A pressurized pipeline tapping machine and intelligent control system

Abstract

The application relates to the technical field of regulation and control, in particular to a pressurized pipeline opening machine and an intelligent control system. The pressurized pipeline opening machine comprises a memory and a processor. The processor executes a computer program stored in the memory to realize the following steps: obtaining different kinds of sensor data in the operation process of the opening machine, determining a load factor, a vibration factor and a pressure factor according to residual terms corresponding to the different kinds of sensor data in the operation process; then comprehensively determining a stage parameter at the current moment according to the load factor, the vibration factor and the pressure factor; obtaining a state parameter at the current moment according to the discrete distribution of the residual terms corresponding to each kind of sensor data in the time neighborhood of the current moment; and adjusting the main shaft rotating speed of the opening machine comprehensively according to the stage parameter and the state parameter. The application improves the control stability of the main shaft rotating speed of the opening machine during the opening of the pressurized pipeline, and improves the opening effect of the pressurized pipeline.

Description

Technical Field

[0001] This invention relates to the field of regulation and control technology, specifically to a pressurized pipe tapping machine and its intelligent control system. Background Technology

[0002] Live pipeline tapping is a technique for tapping pipes under normal operating conditions. It is safe, environmentally friendly, economical, and efficient. It is suitable for routine maintenance and renovation of pipelines carrying various media such as water, crude oil, refined oil, chemical media, and natural gas, as well as emergency repairs in case of accidents, including live repairs, replacement of corroded pipe sections, installation of equipment, and distribution system upgrades.

[0003] Live pipeline tapping technology creates interfaces on pipelines using specialized tapping equipment. During tapping, the pipeline and container are under pressure or in use, allowing for the addition of branch pipes for material input or output. This operation does not require production shutdowns and does not affect output or material supply. While live pipeline tapping technology offers numerous advantages, it also presents certain risks and challenges. Strict control of pressure changes is necessary during the operation to ensure stable pipeline system operation. Furthermore, complex pipeline systems and environmental factors can introduce uncertainties into live pipeline tapping operations, thus placing higher demands on the technology.

[0004] When drilling holes in pressurized pipelines, the pipeline material, wall thickness, internal medium state (gas / liquid, containing impurities), and external load (such as soil pressure) may all change, resulting in a highly nonlinear and time-varying cutting process. This uncertainty can easily affect the drilling effect, and in severe cases, accidents may occur due to the high pressure of the pipeline. Therefore, if the spindle speed of the drilling machine remains constant during drilling operations, it will affect the drilling effect of pressurized pipelines. Summary of the Invention

[0005] To address the problem of poor drilling results in pressurized pipelines due to the fixed spindle speed of the drilling machine in existing methods, the present invention aims to provide a pressurized pipeline drilling machine and an intelligent control system. The specific technical solution adopted is as follows:

[0006] In a first aspect, the present invention provides a pressurized pipe tapping machine, comprising a memory and a processor, wherein the processor executes a computer program stored in the memory to perform the following steps:

[0007] Acquire different types of sensor data during the operation of the tapping machine on pressurized pipelines. The sensor data includes torque data, vibration data, and pressure data of the medium inside the pipeline on the tapping machine spindle.

[0008] The data from each sensor is decomposed to obtain the corresponding residual and trend terms. Based on the residual and trend terms of the torque data during operation and the operating time of the drilling machine, the load factor at the current moment is obtained. Based on the residual terms of the vibration data during operation and the operating time of the drilling machine, the vibration factor at the current moment is obtained. Based on the attenuation characteristics of the pressure data during operation and the medium attenuation coefficient, the pressure factor at the current moment is obtained. By combining the load factor, vibration factor, and pressure factor, the stage parameters at the current moment are determined.

[0009] Based on the discrete distribution of the residual terms corresponding to each type of sensor data in the time neighborhood at the current moment, the state parameters at the current moment are obtained.

[0010] The spindle speed of the drilling machine is adjusted by combining stage parameters and status parameters.

[0011] Preferably, the step of obtaining the load factor at the current moment based on the residual term, trend term, and drilling machine operation time corresponding to the torque data during the operation includes:

[0012] The forward difference sequence of the residual terms corresponding to the torque data of all times in the time neighborhood of the current time is denoted as the first difference sequence; the first standard deviation of all difference values ​​in the first difference sequence is calculated.

[0013] Based on the difference values ​​in the forward difference sequence of the trend term corresponding to the torque data of all times in the time neighborhood of the current time and the duration between the corresponding time and the current time, the characteristic value of the trend term change is obtained.

[0014] The load factor at the current moment is obtained based on the duration between the current moment and the initial moment of the hole punching machine operation, the first standard deviation, and the characteristic value of the trend term change. The duration between the current moment and the initial moment of the hole punching machine operation and the characteristic value of the trend term change are both positively correlated with the load factor, while the first standard deviation is negatively correlated with the load factor.

[0015] Preferably, obtaining the trend term change feature value based on the difference value in the forward difference sequence of the trend term corresponding to the torque data of all times in the time neighborhood of the current time and the duration between the corresponding time and the current time includes:

[0016] The duration between the time corresponding to each difference value in the forward difference sequence of the trend term corresponding to the torque data of all times in the time neighborhood of the current time and the current time is denoted as the first time interval of the corresponding time.

[0017] The ratio between the difference value in the forward difference sequence of the trend term corresponding to the torque data of all times in the time neighborhood of the current time and the first time interval of the corresponding time is used as the first feature value corresponding to each difference value in the forward difference sequence of the trend term corresponding to the torque data of all times in the time neighborhood of the current time.

[0018] The sum of the first eigenvalues ​​corresponding to all difference values ​​in the forward difference sequence of the trend term corresponding to the torque data of all times in the time neighborhood of the current time is determined as the trend term change eigenvalue.

[0019] Preferably, obtaining the vibration factor at the current moment based on the residual terms corresponding to the vibration data during the operation and the operating time of the drilling machine includes:

[0020] The forward difference sequence of the residual terms corresponding to the vibration data of all times in the time neighborhood of the current time is denoted as the second difference sequence; the second standard deviation of all difference values ​​in the second difference sequence is calculated.

[0021] The time weight is obtained by using the residual terms corresponding to the vibration data of all times in the time neighborhood of the current time, and the duration between the current time and all times in the time neighborhood of the current time.

[0022] The vibration factor at the current moment is obtained based on the duration between the current moment and the initial moment of the hole punching machine operation, the second standard deviation, and the time weight. The duration between the current moment and the initial moment of the hole punching machine operation is positively correlated with the vibration factor, and the second standard deviation is negatively correlated with the vibration factor.

[0023] Preferably, obtaining the time weight based on the residual terms corresponding to the vibration data of all times within the time neighborhood of the current time, and the duration between the current time and all times within the time neighborhood of the current time, includes:

[0024] For any time within the time neighborhood of the current time: the product of the absolute value of the residual term corresponding to the vibration data at any time and the time interval between the any time and the current time is taken as the second characteristic value of the any time;

[0025] The average of the second feature values ​​of all times within the time neighborhood of the current time is used as the time weight.

[0026] Preferably, obtaining the pressure factor at the current moment based on the attenuation characteristics of the pressure data during the operation and the medium attenuation coefficient includes:

[0027] The difference between the pressure data of the previous time and the pressure data of the current time is used as the pressure decay value of the current time.

[0028] The pressure factor at the current moment is obtained based on the pressure attenuation value and the medium attenuation coefficient. Both the pressure attenuation value and the medium attenuation coefficient are positively correlated with the pressure factor.

[0029] Preferably, the stage parameters for the current moment are determined by comprehensively considering the load factor, vibration factor, and pressure factor, including;

[0030] Calculate the sum of the load factor, vibration factor, and pressure factor at the current moment;

[0031] The sum is mapped to a preset interval to obtain the stage parameters at the current time. The preset interval is (-1, 1).

[0032] Preferably, obtaining the state parameters at the current moment based on the discrete distribution of the residual terms corresponding to each type of sensor data in the time neighborhood at the current moment includes:

[0033] For any type of sensor data: calculate the standard deviation of the residual term corresponding to the sensor data at all times within the time neighborhood of the current time, and use it as the discrete characteristic value of the sensor data.

[0034] By combining the discrete feature values ​​of all types of sensor data, the state parameter at the current moment is obtained. The discrete feature values ​​are negatively correlated with the state parameter, and the value of the state parameter is within a preset range.

[0035] Preferably, the integrated stage parameters and state parameters adjust the spindle speed of the drilling machine, including:

[0036] When the stage parameter is greater than 0, calculate the first sum of the stage parameter and the state parameter; if the state parameter is also greater than 0, use the negative correlation normalization result of the first sum as the control function value; if the state parameter is less than 0, use the sum of the constant 1 and the state parameter as the control function value.

[0037] When the stage parameter is less than 0, if the state parameter is greater than 0, calculate the second sum of the absolute value of the stage parameter and the state parameter, and use half of the second sum plus the constant 1 as the control function value; if the state parameter is less than 0, record the absolute value of the sum of the stage parameter and the state parameter as the first absolute value, calculate the third sum of the constant 1 and the first absolute value; use the reciprocal of the third sum as the control function value.

[0038] The control function value is smoothed using the exponentially weighted moving average method to obtain the smoothed control function value;

[0039] The product of the smoothed control function value and the current spindle speed of the drilling machine is determined as the adjusted spindle speed of the drilling machine.

[0040] Secondly, the present invention provides an intelligent control system for a pressurized pipe tapping machine, the system comprising:

[0041] The data acquisition module is used to acquire different types of sensor data during the operation of the tapping machine on pressurized pipelines. The sensor data includes the torque data and vibration data of the tapping machine spindle, as well as the pressure data of the medium inside the pipeline.

[0042] The first processing module is used to decompose each type of sensor data to obtain the corresponding residual and trend terms; based on the residual and trend terms of the torque data during operation and the working time of the drilling machine, the load factor at the current moment is obtained; based on the residual terms of the vibration data during operation and the working time of the drilling machine, the vibration factor at the current moment is obtained; based on the attenuation characteristics of the pressure data during operation and the medium attenuation coefficient, the pressure factor at the current moment is obtained; and by combining the load factor, vibration factor, and pressure factor, the stage parameters at the current moment are determined.

[0043] The second processing module is used to obtain the state parameters at the current time based on the discrete distribution of the residual terms corresponding to each type of sensor data in the time neighborhood at the current time.

[0044] The adjustment module is used to adjust the spindle speed of the drilling machine by combining stage parameters and status parameters.

[0045] The present invention has at least the following beneficial effects:

[0046] This invention first extracts the trend and residual terms of each sensor data during the hole-opening machine operation. Then, through the collaborative calculation of load factor, vibration factor, and pressure factor, it generates quantified stage parameters and state parameters to accurately identify the three key stages of cutting: the early stage, the middle stage, and the transient cutting stage. In addition, when determining the pressure factor, a medium attenuation coefficient is introduced to dynamically adapt to the pressure attenuation characteristics of different fluids such as natural gas, crude oil, and water, so that the calculated pressure factor can more accurately reflect the actual situation during the hole-opening machine cutting process. Furthermore, by utilizing the specific values ​​of the stage parameters and state parameters, precise control of the hole-opening machine's spindle speed is achieved, solving the problems of fuzzy cutting state identification, lagging speed adjustment, and insufficient response to sudden working conditions in hole-opening operations. This improves the stability of spindle speed control during pressurized pipe hole opening and further enhances the hole opening effect of pressurized pipes. Attached Figure Description

[0047] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0048] Figure 1 This is a flowchart illustrating a method performed by a pressurized pipe tapping machine according to an embodiment of the present invention. Detailed Implementation

[0049] To further illustrate the technical means and effects adopted by the present invention to achieve the intended purpose, the following detailed description of a pressurized pipe tapping machine and intelligent control system according to the present invention is provided in conjunction with the accompanying drawings and preferred embodiments.

[0050] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0051] The following description, in conjunction with the accompanying drawings, details the specific solution of the pressurized pipe tapping machine and intelligent control system provided by the present invention.

[0052] An embodiment of a pressurized pipe tapping machine:

[0053] This embodiment proposes a pressurized pipe tapping machine, which includes a memory and a processor. The processor executes a computer program stored in the memory to achieve, for example... Figure 1 The steps shown are as follows:

[0054] Step S1: Obtain data from different types of sensors during the operation of the tapping machine on the pressurized pipeline, including the torque data and vibration data of the tapping machine spindle and the pressure data of the medium inside the pipeline.

[0055] Live tapping mainly includes several forms such as vertical pipe tapping, clamp pipe tapping, oblique pipe tapping, inverted pipe tapping, and tank tapping. The structure of a live pipe tapping machine mainly includes a housing, spindle, mandrel, drill bit, transmission structure, and feed mechanism. Furthermore, the entire live tapping operation typically includes the following stages: welding tee flanges and short-connection flanges; installing the clamp valve; installing the tapping machine; purging the air inside the manifold; tapping operation; completing the operation; dismantling the tapping machine; locating the clamp valve; and sealing the tee pipe diameter. Among these, the tapping stage is the most crucial. When using an electrically driven tapping machine, it requires initial feed, penetrating the pipe wall, cutting the cavity, and then retracting the cutter and closing the valve.

[0056] During the tapping operation of a pressurized pipeline tapping machine, complex multi-physics coupling phenomena exist, affecting the final tapping effect. Specifically, when the tool encounters hard spots in the weld during pipe cutting, the cutting load increases, causing spindle overload. Therefore, when the spindle is working, the reaction force of the tool on the spindle causes torsional elastic deformation. During feed, the tool is subjected to axial and radial forces. When the thin wall of the pressurized pipeline is cut through, transient load changes occur. Transient load changes also occur when the drill bit chipps. Therefore, vibration monitoring is required. In addition, during the cutting process, the medium inside the pipeline (water, crude oil, refined oil, chemical media, natural gas) is under high pressure and may leak out in the cut. Therefore, leakage monitoring is necessary to analyze whether there are any abnormalities in the cutting process that could lead to leakage.

[0057] First, multi-source sensors are deployed to collect multi-source data during the operation of the drilling machine, denoted as sensor data. In this embodiment, the sensor data collected includes: torque data of the drilling machine spindle, vibration data, and pressure data of the medium inside the pipe. Specifically, torque data is collected by a torque sensor to reflect the cutting load of the drilling machine; vibration data is collected by a vibration sensor to reflect the stability of the drilling machine's working process and state; and pressure data is collected by a pressure sensor to reflect the pressure state of the medium inside the pipe during the drilling operation. Furthermore, the data sampling frequency of different sensors is set to be the same, and the sensor sampling frequency is greater than or equal to 1kHz. The specific value of the sensor sampling frequency is set by the implementer according to the specific circumstances.

[0058] Then, the multi-source data collected by the sensors undergoes data preprocessing, including Kalman filtering for noise reduction to improve the data quality. It should be noted that the torque, vibration, and pressure data mentioned later are all preprocessed data.

[0059] Step S2: Decompose each type of sensor data to obtain the corresponding residual term and trend term; based on the residual term and trend term of the torque data during the operation and the working time of the drilling machine, obtain the load factor at the current moment; based on the residual term of the vibration data during the operation and the working time of the drilling machine, obtain the vibration factor at the current moment; based on the attenuation characteristics of the pressure data during the operation and the medium attenuation coefficient, obtain the pressure factor at the current moment; combine the load factor, vibration factor, and pressure factor to determine the stage parameters at the current moment.

[0060] The multi-source data from different sensors reflects different aspects of the state during the drilling process. In order to describe the drilling process and state more accurately, so as to facilitate feedback adjustment of the drilling process and improve the stability and safety of the drilling process, this embodiment chooses to use multi-source data to establish a control model, so that the rotation speed of the drilling machine spindle can be controlled in the subsequent drilling process.

[0061] This embodiment will use changes in multi-source data to identify the cutting stage and perform stage analysis on the multi-source data according to the cutting stage to determine the stage parameters corresponding to the current moment.

[0062] During the tapping operation of a pressurized pipe, the depth of the cutting tool increases with the cutting process. Therefore, the cutting process generally goes through several stages: early cutting, middle cutting, and transient cutting. Different stages correspond to different cutting requirements. The neighboring moments that are closer to the current moment have a high similarity to the cutting situation at the current moment and can be regarded as moments belonging to the same stage as the current moment. Therefore, this embodiment selects to identify the cutting stages formed by moments in the time neighborhood of the current moment in order to control the spindle speed of the tapping machine, thereby meeting the corresponding cutting requirements at the current moment.

[0063] First, the cutting stage is identified using changes in multi-source data. Specifically, the STL time-series decomposition algorithm is used to perform time-series decomposition on the data from each sensor during the hole-opening machine operation, obtaining the time-series decomposition results for each sensor data. These results include trend terms, periodic terms, and residual terms. In this embodiment, the residual terms will be analyzed later, so the residual terms and trend terms for each type of sensor data are extracted. The STL time-series decomposition algorithm is existing technology and will not be described in detail here.

[0064] In the three stages of the cutting process described above (i.e., early cutting, middle cutting, and cut-through transient), the early cutting stage is when the cutting tool and the pipe begin to contact, and the tool begins to bear a certain load. At this time, the pipe begins to generate a reaction force on the rotation of the cutting tool, and the torque value at the corresponding moment in the torque data is larger than the value at the beginning of cutting. Since the pipe is cylindrical, the cutting process does not directly open the pipe completely, but gradually causes partial cutting through the pipe, continuously increasing the degree of cutting. In the middle cutting stage, partial cutting through the pipe has begun. At this time, as the depth of the cutting tool in the pipe has increased, the reaction force of the pipe on the cutting tool also begins to increase, causing the torque value at the corresponding moment in the torque data to also increase. Furthermore, during the cutting process, the torque value will fluctuate during the increase due to the thickness of the pipe wall itself or the influence of the welded parts. Further, as the cutting process progresses, the cut-through portion gradually increases, eventually leading to complete cutting through, reaching the cut-through transient. At this time, the pipe no longer generates a reaction force on the cutting tool, and the torque value of the cutting tool will decrease instantaneously.

[0065] Based on the above characteristics, firstly, all times within the time neighborhood of the current time are obtained. In this embodiment, the time neighborhood of the current time is a time period consisting of a preset duration preceding and adjacent to the current time. In this embodiment, the preset duration is set to 1 minute. In specific applications, the implementer can set it according to specific circumstances. Then, the forward difference sequence of the residual terms corresponding to the torque data of all times within the time neighborhood of the current time is obtained, and this forward difference sequence is denoted as the first difference sequence. The method for obtaining the forward difference sequence is existing technology and will not be described in detail here. The standard deviation of all difference values ​​in the first difference sequence is calculated, and this standard deviation is denoted as the first standard deviation. The first standard deviation is used to reflect the dispersion of the difference values ​​in the first difference sequence.

[0066] Obtain the forward difference sequence of the trend term corresponding to the torque data of all times within the time neighborhood of the current time. Record the duration between the time corresponding to each difference value in the forward difference sequence of the trend term corresponding to the torque data of all times within the time neighborhood of the current time and the current time as the first time interval for that time. Use the ratio between the difference value in the forward difference sequence of the trend term corresponding to the torque data of all times within the time neighborhood of the current time and the first time interval for that time as the first feature value corresponding to each difference value in the forward difference sequence of the trend term corresponding to the torque data of all times within the time neighborhood of the current time. The sum of the first feature values ​​corresponding to all difference values ​​in the forward difference sequence of the trend term corresponding to the torque data of all times within the time neighborhood of the current time is determined as the trend term change feature value. Based on the duration between the current time and the initial time of the hole-opening machine operation, the first standard deviation, and the trend term change feature value, obtain the load factor for the current time. The duration between the current time and the initial time of the hole-opening machine operation and the trend term change feature value are positively correlated with the load factor, while the first standard deviation is negatively correlated with the load factor.

[0067] Among them, a positive correlation means that the dependent variable increases as the independent variable increases, and the dependent variable decreases as the independent variable decreases. It can be an additive relationship, a multiplicative relationship, etc., which is determined by practical application. A negative correlation means that the dependent variable decreases as the independent variable increases, and the dependent variable increases as the independent variable decreases. It can be a subtractive relationship, a division relationship, etc., which is determined by practical application.

[0068] It should be noted that since the elements in the forward difference sequence of the trend term corresponding to the torque data of all times within the current time's time neighborhood are obtained by subtracting the data of two adjacent times, the number of elements in the forward difference sequence is one less than the number of times within the current time's time neighborhood. In this embodiment, interpolation processing is performed on the calculated forward difference sequence, that is, an element is added to the first position of the calculated forward difference sequence. The value of this element is the same as the element at the first position of the original calculated forward difference sequence. In other words, the number of elements in the forward difference sequence after interpolation is the same as the number of times within the current time's time neighborhood, and the data values ​​of the first and second elements in the interpolated forward difference sequence are equal. The elements in the forward difference sequence after interpolation have a one-to-one correspondence with the times within the current time's time neighborhood. In other words, the interpolated forward difference sequence serves as the forward difference sequence of the trend term corresponding to the torque data of all times within the current time's time neighborhood. As another implementation, interpolation processing may not be performed.

[0069] In this embodiment, the specific calculation formula for the load factor at the current moment is given, and the load factor at the current moment can be expressed as:

[0070] ;

[0071] in, This represents the load factor at the current moment. This indicates the duration between the current moment and the initial moment of the drilling machine's operation. This represents the standard deviation of all difference values ​​in the first difference sequence, also known as the first standard deviation. This represents the number of difference values ​​in the forward difference sequence of the trend term corresponding to the torque data of all times within the time neighborhood of the current time, which is also the number of times within the time neighborhood of the current time. This represents the difference value in the forward difference sequence of the trend term corresponding to the torque data at all times within the time neighborhood of the current time. Indicates the current moment. This represents the forward difference sequence of the trend term corresponding to the torque data at all times within the time neighborhood of the current time. The time corresponding to each difference value This represents the forward difference sequence of the trend term corresponding to the torque data at all times within the time neighborhood of the current time. The duration between the time corresponding to the difference value and the current time, that is, the th difference value in the forward difference sequence of the trend term corresponding to the torque data of all times in the time neighborhood of the current time. The first time interval corresponding to each difference value Represents the normalization function. This indicates the preset first adjustment parameter.

[0072] In this embodiment, a preset first adjustment parameter is introduced into the calculation formula of the load factor to prevent the denominator from being 0. In this embodiment, the preset first adjustment parameter is 0.01. In specific applications, the implementer can set it according to the specific situation. This represents the forward difference sequence of the trend term corresponding to the torque data at all times within the time neighborhood of the current time. The first eigenvalue corresponding to each difference value.

[0073] The load factor describes the cutting process in terms of torque load; a larger load factor indicates a greater cutting depth. The standard deviation of the forward difference sequence of the torque data corresponding to the residual term in the current time neighborhood reflects the fluctuation of torque data changes in the current time neighborhood. Since the torque value shows a momentary decrease during the penetration transient, in the early and middle stages of cutting, when the pipe is partially penetrated, the reaction force increases and the change process is relatively stable, resulting in a smaller standard deviation for all difference values ​​in the first difference sequence. At the moment of penetration, there is a large fluctuation, resulting in a larger standard deviation for all difference values ​​in the first difference sequence. The trend term of the torque data represents the smoothed torque change trend. This indicates the change in the trend term between adjacent time points. A positive value indicates an increase in torque and load, while a negative value indicates a decrease in torque and load, consistent with the cutting process. This indicates that the torque trend increases during the early and middle stages of cutting. At this time, it indicates that during the cutting transient, the torque trend decreases sharply; Calculate the change value of the trend term The weighted cumulative sum, with weights of The weighting design emphasizes recent changes. This is the time interval between the current moment and the moments in the neighborhood. The smaller the time interval, meaning the moments in the neighborhood are closer to the current moment, the greater the weight, reflecting the greater impact of recent torque changes on the current state. In the early stages of cutting, the torque begins to increase. It is a small positive value, but the cumulative sum is relatively small; the torque continues to increase in the middle of the cutting process. Larger positive values ​​accumulate and increase significantly; during the shear-through transient, the torque drops sharply. When the value is negative, the cumulative sum decreases rapidly, and the weight... Ensure sensitivity to cut-through transients occurring within the time neighborhood.

[0074] In the early stage of cutting, slight vibrations occur when the tool initially contacts the pipe, and the vibration data at this time exhibits low-frequency, small-amplitude fluctuations. As the cutting progresses into the middle stage, the vibration amplitude increases significantly with the increase in tool depth and partial cut-through, especially when encountering hard spots in the weld or uneven pipe thickness, high-frequency impact vibrations occur. When the cut-through transient is reached, the tool will produce brief and violent vibrations due to the sudden loss of support from the pipe wall, which manifests as a sudden change in the peak value of the vibration data.

[0075] Obtain the forward difference sequence of the residual terms corresponding to the vibration data of all times in the time neighborhood of the current time, and denote this forward difference sequence as the second difference sequence; calculate the standard deviation of all difference values ​​in the second difference sequence, and denote this standard deviation as the second standard deviation.

[0076] For any time within the time neighborhood of the current time: the product of the absolute value of the residual term corresponding to the vibration data at that time and the time interval between that time and the current time is used as the second feature value for that time. Using this method, the second feature value for each time within the time neighborhood of the current time can be obtained.

[0077] The average of the second characteristic values ​​of all times within the time neighborhood of the current time is used as the time weight. The vibration factor at the current time is obtained based on the duration between the current time and the initial time of the hole-opening machine operation, the second standard deviation, and the time weight. The duration between the current time and the initial time of the hole-opening machine operation is positively correlated with the vibration factor, while the second standard deviation is negatively correlated with the vibration factor.

[0078] In this embodiment, the formula for calculating the vibration factor at the current moment is given, and the vibration factor at the current moment can be expressed as:

[0079] ;

[0080] in, Indicates the vibration factor at the current moment. This represents the standard deviation of all difference values ​​in the second difference sequence, also known as the second standard deviation. Indicates the time neighborhood of the current moment. The absolute value of the residual term corresponding to the vibration data at each time point. Represents the normalization function. This indicates the preset second adjustment parameter.

[0081] In this embodiment, a preset second adjustment parameter is introduced into the calculation formula of the vibration factor to prevent the denominator from being 0. In this embodiment, the preset second adjustment parameter is 0.01. In specific applications, the implementer can set it according to the specific situation. Indicates the time neighborhood of the current moment. The second eigenvalue at each moment. The larger the vibration factor, the more it tends towards the cutting-through transient state from the early cutting stage, where... It represents the absolute value of the residual, which is used to reflect the energy intensity of high-frequency vibration. When the value is small, it corresponds to the vibration data in the early stage of cutting being dominated by low-frequency vibration. When the value is large, it corresponds to the vibration data in the middle stage of cutting being dominated by high-frequency vibration, reflecting the high-frequency impact on the pipeline. When it appears, the maximum value corresponds to the peak change at the moment of cutting through. As an adjustment weight, the weight of recent oscillations is increased to ensure that the peak value of the cut-through transient is significantly amplified because it occurs at the most recent moment.

[0082] In the early stages of cutting, the pressure of the medium in the pipeline remains stable and high. As the cutting progresses into the middle stage, the pressure data will decrease in a stepwise manner as partial cutting occurs, with the decrease being proportional to the cutting area. When the cutting transient is reached, the pressure data will drop sharply. In addition, different media (such as natural gas / crude oil) will exhibit different pressure decay rate characteristics.

[0083] The difference between the pressure data of the previous moment and the pressure data of the current moment is taken as the pressure decay value of the current moment. Based on the pressure decay value and the medium decay coefficient, the pressure factor of the current moment is obtained. Both the pressure decay value and the medium decay coefficient are positively correlated with the pressure factor. In this embodiment, the normalized result of the product of the pressure decay value and the medium decay coefficient is taken as the pressure factor of the current moment. There are many data normalization methods. When normalizing the product of the pressure decay value and the medium decay coefficient, existing data normalization methods can be used to ensure that the normalized result is (0, 1). The value of the medium decay coefficient is determined based on the fluid viscosity of the medium. The lower the viscosity, the higher the value of the medium decay coefficient. For example: natural gas (rapid decay): K=1.8; crude oil (medium-speed decay): K=1.2; water (slow decay): K=0.8, with a reference value range of [0, 5]. In specific applications, the implementer determines the corresponding medium decay coefficient according to the specific circumstances.

[0084] After determining the load factor, vibration factor, and pressure factor at the current moment, the load factor, vibration factor, and pressure factor are combined to determine the stage parameters at the current moment.

[0085] Specifically, the sum of the load factor, vibration factor, and pressure factor at the current moment is calculated; this sum is then mapped to a preset interval (-1, 1) to obtain the stage parameters at the current moment. In this embodiment, the stage parameters at the current moment can be calculated using the following formula:

[0086] ;

[0087] in, This represents the stage parameters at the current moment. This represents the load factor at the current moment. Indicates the vibration factor at the current moment. This represents the stress factor at the current moment.

[0088] The range of the stage parameter is (-1, 1). The stage parameter is used to describe the process of the hole punching machine punching the pipe, or the degree to which the pipe is cut through. The larger the value of the stage parameter, the deeper the cutting tool of the hole punching machine penetrates, and the higher the degree of pipe penetration.

[0089] Thus, using the above method, the stage parameters for the current moment have been obtained.

[0090] Step S3: Obtain the state parameters at the current time based on the discrete distribution of the residual terms corresponding to each type of sensor data in the time neighborhood at the current time.

[0091] Next, this embodiment performs discrete analysis on the multi-source data to determine the corresponding state parameters at the current moment.

[0092] For any type of sensor data: calculate the standard deviation of the residual term corresponding to the sensor data at all times within the time neighborhood of the current time, and use this standard deviation as the discrete characteristic value of the sensor data. The larger the standard deviation, the more discrete the sensor data is within the time neighborhood of the current time.

[0093] By combining the discrete feature values ​​of all types of sensor data, the state parameter at the current moment is obtained. The discrete feature values ​​are negatively correlated with the state parameter, and the state parameter value lies within a preset range. In this embodiment, a specific formula for calculating the state parameter at the current moment is given, and the state parameter at the current moment can be expressed as:

[0094] ;

[0095] in, This represents the state parameters at the current moment. Indicates the number of types of sensor data. Represents the i-th time among all times in the time neighborhood of the current time. The standard deviation of the residuals corresponding to the sensor data This indicates the preset third adjustment parameter.

[0096] In this embodiment, a preset third adjustment parameter is introduced into the calculation formula of the state parameter to prevent the denominator from being 0. In this embodiment, the preset third adjustment parameter is 0.01. In specific applications, the implementer can set it according to the specific situation. The value range of the state parameter is (-1, 1). The state parameter is used to describe the stable state during the hole cutting process. The larger the value, the more concentrated the value distribution of the data points in the residual term, which reflects the more stable the comprehensive changes in load, vibration, and pressure.

[0097] Thus, this embodiment has obtained the state parameters at the current moment.

[0098] Step S4: Adjust the spindle speed of the drilling machine by combining the stage parameters and status parameters.

[0099] In this embodiment, the current stage parameters and state parameters are obtained in the above steps. The stage parameters are used to reflect the degree of cutting through, and the state parameters are used to reflect the system stability during the hole-opening process. Next, this embodiment will combine the stage parameters and state parameters to adjust the spindle speed of the hole-opening machine.

[0100] When the stage parameter is greater than 0, the sum of the stage parameter and the state parameter is recorded as the first sum value; if the state parameter is also greater than 0, the negative correlation normalization result of the first sum value is used as the control function value; if the state parameter is less than 0, the sum of the constant 1 and the state parameter is used as the control function value.

[0101] When the stage parameter is less than 0, if the state parameter is greater than 0, the sum of the absolute value of the stage parameter and the state parameter is recorded as the second sum, and half of the second sum is summed with the constant 1 as the control function value; if the state parameter is less than 0, the absolute value of the sum of the stage parameter and the state parameter is recorded as the first absolute value, and the third sum of the constant 1 and the first absolute value is calculated; the reciprocal of the third sum is used as the control function value.

[0102] In the above cases, the control function value can be specifically expressed as:

[0103] ;

[0104] in, This represents the value of the control function at the current moment. This represents the stage parameters at the current moment. This represents the state parameters at the current moment. Represents the absolute value symbol. Represents the natural constant.

[0105] This indicates a high degree of cut penetration in the later stages of cutting and a relatively stable cutting process. The first sum, The first sum represents the negative correlation normalization result. The larger the first sum, the higher the cutting depth and the more stable the process. Therefore, the smaller the control function value, the more preventative speed reduction is implemented to avoid the risk of overcutting. When the cutting depth is high, even if the system is stable, the rotation speed is gradually reduced to prevent the tool from excessively penetrating into the pipe. Indicates the second sum. At this point, the cutting speed is increased through a linear speed-up function, indicating a low degree of penetration and a relatively stable cutting process in the early stages of cutting. The larger the value, the farther away it is from the target being cut. A larger value indicates better stability and a larger control function value, thereby improving efficiency while ensuring safety. Represents the first absolute value. Indicates the third sum. This indicates that the cutting process is unstable at low penetration levels, such as when tool chipping or weld hard spots cause a sharp increase in vibration. The larger the size, the more severe the abnormality. At this point, [the following steps are needed:] This rapidly reduces the spindle speed to prevent tool breakage and spindle overload. When the cutting process is unstable in the later stages of a high degree of penetration, such as when a large amount of transient medium leaks during penetration, causing a sudden drop in pressure, the system instability is usually caused by leakage when the penetration degree is high. At this time, safety should be prioritized under high penetration conditions. The rotation speed is directly controlled through state parameters to suppress the expansion of leakage and wait for the sealing system to respond.

[0106] Specifically, when the state parameter When the value is 0, it indicates that the opening process at the current moment is in a stable state, and the constant 1 is used as the control function value. When the stage parameter... =0, state parameter hour, When the stage parameter =0, state parameter hour, Since the state with a stage parameter of 0 is a short-lived state, this method is used to connect the preceding and following states, thus providing a smooth transition.

[0107] After obtaining the control function value using the above method, the significant difference between the obtained control function value and the spindle speed of the drilling machine can lead to excessive speed changes during spindle speed adjustment, resulting in decreased stability of the drilling process. Therefore, an exponentially weighted moving average method is used to smooth the control function value at each time point, thus obtaining the smoothed control function value at the current time point. The exponentially weighted moving average method is a current technique and will not be discussed in detail here.

[0108] The product of the smoothed control function value and the current spindle speed of the drilling machine is used to determine the adjusted spindle speed, which is then adjusted accordingly. It should be noted that the spindle speed has a range limitation. When the calculated adjusted speed is greater than the maximum preset speed, the maximum preset speed is used as the adjusted speed, and this adjusted speed is sent to the spindle drive controller (such as a frequency converter or servo motor) for real-time spindle speed adjustment. When the calculated adjusted speed is less than the minimum preset speed, the minimum preset speed is used as the adjusted speed, and this adjusted speed is sent to the spindle drive controller (such as a frequency converter or servo motor) for real-time spindle speed adjustment. The maximum and minimum preset speed values ​​are set by the operator according to specific circumstances, and will not be elaborated further here. The drilling machine has an initial speed set during operation; the specific value of the initial speed is set by the operator according to specific circumstances.

[0109] Thus, by using the method provided in this embodiment, real-time control of the spindle speed during the hole-opening operation of the hole-opening machine is achieved.

[0110] This embodiment first extracts the trend and residual terms of each sensor data during the hole-opening machine operation. Then, through the collaborative calculation of load factor, vibration factor, and pressure factor, quantified stage parameters and state parameters are generated to accurately identify the three key stages of cutting: early stage, middle stage, and cutting-through transient. In addition, when determining the pressure factor, a medium attenuation coefficient is introduced to dynamically adapt to the pressure attenuation characteristics of different fluids such as natural gas, crude oil, and water, so that the calculated pressure factor can more accurately reflect the actual situation during the hole-opening machine cutting process. Furthermore, by utilizing the specific values ​​of the stage and state parameters, the spindle speed of the hole-opening machine can be adjusted, solving the problems of fuzzy cutting state identification, lagging speed adjustment, and insufficient response to sudden working conditions in hole-opening operations. This improves the control stability of the spindle speed of the hole-opening machine when opening pressurized pipelines, and further enhances the hole-opening effect of pressurized pipelines.

[0111] An embodiment of an intelligent control system for a pressurized pipe tapping machine:

[0112] An embodiment of the present invention provides an intelligent control system for a pressurized pipe tapping machine, which may include a data acquisition module, a first processing module, a second processing module, and an adjustment module;

[0113] The data acquisition module is used to acquire different types of sensor data during the operation of the tapping machine on pressurized pipelines. The sensor data includes the torque data and vibration data of the tapping machine spindle, as well as the pressure data of the medium inside the pipeline.

[0114] The first processing module is used to decompose each type of sensor data to obtain the corresponding residual and trend terms; based on the residual and trend terms of the torque data during operation and the working time of the drilling machine, the load factor at the current moment is obtained; based on the residual terms of the vibration data during operation and the working time of the drilling machine, the vibration factor at the current moment is obtained; based on the attenuation characteristics of the pressure data during operation and the medium attenuation coefficient, the pressure factor at the current moment is obtained; and by combining the load factor, vibration factor, and pressure factor, the stage parameters at the current moment are determined.

[0115] The second processing module is used to obtain the state parameters at the current time based on the discrete distribution of the residual terms corresponding to each type of sensor data in the time neighborhood at the current time.

[0116] The adjustment module is used to adjust the spindle speed of the drilling machine by combining stage parameters and status parameters.

[0117] It should be understood that the intelligent control system and its modules for a pressurized pipe tapping machine provided in this embodiment can be implemented in various ways. For example, in some embodiments, the system and its modules can be implemented by hardware, software, or a combination of software and hardware. The hardware portion can be implemented using dedicated logic; the software portion can be stored in memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated hardware. Those skilled in the art will understand that the above-described methods and systems can be implemented using computer-executable instructions and / or included in processor control code, for example, such code provided on a carrier medium such as a disk, CD, or DVD-ROM, a programmable memory such as read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The system and its modules in this specification can be implemented not only by hardware circuits such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field-programmable gate arrays, programmable logic devices, etc., but also by software executed by various types of processors, or by a combination of the above-described hardware circuits and software (e.g., firmware).

[0118] For more details about the above modules, please refer to other parts of this manual; they will not be repeated here.

[0119] It should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A pressurized pipe tapping machine, comprising a memory and a processor, characterized in that, The processor executes a computer program stored in memory to perform the following steps: Acquire different types of sensor data during the operation of the tapping machine on pressurized pipelines. The sensor data includes torque data, vibration data, and pressure data of the medium inside the pipeline on the tapping machine spindle. The data from each sensor is decomposed to obtain the corresponding residual and trend terms; the load factor at the current moment is obtained based on the residual and trend terms of the torque data during the operation and the operating time of the hole punching machine; the vibration factor at the current moment is obtained based on the residual terms of the vibration data during the operation and the operating time of the hole punching machine. Based on the attenuation characteristics of pressure data during operation and the medium attenuation coefficient, the pressure factor at the current moment is obtained, including: taking the difference between the pressure data at the previous moment and the pressure data at the current moment as the pressure attenuation value at the current moment; and obtaining the pressure factor at the current moment based on the pressure attenuation value and the medium attenuation coefficient, both of which are positively correlated with the pressure factor. By combining the load factor, vibration factor, and pressure factor, the stage parameters at the current moment are determined; Based on the discrete distribution of the residual terms corresponding to each type of sensor data in the time neighborhood of the current moment, the state parameters for the current moment are obtained, including: for any type of sensor data: calculate the standard deviation of the residual terms corresponding to any type of sensor data at all times in the time neighborhood of the current moment, and use it as the discrete characteristic value of any type of sensor data; combine the discrete characteristic values ​​of all types of sensor data to obtain the state parameters for the current moment. The discrete characteristic values ​​and the state parameters are negatively correlated, and the values ​​of the state parameters are within a preset range. The spindle speed of the drilling machine is adjusted by combining stage parameters and status parameters.

2. The pressurized pipe tapping machine according to claim 1, characterized in that, Based on the residual term, trend term, and drilling machine operation time corresponding to the torque data during the operation, the load factor at the current moment is obtained, including: The forward difference sequence of the residual terms corresponding to the torque data of all times in the time neighborhood of the current time is denoted as the first difference sequence; the first standard deviation of all difference values ​​in the first difference sequence is calculated. Based on the difference values ​​in the forward difference sequence of the trend term corresponding to the torque data of all times in the time neighborhood of the current time and the duration between the corresponding time and the current time, the characteristic value of the trend term change is obtained. The load factor at the current moment is obtained based on the duration between the current moment and the initial moment of the hole punching machine operation, the first standard deviation, and the characteristic value of the trend term. The duration between the current moment and the initial moment of the hole punching machine operation and the characteristic value of the trend term are both positively correlated with the load factor, while the first standard deviation is negatively correlated with the load factor.

3. A pressurized pipe tapping machine according to claim 2, characterized in that, Based on the difference values ​​in the forward difference sequence of the trend term corresponding to the torque data of all times within the time neighborhood of the current time, and the duration between the corresponding times and the current time, the characteristic values ​​of the trend term change are obtained, including: The duration between the time corresponding to each difference value in the forward difference sequence of the trend term corresponding to the torque data of all times in the time neighborhood of the current time and the current time is denoted as the first time interval of the corresponding time. The ratio between the difference value in the forward difference sequence of the trend term corresponding to the torque data of all times in the time neighborhood of the current time and the first time interval of the corresponding time is used as the first feature value corresponding to each difference value in the forward difference sequence of the trend term corresponding to the torque data of all times in the time neighborhood of the current time. The sum of the first eigenvalues ​​corresponding to all difference values ​​in the forward difference sequence of the trend term corresponding to the torque data of all times in the time neighborhood of the current time is determined as the trend term change eigenvalue.

4. The pressurized pipe tapping machine according to claim 1, characterized in that, Based on the residual terms corresponding to the vibration data during the operation and the operating time of the hole punching machine, the vibration factor at the current moment is obtained, including: The forward difference sequence of the residual terms corresponding to the vibration data of all times in the time neighborhood of the current time is denoted as the second difference sequence; the second standard deviation of all difference values ​​in the second difference sequence is calculated. The time weight is obtained by using the residual terms corresponding to the vibration data of all times in the time neighborhood of the current time, and the duration between the current time and all times in the time neighborhood of the current time. The vibration factor at the current moment is obtained based on the duration between the current moment and the initial moment of the hole punching machine operation, the second standard deviation, and the time weight. The duration between the current moment and the initial moment of the hole punching machine operation is positively correlated with the vibration factor, while the second standard deviation is negatively correlated with the vibration factor.

5. A pressurized pipe tapping machine according to claim 4, characterized in that, The time weights are obtained based on the residual terms corresponding to the vibration data of all times within the current time's time neighborhood, and the duration between the current time and all times within the current time's time neighborhood. These weights include: For any time in the time neighborhood of the current time: the product of the absolute value of the residual term corresponding to the vibration data at any time and the time interval between any time and the current time is taken as the second characteristic value of any time. The average of the second feature values ​​of all times within the time neighborhood of the current time is used as the time weight.

6. A pressurized pipe tapping machine according to claim 1, characterized in that, By combining load factor, vibration factor, and pressure factor, the stage parameters for the current moment are determined, including; Calculate the sum of the load factor, vibration factor, and pressure factor at the current moment; The sum is mapped to a preset interval to obtain the stage parameters at the current time. The preset interval is (-1, 1).

7. A pressurized pipe tapping machine according to claim 1, characterized in that, The spindle speed of the drilling machine is adjusted based on the combined stage parameters and status parameters, including: When the stage parameter is greater than 0, calculate the first sum of the stage parameter and the state parameter; if the state parameter is also greater than 0, use the negative correlation normalized result of the first sum as the control function value; if the state parameter is less than 0, use the sum of the constant 1 and the state parameter as the control function value. When the stage parameter is less than 0, if the state parameter is greater than 0, calculate the second sum of the absolute value of the stage parameter and the state parameter, and use half of the second sum plus the constant 1 as the control function value; if the state parameter is less than 0, record the absolute value of the sum of the stage parameter and the state parameter as the first absolute value, calculate the third sum of the constant 1 and the first absolute value, and use the reciprocal of the third sum as the control function value. The control function value is smoothed using the exponentially weighted moving average method to obtain the smoothed control function value; The product of the smoothed control function value and the current spindle speed of the drilling machine is determined as the adjusted spindle speed of the drilling machine.

8. An intelligent control system for a pressurized pipe tapping machine, characterized in that, The system includes: The data acquisition module is used to acquire different types of sensor data during the operation of the tapping machine on pressurized pipelines. The sensor data includes the torque data and vibration data of the tapping machine spindle, as well as the pressure data of the medium inside the pipeline. The first processing module is used to decompose each type of sensor data to obtain the corresponding residual and trend terms; based on the residual and trend terms of the torque data during operation and the working time of the drilling machine, the load factor at the current moment is obtained; based on the residual terms of the vibration data during operation and the working time of the drilling machine, the vibration factor at the current moment is obtained; based on the attenuation characteristics of the pressure data during operation and the medium attenuation coefficient, the pressure factor at the current moment is obtained; and by combining the load factor, vibration factor, and pressure factor, the stage parameters at the current moment are determined. The second processing module is used to obtain the state parameters at the current time based on the discrete distribution of the residual terms corresponding to each type of sensor data in the time neighborhood at the current time. The adjustment module is used to adjust the spindle speed of the drilling machine by combining stage parameters and status parameters; Based on the attenuation characteristics of pressure data during operation and the medium attenuation coefficient, the pressure factor at the current moment is obtained, including: The difference between the pressure data of the previous time and the pressure data of the current time is taken as the pressure decay value of the current time. The pressure factor of the current time is obtained based on the pressure decay value and the medium decay coefficient. Both the pressure decay value and the medium decay coefficient are positively correlated with the pressure factor. Based on the discrete distribution of the residual terms corresponding to each sensor data within the current time neighborhood, the state parameters for the current time are obtained, including: For any type of sensor data: calculate the standard deviation of the residual term corresponding to any type of sensor data at all times within the time neighborhood of the current time, and use it as the discrete characteristic value of any type of sensor data; combine the discrete characteristic values ​​of all types of sensor data to obtain the state parameter at the current time. The discrete characteristic value and the state parameter are negatively correlated, and the value of the state parameter is within a preset interval.

Images