Shaft digital twinning system based on simulation technology

Abstract

The invention relates to the technical field of oil exploitation, in particular to a simulation technology-based shaft digital twinning system, which comprises a data acquisition unit, a data processing unit, a data compensation unit, a data modeling unit, a data prediction unit, an operation grading unit, a data storage unit and a data visualization unit, the data acquisition unit is used for acquiring data of a shaft, and the shaft data acquired by the data acquisition unit comprises well body structure data, drill string data, in-well fluid data, well track data and well periphery geological data; according to the digital twin system designed by the invention, data acquired by the data acquisition unit can be verified and compensated through the data compensation unit, wrong data are screened out, and the wrong data detected by the sensor is prevented from being transmitted to the digital twin system to influence simulation modeling of the digital twin system; and meanwhile, the problem of logic errors of the digital twinborn system caused by the fact that the digital twinborn system cannot process error data to obtain a result is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of oil extraction, and in particular to a wellbore digital twin system based on simulation technology. Background Art

[0002] Oil drilling is an extremely complex process. With the continuous growth of global energy demand and the gradual depletion of oil and gas resources, drilling technology is facing unprecedented challenges and opportunities. Against this background, drilling digital twin technology, as an emerging intelligent technology, has received widespread attention from academia and industry at home and abroad.

[0003] For example, a digital wellbore construction method based on digital twin technology, with application number CN202310388020.X and application date 20230412, has the following technical solutions: the first layer, the physical space layer, that is, the physical wellbore part that actually exists in the physical world; the second layer, the data layer, that is, the twin database, including basic data and real-time data; the third layer, the data interaction layer, that is, relying on downhole sensors, signal receivers, optical fibers, and 5G communication technology to transmit real-time data to the virtual model layer; the fourth layer, the virtual model layer, that is, the real wellbore in the physical world is realized in real time and synchronously in the virtual digital space through mathematical modeling; the fifth layer, the application layer, the twin wellbore is continuously updated under the drive of real-time data, and is always kept synchronized with the real wellbore in the physical space. The beneficial effect is that the present invention uses a digital method to accurately map the real wellbore in the drilling process from multiple dimensions, thereby realizing the monitoring, optimization, analysis, control and prediction of the entire drilling process.

[0004] When the drilling wellbore is modeled and simulated through digital twin technology, data will be collected through a variety of sensors, and the collected data will be transmitted through network communication. However, during drilling, sensors are prone to unexpected failures and other problems, resulting in errors in the data detected by sensors arranged in the wellbore. The erroneous data will affect the simulation modeling accuracy of the wellbore digital twin system, resulting in large errors during drilling. At the same time, when the wellbore digital twin system processes erroneous data, it will take a long time to build a suitable model due to data errors, resulting in logical problems in the wellbore digital twin system. Therefore, it is urgent to design a wellbore digital twin system based on simulation technology to solve the above problems. Summary of the invention

[0005] The purpose of the present invention is to provide a wellbore digital twin system based on simulation technology to solve the above-mentioned deficiencies in the prior art.

[0006] In order to achieve the above object, the present invention provides the following technical solutions: A wellbore digital twin system based on simulation technology, comprising a data acquisition unit, a data processing unit, a data compensation unit, a data modeling unit, a data prediction unit, an operation classification unit, a data storage unit, and a data visualization unit; The data acquisition unit is used to acquire wellbore data, and the wellbore data acquired by the data acquisition unit includes wellbore structure data, drill string data, wellbore fluid data, wellbore trajectory data, and well periphery geological data. The data acquisition unit includes a sensor module, a camera module, and a node module. The sensor module, the camera module, and the node module are divided into multiple groups, and each group of the sensor module, the camera module, and the node module are arranged in the same wellbore. The sensor module collects various parameters in the drilling process in real time by being set on the drilling equipment. The camera module is used to monitor the process of wellbore construction. The node module includes a main node submodule, a sub-node submodule, a detection submodule, and a data compression submodule. The main node submodule and the sub-node submodule are both sensor module communication interfaces. The detection submodule is established based on the PhiAccrualFailure algorithm. The detection submodule is used to detect the operating status of the main node submodule or the sub-node submodule. The data compression submodule determines whether to compress the data by calculating the compression comparison formula, and the compression comparison formula is as follows:

[0007] Among them, S is the compression comparison formula ratio, A is the size of the data to be transmitted, and B is the network rate. If S≤1, the data compression submodule will not compress the data through the data compression technology. If S>1, the data compression submodule will compress the data through the data compression technology. The data compensation unit is used to verify and compensate the data acquired by the data acquisition unit. The data compensation unit includes a temporary storage submodule, a verification submodule and a compensation submodule. The temporary storage submodule uses a cloud cache database. The temporary storage submodule is used to temporarily store the data acquired by the data acquisition unit. When verifying, the verification submodule compares and verifies the data temporarily stored in the temporary storage submodule with the stored previous wellbore data, and uses a similarity comparison formula during verification. The similarity comparison formula is as follows:

[0008] in, Represents two sets of data, , is the similarity between two sets of data. The larger the value, the more similar the two sets of data are. 0≤ ≤1, is the variance between the two corresponding data in the two sets of data, is the data in the first set of data, For the second set of data Corresponding data, d is the number of data in the two groups of data, is the sum of products of similar data, is the base of the natural logarithm of the two sets of data; The compensation submodule uses the Smith estimation compensation control algorithm to compensate the data temporarily stored in the temporary storage submodule; The data processing unit is used to process the data compensated by the data compensation unit, the data modeling unit is used to model and simulate the data processed by the data processing unit, the data prediction unit predicts the wellbore according to the processing result of the data processing unit, the data storage unit is used to store the data of the digital twin system operation, the data visualization unit is used to visualize the data of the digital twin system operation, the operation classification unit is used to provide operation computing power for the data compensation unit, the data processing unit, the data modeling unit and the data prediction unit, the data processing unit analyzes and processes the data acquired by the data acquisition unit through four methods: data preprocessing, data cleaning, data fusion and data analysis, the modeling unit constructs a three-dimensional simulation model of the wellbore through modeling and simulation software, the prediction unit is constructed based on deep learning technology, and the prediction unit predicts based on the simulation of the data modeling unit, the data storage unit selects two types of cloud database and storage server, the data visualization unit uses one or more of desktop computers, laptops and industrial tablets, the operation classification unit is established based on virtual computing technology, and the operation classification unit is opened according to the amount of memory occupied by the digital twin system.

[0009] In the above technical solution, the present invention provides a wellbore digital twin system based on simulation technology, which has the following beneficial effects: (1) The digital twin system designed by the present invention can verify and compensate the data collected by the data acquisition unit through the data compensation unit, filter out erroneous data, and avoid the erroneous data detected by the sensor being transmitted to the digital twin system, affecting the simulation modeling of the digital twin system. At the same time, it also solves the problem that the digital twin system cannot process the erroneous data and causes logical errors in the digital twin system.

[0010] (2) The data acquisition unit designed in the present invention can not only acquire the data of the wellbore, but also switch the sub-node sub-module to transmit data when the main node sub-module fails through the detection of the detection sub-module, which greatly improves the disaster recovery capability of the digital twin system when transmitting data and reduces the probability of data loss, defect and other problems. At the same time, it can also enable the data to be transmitted to the digital twin system in a timely manner, so that the digital twin system can model and simulate in time and display the wellbore data, avoiding the workers' inability to deal with the failure in time when the failure occurs, causing greater disasters. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0012] Figure 1 A system flow diagram is provided for an embodiment of a wellbore digital twin system based on simulation technology of the present invention.

[0013] Figure 2 A schematic diagram of the data acquisition unit structure provided for an embodiment of a wellbore digital twin system based on simulation technology of the present invention.

[0014] Figure 3 A schematic diagram of the node module structure provided for an embodiment of a wellbore digital twin system based on simulation technology of the present invention.

[0015] Figure 4 A schematic diagram of the structure of a data compensation unit provided in an embodiment of a wellbore digital twin system based on simulation technology of the present invention. DETAILED DESCRIPTION

[0016] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings.

[0017] like Figure 1-4 As shown, a wellbore digital twin system based on simulation technology provided by an embodiment of the present invention includes a data acquisition unit, a data processing unit, a data compensation unit, a data modeling unit, a data prediction unit, an operation classification unit, a data storage unit, and a data visualization unit; The data acquisition unit is used to acquire the data of the wellbore. The wellbore data acquired by the data acquisition unit includes wellbore structure data, drill string data, wellbore fluid data, wellbore trajectory data, and wellbore geological data. The data acquisition unit includes a sensor module, a camera module, and a node module. The sensor module, the camera module, and the node module are divided into multiple groups. Each group of sensor modules, camera modules, and node modules are arranged in the same wellbore. The sensor module collects various parameters in the drilling process in real time by being set on the drilling equipment. The camera module is used to monitor the process of wellbore construction. The node module includes a main node submodule, a sub-node submodule, a detection submodule, and a data compression submodule. The main node submodule and the sub-node submodule are both sensor module communication interfaces. The detection submodule is established based on the PhiAccrualFailure algorithm. The detection submodule is used to detect the operating status of the main node submodule or the sub-node submodule. The data compression submodule determines whether to compress the data by calculating the compression comparison formula, and the compression comparison formula is as follows:

[0018] Among them, S is the compression comparison formula ratio, A is the size of the data to be transmitted, and B is the network rate. If S≤1, the data compression submodule will not compress the data through the data compression technology. If S>1, the data compression submodule will compress the data through the data compression technology. It should be noted that ‌PhiAccrualFailureDetector‌ is a fault detection algorithm used in distributed systems. It estimates the probability of node failure by counting the arrival time of heartbeat signals. The core idea of ​​the algorithm is to use exponential distribution to estimate the probability of node failure and decide whether to mark the node as failed based on this probability; The basic principle is as follows: PhiAccrualFailureDetector uses exponential distribution to estimate the probability of node failure. The algorithm records the time interval of received heartbeat signals through a sliding window and uses this data to generate an exponential distribution to estimate the probability that the next heartbeat should arrive at the current moment. Specifically, the algorithm calculates the average interval time of heartbeat signals and uses this average value to calculate the probability of node failure.

[0019] Algorithm steps ‌Collect heartbeat signals‌: The algorithm continuously collects heartbeat signals from each node and records the arrival time of each heartbeat signal; ‌Calculate the average interval time‌: Using the sliding window technique, the algorithm calculates the average interval time of the heartbeat signal; ‌Estimate failure probability‌: Based on the mean interval time, the probability of node failure is calculated using the exponential distribution formula; Decision: Based on the calculated failure probability, the algorithm decides whether to mark the node as failed. If the probability exceeds a certain threshold, the node is considered to have probably failed.

[0020] The data compensation unit is used to verify and compensate the data acquired by the data acquisition unit. The data compensation unit includes a temporary storage submodule, a verification submodule and a compensation submodule. The temporary storage submodule uses a cloud cache database. The temporary storage submodule is used to temporarily store the data acquired by the data acquisition unit. When verifying, the verification submodule will compare and verify the data temporarily stored in the temporary storage submodule with the stored previous wellbore data, and a similarity comparison formula is used during verification. The similarity comparison formula is as follows:

[0021] in, Represents two sets of data, , is the similarity between two sets of data. The larger the value, the more similar the two sets of data are. 0≤ ≤1, is the variance between the two corresponding data in the two sets of data, is the data in the first set of data, For the second set of data Corresponding data, d is the number of data in the two groups of data, is the sum of products of similar data, is the base of the natural logarithm of the two sets of data; The compensation submodule uses the Smith predictive compensation control algorithm to compensate the data temporarily stored in the temporary storage submodule; It should be noted that the Smith predictive control algorithm improves the dynamic performance of the system by introducing a model prediction to compensate for the lag in the system. Its working principle includes the following steps: ‌System Modeling‌: Assume there is a pure hysteresis system G(s), which can be modeled. The Smith predictor uses this model to predict the future behavior of the system. ‌Prediction hysteresis‌: By calculating the system model, the Smith estimator predicts the behavior of the system at future moments without hysteresis; ‌Calculation of control quantity‌: The controller calculates the control signal based on the error between the predicted system output (without hysteresis) and the set point, thereby compensating for the system hysteresis in advance;‌ The data processing unit is used to process the data compensated by the data compensation unit, the data modeling unit is used to model and simulate the data processed by the data processing unit, the data prediction unit predicts the wellbore according to the processing result of the data processing unit, the data storage unit is used to store the data of the digital twin system operation, the data visualization unit is used to visualize the data of the digital twin system operation, the operation classification unit is used to provide operation computing power for the data compensation unit, the data processing unit, the data modeling unit and the data prediction unit, the data processing unit analyzes and processes the data acquired by the data acquisition unit through four methods: data preprocessing, data cleaning, data fusion and data analysis, the modeling unit constructs a three-dimensional simulation model of the wellbore through modeling and simulation software, the prediction unit is constructed based on deep learning technology, and the prediction unit predicts based on the simulation of the data modeling unit, the data storage unit selects two types of cloud database and storage server, the data visualization unit uses one or more types of desktop computers, laptop computers and industrial tablets, the operation classification unit is established based on virtual computing technology, and the operation classification unit is opened according to the amount of memory occupied by the digital twin system; It should be noted that data preprocessing is the process of converting raw data into a format and structure suitable for further processing. A common data preprocessing method is data standardization, such as: X'=(X-min(X)) / (max(X)-min(X)) Among them, X' is the standardized data, X is the original data, min(X) and max(X) are the minimum and maximum values ​​of the data respectively; Data cleaning is the process of removing or correcting errors, noise, and outliers in data. There are many methods for data cleaning, such as missing value processing, outlier detection, etc. Data fusion is the process of integrating data from different sources to provide consistent, accurate and useful data. Data fusion methods include data alignment, data fusion, data resampling, etc. Data analysis is the process of extracting valuable information and knowledge from data. Data analysis methods include descriptive analysis, predictive analysis, normative analysis, etc. The data modeling unit will use GIS technology, remote sensing technology, big data technology, machine learning technology, etc. to build a multi-scale three-dimensional model.

[0022] Working principle: When applying the digital twin system, the prepared sensor module, camera module and node module can be arranged first. Then, during drilling, the sensor module will detect the data inside the wellbore, and the camera module will monitor the process of wellbore construction. At the same time, through the main node submodule, the data detected by the sensor module and the camera module will be transmitted to the data compensation unit. The process detection submodule will detect the entry and exit of the main node submodule. When a failure of the main node submodule is detected, the secondary node submodule will be switched to transmit data. At the same time, the data compression submodule compresses the data through data compression technology; then the temporary storage submodule in the data compensation unit will temporarily store the data, and the verification submodule will verify the temporary storage submodule. The data temporarily stored in the block is verified to avoid erroneous data being transmitted to the data modeling unit. At the same time, the compensation submodule uses the Smith estimated compensation control algorithm to compensate the data temporarily stored in the temporary storage submodule. The initially processed data will be transmitted to the data processing unit. The data processing unit analyzes and processes the data obtained by the data acquisition unit through four methods: data preprocessing, data cleaning, data fusion, and data analysis to ensure the integrity of the data. Then the modeling unit constructs a three-dimensional simulation model of the wellbore through modeling simulation software. The prediction unit makes predictions based on the simulation of the data modeling unit. According to the prediction results, workers can rectify drilling matters in time to avoid major accidents during drilling.

[0023] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. A wellbore digital twin system based on simulation technology, comprising a data acquisition unit, a data processing unit, a data compensation unit, a data modeling unit, a data prediction unit, an operation classification unit, a data storage unit, and a data visualization unit, characterized in that: The data acquisition unit is used to acquire wellbore data; The data compensation unit is used to perform verification and compensation processing on the data acquired by the data acquisition unit; The data processing unit is used to process the data compensated by the data compensation unit; The data modeling unit is used to perform modeling simulation on the data processed by the data processing unit; The data prediction unit predicts the wellbore according to the result processed by the data processing unit; The data storage unit is used to store data running on the digital twin system; The data visualization unit is used to visualize the data running on the digital twin system; The operation classification unit is used to provide operation computing power for the data compensation unit, the data processing unit, the data modeling unit and the data prediction unit.

2. A wellbore digital twin system based on simulation technology according to claim 1, characterized in that: The wellbore data acquired by the data acquisition unit includes wellbore structure data, drill string data, in-well fluid data, wellbore trajectory data, and wellbore geological data. The data acquisition unit includes a sensor module, a camera module, and a node module. The sensor module, camera module, and node module are divided into multiple groups, and each group of sensor modules, camera modules, and node modules are arranged in the same wellbore.

3. A wellbore digital twin system based on simulation technology according to claim 2, characterized in that: The sensor module is arranged on the drilling equipment to collect various parameters in the drilling process in real time, and the camera module is used to monitor the process of wellbore construction.

4. A wellbore digital twin system based on simulation technology according to claim 2, characterized in that: The node module includes a main node submodule, a secondary node submodule, a detection submodule, and a data compression submodule. The main node submodule and the secondary node submodule are both sensor module communication interfaces. The detection submodule is established based on the PhiAccrualFailure algorithm. The detection submodule is used to detect the operating status of the main node submodule or the secondary node submodule.

5. A wellbore digital twin system based on simulation technology according to claim 4, characterized in that: The data compression submodule determines whether to compress the data by calculating the compression comparison formula, and the compression comparison formula is as follows: Among them, S is the compression comparison formula ratio, A is the size of the data to be transmitted, and B is the network rate. If S≤1, the data compression submodule will not compress the data through the data compression technology. If S>1, the data compression submodule will compress the data through the data compression technology.

6. A wellbore digital twin system based on simulation technology according to claim 1, characterized in that: The data compensation unit includes a temporary storage submodule, a verification submodule and a compensation submodule. The temporary storage submodule selects a cloud cache database and is used to temporarily store the data acquired by the data acquisition unit.

7. A wellbore digital twin system based on simulation technology according to claim 6, characterized in that: During verification, the verification submodule will compare and verify the data temporarily stored in the temporary storage submodule with the previously stored wellbore data, and a similarity comparison formula is selected during verification. The similarity comparison formula is as follows: in, Represents two sets of data, , is the similarity between two sets of data. The larger the value, the more similar the two sets of data are. 0≤ ≤1, is the variance between the two corresponding data in the two sets of data, is the data in the first set of data, For the second set of data Corresponding data, d is the number of data in the two groups of data, is the sum of products of similar data, is the base of the natural logarithm of the two sets of data; The compensation submodule uses the Smith predictive compensation control algorithm to compensate the data temporarily stored in the temporary storage submodule.

8. The wellbore digital twin system based on simulation technology according to claim 1, characterized in that: The data processing unit analyzes and processes the data acquired by the data acquisition unit through four methods: data preprocessing, data cleaning, data fusion, and data analysis. The modeling unit constructs a three-dimensional simulation model of the wellbore through modeling simulation software. The prediction unit is constructed based on deep learning technology, and the prediction unit makes predictions based on simulation of the data modeling unit.

9. The wellbore digital twin system based on simulation technology according to claim 1, characterized in that: The data storage unit uses a cloud database and a storage server, and the data visualization unit uses one or more of a desktop computer, a laptop computer, and an industrial tablet.

10. A wellbore digital twin system based on simulation technology according to claim 1, characterized in that: The computing hierarchical unit is established based on virtual computing technology, and the computing hierarchical unit is enabled according to the amount of memory occupied by the digital twin system.

Images