Drilling engineering drilling rate prediction network training method and application method

Abstract

The invention provides a drilling engineering drilling speed prediction network training method and an application method, and belongs to the technical field of drilling engineering optimizing.The training method comprises the steps that data screening is conducted on obtained drilling construction data to obtain effective construction data, variational mode decomposition algorithm noise reduction is conducted on the effective construction data to obtain noise reduction data, and the noise reduction data is used for obtaining the drilling engineering drilling speed prediction network; mechanism model prediction is carried out on the noise reduction data to obtain a mechanism prediction drilling speed, and the noise reduction data and the mechanism prediction drilling speed are combined to obtain drilling speed prediction training data; and inputting the drilling speed prediction training data into the initial drilling engineering drilling speed prediction network, and performing iterative optimization on network parameters of the initial drilling engineering drilling speed prediction network based on a particle swarm optimization algorithm to obtain a well drilling engineering drilling speed prediction network which is completely trained. According to the method, data noise reduction is carried out through the variational mode decomposition algorithm, a drilling mechanism model is combined, data features can be effectively mined, the model accuracy is improved, the calculated amount in the training process is reduced through the particle swarm optimization algorithm, and the training efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of drilling engineering optimization, and in particular to a drilling engineering drilling speed prediction network training method and an application method. Background Art

[0002] As the core process of oil and gas resource exploration and development, the complexity of drilling engineering is reflected in the fine operations from the surface to the target formation. In the face of resource depletion and the increasing difficulty of mining, how to accelerate the drilling process, reduce costs and ensure operational safety is the current focus of the oil and gas resource exploration industry. In this context, the drilling speed of drilling engineering machinery is the core indicator for evaluating drilling efficiency, and its optimization strategy has become the key to reducing costs, improving efficiency and ensuring operational safety. Furthermore, accurate prediction of drilling speed is the basis for formulating optimization strategies and improving drilling efficiency.

[0003] In drilling projects, the drilling speed is affected by many complex factors, such as drilling pressure, density, viscosity and flow rate of drilling fluid, rock hardness, drill bit size, drilling depth and hydraulic parameters. However, due to the limitations of equipment accuracy and operating conditions, various types of data collected in drilling projects have a lot of noise. The existing technology usually fails to effectively denoise the noise during the training of the drilling speed prediction model, and does not consider the drilling mechanism model. Therefore, the obtained drilling speed prediction model cannot fully mine the data features, resulting in low model accuracy. In addition, due to the large number of factors affecting the drilling speed of drilling projects, the existing technology has a large amount of calculation in the training process, and the model training efficiency is low.

[0004] Therefore, the existing technology has the following technical problems: the noise cannot be effectively denoised during the model training process, the drilling mechanism model is not considered, and the data characteristics cannot be fully mined, resulting in low model accuracy. In addition, the large amount of calculation during the training process leads to low model training efficiency, which needs to be improved. Summary of the invention

[0005] In view of this, it is necessary to provide a drilling engineering drilling speed prediction network training method and application method to solve the technical problems existing in the prior art that the noise cannot be effectively denoised, the drilling mechanism model is not considered, the data characteristics cannot be fully mined, resulting in low model accuracy, and the model training efficiency is low due to the large amount of calculation during the training process.

[0006] In order to solve the above problems, on the one hand, the present invention provides a drilling engineering drilling speed prediction network training method, comprising: The acquired drilling construction data is screened to obtain effective construction data, the effective construction data is denoised by using a variational mode decomposition algorithm to obtain denoised data, the denoised data is predicted by a mechanism model to obtain a mechanism-predicted drilling speed, and the denoised data and the mechanism-predicted drilling speed are combined to obtain drilling speed prediction training data; The drilling speed prediction training data is input into the initial drilling engineering drilling speed prediction network. The network parameters of the initial drilling engineering drilling speed prediction network are iteratively optimized based on the particle swarm optimization algorithm to obtain a fully trained drilling engineering drilling speed prediction network.

[0007] In a possible implementation, the acquired drilling construction data is screened to obtain effective construction data, including: Based on the Spearman correlation coefficient method and the Mantel test method, the correlation coefficient of each parameter type in the drilling construction data is obtained by performing correlation analysis on the acquired drilling construction data; The drilling construction data is screened according to the correlation coefficient to obtain effective construction data.

[0008] In a possible implementation, effective construction data is denoised using a variational mode decomposition algorithm to obtain denoised data, including: Initialize the algorithm parameters of the variational mode decomposition algorithm according to the effective construction data; Based on the variational modal decomposition algorithm, the modal decomposition of the effective construction data is performed to obtain several modal components; The modal components are subjected to spectrum analysis and statistical feature analysis to obtain effective modal components, which are then reorganized to obtain noise-reduced data.

[0009] In a possible implementation, the noise reduction data is predicted using a mechanism model to obtain a mechanism predicted drilling speed, including: Solve the model parameters of the initial mechanism model based on the least squares method; The noise reduction data is input into the mechanism model to predict the drilling speed and obtain the mechanism predicted drilling speed.

[0010] In a possible implementation, the noise reduction data includes drilling speed influencing factor data and drilling speed measurement data, and the noise reduction data and the mechanism predicted drilling speed are combined to obtain drilling speed prediction training data, including: The drilling speed influencing factor data and the mechanism predicted drilling speed are combined as the model input variables, the drilling speed measurement data are used as the model output variables, and the model input variables and model output variables are normalized to obtain the drilling speed prediction training data.

[0011] In a possible implementation, the network parameters of the initial drilling engineering drilling speed prediction network are iteratively optimized based on a particle swarm optimization algorithm, including: The network parameters of the initial drilling engineering drilling speed prediction network are used as the optimization target parameters of the particle swarm optimization algorithm, and the particle swarm to be optimized is initialized according to the optimization target parameters; The individual positions of particles in the particle swarm to be optimized are updated based on a preset speed update formula and a preset position update formula to obtain an optimized particle swarm; The individual fitness of each particle in the optimized particle swarm is calculated based on the mean relative error method. The individual optimal value and the global optimal value are updated according to the individual fitness, and a new round of population to be optimized is determined. The optimization process is iterated until the preset maximum number of iterations is reached.

[0012] In a possible implementation, the individual optimal value and the global optimal value are updated according to the individual fitness and a new round of population to be optimized is determined, including: Compare the individual fitness of each particle with the historical optimal fitness of each particle individual to obtain the new round of historical optimal fitness, take the particle individual corresponding to the new round of historical optimal fitness as the new round of individual optimal value, and form the new round of individual optimal values ​​into a new round of population to be optimized; The current global optimal value is determined according to the new round of individual optimal values, and the current global optimal value is compared with the historical global optimal value to obtain the new round of global optimal value.

[0013] On the other hand, the present invention also provides a drilling engineering drilling speed prediction network application method, comprising: Obtain the construction data of the drilling project to be predicted; Input drilling engineering construction data into the well-trained drilling engineering drilling speed prediction network to obtain the drilling speed prediction result; The fully trained drilling engineering drilling speed prediction network is determined according to the above-mentioned drilling engineering drilling speed prediction network training method.

[0014] On the other hand, the present invention also provides an electronic device, including a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the above-mentioned drilling engineering drilling speed prediction network training method and / or the above-mentioned drilling engineering drilling speed prediction network application method are implemented.

[0015] On the other hand, the present invention also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the above-mentioned drilling engineering drilling speed prediction network training method and / or the above-mentioned drilling engineering drilling speed prediction network application method are implemented.

[0016] The beneficial effects of the present invention are as follows: the drilling speed prediction network training method for drilling engineering provided by the embodiment of the present invention first performs data screening on the acquired drilling construction data to obtain effective construction data, performs variational mode decomposition algorithm denoising on the effective construction data to obtain denoised data, performs mechanism model prediction on the denoised data to obtain mechanism predicted drilling speed, and combines the denoised data and mechanism predicted drilling speed to obtain drilling speed prediction training data; then the drilling speed prediction training data is input into the initial drilling engineering drilling speed prediction network, and the network parameters of the initial drilling engineering drilling speed prediction network are iteratively optimized based on the particle swarm optimization algorithm to obtain a fully trained drilling engineering drilling speed prediction network. The present invention can effectively denoise the data through the variational mode decomposition algorithm, and combines the mechanism model of drilling through mechanism model prediction, which can effectively mine data features and improve model accuracy, and iteratively optimizes the network parameters through the particle swarm optimization algorithm, which can reduce the amount of calculation in the training process and improve training efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 A schematic flow chart of an embodiment of a drilling speed prediction network training method for drilling engineering provided by the present invention; Figure 2 A schematic diagram of a process for screening drilling construction data according to an embodiment of the present invention; Figure 3 Schematic diagram of the process of the variational mode decomposition algorithm of the embodiment of the present invention; Figure 4 A schematic diagram of a flow chart of a mechanism model prediction of an embodiment of the present invention; Figure 5 A schematic diagram of a particle swarm optimization algorithm according to an embodiment of the present invention; Figure 6 A schematic diagram of a process for iteratively updating a population to be optimized according to an embodiment of the present invention; Figure 7 A schematic flow chart of an embodiment of a network application method for predicting drilling speed in drilling engineering provided by the present invention; Figure 8 A schematic structural diagram of an embodiment of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0020] In the description of the embodiments of the present invention, unless otherwise specified, "multiple" means two or more than two. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" may mean: A exists alone, A and B exist at the same time, and B exists alone.

[0021] The descriptions of "first" and "second" in the embodiments of the present invention are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the technical features defined as "first" and "second" may explicitly or implicitly include at least one of the features.

[0022] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0023] The present invention provides a drilling engineering drilling speed prediction network training method, application method electronic device and medium, which are respectively described below.

[0024] Figure 1 A flow chart of an embodiment of a drilling speed prediction network training method for drilling engineering provided by the present invention is shown as follows: Figure 1 As shown, the drilling engineering drilling speed prediction network training method includes: S101, performing data screening on the acquired drilling construction data to obtain effective construction data, performing variational mode decomposition algorithm to reduce noise on the effective construction data to obtain reduced noise data, performing mechanism model prediction on the reduced noise data to obtain mechanism predicted drilling speed, and combining the reduced noise data and the mechanism predicted drilling speed to obtain drilling speed prediction training data; S102, inputting the drilling speed prediction training data into the initial drilling engineering drilling speed prediction network, iteratively optimizing the network parameters of the initial drilling engineering drilling speed prediction network based on the particle swarm optimization algorithm, and obtaining a fully trained drilling engineering drilling speed prediction network.

[0025] Compared with the prior art, the drilling speed prediction network training method for drilling engineering provided by the embodiment of the present invention first performs data screening on the acquired drilling construction data to obtain effective construction data, performs variational mode decomposition algorithm denoising on the effective construction data to obtain denoised data, performs mechanism model prediction on the denoised data to obtain mechanism predicted drilling speed, and combines the denoised data and mechanism predicted drilling speed to obtain drilling speed prediction training data; then the drilling speed prediction training data is input into the initial drilling engineering drilling speed prediction network, and the network parameters of the initial drilling engineering drilling speed prediction network are iteratively optimized based on the particle swarm optimization algorithm to obtain a fully trained drilling engineering drilling speed prediction network. The present invention can effectively denoise the data through the variational mode decomposition algorithm, and combines the mechanism model of drilling through mechanism model prediction, which can effectively mine data features and improve model accuracy, and iteratively optimizes the network parameters through the particle swarm optimization algorithm, which can reduce the amount of calculation in the training process and improve training efficiency.

[0026] In some embodiments of the present invention, Figure 2 FIG. 1 is a flow chart of the drilling construction data screening process according to an embodiment of the present invention. Figure 2 As shown, the acquired drilling construction data is screened to obtain effective construction data, including: S201, performing correlation analysis on the acquired drilling construction data based on the Spearman correlation coefficient method and the Mantel test method to obtain the correlation coefficient of each parameter type in the drilling construction data; S202: Screen the drilling construction data according to the correlation coefficient to obtain effective construction data.

[0027] Specifically, considering that there are many factors that affect the drilling speed in drilling construction, but not all factors have a significant impact on the drilling speed. In actual construction, depending on the construction environment and construction equipment, some factors may have a smaller impact on the drilling speed, so it is necessary to first screen the data and eliminate the parameter types with less impact in the drilling construction data. In this regard, the embodiment performs a correlation analysis on the drilling construction data based on the Spearman correlation coefficient method and the Mantel test method to determine the correlation coefficient between each parameter type and the drilling speed.

[0028] Among them, the Spearman correlation coefficient method is a non-parametric indicator to measure the dependence of two variables. It uses a monotonic equation to evaluate the correlation between two statistical variables. If there are no repeated values ​​in the data, and when the two variables are completely monotonically correlated, the value of the Spearman correlation coefficient is 1 or -1.

[0029] The Mantel test method reflects the correlation between two representations by comparing the correlation between two distance matrices. The two distance matrices are generally converted into numerical matrices of similarity or difference through actual data.

[0030] The embodiment calculates the correlation coefficient between each parameter type and the drilling speed by using the Spearman correlation coefficient method and the Mantel test method respectively. When the correlation coefficients calculated by the two methods are both lower than the preset threshold value, the corresponding type of parameters are eliminated to obtain effective construction data useful for drilling speed prediction after the screening is completed.

[0031] In some embodiments of the present invention, Figure 3 Schematic diagram of the process of the variational mode decomposition algorithm of the embodiment of the present invention, such as Figure 3 As shown in the figure, the effective construction data is denoised by using the variational mode decomposition algorithm to obtain denoised data, including: S301, initializing algorithm parameters of the variational mode decomposition algorithm according to effective construction data; S302, performing modal decomposition on the effective construction data based on a variational modal decomposition algorithm to obtain a number of modal components; S303 , performing spectrum analysis and statistical feature analysis on the modal components to obtain effective modal components, and reorganizing the effective modal components to obtain noise reduction data.

[0032] Specifically, in order to effectively reduce the noise of the collected data, so that the data features can be effectively mined during the model training process and the model accuracy can be improved, the embodiment performs data noise reduction through a variational mode decomposition algorithm. Variational mode decomposition is an advanced signal processing technology used to decompose non-stationary and nonlinear signals. Variational mode decomposition extracts modes from signals through a variational framework and optimizes them in the frequency domain so that each mode has a minimum bandwidth, which can effectively separate the different components of the signal. This method has significant advantages in processing complex signals.

[0033] First, the embodiment initializes the algorithm parameters of the variational modal decomposition algorithm according to the effective construction data to be processed, including the number of decomposition layers, regularization parameters and initial center frequency of the variational modal decomposition algorithm. The number of decomposition layers is used to determine the number of modes into which the signal is to be decomposed. The embodiment selects it according to the complexity of the data and the noise reduction requirements. The regularization parameter is used to control the bandwidth of the signal and the smoothness of the center frequency. The initial center frequency is usually set to a uniformly distributed frequency range to ensure that all frequency components are considered.

[0034] Then, the embodiment uses a variational modal decomposition algorithm to modally decompose the effective construction data into several modal components, each of which represents a signal component with a specific frequency bandwidth. During the decomposition process, the embodiment minimizes the bandwidth of each modal component through iterative optimization while keeping the reconstruction error of the signal as low as possible.

[0035] Then, the embodiment analyzes each modal component through spectrum analysis and statistical feature analysis to identify and filter out effective modal components containing useful signal components, superimposes the filtered effective modal components, and reorganizes them to obtain noise reduction data with complete noise reduction.

[0036] In some embodiments of the present invention, Figure 4 Schematic diagram of the mechanism model prediction process of the embodiment of the present invention, such as Figure 4 As shown in the figure, the noise reduction data is predicted by the mechanism model to obtain the mechanism predicted drilling speed, including: S401, solving the model parameters of the initial mechanism model based on the least square method; S402, inputting the noise reduction data into the mechanism model to predict the drilling speed to obtain the mechanism predicted drilling speed.

[0037] In some embodiments of the present invention, the noise reduction data includes drilling speed influencing factor data and drilling speed measurement data, and the noise reduction data and the mechanism predicted drilling speed are combined to obtain drilling speed prediction training data, including: The drilling speed influencing factor data and the mechanism predicted drilling speed are combined as the model input variables, the drilling speed measurement data are used as the model output variables, and the model input variables and model output variables are normalized to obtain the drilling speed prediction training data.

[0038] Specifically, in order to more fully mine the data features, the embodiment reasonably considers and integrates the mechanism model of the drilling project while performing the prediction of the machine learning algorithm. In this process, the embodiment first obtains experimental data through simulation experiments, fits the mechanism model to the experimental data, and uses the least squares method to solve the mechanism model coefficients, and then uses the obtained mechanism model to predict the noise reduction data to obtain the mechanism predicted drilling speed. Then the embodiment uses the predicted mechanism predicted drilling speed and the noise reduction data as the model input variables of the drilling engineering drilling speed prediction network, and uses the actual measured drilling speed measurement value as the model output variable of the drilling engineering drilling speed prediction network, and obtains the drilling speed prediction training data after normalizing each data through the maximum and minimum normalization algorithm.

[0039] In some embodiments of the present invention, Figure 5 Schematic diagram of the particle swarm optimization algorithm of the embodiment of the present invention. Figure 5 As shown in the figure, the network parameters of the initial drilling engineering drilling speed prediction network are iteratively optimized based on the particle swarm optimization algorithm, including: S501, using the network parameters of the initial drilling engineering drilling speed prediction network as the optimization target parameters of the particle swarm optimization algorithm, and initializing the particle swarm to be optimized according to the optimization target parameters; S502, updating the individual positions of particles of the particle swarm to be optimized based on a preset speed update formula and a preset position update formula to obtain an optimized particle swarm; S503, calculating the individual fitness of each particle in the optimized particle swarm based on the mean relative error method, updating the individual optimal value and the global optimal value according to the individual fitness, and determining a new round of population to be optimized, iterating the optimization process until the preset maximum number of iterations is reached.

[0040] In some embodiments of the present invention, Figure 6 FIG. 1 is a flow chart of iterative updating of the population to be optimized according to an embodiment of the present invention. Figure 6 As shown, the individual optimal value and the global optimal value are updated according to the individual fitness and a new round of population to be optimized is determined, including: S601, compare the individual fitness of each particle individual with the historical optimal fitness of each particle individual to obtain a new round of historical optimal fitness, take the particle individual corresponding to the new round of historical optimal fitness as the new round of individual optimal value, and form a new round of population to be optimized with the new round of individual optimal values; S602: Determine the current global optimal value according to the new round of individual optimal values, and compare the current global optimal value with the historical global optimal value to obtain a new round of global optimal value.

[0041] Specifically, in the drilling engineering drilling speed prediction network training process, in order to reduce the amount of calculation and increase the training speed, the embodiment adopts the particle swarm optimization algorithm to perform model training.

[0042] First, the embodiment determines the parameters that need to be optimized based on the initial drilling engineering drilling speed prediction network. Among them, the drilling engineering drilling speed prediction network is constructed by combining a time series convolutional network and a long short-term memory network. The model parameters that need to be optimized include the number of layers and convolution kernel size of the time series convolutional network, the hidden layer parameters and number of layers of the long short-term memory network, the initial learning rate, weight decay and sliding window. The embodiment uses these model parameters as the optimization target parameters of the particle swarm optimization algorithm, sets the optimization range of each parameter, and initializes the particle swarm to be optimized within the optimization range. In addition, considering that the prediction model is more complex, the number of particle swarms can be set a little more to facilitate finding the optimal solution, but at the same time, the equipment performance needs to be considered. The larger the particle swarm, the higher the requirements for equipment performance. For this reason, the embodiment sets the number of particle swarms to 50 when initializing the particle swarm.

[0043] Then the embodiment needs to calculate the fitness value of each particle in the current generation. The calculation method is to substitute the parameters in the particle into the drilling speed prediction network of the drilling engineering to predict the drilling speed, and calculate the average relative error between the predicted drilling speed and the actual drilling speed as the fitness value of the population. After the fitness value is calculated by the embodiment, it is used as the historical optimal fitness of each particle in the first generation, and the position of each particle at this time is used as the initial historical optimal position.

[0044] Then, the embodiment updates the speed and position of each particle through a preset speed update formula and a position update formula, wherein the speed update formula is expressed as follows:

[0045] The position update formula is as follows:

[0046] in, Represents particles In the In the iteration dimensional velocity vector, Represents particles In the In the iteration dimensional position vector, represents the number of iterations, represents the inertia weight, represents the individual learning factor, represents the group learning factor, and For interval The random number inside increases the randomness of the search.

[0047] The embodiment updates each particle through the above-mentioned speed update formula and position update formula to obtain the updated optimized particle group. Then the fitness value of each particle in the optimized particle group is calculated by the average relative error method. For each particle, the fitness value of the updated particle is compared with its historical optimal fitness, and the higher value is used as the historical optimal fitness of the new round, and the corresponding particle individual is retained as the individual optimal value of the new round, and the obtained new round of individual optimal values ​​is combined as the new round of population to be optimized. Then the current global optimal value is found from the individual optimal value of the new round, and the global optimal value of the new round is obtained after the fitness is compared with the historical global optimal value.

[0048] The last embodiment repeatedly iterates the optimization process until the preset maximum number of iterations is reached, and uses the global optimal value at this time as the optimized network parameter to complete the training of the drilling speed prediction network for drilling engineering.

[0049] In summary, in order to effectively reduce the noise of the collected data, fully explore the data features, and improve the training speed. The present invention first screens the acquired drilling construction data to obtain effective construction data, performs variational mode decomposition algorithm to reduce the noise of the effective construction data to obtain reduced noise data, performs mechanism model prediction on the reduced noise data to obtain mechanism predicted drilling speed, and combines the reduced noise data and mechanism predicted drilling speed to obtain drilling speed prediction training data; then the drilling speed prediction training data is input into the initial drilling engineering drilling speed prediction network, and the network parameters of the initial drilling engineering drilling speed prediction network are iteratively optimized based on the particle swarm optimization algorithm to obtain a fully trained drilling engineering drilling speed prediction network. The present invention can effectively reduce the noise of the data through the variational mode decomposition algorithm, and can effectively mine the data features and improve the model accuracy by combining the mechanism model prediction with the drilling mechanism model, and iteratively optimize the network parameters through the particle swarm optimization algorithm, which can reduce the amount of calculation in the training process and improve the training efficiency.

[0050] The present invention also provides a network application method for predicting drilling speed in drilling engineering, combining Figure 7 Come and see, Figure 7 A flow chart of an embodiment of a network application method for predicting drilling speed in drilling engineering provided by the present invention is shown in FIG. Figure 7 As shown, the drilling speed prediction network application method for drilling engineering includes: S701, obtaining construction data of the drilling project to be predicted; S702, inputting the drilling engineering construction data into the well-trained drilling engineering drilling speed prediction network to obtain the drilling speed prediction result; The fully trained drilling engineering drilling speed prediction network is determined according to the above-mentioned drilling engineering drilling speed prediction network training method.

[0051] In an embodiment of the present invention, first, the drilling engineering construction data to be predicted is effectively acquired, and then the drilling speed of the drilling machinery is effectively predicted using the above-mentioned fully trained drilling engineering drilling speed prediction network, and the drilling speed prediction result can be output.

[0052] like Figure 8 As shown, the present invention also provides an electronic device 800. The electronic device 800 includes a processor 801, a memory 802 and a display 803. Figure 8 Only some components of the electronic device 800 are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0053] In some embodiments, the processor 801 may be a central processing unit (CPU), a microprocessor or other data processing chip, which is used to run the program code or process data stored in the memory 802, such as the drilling engineering drilling speed prediction network training method and / or the drilling engineering drilling speed prediction network application method in the present invention.

[0054] In some embodiments, the processor 801 may be a single server or a server group. The server group may be centralized or distributed. In some embodiments, the processor 801 may be local or remote. In some embodiments, the processor 801 may be implemented in a cloud platform. In one embodiment, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-cloud, etc., or any combination thereof.

[0055] In some embodiments, the memory 802 may be an internal storage unit of the electronic device 800, such as a hard disk or memory of the electronic device 800. In other embodiments, the memory 802 may also be an external storage device of the electronic device 800, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc., equipped on the electronic device 800.

[0056] Furthermore, the memory 802 may include both an internal storage unit of the electronic device 800 and an external storage device. The memory 802 is used to store application software installed in the electronic device 800 and various data.

[0057] In some embodiments, the display 803 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 803 is used to display information of the electronic device 800 and to display a visual user interface. The components 801-803 of the electronic device 800 communicate with each other via a system bus.

[0058] In one embodiment, when the processor 801 executes the drilling engineering drilling speed prediction network training program in the memory 802, the following steps may be implemented: The acquired drilling construction data is screened to obtain effective construction data, the effective construction data is denoised by using a variational mode decomposition algorithm to obtain denoised data, the denoised data is predicted by a mechanism model to obtain a mechanism-predicted drilling speed, and the denoised data and the mechanism-predicted drilling speed are combined to obtain drilling speed prediction training data; The drilling speed prediction training data is input into the initial drilling engineering drilling speed prediction network. The network parameters of the initial drilling engineering drilling speed prediction network are iteratively optimized based on the particle swarm optimization algorithm to obtain a fully trained drilling engineering drilling speed prediction network.

[0059] In one embodiment, when the processor 801 executes the drilling engineering drilling speed prediction network application in the memory 802, the following steps may be implemented: Obtain the construction data of the drilling project to be predicted; The drilling engineering construction data is input into the well-trained drilling engineering drilling speed prediction network to obtain the drilling speed prediction result.

[0060] It should be understood that: when the processor 801 executes the drilling engineering drilling speed prediction network training program and / or the drilling engineering drilling speed prediction network application program in the memory 802, in addition to the above functions, other functions can also be implemented. For details, please refer to the description of the corresponding method embodiments above.

[0061] Furthermore, the embodiment of the present invention does not specifically limit the type of the electronic device 800 mentioned, and the electronic device 800 may be a portable electronic device such as a mobile phone, a tablet computer, a personal digital assistant (PDA), a wearable device, a laptop computer, etc. Exemplary embodiments of portable electronic devices include but are not limited to portable electronic devices equipped with IOS, Android, Microsoft or other operating systems. The above-mentioned portable electronic devices may also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the present invention, the electronic device 800 may not be a portable electronic device, but a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0062] Accordingly, an embodiment of the present application also provides a computer-readable storage medium, which is used to store computer-readable programs or instructions. When the program or instructions are executed by a processor, it can implement the steps or functions in the drilling engineering drilling speed prediction network training method and / or the drilling engineering drilling speed prediction network application method provided in the above-mentioned method embodiments.

[0063] Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware (such as a processor, a controller, etc.) through a computer program, and the computer program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0064] The drilling engineering drilling speed prediction network training method, application method, electronic device and medium provided by the present invention are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A drilling engineering drilling speed prediction network training method, characterized in that: include: Performing data screening on the acquired drilling construction data to obtain effective construction data, performing variational mode decomposition algorithm denoising on the effective construction data to obtain denoised data, performing mechanism model prediction on the denoised data to obtain mechanism predicted drilling speed, and combining the denoised data and the mechanism predicted drilling speed to obtain drilling speed prediction training data; The drilling speed prediction training data is input into an initial drilling engineering drilling speed prediction network, and the network parameters of the initial drilling engineering drilling speed prediction network are iteratively optimized based on a particle swarm optimization algorithm to obtain a fully trained drilling engineering drilling speed prediction network.

2. The drilling engineering drilling speed prediction network training method according to claim 1 is characterized in that: The step of screening the acquired drilling construction data to obtain effective construction data includes: Based on the Spearman correlation coefficient method and the Mantel test method, the obtained drilling construction data is subjected to correlation analysis to obtain the correlation coefficient of each parameter type in the drilling construction data; The drilling construction data is screened according to the correlation coefficient to obtain effective construction data.

3. The drilling engineering drilling speed prediction network training method according to claim 1 is characterized in that: The step of performing a variational mode decomposition algorithm on the effective construction data to obtain denoised data includes: Initializing algorithm parameters of a variational mode decomposition algorithm according to the effective construction data; Performing modal decomposition on the effective construction data based on the variational modal decomposition algorithm to obtain a number of modal components; Spectral analysis and statistical feature analysis are performed on the modal components to obtain effective modal components, and the effective modal components are reorganized to obtain noise reduction data.

4. The drilling engineering drilling speed prediction network training method according to claim 1 is characterized in that: The performing mechanism model prediction on the noise reduction data to obtain the mechanism predicted drilling speed includes: Solving the model parameters of the initial mechanism model based on the least squares method; The noise reduction data is input into the mechanism model to predict the drilling speed to obtain the mechanism predicted drilling speed.

5. The drilling engineering drilling speed prediction network training method according to claim 1 is characterized in that: The noise reduction data includes drilling speed influencing factor data and drilling speed measurement data, and the noise reduction data and the mechanism predicted drilling speed are combined to obtain drilling speed prediction training data, including: The drilling speed influencing factor data and the mechanism predicted drilling speed are combined as model input variables, the drilling speed measurement data are used as model output variables, and the model input variables and the model output variables are normalized to obtain drilling speed prediction training data.

6. The drilling engineering drilling speed prediction network training method according to claim 1 is characterized in that: The iterative optimization of the network parameters of the initial drilling engineering drilling speed prediction network based on the particle swarm optimization algorithm includes: Using the network parameters of the initial drilling engineering drilling speed prediction network as the optimization target parameters of the particle swarm optimization algorithm, and initializing the particle swarm to be optimized according to the optimization target parameters; Based on a preset speed update formula and a preset position update formula, the individual positions of particles in the particle group to be optimized are updated to obtain an optimized particle group; The individual fitness of each particle in the optimized particle swarm is calculated based on the mean relative error method, the individual optimal value and the global optimal value are updated according to the individual fitness, and a new round of population to be optimized is determined, and the optimization process is iterated until a preset maximum number of iterations is reached.

7. The drilling engineering drilling speed prediction network training method according to claim 6 is characterized in that: The updating of the individual optimal value and the global optimal value according to the individual fitness and determining a new round of population to be optimized includes: Compare the individual fitness of each of the individual particles with the historical optimal fitness of each of the individual particles to obtain a new round of historical optimal fitness, use the individual particles corresponding to the new round of historical optimal fitness as the new round of individual optimal value, and form a new round of population to be optimized with the new round of individual optimal values; The current global optimal value is determined according to the new round of individual optimal values, and the current global optimal value is compared with the historical global optimal value to obtain a new round of global optimal value.

8. A network application method for predicting drilling speed in drilling engineering, characterized in that: include: Obtain the construction data of the drilling project to be predicted; Inputting the drilling engineering construction data into a well-trained drilling engineering drilling speed prediction network to obtain a drilling speed prediction result; Wherein, the fully trained drilling engineering drilling speed prediction network is determined according to the drilling engineering drilling speed prediction network training method according to any one of claims 1 to 7.

9. An electronic device comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the drilling engineering drilling speed prediction network training method according to any one of claims 1 to 7 and / or the drilling engineering drilling speed prediction network application method according to claim 8 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the drilling engineering drilling speed prediction network training method according to any one of claims 1 to 7 and / or the drilling engineering drilling speed prediction network application method according to claim 8 are implemented.

Images