Measurement-while-drilling instrument and industrial control method thereof
By combining magnetic sensors and gyroscope sensors, and using the main processor and neural network for data analysis and mode switching, the problem of magnetic sensors being disturbed by magnetic field and gyroscope sensors in the prior art is solved, and high-precision and low-power drilling trajectory measurement is achieved.
Patent Information
- Application Number
- CN202510140617.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-08
- Publication Date
- 2025-05-13
AI Technical Summary
The existing drilling measurement instruments are in coal mines due to the interference of magnetic field, which cannot achieve accurate measurement of the trajectory of the entire hole. Moreover, the gyro sensor has a long search time, a large error drift, and high power consumption.
A drill-as-alive measuring instrument combining magnetic sensors and gyroscope sensors is used to monitor magnetic field data in real time through the main processor. If the magnetic field is abnormal, switch to gyroscope sensor mode, and use neural networks and automatic encoder for data analysis and mode switching.
It improves measurement accuracy and reliability, improves measurement timeliness and efficiency, optimizes power consumption and power supply management, and enhances data processing and anti-interference capabilities.
Smart Images

Figure CN119981857A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of underground coal mine drilling, and in particular to a measurement while drilling instrument and an industrial control method thereof. Background Art
[0002] The measurement while drilling instrument plays a key role in directional drilling in mines. It can detect and display the borehole trajectory and deviation from the design in real time, guide directional engineers to adjust the borehole direction according to the design requirements, ensure that the borehole extends along the design direction, and achieve precise directional drilling. At present, the mature measurement while drilling methods in coal mines mainly include wired measurement while drilling, mud pulse wireless measurement while drilling, and electromagnetic wave wireless measurement while drilling. These measuring instruments usually use a sensor group fixed on the probe for parameter measurement. There are mainly two sensor schemes: one is composed of an acceleration sensor and a magnetic sensor. The magnetic sensor measures the three directional components of the geomagnetic field and obtains the borehole azimuth through formula calculation; the other is composed of an acceleration sensor and a gyro sensor, and uses a gyro to self-seek north to determine the true azimuth. However, these two schemes have their own defects.
[0003] When using magnetic sensors alone, due to interference from ferromagnetic materials such as the drill bit, the instrument is installed far from the drill bit, resulting in a lag in the measured azimuth, which cannot reflect the actual situation of the borehole in a timely manner, reducing the timeliness of the measurement. At the same time, external stratum magnetic interference can easily affect the azimuth measurement accuracy, so that the measurement results cannot accurately reflect the changes in the borehole trajectory, and cannot achieve precise orientation. In addition, there are errors in the conversion between the magnetic azimuth and the true azimuth, resulting in the measurement data cannot truly reflect the actual drilling trajectory, affecting the drilling construction effect.
[0004] When using gyro sensors alone, the time required to find north is long, the measured data response is slow, and the drilling efficiency is low. Over time, the gyro sensor has serious bias drift and random drift, and frequent re-finding of north is required during long-term drilling operations, further reducing drilling efficiency. In addition, the gyro sensor consumes a lot of power, which will reduce the continuous working time of the instrument. For wired methods, since a single-core cable drill rod is used for power supply and carrier, it will also affect the transmission distance and data distortion. Summary of the invention
[0005] In view of this, the purpose of the present invention is to provide a measurement while drilling instrument and an industrial control method, which complement the two advantages of the fast response of the magnetic sensor and the accurate gyro measurement of the orientation, so as to solve the problems in the prior art that the existing magnetic sensors generate measurement data errors due to the influence of the magnetic field, resulting in the inability to accurately measure the trajectory of the entire borehole section, and the existing gyro measurement while drilling instruments have a long north-seeking time, large errors after long-term operation, and high power consumption.
[0006] According to a first aspect of an embodiment of the present invention, a measurement while drilling instrument is provided, the measurement while drilling instrument comprising:
[0007] An integral measuring instrument probe, and a host computer for processing probe data connected to the integral measuring instrument probe by wire or wireless means;
[0008] The overall measuring instrument probe comprises: a data transmission end and a sensor measurement circuit, wherein the data transmission end is used to complete the overall measuring instrument probe and related data transmission by wired or wireless transmission;
[0009] The sensor measurement circuit includes: a gyro measurement component and a magnetic sensor measurement component, which are used to control the power supply to switch to the corresponding mode through a preset circuit.
[0010] Furthermore, the sensor measurement circuit also includes: a set of three-axis acceleration sensors.
[0011] Furthermore, the data transmission end transmits data to the host by wired or wireless means, and the data transmission end includes a main processor unit and a power management unit. The wired or wireless means include a center cable drill pipe wired means, an electromagnetic wave wireless means, a mud pulse wireless means and an acoustic wave wireless means.
[0012] Furthermore, the host for processing the probe data includes:
[0013] A data demodulation and transmission unit, used to demodulate the data collected by the measuring probe and send it to a preset receiving end;
[0014] The data control unit is used to analyze the probe data and actively switch the probe working mode.
[0015] Furthermore, the gyro measurement component includes: a MEMS gyro sensor.
[0016] According to a second aspect of an embodiment of the present invention, there is provided an industrial control method for a measurement while drilling instrument, which is applied to a measurement while drilling instrument as described in any one of the above items, and the method comprises:
[0017] Get the start measurement instruction;
[0018] Using the start measurement instruction, controlling the power supply to start the magnetic sensor and the acceleration sensor, using the magnetic sensor and the acceleration sensor to detect and calculate the magnetic field strength and the magnetic inclination, and returning the magnetic azimuth;
[0019] The preset main processor will judge the magnetic field strength, magnetic inclination and magnetic azimuth angle. If the current magnetic field strength or magnetic azimuth and magnetic inclination are abnormal, the main processor will switch the power supply to the gyro sensor and start the gyro north-seeking test. At the same time, the preset host will receive a flag that has switched to the gyro sensor mode.
[0020] Furthermore, the preset main processor will judge the magnetic field strength, magnetic inclination and magnetic azimuth angle. If the current magnetic field strength or magnetic azimuth and magnetic inclination are abnormal, the main processor will switch the power supply to the gyro sensor and start the gyro north-seeking test. At the same time, the preset host will receive a flag that has been switched to the gyro sensor mode, including:
[0021] Using a preset main processing unit to perform a neural network data statistical analysis on the magnetic field intensity data and the magnetic field anomaly data uploaded by the magnetic sensor to obtain a first processing result;
[0022] Use the preset automatic encoder to determine abnormal data and detect the magnetic field state around the entire instrument.
[0023] If the magnetic field strength is detected to be abnormal, the power supply is switched to the gyro sensor, and the gyro north-seeking test is started. At the same time, the preset host receives the flag that has been switched to the gyro sensor mode.
[0024] Furthermore, the method further comprises:
[0025] Input multiple azimuth angle data for training at the same time. If the automatic encoder cannot restore normal data when the azimuth angle changes abnormally, switch to gyro sensor mode.
[0026] The technical solution provided by the embodiments of the present invention may have the following beneficial effects:
[0027] 1. Improve measurement accuracy and reliability
[0028] The advantages of the combined magnetic sensor and gyro sensor are overcome, and the problems of using only magnetic sensors, such as the influence of ferromagnetic materials and formation magnetic interference on the azimuth measurement accuracy, the inability to accurately measure the trajectory of the entire hole section, and the defects of the gyro sensor's long north search time and large error drift during long-term operation, are overcome. Through the real-time monitoring and intelligent judgment of the main processor based on the magnetic field strength, magnetic azimuth, magnetic inclination and other data, it can quickly switch to the gyro measurement mode when the magnetic field is abnormal, ensuring the accuracy of the measurement results and achieving stable and reliable drilling trajectory measurement of the entire hole section.
[0029] For example, in a complex geological environment, when encountering a strong magnetic interference area, timely switching to the gyro sensor can avoid measurement errors caused by interference of the magnetic sensor and ensure accurate control of the drilling direction.
[0030] 2. Improve measurement timeliness and efficiency
[0031] The magnetic sensor has a fast response speed and can quickly obtain measurement data in a normal magnetic field environment, ensuring the timeliness of the measurement. When the magnetic field is abnormal, it switches to the gyro sensor, and can continue to measure accurately by using its characteristics that are not affected by the magnetic field, avoiding inaccurate measurements or re-measurements due to the influence of the magnetic field, and improving the overall drilling efficiency.
[0032] For example, during the drilling process, inaccurate measurements and repeated measurements caused by magnetic field interference are reduced, allowing the drilling operation to be carried out more efficiently.
[0033] 3. Optimize power consumption and power supply management
[0034] The use of MEMS gyro sensors saves power consumption, does not require the addition of battery capacity, and reduces the energy consumption and complexity of the equipment. At the same time, the energy storage unit of the magnetic sensor is used to power the gyro sensor, ensuring the power supply when the gyro sensor is working at high power consumption, extending the data transmission distance and ensuring the stable transmission of the measured data.
[0035] For example, during long-term underground operations, it effectively solves the problems of equipment performance fluctuations or insufficient power supply caused by power consumption issues, and improves the equipment's endurance and stability.
[0036] 4. Enhance data processing and anti-interference capabilities
[0037] The main processor processes the magnetic field data through neural network data statistical analysis and automatic encoder, which can accurately identify abnormal data and switch sensor modes in time, improving the intelligence and adaptability of the system.
[0038] Interleaved coding is used for signal transmission, which significantly improves the anti-interference performance compared with general serial coding, ensures the integrity and accuracy of the measurement data during transmission, and reduces data loss or errors caused by interference.
[0039] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS
[0040] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.
[0041] Figure 1 is a schematic diagram showing the composition of a device of a while drilling measurement instrument according to an exemplary embodiment;
[0042] Figure 2 is a diagram showing the overall structure of a measurement while drilling instrument according to an exemplary embodiment;
[0043] Figure 3 is a schematic diagram of a working process of a measurement while drilling instrument according to an exemplary embodiment;
[0044] Figure 4 is a schematic diagram of the structure of an automatic encoder according to an exemplary embodiment. DETAILED DESCRIPTION
[0045] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.
[0046] Embodiment 1
[0047] See also Figure 1 , Figure 1 The present invention is a schematic diagram showing the composition of a measurement while drilling instrument according to an exemplary embodiment, wherein the measurement while drilling instrument comprises:
[0048] An integral measuring instrument probe 1, and a host 2 for processing probe data connected to the integral measuring instrument probe 1 via or wirelessly;
[0049] The overall measuring instrument probe 1 comprises: a data transmission terminal 3 and a sensor measurement circuit 4, wherein the data transmission terminal 3 is used to complete the overall measuring instrument probe 1 and related data transmission by wired or wireless transmission;
[0050] The sensor measurement circuit 4 includes a gyro measurement component 5 and a magnetic sensor measurement component 6, which are used to control the power supply to switch to the corresponding mode through a preset circuit.
[0051] In the specific implementation, the measuring instrument is first installed in accordance with the regulations to ensure that the communication between the probe and the host and other related equipment is normal. When drilling measurement is required, the host terminal at the borehole sends a measurement instruction to the measuring probe by wired or wireless means. The power management unit in the probe starts the magnetic sensor and acceleration sensor according to the program, starts to collect and calculate data such as magnetic field strength, magnetic inclination and magnetic azimuth, and transmits these data to the main processor. The main processor analyzes and judges these data according to the pre-set algorithm and training model. If it is found during the analysis process that the data such as magnetic field strength, magnetic azimuth or magnetic inclination are beyond the normal range or abnormal fluctuations occur, the main processor immediately controls the power switching module to switch the power to the gyro sensor. The gyro sensor starts the north-seeking test and sends the switching mode flag to the host at the same time. After receiving the flag, the host can perform corresponding recording or prompt operations. During the entire drilling process, the above measurement and judgment steps are repeated continuously to continuously monitor the drilling trajectory. In terms of data transmission, the data transmission part uses wired carrier technology or wireless modulation technology (electromagnetic wave low-frequency modulation technology or mud pulse pressure pulsation modulation technology or acoustic wave intermediate frequency modulation technology) to stably transmit the collected measurement data and equipment status information to the host, and the data processing unit of the host further processes and analyzes the data, such as sending the data to the ground monitoring center after sorting, or adjusting and optimizing the measurement parameters of the probe according to the data analysis results. Through such an implementation method, the present invention can effectively realize high-precision and high-efficiency measurement while drilling operations in the complex environment of coal mines, and provide reliable technical support for directional drilling in coal mines.
[0052] In specific implementation, the probe 1 of the integral measuring instrument is located in the hole and is the part that directly performs the measuring work. It transmits signals by wire or wireless means and is connected to the host 2 that processes the probe data. This connection may be through the following means: wired transmission, electromagnetic wave wireless transmission, mud pulse wireless transmission, and acoustic wave wireless method as a medium to achieve the interaction of data and control signals between the two.
[0053] The host is usually located at the hole mouth, and forms a master-slave relationship with the probe 1 of the overall measuring instrument. The host can send instructions to the probe and receive data from the probe, thereby realizing the control and data collection of the probe measurement work in the hole.
[0054] In specific implementation, the data transmission terminal 3 and the sensor measurement circuit 4 cooperate with each other in the overall measuring instrument probe 1. The data transmission terminal 3 is mainly responsible for providing power supply to the sensor measurement circuit 4 using wired or wireless transmission technology, and transmitting the data obtained by the sensor measurement circuit 4.
[0055] Specifically, the gyro measurement component and the magnetic sensor measurement component in the sensor measurement circuit 4 are part of the sensor measurement circuit 4, and are connected to each other through an internal preset circuit, and are connected to the data transmission terminal 3 to achieve data transmission and power supply. The gyro measurement component and the magnetic sensor measurement component receive power from the data transmission terminal 3, and feed back the measured data to the data transmission terminal 3 for transmission to the host.
[0056] In a specific implementation, the sensor measurement circuit 4 further includes: a set of three-axis acceleration sensors.
[0057] One of the three-axis accelerometers plays an important role. It works in conjunction with the magnetic sensor and gyro sensor. During the measurement process, the three-axis accelerometer can sense the acceleration changes of the instrument in three axial directions in real time. This helps to more accurately determine the attitude and motion state of the instrument, and provide key auxiliary data for subsequent drilling trajectory measurements. For example, during the drilling process, when the instrument is vibrated or tilted, the three-axis accelerometer can quickly capture these changes and pass the data to the main processor for fusion analysis with the data from the magnetic sensor and gyro sensor, so as to more accurately calculate parameters such as the azimuth and inclination of the borehole, further improving the accuracy and reliability of the measurement.
[0058] Furthermore, the data transmission terminal 3 transmits data to the orifice in a wired or wireless manner, and the data transmission terminal 3 includes a main processor unit and a power management unit.
[0059] Furthermore, the host 2 for processing the probe data includes:
[0060] A data demodulation and transmission unit, used to demodulate the data collected by the measuring probe and send it to a preset receiving end;
[0061] The data control unit is used to analyze the probe data and actively switch the probe working mode.
[0062] Furthermore, the gyro measurement component includes: a MEMS gyro sensor.
[0063] It should be noted that, considering the fact that the power consumption of MEMS gyro sensors is relatively high, an energy storage unit will store energy when the magnetic sensor is working. When the MEMS gyro sensor is working, the energy storage unit discharges to power the gyro sensor, which can ensure longer continuous working time and longer data transmission distance.
[0064] For specific implementation, please refer to Figure 2 , Figure 2 The system structure and workflow of a measurement while drilling instrument combining magnetic sensors and gyro sensors in coal mines are demonstrated.
[0065] The figure is divided into two main parts, the left side is the probe part, and the right side is the host part, and the two parts are connected by wire or wirelessly.
[0066] The probe part includes:
[0067] Power control unit: It is the power control center of the entire probe. It controls the distribution and start and stop of power according to the instructions of the main processor unit, and provides power support for the magnetic sensor unit, gyro sensor unit, etc.
[0068] Main processor unit: Located at the core of the probe, it controls the power control unit according to the working conditions, receives data from the magnetic sensor unit and the gyro sensor unit, and transmits the data to the data transmission unit. At the same time, it also receives control instructions from the host's data transmission unit, thereby realizing intelligent management and control of the working status of the entire probe.
[0069] Magnetic sensor unit: responsible for measuring magnetic field related data, such as magnetic field strength, magnetic azimuth, magnetic inclination, etc., and transmitting these data to the main processor unit.
[0070] Gyro sensor unit: used to measure gyro-related parameters, such as azimuth, etc., and its measurement data will also be transmitted to the main processor unit.
[0071] Data transmission unit: It communicates with the data transmission unit of the host through wired or wireless means, sends the data processed by the main processor unit to the host, and receives the control instructions sent by the host to realize data interaction and collaborative work between the probe and the host.
[0072] And the host part, including:
[0073] Data demodulation and transmission unit: connected to the data transmission unit of the probe, responsible for receiving the data sent by the probe and sending the control instructions of the host to the probe.
[0074] Data control unit: further processes and analyzes the data received from the probe, and controls the functions of the probe as needed, such as adjusting the measurement parameters of the sensor.
[0075] Data demodulation and transmission unit (external display): The data processed by the data control unit is sent out so that the outside world can intuitively see the measurement results and related information. It may be displayed on the monitoring equipment on the ground or at the hole mouth for operators to monitor the downhole drilling situation in real time.
[0076] Through such a structure and process, the entire system realizes the accurate measurement of drilling trajectory in coal mines and the reliable transmission and display of data. The various units cooperate with each other to ensure the normal operation and efficient work of the measurement while drilling instrument.
[0077] In one embodiment, see Figure 3 , Figure 3 The present invention is a schematic diagram of a working process of a measurement while drilling instrument according to an exemplary embodiment, wherein the method comprises:
[0078] S1. Get the start measurement instruction;
[0079] S2. Using the start measurement instruction, the control power supply starts the magnetic sensor and the acceleration sensor, and uses the magnetic sensor and the acceleration sensor to detect and calculate the magnetic field strength, the magnetic inclination, and return the magnetic azimuth;
[0080] S3. The preset main processor will judge the magnetic field strength, magnetic inclination and magnetic azimuth angle. If the current magnetic field strength or magnetic azimuth and magnetic inclination are abnormal, the main processor will switch the power supply to the gyro sensor and start the gyro north-seeking test. At the same time, the preset host will receive the flag that it has switched to the gyro sensor mode.
[0081] For specific implementation, please refer to Figure 3 , the system will determine whether it has received the measurement instruction. If it has not received it ("No"), it will continue to remain in standby mode; if it has received it ("Yes"), it will proceed to the next step.
[0082] When a yes instruction is received, the power control unit starts the magnetic sensor, and the magnetic sensor starts working and uploading data. After that, the main processor analyzes the data uploaded by the magnetic sensor to determine whether the magnetic field condition is abnormal.
[0083] If the magnetic field condition is normal ("No"), the magnetic sensor continues to upload magnetic orientation data, and then the process returns to the "Standby" state, waiting for the next measurement instruction.
[0084] If the magnetic field is abnormal ("yes"), go to the next step, execute the switching power control to enter the north-seeking measurement mode, the gyro sensor starts to seek north and measure the azimuth data, and then the process returns to the "standby" state and waits for the next measurement instruction.
[0085] In the specific implementation, the whole process clearly shows how the MWD instrument switches between magnetic sensor measurement and gyro sensor measurement according to the magnetic field conditions after receiving the measurement instruction, so as to ensure that the borehole orientation data can be accurately measured in different magnetic field environments, and ensure the smooth progress of directional drilling operations in coal mines and the reliability of measurement data. This workflow design can effectively overcome the measurement error problem that may occur with a single sensor in a complex underground environment, and improve the adaptability and accuracy of the entire measurement system.
[0086] Furthermore, the preset main processor will judge the magnetic field strength, magnetic inclination and magnetic azimuth angle. If the current magnetic field strength or magnetic azimuth and magnetic inclination are abnormal, the main processor will switch the power supply to the gyro sensor and start the gyro north-seeking test. At the same time, the preset host will receive a flag that has been switched to the gyro sensor mode, including:
[0087] Using a preset main processing unit to perform a neural network data statistical analysis on the magnetic field intensity data and the magnetic field anomaly data uploaded by the magnetic sensor to obtain a first processing result;
[0088] Use the preset automatic encoder to determine abnormal data and detect the magnetic field state around the entire instrument.
[0089] If the magnetic field strength is detected to be abnormal, the power supply is switched to the gyro sensor, and the gyro north-seeking test is started. At the same time, the preset host receives the flag that has been switched to the gyro sensor mode.
[0090] Furthermore, the method further comprises:
[0091] Input multiple azimuth angle data for training at the same time. If the automatic encoder cannot restore normal data when the azimuth angle changes abnormally, switch to gyro sensor mode.
[0092] In the specific implementation, the main processing will perform neural network data statistical analysis on the magnetic field strength data uploaded by the magnetic sensor and the data of magnetic field anomalies, and use the automatic encoder to determine the abnormal data to detect the magnetic field state around the entire instrument at any time, thereby providing data support for the selection of the overall test sensor. The general principle is as follows:
[0093] Autoencoder, also known as self-encoder in Chinese, is an unsupervised learning model. Essentially, it uses a neural network to generate a low-dimensional representation of a high-dimensional input. Autoencoder is similar to principal component analysis (PCA), but Autoencoder overcomes the linear limitations of PCA when using nonlinear activation functions.
[0094] Autoencoder consists of two main parts, encoder and decoder. The encoder is used to find the compressed representation of the given data, and the decoder is used to reconstruct the original input. During training, the decoder forces the autoencoder to select the most informative features and finally save them in the compressed representation. The final compressed representation is in the middle encoder layer.
[0095] the following Figure 4 For example, the dimension of the original data is 10, the encoder and decoder have two layers respectively, and the middle encoder has 3 nodes, which means that the original data is reduced to only 3 dimensions. The decoder reconstructs the original data based on the reduced-dimensional data and obtains a 10-dimensional output. In the process from input to output, the autoencoder actually also plays a role in noise reduction.
[0096] Anomaly detection is usually divided into two cases: supervised and unsupervised. In the unsupervised case, we do not have abnormal samples to learn from, and the basic assumption of the algorithm is that the abnormal points follow different distributions. The Autoencoder trained based on normal data can reconstruct and restore normal samples, but it cannot restore data points that are different from the normal distribution well, resulting in large restoration errors.
[0097] If the features of the samples are all numerical variables, we can use MSE or MAE as the restoration error. For example, in the figure above, if the input sample is:
[0098] X=(X1,X2,…,X 10 )
[0099] The result reconstructed by Autoencoder is:
[0100]
[0101] The restoration error MSE is:
[0102]
[0103] The restoration error MAE is:
[0104]
[0105] When the restoration error is larger than a certain threshold, we mark it as an outlier.
[0106] According to the above algorithm, under the condition of no magnetic field interference, the normal magnetic field strength is input to train the overall magnetic field strength, and the overall restoration model is trained (3-layer neural network, judged once every 10 data). When the magnetic field strength is abnormal, the overall automatic encoder cannot restore the normal data, indicating that the data is abnormal and the overall sensor mode needs to be switched.
[0107] In the specific implementation, the preset main processor is used to make in-depth and accurate judgments on the magnetic field strength, magnetic inclination and magnetic azimuth angle:
[0108] First, the main processor performs a neural network data statistical analysis on the magnetic field strength data uploaded by the magnetic sensor. This neural network data statistical analysis method is an advanced data processing technology that can mine hidden patterns and features in the data and provide a more accurate and comprehensive basis for subsequent judgments. Through this analysis, the first processing result is obtained, laying the foundation for subsequent abnormal judgments.
[0109] Furthermore, the preset autoencoder is used to determine abnormal data and detect the magnetic field state around the entire instrument. As a powerful unsupervised learning model, the autoencoder plays a key role here. It consists of two parts: the encoder and the decoder. The encoder compresses the input high-dimensional data such as the magnetic field strength into a low-dimensional representation, and the decoder reconstructs the original data based on the low-dimensional representation. During training, the decoder will force the selection of the most informative features to be saved in the compressed representation, overcoming the linear limitations of traditional principal component analysis (PCA) and showing excellent performance in data denoising.
[0110] In unsupervised anomaly detection, normal magnetic field strength data can be well reconstructed and restored by the autoencoder, while abnormal data will lead to large restoration errors due to its deviation from the normal distribution. Here, mean square error (MSE) or mean absolute error (MAE) is used as a measure of restoration error. When the restoration error exceeds the set threshold, it indicates that the magnetic field strength is abnormal.
[0111] When an abnormal magnetic field strength is detected, the main processor quickly and intelligently switches the power supply to the gyro sensor and starts the gyro north-seeking test. At the same time, the preset host receives the flag that has switched to the gyro sensor mode, realizing seamless switching of the measurement mode. This dynamic switching mechanism greatly improves the adaptability and reliability of the measurement system in complex underground environments, avoids measurement errors caused by abnormal magnetic fields, and ensures the continuity and accuracy of measurement work.
[0112] In addition to the abnormal judgment of magnetic field strength, the present invention also includes monitoring of azimuth data. Multiple azimuth data are input for training at the same time, and these data are processed by the automatic encoder. Under normal circumstances, the automatic encoder can accurately restore these azimuth data because the normal azimuth data conforms to the pattern learned by the training model.
[0113] However, when the azimuth angle changes abnormally, the autoencoder cannot restore normal data. In this way, the azimuth angle abnormality can be detected quickly and sensitively. Once an abnormality is detected, the system will immediately switch to the gyro sensor mode, further ensuring the accuracy and reliability of the measurement.
[0114] Specifically, the magnetic field strength and azimuth angle data are processed and analyzed through technologies such as automatic encoders, realizing intelligent detection of abnormal data. This automatic detection mechanism can monitor the quality of measurement data in real time and detect data anomalies in a timely manner.
[0115] The sensor mode is automatically switched according to the test results, so that the measurement system can flexibly select the most appropriate sensor for measurement according to the actual measurement environment and data conditions. For example, when the magnetic field environment is normal, the magnetic sensor is used for measurement to obtain fast and accurate measurement results; when the magnetic field is abnormal, it automatically switches to the gyro sensor to avoid measurement errors caused by magnetic field interference, ensuring the accuracy and reliability of drilling trajectory measurement.
[0116] This technical solution improves the adaptability and stability of the entire underground coal mine measurement instrument, and can work stably in the complex and changeable underground environment, providing more accurate and reliable data support for directional drilling operations in coal mines, helping to improve drilling efficiency and quality, and ensuring the safety and smooth progress of underground operations. At the same time, these technical points and processing methods constitute the core innovation and protection content of the patent, and have important technical value and application prospects.
[0117] It can be understood that the same or similar parts of the above embodiments can be referenced to each other, and the contents not described in detail in some embodiments can refer to the same or similar contents in other embodiments.
[0118] It should be noted that, in the description of the present invention, the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of the present invention, unless otherwise specified, the meaning of "plurality" refers to at least two.
[0119] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention belong.
[0120] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.
[0121] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.
[0122] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.
[0123] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.
[0124] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.
[0125] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.
Claims
1. A measurement while drilling instrument, characterized in that: The drilling measurement instrument comprises: An integral measuring instrument probe, and a host computer for processing probe data connected to the integral measuring instrument probe by wire or wireless means; The overall measuring instrument probe comprises: a data transmission end and a sensor measurement circuit, wherein the data transmission end is used to complete the overall measuring instrument probe and related data transmission by wired or wireless transmission; The sensor measurement circuit includes: a gyro measurement component and a magnetic sensor measurement component, which are used to control the power supply to switch to the corresponding mode through a preset circuit.
2. A measurement while drilling instrument according to claim 1, characterized in that: The sensor measurement circuit also includes: a set of three-axis acceleration sensors.
3. A measurement while drilling instrument according to claim 1, characterized in that: The data transmission end is transmitted to the host by wired or wireless means, and the data transmission end includes a main processor unit and a power management unit. The wired or wireless means include a center cable drill pipe wired means, an electromagnetic wave wireless means, a mud pulse wireless means and an acoustic wave wireless means.
4. A measurement while drilling instrument according to claim 1, characterized in that: The host for processing the probe data comprises: A data demodulation and transmission unit, used to demodulate the data collected by the measuring probe and send it to a preset receiving end; The data control unit is used to analyze the probe data and actively switch the probe working mode.
5. The measurement while drilling instrument according to claim 1, characterized in that: The gyro measurement component includes: a MEMS gyro sensor.
6. An industrial control method for a while drilling measurement instrument, applied to a while drilling measurement instrument as claimed in any one of claims 1 to 5, characterized in that: The method comprises: Get the start measurement instruction; Using the start measurement instruction, controlling the power supply to start the magnetic sensor and the acceleration sensor, using the magnetic sensor and the acceleration sensor to detect and calculate the magnetic field strength and the magnetic inclination, and returning the magnetic azimuth; The preset main processor will judge the magnetic field strength, magnetic inclination and magnetic azimuth angle. If the current magnetic field strength or magnetic azimuth and magnetic inclination are abnormal, the main processor will switch the power supply to the gyro sensor and start the gyro north-seeking test. At the same time, the preset host will receive a flag that has switched to the gyro sensor mode.
7. The method according to claim 6, characterized in that The preset main processor will judge the magnetic field strength, magnetic inclination and magnetic azimuth angle. If the current magnetic field strength or magnetic azimuth and magnetic inclination angle are abnormal, the main processor will switch the power supply to the gyro sensor and start the gyro north-seeking test. At the same time, the preset host will receive the flag that has been switched to the gyro sensor mode, including: Using a preset main processor to perform neural network data statistical analysis on the magnetic field intensity data and magnetic field anomaly data uploaded by the magnetic sensor to obtain a first processing result; The preset automatic encoder is used to determine abnormal data and detect the magnetic field state around the entire instrument. If the magnetic field strength is detected to be abnormal, the power supply is switched to the gyro sensor, and the gyro north-seeking test is started. At the same time, the preset host receives the flag that has been switched to the gyro sensor mode.
8. The method according to claim 7, characterized in that The method further comprises: Input multiple azimuth angle data for training at the same time. If the azimuth angle changes abnormally and the automatic encoder cannot restore normal data, switch to the gyro sensor mode.