Calculation Method, Device, Storage Medium and Terminal for Near-Bit Inclination Angle

Abstract

The present invention provides a method, device, storage medium and terminal for calculating the inclination angle of a near-bit, including: obtaining the past data of the near-bit, and establishing a correction model according to the past data; obtaining the initial measured inclination angle value of the near-bit at the current moment; obtaining the relevant parameter information of the near-bit at the current moment and the previous moment, and calculating the error coefficient of the inclination angle measuring tool according to the relevant parameter information at the current moment; calculating the current angle change ratio of the near-bit; inputting the relevant parameter information of the near-bit at the current moment and the previous moment into the correction model to obtain a primary output result and a secondary output result, and performing correction processing on the primary output result, the initial measured inclination angle value and the secondary output result according to the error coefficient and the angle change ratio to obtain the target inclination angle. Without changing the hardware conditions, the present invention effectively improves the accuracy of the inclination angle measurement result inside the near-bit.

Description

Technical Field

[0001] The present invention belongs to the technical field of drilling, and particularly relates to a method, device, storage medium and terminal for calculating the inclination angle of a near-bit Background Art

[0002] During the drilling process, the drill bit is the main tool for breaking rocks, and the wellbore is formed by the drill bit breaking rocks. The quality of a wellbore and the time taken are related not only to the characteristics of the formation rocks to be drilled and the performance of the drill bit itself, but more importantly to the degree of matching between the drill bit and the formation. The reasonable selection of the drill bit plays an important role in improving the drilling speed and reducing the comprehensive drilling cost. The drill bit is one of the important tools for oil drilling work. Whether the drill bit is suitable for the rock properties and its quality plays a very important role in the selection of drilling techniques, especially having a huge impact on drilling quality, drilling speed, and drilling cost. The PDC drill bit is a rock-breaking tool widely used in the current oil and gas exploration and development industry, which effectively improves the mechanical drilling tool and shortens the drilling cycle.

[0003] During the near-bit drilling process, in order to understand the drilling situation, it is necessary to continuously measure the current inclination angle of the drill bit. However, due to the high-speed movement of the near-bit during use, the results measured by conventional measurement tools have too large errors and accurate inclination angles cannot be obtained. But if the drill bit is stopped for measurement, it will not only affect the construction progress, but also easily pose the risk of collapse of the drilling rock formation, affecting construction safety. Summary of the Invention

[0004] In view of the above-mentioned disadvantages of the prior art, the purpose of the present invention is to provide a method, device, storage medium and terminal for calculating the inclination angle of a near-bit, which is used to solve the problem of inaccurate measurement of the inclination angle during the use of the near-bit in the prior art.

[0005] To achieve the above object and other related objects, the present invention provides a method for calculating the inclination angle of a near-bit, including:

[0006] Obtain the historical data of the near-bit, and establish a correction model according to the historical data;

[0007] Start the inclination angle measurement tool located inside the near-bit to obtain the initial measurement inclination angle value of the near-bit at the current moment, wherein a gyroscope is installed inside the inclination angle measurement tool;

[0008] Send an ultrasonic signal to the control terminal, obtain the relevant parameter information of the near-bit at the current moment and the previous moment according to the feedback signal of the control terminal, and calculate the error coefficient of the inclination angle measurement tool according to the relevant parameter information at the current moment;

[0009] A laser emitter emits laser signals at the current moment and the previous moment respectively, and acquires a first reflection signal and a second reflection signal respectively. The current angle change ratio of the near-bit is calculated according to the first reflection signal and the second reflection signal, wherein the interval between the current moment and the previous moment is between 1 and 3 s;

[0010] Input the relevant parameter information of the near-bit at the current moment and the previous moment into the correction model to obtain a primary output result and a secondary output result. The primary output result, the initial measured dip value and the secondary output result are corrected according to the error coefficient and the angle change ratio to obtain the target dip.

[0011] Optionally, acquiring the historical data of the near-bit and establishing a correction model according to the historical data includes:

[0012] Acquire the relevant parameter information at different moments in the historical data of the near-bit, and the historical dip information corresponding to the relevant parameter information, wherein the relevant parameter information includes rotational speed information, vibration frequency information, drilling depth information and pressure information;

[0013] An initial neural network model is established according to the relevant parameter information and the historical dip information. The initial neural network model includes a first input neuron, a second input neuron, a third input neuron, a fourth input neuron, a fifth input neuron, a hidden neuron and an output neuron. After the first input neuron, the second input neuron, the third input neuron, the fourth input neuron and the fifth input neuron are fitted by a fitting neuron, the model output result is output through the output neuron;

[0014] The rotational speed information, the vibration frequency information, the drilling depth information and the pressure information at the same moment are respectively input into the first input neuron, the second input neuron, the third input neuron and the fourth input neuron as training data, and the historical dip information corresponding to this moment is input into the fifth input neuron as comparison data to compare with the output result of the output neuron;

[0015] Optimize and adjust the hidden neurons in the initial neural network model according to the difference between the historical dip information and the output result;

[0016] Continuously input the relevant parameter information and the historical dip information into the initial neural network model for training until the difference between the output result of the output neuron and the corresponding historical dip information is less than the model threshold, and then use the adjusted initial neural network model as the correction model.

[0017] Optionally, the size of the model threshold is positively correlated with the size of the near-bit

[0018] Optionally, sending an ultrasonic signal to the control terminal to obtain relevant parameter information of the near-bit at the current moment, and calculating the error coefficient of the inclination measurement tool according to the relevant parameter information includes:

[0019] Sending an ultrasonic signal to the control terminal;

[0020] The control terminal reads the current moment, rotational speed information, vibration frequency information, drilling depth information, and pressure information of the near-bit according to the ultrasonic signal;

[0021] Sending the rotational speed information, the vibration frequency information, the drilling depth information, and the pressure information to the receiving end in the near-bit;

[0022] The receiving end calculates the error coefficient of the inclination measurement tool under the current conditions according to the rotational speed information, the vibration frequency information, the drilling depth information, and the pressure information.

[0023] Optionally, the error coefficient is positively correlated with the magnitude of the vibration frequency information and the magnitude of the rotational speed, and the error coefficient is negatively correlated with the magnitude of the pressure information and the magnitude of the drilling depth information.

[0024] Optionally, emitting laser signals at the current moment and the previous moment respectively through a laser emitter and obtaining a first reflection signal and a second reflection signal respectively, and calculating the current angle change ratio of the near-bit according to the first reflection signal and the second reflection signal includes:

[0025] Emitting the same beam of laser signal to the inner wall of the near-bit at the previous moment and the current moment respectively;

[0026] Obtaining the photosensitive images when the laser signal is reflected at the previous moment and the current moment through a photosensitive camera, where the photosensitive image is the image of the laser signal on the reflection surface;

[0027] Determining the reflection positions of the laser signal according to the brightness values of the photosensitive images at the previous moment and the current moment respectively, and obtaining the reflection intensities of the first reflection signal and the second reflection signal respectively;

[0028] Determining the current angle change ratio of the near-bit according to the magnitudes of the reflection positions and the reflection intensities at the current moment and the previous moment.

[0029] Optionally, inputting the relevant parameter information of the near-bit at the current moment and the previous moment into the correction model to obtain a primary output result and a secondary output result, and performing correction processing on the primary output result, the initial measured inclination value, and the secondary output result according to the error coefficient and the angle change ratio to obtain the target inclination angle, includes:

[0030] Obtaining a real-time inclination angle range according to the initial measured inclination value and the error coefficient, and determining whether the primary output result is within the real-time inclination angle range;

[0031] After determining that the primary output result is within the real-time inclination angle range, calculating the angle difference between the primary output result and the secondary output result within a unit time, and judging the magnitude relationship between the angle difference and the angle change ratio;

[0032] If the difference between the angle difference and the angle change ratio is less than or equal to the error threshold, then taking the primary output result as the target inclination angle;

[0033] If the difference between the angle difference and the angle change ratio is greater than the error threshold, then calculating the target inclination angle according to the secondary output result, the angle change ratio, and the time difference, where the time difference is the difference between the previous moment and the current moment.

[0034] The present invention also provides a calculation device for the near-bit inclination angle, including:

[0035] A modeling module, configured to obtain the historical data of the near-bit and establish a correction model according to the historical data;

[0036] An initial measurement module, configured to start an inclination angle measurement tool located inside the near-bit to obtain the initial measured inclination value of the near-bit at the current moment, where a gyroscope is installed inside the inclination angle measurement tool;

[0037] An error calculation module, configured to send an ultrasonic signal to a control terminal, obtain the relevant parameter information of the near-bit at the current moment and the previous moment according to the feedback signal of the control terminal, and calculate the error coefficient of the inclination angle measurement tool according to the relevant parameter information at the current moment;

[0038] A ratio calculation module, configured to emit laser signals at the current moment and the previous moment respectively through a laser emitter and obtain a first reflection signal and a second reflection signal respectively, and calculate the current angle change ratio of the near-bit according to the first reflection signal and the second reflection signal, where the interval between the current moment and the previous moment is between 1 and 3 s;

[0039] The correction module is used to input the relevant parameter information of the near-bit at the current moment and the previous moment into the correction model to obtain a primary output result and a secondary output result, and perform correction processing on the primary output result, the initial measured dip value, and the secondary output result according to the error coefficient and the angle change ratio to obtain the target dip angle.

[0040] The present invention provides a storage medium on which a computer program is stored, and when the program is executed by a processor, the above-mentioned method for calculating the near-bit dip angle is implemented.

[0041] The present invention provides a terminal, including: a processor and a memory; the memory is used to store a computer program; the processor is used to execute the computer program stored in the memory so that the terminal executes the above-mentioned method for calculating the near-bit dip angle.

[0042] As described above, the method, device, storage medium, and terminal for calculating the near-bit dip angle according to the present invention have the following beneficial effects:

[0043] The present invention establishes a correction model for the past data of the near-bit, so as to compare and correct the measurement results of the measurement tool according to the correction model. Instead of relying on traditional tool measurements, it outputs results by cooperating with a neural network model, effectively improving the accuracy of the measurement of the near-bit internal dip angle. At the same time, the relevant parameter information at the current moment is obtained to obtain the error coefficient of the measurement tool at the current moment, and the angle change ratio of the near-bit at the current moment is calculated in cooperation with the laser emitter, so as to perform correction processing on the primary output result and the secondary output result output by the correction model through the error coefficient and the angle change ratio to obtain a more accurate target dip angle, effectively improving the accuracy of the measurement result. Without changing the hardware conditions, the measurement process of the near-bit internal dip angle can be realized, and the near-bit does not need to be stopped, which not only speeds up the construction period, but also does not cause the risk of rock formation collapse inside the well due to stopping the near-bit. Moreover, during the measurement process of the measurement tool, the gyroscope can effectively reduce the measurement deviation and improve the accuracy of the subsequent obtained target dip angle. Description of the Drawings

[0044] Figure 1 It shows a flowchart of the method for calculating the near-bit dip angle according to the present invention.

[0045] Figure 2 It shows a flowchart of step S104 in the method for calculating the near-bit dip angle according to the present invention.

[0046] Figure 3 It shows a flowchart of step S105 in the method for calculating the near-bit dip angle according to the present invention.

[0047] Figure 4The structural block diagram of the near-bit inclination angle calculation device according to the present invention is shown. Specific embodiments

[0048] The following uses specific examples to illustrate the implementation manners of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific implementation manners. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that, without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0049] It should be noted that the diagrams provided in the following embodiments only illustrate the basic concept of the present invention in a schematic manner. Therefore, only the components related to the present invention are shown in the diagrams, rather than being drawn according to the number, shape, and size of the components in actual implementation. The types, quantities, and proportions of the components in actual implementation can be arbitrarily changed, and the component layout type may also be more complex.

[0050] The near-bit inclination angle calculation method, device storage medium, and terminal of the present invention establish a correction model based on the past data of the near-bit, so as to compare and correct the measurement results of the measurement tool according to the correction model. Instead of relying on traditional tool measurements, it outputs results by cooperating with a neural network model, effectively improving the accuracy of the near-bit internal inclination angle measurement. Moreover, relevant parameter information at the current moment is obtained simultaneously to obtain the error coefficient of the measurement tool at the current moment, and the angle change ratio of the near-bit at the current moment is calculated in cooperation with a laser emitter, so as to correct the primary output result and the secondary output result output by the correction model through the error coefficient and the angle change ratio to obtain a more accurate target inclination angle, effectively improving the accuracy of the measurement result. Without changing the hardware conditions, the measurement process of the near-bit internal inclination angle can be realized, and the near-bit does not need to be stopped, which not only speeds up the construction period, but also does not cause the risk of rock formation collapse inside the well due to stopping the near-bit. Moreover, during the measurement process of the measurement tool, the gyroscope can effectively reduce the measurement deviation and improve the accuracy of the subsequent obtained target inclination angle.

[0051] As Figure 1 shown, in an embodiment, a near-bit inclination angle calculation method of the present invention refers to Figure 1 , and includes the following steps:

[0052] S101. Obtain the past data of the near-bit, and establish a correction model according to the past data.

[0053] In some embodiments, the obtaining the past data of the near-bit and establishing a correction model according to the past data includes:

[0054] Obtain the relevant parameter information at different times in the past data of the near-bit, and the corresponding historical inclination angle information of the relevant parameter information, where the relevant parameter information includes rotational speed information, vibration frequency information, drilling depth information, and pressure information;

[0055] Establish an initial neural network model according to the relevant parameter information and the historical inclination angle information, where the initial neural network model includes a first input neuron, a second input neuron, a third input neuron, a fourth input neuron, a fifth input neuron, a hidden neuron, and an output neuron. After the first input neuron, the second input neuron, the third input neuron, the fourth input neuron, and the fifth input neuron are fitted by a fitting neuron, the model output result is output through the output neuron;

[0056] Respectively input the rotational speed information, the vibration frequency information, the drilling depth information, and the pressure information at the same time as training data into the first input neuron, the second input neuron, the third input neuron, and the fourth input neuron, and input the corresponding historical inclination angle information at this time into the fifth input neuron as comparison data to compare with the output result of the output neuron;

[0057] Optimize and adjust the hidden neurons in the initial neural network model according to the difference between the historical inclination angle information and the output result;

[0058] Continuously input the relevant parameter information and the historical inclination angle information into the initial neural network model for training until the difference between the output result of the output neuron and the corresponding historical inclination angle information is less than the model threshold, and then use the adjusted initial neural network model as the correction model.

[0059] Specifically, since there are multiple drilling operations of the same type of near-bit in the same area, the past data of the near-bit is used as the basis for establishing the subsequent neural network model. The past data of the near-bit includes the relevant parameter information at different times and the measured historical inclination angle information at this time, and the measurement method of the historical inclination angle information is measured by the method in the prior art, which will not be elaborated here.

[0060] After that, an initial neural network model is established based on relevant parameter information and historical inclination information, such as a deep feed-forward neural network model (DFF, Deep Feed-forward). Since the measurement tool is generally affected by the depth, pressure, near-bit rotation speed, and vibration frequency inside the drill during the measurement process, the rotation speed information, the vibration frequency information, the drill depth information, and the pressure information in the relevant parameter information are respectively input as training data to the first input neuron, the second input neuron, the third input neuron, and the fourth input neuron, and the historical inclination information at this moment and under this parameter condition is input to the fifth input neuron, so as to be used as comparison data in the subsequent process to compare and train the output results of the output neuron, and to optimize and adjust the hidden neurons during the training process, thereby optimizing the entire initial neural network model to obtain a neural network model that better meets the measurement accuracy.

[0061] Exemplarily, after continuously inputting relevant parameter information and historical inclination information to the initial neural network model, by comparing the difference between the output result of the output neuron and the historical inclination information used as comparison data with the model threshold, so as to continuously optimize and adjust the hidden neurons according to the size of the difference between the two and the model threshold, to obtain a neural network model that better meets the near-bit working environment, and after the difference between the output result of the output neuron and the corresponding historical inclination information is less than the model threshold, the adjusted initial neural network model is used as the correction model.

[0062] Among them, the correction model adopts a feed-forward network composed of multiple hidden neurons. By increasing the hidden layer, overfitting can be reduced, the generalization ability can be improved, and the accuracy of the final output result of the correction model can be improved.

[0063] In some embodiments, the size of the model threshold is positively correlated with the size of the near-bit.

[0064] It should be noted that the size of the model threshold can be set manually according to the size of the near-bit or an empirical value can be used. This solution does not limit this and will not be elaborated here.

[0065] S102. Start the inclination measurement tool located inside the near-bit to obtain the initial measurement inclination value of the near-bit at the current moment, where a gyroscope is installed inside the inclination measurement tool.

[0066] In this embodiment, the influence caused by the rotation and vibration of the near-bit is reduced by the gyroscope inside the inclination measurement tool, thereby improving the accuracy of the initial measurement inclination value measured by the inclination measurement tool. It should be noted that the inclination measurement tool adopts a solution in the prior art, and the installation process of the gyroscope and the inclination measurement tool also adopts a conventional method. This solution does not involve improvements to the installation methods of the inclination measurement tool and the gyroscope themselves, and will not be elaborated here.

[0067] S102. Send an ultrasonic signal to the control terminal, obtain the relevant parameter information of the near-bit at the current moment and the previous moment according to the feedback signal of the control terminal, and calculate the error coefficient of the inclination measurement tool according to the relevant parameter information at the current moment.

[0068] In some embodiments, sending the ultrasonic signal to the control terminal to obtain the relevant parameter information of the near-bit at the current moment and calculating the error coefficient of the inclination measurement tool according to the relevant parameter information includes:

[0069] Send an ultrasonic signal to the control terminal;

[0070] The control terminal reads the rotation speed information, vibration frequency information, drilling depth information, and pressure information of the near-bit at the current moment according to the ultrasonic signal;

[0071] Send the rotation speed information, the vibration frequency information, the drilling depth information, and the pressure information to the receiving end inside the near-bit;

[0072] The receiving end calculates the error coefficient of the inclination measurement tool under the current conditions according to the rotation speed information, the vibration frequency information, the drilling depth information, and the pressure information.

[0073] In this embodiment, during the drilling process of the near-bit, in order to calculate the error coefficient of the entire inclination measurement tool under the current conditions, an ultrasonic generator is used to send an ultrasonic signal to the control terminal of the near-bit, so that the receiving end can receive the feedback signal of the control terminal and timely obtain the relevant parameter information of the near-bit at the current moment, including the rotation speed information, the vibration frequency information, the drilling depth information, and the pressure information. After obtaining the rotation speed information, the vibration frequency information, the drilling depth information, and the pressure information of the near-bit at the current moment, the influence of the current environment on the inclination measurement tool can be calculated, so as to calculate the error coefficient of the inclination measurement tool under the current conditions. This is to facilitate the subsequent calculation of the error range of the inclination measurement tool under the current conditions, and to facilitate the subsequent comparison and screening of the output results of the correction model.

[0074] In some embodiments, the error coefficient is positively correlated with the magnitude of the vibration frequency information and the magnitude of the rotational speed, and the error coefficient is negatively correlated with the magnitude of the pressure information and the magnitude of the drilling depth information.

[0075] S104. Laser signals are emitted by a laser emitter at the current moment and the previous moment respectively, and a first reflection signal and a second reflection signal are obtained respectively. The current angular change ratio of the near-bit is calculated according to the first reflection signal and the second reflection signal, where the interval between the current moment and the previous moment is between 1 and 3 s.

[0076] In some embodiments, referring to Figure 2 the calculating the current angular change ratio of the near-bit according to the first reflection signal and the second reflection signal by emitting laser signals by the laser emitter at the current moment and the previous moment respectively includes:

[0077] S201. The same laser signal is emitted to the inner wall of the near-bit at the previous moment and the current moment respectively;

[0078] S202. A photosensitive image of the laser signal during reflection at the previous moment and the current moment is obtained by a photosensitive camera, where the photosensitive image is an image of the laser signal on the reflection surface;

[0079] S203. The reflection positions of the laser signal are determined according to the brightness values of the photosensitive images at the previous moment and the current moment respectively, and the reflection intensities of the first reflection signal and the second reflection signal are obtained respectively;

[0080] S204. The current angular change ratio of the near-bit at the current moment is determined according to the magnitudes of the reflection positions and the reflection intensities at the current moment and the previous moment.

[0081] In this embodiment, when the dip measurement tool measures inside the near-bit, since the current dip cannot be directly obtained, the current angular change ratio at the current moment can be calculated through the laser change situation inside the near-bit, so as to facilitate further judgment on the output result of the correction model according to the angular change ratio and realize the data screening process.

[0082] Exemplarily, at the previous moment and the current moment, the same laser signal is emitted inside the near-bit, and then the photosensitive image of the laser signal on the reflection surface is obtained through the built-in photosensitive camera, so as to determine the reflection position of the laser signal according to the brightness values of the photosensitive images at the previous moment and the current moment, thereby obtaining the deviation of the reflection positions at the previous moment and the current moment. Then, the reflection intensities of the first reflection signal and the second reflection signal are obtained through the laser receiver to obtain the difference in the reflection intensities of the laser signals at the previous moment and the current moment, so as to calculate the angle change ratio at the current moment according to the difference in the reflection intensities, the deviation of the reflection positions, and the difference between the previous moment and the current moment. Wherein, the angle change ratio is the change value of the inclination angle inside the near-bit per unit time, so as to facilitate subsequent comparison and correction of the output results of the calibration model.

[0083] Wherein, the time interval between the previous moment and the current moment is within 1 to 3 seconds, so as to avoid obvious deviation of the inclination angle due to too large a time interval and affect the accuracy of the final inclination angle measurement result.

[0084] S105. Input the relevant parameter information of the near-bit at the current moment and the previous moment into the correction model to obtain a primary output result and a secondary output result, and perform correction processing on the primary output result, the initial measured inclination angle value, and the secondary output result according to the error coefficient and the angle change ratio to obtain the target inclination angle.

[0085] In some embodiments, referring to Figure 3 , the step of inputting the relevant parameter information of the near-bit at the current moment and the previous moment into the correction model to obtain a primary output result and a secondary output result, and performing correction processing on the primary output result, the initial measured inclination angle value, and the secondary output result according to the error coefficient and the angle change ratio to obtain the target inclination angle includes:

[0086] S301. Obtain the real-time inclination angle range according to the initial measured inclination angle value and the error coefficient, and determine whether the primary output result is within the real-time inclination angle range;

[0087] S302. After determining that the primary output result is within the real-time inclination angle range, calculate the angle difference between the primary output result and the secondary output result per unit time, and judge the magnitude relationship between the angle difference and the angle change ratio;

[0088] S303. If the difference between the angle difference and the angle change ratio is less than or equal to the error threshold, use the primary output result as the target inclination angle;

[0089] S304. If the difference between the angle difference and the angle change ratio is greater than the error threshold, calculate the target dip angle based on the secondary output result, the angle change ratio, and the time difference, where the time difference is the difference between the previous time and the current time.

[0090] In this embodiment, after obtaining the initial measured dip angle value measured by the dip angle measuring tool, the primary output results and secondary output results output by the correction model at the previous time and the current time, the error coefficient, and the angle change ratio, first obtain the real-time dip angle range at the current time according to the initial measured dip angle value and the error coefficient, and determine whether the primary output result is within the real-time dip angle range. If the primary output result is within the real-time dip angle range, perform subsequent judgments; otherwise, output a new dip angle result through the correction model. After determining that the primary output result is within the real-time dip angle range, calculate the angle difference between the primary output result and the secondary output result per unit time. By comparing the magnitudes of the angle difference and the angle change ratio, it can be determined whether the currently output primary output result meets the requirements. If the difference between the angle difference and the angle change ratio is less than or equal to the error threshold, use the primary output result as the target dip angle; if the difference between the angle difference and the angle change ratio is greater than the error threshold, it indicates that there is an obvious error in the primary output result. Therefore, calculate the target dip angle based on the secondary output result, the angle change ratio, and the time difference, where the time difference is the difference between the previous time and the current time, so as to obtain the final target dip angle, thereby effectively improving the accuracy of the near-bit internal dip angle measurement.

[0091] By using the above calculation method to obtain the dip angle inside the near-bit, accurate dip angle measurement results can be obtained without stopping the near-bit, effectively improving the drilling construction cycle. Moreover, through the non-stop treatment of the near-bit, the safety of the drilling construction is ensured.

[0092] It should be noted that the protection scope of the calculation method for the near-bit dip angle of the present invention is not limited to the execution order of the steps listed in this embodiment. Any solution achieved by adding or subtracting steps of the prior art and replacing steps according to the principle of the present invention is included in the protection scope of the present invention.

[0093] The present invention also provides a calculation device for the near-bit dip angle. Refer to Figure 4 , including:

[0094] A modeling module 401, configured to obtain the past data of the near-bit and establish a correction model according to the past data;

[0095] The initial measurement module 402 is configured to activate an inclination measurement tool located inside the near-bit to obtain the initial measurement inclination value of the near-bit at the current moment, wherein a gyroscope is installed inside the inclination measurement tool;

[0096] The error calculation module 403 is configured to send an ultrasonic signal to a control terminal, obtain relevant parameter information of the near-bit at the current moment and the previous moment according to the feedback signal of the control terminal, and calculate the error coefficient of the inclination measurement tool according to the relevant parameter information at the current moment;

[0097] The ratio calculation module 404 is configured to emit laser signals at the current moment and the previous moment respectively through a laser emitter and obtain a first reflection signal and a second reflection signal respectively, and calculate the current angle change ratio of the near-bit according to the first reflection signal and the second reflection signal, wherein the interval between the current moment and the previous moment is between 1 and 3 s;

[0098] The correction output module 405 is configured to input the relevant parameter information of the near-bit at the current moment and the previous moment into the correction model to obtain a primary output result and a secondary output result, and perform correction processing on the primary output result, the initial measurement inclination value, and the secondary output result according to the error coefficient and the angle change ratio to obtain the target inclination.

[0099] It should be noted that it should be understood that the division of each module of the above device is only a logical function division. In actual implementation, it can be fully or partially integrated into a physical entity, or physically separated. And these modules can all be implemented in the form of software called by a processing element; they can also all be implemented in the form of hardware; or some modules can be implemented in the form of software called by a processing element, and some modules can be implemented in the form of hardware. For example, the x module can be a separately established processing element, or can be integrated in a certain chip of the above device. In addition, it can also be stored in the memory of the above device in the form of program code, and called and executed by a certain processing element of the above device to perform the functions of the above x module. The implementation of other modules is similar. In addition, these modules can be fully or partially integrated together, or can be independently implemented. The processing element mentioned here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each of the above modules can be completed by the integrated logic circuit in the processor element in hardware or in the form of instructions in software.

[0100] For example, these above modules may be one or more integrated circuits configured to implement the above methods, such as: one or more Application Specific Integrated Circuits (ASICs), or, one or more Digital Signal Processors (DSPs), or, one or more Field Programmable Gate Arrays (FPGAs), etc. Again, when a certain above module is implemented in the form of a processing element scheduler code, the processing element may be a general-purpose processor, such as a Central Processing Unit (CPU) or other processors that can call program code. Again, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0101] A computer program is stored on the storage medium of the present invention, and when the program is executed by a processor, the above-described method for calculating the near-bit inclination angle is implemented. The storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic disks, USB flash drives, memory cards, or optical discs.

[0102] A terminal of the present invention includes: a processor and a memory;

[0103] The memory is used to store a computer program;

[0104] The processor is used to execute the computer program stored in the memory, so that the terminal executes the above-described method for calculating the near-bit inclination angle.

[0105] Preferably, the processor may be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0106] It should be noted that the calculation device for the near-bit inclination angle of the present invention can implement the calculation method for the near-bit inclination angle of the present invention. However, the implementation device for the calculation method for the near-bit inclination angle of the present invention includes, but is not limited to, the structure of the calculation device for the near-bit inclination angle listed in this embodiment. Any structural deformation and substitution of the prior art made according to the principle of the present invention are included in the protection scope of the present invention.

[0107] In summary, for the calculation method, device, storage medium and terminal of the near-bit inclination angle of the present invention, a correction model is established based on the past data of the near-bit, so as to compare and correct the measurement results of the measuring tool according to the correction model. It does not rely on traditional tool measurement, but outputs results by cooperating with a neural network model, effectively improving the accuracy of the measurement of the near-bit internal inclination angle. At the same time, relevant parameter information at the current moment is obtained to obtain the error coefficient of the measuring tool at the current moment, and the angle change ratio of the near-bit at the current moment is calculated in cooperation with a laser emitter, so as to correct the primary output result and the secondary output result output by the correction model through the error coefficient and the angle change ratio to obtain a more accurate target inclination angle, effectively improving the accuracy of the measurement result. Without changing the hardware conditions, the measurement process of the near-bit internal inclination angle can be realized, and it is not necessary to stop the near-bit, which not only speeds up the construction period, but also does not cause the risk of rock formation collapse inside the well due to stopping the near-bit. Moreover, during the measurement process of the measuring tool, the gyroscope can effectively reduce the measurement deviation and improve the accuracy of the subsequent obtained target inclination angle. Therefore, the present invention effectively overcomes various disadvantages in the prior art and has high industrial utilization value.

[0108] The above embodiments are only illustrative of the principles and effects of the present invention, and are not used to limit the present invention. Any person familiar with this technology can modify or change the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or changes made by those with ordinary knowledge in the technical field without departing from the spirit and technical idea disclosed by the present invention should still be covered by the claims of the present invention.

Claims

1. A calculation method for the near-bit dip angle, characterized in that, Including: Obtain the past data of the near-bit, and establish a correction model according to the past data; Start the inclination measurement tool located inside the near-bit to obtain the initial measurement inclination value of the near-bit at the current moment, wherein a gyroscope is installed inside the inclination measurement tool; Send an ultrasonic signal to the control terminal, obtain the relevant parameter information of the near-bit at the current moment and the previous moment according to the feedback signal of the control terminal, and calculate the error coefficient of the inclination measurement tool according to the relevant parameter information at the current moment; Send laser signals at the current moment and the previous moment through a laser emitter respectively, and obtain a first reflection signal and a second reflection signal respectively, and calculate the current angle change ratio of the near-bit according to the first reflection signal and the second reflection signal, wherein the interval between the current moment and the previous moment is between 1 and 3 s; Input the relevant parameter information of the near-bit at the current moment and the previous moment into the correction model to obtain a primary output result and a secondary output result, and perform correction processing on the primary output result, the initial measurement inclination value and the secondary output result according to the error coefficient and the angle change ratio to obtain the target inclination.

2. The calculation method for the near-bit dip angle according to claim 1, characterized in that, The obtaining the past data of the near-bit and establishing a correction model according to the past data includes: Obtain the relevant parameter information at different moments in the past data of the near-bit, and the historical inclination information corresponding to the relevant parameter information, wherein the relevant parameter information includes rotational speed information, vibration frequency information, drilling depth information and pressure information; Establish an initial neural network model according to the relevant parameter information and the historical inclination information, wherein the initial neural network model includes a first input neuron, a second input neuron, a third input neuron, a fourth input neuron, a fifth input neuron, a hidden neuron and an output neuron, and after the first input neuron, the second input neuron, the third input neuron, the fourth input neuron and the fifth input neuron are fitted by a fitting neuron, the model output result is output through the output neuron; Respectively input the rotational speed information, the vibration frequency information, the drilling depth information and the pressure information at the same moment as training data into the first input neuron, the second input neuron, the third input neuron and the fourth input neuron, and input the historical inclination information corresponding to this moment into the fifth input neuron as comparison data to compare with the output result of the output neuron; Optimize and adjust the hidden neurons in the initial neural network model according to the difference between the historical inclination information and the output result; Continuously input the relevant parameter information and the historical inclination information into the initial neural network model for training until the difference between the output result of the output neuron and the corresponding historical inclination information is less than the model threshold, and then use the adjusted initial neural network model as the correction model.

3. The calculation method for the near-bit dip angle according to claim 2, characterized in that, The magnitude of the model threshold is positively correlated with the size of the near-bit.

4. The calculation method for the near-bit dip angle according to claim 1, characterized in that, Sending an ultrasonic signal to the control terminal to obtain relevant parameter information of the near-bit at the current moment, and calculating an error coefficient of the inclination measurement tool according to the relevant parameter information, including: Sending an ultrasonic signal to the control terminal; The control terminal reads the current moment, rotational speed information, vibration frequency information, drilling depth information, and pressure information of the near-bit according to the ultrasonic signal; Sending the rotational speed information, the vibration frequency information, the drilling depth information, and the pressure information to a receiving end in the near-bit; The receiving end calculates an error coefficient of the inclination measurement tool under the current conditions according to the rotational speed information, the vibration frequency information, the drilling depth information, and the pressure information.

5. The calculation method for the near-bit dip angle according to claim 4, characterized in that, The error coefficient is positively correlated with the magnitude of the vibration frequency information and the magnitude of the rotational speed, and the error coefficient is negatively correlated with the magnitude of the pressure information and the magnitude of the drilling depth information.

6. The calculation method for the near-bit dip angle according to claim 1, characterized in that, Calculating a current angle change ratio of the near-bit by respectively emitting laser signals at the current moment and the previous moment through a laser emitter and respectively obtaining a first reflection signal and a second reflection signal, including: Emitting the same beam of laser signal to the inner wall of the near-bit at the previous moment and the current moment respectively; Obtaining photosensitive images of the laser signal when reflected at the previous moment and the current moment through a photosensitive camera, wherein the photosensitive image is an image of the laser signal on the reflection surface; Determining the reflection positions of the laser signal according to the brightness values of the photosensitive images at the previous moment and the current moment respectively, and respectively obtaining the reflection intensities of the first reflection signal and the second reflection signal; Determining the current angle change ratio of the near-bit according to the reflection positions and the magnitudes of the reflection intensities at the current moment and the previous moment.

7. The calculation method for the near-bit dip angle according to any one of claims 1 to 6, characterized in that, Inputting the relevant parameter information of the near-bit at the current moment and the previous moment into the correction model to obtain a primary output result and a secondary output result, and performing correction processing on the primary output result, the initial measured inclination value, and the secondary output result according to the error coefficient and the angle change ratio to obtain a target inclination, including: Obtaining a real-time inclination range according to the initial measured inclination value and the error coefficient, and determining whether the primary output result is within the real-time inclination range; After determining that the primary output result is within the real-time inclination range, calculating an angle difference between the primary output result and the secondary output result per unit time, and judging the magnitude relationship between the angle difference and the angle change ratio; If the difference between the angle difference and the angle change ratio is less than or equal to an error threshold, using the primary output result as the target inclination; If the difference between the angle difference and the angle change ratio is greater than the error threshold, calculating the target inclination according to the secondary output result, the angle change ratio, and a time difference, where the time difference is the difference between the previous moment and the current moment.

8. A calculation device for the near-bit dip angle, characterized in that, Including: A modeling module, configured to obtain the historical data of the near-bit, and establish a correction model according to the historical data; An initial measurement module, configured to start an inclination measurement tool located inside the near-bit to obtain the initial measurement inclination value of the near-bit at the current moment, wherein a gyroscope is installed inside the inclination measurement tool; An error calculation module, configured to send an ultrasonic signal to a control terminal, obtain the relevant parameter information of the near-bit at the current moment and the previous moment according to the feedback signal of the control terminal, and calculate the error coefficient of the inclination measurement tool according to the relevant parameter information at the current moment; A ratio calculation module, configured to emit laser signals at the current moment and the previous moment respectively through a laser emitter, and obtain a first reflection signal and a second reflection signal respectively, and calculate the current angle change ratio of the near-bit according to the first reflection signal and the second reflection signal, wherein the interval between the current moment and the previous moment is between 1 and 3 s; A correction module, configured to input the relevant parameter information of the near-bit at the current moment and the previous moment into the correction model to obtain a primary output result and a secondary output result, and perform correction processing on the primary output result, the initial measurement inclination value and the secondary output result according to the error coefficient and the angle change ratio to obtain a target inclination; 9. A storage medium, on which a computer program is stored, characterized in that, When the program is executed by a processor, it implements the calculation method of the near-bit inclination according to any one of claims 1 to 7; 10. A terminal, characterized in that, Comprising: A processor and a memory; The memory is used for storing a computer program; The processor is used for executing the computer program stored in the memory, so that the terminal executes the calculation method of the near-bit inclination according to any one of claims 1 to 7.

Images