Remote management system for torque monitoring short section of rotary running casing

Abstract

The invention provides a remote management system for a rotary running casing torque monitoring short section, and relates to the technical field of petroleum engineering, a multi-modal sensor is arranged and configured through a multi-modal sensing module, and sensing connection is established; the data acquisition module acquires original data based on a preset acquisition constraint, and obtains initial monitoring data through AD conversion; a data correction module performs environment correction on the strain data and the rotation data based on the environment state data to obtain standard state monitoring data; the data processing module performs self-division filtering noise reduction on the standard state monitoring data to obtain standard monitoring data; and the data transmission module transmits the standard monitoring data to an upper computer, and performs remote management decision of the lower casing torque monitoring short section. The technical problem that monitoring efficiency and decision-making quality are affected due to the fact that monitoring data obtained in the prior art are not comprehensive and accurate is solved, comprehensive and accurate monitoring data are obtained in real time, and accuracy and reliability of operation remote management are improved.

Description

Technical Field

[0001] The present application relates to the technical field of petroleum engineering, and in particular to a remote management system for rotating casing torque monitoring pup joints. Background Art

[0002] In the oil drilling industry, casing operation is one of the key links, and torque monitoring is particularly important. Rotary casing torque monitoring technology is used to ensure the safety and efficiency of casing operation, and prevent overload and other potential problems by monitoring torque changes in real time.

[0003] Existing methods for monitoring rotating casing mainly rely on single torque sensors. These sensors are usually fixed to the casing and provide monitoring data by measuring the torque changes when the casing rotates. However, this method has obvious shortcomings. First, it ignores the impact of environmental factors on monitoring data. For example, changes in temperature and humidity may cause deviations in sensor readings, thereby affecting the accuracy of torque monitoring. Second, this method lacks comprehensive monitoring of the casing rotation status, limiting the operator's understanding of the overall status of the casing operation. Summary of the invention

[0004] The present application provides a remote management system for a rotating casing running torque monitoring pup joint, which solves the technical problem that the monitoring data obtained by the existing casing running monitoring technology is not comprehensive and accurate, thereby affecting the monitoring efficiency and decision-making quality, and achieves the technical effect of obtaining comprehensive and accurate monitoring data in real time and improving the accuracy and reliability of remote management of operations.

[0005] In view of the above problems, the present application provides a remote management system for a rotating casing torque monitoring pup joint, the system comprising: a multimodal sensing module, the multimodal sensing module is used to deploy and configure multimodal sensors and establish a sensing connection, wherein the multimodal sensors include environmental state sensors, torque monitoring sensors and rotation monitoring sensors; a data acquisition module, the data acquisition module is used to collect raw data based on preset acquisition constraints, and obtain initial monitoring data after AD conversion, wherein the initial monitoring data includes environmental state data, strain data and rotation data; a data correction module, the data correction module is used to perform environmental correction on the strain data and the rotation data based on the environmental state data, and obtain standard state monitoring data, wherein the standard state monitoring data includes standard strain data and standard rotation data; a data processing module, the data processing module is used to perform self-division filtering and noise reduction on the standard state monitoring data, and obtain standard monitoring data; a data transmission module, the data transmission module is used to transmit the standard monitoring data to a host computer to make remote management decisions for the casing torque monitoring pup joint.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages: The multimodal sensing module provides a comprehensive data acquisition basis by laying out and configuring multimodal sensors and establishing sensor connections. The multimodal sensors include environmental state sensors, torque monitoring sensors and rotation monitoring sensors. The data acquisition module collects raw data based on preset acquisition constraints, obtains initial monitoring data through AD conversion, and converts physical signals into digital signals for subsequent digital processing, thereby realizing automated and standardized data acquisition and improving the efficiency and accuracy of data acquisition. The initial monitoring data includes environmental state data, strain data and rotation data. The data correction module performs environmental correction on the strain data and the rotation data based on the environmental state data, and obtains standard state monitoring data to eliminate the influence of environmental factors on the data, thereby improving the accuracy of the data. The standard state monitoring data includes standard strain data and standard rotation data, which more truly reflects the torque state of the casing. The data processing module performs self-division filtering and noise reduction on the standard state monitoring data, obtains standard monitoring data, eliminates random errors and noise in the data, and obtains more accurate and reliable monitoring data. The data transmission module transmits the standard monitoring data to the host computer to make remote management decisions for the casing torque monitoring sub, thereby realizing remote monitoring and management and improving the safety and efficiency of the operation.

[0007] In summary, this application effectively captures and corrects environmental, strain and rotation data through multimodal sensors and data correction modules to ensure the accuracy and reliability of monitoring data, and the data processing module further improves data quality and reduces noise interference through self-division filtering and noise reduction methods. Finally, the data transmission module transmits high-quality standard monitoring data to the host computer, realizing remote real-time management and decision-making. In this way, the system not only improves monitoring accuracy, but also enhances real-time response capabilities and the convenience of remote management, which helps to timely detect and handle casing torque anomalies and improves the safety and efficiency of operations.

[0008] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 A schematic diagram of the structure of a remote management system for a rotating casing torque monitoring sub provided in an embodiment of the present application; Figure 2 A schematic diagram of a process for obtaining initial monitoring data in a remote management system for a rotating casing torque monitoring sub provided in an embodiment of the present application; Figure 3 A schematic diagram of a process for obtaining standard state monitoring data in a remote management system for a rotary casing torque monitoring sub provided in an embodiment of the present application.

[0010] Explanation of the accompanying drawings: multimodal sensing module 10, data acquisition module 20, data correction module 30, data processing module 40, data transmission module 50. DETAILED DESCRIPTION

[0011] The embodiment of the present application solves the technical problem that the monitoring data obtained by the existing casing running monitoring technology is not comprehensive and accurate, thereby affecting the monitoring efficiency and decision-making quality, by providing a remote management system for the rotating casing running torque monitoring pup joint. The embodiment of the present application achieves the technical effect of obtaining comprehensive and accurate monitoring data in real time and improving the accuracy and reliability of remote management of operations.

[0012] like Figure 1 As shown, an embodiment of the present application provides a remote management system for rotating casing torque monitoring sub, the system comprising: The multimodal sensing module 10 is used to arrange and configure multimodal sensors and establish sensing connections, wherein the multimodal sensors include environmental status sensors, torque monitoring sensors, and rotation monitoring sensors.

[0013] Specifically, multimodal sensors are sensors that can obtain data from different aspects and provide comprehensive information. They include environmental state sensors, torque monitoring sensors and rotation monitoring sensors. Among them, environmental state sensors are sensors used to monitor external environmental parameters, such as temperature, humidity, pressure, etc., to help determine the impact of environmental factors on torque readings. Torque monitoring sensors are sensors specifically used to measure the torque of an object, which can monitor the changes in torque applied to the object in real time. Rotation monitoring sensors are sensors used to measure the rotational motion of an object, such as angular velocity sensors or gyroscopes.

[0014] First, select the appropriate sensor type and specifications according to the needs of the drilling operation. Install the sensors at key locations, such as the connection of the casing and the drive device, to ensure that they can accurately capture the required physical quantities. For example, when laying out environmental status sensors, durable sensors suitable for harsh environments can be selected. These sensors can monitor environmental parameters such as temperature, humidity and pressure in real time and connect to the multimodal sensing module 10 wirelessly or wired. The torque monitoring sensor can use a strain gauge torque sensor and be installed at the connection of the casing to calculate the torque by measuring the strain of the object when it is twisted. The rotation monitoring sensor can be installed on the rotating part and use a gyroscope or optical encoder to monitor the rotation angle and speed.

[0015] Next, the sensor is configured and calibrated through the configuration software, and appropriate parameters such as sampling rate, range, etc. are set to ensure that the sensor can provide accurate and reliable data. Then, a sensor connection is established, and the sensor is connected to the system through a physical connection and / or a wireless connection to ensure that the data of all sensors can be synchronously collected and transmitted to the data acquisition module 20. For example, Bluetooth or Wi-Fi technology is used to transmit the sensor data to the data acquisition module 20.

[0016] Through the above steps, the multimodal sensing module 10 successfully integrates the data of environmental status, torque and rotational motion to form a comprehensive and accurate monitoring system. The environmental status sensor can detect sudden changes in the surrounding environment, the torque monitoring sensor can measure the torque in real time, and the rotation monitoring sensor can track the rotation speed and direction of the casing to ensure that it is within a safe range, thereby achieving comprehensive monitoring of the casing operation environment and providing a comprehensive collection basis for subsequent data collection and processing.

[0017] The data acquisition module 20 is used to collect raw data based on preset acquisition constraints, and obtain initial monitoring data through AD conversion, wherein the initial monitoring data includes environmental state data, strain data, and rotation data.

[0018] Specifically, the preset acquisition constraints are pre-set conditions or parameters in the data acquisition process, such as sampling frequency, time interval, data accuracy, etc. Raw data is unprocessed data obtained directly from the sensor. AD conversion, that is, analog-to-digital conversion, is the process of converting analog signals into digital signals. The initial monitoring data is the digitized monitoring data obtained after AD conversion, including environmental state data, strain data and rotation data. Among them, environmental state data is information reflecting environmental conditions, such as temperature, humidity, pressure, etc. Strain data is data information reflecting the deformation of an object under force. Rotation data is information reflecting the rotational motion of an object, such as angular velocity and angular displacement.

[0019] First, parameters such as sampling frequency, data accuracy, and time interval are set according to monitoring requirements. For example, when monitoring high-speed rotating mechanical parts, a higher sampling frequency can be set to ensure that rapidly changing data is captured. After setting the acquisition constraints, the data acquisition module 20 begins to acquire raw data from various sensors.

[0020] The environmental status data is collected through environmental status sensors, such as temperature sensors and pressure sensors. Temperature sensors such as DS18B20 can measure the environmental temperature in real time and transmit data through a digital interface. Pressure sensors such as BMP280 can measure atmospheric pressure and convert analog signals into digital signals and transmit them to the data acquisition module 20. The strain data is collected through strain gauge sensors, such as TML's FLA series strain gauges. These sensors measure strain through a bridge circuit and generate a voltage signal proportional to the strain. This signal is converted into a digital signal by an AD converter (such as ADS1115) and transmitted to the data acquisition module 20. The rotation data is collected through MEMS gyroscopes and geomagnetic sensors. MEMS gyroscopes such as ADXL345 can measure angular velocity and generate digital signals. Geomagnetic sensors such as HMC5883L can measure the direction of the geomagnetic field and output digital signals. These data are transmitted to the data acquisition module 20 through the I2C or SPI interface.

[0021] Once all sensor data are collected, the data acquisition module 20 converts all analog signals into digital signals through AD conversion. AD converters such as ADS1115 can convert analog signals into digital signals with 16-bit resolution and high accuracy. The converted data is stored and processed to form initial monitoring data, including environmental status data, strain data and rotation data. These data can then be used for further analysis and processing.

[0022] Through the above steps, the data acquisition module 20 collects and processes various sensor data according to preset acquisition constraints, ensuring that the system can accurately and in real time monitor environmental status, strain and rotation, and provide comprehensive monitoring data support.

[0023] The data correction module 30 is used to perform environmental correction on the strain data and the rotation data based on the environmental state data to obtain standard state monitoring data, wherein the standard state monitoring data includes standard strain data and standard rotation data.

[0024] Specifically, during environmental correction, strain data and rotation data are adjusted according to environmental state data to obtain more accurate monitoring data. Standard state monitoring data is monitoring data after environmental correction, including standard strain data and standard rotation data. Among them, standard strain data is strain data after environmental correction. Standard rotation data is rotation data after environmental correction.

[0025] First, the data correction module 30 receives environmental status data, which reflects the actual conditions of the monitoring environment. Then, the module analyzes the impact of the environmental status data on the strain data and the rotation data. For example, temperature changes will affect the strain data of the material, while pressure changes may affect the accuracy of the rotation data. According to the results of the environmental impact analysis, the data correction module 30 uses a preset algorithm or calibration model to correct the original strain data and rotation data. The corrected data are called standard state monitoring data, which are equivalent data under standard environmental conditions. For example, if the original strain data is affected by temperature changes, the correction module will calculate the corrected strain data based on the temperature change and the temperature coefficient of the strain material to make it meet the standard environmental conditions.

[0026] Through the above steps, the data correction module 30 can provide standard state monitoring data after environmental correction. These corrected data are more accurate, can reflect the actual operating state of the equipment under different environmental conditions, and provide reliable monitoring and analysis results.

[0027] The data processing module 40 is used to perform self-division filtering and noise reduction on the standard state monitoring data to obtain standard monitoring data.

[0028] Specifically, self-division filtering and noise reduction is a data processing technology that automatically divides the data interval and applies a filtering algorithm to remove noise and improve the accuracy of the data. Standard monitoring data is high-quality data obtained after filtering and noise reduction.

[0029] First, the standard state monitoring data is divided into intervals, and the data is divided into multiple intervals by analyzing data characteristics, such as change trends and frequency components. A filtering algorithm is applied to each divided data interval to remove noise. Commonly used filtering algorithms include mean filtering, median filtering, wavelet transform and Kalman filtering. The processed data intervals are recombined to generate the final standard monitoring data. The data processing module 40 performs effective self-division filtering and noise reduction processing on the standard state monitoring data, and finally obtains high-quality standard monitoring data, thereby ensuring the quality of the data and providing reliable data support for subsequent analysis and decision-making.

[0030] The data transmission module 50 is used to transmit the standard monitoring data to a host computer to make remote management decisions for the casing torque monitoring sub.

[0031] Specifically, the host computer refers to the main control computer in the remote management system, which is responsible for receiving the transmitted standard data, analyzing and making decisions. The casing torque monitoring sub is a device used to monitor the torque changes during the casing lowering process, helping to monitor the installation status of the casing and the stability of the drilling process. Remote management decisions refer to the control and adjustment decisions made after data analysis through the remote system to maintain the optimal operating status of the equipment.

[0032] The data transmission module 50 first packages and encodes the standard monitoring data obtained from the data processing module 40 to ensure that the data is not lost and is complete during the transmission process. Using a network communication protocol, such as TCP / IP or UDP, the data is transmitted from the data acquisition point to the host computer to ensure the reliability and real-time performance of data transmission. The host computer usually runs specific software, such as monitoring software or data analysis software, to receive and process the data. After receiving the data, the host computer parses and processes it for further analysis and display. The software on the host computer analyzes the received data and makes decisions based on the data. Exemplarily, when the monitoring system detects a change in the strain data of the casing torque, the data transmission module 50 sends these changed standard data to the host computer located in the control center through the network. After the host computer receives the data, it uses data analysis software, such as the analysis library in MATLAB or Python, to process and analyze the data. If an abnormal increase in torque is detected, the system may adjust the torque or stop the equipment through remote instructions to prevent damage to the equipment.

[0033] Through the above steps, the data transmission module 50 ensures the real-time and accuracy of the data, supports remote monitoring and management decisions, and improves the safety and efficiency of operations.

[0034] Furthermore, the multimodal sensor described in the multimodal sensing module 10 of the embodiment of the present application includes an environmental state sensor, a torque monitoring sensor and a rotation monitoring sensor, wherein the environmental state sensor includes at least a temperature sensor and a pressure sensor, the torque monitoring sensor includes at least a microstrain sensor, and the rotation monitoring sensor includes at least a MEMS gyroscope and a geomagnetic sensor.

[0035] Specifically, in the specific multimodal sensor configuration process, the environmental state sensor includes at least a temperature sensor and a pressure sensor, which are used to measure the temperature and pressure of the environment. The temperature sensor can be a thermocouple or an RTD sensor, such as a K-type thermocouple, which can accurately measure the ambient temperature and remain stable under extreme conditions. The pressure sensor can be a piezoresistive pressure sensor, such as an MPX series sensor, which can accurately detect changes in ambient pressure. These sensors monitor and record environmental state data in real time by connecting to the data acquisition module 20.

[0036] The torque monitoring sensor includes at least a micro strain sensor, which is a sensor that detects tiny strain changes in an object. The micro strain sensor usually measures the strain through a strain gauge and then converts it into an electrical signal through a bridge circuit. For example, a strain gauge sensor can be attached to the surface of the casing and measures the torque by detecting strain changes. It has high sensitivity and stability. These sensors are connected to the data acquisition module 20 through a dedicated amplifier to provide torque data in real time.

[0037] The rotation monitoring sensor includes at least a MEMS gyroscope and a geomagnetic sensor. The MEMS gyroscope, i.e., a micro-electromechanical system gyroscope, is a small sensor for detecting angular velocity. For example, ADI's ADXL series gyroscope can be installed on a rotating part to detect angular velocity. The geomagnetic sensor is a sensor for measuring the direction of the geomagnetic field, such as an electronic compass, which can detect the direction of the geomagnetic field and can be installed on the casing to monitor the rotation direction of the casing. These sensors are connected to the data acquisition module 20 through a digital interface to ensure rapid transmission and processing of data.

[0038] Further, such as Figure 2 As shown, the data acquisition module 20 in the embodiment of the present application is also used to perform the following steps: Step P21: Initializing monitoring acquisition parameters of the multimodal sensor based on the acquisition constraints.

[0039] Step P22: Activate the initialized environmental state sensor to obtain environmental state data, where the environmental state data includes an environmental temperature series and an environmental pressure series.

[0040] Step P23: Synchronously activate the torque monitoring sensor to obtain strain data, wherein the strain data includes a torque fluctuation series and a tension fluctuation series.

[0041] Step P24: Based on the target casing setting control parameters, the rotation monitoring sensor is synchronously activated to collect and acquire the rotation data, wherein the rotation data includes a rotation speed series and a revolution number series.

[0042] Step P25: aligning the environmental state data, the strain data, and the rotation data in terms of time granularity to determine them as the initial monitoring data.

[0043] Specifically, first, the monitoring acquisition parameters of the multimodal sensor are initialized based on the preset acquisition constraints. The monitoring acquisition parameters are the parameters that the sensor needs to set during the data acquisition process, including sampling frequency, sensitivity, and data format. During the sensor initialization phase, the sampling frequency and timestamp of all sensors are set to be consistent to ensure that they work under the same time reference.

[0044] Next, data collection is performed. During the data collection process, all sensor data are accompanied by accurate timestamps, which are used for subsequent data alignment. The data collection module 20 uses a synchronization signal, such as an external trigger signal or an internal clock signal, to ensure that all sensors start collecting data at the same time point.

[0045] The initialized environmental state sensor is activated to start collecting raw temperature, pressure and other data, and obtain environmental state data through AD conversion. The environmental state data includes an environmental temperature series and an environmental pressure series. The environmental temperature series refers to a temperature data sequence that changes over time. The environmental pressure series refers to a pressure data sequence that changes over time. The torque monitoring sensor is synchronously activated to collect raw data, and obtain strain data through AD conversion. Strain data includes a torque fluctuation series and a tension fluctuation series. The torque fluctuation series refers to a torque data sequence that changes over time. The tension fluctuation series refers to a tension data sequence that changes over time. Based on the control setting parameters of the target casing, the rotation monitoring sensor is synchronously activated to collect raw angular velocity and angular displacement data, and obtain rotation data through AD conversion. The control setting parameters are the operating parameters required for the target casing during operation. The target casing refers to any casing for operation monitored by the system. The rotation data includes a rotation speed series and a number of revolutions series. The rotation speed series refers to a rotation speed data sequence that changes over time. The number of revolutions series refers to a cumulative rotation number of revolutions data sequence.

[0046] Finally, the environmental state data, strain data, and rotation data are aligned in time granularity. This process can be done using data processing software, such as MATLAB, to ensure that all data are compared and analyzed at the same time point through timestamps or synchronization signals. For example, temperature data, pressure data, torque data, and rotation data are sampled at the same time interval so that these data can be analyzed on the same time axis.

[0047] Through the above steps, the data acquisition module 20 can effectively initialize sensor parameters according to preset acquisition constraints, collect and process environmental state data, strain data and rotation data, and perform time granularity alignment to ensure the synchronization and accuracy of all data.

[0048] Preferably, the data acquisition module 20 of the embodiment of the present application is also used to perform the following steps: Step P24-1: Interact with the casing lowering control terminal to obtain the control setting parameters.

[0049] Step P24-2: Perform interval discrimination based on the control setting parameters and the monitoring confidence interval of the rotation monitoring sensor.

[0050] Step P24-3: If the control setting parameter is in the low-speed acquisition interval, the geomagnetic sensor is activated to perform rotation monitoring, and the rotation monitoring result is AD converted to obtain the rotation data.

[0051] Step P24-4: If the control setting parameter is in the high-speed acquisition interval, switch to the MEMS gyroscope for rotation monitoring, and perform AD conversion on the rotation monitoring result to obtain the current rotation speed and number of revolutions, and output it as the rotation data.

[0052] Specifically, the monitoring confidence interval refers to the credible interval of sensor measurement, that is, the effective working range of the sensor under specific conditions. The low-speed acquisition interval refers to the measurement range of the sensor applicable to low-speed rotation. The high-speed acquisition interval refers to the measurement range of the sensor applicable to high-speed rotation.

[0053] When monitoring the rotation of the target casing, it is first necessary to interact with the casing control terminal to obtain the control setting parameters. These parameters include the target speed and number of revolutions of the target casing. According to the control setting parameters, the interval is judged in combination with the monitoring confidence interval of the rotation monitoring sensor. If the control setting parameters are in the low-speed acquisition interval, the geomagnetic sensor is activated for rotation monitoring. If the control setting parameters are in the high-speed acquisition interval, the MEMS gyroscope is switched to rotation monitoring. The sensor converts the analog signal into a digital signal through an AD converter to obtain the current speed and accumulated number of revolutions. These data are output as rotation data.

[0054] Exemplarily, the effective working range of the geomagnetic sensor is 0-50 rpm, and the effective working range of the MEMS gyroscope is 50-1000 rpm, that is, the monitoring confidence interval of the rotation monitoring sensor is the low-speed acquisition interval: 0-50 rpm, and the high-speed acquisition interval: 50-1000 rpm. Interact with the casing control terminal, when the speed is set to 30 rpm, it is in the low-speed acquisition interval, and the geomagnetic sensor is activated for rotation monitoring. When the speed is set to 600 rpm, it is in the high-speed acquisition interval, and the MEMS gyroscope is activated for rotation monitoring.

[0055] Through the above steps, the module can set the control parameters of the target casing, select the appropriate sensor for rotation monitoring, obtain high-precision rotation data through AD conversion, ensure accurate monitoring of the rotation state of the casing at different speeds, and provide reliable data support.

[0056] Further, such as Figure 3 As shown, the data correction module 30 in the embodiment of the present application is also used to perform the following steps: Step P31: Obtain historical monitoring records, and extract a sample correction data set based on a sliding window method, wherein the sample correction data set includes historical environmental status data, historical standard state monitoring data, and historical initial monitoring data that are stored in an associated manner.

[0057] Step P32: Calculate and obtain the data difference between the historical standard state monitoring data and the historical initial monitoring data, and construct a difference distribution.

[0058] Step P33: Based on the difference distribution, a partition extraction ratio is configured, and based on the partition extraction ratio, a lightweight extraction of the sample correction data set is performed to obtain corrected training data.

[0059] Step P34: construct an environment correction model, train the environment correction model according to the correction training data, and input the environment state data, the strain data, and the rotation data to perform environment correction.

[0060] Specifically, firstly, historical monitoring records are obtained from the database. Historical monitoring records are data collected during past monitoring processes. These records include historical environmental state data, historical standard state monitoring data, and historical initial monitoring data. These historical environmental state data, historical standard state monitoring data, and historical initial monitoring data are stored in the database in chronological order and in association, so as to facilitate subsequent data extraction and analysis. The sample correction data set is extracted using the sliding window method. First, a fixed sliding window is set, starting from the first point of the data, and each sliding is performed at a fixed time interval to extract a subset of the data within the window. In this way, the sample correction data set is extracted, wherein the sample correction data set contains historical environmental state data such as temperature and pressure stored in association; historical standard state monitoring data, i.e., strain and rotation data after environmental correction; and historical initial monitoring data, i.e., original strain and rotation data without correction.

[0061] For example, assuming that the sliding window size is 1 hour, the data correction module 30 will extract hourly environmental status data, corresponding standard state monitoring data and initial monitoring data from the historical data.

[0062] For each time point, calculate the difference between the historical standard state monitoring data and the historical initial monitoring data, that is, the data difference. Data difference refers to the difference between the historical standard state monitoring data and the historical initial monitoring data, which can be obtained by directly calculating the difference or calculating the root mean square error. Difference distribution refers to the distribution of data difference in the sample data set, which is used to guide the lightweight extraction of the sample correction data set. Exemplarily, the difference calculation formula is: Difference = standard state monitoring data-initial monitoring data. The initial strain data at a certain time point is 0.003, and the standard state strain data is 0.0028, then the difference is 0.0002. Collect the differences at all time points and construct a difference distribution graph. You can use tools such as Matplotlib in Python to draw a difference distribution graph to show the distribution of the difference in the entire data set.

[0063] According to the difference distribution, the data is divided into multiple intervals, and the partition extraction ratio is configured for each interval. Use the configured partition extraction ratio to perform lightweight extraction on the sample correction data set to reduce the amount of data and improve processing efficiency. The partition extraction ratio is the data extraction ratio of different intervals set according to the difference distribution. Lightweight extraction means extracting data from the sample data set in proportion. For example, the data is divided into low difference intervals, medium difference intervals, and high difference intervals. Extract 10% of the data from the low difference interval, 30% of the data from the medium difference interval, and 50% of the data from the high difference interval.

[0064] The extracted data is used as the corrected training data. The environmental correction model is constructed using the corrected training data. Machine learning algorithms such as linear regression, decision trees, or neural networks can be used. Corrected training data is a data set used to train the environmental correction model. The environmental correction model is a mathematical model used to correct strain data and rotation data based on environmental state data. For example, using the Scikit-learn library in Python, a linear regression model is constructed, and the environmental state data is used as input features and the standard state monitoring data is used as output labels for training. After the training is completed, the environmental state data, strain data, and rotation data collected in real time are input into the environmental correction model, and the model makes predictions based on the input data and outputs the corrected standard strain data and standard rotation data.

[0065] Through the above steps, the data correction module 30 can establish an effective environmental correction model, and finally realize the environmental correction of real-time data, ensuring the accuracy and reliability of the data.

[0066] Furthermore, the data processing module 40 in the embodiment of the present application is also used to perform the following steps: Step P41: Performing empirical mode decomposition on the standard state monitoring data to obtain multiple modal components.

[0067] Step P42: Calculate the correlation coefficients between the multiple modal components and the standard state monitoring data to obtain a correlation coefficient set.

[0068] Step P43: According to a preset correlation threshold, a noise modal component set is extracted based on the correlation coefficient set, and wavelet filtering is performed on the noise modal component set to obtain the standard monitoring data.

[0069] Specifically, first, perform empirical mode decomposition on the standard monitoring data to decompose the signal into several intrinsic mode components, each of which represents the oscillation component of the signal at different frequency scales. Through an iterative process, empirical mode decomposition identifies and extracts the intrinsic mode components in the signal. For example, if the standard monitoring data is the strain data of the casing, empirical mode decomposition can decompose the data into several mode components, each of which corresponds to a different vibration frequency.

[0070] Calculate the correlation coefficient between each modal component and the standard monitoring data to obtain a set of correlation coefficients. The correlation coefficient indicates the strength of the linear relationship between two variables. The most commonly used correlation coefficient is the Pearson correlation coefficient, which ranges from -1 to 1. A value of 1 indicates a perfect positive correlation, a value of -1 indicates a perfect negative correlation, and a value close to 0 indicates no linear relationship. During implementation, the Pearson correlation coefficient between each modal component and the standard monitoring data can be calculated using statistical software, such as the numpy.corrcoef function in Python or the cor function in R. A set of correlation coefficients refers to a collection of correlation coefficients between multiple modal components and standard monitoring data. The correlation coefficient measures the strength of the linear relationship between the modal component and the original data. For example, if a modal component is highly correlated with the original strain data, then this component may represent the main vibration mode of the data.

[0071] According to the preset correlation threshold, the modal components with low correlation with the original data are selected as the noise modal component set. The correlation threshold is a preset critical value for judging the strength of the correlation. If the correlation coefficient of a modal component is lower than the threshold, it is considered to be mainly composed of noise and added to the noise modal component set. The noise modal component set is the modal component determined based on the correlation coefficient being lower than the correlation threshold, and it is considered that these components are mainly composed of noise. The noise modal component set is subjected to wavelet filtering, which is a filtering technique using wavelet transform to remove noise. Wavelet filtering reduces high-frequency noise by adjusting the wavelet coefficients and retains the low-frequency components of the signal. Finally, the processed modal components are reconstructed to obtain standard monitoring data.

[0072] Through these steps, the data processing module 40 can extract useful information from the signal, remove noise, and generate clearer standard monitoring data.

[0073] Furthermore, the data transmission module 50 in the embodiment of the present application is also used to perform the following steps: Step P51: The host computer performs unloading judgment based on the embedded load control limit, wherein the load control limit includes the strain control limit and the rotation control limit.

[0074] Step P52: If any one of the standard strain data and the standard rotation data does not satisfy the load control limit, the load unloading quality is activated to perform automatic unloading.

[0075] Specifically, the load control limit is the safety control limit of strain and rotation preset in the host computer, which is used to judge the load condition of the equipment. The strain control limit is the safety threshold of the strain data, that is, the maximum allowable value of the strain borne by the casing. Exceeding this threshold may mean that the equipment is subjected to excessive pressure or load. The rotation control limit is the safety threshold of the rotation data, that is, the maximum allowable value of the torque borne by the casing. Exceeding this threshold may mean that the rotation speed or angle of the equipment exceeds the safe range. These thresholds are set based on engineering experience and safety standards to prevent equipment damage and operational accidents. For example, the strain control limit can be determined based on the strength and design parameters of the casing material, while the rotation control limit can be set based on the maximum bearing capacity of the drilling equipment.

[0076] The data transmission module 50 first sends the standard strain data and the standard rotation data to the host computer. After receiving the standard strain data and the standard rotation data, the embedded control program of the host computer will perform unloading judgment and compare these standard monitoring data with the load control limit in real time. If any data exceeds its control limit, that is, it does not meet the load control limit, the host computer will automatically activate the load unloading mechanism and perform automatic unloading. This usually means that the operating conditions have exceeded the safety range and measures need to be taken to avoid equipment damage or accidents. Load unloading quality refers to the measures taken to reduce or eliminate loads that exceed the control limit. Automatic unloading means that the system automatically performs unloading operations, such as reducing the drilling speed or adjusting the drilling parameters to reduce torque and strain. Through automatic unloading, the data transmission module 50 realizes real-time monitoring and safe control of the casing torque, ensuring the safety and efficiency of the operation process.

[0077] Furthermore, the data transmission module 50 of the embodiment of the present application transmits the standard monitoring data to the host computer, including transmitting the standard monitoring data via a 2.4G wireless signal.

[0078] Specifically, in a specific implementation, the data transmission module 50 first packages the processed standard monitoring data and prepares for wireless transmission. The packaged data is converted into a 2.4G wireless signal through a modem and sent. The 2.4G wireless signal uses radio waves in the 2.4GHz frequency band for data transmission. This frequency band is a license-free frequency band allowed in most countries around the world, and has the advantages of fast transmission speed and wide coverage. The host computer is equipped with a corresponding wireless receiving module to receive wireless signals in the 2.4G frequency band. After receiving the wireless signal, the signal is decoded into raw data through a modem for further analysis and application.

[0079] In summary, the remote management system for rotating casing torque monitoring sub provided by the embodiments of the present application has the following technical effects: The multimodal sensing module 10 provides a comprehensive data acquisition basis by arranging and configuring multimodal sensors and establishing sensor connections. Among them, the multimodal sensors include environmental state sensors, torque monitoring sensors and rotation monitoring sensors. The data acquisition module 20 collects raw data based on preset acquisition constraints, obtains initial monitoring data through AD conversion, and converts physical signals into digital signals for subsequent digital processing, thereby realizing automated and standardized data acquisition and improving the efficiency and accuracy of data acquisition. Among them, the initial monitoring data includes environmental state data, strain data, and rotation data. The data correction module 30 uses the sliding window method and difference distribution to train the environmental correction model based on historical monitoring records, uses the environmental correction model to perform environmental correction on the strain data and the rotation data based on the environmental state data, and obtains standard state monitoring data to eliminate the influence of environmental factors on the data, thereby improving the accuracy of the data. The standard state monitoring data includes standard strain data and standard rotation data, which more truly reflects the torque state of the casing. The data processing module 40 performs self-division filtering and noise reduction on the standard state monitoring data, obtains standard monitoring data, eliminates random errors and noise in the data, and obtains more accurate and reliable monitoring data. The data transmission module 50 transmits the standard monitoring data to the host computer, which performs unloading judgment and automatic unloading based on the embedded load control limit, completes the remote management decision of the casing torque monitoring short section, realizes remote monitoring and management, and improves the safety and efficiency of the operation.

[0080] In general, the embodiment of the present application effectively captures and corrects environmental, strain and rotation data through multimodal sensors and data correction module 30, ensures the accuracy and reliability of monitoring data, and further improves data quality and reduces noise interference through self-division filtering and noise reduction method by data processing module 40. Finally, data transmission module 50 transmits high-quality standard monitoring data to the host computer, realizing remote real-time management and decision-making. In this way, the system not only improves monitoring accuracy, but also enhances real-time response capability and convenience of remote management, helps to timely discover and handle casing torque anomalies, and improves the safety and efficiency of operations.

[0081] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. Remote management system for rotating casing torque monitoring sub, It is characterized in that The system comprises: A multimodal sensing module, which is used to arrange and configure multimodal sensors and establish sensing connections, wherein the multimodal sensors include environmental status sensors, torque monitoring sensors, and rotation monitoring sensors; A data acquisition module, the data acquisition module is used to collect raw data based on preset acquisition constraints, and obtain initial monitoring data through AD conversion, wherein the initial monitoring data includes environmental state data, strain data, and rotation data; A data correction module, the data correction module is used to perform environmental correction on the strain data and the rotation data based on the environmental state data to obtain standard state monitoring data, wherein the standard state monitoring data includes standard strain data and standard rotation data; A data processing module, the data processing module is used to perform self-division filtering and noise reduction on the standard state monitoring data to obtain standard monitoring data; A data transmission module is used to transmit the standard monitoring data to a host computer to make remote management decisions for the casing torque monitoring sub.

2. The remote management system for rotating casing torque monitoring sub according to claim 1, It is characterized in that The multimodal sensor in the multimodal sensing module includes an environmental state sensor, a torque monitoring sensor and a rotation monitoring sensor, wherein the environmental state sensor includes at least a temperature sensor and a pressure sensor, the torque monitoring sensor includes at least a microstrain sensor, and the rotation monitoring sensor includes at least a MEMS gyroscope and a geomagnetic sensor.

3. The remote management system for rotating casing torque monitoring sub according to claim 2, It is characterized in that The data acquisition module collects raw data based on preset acquisition constraints, and obtains initial monitoring data through AD conversion. The execution steps include: Initializing monitoring acquisition parameters of the multimodal sensor based on the acquisition constraints; activating the initialized environmental state sensor to obtain environmental state data, wherein the environmental state data includes an environmental temperature series and an environmental pressure series; Synchronously activating the torque monitoring sensor to obtain strain data, wherein the strain data includes a torque fluctuation series and a tension fluctuation series; Based on the control setting parameters of the target casing, the rotation monitoring sensor is synchronously activated to collect and obtain the rotation data, wherein the rotation data includes a rotation speed series and a revolution number series; The environmental state data, the strain data, and the rotation data are aligned in time granularity to be determined as the initial monitoring data.

4. The remote management system for rotating casing torque monitoring sub according to claim 3, It is characterized in that The data acquisition module synchronously activates the rotation monitoring sensor based on the control setting parameters of the target casing, collects and obtains the rotation data, and the execution steps include: Interactively access the casing control terminal to obtain the control setting parameters; According to the control setting parameters, combined with the monitoring confidence interval of the rotation monitoring sensor, interval discrimination is performed; If the control setting parameter is in the low-speed acquisition interval, the geomagnetic sensor is activated to perform rotation monitoring, and AD conversion is performed on the rotation monitoring result to obtain the rotation data; If the control setting parameter is in the high-speed acquisition interval, the MEMS gyroscope is switched to perform rotation monitoring, and the rotation monitoring result is AD converted to obtain the current rotation speed and number of revolutions, which are output as the rotation data.

5. The remote management system for rotating casing torque monitoring sub according to claim 4, It is characterized in that The data correction module performs environmental correction on the strain data and the rotation data based on the environmental state data to obtain standard state monitoring data, and the execution step further includes: Obtain historical monitoring records, and extract a sample correction data set based on a sliding window method, wherein the sample correction data set includes historical environmental state data, historical standard state monitoring data, and historical initial monitoring data that are stored in an associated manner; Calculate and obtain the data difference between the historical standard state monitoring data and the historical initial monitoring data, and construct a difference distribution; Based on the difference distribution, a partition extraction ratio is configured, and based on the partition extraction ratio, a lightweight extraction of the sample correction data set is performed to obtain correction training data; An environment correction model is constructed, the environment correction model is trained according to the correction training data, and the environment state data, the strain data, and the rotation data are input to perform environment correction.

6. The remote management system for rotating casing torque monitoring sub according to claim 5, It is characterized in that The data processing module performs self-division filtering and noise reduction on the standard state monitoring data to obtain standard monitoring data, and the execution step further includes: Performing empirical mode decomposition on the standard state monitoring data to obtain multiple modal components; Calculating correlation coefficients between a plurality of modal components and the standard state monitoring data to obtain a correlation coefficient set; According to a preset correlation threshold, a noise modal component set is extracted based on the correlation coefficient set, and wavelet filtering is performed on the noise modal component set to obtain the standard monitoring data.

7. The remote management system for rotating casing torque monitoring sub according to claim 6, It is characterized in that The data transmission module transmits the standard monitoring data to the host computer to make remote management decisions for the casing torque monitoring sub, and the execution steps also include: The host computer performs unloading judgment based on the embedded load control limit, wherein the load control limit includes a strain control limit and a rotation control limit; If any one of the standard strain data and the standard rotation data does not satisfy the load control limit, the load unloading quality is activated to perform automatic unloading.

8. The remote management system for rotating casing torque monitoring sub according to claim 1, It is characterized in that The data transmission module transmits the standard monitoring data to the host computer, including transmitting the standard monitoring data via a 2.4G wireless signal.

Images