Power system of oilfield automatic workover rig and method for operating power system

Abstract

The application discloses an oil field automatic workover rig power system and a power system operation method, relates to the power operation technical field of the oil field automatic workover rig, and specifically comprises the following steps: real-time acquisition of fluctuation characteristic information of the workover rig when the workover rig encounters a pipe sticking area during pipe lifting, analysis after acquisition, generation of friction increase amplitude coefficients and vibration propagation indexes respectively; construction of a load fluctuation influence evaluation model for the generated friction increase amplitude coefficients and vibration propagation indexes, generation of fluctuation influence evaluation coefficients, analysis after generation, evaluation of the influence degree of local vibration of the pipe sticking area on load fluctuation, and division of fluctuation conditions into low fluctuation conditions, medium fluctuation conditions and high fluctuation conditions according to the evaluation results. The application solves the lag response problem of the workover rig when load fluctuation suddenly increases in the pipe sticking area, significantly improves the stability and safety of workover operation through real-time monitoring and dynamic adjustment.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power operation of automatic workover rigs in oilfields, and particularly relates to a power system of an automatic workover rig in an oilfield and a power system operation method. BACKGROUND

[0002] An automatic workover rig in an oilfield is a high-efficiency mechanical device used in oilfield operations, mainly used for repairing, maintaining and optimizing the working state of oil wells. Its automatic characteristics can significantly reduce manual intervention and improve the efficiency and safety of workover operations. During workover, the workover rig needs to drive multiple key components through a power operation system to complete complex tasks such as pulling and lowering well pipes, lifting and rotating equipment, etc. As the core of the workover rig, the power operation system usually includes a power source, a transmission mechanism and a control system, and its main function is to provide stable, continuous and efficient power support for workover operations. However, due to the complex and variable environment of oilfields and the diversified requirements of workover tasks, the traditional power system often has problems such as high energy consumption, low efficiency and difficulty in adapting to dynamic load changes, which not only increases the operation cost, but also may cause equipment failure and downtime risks. Therefore, developing the power system operation technology of the automatic workover rig in the oilfield, optimizing power distribution using intelligent algorithms, monitoring the running state of the equipment in real time, and realizing the coordinated operation of the power system and the workover process can not only significantly improve the workover efficiency and equipment reliability, but also reduce energy consumption and maintenance costs, meeting the needs of modern oilfield operations for high efficiency, safety and sustainable development.

[0003] The existing power system operation technology of the automatic workover rig in the oilfield realizes the power support for workover operations through the cooperation of the power source, the transmission mechanism and the controller. Usually, the power system first provides stable mechanical energy by the power source (such as internal combustion engine or electric motor), and then transmits the power to each working unit of the workover rig, such as lifting device, rotating device and grabbing device, through the transmission mechanism (such as gear box, hydraulic system or electrical transmission system). During operation, the system collects key parameters such as equipment speed, load, pressure and temperature using sensors, and analyzes them in real time through the controller to adjust the size and distribution of power output. For example, when the workover rig performs the task of pulling the pipe column or lowering the well pipe, the power system adjusts the output power according to the real-time load change to ensure the stability and continuity of the operation. In addition, some systems are also equipped with basic safety monitoring functions, such as issuing an alarm signal when the equipment operating parameters exceed the set threshold, prompting the operator to take measures to ensure the safe operation of the equipment. Through the above cooperation, the existing power system can provide reliable power support for workover operations and realize the coordinated operation between multiple equipment units.

[0004] The existing technology has the following shortcomings:

[0005] In the workover operation, when the workover machine lifts the tubing, especially when the tubing is stuck, the friction between the tubing and the well wall increases sharply, resulting in a sudden increase in load in a very short time. This load fluctuation is mainly due to the sharp increase in local friction near the stuck tubing area, especially when the well wall is loose or the material (such as mud, stones) in the well enters the lifting process, the load fluctuation amplitude is large and changes quickly. The existing automatic workover machine power system can only detect the change of load through the load sensor, but it cannot accurately identify the load fluctuation characteristics caused by the change of local friction in the stuck tubing area, especially when the well wall near the stuck tubing position vibrates slightly, resulting in feedback lag of the system. The control method of the prior art cannot accurately respond to the load fluctuation in an instant, often causing the system to respond lag or over-response, thereby causing the motor power to be unstable, and even causing the motor to be overloaded or the operation to be interrupted, affecting the stability of the workover operation, increasing the risk of equipment failure and maintenance cost.

[0006] The above information disclosed in the background section is only used to strengthen the understanding of the background of the present disclosure, and therefore it can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0007] The purpose of the present application is to provide a power system of an automatic workover machine in an oilfield and a power system operation method to solve the problems in the background.

[0008] In order to achieve the above-mentioned purpose, the present application provides the following technical solution: a power system operation method of an automatic workover machine in an oilfield, specifically comprising the following steps:

[0009] In the process of lifting the tubing by the workover machine, it is monitored in real time whether there is a stuck tubing area, whether the stuck tubing phenomenon occurs is judged by monitoring the load change, in the case of confirming that the stuck tubing area is encountered, it is further detected whether the load is suddenly increased, and in the case of sudden load increase, the load fluctuation monitoring and adjustment process is triggered;

[0010] The fluctuation characteristic information of the workover machine when lifting the tubing and encountering the stuck tubing area is acquired in real time, and after acquisition, it is analyzed to generate a friction increase amplitude coefficient and a vibration propagation index, respectively;

[0011] Specifically comprising the following steps:

[0012] The fluctuation characteristic information of the workover machine when lifting the tubing and encountering the stuck tubing area is acquired in real time, and after acquisition, it is preprocessed;

[0013] The load fluctuation information and vibration propagation characteristic information in the preprocessed fluctuation characteristic information are extracted;

[0014] The extracted load fluctuation information and vibration propagation characteristic information are analyzed to generate a friction increase amplitude coefficient and a vibration propagation index, respectively;

[0015] A load fluctuation impact assessment model was constructed based on the generated friction force amplification coefficient and vibration propagation index. A fluctuation impact assessment coefficient was generated and analyzed after generation to assess the degree of impact of local vibration in the pipe clamping area on load fluctuation. Based on the assessment results, the fluctuation situation was divided into low fluctuation, medium fluctuation and high fluctuation.

[0016] Based on the classification results, corresponding adjustment measures were taken for workover rigs under low, medium, and high volatility conditions, respectively.

[0017] Continuously monitor load fluctuations, vibration data, and well workover rig operating status information, and dynamically adjust the load fluctuation impact assessment model and adjustment measures based on real-time monitoring results. At the same time, store and analyze historical monitoring data to optimize model parameters and adjustment strategies.

[0018] Preferably, the logic for obtaining the friction force amplification coefficient is as follows:

[0019] Load fluctuation information is extracted from the preprocessed fluctuation feature information. Specifically, this includes the load value at different times within a certain period when the workover rig encounters a stuck area while pulling up the tubing, the pressure change in the contact area between the tubing and the well wall, the tubing pull-out speed, and the viscosity of the downhole fluid, and these are denoted as FZ. m ΔPC m VP m and ND m FZ m ΔPC represents the load value at time m within a certain period when the workover rig encounters a stuck pipe area during pipe lifting. m VP represents the pressure change at time m in the contact area between the tubing and the wellbore during a certain period when the workover rig encounters a stuck area while pulling out the tubing. m ND represents the lifting speed of the tubing at time m within a certain period when the workover rig encounters a stuck area during tubing lifting. m This represents the viscosity of the downhole fluid at time m during a certain period when the workover rig encounters a stuck area while pulling out the well casing, where m = 1, 2, 3, ..., g, and g is a positive integer;

[0020] The load value FZ at different times within a certain period of time when the workover rig encounters a stuck area while pulling out the well casing. m Construct a set, and label the maximum and minimum values ​​within the set as FZ respectively. max and FZ min ;

[0021] The specific formula for calculating the friction force amplification factor is as follows:

[0022] ,

[0023] Wherein, FAC is the friction force amplification coefficient.

[0024] Preferably, the vibration propagation index is obtained as follows:

[0025] The vibration propagation characteristic information in the pre-processed fluctuation characteristic information is extracted, specifically including the vibration amplitude of the stuck pipe region at different time points within a period of time when the workover rig lifts the well pipe to the stuck pipe region, the pressure change amount of the contact region between the oil pipe and the well wall, the density of the downhole fluid, and the stiffness and length of the oil pipe, and are respectively marked as AV n , ΔPC n , ρF n , EP and LP, AV n represents the vibration amplitude of the stuck pipe region at time n within a period of time when the workover rig lifts the well pipe to the stuck pipe region, ΔPC n represents the pressure change amount of the contact region between the oil pipe and the well wall at time n within a period of time when the workover rig lifts the well pipe to the stuck pipe region, ρF n represents the density of the downhole fluid at time n within a period of time when the workover rig lifts the well pipe to the stuck pipe region, EP represents the stiffness of the oil pipe, and LP represents the length of the oil pipe, n = 1, 2, 3, …, k, k is a positive integer;

[0026] The vibration propagation index is calculated, and the specific calculation formula is as follows:

[0027] ,

[0028] Wherein, VPR is the vibration propagation index.

[0029] Preferably, the generated friction force amplification coefficient and vibration propagation index are used to construct a load fluctuation influence evaluation model to generate a fluctuation influence evaluation coefficient, specifically including the following steps:

[0030] Collect several friction force amplification coefficients, vibration propagation indexes and corresponding fluctuation influence evaluation coefficients generated in the past period of time, and mark them as FAC x , VPR x and IEC x respectively, x represents the number of several friction force amplification coefficients, vibration propagation indexes and corresponding fluctuation influence evaluation coefficients generated in the past period of time, x = 3, 4, 5, …, d, d is a positive integer, and the collected data in the past period of time form a historical data set;

[0031] Select a multiple regression model as the load fluctuation influence evaluation model, and train it through the historical data set to determine the value of the regression coefficient, according to the formula:

[0032] ,

[0033] In the formula, β0, β1 and β2 are regression coefficients;

[0034] The regression coefficients are optimized by minimizing the error between the predicted value and the actual value, and the values of the regression coefficients β0, β1 and β2 are finally determined;

[0035] Using the finally determined regression coefficients, the load fluctuation influence evaluation model constructed is input with the real-time generated friction force amplification coefficient FAC and vibration propagation index VPR, and the real-time generated fluctuation influence evaluation coefficient IEC is generated.

[0036] Preferably, the generated fluctuation influence evaluation coefficient IEC is compared with the pre-set fluctuation influence evaluation coefficient threshold interval [IEC min , IEC max ], the influence degree of the local vibration of the card tube area on the load fluctuation is evaluated according to the comparison result, and the fluctuation condition is divided into low fluctuation condition, medium fluctuation condition and high fluctuation condition according to the evaluation result, and the specific comparison analysis and division are as follows:

[0037] If IEC < IEC min , the influence degree of the local vibration of the card tube area on the load fluctuation is low, and the fluctuation condition under this influence degree is divided into low fluctuation condition;

[0038] If IEC min ≤IEC≤IEC max , the influence degree of the local vibration of the card tube area on the load fluctuation is medium, and the fluctuation condition under this influence degree is divided into medium fluctuation condition;

[0039] If IEC > IEC max , the influence degree of the local vibration of the card tube area on the load fluctuation is high, and the fluctuation condition under this influence degree is divided into high fluctuation condition.

[0040] Preferably, according to the division result, corresponding adjustment measures are taken for the workover rig under the low fluctuation condition, the medium fluctuation condition and the high fluctuation condition, specifically:

[0041] If the division result is low fluctuation condition, the adjustment measure taken is to maintain the existing operation parameters, continue to monitor the load fluctuation condition, and regularly check the equipment operation state to ensure stability;

[0042] If the division result is medium fluctuation condition, the adjustment measure taken is to adjust the lifting speed and power output of the workover rig to reduce the load fluctuation, optimize the equipment operation condition, and increase the load fluctuation monitoring frequency to ensure operation safety;

[0043] If the classification result indicates high fluctuations, the adjustment measures to be taken are: immediately reduce the lifting speed and optimize system power control, implement strict vibration monitoring, and conduct equipment inspection and maintenance to ensure the stability and safety of the workover rig.

[0044] Preferably, the power system of the oilfield automatic workover rig includes a pipe jamming detection and load monitoring module, a fluctuation characteristic acquisition and analysis module, a fluctuation assessment model construction module, a fluctuation classification and adjustment module, and a real-time monitoring and system optimization module;

[0045] The pipe jamming detection and load monitoring module monitors in real time whether there is a pipe jamming area during the well workover rig's pipe pulling process. It determines whether a pipe jamming phenomenon has occurred by monitoring load changes. If a pipe jamming area is confirmed, it further detects whether the load suddenly increases. If the load suddenly increases, it triggers the load fluctuation monitoring and adjustment process.

[0046] The fluctuation feature acquisition and analysis module acquires the fluctuation feature information of the workover rig when it encounters a stuck area while pulling out the well casing in real time, and analyzes the acquired information to generate the friction amplification coefficient and vibration propagation index, respectively.

[0047] The fluctuation assessment model construction module constructs a load fluctuation impact assessment model based on the generated friction amplification coefficient and vibration propagation index, generates fluctuation impact assessment coefficients, and analyzes them after generation to assess the degree of impact of local vibration in the pipe clamping area on load fluctuations. Based on the assessment results, the fluctuation situation is divided into low fluctuation, medium fluctuation and high fluctuation situations.

[0048] The fluctuation classification and adjustment module takes corresponding adjustment measures for workover rigs under low fluctuation, medium fluctuation and high fluctuation conditions according to the classification results;

[0049] The real-time monitoring and system optimization module continuously monitors load fluctuations, vibration data, and the operating status information of the workover rig. Based on the real-time monitoring results, it dynamically adjusts the load fluctuation impact assessment model and adjustment measures. At the same time, it stores and analyzes historical monitoring data to optimize model parameters and adjustment strategies.

[0050] The beneficial effects of this invention are:

[0051] 1. This invention effectively identifies load fluctuations and their changes by real-time monitoring of whether the workover rig encounters a stuck area during tubing extraction and dynamically detecting load changes, especially under conditions of a sharp increase in local friction. Traditional oilfield automatic workover rig power systems rely solely on load sensors to detect load changes, failing to accurately identify load fluctuation characteristics caused by changes in local friction in the stuck area. Furthermore, the system response is often delayed or excessive during sudden load increases, leading to unstable motor power or work interruption. This invention, however, integrates multiple data sources such as load and vibration, and through precise model calculations and adjustment strategies, enables the system to respond quickly to load fluctuations, preventing motor overload or system instability, thus significantly improving the stability and safety of workover operations.

[0052] 2. This invention constructs a load fluctuation impact assessment model and generates fluctuation impact assessment coefficients in real time, enabling the system to more accurately assess the degree of impact of local vibration in the stuck pipe area on load fluctuations. Based on this assessment result, the system can classify fluctuation conditions into three states: low fluctuation, medium fluctuation, and high fluctuation, and take corresponding adjustment measures for each. For example, in the case of low fluctuation, the system maintains existing operating parameters to avoid unnecessary intervention; in the case of medium fluctuation, it automatically optimizes the lifting speed and power output of the workover rig; and in the case of high fluctuation, the system immediately takes strict control measures to ensure operational safety. This flexible adjustment strategy not only improves operational stability but also reduces damage to equipment and extends equipment lifespan.

[0053] 3. This invention also continuously optimizes the load fluctuation impact assessment model and adjustment strategy through historical data storage and analysis, improving the system's adaptability and long-term stability. The software system is trained based on historical data, optimizing regression coefficients by minimizing errors, thereby improving the accuracy of the fluctuation impact assessment coefficients. As well workover operations continue, the system can dynamically adjust parameters according to different operating environments, downhole conditions, and equipment status, ensuring efficient and stable operation even in complex and changing environments. This data-driven optimization method not only enhances the system's adaptability but also makes the entire well workover process more intelligent and automated, reducing manual intervention, lowering maintenance costs, and improving operational safety and efficiency. Attached Figure Description

[0054] Figure 1 This is a flowchart illustrating the operation method of the power system of the automatic well repair rig in the oilfield according to the present invention.

[0055] Figure 2 This is a schematic diagram of the power system of the automatic well repair machine for oil fields according to the present invention. Detailed Implementation

[0056] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, they are provided so that the description of this disclosure will be more complete and fully convey the concept of the exemplary embodiments to those skilled in the art.

[0057] This invention provides, for example Figure 1 The operating method of the power system of the oilfield automatic workover rig shown includes the following steps:

[0058] During the process of the workover rig pulling out the tubing, the presence of a stuck area is monitored in real time. The presence of a stuck area is determined by monitoring load changes. If a stuck area is confirmed, the load is further checked for a sudden increase. If the load increases suddenly, the load fluctuation monitoring and adjustment process is triggered.

[0059] During the tubing retraction process by a workover rig, real-time monitoring of load changes can help determine if tubing jamming has occurred. The workover rig's load sensor continuously collects load data during the retraction process. Through real-time analysis of load changes, the system can detect sudden load fluctuations. When the load change reaches a set threshold, the system identifies a potential jamming area. Specifically, by calculating and comparing the rate of load change, if the load increase exceeds the normal range within a short period, it can be inferred that the tubing may have come into contact with the jamming area. Simultaneously, vibration sensors also monitor minute vibrations of the wellbore, which typically change drastically in the jamming area, further enhancing the detection of a jamming phenomenon.

[0060] After confirming the encounter with a bottleneck area, the system needs to further detect any sudden load increases. This process can be achieved through the calculation of a dynamic load surge coefficient. The system will acquire current load data in real time and compare it with load values ​​over a past period. If the load increases significantly within a very short period and the fluctuation is abnormal, the system will identify it as a load surge. At this point, using time series analysis and abrupt change detection algorithms, the system can accurately identify the magnitude and trend of the load surge. This information is crucial for subsequent adjustments, providing a basis for taking appropriate regulatory measures.

[0061] By monitoring load changes and detecting sudden increases in real time, the system can promptly identify stuck pipe areas and the severity of load fluctuations, thus preventing system response lag or over-response when the workover rig encounters stuck pipe areas. This method helps the system respond quickly and accurately to sudden load increases, preventing motor power instability or operation interruption, thereby ensuring the stability and safety of workover operations, reducing the risk of equipment failure, and lowering maintenance costs. Through software algorithm optimization, the system can respond rapidly when stuck pipe areas appear, ensuring that the workover rig maintains efficient and stable operation during the operation.

[0062] Real-time acquisition and analysis of fluctuation characteristics when the workover rig encounters a stuck area during casing extraction are performed, generating friction amplification coefficient and vibration propagation index, specifically including the following steps:

[0063] Real-time acquisition of fluctuation characteristics when the workover rig encounters a stuck area while pulling up the well casing, and preprocessing of the acquired information;

[0064] When acquiring real-time fluctuation characteristics of the workover rig when encountering a stuck tubing area during tubing extraction, the rig's operating status can be monitored in real time using load sensors and vibration sensors. Load sensors acquire real-time load change data during tubing extraction, especially when encountering a stuck area, where the friction between the tubing and the wellbore changes drastically, causing sudden increases or violent fluctuations in load data. Vibration sensors monitor wellbore vibration caused by increased local friction, capturing abnormal changes in vibration amplitude and frequency. In addition to load and vibration data, downhole environmental sensors can acquire information on potential factors influencing load fluctuations, such as wellbore stability and well materials (e.g., mud, rocks). These sensors can connect to the workover rig's control system via a wireless network, transmitting data in real-time to the software system for analysis. The software system integrates data streams from multiple sensors, processes them synchronously, and marks potential stuck areas and moments of sudden load increases.

[0065] The purpose of preprocessing is to ensure the accuracy and usability of the data. During well workover operations, the acquired load and vibration data may be affected by noise, interference, and sensor errors; therefore, the raw data must be cleaned and filtered. First, a low-pass filter is used to remove high-frequency noise, which is typically related to external interference and sensor errors. Next, load fluctuation data is processed using smoothing algorithms (such as moving averages) to remove sudden, instantaneous fluctuations while retaining long-term trends and changes. Vibration data also needs to have high-frequency components unrelated to friction removed to ensure that the main characteristics of vibration fluctuations are accurately captured. Furthermore, data time synchronization is crucial; it is necessary to ensure that the timestamps of all sensor data are aligned and to handle differences in data acquisition times from different sensors using interpolation. Through these preprocessing steps, the fluctuation characteristic information acquired by the workover rig can more accurately reflect the load changes and vibration characteristics of the stuck pipe area, providing reliable input data for subsequent analysis and evaluation.

[0066] Extract load fluctuation information and vibration propagation characteristic information from the preprocessed fluctuation feature information;

[0067] When extracting load fluctuation and vibration propagation characteristics from the preprocessed fluctuation feature information, feature extraction is first required on the preprocessed data. For load fluctuation information, this can be extracted by analyzing the amplitude changes and frequency characteristics of the load data. Specifically, peak detection algorithms are used to identify sudden fluctuations in the load data, which are usually related to a sharp increase in friction in the jammed area. Furthermore, methods such as Fourier transform or wavelet transform can be used to perform frequency domain analysis on the load data to extract high-frequency components in the load fluctuations. These frequency components typically indicate rapid fluctuations and changes in friction in the jammed area. For vibration propagation characteristics, this can be analyzed by extracting the vibration amplitude and frequency spectrum from the vibration data. Fast Fourier Transform (FFT) is used to perform frequency domain transformation on the vibration signal to extract the frequency distribution of the vibration and analyze the propagation characteristics, especially the different propagation modes of low-frequency and high-frequency vibrations in the jammed area. Further, the propagation speed and directionality of the vibration can be analyzed by calculating the phase difference of the vibration signal. These methods, implemented in software, can help accurately extract key information on load fluctuations and vibration propagation, thus providing data support for subsequent analysis and evaluation.

[0068] The extracted load fluctuation information and vibration propagation characteristic information are analyzed to generate the friction force amplification coefficient and vibration propagation index, respectively.

[0069] In this embodiment, the logic for obtaining the friction force amplification coefficient is as follows:

[0070] Load fluctuation information is extracted from the preprocessed fluctuation feature information. Specifically, this includes the load value at different times within a certain period when the workover rig encounters a stuck area while pulling up the tubing, the pressure change in the contact area between the tubing and the well wall, the tubing pull-out speed, and the viscosity of the downhole fluid, and these are denoted as FZ. m ΔPC m VP m and ND m FZ m ΔPC represents the load value at time m within a certain period when the workover rig encounters a stuck pipe area during pipe lifting. m VP represents the pressure change at time m in the contact area between the tubing and the wellbore during a certain period when the workover rig encounters a stuck area while pulling out the tubing. m ND represents the lifting speed of the tubing at time m within a certain period when the workover rig encounters a stuck area during tubing lifting. m This represents the viscosity of the downhole fluid at time m during a certain period when the workover rig encounters a stuck area while pulling out the well casing, where m = 1, 2, 3, ..., g, and g is a positive integer;

[0071] When a workover rig encounters a stuck tubing area while pulling out the tubing, the load value at different times over a period of time, the pressure change in the tubing-wellbore contact area, the pull-out speed, and the viscosity of the downhole fluid can be acquired in real time using various sensors. The load value is obtained through load sensors installed in the workover rig's power system. These sensors monitor load changes during the pull-out process in real time and transmit the data to the control system. The pressure change in the tubing-wellbore contact area is obtained through pressure sensors, typically installed on the tubing surface or near the wellbore, to monitor pressure changes in the contact area in real time, especially pressure fluctuations when friction increases dramatically in the stuck area. The pull-out speed is measured by speed sensors. The workover rig's speed sensor monitors the tubing pull-out speed and feeds the data back to the control system. The software can then calculate the speed changes during the pull-out process using this data. The viscosity of the downhole fluid is detected by fluid viscosity sensors. These sensors monitor the characteristics of the downhole fluid; changes in fluid viscosity can affect friction, especially in the stuck area, where the fluid viscosity fluctuates with changes in local friction. The control system can perform comprehensive analysis of the data collected in real time by these sensors, providing necessary parameters for subsequent operational adjustments.

[0072] The load value FZ at different times within a certain period of time when the workover rig encounters a stuck area while pulling out the well casing. m Construct a set, and label the maximum and minimum values ​​within the set as FZ respectively. max and FZ min ;

[0073] The specific formula for calculating the friction force amplification factor is as follows:

[0074] ,

[0075] In the formula, FAC is the friction force amplification coefficient.

[0076] The formula for calculating the friction amplification factor (FAC) reflects the impact of friction in the tube clamping area on load fluctuations through a comprehensive evaluation of multiple physical parameters. Firstly, in the formula (FZ... max -FZ min This represents the amplitude of load fluctuation, specifically the maximum range of load change that occurs when the workover rig pulls out the tubing, especially in the stuck area, due to the sharp increase in friction. This item reflects the severity of load fluctuations caused by the stuck tubing phenomenon. Next, the viscosity ND of the downhole fluid... m The resistance characteristics of the fluid are considered by multiplying it with the load fluctuation, because changes in fluid viscosity affect the friction between the tubing and the wellbore, thus affecting the intensity of the load fluctuation. The pressure change ΔPC in the tubing-wellbore contact area is also considered. m This reflects the change in local pressure in the contact area when friction increases, which is directly related to the increase in friction and the intensity of load fluctuations. Lifting speed VP m As an operating parameter of the workover rig, it affects the propagation speed of increased friction, which in turn affects the frequency and amplitude of load fluctuations. Ultimately, the formula combines these factors through weighted summation and averaging to derive the friction amplification coefficient. This calculation method ensures accurate assessment of the degree of load fluctuation when considering different physical factors in the stuck pipe area (such as friction, fluid characteristics, and operating speed), and provides a reasonable basis for subsequent dynamic adjustments.

[0077] The magnitude of the friction amplification coefficient is directly related to the extent to which local vibration in the stuck pipe area affects load fluctuations. A larger friction amplification coefficient indicates a sharp increase in local friction in the stuck pipe area, leading to a corresponding increase in load fluctuation amplitude. In this case, the friction in the stuck pipe area not only directly affects the sudden increase in load but also intensifies local vibrations of the wellbore, especially when friction increases significantly, the vibration propagation effect becomes more pronounced. Vibration, through its influence on the wellbore and tubing, exacerbates the severity of load fluctuations, making them more unstable and consequently affecting the operational stability of the workover rig. Therefore, an increase in the friction amplification coefficient usually indicates that the impact of vibration on load fluctuations is also intensifying, vibration propagation is more severe, and the amplitude and frequency of load fluctuations increase accordingly. The magnitude of the friction amplification coefficient can be used to indirectly assess the impact of vibration in the stuck pipe area on load fluctuations, providing an accurate basis for system adjustment.

[0078] In this embodiment, the logic for obtaining the vibration propagation index is as follows:

[0079] The vibration propagation characteristics information is extracted from the preprocessed wave feature information. Specifically, this includes the vibration amplitude of the stuck area at different times over a period of time when the workover rig encounters the stuck area during tubing extraction, the pressure change in the contact area between the tubing and the well wall, the density of the downhole fluid, and the stiffness and length of the tubing. These are then calibrated as AV. n ΔPC n ,ρF n EP and LP, AV n ΔPC represents the vibration amplitude of the stuck area at time n within a certain period when the workover rig encounters the stuck area during well casing extraction. n ρF represents the pressure change at time n in the contact area between the tubing and the wellbore during a certain period when the workover rig encounters a stuck area while retrieving the tubing. n EP represents the density of the downhole fluid at time n during a certain period when the workover rig encounters a stuck area while pulling out the tubing. LP represents the stiffness of the tubing and the length of the tubing. n = 1, 2, 3, ..., k, where k is a positive integer.

[0080] During the wellbore rig's tubing retrieval process, when encountering a stuck area, a series of sensors and measuring devices can be used for real-time monitoring to obtain quantitative data such as vibration amplitude, pressure changes in the tubing-wellbore contact area, downhole fluid density, and tubing stiffness and length. First, vibration amplitude can be acquired in real-time using vibration sensors mounted on the rig. These sensors, typically installed on the tubing surface or rig structure, detect vibration fluctuations caused by a sharp increase in friction. The vibration sensors continuously measure the frequency and amplitude of the vibration and transmit this data to the control system in real-time. The software analyzes this data, extracting vibration amplitude information, especially important in the stuck area where amplitude often changes drastically. Next, pressure changes in the tubing-wellbore contact area can be acquired using pressure sensors installed in the contact area to monitor changes in contact pressure as local friction increases. The pressure sensors transmit pressure data to the control system, where the software analyzes this data and calculates the pressure changes to track the impact of friction on the system. The density of downhole fluids can be monitored using fluid density sensors installed downhole. These sensors measure the density of the well fluid in real time, and changes in density reflect the resistance characteristics of the downhole fluid, especially in areas where fluid properties may fluctuate due to stuck tubing. The software system integrates density data with data from other sensors to provide information on dynamic changes. As for the stiffness and length of the tubing, stiffness can be obtained using strain sensors installed on the tubing surface. These sensors monitor the strain caused by increased friction during tubing pull-out, thus calculating the tubing stiffness. The tubing length is a fixed parameter, set before the workover operation, and can be retrieved using known parameters in the software. Through real-time data acquisition from these sensors and software analysis, the system can dynamically assess the impact of increased friction on load fluctuations and operational safety during workover operations.

[0081] The specific formula for calculating the vibration propagation index is as follows:

[0082] ,

[0083] In the formula, VPR is the vibration propagation index.

[0084] The vibration propagation index calculation formula, by combining multiple key parameters, quantitatively assesses the impact of vibration in the stuck pipe area on load fluctuation propagation. First, the product of vibration amplitude and downhole fluid density in the formula reflects the intensity and propagation characteristics of the vibration wave. A larger vibration amplitude results in a more significant impact on load fluctuations. The pressure change in the contact area is directly related to friction; a larger pressure change leads to increased friction, further affecting vibration propagation. Next, the tubing stiffness is multiplied by the vibration amplitude and pressure change. Considering the effect of stiffness on vibration propagation, a stiffer tubing can more effectively transmit vibration, enhancing its impact on load fluctuations. Finally, the formula uses tubing length and fluid density as denominators, representing the attenuation effect and the effect of slower propagation speed, respectively. A longer tubing results in more attenuation during propagation, weakening the propagation effect; conversely, fluid density affects the vibration propagation rate; higher density leads to slower propagation speed, further weakening the propagation effect. Therefore, by weighted summation of these parameters, the vibration propagation index can comprehensively consider the propagation intensity, propagation speed, and the influence of friction on the propagation effect, providing an accurate assessment basis for load fluctuations caused by vibration during well workover operations.

[0085] The magnitude of the vibration propagation index is directly related to the degree of impact of local vibration in the stuck pipe area on load fluctuations. A larger vibration propagation index indicates stronger vibration intensity and propagation effect, and a more significant impact of local vibration in the stuck pipe area on load fluctuations. This is because the vibration propagation index considers multiple factors such as vibration amplitude, fluid density, tubing stiffness, tubing length, and contact pressure changes. The greater the vibration amplitude, the lower the fluid density, the higher the tubing stiffness, the shorter the tubing length, and the greater the contact pressure changes, the stronger the vibration propagation effect and the more severe the load fluctuations. A larger vibration propagation index means that the vibration wave propagates faster and with greater intensity in the stuck pipe area, leading to an increase in the amplitude and frequency of load fluctuations, making the workover rig operation more susceptible to interference. Therefore, an increase in the vibration propagation index leads to a greater impact of local vibration in the stuck pipe area on load fluctuations, thereby affecting the stability and safety of workover operations.

[0086] A load fluctuation impact assessment model was constructed based on the generated friction force amplification coefficient and vibration propagation index. A fluctuation impact assessment coefficient was generated and analyzed after generation to assess the degree of impact of local vibration in the pipe clamping area on load fluctuation. Based on the assessment results, the fluctuation situation was divided into low fluctuation, medium fluctuation and high fluctuation.

[0087] In this embodiment, a load fluctuation impact assessment model is constructed based on the generated friction force amplification coefficient and vibration propagation index, and a fluctuation impact assessment coefficient is generated. This specifically includes the following steps:

[0088] Several friction amplification coefficients, vibration propagation indices, and corresponding fluctuation impact assessment coefficients generated over a period of time were collected and labeled as FAC. x VPR x and IEC x x represents the number of several friction amplification coefficients, vibration propagation indices and corresponding fluctuation impact assessment coefficients generated in the past period, x=3, 4, 5, ..., d, where d is a positive integer, and the collected data in the past period are formed into a historical dataset;

[0089] To collect several friction amplification coefficients, vibration propagation indices, and corresponding fluctuation impact assessment coefficients generated over a period of time, real-time monitoring and storage can be achieved through the workover rig's data acquisition system. First, during workover operations, devices such as load sensors, vibration sensors, pressure sensors, fluid density sensors, and strain sensors continuously collect relevant friction amplification coefficient and vibration propagation index data. The sensors record data such as friction force, vibration amplitude, and pressure changes at each moment in real time, and this data is transmitted to the workover rig's central control system. The software system processes this real-time data through a data interface and calculates the corresponding friction amplification coefficient and vibration propagation index, storing it in a historical data database. During this process, the software system also calculates and updates the fluctuation impact assessment coefficient at each moment. This coefficient is derived from the real-time calculation of the friction amplification coefficient and vibration propagation index and stored along with the corresponding timestamp. During each operation, the system automatically records the friction amplification coefficient, vibration propagation index, and fluctuation impact assessment coefficient generated within each time period, forming a complete historical dataset. This data will be saved to the database through periodic storage or real-time data streaming for subsequent training and real-time calculation of multiple regression models. In this way, the system can effectively collect and manage these key data, providing a precise basis for subsequent analysis and optimization.

[0090] When the regression coefficients are unknown, the fluctuation impact assessment coefficients can be calculated using a preliminary estimation method. First, a preliminary predictive model is built based on previously collected historical or experimental data. This model does not rely on the precise values ​​of the regression coefficients but estimates the fluctuation impact assessment coefficients by performing a simple weighted calculation of the friction amplification coefficient and the vibration propagation index, or based on existing empirical data. At this point, the mean or other statistical characteristics (such as the median) of the friction amplification coefficient and vibration propagation index from historical data can be used to fill in the gaps in the regression coefficients. Based on these estimated values, a simplified model is used to generate preliminary fluctuation impact assessment coefficients. These preliminary estimated fluctuation impact assessment coefficients will be further optimized in subsequent model training; as the calculation of the regression coefficients becomes more accurate, the calculated assessment coefficients will gradually become more precise.

[0091] The fluctuation impact assessment coefficient can be collected in various ways, depending on the system's real-time monitoring and data acquisition capabilities. Firstly, during the workover rig's operation, sensors installed on the rig (such as load sensors, vibration sensors, and pressure sensors) can monitor the friction amplification coefficient and vibration propagation index in real time. These sensors continuously record various data points during operation, forming a data stream. For each moment, the friction amplification coefficient and vibration propagation index are stored in a database, creating a historical dataset. Then, the data processing module analyzes this real-time data, estimating the corresponding fluctuation impact assessment coefficient based on a pre-defined algorithm or simplified calculation method. This process can be accomplished through real-time data storage, analysis, calculation, and feedback mechanisms. In this way, the fluctuation impact assessment coefficient can be continuously collected as workover operations continue, providing reliable data support for subsequent model optimization. Historical data will be continuously accumulated through cloud storage or a local database, providing a foundation for subsequent training and evaluation of multiple regression models.

[0092] The value of x is limited to a positive integer greater than or equal to 3 because in regression analysis, at least three data points are needed to form a valid system of equations, allowing for the accurate calculation of the three regression coefficients. Specifically, the regression model contains three regression coefficients (β0, β1, and β2), where β0 is a constant term, and β1 and β2 represent the influence of the friction amplification coefficient and the vibration propagation index on the wave impact assessment coefficient, respectively. To accurately calculate these coefficients using multiple regression, at least three different sample data points (i.e., three different x values, corresponding to different values ​​of FAC and VPR) are needed to construct the system of equations. If the value of x is less than 3, sufficient equations cannot be generated to solve for the regression coefficients, making accurate calculation impossible. Therefore, the restriction of x ≥ 3 is necessary to ensure the accuracy and stability of the regression analysis results. Furthermore, as the number of data points increases, the robustness and accuracy of the regression analysis also improve, further ensuring the reliability of the regression coefficient calculation. Therefore, at least three data points are needed to form a complete system of equations to support the calculation of the regression coefficients.

[0093] A multiple regression model was selected as the model for assessing the impact of load fluctuations. The model was trained using historical datasets to determine the values ​​of the regression coefficients, based on the formula:

[0094] ,

[0095] In the formula, β0, β1, and β2 are regression coefficients;

[0096] Multiple regression is a statistical method used to analyze the relationship between multiple independent variables and a dependent variable. In a multiple regression model, the dependent variable (also called the explained variable) depends on two or more independent variables (explanatory variables). This model helps us understand how different factors work together on a target variable, and thus predict changes in the target variable. In load fluctuation impact assessment, a multiple regression model is chosen because the friction amplification coefficient and the vibration propagation index are key factors affecting the fluctuation impact assessment coefficient. By training the model with historical datasets, the specific degree of influence of each independent variable (friction amplification coefficient and vibration propagation index) on the target variable (fluctuation impact assessment coefficient) can be determined, thus providing accurate predictions for fluctuation assessment in actual operations. In a multiple regression model, the regression coefficients represent the strength of the influence of each independent variable on the dependent variable. Specifically, β0 is the intercept term, representing the baseline value of the fluctuation impact assessment coefficient when all independent variables are zero. β1 is the degree of influence of the friction amplification coefficient on the fluctuation impact assessment coefficient, representing the contribution of the change in the amplitude of load fluctuation to the overall fluctuation impact when friction increases. β2 is the degree of influence of the vibration propagation index on the fluctuation impact assessment coefficient, reflecting how the intensity of vibration propagation affects the propagation effect of load fluctuation. By training on historical datasets, the model can determine the values ​​of these three regression coefficients, thus providing a basis for generating real-time assessment coefficients of the impact of fluctuations.

[0097] By minimizing the error between the predicted and actual values, the regression coefficients are optimized, and the values ​​of the regression coefficients β0, β1, and β2 are finally determined.

[0098] Optimizing regression coefficients by minimizing the error between predicted and actual values ​​ensures that the regression model accurately reflects patterns in historical data, thereby providing precise predictions in practical applications. The optimization process for regression coefficients is based on the principle of error minimization, that is, adjusting the values ​​of the regression coefficients to minimize the difference (error) between the model-predicted fluctuation impact assessment coefficient and the actually observed fluctuation impact assessment coefficient. Specifically, this process is typically achieved using the least squares method, where the error is defined as the sum of the squares of the differences between the actual and predicted values ​​for each data point. Through iterative optimization, the regression coefficients are gradually adjusted until the minimum error value is reached, ensuring that the regression coefficients accurately reflect the influence of the friction amplification coefficient and the vibration propagation index on the fluctuation impact assessment coefficient. Using this method, the regression model can more accurately assess future load fluctuations, improving decision support capabilities during operation.

[0099] Using the finalized regression coefficients, the constructed load fluctuation impact assessment model is input with the real-time generated friction amplification coefficient FAC and vibration propagation index VPR to generate the fluctuation impact assessment coefficient IEC in real time.

[0100] In this embodiment, the generated fluctuation impact assessment coefficient IEC is compared with the pre-set fluctuation impact assessment coefficient threshold range [IEC]. min IEC max A comparison was conducted, and the impact of local vibration in the pipe clamping area on load fluctuations was assessed based on the comparison results. The fluctuations were then categorized into low, medium, and high fluctuations based on the assessment results. The specific comparison analysis and categorization are as follows:

[0101] If IEC < IEC min The impact of local vibration in the pipe clamping area on load fluctuation is considered to be of low impact level, and fluctuations under this impact level are classified as low fluctuations.

[0102] In this situation, although pipe jamming may occur during the well workover rig's extraction process, the impact of increased friction on load fluctuations is limited due to the relatively low intensity of vibration. At this time, the load change in the workover system is not drastic, and the equipment stability is high, typically requiring no excessive adjustments. The system can maintain its normal operating state in this case, without frequent intervention, reducing operational complexity and maintenance costs. However, despite the minor impact, monitoring is still necessary to prevent the vibration from gradually increasing and entering a medium or high fluctuation state.

[0103] If IEC min ≤IEC≤IEC max The impact of local vibration in the pipe clamping area on load fluctuation is moderate, and the fluctuation under this impact level is classified as medium fluctuation.

[0104] At this point, the impact of vibration intensity and frictional changes during well workover operations on load fluctuations is significantly amplified, potentially leading to noticeable load fluctuations in the system and affecting operational stability. In such cases, the system needs dynamic monitoring of load fluctuations and vibration, and timely adjustments to the workover rig's operating parameters based on assessment results, such as reducing the pull-out speed and adjusting power output, to minimize the impact of vibration on the equipment and prevent further exacerbation of load fluctuations. In cases of moderate fluctuations, certain preventative measures are typically required to ensure the smooth progress of the operation.

[0105] If IEC > IEC max The impact of local vibration in the pipe clamping area on load fluctuation is considered to be of a high degree, and fluctuations under this level of impact are classified as high fluctuations.

[0106] At this point, the vibration intensity is extremely high, friction increases dramatically, and load fluctuations also rise significantly, potentially leading to severe system overload or equipment failure. High fluctuations typically mean that the stability of well workover operations faces significant challenges, requiring the system to immediately implement strong countermeasures, such as immediately slowing the pull-out speed, reducing power output, or temporarily halting operations until the vibration level decreases to a safe range. This situation necessitates highly sensitive monitoring and rapid response mechanisms to prevent equipment damage or operational interruptions, ensuring the safety and efficiency of the operation.

[0107] The pre-defined threshold range for the fluctuation impact assessment coefficient can be determined through a combination of historical data analysis and expert experience. First, the software system can collect and analyze the relationship between the friction amplification coefficient, vibration propagation index, and fluctuation impact assessment coefficient across multiple well workover cycles based on data from well workover operations over a past period. Through statistical analysis of this data, such as calculating the mean, standard deviation, or percentile of the fluctuation impact assessment coefficient, the approximate distribution range of the coefficient can be preliminarily determined. Then, based on the actual needs of the well workover operation, combined with the equipment's operating characteristics and safety standards, the software system can set a reasonable threshold range. Specifically, the minimum value can be set as the lower percentile of the fluctuation impact assessment coefficient, representing the system's low tolerance for load fluctuations under normal circumstances; the maximum value can be set as the higher percentile of the coefficient, indicating that the system needs to take intervention measures when vibration and friction increase to a certain extent. To ensure the accuracy of the range, the software system can also dynamically optimize the threshold range setting, continuously adjusting it based on actual operating data from each well workover cycle to adapt to changes in different operating environments and downhole conditions.

[0108] Based on the classification results, corresponding adjustment measures were taken for workover rigs under low, medium, and high volatility conditions, respectively.

[0109] In this embodiment, based on the classification results, corresponding adjustment measures are taken for the workover rig under low fluctuation, medium fluctuation, and high fluctuation conditions, respectively, as follows:

[0110] If the classification result is low fluctuation, the adjustment measures to be taken are: maintain the existing operating parameters, continue to monitor load fluctuations, and regularly check the equipment operating status to ensure stability;

[0111] When the assessment result indicates low fluctuation, it means that the local vibration in the stuck area has a relatively small impact on load fluctuations. In this case, system stability can be maintained by keeping existing operating parameters. Specifically, the software system can maintain the rig's lifting speed and power output within normal ranges based on real-time monitored load fluctuation data and feedback from vibration sensors. Simultaneously, it can periodically monitor equipment status and record data to ensure that load fluctuations do not exceed normal limits. The system can be set to a baseline operating mode, which includes a tolerance threshold for load fluctuations. Adjustments will only be triggered when load fluctuation data enters the warning zone. The advantage of this approach is that it avoids excessive intervention when the impact is minimal, reduces unnecessary operational adjustments, and improves operational efficiency.

[0112] If the classification result is a medium fluctuation, the adjustment measures to be taken are: adjust the lifting speed and power output of the workover rig to reduce load fluctuation, optimize equipment operating conditions, and increase the frequency of load fluctuation monitoring to ensure operational safety;

[0113] When the assessment result indicates moderate fluctuations, it means that the impact of local vibrations on load fluctuations has reached a certain level, potentially affecting the operational stability of the workover rig. In this case, adjustment measures are necessary. Specifically, the software system automatically adjusts the workover rig's lifting speed and power output based on real-time load fluctuation data to optimize its operational status and reduce the impact of vibration on load fluctuations. For example, the software can calculate the relationship between vibration frequency and load fluctuations in real time and automatically adjust the lifting speed or power according to preset parameter ranges to reduce vibration amplitude. Simultaneously, the system can increase monitoring frequency and periodically assess operating conditions to ensure operational stability. This measure effectively addresses moderate fluctuations, prevents further deterioration of load fluctuations, and reduces excessive adjustments to the equipment.

[0114] If the classification result indicates high fluctuations, the adjustment measures to be taken are: immediately reduce the lifting speed and optimize system power control, implement strict vibration monitoring, and conduct equipment inspection and maintenance to ensure the stability and safety of the workover rig.

[0115] When the assessment result indicates high fluctuations, it means that the local vibration in the stuck pipe area has a significant impact on load fluctuations, seriously threatening the stability of the workover rig. At this point, more stringent measures are needed to ensure safe equipment operation. The software system automatically detects high fluctuations and first automatically reduces the pull-out speed and optimizes power control. By adjusting the workover rig's operating parameters, the impact of vibration on the equipment is reduced. The software also automatically activates the vibration monitoring system, tracking vibration and load fluctuation data in real time. Once abnormal fluctuations occur, the system immediately issues an alarm, recommends suspending operations, and initiates a fault diagnosis program to check the equipment. The system can communicate with maintenance personnel to determine whether it is necessary to suspend operations for a thorough inspection or perform equipment maintenance and cleaning. Implementing these measures can effectively avoid equipment damage or operation interruptions that may occur under high fluctuation conditions, ensuring the safety and continuity of workover operations.

[0116] Continuously monitor load fluctuations, vibration data, and well workover rig operating status information, and dynamically adjust the load fluctuation impact assessment model and adjustment measures based on real-time monitoring results. At the same time, store and analyze historical monitoring data to optimize model parameters and adjustment strategies, thereby improving the system's adaptability and operational stability.

[0117] To ensure the operational stability of the workover rig, the software system can monitor load fluctuations and vibration data in real time using sensors. Specifically, data is collected through load and vibration sensors. The system can be configured with data collection frequencies and monitoring thresholds to ensure timely detection of any abnormal load or vibration fluctuations. When the load fluctuation or vibration amplitude exceeds the set threshold, the system will issue an alarm and trigger corresponding adjustment measures. Furthermore, the system will display real-time trend charts of load fluctuations and vibrations, helping operators intuitively understand the operational status. This real-time monitoring not only ensures timely detection of anomalies during operations but also provides data support for subsequent dynamic adjustments and optimizations, preventing equipment failures or operational interruptions caused by excessive load fluctuations or vibrations.

[0118] Based on real-time monitoring results, the software system dynamically adjusts the load fluctuation impact assessment model, optimizing assessment coefficients and adjustment strategies. For example, when load fluctuations exceed the preset normal range, the system will reassess the applicability of the existing model, potentially resetting the weights of the fluctuation impact assessment coefficients or adjusting the parameters of the regression model based on new data. Regarding adjustment measures, the system can automatically adjust operating parameters such as the workover rig's pull-out speed and power output based on changes in real-time load fluctuations, vibration data, and vibration propagation index. In this way, the system can continuously self-optimize, responding quickly to changes in different operating environments and downhole conditions, ensuring operational stability and reducing human intervention.

[0119] To enhance system adaptability and operational stability, the storage and analysis of historical monitoring data are crucial. Through the software system, all real-time collected load fluctuation, vibration data, and well workover rig operating status information are automatically stored in the database, and data reviews and trend analyses are performed regularly. The system can utilize machine learning and statistical analysis methods to extract patterns from historical data and identify potential operational patterns or signs of equipment failure. By analyzing historical data, the system can continuously optimize the load fluctuation impact assessment model and adjustment strategies, thereby improving the model's predictive accuracy and adaptability for future operating conditions. This data-driven optimization approach helps make well workover systems more intelligent, improve operational efficiency and safety, and reduce maintenance and failure risks.

[0120] like Figure 2 The power system of the oilfield automatic workover rig shown includes a pipe jamming detection and load monitoring module, a fluctuation characteristic acquisition and analysis module, a fluctuation assessment model construction module, a fluctuation classification and adjustment module, and a real-time monitoring and system optimization module.

[0121] The pipe jamming detection and load monitoring module monitors in real time whether there is a pipe jamming area during the well workover rig's pipe pulling process. It determines whether a pipe jamming phenomenon has occurred by monitoring load changes. If a pipe jamming area is confirmed, it further detects whether the load suddenly increases. If the load suddenly increases, it triggers the load fluctuation monitoring and adjustment process.

[0122] The fluctuation feature acquisition and analysis module acquires the fluctuation feature information of the workover rig when it encounters a stuck area while pulling out the well casing in real time, and analyzes the acquired information to generate the friction amplification coefficient and vibration propagation index, respectively.

[0123] The fluctuation assessment model construction module constructs a load fluctuation impact assessment model based on the generated friction amplification coefficient and vibration propagation index, generates fluctuation impact assessment coefficients, and analyzes them after generation to assess the degree of impact of local vibration in the pipe clamping area on load fluctuations. Based on the assessment results, the fluctuation situation is divided into low fluctuation, medium fluctuation and high fluctuation situations.

[0124] The fluctuation classification and adjustment module takes corresponding adjustment measures for workover rigs under low fluctuation, medium fluctuation and high fluctuation conditions according to the classification results;

[0125] The real-time monitoring and system optimization module continuously monitors load fluctuations, vibration data, and the operating status information of the workover rig. Based on the real-time monitoring results, it dynamically adjusts the load fluctuation impact assessment model and adjustment measures. At the same time, it stores and analyzes historical monitoring data to optimize model parameters and adjustment strategies.

[0126] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0127] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0128] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0129] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0130] In the several embodiments provided in this application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0131] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0132] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0133] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for operating the power system of an automatic well workover rig in an oilfield, characterized in that, Specifically, the following steps are included: During the process of the workover rig pulling out the tubing, the presence of a stuck area is monitored in real time. The presence of a stuck area is determined by monitoring load changes. If a stuck area is confirmed, the load is further checked for a sudden increase. If the load increases suddenly, the load fluctuation monitoring and adjustment process is triggered. Real-time acquisition of fluctuation characteristics when the workover rig encounters a stuck area while pulling out the well casing, and analysis of the acquired information to generate friction amplification coefficient and vibration propagation index respectively; Specifically, the following steps are included: Real-time acquisition of fluctuation characteristics when the workover rig encounters a stuck area while pulling up the well casing, and preprocessing of the acquired information; Extract load fluctuation information and vibration propagation characteristic information from the preprocessed fluctuation feature information; The extracted load fluctuation information and vibration propagation characteristic information are analyzed to generate the friction force amplification coefficient and vibration propagation index, respectively. A load fluctuation impact assessment model was constructed based on the generated friction force amplification coefficient and vibration propagation index. A fluctuation impact assessment coefficient was generated and analyzed after generation to assess the degree of impact of local vibration in the pipe clamping area on load fluctuation. Based on the assessment results, the fluctuation situation was divided into low fluctuation, medium fluctuation and high fluctuation. Based on the classification results, corresponding adjustment measures were taken for workover rigs under low, medium, and high volatility conditions, respectively. Continuously monitor load fluctuations, vibration data, and well workover rig operating status information, and dynamically adjust the load fluctuation impact assessment model and adjustment measures based on real-time monitoring results. At the same time, store and analyze historical monitoring data to optimize model parameters and adjustment strategies. The logic for obtaining the friction amplification coefficient is as follows: Load fluctuation information is extracted from the preprocessed fluctuation feature information. Specifically, this includes the load value at different times within a certain period when the workover rig encounters a stuck area while pulling up the tubing, the pressure change in the contact area between the tubing and the well wall, the tubing pull-out speed, and the viscosity of the downhole fluid, and these are denoted as FZ. m ΔPC m VP m and ND m FZ m ΔPC represents the load value at time m within a certain period when the workover rig encounters a stuck pipe area during pipe lifting. m VP represents the pressure change at time m in the contact area between the tubing and the wellbore during a certain period when the workover rig encounters a stuck area while pulling out the tubing. m ND represents the lifting speed of the tubing at time m within a certain period when the workover rig encounters a stuck area during tubing lifting. m This represents the viscosity of the downhole fluid at time m during a certain period when the workover rig encounters a stuck area while pulling out the well casing, where m = 1, 2, 3, ..., g, and g is a positive integer; The load value FZ at different times within a certain period of time when the workover rig encounters a stuck area while pulling out the well casing. m Construct a set, and label the maximum and minimum values ​​within the set as FZ respectively. max and FZ min ; The specific formula for calculating the friction force amplification factor is as follows: ， In the formula, FAC is the friction force amplification coefficient; The logic for obtaining the vibration propagation index is as follows: The vibration propagation characteristics information is extracted from the preprocessed wave feature information. Specifically, this includes the vibration amplitude of the stuck area at different times over a period of time when the workover rig encounters the stuck area during tubing extraction, the pressure change in the contact area between the tubing and the well wall, the density of the downhole fluid, and the stiffness and length of the tubing. These are then calibrated as AV. n ΔPC n ,ρF n EP and LP, AV n ΔPC represents the vibration amplitude of the stuck area at time n within a certain period when the workover rig encounters the stuck area during well casing extraction. n ρF represents the pressure change at time n in the contact area between the tubing and the wellbore during a certain period when the workover rig encounters a stuck area while retrieving the tubing. n EP represents the density of the downhole fluid at time n during a certain period when the workover rig encounters a stuck area while pulling out the tubing. LP represents the stiffness of the tubing and the length of the tubing. n = 1, 2, 3, ..., k, where k is a positive integer. The specific formula for calculating the vibration propagation index is as follows: ， In the formula, VPR is the vibration propagation index.

2. The method for operating the power system of the automatic well workover rig according to claim 1, characterized in that, A load fluctuation impact assessment model is constructed based on the generated friction force amplification coefficient and vibration propagation index, and fluctuation impact assessment coefficients are generated. This process includes the following steps: Several friction amplification coefficients, vibration propagation indices, and corresponding fluctuation impact assessment coefficients generated over a period of time were collected and labeled as FAC. x VPR x and IEC x x represents the number of several friction amplification coefficients, vibration propagation indices and corresponding fluctuation impact assessment coefficients generated in the past period, x=3, 4, 5, ..., d, where d is a positive integer, and the collected data in the past period are formed into a historical dataset; A multiple regression model was selected as the model for assessing the impact of load fluctuations. The model was trained using historical datasets to determine the values ​​of the regression coefficients, based on the formula: ， In the formula, β0, β1, and β2 are regression coefficients; By minimizing the error between the predicted and actual values, the regression coefficients are optimized, and the values ​​of the regression coefficients β0, β1, and β2 are finally determined. Using the finalized regression coefficients, the constructed load fluctuation impact assessment model is input with the real-time generated friction amplification coefficient FAC and vibration propagation index VPR to generate the fluctuation impact assessment coefficient IEC in real time.

3. The method for operating the power system of the automatic well workover rig according to claim 2, characterized in that, The generated fluctuation impact assessment coefficient IEC is compared with the pre-set fluctuation impact assessment coefficient threshold range [IEC]. min IEC max A comparison was conducted, and the impact of local vibration in the pipe clamping area on load fluctuations was assessed based on the comparison results. The fluctuations were then categorized into low, medium, and high fluctuations based on the assessment results. The specific comparison analysis and categorization are as follows: If IEC < IEC min The impact of local vibration in the pipe clamping area on load fluctuation is considered to be of low impact level, and fluctuations under this impact level are classified as low fluctuations. If IEC min ≤IEC≤IEC max The impact of local vibration in the pipe clamping area on load fluctuation is moderate, and the fluctuation under this impact level is classified as medium fluctuation. If IEC > IEC max The impact of local vibration in the pipe clamping area on load fluctuation is considered to be of a high degree, and fluctuations under this level of impact are classified as high fluctuations.

4. The method for operating the power system of the automatic well workover rig according to claim 3, characterized in that, Based on the classification results, corresponding adjustment measures are taken for workover rigs under low-fluctuation, medium-fluctuation, and high-fluctuation conditions, as follows: If the classification result is low fluctuation, the adjustment measures to be taken are: maintain the existing operating parameters, continue to monitor load fluctuations, and regularly check the equipment operating status to ensure stability; If the classification result is a medium fluctuation, the adjustment measures to be taken are: adjust the lifting speed and power output of the workover rig to reduce load fluctuation, optimize equipment operating conditions, and increase the frequency of load fluctuation monitoring to ensure operational safety; If the classification result indicates high fluctuations, the adjustment measures to be taken are: immediately reduce the lifting speed and optimize system power control, implement strict vibration monitoring, and conduct equipment inspection and maintenance to ensure the stability and safety of the workover rig.

5. A power system for an automatic well-servicing rig in an oilfield, used to implement the operation method of the power system of the automatic well-servicing rig in an oilfield as described in any one of claims 1-4, characterized in that, It includes modules for pipe detection and load monitoring, fluctuation characteristics acquisition and analysis, fluctuation assessment model construction, fluctuation classification and adjustment, and real-time monitoring and system optimization. The pipe jamming detection and load monitoring module monitors in real time whether there is a pipe jamming area during the well workover rig's pipe pulling process. It determines whether a pipe jamming phenomenon has occurred by monitoring load changes. If a pipe jamming area is confirmed, it further detects whether the load suddenly increases. If the load suddenly increases, it triggers the load fluctuation monitoring and adjustment process. The fluctuation feature acquisition and analysis module acquires the fluctuation feature information of the workover rig when it encounters a stuck area while pulling out the well casing in real time, and analyzes the acquired information to generate the friction amplification coefficient and vibration propagation index, respectively. The fluctuation assessment model construction module constructs a load fluctuation impact assessment model based on the generated friction amplification coefficient and vibration propagation index, generates fluctuation impact assessment coefficients, and analyzes them after generation to assess the degree of impact of local vibration in the pipe clamping area on load fluctuations. Based on the assessment results, the fluctuation situation is divided into low fluctuation, medium fluctuation and high fluctuation situations. The fluctuation classification and adjustment module takes corresponding adjustment measures for workover rigs under low fluctuation, medium fluctuation and high fluctuation conditions according to the classification results; The real-time monitoring and system optimization module continuously monitors load fluctuations, vibration data, and the operating status information of the workover rig. Based on the real-time monitoring results, it dynamically adjusts the load fluctuation impact assessment model and adjustment measures. At the same time, it stores and analyzes historical monitoring data to optimize model parameters and adjustment strategies.

Images