Thermal washing paraffin removal and plug removal process for coiled tubing of oil and gas well

Abstract

The invention relates to the field of petroleum engineering, and provides an oil and gas well coiled tubing thermal washing paraffin removal and plug removal process which comprises the following steps: firstly, heating well washing fluid through a hot oil vehicle, then injecting the heated well washing fluid into a coiled tubing operation machine by using a pump truck, then feeding the well washing fluid into a well through a coiled tubing, and circularly flowing in a circulating channel in the well, in the circulating process of the flushing fluid, water horsepower impact, heat exchange and mechanical crushing effects generated by the flushing fluid are utilized to remove or crush blockages in a well, and finally the decomposed blockages return to the ground together with the flushing fluid. In this way, the paraffin removal and plug removal effects in the oil and gas well can be improved, and effective maintenance of the oil and gas well can be better achieved.

Description

Technical Field

[0001] The present application relates to the field of petroleum engineering, and more specifically, to a process for hot-washing, wax-removing and plugging-removing of coiled tubing in oil and gas wells. Background Art

[0002] Wax removal and blockage removal are important aspects of oil and gas well management. During crude oil production, due to the decrease in temperature and the escape of light hydrocarbons, wax precipitates and adsorbs on the oil pipe wall, casing wall and other oil production equipment, resulting in reduced production and even blockage of the production string, which is one of the prominent problems affecting the high and stable production of oil and gas wells.

[0003] However, traditional oil and gas well mechanical wax cleaning, chemical wax melting, and squeezing hot oil wax melting operations are risky, wax cleaning is not thorough, and cannot solve the problem of production tubing being blocked by wax and other blockages. Specifically, although mechanical wax cleaning can directly remove some wax deposits, it has limited effect on tubing that is already severely blocked, and the operation is complicated and labor-intensive. Chemical wax melting dissolves wax by injecting chemical solvents, but chemical reagents are expensive, have a certain impact on the environment, and cannot completely solve the blockage problem. Squeezing hot oil wax melting has high construction pressure, high risks, low success rate of unblocking, large workload, incomplete wax cleaning, and poor results.

[0004] Therefore, an optimized solution for hot washing, wax removal and plugging removal of coiled tubing in oil and gas wells is desired. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present application provides a process for hot-washing, wax-removing and plugging-removing of coiled tubing in oil and gas wells.

[0006] According to one aspect of the present application, a process for hot washing, wax removal and blockage removal of coiled tubing in oil and gas wells is provided, which comprises: heating the well washing fluid by a hot oil truck to obtain heated well washing fluid; injecting the heated well washing fluid into a coiled tubing operating machine by a pump truck; the coiled tubing operating machine lowering the well washing fluid into a well through a coiled tubing, wherein the well has a well washing fluid circulation channel, and the well washing fluid can circulate in the well through the well washing fluid circulation channel to utilize the water horsepower impact, heat energy exchange and mechanical crushing generated by the well washing fluid during the circulation process to remove or crush the blockage, including: real-time monitoring of the state parameters of the well washing fluid circulating in the well washing fluid circulation channel to obtain a time queue of the state parameters, wherein the state parameters include temperature value, pressure value and flow value; sorting the time queue of the state parameters to obtain the time queue of temperature value, the time queue of pressure value and the time queue of flow value; performing sequence encoding on the time queue of temperature value and the time queue of flow value to obtain temperature time series characteristics and flow time series characteristics; performing temperature-flow time series dual-view response correlation analysis on the temperature time series characteristics and the flow time series characteristics to obtain temperature-flow time series interactive response coding characteristics; performing pressure inference on the temperature-flow time series interactive response coding characteristics to obtain the time queue of inferred pressure values; determining whether there is a circulation abnormality based on the time queue of pressure value and the time queue of inferred pressure value; the decomposed blockage is returned to the ground together with the well washing fluid.

[0007] The present application has significant technical effects due to the adoption of the above technical solutions: the present application provides a hot-washing, wax-removing and plugging-removing process for coiled tubing in oil and gas wells, which first heats the well-washing fluid by a hot oil truck, then uses a pump truck to inject the heated well-washing fluid into a coiled tubing operation machine, and then the well-washing fluid is sent into the well through the coiled tubing, and circulates in the circulation channel in the well. During the circulation of the well-washing fluid, the water horsepower impact, heat exchange and mechanical crushing effect generated by the well-washing fluid are used to remove or crush the blockage in the well, and finally the decomposed blockage is returned to the ground together with the well-washing fluid. In this way, the effect of wax-removing and plugging-removing in oil and gas wells can be improved, which is conducive to better effective maintenance of oil and gas wells. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0009] Figure 1 This is a flow chart of a hot-washing, wax-removing and plugging-removing process for coiled tubing in oil and gas wells according to an embodiment of the present application.

[0010] Figure 2 This is a flow chart of step S3 in the process for hot washing, dewaxing and unblocking coiled tubing in oil and gas wells according to an embodiment of the present application.

[0011] Figure 3 This is a flow chart of step S34 in the process for hot washing, dewaxing and unblocking coiled tubing in oil and gas wells according to an embodiment of the present application.

[0012] Figure 4 This is a flow chart of step S36 in the process for hot washing, dewaxing and unblocking coiled tubing in oil and gas wells according to an embodiment of the present application. DETAILED DESCRIPTION

[0013] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0014] Wax removal and blockage removal are key tasks in oil and gas well management. During crude oil production, due to temperature drop and volatilization of light hydrocarbons, wax will gradually precipitate and adhere to the oil pipe wall, casing wall and other oil production equipment, causing a decrease in production and even causing blockage of the production string. This phenomenon has become one of the main problems restricting the efficient and stable production of oil and gas wells.

[0015] Existing wax removal technologies mainly include mechanical wax removal, chemical wax melting, and hot oil extrusion wax melting. However, these traditional methods have great limitations in practical applications and are difficult to completely solve the problem of pipe blockage. Specifically, although mechanical wax removal can directly remove some wax deposits, its effect is limited for severely blocked pipes. At the same time, the operation is complicated and the workload is large. Chemical wax melting dissolves wax by injecting chemical reagents. However, this method is costly, may have adverse effects on the environment, and is not ideal when dealing with stubborn blockages. Although hot oil extrusion wax melting can melt wax at high temperatures, the pressure during the construction process is high, there are certain safety risks, and the success rate of unblocking is low, and the cleaning effect is still not thorough enough.

[0016] Based on this, this application proposes a hot-washing wax removal and unblocking process for coiled tubing in oil and gas wells, which significantly improves the effect and safety of wax removal and unblocking by introducing advanced technology and optimized operation procedures, and reduces construction risks and maintenance costs. Specifically, Figure 1 This is a flow chart of a hot-washing, wax-removing and plugging-removing process for coiled tubing in oil and gas wells according to an embodiment of the present application. Figure 1As shown, according to the embodiment of the present application, the process for hot washing, dewaxing and unblocking of coiled tubing in oil and gas wells comprises: S1, heating the well washing fluid by a hot oil truck to obtain heated well washing fluid; S2, injecting the heated well washing fluid into a coiled tubing operating machine by a pump truck; S3, the coiled tubing operating machine lowers the well washing fluid into a well through a coiled tubing, the well having a well washing fluid circulation channel, and the well washing fluid can circulate in the well through the well washing fluid circulation channel to remove or break up blockages by utilizing the water horsepower impact, heat energy exchange and mechanical crushing generated by the well washing fluid during the circulation process; S4, the decomposed blockages are returned to the ground together with the well washing fluid.

[0017] In step S1, the well washing fluid is heated by a hot oil truck to obtain heated well washing fluid. It should be understood that wax will precipitate from crude oil under low temperature conditions and adhere to oil production equipment such as the oil pipe wall and casing wall, and in severe cases will block the production tubing. By heating the well washing fluid, the temperature of the well washing fluid can be increased, and the heat energy can be used to melt the wax blocks attached to the surface of the equipment, thereby achieving the purpose of wax removal. Compared with the traditional hot oil extrusion wax melting operation, this method reduces construction pressure, reduces operational risks, and improves wax removal efficiency and thoroughness. It is worth noting that according to different operating conditions and blockage conditions, a suitable well washing fluid type (such as water or crude oil) can be selected to optimize operating efficiency and effect.

[0018] In step S2, the pump truck injects the heated well-washing fluid into the coiled tubing operation machine. It should be understood that the well-washing fluid cannot circulate in the well by itself and play a role in clearing wax and unblocking if it is only heated. The pump truck can provide strong power to inject the heated well-washing fluid into the coiled tubing operation machine, push the well-washing fluid into the coiled tubing in the well, thereby establishing a well-washing fluid circulation channel in the well, allowing the well-washing fluid to circulate continuously. In short, only when the well-washing fluid circulates continuously can it continuously contact and clean the wax and blockages on the tubing wall and casing wall to achieve wax clearing and unblocking. Moreover, different oil and gas wells have different conditions and different requirements for the flow rate and pressure of the well-washing fluid. The pump truck can accurately adjust the flow rate and pressure of the well-washing fluid injected into the coiled tubing operation machine according to actual needs. When dealing with a severely blocked well section, the flow rate and pressure can be increased to enhance the impact force of the well-washing fluid and better break and remove the blockage; for relatively minor blockages or areas with more complex well conditions, the flow rate and pressure can be appropriately reduced to avoid damage to the well structure.

[0019] In step S3, the coiled tubing operation machine lowers the well-washing fluid into the well through the coiled tubing. The well has a well-washing fluid circulation channel. The well-washing fluid can circulate in the well through the well-washing fluid circulation channel to remove or break the blockage by utilizing the water horsepower impact, heat energy exchange and mechanical crushing generated by the well-washing fluid during the circulation process. It should be understood that the well-washing fluid has a high temperature after being heated, and exchanges heat energy with the wax attached to the oil pipe wall, casing wall and other oil production equipment during the circulation process. The heat transfer increases the temperature of the wax, and after reaching the melting point, it changes from solid to liquid, thereby weakening the adhesion to the pipe wall. At the same time, the water horsepower impact continuously acts on the melted wax, peeling it off the pipe wall, so that the originally attached wax gradually detaches from the equipment surface, creating conditions for the subsequent well-washing fluid to be taken out of the wellhead. Since the coiled tubing can penetrate into different depths and positions in the well, the well-washing fluid can flow in the entire well-washing fluid circulation channel after entering the well through the coiled tubing. This allows the well-washing fluid to reach every corner of the well, including some parts that are difficult to reach with conventional wax removal methods, ensuring that every part of the pipe string can be cleaned, achieving comprehensive wax removal, and avoiding wax residue in local areas, effectively solving the problem of incomplete wax removal by traditional wax removal methods. For blockages in the well, such as sand blockages, combustible ice blockages, etc., the water horsepower impact and mechanical crushing effect generated by the circulation of the well-washing fluid play a key role. The water horsepower impact can exert a strong external force on the blockage to loosen and break it. When the strength of the blockage is large, a combination of continuous tubing + screw drill + crushing tool can also be used to further enhance the mechanical crushing ability and break large pieces of blockage into small pieces. These crushed blockages will return to the ground with the circulation of the well-washing fluid, thereby removing the blockage of the pipe string and restoring the normal production of the oil and gas well. That is, the present application can more thoroughly remove or crush the blockage by combining the three mechanisms of water horsepower impact, heat energy exchange and mechanical crushing, significantly improve the wax removal effect, and effectively restore the production capacity of the oil well. It should be noted that the entire process does not rely on chemical reagents, reduces the impact on the environment, and is fully in line with the concept of modern green mining.

[0020] It is particularly important to detect circulation anomalies in the step where the well-washing fluid circulates in the well through the well-washing fluid circulation channel to remove or break the blockage by water horsepower impact, heat exchange and mechanical crushing. It can ensure that the well-washing fluid effectively plays the role of water horsepower impact, heat exchange and mechanical crushing, avoid problems such as failure of wax removal and blockage removal, equipment damage and environmental pollution, and ensure that the oil and gas well washing operation is carried out efficiently, safely and environmentally friendly. However, traditional circulation anomaly detection methods have limitations. They only focus on a few parameters, such as pressure thresholds, and it is difficult to comprehensively analyze multi-parameter data such as temperature, pressure and flow. For example, the pressure can be easily misjudged as normal after it briefly exceeds the threshold and returns to normal, while ignoring the correlation between pressure fluctuations and temperature and flow. In addition, traditional methods rely on fixed thresholds and simple rules, and cannot automatically adjust the judgment criteria according to complex working conditions. They are difficult to adapt to changes in different formation temperatures and are prone to missed judgments or misjudgments.

[0021] Based on this, in the well-washing fluid that can circulate in the well through the well-washing fluid circulation channel to utilize the water horsepower impact, heat energy exchange and mechanical crushing generated by the well-washing fluid during the circulation process to remove or crush the blockage, the technical concept of the present application is to monitor the state parameters of the well-washing fluid circulating in the well-washing fluid circulation channel in real time to obtain the time queue of the state parameters (temperature value, pressure value and flow value), and use the data analysis and processing technology based on deep learning to sort the temperature value, pressure value and flow value to obtain the time queue of the temperature value, the time queue of the pressure value and the time queue of the flow value. Then, the time queues of the temperature value and the flow value are respectively encoded with time series features, and the encoded temperature time series features and flow time series features are associated with dual-view responses, so as to intelligently judge whether there is a circulation abnormality based on the deviation between the time queue of the inferred pressure value and the time queue of the pressure value obtained by pressure inference according to the temperature-flow time series interaction representation. The present application not only focuses on the pressure threshold, but also monitors multi-parameter data such as temperature, pressure and flow at the same time to comprehensively reflect the dynamic changes in the circulation process of the well-washing fluid. Moreover, the judgment criteria can be adjusted dynamically according to the actual situation, which is conducive to improving the accuracy of anomaly detection and ensuring that anomalies can be effectively detected under various conditions.

[0022] Figure 2 This is a flow chart of step S3 in the hot-washing, wax-removing and plugging-removing process for coiled tubing in oil and gas wells according to an embodiment of the present application. Figure 2As shown, the step S3 includes: S31, real-time monitoring of the state parameters of the well washing fluid circulating in the well washing fluid circulation channel to obtain a time queue of the state parameters, wherein the state parameters include a temperature value, a pressure value and a flow value; S32, data sorting of the time queue of the state parameters to obtain a time queue of the temperature value, a time queue of the pressure value and a time queue of the flow value; S33, sequence encoding the time queue of the temperature value and the time queue of the flow value to obtain a temperature time series feature and a flow time series feature; S34, performing a temperature-flow time series dual-perspective response correlation analysis on the temperature time series feature and the flow time series feature to obtain a temperature-flow time series interactive response coding feature; S35, performing pressure inference on the temperature-flow time series interactive response coding feature to obtain a time queue of inferred pressure values; S36, determining whether there is a circulation abnormality based on the time queue of the pressure value and the time queue of the inferred pressure value.

[0023] In step S31, the state parameters of the well washing fluid circulating in the well washing fluid circulation channel are monitored in real time to obtain a time queue of the state parameters, and the state parameters include temperature value, pressure value and flow value. It should be understood that the temperature value can intuitively show the heat carried by the well washing fluid. One of the main tasks of the well washing fluid is to melt wax and other blockages through heat exchange. If the temperature value is abnormally reduced, it may mean that the heating system fails, resulting in the well washing fluid being unable to effectively melt the blockage, and the wax removal and unblocking effect is greatly reduced; the pressure value reflects the power of the well washing fluid during the circulation process. Sufficient pressure is the key to achieving water horsepower impact and mechanical crushing. Insufficient pressure will weaken the impact force of the well washing fluid and make it difficult to break the blockage; the flow value indicates the circulation speed of the well washing fluid. The appropriate flow rate can ensure that the well washing fluid fully contacts the pipe string within a unit time, taking away the melted wax and broken blockages. Abnormal flow may cause blockages to accumulate, affecting the wax removal and unblocking effect. Relying on any one parameter alone (such as only focusing on the pressure threshold) may lead to misjudgment of the circulation state. For example, a short pressure fluctuation may not cause an immediate problem, but if combined with a drop in temperature and a reduction in flow, it may be due to some kind of blockage that causes the entire cycle to become abnormal. That is, this application can more accurately identify abnormal patterns in the circulation of well washing fluids through continuous monitoring and in-depth correlation analysis of key parameters such as temperature, pressure, and flow, thereby effectively improving the reliability of circulation anomaly detection, which is conducive to ensuring the smooth progress of well washing operations.

[0024] The following is a detailed description of a specific implementation process of "real-time monitoring of the state parameters of the well-washing fluid circulating in the well-washing fluid circulation channel to obtain the time queue of the state parameters, wherein the state parameters include temperature value, pressure value and flow value": First, the selection and installation of monitoring equipment. In terms of temperature monitoring, platinum resistance temperature sensors can be selected, which have the characteristics of high temperature resistance, corrosion resistance and high precision. Installing a temperature sensor near the wellhead of the coiled tubing can grasp the initial temperature of the well-washing fluid before entering the well in real time. At the same time, according to the specific structure of the well and the area where there may be a risk of blockage, the temperature sensors are reasonably arranged at key nodes at different depths in the well to ensure that the temperature changes of the well-washing fluid at different positions can be fully and accurately measured. During installation, the sensor probe must be fully in contact with the well-washing fluid to ensure that an accurate temperature value is obtained. In the pressure monitoring link, strain gauge pressure sensors are widely used because they can adapt to the high-pressure environment downhole and have good stability. On the coiled tubing, the installation position should be carefully selected to ensure that the sensor is directly connected to the well-washing fluid, and full consideration should be given to avoiding the sensor from being affected by mechanical collision and blockage. Pressure sensors are installed at key locations where pressure changes are likely to occur at the wellhead and underground, such as near pipe sections that may be blocked. This allows real-time and accurate monitoring of pressure fluctuations during the circulation of the well-washing fluid, providing an important basis for judging the circulation status. Flow monitoring is also indispensable for well-washing operations. According to the properties and flow range of the well-washing fluid, an electromagnetic flowmeter or an ultrasonic flowmeter should be reasonably selected. If the well-washing fluid is conductive, the electromagnetic flowmeter can accurately measure the flow rate based on its principle; for non-conductive well-washing fluid, the ultrasonic flowmeter can play its advantages. When installing the flow sensor, a straight section of the continuous tubing should be selected, because in the straight section, the flow state of the well-washing fluid is relatively stable, which can effectively avoid the adverse effects of pipe bending or diameter change on the measurement accuracy, thereby ensuring the accuracy of the flow measurement.

[0025] Next, it is necessary to determine the appropriate frequency of data collection. In the early stage of the well washing operation, since the circulation state of the well washing fluid is in an unstable stage, various parameters change rapidly and the trend is not obvious. In order to fully and carefully understand the startup of the circulation and the trend of parameter changes, it is necessary to set a higher data collection frequency, such as collecting data once per second. In this way, rich initial data can be obtained to provide sufficient information for subsequent analysis. As the well washing operation gradually stabilizes, if the changes in various parameters are relatively stable, the collection frequency can be appropriately reduced to collect data every 5-10 seconds to balance the amount of data and data processing costs. However, once an abnormal situation occurs, such as sudden pressure fluctuations, sharp changes in temperature, etc., the system should have the function of automatically increasing the collection frequency, so as to capture abnormal parameter changes more timely and accurately, and provide strong support for timely discovery and resolution of problems.

[0026] The transmission and storage of data are important links in the entire monitoring process. In terms of data transmission, wired or wireless transmission methods can be selected according to actual conditions. In wired transmission, armored cables are commonly used due to their good protection performance. By connecting the sensor to the ground data acquisition station with armored cables, signal interference can be effectively avoided, ensuring the stability and reliability of data transmission. However, in some special well site environments, such as areas with complex terrain, difficult cable laying or high costs, wireless transmission technology shows its advantages. Wireless modules based on low-power, long-distance transmission protocols such as ZigBee and LoRa can send the data collected by the sensor to the ground receiving device to realize wireless transmission of data.

[0027] In terms of data storage, a special database needs to be established in the ground data processing system to store the collected state parameter data. According to the characteristics of the data and the subsequent processing requirements, a relational database (such as MySQL) or a time series database (such as InfluxDB) can be selected. These databases can store the collected temperature values, pressure values, and flow values ​​in the order of collection time in the form of a time queue, which can provide reliable raw data support for subsequent data collation, analysis, and model processing.

[0028] In order to ensure the accuracy and reliability of data, data verification and preprocessing are essential steps. During the data collection and transmission process, data errors or abnormal values ​​may occur due to various factors. Therefore, the collected data needs to be strictly verified. The rationality of the data can be judged by setting a reasonable threshold range, such as determining the normal range of temperature values, the safe range of pressure values, and the reasonable fluctuation range of flow values ​​based on the actual experience of well washing operations and theoretical calculations. For data that exceeds the threshold, it should be clearly marked and further verified for its accuracy to ensure that the data is true and reliable.

[0029] In the data preprocessing stage, missing values ​​and outliers are mainly processed. For a small number of missing values, interpolation can be used to supplement them. The linear interpolation method estimates the missing values ​​through the linear relationship between known data points, and the Lagrange interpolation rule uses a polynomial function to fit the data to obtain the approximate value of the missing value. For outliers, they should be processed according to the characteristics of the data and the actual situation. If the outlier is caused by measurement error, it can be corrected; if its rationality cannot be determined and it has a great impact on subsequent analysis, it can be considered to be eliminated. At the same time, in order to facilitate subsequent data analysis and model processing, it is also necessary to normalize the data, convert data of different physical dimensions into a unified numerical range, and eliminate the impact of dimensional differences on the analysis results.

[0030] In step S32, the time queue of the state parameters is sorted to obtain the time queue of temperature values, the time queue of pressure values, and the time queue of flow values. Accordingly, considering that temperature, pressure, and flow are parameters of different physical properties, the state of the well washing fluid reflected by them and the mechanism of their influence on the paraffin removal and unblocking process are different. Temperature mainly involves heat energy transfer and wax dissolution, pressure is related to the integrity of the circulation system and water horsepower impact, and flow focuses on the circulation efficiency of the well washing fluid and the carrying capacity of blockages. Therefore, in order to be able to analyze each parameter in a targeted manner to capture and mine the time series characteristics of each parameter in the time dimension, in the technical solution of the present application, it is necessary to sort the time queue of the state parameters to obtain the time queue of temperature values, the time queue of pressure values, and the time queue of flow values.

[0031] In step S33, the time queue of the temperature value and the time queue of the flow value are sequence-encoded to obtain the temperature time series feature and the flow time series feature. Specifically, in the embodiment of the present application, the step S33 includes: using a sequence encoder to sequence-encode the time queue of the temperature value and the time queue of the flow value respectively to obtain the temperature time series feature implicit encoding vector as the temperature time series feature and the flow time series feature implicit encoding vector as the flow time series feature. In particular, the sequence encoder is a sequence encoder based on a bidirectional gated cyclic unit. It should be understood that the sequence data of the temperature value and the flow value changing over time contains rich information about the well washing process, which is crucial to understanding the dynamic changes of the well washing fluid during the circulation process. Based on this, the present application performs sequence encoding on the time queue of the temperature value and the time queue of the flow value to mine the hidden features of the data in the time dimension, such as trend, periodicity, seasonality, etc., to obtain the temperature time series feature implicit encoding vector and the flow time series feature implicit encoding vector, so as to better understand the dynamic changes of the well washing process. In particular, in a specific embodiment of the present application, the time queue of the temperature value and the time queue of the flow value are respectively sequence-encoded by using a sequence encoder based on a bidirectional gated cyclic unit to simultaneously process the forward and backward time series information, thereby obtaining an implicit encoding vector of the temperature time series feature and an implicit encoding vector of the flow time series feature. A person skilled in the art should know that the bidirectional gated cyclic unit is an improved recurrent neural network (RNN) structure that combines the advantages of the gated cyclic unit and bidirectional processing. It enhances the ability to understand time dependencies by simultaneously processing the forward and backward information of time series data. The change of temperature and flow over time is a complex dynamic process. Not only is the current value affected by the past value, but it may also be related to the future change trend. For example, in the process of hot washing and paraffin removal of oil and gas wells, the temperature rise at a certain moment may be because more high-temperature well washing fluid is about to be injected (future information) later, and it is also related to the temperature change of the previous well washing fluid (past information). The bidirectional gated cyclic unit can process the time series data of temperature and flow from both the forward and reverse directions, and dig out these nonlinear relationships hidden in the data, thereby fully characterizing this complex time-dependent feature.

[0032] In step S34, a temperature-flow time series dual-view response correlation analysis is performed on the temperature time series characteristics and the flow time series characteristics to obtain a temperature-flow time series interactive response coding feature. Specifically, Figure 3 This is a flow chart of step S34 in the hot-washing, wax-removing and plugging-removing process of coiled tubing in oil and gas wells according to an embodiment of the present application. Figure 3As shown, the step S34 includes: S341, performing homography projection transformation on the temperature time series feature implicit coding vector and the flow time series feature implicit coding vector to obtain the temperature time series feature homography projection coding vector and the flow time series feature homography projection coding vector; S342, calculating the dual-view temperature-flow time series feature attention score field between the temperature time series feature homography projection coding vector and the flow time series feature homography projection coding vector; S343, based on the dual-view temperature-flow time series feature attention score field, modulating the temperature time series feature homography projection coding vector and the flow time series feature homography projection coding vector to obtain the temperature time series feature homography projection attention modulation coding vector and the flow time series feature homography projection attention modulation coding vector; S344, calculating the temperature-flow time series interaction response coding vector obtained by dividing the temperature time series feature homography projection attention modulation coding vector and the flow time series feature homography projection attention modulation coding vector by the position point as the temperature-flow time series interaction response coding feature.

[0033] It should be understood that in the process of hot washing, wax removal and blockage removal, temperature and flow rate do not exist independently, but influence each other and are closely related. For example, changes in temperature will affect the viscosity of the well washing fluid, thereby affecting its fluidity, and ultimately leading to changes in flow rate; conversely, the size of the flow rate will also affect the transfer and distribution of heat in the wellbore, thereby affecting the temperature. Therefore, in order to capture and tap into this complex internal connection and fully understand the interaction mechanism between parameters, this application introduces a temperature-flow time series dual-perspective response association analysis method to interactively respond to the temperature time series characteristics and the flow time series characteristics to obtain the temperature-flow time series interactive response encoding characteristics. In particular, this method can fuse the information of the two perspectives, enhance the model's ability to understand multidimensional time series data, and provide a richer semantic representation, so that the obtained representation not only contains the change law of each parameter, but also reflects the new information generated by the interaction between the two, thereby more comprehensively describing the physical phenomena in the well washing process.

[0034] Specifically, in the embodiment of the present application, the step S341 includes: mapping the temperature time series feature implicit coding vector through the temperature time series feature mapping homography matrix to obtain the temperature time series feature homography projection coding vector. This process can be expressed as: ;in, is the temperature time series feature implicit encoding vector, is the temperature time series feature mapping homography matrix, It is the homography projection encoding vector of temperature time series features.

[0035] The implicit coding vector of the traffic time series feature is mapped by the traffic time series feature mapping homography matrix to obtain the homography projection coding vector of the traffic time series feature. This process can be expressed as: ;in, is the implicit coding vector of the traffic time series characteristics, is the homography matrix of traffic time series feature mapping, It is the homography projection encoding vector of traffic time series features.

[0036] It should be understood that the implicit encoding vector of the temperature time series feature and the implicit encoding vector of the flow time series feature are subjected to homography projection transformation, and the implicit encoding vector of the temperature time series feature and the implicit encoding vector of the flow time series feature can be mapped to a new feature space. In the new feature space, the temperature and flow characteristics can be observed from different perspectives, which allows the model to discover some information that is difficult to detect in the original space, which helps to better understand the essence of physical phenomena in the well washing process. Moreover, the homography projection transformation can ensure that the relative position relationship of the temperature and flow time series characteristics is maintained in the new feature space. This means that in the original feature space, key information such as the correlation, sequence and relative importance between the temperature and flow characteristics will not be lost. For example, in the process of hot washing, wax removal and plugging, if the temperature increase is always accompanied by a certain change in flow, this correlation implicit in the original vector can still be reflected after the projection transformation. This can provide a stable foundation for the subsequent in-depth analysis of the relationship between the two and ensure the reliability of the analysis results.

[0037] Specifically, in the embodiment of the present application, the step S342 includes: calculating the forward temperature-flow time series feature attention score field of the temperature time series feature homography projection coding vector relative to the flow time series feature homography projection coding vector, and the process can be expressed as: ;in, is the homography projection encoding vector of temperature time series features, is the homography projection encoding vector of traffic time series features yes The transposed vector of is matrix multiplication, yes Length, It is the forward temperature-flow time series feature attention score field.

[0038] The inverse temperature-flow time series feature attention score field of the flow time series feature homography projection coding vector relative to the temperature time series feature homography projection coding vector is calculated. The process can be expressed as: ;in, is the homography projection encoding vector of temperature time series features, is the homography projection coding vector of traffic time series features, yes The transposed vector of is matrix multiplication, yes Length, It is the inverse temperature-flow time series feature attention score field.

[0039] Based on the forward temperature-flow time series feature attention score field and the reverse temperature-flow time series feature attention score field, the dual-view temperature-flow time series feature attention score field is obtained. This process can be expressed as: ;in, is the forward temperature-flow time series characteristic attention score field, is the inverse temperature-flow time series feature attention score field, is the feature concatenation operation, is a convolutional code with a convolution kernel of 3×3. It is the dual-view temperature-flow time series feature attention score field.

[0040] Accordingly, considering that in the process of hot washing, wax removal and plugging removal, temperature and flow rate are key factors that affect each other, but the relationship between them is complex and nonlinear. Calculating the forward temperature-flow time series feature attention score field can accurately quantify the degree of correlation between the temperature time series feature homography projection coding vector and the flow time series feature homography projection coding vector. Through this quantification method, it is possible to clearly understand which parts of the temperature feature are more critical to the entire well washing process under the background of flow characteristics, thereby digging out the deep intrinsic connection between the two. That is, by obtaining the forward temperature-flow time series feature attention score field, the model can have a deeper understanding of the complex interaction between temperature and flow rate. This understanding is not only limited to the surface change trend, but also can dig out the causal relationship and synergistic effect hidden behind the data. When analyzing the circulation process of the well washing fluid, the model can clearly distinguish which temperature changes are caused by flow changes and how these changes affect the wax removal and plugging removal effect based on the forward attention score field, thereby improving the level of cognition of the entire well washing process. Moreover, in the actual monitoring and data processing process, there will inevitably be some noise information, which may interfere with the judgment of the true relationship between temperature and flow rate. Calculating the positive attention score field is equivalent to setting up a filter, which can filter out those temperature feature parts that are weakly correlated with the flow feature vector, that is, irrelevant noise information, thereby improving the quality of the data and the accuracy of the analysis.

[0041] It should be understood that the forward temperature-flow time series feature attention score field mainly focuses on the importance distribution of the temperature time series feature in the context of the flow time series feature, but this may not fully reflect the relationship between the two feature vectors. In the process of hot washing, wax removal and plugging, the impact of flow change on temperature and the impact of temperature change on flow may be different, and the interaction between the two is relatively complex. By calculating the reverse temperature-flow time series feature attention score field, it is possible to supplement the information that the forward attention score field fails to cover from the perspective of the importance distribution of flow features in the context of temperature features, so as to have a more comprehensive understanding of the interaction between temperature and flow. In other words, the reverse temperature-flow time series feature attention score field provides an opportunity to understand the relationship between temperature and flow features from the opposite direction. Through reverse analysis, it is possible to dig out the interaction details that may be overlooked in the forward analysis and gain a deeper insight into the intrinsic connection between the two features. For example, during the well washing process, the change in flow rate may affect the distribution and change of temperature in a special way. This influence may not be obvious in the forward analysis, but it can be clearly presented through the calculation of the reverse attention score field.

[0042] Accordingly, when analyzing the relationship between temperature and flow, it is necessary to comprehensively consider the mutual influence between the two eigenvectors to prevent over-emphasis on the role of a certain eigenvector. If only relying on the forward temperature-flow time series feature attention score field or the reverse temperature-flow time series feature attention score field, the final analysis result may over-emphasize the influence of one feature on another feature, while ignoring the role of the other direction. The construction of the dual-view temperature-flow time series feature attention score field can balance this influence and ensure that the contribution of the two eigenvectors is fully reflected in the interactive response coding, thereby more accurately describing the essential connection behind the physical phenomena in the well washing process.

[0043] Specifically, in the embodiment of the present application, the step S343 includes: multiplying the dual-view temperature-flow time series feature attention score field with the temperature time series feature homography projection coding vector and the flow time series feature homography projection coding vector to obtain the temperature time series feature homography projection attention modulation coding vector and the flow time series feature homography projection attention modulation coding vector. The above process can be expressed as: ;in, is the homography projection encoding vector of temperature time series features, is the homography projection coding vector of traffic time series features, is the dual-view temperature-flow time series feature attention score field, is matrix multiplication, is the temperature time series feature homography projection attention modulation encoding vector, is the homography projection attention modulation encoding vector of traffic time series features.

[0044] It should be understood that based on the dual-view temperature-flow time series feature attention score field, the temperature time series feature homography projection coding vector and the flow time series feature homography projection coding vector are modulated, so that the two vectors are no longer limited to their original feature information, but integrate the influence of each other's features. This makes the newly generated temperature time series feature homography projection attention modulation coding vector and flow time series feature homography projection attention modulation coding vector contain richer and more comprehensive information. That is, when describing the well washing fluid circulation process, the new coding vector can not only reflect the change trend of the temperature or flow itself, but also reflect the impact of the interaction between the two on their respective changes. Moreover, under different oil and gas well conditions, the interaction mode of temperature and flow is different. This modulation method allows the model to flexibly adjust the understanding and representation of features according to specific circumstances. For example, in the special oil and gas well environment of high temperature and high pressure, the changes in temperature and flow are more complex. Through modulation, the model can better adapt to this special condition, accurately capture the unique interaction relationship between temperature and flow, and improve the analysis and processing capabilities of the well washing process under different conditions, thereby enhancing the adaptability and generalization of the model.

[0045] Finally, the temperature-flow time series interaction response coding vector is obtained by dividing the homography projection attention modulation coding vector of the temperature time series feature and the homography projection attention modulation coding vector of the flow time series feature by the position point as the temperature-flow time series interaction response coding feature. The above process can be expressed as: ;in, is the temperature time series feature homography projection attention modulation encoding vector, is the homography projection attention modulation encoding vector of traffic time series features, is the temperature-flow time series interaction response encoding vector.

[0046] It should be understood that by dividing the homography projection attention modulation coding vector of the temperature time series feature and the homography projection attention modulation coding vector of the flow time series feature by position, it is possible to dig out the new relationship between the two after modulation. These new relationships are based on the coding vectors after the mutual influence information is integrated, which is more complex and in-depth than the original feature vector relationship. When analyzing the well washing process, this point division operation can clearly show the specific degree of correlation after the interaction between the temperature and flow characteristics at each time point. This can provide more comprehensive and targeted information for subsequent data analysis tasks, which in turn helps to more accurately grasp the circulation state of the well washing fluid during the well washing process.

[0047] In step S35, the temperature-flow time series interactive response coding feature is subjected to pressure inference to obtain a time queue of inferred pressure values. Specifically, in an embodiment of the present application, step S35 includes: inputting the temperature-flow time series interactive response coding vector into a pressure simulator based on an RNN model to obtain a time queue of inferred pressure values. It should be understood that during the well washing process, pressure is one of the important indicators for judging whether the circulation is normal. And the changes in temperature and flow will directly affect the pressure in the well, and these changes are often dynamic and complex. Based on this, in order to infer the actual situation of the ideal pressure based on the interactive representation between temperature and flow, in the technical solution of the present application, the temperature-flow time series interactive response coding vector is input into a pressure simulator based on an RNN model to realize intelligent prediction of pressure and obtain a time queue of inferred pressure values. Those skilled in the art should know that RNN has memory and can process time dependencies in sequence data. The temperature-flow time series interactive response coding vector is a data containing time series information, which records the interactive characteristics of temperature and flow at different times. The RNN model can capture the potential laws between the dynamic changes of temperature-flow and pressure by learning these sequence information. For example, in different well-washing stages, the change patterns of temperature and flow are different, and the RNN can predict the corresponding pressure changes based on these historical patterns. In other words, the RNN model can establish a mapping relationship between temperature-flow and pressure, and thus predict the corresponding pressure value based on the current temperature-flow interaction characteristics, providing data support for more accurate judgment of whether there are abnormalities in the well-washing cycle in the future.

[0048] The following is a detailed description of a specific implementation process of "inputting the temperature-flow time series interaction response encoding vector into a pressure simulator based on an RNN model to obtain a time queue of the inferred pressure value": First, it is necessary to build a pressure simulator based on an RNN model. Determining the model hyperparameters is a key step in building a model, which includes the number of hidden layers, the number of neurons in each hidden layer, the learning rate, and the number of training rounds. The values ​​of these hyperparameters have a profound impact on the performance of the model, and it is usually necessary to use experiments and adjustments to find the optimal values. Methods such as grid search or random search can be used to try different hyperparameter combinations within a set range, and the optimal model configuration is selected based on the performance of the validation set. For example, by training the model under different combinations of the number of hidden layers and learning rates, and observing the changes in the mean square error (MSE) on the validation set, the optimal hyperparameter settings can be determined.

[0049] Next, model training is required. Model training is the core process for the pressure simulator to learn the relationship between temperature-flow data and pressure. Before model training, a high-quality data set must be prepared. This includes historical data on temperature, flow, and pressure collected from oil and gas well sites. These data should cover various situations under different working conditions in order to train a model that can adapt to a variety of environmental changes. The collected data needs to be preprocessed and divided into training set, validation set, and test set according to a certain ratio. The training set is used to train the model so that the model can learn the inherent laws in the data; the validation set is used to evaluate the model performance during the training process, adjust the hyperparameters, and prevent overfitting; the test set is used to evaluate the generalization ability of the final model. The data of the training set is input into the constructed RNN model, and the weights and parameters of the model are adjusted with the help of the back-propagation algorithm to minimize the error (such as mean square error MSE) between the model's predicted value and the actual pressure value. During the training process, in order to accelerate model convergence and improve training efficiency, a suitable optimizer such as Adam, SGD, etc. can be selected. During the training process, the validation set data is used to evaluate the model's performance indicators (such as MSE, RMSE, etc.). If the model's performance on the validation set no longer improves, or even shows a downward trend, this indicates that overfitting may have occurred. At this time, the training should be stopped and the current optimal model parameters should be saved.

[0050] Model validation is an important step to test the reliability of the model. Use the test set data to validate the trained model and evaluate the performance of the model on unseen data. By calculating the error indicators between the inference pressure value predicted by the model and the actual pressure value in the test set, such as MSE, RMSE, MAPE (mean absolute percentage error), etc., the prediction accuracy of the model can be intuitively reflected. If the error indicators of the model on the test set meet the requirements of practical applications, it means that the model has good generalization ability and can be used for actual pressure reasoning; if the error is large, it is necessary to further adjust the model structure, hyperparameters or re-preprocess the data, and then retrain and validate the model.

[0051] After the above series of rigorous steps, when the model training and verification have achieved the expected results, the inference prediction stage can be entered. The temperature-flow time series interactive response encoding vector obtained by actual analysis is input into the trained and verified model. Based on the learned relationship between temperature-flow and pressure, the model infers and predicts the pressure value at each time point, thereby obtaining the time queue of the inferred pressure value. In actual application scenarios, as new temperature-flow data is continuously generated, the updated temperature-flow time series interactive response encoding vector is continuously input into the model to update the time queue of the inferred pressure value in real time. In this way, timely and accurate data support can be provided for judging whether there is an abnormality in the well washing fluid circulation, thereby ensuring the smooth progress of the hot washing, dewaxing and deblocking process of the continuous tubing of the oil and gas well, which is conducive to improving the mining efficiency and production safety of the oil and gas well.

[0052] Preferably, inputting the temperature-flow time series interactive response encoding vector into a pressure simulator based on an RNN model to obtain a time queue of the inferred pressure value comprises: calculating the first Eigenvalues ​​and The low-order proximity and high-order similarity between eigenvalues ​​can obtain the low-order proximity matrix of temperature-flow time series interaction response and the high-order similarity matrix of temperature-flow time series interaction response: ;in, and respectively represent the first Eigenvalues ​​and Eigenvalues, The low-order proximity matrix representing the temperature-flow time series interaction response The eigenvalues ​​of the positions, Represents the high-order similarity matrix of the temperature-flow time series interaction response The eigenvalue of the location.

[0053] The temperature-flow timing interaction response encoding vector is matrix-multiplied with the temperature-flow timing interaction response low-order proximity matrix and the temperature-flow timing interaction response high-order similarity matrix to obtain a first temperature-flow timing interaction response encoding recursive vector: ;in, represents the low-order proximity matrix of the temperature-flow time series interaction response, represents the high-order similarity matrix of the temperature-flow time series interaction response, represents matrix multiplication, represents the temperature-flow time series interaction response encoding vector, Represents the first temperature-flow time series interaction response encoding recursive vector.

[0054] The temperature-flow timing interaction response encoding vector is matrix-multiplied with the temperature-flow timing interaction response high-order similarity matrix and the temperature-flow timing interaction response low-order proximity matrix to obtain a second temperature-flow timing interaction response encoding recursive vector: ;in, Represents the second temperature-flow rate time series interaction response encoding recursive vector.

[0055] The temperature-flow timing interaction response low-order proximity matrix is ​​matrix-multiplied with the first temperature-flow timing interaction response encoding recursive vector and the second temperature-flow timing interaction response encoding recursive vector to obtain a first temperature-flow timing interaction response sparse expansion matrix ,in, Represents the transpose of a vector.

[0056] The temperature-flow time series interaction response high-order similarity matrix is ​​matrix-multiplied with the first temperature-flow time series interaction response coding recursive vector and the second temperature-flow time series interaction response coding recursive vector to obtain a second temperature-flow time series interaction response sparse expansion matrix .

[0057] The first temperature-flow timing interaction response sparse expansion matrix and the second temperature-flow timing interaction response sparse expansion matrix are added, and then multiplied with the transposed vector of the temperature-flow timing interaction response encoding vector to obtain an optimized temperature-flow timing interaction response encoding vector ;in, Indicates point addition.

[0058] The optimized temperature-flow timing interaction response encoding vector is input into a pressure simulator based on an RNN model to obtain a time queue of inferred pressure values.

[0059] Here, in the case where the temperature time series feature implicit coding vector and the flow time series feature implicit coding vector represent the time series implicit coding features of temperature and pressure respectively, when performing an interactive response based on the feature positive and negative attention fields, the insufficient correspondence of the positive and negative attention field reinforcement associations caused by the source time series distribution differences will cause the sparse association interactive response of the temperature-flow time series interactive response coding vector, thereby reducing the accuracy of the time series distribution of the time queue of the inferred pressure value obtained by the pressure simulator based on the RNN model due to the lack of time series cyclic reasoning degree, affecting the accuracy of the final determination result.

[0060] Therefore, for the temperature-flow timing interaction response coding vector, its low-order proximity and high-order similarity matrix representations are used as multi-scale feature association quantitative representations, and the coupling between different association modes of the time-delayed autoencoding representation of the temperature-flow timing interaction response coding vector is simulated through recursive optimization to simulate the sparse activation mechanism of the feature distribution neuron group, and the distribution sub-dimension in the feature component space is used for forward-looking sparse constraint expansion to achieve multi-granular predictable expression of the temperature-flow timing interaction response coding vector, effectively avoid the timing loop attenuation problem caused by joint inference failure, improve the timing distribution accuracy of the time queue of the inference pressure value obtained by the pressure simulator based on the RNN model when the temperature-flow timing interaction response coding vector is input, and improve the accuracy of the final determination result.

[0061] In step S36, it is determined whether there is a cycle abnormality based on the time queue of the pressure value and the time queue of the inferred pressure value. Specifically, Figure 4 This is a flow chart of step S36 in the hot-washing, wax-removing and plugging-removing process of coiled tubing in oil and gas wells according to an embodiment of the present application. Figure 4 As shown, the step S36 includes: S361, calculating the difference between the pressure value and the inferred pressure value at each time point in the time queue of the pressure value and the time queue of the inferred pressure value to obtain the time queue of the pressure deviation value; S362, determining whether there is a cyclic abnormality based on the mean and variance of the time queue of the pressure deviation value.

[0062] In step S361, the difference between the pressure value and the inferred pressure value at each time point in the time queue of the pressure value and the time queue of the inferred pressure value is calculated to obtain the time queue of the pressure deviation value. Accordingly, considering that the pressure value actually measured represents the real pressure condition in the well washing process, and the inferred pressure value is a predicted value obtained by model simulation based on other parameters such as temperature-flow rate. Therefore, in order to be able to observe more clearly and intuitively whether there are abnormal fluctuations in the pressure value, which may be signals of abnormal circulation, in the technical solution of the present application, the difference between the pressure value and the inferred pressure value at each time point in the time queue of the pressure value and the time queue of the inferred pressure value is calculated to obtain the time queue of the pressure deviation value. The obtained time queue of the pressure deviation value can be used as an important basis for detecting whether the well washing cycle process is abnormal. Under normal circumstances, since the model is obtained based on the physical laws of the process and a large amount of historical data training, the inferred pressure value should be close to the actual pressure value, and the pressure deviation value is in a small range and fluctuates smoothly. If there are abnormal conditions such as local blockage of the well washing pipeline and leakage of the well washing fluid, the actual pressure value will change significantly, causing the pressure deviation value to exceed the normal range or fluctuate abnormally. By real-time monitoring of the time queue of pressure deviation values, these abnormal signals can be discovered in time, providing early warning for operators to take corresponding measures.

[0063] In step S362, based on the mean and variance of the time queue of the pressure deviation value, it is determined whether there is a circulation anomaly. It should be understood that in order to quantify the extent of these differences and provide an objective basis for determining whether there is a circulation anomaly, the present application determines whether there is a circulation anomaly by using the mean and variance of the time queue based on the pressure deviation value. Specifically, the mean of the time queue of the pressure deviation value represents the average level of the sequence data, reflecting the average degree of deviation between the inferred pressure value and the actual pressure value. In the normal well washing cycle, due to the stability of the system and the relative consistency of the process parameters, the pressure deviation value should fluctuate around a smaller mean. If the mean deviates from the normal range, it means that there is a systematic deviation between the inferred pressure and the actual pressure, which may imply potential problems in the well washing cycle system, such as the systematic error of the measuring instrument, the offset of the model parameters, etc. The variance measures the degree of dispersion of the pressure deviation value around the mean. A smaller variance indicates that the pressure deviation value is relatively stably distributed near the mean, indicating that the pressure changes during the well washing process are more regular and the system operates stably. A larger variance indicates that the pressure deviation value fluctuates greatly, and there may be some random or sudden factors affecting the well washing cycle, such as the sudden movement of blockages in the wellbore, local instability of the flow of the well washing fluid, etc. By setting a reasonable mean and variance threshold range, and comparing the mean and variance of the pressure deviation value time queue actually calculated with it, it is possible to accurately determine whether there is an abnormality in the well washing cycle. When the mean exceeds the normal range or the variance is too large, it can be determined that there may be a circulation abnormality. This judgment method based on data statistical characteristics has high accuracy and reliability, can avoid misjudgment caused by fluctuations in a single data point, and provide operators with clear abnormal signals so that they can take timely measures to investigate and deal with it.

[0064] In summary, the step S3 is clearly explained, which uses data analysis and processing technology based on deep learning to sort the data of temperature values, pressure values ​​and flow values ​​to obtain the time queue of temperature values, the time queue of pressure values ​​and the time queue of flow values, and then respectively encodes the time series features of temperature values ​​and flow values, and associates the encoded temperature time series features and flow time series features with dual-view responses, so as to intelligently judge whether there is a cycle anomaly based on the deviation between the time queue of the inferred pressure value and the time queue of the pressure value obtained by pressure inference according to the temperature-flow time series interaction representation. In this way, the accuracy of cycle anomaly detection can be effectively improved.

[0065] In step S4, the decomposed blockage is returned to the ground together with the well washing fluid. It should be understood that through the circulation of the well washing fluid, blockages such as wax blocks can be melted, broken or loosened and can be brought back to the ground together with the well washing fluid. This ensures that the blockage is effectively removed, rather than simply being broken up and redeposited in other parts. Moreover, since the blockage is completely taken out of the well, the risk of secondary blockage caused by the redeposition of residues is reduced, which is conducive to ensuring the long-term smooth flow of the production tubing. That is, as the blockage is removed and broken, the circulation channel of the well washing fluid gradually becomes unblocked. The well washing fluid that was originally blocked by the blockage can flow more smoothly to form a stable cycle. This is not only conducive to the continuous wax removal and unblocking operations, but also ensures the normal flow of oil and gas in the tubing, thereby improving the production efficiency of oil and gas.

[0066] In summary, the hot washing, wax removal and blockage removal process of coiled tubing in oil and gas wells based on the embodiment of the present application is explained. First, the well washing fluid is heated by a hot oil truck, and then the heated well washing fluid is injected into the coiled tubing operation machine by a pump truck. Then, the well washing fluid is sent into the well through the coiled tubing and circulates in the circulation channel in the well. During the circulation of the well washing fluid, the water horsepower impact, heat exchange and mechanical crushing effect generated by the well washing fluid are used to remove or crush the blockage in the well, and finally the decomposed blockage is returned to the ground together with the well washing fluid. In this way, the effect of wax removal and blockage removal in oil and gas wells can be improved, which is conducive to better realizing the effective maintenance of oil and gas wells.

Claims

1. A process for hot washing, wax removal and plugging removal of coiled tubing in oil and gas wells, characterized in that: include: The well washing fluid is heated by a hot oil truck to obtain heated well washing fluid; The heated well-washing fluid is injected into the coiled tubing operation machine by a pump truck; The coiled tubing operation machine lowers the well-washing fluid into the well through the coiled tubing, and the well has a well-washing fluid circulation channel. The well-washing fluid can circulate in the well through the well-washing fluid circulation channel to remove or break the blockage by utilizing the water horsepower impact, heat energy exchange and mechanical crushing generated by the well-washing fluid during the circulation process, including: real-time monitoring of the state parameters of the well-washing fluid circulating in the well-washing fluid circulation channel to obtain a time queue of the state parameters, the state parameters including temperature value, pressure value and flow value; data sorting of the time queue of the state parameters to obtain a time queue of temperature value, a time queue of pressure value and a time queue of flow value; sequence encoding of the time queue of temperature value and the time queue of flow value to obtain temperature time series characteristics and flow time series characteristics; temperature-flow time series dual-view response correlation analysis of the temperature time series characteristics and the flow time series characteristics to obtain temperature-flow time series interactive response coding characteristics; Performing pressure inference on the temperature-flow time series interactive response coding feature to obtain a time queue of inferred pressure values; determining whether there is a circulation anomaly based on the time queue of the pressure values ​​and the time queue of the inferred pressure values; and returning the decomposed blockage to the surface together with the well washing fluid.

2. The process for hot-washing, wax-removing and plugging-removing of coiled tubing in oil and gas wells according to claim 1, characterized in that: The time queue of the temperature values ​​and the time queue of the flow values ​​are sequence-encoded to obtain temperature time series characteristics and flow time series characteristics, including: using a sequence encoder to sequence-encode the time queue of the temperature values ​​and the time queue of the flow values ​​respectively to obtain an implicit encoding vector of temperature time series characteristics as the temperature time series characteristics and an implicit encoding vector of flow time series characteristics as the flow time series characteristics.

3. The process for hot-washing, wax-removing and plugging-removing of coiled tubing in oil and gas wells according to claim 2, characterized in that: The sequence encoder is a sequence encoder based on a bidirectional gated recurrent unit.

4. The process for hot-washing, wax-removing and plugging-removing of coiled tubing in oil and gas wells according to claim 3, characterized in that: The temperature-flow time series dual-perspective response correlation analysis is performed on the temperature time series feature and the flow time series feature to obtain the temperature-flow time series interactive response coding feature, including: performing homography projection transformation on the temperature time series feature implicit coding vector and the flow time series feature implicit coding vector to obtain the temperature time series feature homography projection coding vector and the flow time series feature homography projection coding vector; calculating the dual-perspective temperature-flow time series feature attention score field between the temperature time series feature homography projection coding vector and the flow time series feature homography projection coding vector; based on the dual-perspective temperature-flow time series feature attention score field Viewing angle temperature-flow timing feature attention score field, modulating the temperature timing feature homography projection coding vector and the flow timing feature homography projection coding vector to obtain the temperature timing feature homography projection attention modulation coding vector and the flow timing feature homography projection attention modulation coding vector; calculating the temperature timing feature homography projection attention modulation coding vector and the flow timing feature homography projection attention modulation coding vector divided by the position point to obtain the temperature-flow timing interaction response coding vector as the temperature-flow timing interaction response coding feature.

5. The process for hot-washing, wax-removing and plugging-removing of coiled tubing in oil and gas wells according to claim 4, characterized in that: The temperature time series feature implicit coding vector and the flow time series feature implicit coding vector are subjected to homography projection transformation to obtain the temperature time series feature homography projection coding vector and the flow time series feature homography projection coding vector, including: mapping the temperature time series feature implicit coding vector through a temperature time series feature mapping homography matrix to obtain the temperature time series feature homography projection coding vector; mapping the flow time series feature implicit coding vector through a flow time series feature mapping homography matrix to obtain the flow time series feature homography projection coding vector.

6. The process for hot-washing, wax-removing and plugging-removing of coiled tubing in oil and gas wells according to claim 5, characterized in that: Calculate the dual-view temperature-flow timing feature attention score field between the temperature timing feature homography projection coding vector and the flow timing feature homography projection coding vector, including: calculating the forward temperature-flow timing feature attention score field of the temperature timing feature homography projection coding vector relative to the flow timing feature homography projection coding vector; calculating the reverse temperature-flow timing feature attention score field of the flow timing feature homography projection coding vector relative to the temperature timing feature homography projection coding vector; based on the forward temperature-flow timing feature attention score field and the reverse temperature-flow timing feature attention score field, obtain the dual-view temperature-flow timing feature attention score field.

7. The process for hot-washing, wax-removing and plugging-removing of coiled tubing in oil and gas wells according to claim 6, characterized in that: Based on the dual-view temperature-flow timing feature attention score field, the temperature timing feature homography projection coding vector and the flow timing feature homography projection coding vector are modulated to obtain the temperature timing feature homography projection attention modulation coding vector and the flow timing feature homography projection attention modulation coding vector, including: multiplying the dual-view temperature-flow timing feature attention score field with the temperature timing feature homography projection coding vector and the flow timing feature homography projection coding vector respectively to obtain the temperature timing feature homography projection attention modulation coding vector and the flow timing feature homography projection attention modulation coding vector.

8. The process for hot-washing, wax-removing and plugging-removing of coiled tubing in oil and gas wells according to claim 7, characterized in that: Performing pressure inference on the temperature-flow timing interaction response coding feature to obtain a time queue of inferred pressure values ​​includes: inputting the temperature-flow timing interaction response coding vector into a pressure simulator based on an RNN model to obtain a time queue of inferred pressure values.

9. The process for hot-washing, wax-removing and plugging-removing of coiled tubing in oil and gas wells according to claim 8, characterized in that: Based on the time queue of the pressure values ​​and the time queue of the inferred pressure values, determining whether there is a circulation abnormality includes: calculating the difference between the pressure value and the inferred pressure value at each time point in the time queue of the pressure values ​​and the time queue of the inferred pressure values ​​to obtain a time queue of pressure deviation values; and determining whether there is a circulation abnormality based on the mean and variance of the time queue of the pressure deviation values.

Images