drill bit, in m; m and n are regional coefficients; λ is the jet force reduction coefficient, G r W is the total weight of the conduit, in N; K b W is the linear weight of the conduit, in N / m; L c L is the length of the conduit, in m; W LPWH W is the weight of the anti-settling plate, in N; W m W is the weight of the underwater wellhead, in N; W CADA W is the weight of the continuous drilling tool CADA, in N.

[0121] The surface conduit static time from jetting in place to the release of the running tool stage. The surface conduit static time from jetting in place to the release of the running tool stage is obtained by combining equation (11) and equation (12). Using soil data, operation parameters, and surface conduit size parameters, real-time bearing capacity recovery curves of the conduit at different times are obtained through simulation and calculation to determine the safe static time and guide the drilling operation of 82 wells on site, and no accidents occurred during this process.

[0122] In the jet drilling process, the design of jet displacement is a complex process that needs to consider multiple factors, including conduit size, installation depth, soil parameters, and drill bit nozzle parameters. In order to ensure jetting efficiency and operation safety, based on the principles of fluid mechanics and soil mechanics, the upper and lower limits of jet displacement are determined, as shown in equation (13). Figure 3 The upper limit of jet displacement is to avoid excessive impact on the bearing capacity of the conduit, while the lower limit of jet displacement is to ensure jetting efficiency. The design of jet displacement in the surface well construction process ensures that both the soil can be effectively broken and the safety of the conduit can be guaranteed during the jet drilling process.

[0123] In the jet installation stage of surface well construction, drilling parameters and geological conditions are influenced by multiple factors, and BP neural network has an advantage in fusing the influence of multiple factors and calculating the relationship between displacement and mechanical drilling speed. BP neural network can be designed according to the above equations (1)-(8).

[0124] LSTM model can consider the influence of time sequence and accurately calculate the recovery of bearing capacity during the waiting process to determine the shortest waiting time to avoid excessive waiting, waste of energy, and excessive emission of greenhouse gases, as well as too short waiting time to avoid operation safety accidents. LSTMBP neural network can be designed according to the above equations (9)-(12).

[0125] The particle swarm optimization algorithm can optimize the coupling effect of displacement on the installation and static waiting stages of the jet drilling, and calculate the optimal solution for the entire jet drilling installation and static waiting stages.

[0126] In the design of deep water surface jetting stage, a model based on BP neural network is established to predict the relationship between drilling displacement and mechanical drilling speed of jet drilling, and the calculation principle and route are as shown in Figure 4

[0127] The drilling parameters and geological parameters are collected, and the structure of BP neural network is designed according to the relationship between drilling displacement and mechanical drilling speed, including the number of neurons in input layer, hidden layer and output layer. The design of these layers takes into account the complexity of input data and the nonlinear characteristics of output relationship.

[0128] The collected data are used to train the BP neural network. Through iterative optimization, the network weights are adjusted to make the network output close to the actual relationship between drilling displacement and mechanical drilling speed. Then, the trained BP neural network is tested using test data to verify the prediction performance of the network. This helps to evaluate the reliability and accuracy of the model.

[0129] Finally, in the optimization network stage, the network structure or training parameters are adjusted according to the test results to further improve the prediction accuracy of the network and better adapt to the needs of actual drilling operations.

[0130] In the calculation of real-time bearing capacity during the waiting period of jet drilling, a surface bearing capacity recovery curve considering confidence interval is established by LSTM method, so as to calculate the static waiting time during the waiting period of jet drilling. The confidence interval refers to the establishment of a surface bearing capacity recovery curve considering a certain error range due to fluctuations and operation errors in the operation, so that a more safe static waiting time can be obtained.

[0131] After collecting the jet drilling parameters and waiting time, the structure of LSTM network is designed, including input layer, LSTM layer and output layer. The number of LSTM units and layers in LSTM layer need to be adjusted according to specific problems to adapt to the complexity of data. Because different wells have different parameters, the input can be made according to the operation characteristics of each well. Engineering data are used to train the LSTM network, and through iterative optimization, the network weights are adjusted to make the network output close to the actual bearing capacity data. The engineering data can include: jet drilling pressure, displacement, bit parameters, rotation speed engineering operation parameters and geological parameters. The geological parameters can include: soil shear strength, fracture pressure, loss pressure, bulk weight, friction parameter, etc.

[0132] ​According to the prediction result of the LSTM network, a confidence interval of the recovery curve of the surface bearing capacity changing with time is established, reflecting the change trend of the bearing capacity. According to the bearing capacity recovery curve, the shortest waiting time during the waiting period of jet drilling is determined to ensure that the bearing capacity of the conduit is safe and not excessively waiting to waste the positioning of the operation platform, and to ensure the safety and efficiency of deep water surface well construction. Specifically, according to the soil bearing capacity recovery, that is, the maximum gravity that the soil body can bear is compared with the downward equipment gravity (known before operation) such as the self-weight of the conduit, the weight of the underwater wellhead, and the weight of the CADA, the shortest time for safe operation can be obtained. While ensuring the safety of the operation, the waiting time is the shortest and the consumption is the least.

[0133] In order to improve the overall efficiency and safety of jet drilling, the particle swarm optimization (PSO) algorithm is used to optimize the displacement combination of jet drilling installation and static waiting stage in the embodiments of the present specification. The particle swarm algorithm starts from a random solution, finds the optimal solution through iteration, evaluates the quality of the solution by fitness, and finds the global optimum by following the current optimal value found. Increasing the displacement increases the rate of penetration, but if the increase is too large, the waiting time will be too long. Therefore, by considering the comprehensive influence during drilling and waiting, a suitable displacement is established, and the displacement is the main factor to control and affect the rate of penetration. The calculation principle and route are as shown in Figure 5 .

[0134] According to the target of jet drilling, a fitness function is defined to evaluate the pros and cons of each particle. This fitness function considers factors such as jet efficiency, safety, environmental impact, etc. to ensure that the optimization result can meet the actual demand.

[0135] In one embodiment, the fitness function is:

[0136] f(t)best=t1+t2;

[0137] Where f(t)best is the fitness function, representing the global time, t1 is the drilling period time, and t2 is the static waiting time during the waiting period. t1 can be calculated according to the conduit running speed in formula (8). Specifically, Where L is the conduit depth, and v is the conduit running speed. t2 can be calculated according to formula (11).

[0138] According to the historical best position and global best position of each particle, its speed and position are updated, the new position of each particle is evaluated, and its fitness is calculated. If the fitness of the current particle is better than its historical best position, the individual best position is updated; if the fitness of the current particle is better than the global best position, the global best position is updated. This process is iterated until a preset number of iterations or a fitness threshold is met.

[0139] Finally, the global optimal position is output, which is the optimal solution for the entire jet drilling installation phase and the static waiting phase. This optimal solution can guide the actual jet drilling operation and improve efficiency and safety. The optimal solution for the entire jet drilling installation phase and the static waiting phase includes the optimal solution for the following parameters: jet flow rate and rate of penetration during drilling, drilling time, waiting time during static period, and surface conduit bearing capacity.

[0140] In this embodiment, three different algorithms, BP neural network, LSTM, and particle swarm optimization (PSO), are used to predict the relationship between jet flow rate and rate of penetration during drilling. The three algorithms are similar in the data collection and processing stage, which requires collecting key parameter data and cleaning, handling missing values, and normalizing or standardizing the data to ensure data quality and consistency. To provide effective solutions for different data types and analysis needs, the specific details of the data collection and processing stage differ. The three methods complement each other in prediction, with jet flow rate only during drilling, but it affects waiting time. Therefore, BP neural network predicts jet flow rate and rate of penetration, LSTM predicts waiting time and bearing capacity. PSO predicts the global optimal flow rate, resulting in jet flow rate, rate of penetration, drilling time, waiting time during static period, and bearing capacity.

[0141] The data collection stage of the BP neural network algorithm involves collecting data on key parameters such as nozzle diameter, drilling fluid density, jet break range, and soil properties. In the data preprocessing stage, the collected data is cleaned, missing values are handled, and the data is normalized or standardized to ensure data quality and consistency.

[0142] The data collection stage of the LSTM algorithm also involves collecting jet drilling parameter data, mainly time series data and input features that may affect bearing capacity, such as jet flow rate and soil properties. The collected data is cleaned and missing values are handled to prepare for subsequent calls to the independently developed deepwater surface well construction static period conduit bearing capacity recovery prediction soft computing.

[0143] The particle swarm optimization (PSO) algorithm relies mainly on the above two algorithms and randomly generates a set of particles, each representing a jet drilling scheme, including different combinations of jet flow rate and static waiting time, providing initial solutions for the PSO algorithm.

[0144] This scheme combines machine learning, deep learning, and intelligent optimization methods to provide a comprehensive data-driven solution for drilling operations. Through analysis and mining of large amounts of data, the system can automatically identify key factors and provide real-time decision support. The calculation principle and route are as shown in Figure 6 .

[0145] In the data collection and processing stage, formation parameters, drilling parameters and other related data are collected, and preprocessing operations such as cleaning and normalization are performed on these data to improve the accuracy of subsequent analysis.

[0146] In the BP neural network prediction of jet drilling, the number of neurons in the input layer is designed according to the dimension of the input data, and the appropriate number of hidden layers and the number of neurons in each layer are selected. The design of the output layer is to set the number of neurons according to the type of relationship needed to output. The collected data is used to train the neural network, and the weight and bias values are adjusted so that the model can accurately reflect the complex nonlinear relationship between well depth and drilling speed.

[0147] In the LSTM network prediction of the static waiting stage, the time sequence dependence in the sequence data is captured. The catheter carrying capacity recovery mechanism model is used to train the LSTM network using data and to compare and verify the actual engineering data, so that it can predict the recovery of the catheter carrying capacity after jetting in place.

[0148] In the PSO-based optimization stage, a set of randomly generated particles is initialized, and the fitness of each particle is calculated according to its performance index. Standard operations of genetic algorithm are performed, including selection, crossover and mutation, and the particle population is constantly updated to find the global optimal solution.

[0149] Finally, in the result analysis and decision support stage, the shortest time of well construction and the real-time carrying capacity of the catheter during the waiting period are calculated according to the jet displacement and the mechanical drilling speed obtained by optimization. These results are fed back to the actual production process to guide the implementation of drilling operations, so as to improve efficiency and reduce cost.

[0150] Based on the same inventive concept, the embodiments of the present specification also provide a device for determining the jet displacement of the deep water surface pipe well construction process, as described in the following embodiments. Since the device for determining the jet displacement of the deep water surface pipe well construction process solves the problem by the same principle as the method for determining the jet displacement of the deep water surface pipe well construction process, the implementation of the device for determining the jet displacement of the deep water surface pipe well construction process can be referred to the implementation of the method for determining the jet displacement of the deep water surface pipe well construction process, and the repeated parts will not be described here. The term "unit" or "module" used below can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware, or a combination of software and hardware is also possible and contemplated. Figure 7 is a structural block diagram of the device for determining the jet displacement of the deep water surface pipe well construction process of the embodiments of the present specification, as Figure 7As shown, the apparatus includes an acquisition module 701, a determination module 702, an establishment module 703, and a calculation module 704, which are described below.

[0151] The acquisition module 701 is configured to acquire drilling parameters and formation property parameters of the deepwater surface layer jet well construction operation.

[0152] The determination module 702 is configured to determine a correlation between jet discharge and mechanical drilling speed based on the drilling parameters and the formation property parameters by using a target BP neural network.

[0153] The establishment module 703 is configured to establish a surface layer bearing capacity recovery curve according to the drilling parameters and the formation property parameters by using a target long short-term memory neural network; the surface layer bearing capacity recovery curve is a curve of surface layer bearing capacity changing with time.

[0154] The calculation module 704 is configured to calculate a target jet discharge based on the correlation between the jet discharge and the mechanical drilling speed and the surface layer bearing capacity recovery curve by using a particle swarm optimization algorithm.

[0155] In some embodiments of the present disclosure, the target BP neural network is constructed in the following manner: the structure of the BP neural network and the number of neurons of the input layer, the hidden layer and the output layer included in the BP neural network are determined according to the physical relationship between the jet discharge and the mechanical drilling speed; the drilling parameters and the geological parameters are collected; the collected data is used to train the BP neural network to obtain the target BP neural network; in the training process, the network weights of the BP neural network are adjusted through iterative optimization, so that the correlation between the jet discharge and the mechanical drilling speed output by the BP neural network is close to the actual relationship between the jet discharge and the mechanical drilling speed.

[0156] In some embodiments of the present disclosure, the target long short-term memory neural network is constructed in the following manner: the structure of the long short-term memory neural network and the number of long short-term memory units and layers are determined; the jet drilling parameters and the waiting time are collected; the collected jet drilling parameters and the waiting time are used to train the long short-term memory neural network to obtain the target long short-term memory neural network; in the training process, the network weights of the long short-term memory neural network are adjusted through iterative optimization, so that the output of the long short-term memory neural network is close to the actual bearing capacity data.

[0157] In some embodiments of the present disclosure, the establishment module is specifically configured to: establish a surface layer bearing capacity recovery curve according to the bearing capacity data output by the target long short-term memory neural network; and determine a static waiting time during jet drilling waiting according to the surface layer bearing capacity recovery curve, the static waiting time being a static waiting time for ensuring the safety of the deepwater surface layer jet well construction operation.

[0158] In some embodiments of the present specification, the computing module is specifically configured to: initialize a set of particles generated randomly, and calculate the corresponding fitness according to the performance index of each set of particles; each particle is used to represent a jet drilling scheme, and the jet drilling scheme includes a combination of corresponding jet discharge and static waiting time; update the speed and position of each particle according to the historical best position and the global best position of each particle, evaluate the new position of each particle, and calculate the fitness thereof; if the fitness of the current particle is better than the historical best position thereof, update the individual best position; if the fitness of the current particle is better than the global best position, update the global best position, and keep iterating until a preset iteration number is met or a fitness threshold is reached; and output the global best position to obtain the optimal solution of the jet drilling installation stage and the static waiting stage.

[0159] In some embodiments of the present specification, the computing module is further configured to: after calculating the target jet discharge based on the correlation between the jet discharge and the penetration rate and the surface bearing capacity recovery curve by using the particle swarm optimization algorithm, determine the corresponding target penetration rate according to the target jet discharge and the correlation between the jet discharge and the penetration rate; and calculate the shortest well construction time and the real-time bearing capacity of the guide pipe during the waiting period based on the target jet discharge, the target penetration rate, and the surface bearing capacity recovery curve.

[0160] The present specification also provides a computer device, which can specifically refer to Figure 8 The computer device for determining the jet discharge of the deep water surface guide pipe well construction process provided by the embodiments of the present specification, as shown in the composition structure schematic diagram of the computer device for determining the jet discharge of the deep water surface guide pipe well construction process provided by the embodiments of the present specification, can specifically include an input device 81, a processor 82, and a memory 83. The memory 83 is used to store processor executable instructions. The processor 82 executes the instructions to implement the steps of the method for determining the jet discharge of the deep water surface guide pipe well construction process in any of the above embodiments.

[0161] In the embodiment, the input device can be specifically one of main devices for information exchange between the user and the computer system. The input device can include a keyboard, a mouse, a camera, a scanner, a light pen, a handwriting input board, a voice input device, etc.; the input device is used to input raw data and programs for processing the data into the computer. The input device can also acquire data transmitted by other modules, units, devices. The processor can be implemented in any appropriate manner. For example, the processor can take the form of a microprocessor or a processor and a computer readable medium storing computer readable program code (such as software or firmware) executable by the (micro)processor, logic gates, switches, application specific integrated circuits (ASIC), programmable logic controllers, and embedded microcontrollers, etc. The memory can be specifically a memory device for saving information in modern information technology. The memory can include multiple levels, and in a digital system, as long as it can save binary data, it can be a memory; in an integrated circuit, a circuit without a physical form and with a storage function is also called a memory, such as RAM, FIFO, etc.; in a system, a storage device with a physical form is also called a memory, such as a memory stick, a TF card, etc.

[0162] In the embodiment, the functions and effects realized by the computer device can be explained in comparison with other embodiments, and will not be repeated here.

[0163] The embodiment of the present specification also provides a computer storage medium based on a method for determining the jet displacement of a deep water surface conduit well construction process, the computer storage medium storing computer program instructions, when the computer program instructions are executed, realizing the steps of the method for determining the jet displacement of the deep water surface conduit well construction process in any of the above embodiments.

[0164] In the embodiment, the storage medium includes but is not limited to a random access memory (RAM), a read-only memory (ROM), a cache, a hard disk drive (HDD), or a memory card. The memory can be used to store computer program instructions. The network communication unit can be an interface set according to the standard of the communication protocol, used for network connection communication.

[0165] In the embodiment, the functions and effects realized by the program instructions stored in the computer storage medium can be explained in comparison with other embodiments, and will not be repeated here.

[0166] Obviously, those skilled in the art should understand that each module or each step of the above-mentioned embodiments of the present description can be realized by a general computing device, which can be centralized on a single computing device or distributed on a network composed of multiple computing devices, and optionally, each module or each step can be realized by program codes executable by a computing device, so that each module or each step can be stored in a storage device and executed by a computing device, and in some cases, the steps shown or described can be executed in different order, or each module or step can be manufactured as an individual integrated circuit module, or multiple modules or steps can be manufactured as a single integrated circuit module. Thus, the embodiments of the present description are not limited to any specific combination of hardware and software.

[0167] It is to be understood that the above description is intended to be illustrative and not restrictive. Many embodiments and applications other than the examples provided would be apparent to those of skill in the art upon reading the above description. The scope of the description should be determined, not with reference to the above description, but should instead be determined with reference to the appended claims, along with the full scope of equivalents to which such claims are entitled. The disclosures of patents and patent applications cited herein are hereby incorporated by reference in their entirety.

[0168] The above description is merely illustrative of the exemplary embodiments of the present description, and is not intended to limit the present description. The embodiments of the present description can have various modifications and changes, and all modifications, equivalent replacements, improvements, etc. within the spirit and principles of the present description should be included in the protection scope of the present description.

Claims

1. A method for determining the jetting displacement for a deep water surface conductor well completion process, characterized by, The method comprises the following steps: acquiring drilling parameters and formation property parameters of a deep water surface layer jet drilling well construction operation; determining a correlation between jet discharge and mechanical drilling speed based on the drilling parameters and the formation property parameters by using a target BP neural network; adopting a target long short-term memory neural network to determine bearing capacity data according to the drilling parameters and the formation property parameters, and establishing a surface layer bearing capacity recovery curve according to the bearing capacity data output by the target long short-term memory neural network; the surface layer bearing capacity recovery curve is a curve of surface layer bearing capacity changing with time; input data of the target long short-term memory neural network comprises the drilling parameters and the formation property parameters, and output data of the target long short-term memory neural network comprises the bearing capacity data; initializing a group of particles generated randomly, and calculating a corresponding fitness according to a performance index of each group of particles; each particle is used to represent a jet drilling scheme, and the jet drilling scheme comprises a combination of a corresponding jet discharge and a static waiting time; updating a speed and a position of each particle according to a historical best position and a global best position of the particle, evaluating a new position of each particle, and calculating a fitness of the particle; if the fitness of the current particle is better than the historical best position of the particle, updating the individual best position; if the fitness of the current particle is better than the global best position, updating the global best position, and continuously iterating until a preset iteration number is met or a fitness threshold is reached; outputting the global best position to obtain a target jet discharge; determining a corresponding target mechanical drilling speed according to the target jet discharge and the correlation between the jet discharge and the mechanical drilling speed; calculating a well construction shortest time and a real-time duct bearing capacity during a waiting period based on the target jet discharge, the target mechanical drilling speed, and the surface layer bearing capacity recovery curve.

2. The method for determining the jetting displacement for a deep water surface conductor well completion process of claim 1, wherein, The target BP neural network is constructed in the following manner: determining a structure of the BP neural network and neuron numbers of an input layer, a hidden layer and an output layer included in the BP neural network according to a physical relationship between the jet discharge and the mechanical drilling speed; collecting drilling parameters and geological parameters; training the BP neural network by using the collected data to obtain the target BP neural network; in a training process, adjusting network weights of the BP neural network through iterative optimization, so that a correlation between the jet discharge and the mechanical drilling speed output by the BP neural network is close to an actual relationship between the jet discharge and the mechanical drilling speed.

3. The method for determining the jetting displacement for a deep water surface conductor well completion process of claim 1, wherein, The target long short-term memory neural network is constructed in the following manner: determining a structure of the long short-term memory neural network and numbers of long short-term memory units and layers; collecting jet drilling parameters and waiting times; training the long short-term memory neural network by using the collected jet drilling parameters and waiting times to obtain the target long short-term memory neural network; in a training process, adjusting network weights of the long short-term memory neural network through iterative optimization, so that an output of the long short-term memory neural network is close to actual bearing capacity data.

4. The method for determining the jetting displacement for a deep water surface conductor well completion process of claim 1, wherein, The method further comprises the following steps: According to the surface layer bearing capacity recovery curve, a static waiting time during jet drilling waiting is determined, the static waiting time being the shortest waiting time ensuring safety of deep water surface layer jet well construction operation.

5. An apparatus for determining the jetting displacement for a deep water surface conductor well completion process, characterized by, The method comprises the following steps: an acquisition module is configured to acquire drilling parameters and formation property parameters of deep water surface layer jet well construction operation; a determination module is configured to determine a correlation between jet discharge and rate of penetration by using a target BP neural network based on the drilling parameters and the formation property parameters; an establishment module is configured to determine bearing capacity data according to the drilling parameters and the formation property parameters by using a target long short-term memory neural network, and establish a surface layer bearing capacity recovery curve according to the bearing capacity data output by the target long short-term memory neural network; the surface layer bearing capacity recovery curve is a curve of surface layer bearing capacity changing with time; input data of the target long short-term memory neural network comprises the drilling parameters and the formation property parameters, and output data of the target long short-term memory neural network comprises the bearing capacity data; a calculation module is configured to initialize a group of particles generated randomly, and calculate a corresponding fitness according to a performance index of each group of particles; each particle is used to represent a jet drilling scheme, the jet drilling scheme comprising a combination of a corresponding jet discharge and static waiting time; the speed and position of each particle are updated according to a historical best position and a global best position of the particle, the new position of each particle is evaluated, and the fitness of each particle is calculated; if the fitness of the current particle is better than the historical best position, the individual best position is updated; if the fitness of the current particle is better than the global best position, the global best position is updated, and iteration is continuously performed until a preset iteration number is met or a fitness threshold is reached; a global best position is output to obtain a target jet discharge; a corresponding target rate of penetration is determined according to the target jet discharge and the correlation between the jet discharge and the rate of penetration. a shortest well construction time and a real-time bearing capacity of a guide pipe during waiting are calculated based on the target jet discharge, the target rate of penetration, and the surface layer bearing capacity recovery curve.

6. A computer device, comprising: The processor executes the instructions to implement the steps of the method of any one of claims 1 to 4.

7. A computer readable storage medium having stored thereon computer instructions, wherein, The processor executes the instructions to implement the steps of the method of any one of claims 1 to 4.

8. A computer program product comprising computer programs / instructions, characterized in that, The processor executes the instructions to implement the steps of the method of any one of claims 1 to 4.

Images