Multi-parameter real-time visual analysis method and system for fracturing wellhead lifting monitoring

Abstract

The invention relates to the technical field of oil field fracturing wellhead operation risk monitoring, in particular to a multi-parameter real-time visual analysis method and system for fracturing wellhead lifting monitoring, a triple combination protection structure is arranged in a wellhead flange non-pressure-bearing area, and a three-axis vibration sensor and a temperature sensor are embedded in the triple combination protection structure to collect data in real time; after data encryption transmission and preprocessing are carried out through edge computing nodes, multi-source data fusion analysis is achieved through a stream processing engine of an Internet of Things cloud platform, and intelligent analysis is achieved through a constructed wellhead health scoring model and a lifting trend recognition model; and finally, dynamically displaying visual results such as a three-axis vibration scatter diagram and a trend curve on a client, and triggering graded early warning. The problems that a traditional monitoring technology is single in monitoring dimension, insufficient in real-time performance, poor in environmental adaptability and the like are effectively solved, and the accuracy and reliability of wellhead safety monitoring are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of oilfield fracturing wellhead operation risk monitoring, and in particular to a multi-parameter real-time visual analysis method and system for fracturing wellhead uplift monitoring. Background Art

[0002] Fracturing wellheads are high-temperature, high-pressure oil and gas wellheads, and sudden wellhead lift is common during operation. Since personnel cannot enter the high-pressure, dangerous area during fracturing, and sudden events cannot be monitored in real time, wellhead lift not only affects safe production operations but can also cause serious safety accidents if the problem is not discovered and resolved promptly. Oil and gas production practice shows that wellhead lift primarily manifests as relative displacement between the wellhead and the ground, with two main possible causes: First, the higher temperature at the oil and gas fracturing wellhead causes thermal expansion and elongation of the casing, which can easily lead to wellhead lift; second, ground subsidence can also cause wellhead lift.

[0003] Currently, wellhead uplift monitoring technology has made considerable progress. Traditional monitoring methods primarily include manual inspections to measure displacement and the use of traditional displacement sensors. Manual inspections can detect wellhead uplift to a certain extent, while traditional displacement sensors can provide sufficient displacement measurement data. These methods provide a foundation for monitoring wellhead uplift, helping to promptly detect signs of wellhead uplift and take appropriate measures.

[0004] However, existing wellhead uplift monitoring technology still suffers from numerous shortcomings and deficiencies. First, monitoring accuracy and real-time performance are insufficient. Existing monitoring methods cannot simultaneously meet the requirements for high-precision and real-time monitoring, and cannot provide reliable support for wellhead uplift monitoring. Second, manual inspections to measure displacement are inefficient, resulting in untimely and inaccurate results, making it difficult to perform real-time and accurate displacement measurements in high-pressure hazardous areas. Furthermore, traditional displacement sensors are significantly affected by mechanical wear and electromagnetic interference in the complex vibration environment of the wellhead, making them unable to accurately capture early signs of wellhead uplift. Furthermore, they lack coordinated three-axis displacement monitoring, making it impossible to fully and accurately reflect the actual wellhead uplift. Finally, in extreme environments such as high temperature and high pressure, sensors are prone to drift, and chemicals can contaminate the measurement unit, causing sensor damage and affecting the normal operation of the monitoring system. These issues have severely restricted the development and application of wellhead uplift monitoring technology, making it unable to meet the high requirements for wellhead uplift monitoring in oil and gas field fracturing operations. Summary of the Invention

[0005] The purpose of the present invention is to provide a multi-parameter real-time visualization analysis method and system for monitoring fracturing wellhead lift, which solves the problems of insufficient accuracy and real-time performance of existing wellhead lift monitoring technologies and easy damage of sensors.

[0006] To achieve the above objectives, the present invention provides a multi-parameter real-time visualization analysis method for monitoring fracturing wellhead lift, comprising the following steps: A reserved cavity is set in the non-pressure-bearing area of ​​the wellhead flange, and a sensor device is embedded in it to collect the wellhead's triaxial vibration acceleration, displacement, frequency and temperature data in real time; Receive data collected by sensor devices through edge computing nodes, process the data, and make local early warning judgments based on preset thresholds; The processed data is transmitted to the IoT cloud platform, where a stream processing engine is used to integrate and analyze multi-source data. The wellhead health scoring model is used to assess the wellhead status, and an uplift trend recognition model is used to distinguish between uplift caused by thermal expansion and foundation settlement. The analysis results are pushed to the client in real time, dynamically displaying the three-axis vibration scatter plot, trend curve and temperature changes, and triggering graded warnings based on the health score and trend analysis results.

[0007] Among them, a reserved cavity is set in the non-pressure-bearing area of ​​the wellhead flange, and the sensor device is embedded in it to collect the three-axis vibration acceleration, displacement, frequency and temperature data of the wellhead in real time. The calculation formula for the size of the reserved cavity is: Lc=Ls+2t, Wc=Ws+2t, Hc=Hs+2t, where Ls is the length of the sensor device, Ws is the width of the sensor device, Hs is the height of the sensor device, t is the thickness of the single-sided protective layer, Lc is the length of the reserved cavity, Wc is the width of the reserved cavity, and Hc is the height of the reserved cavity.

[0008] Among them, a reserved cavity is set in the non-pressure-bearing area of ​​the wellhead flange, and the sensor device is embedded in it to collect the three-axis vibration acceleration, displacement, frequency and temperature data of the wellhead in real time. The internal structure of the reserved cavity consists of a silicon nitride ceramic coating, an aramid fiber buffer layer, and a Hastelloy alloy lining. The silicon nitride ceramic coating is the innermost layer with a thickness of 1 mm. A dense film is formed on the inner wall surface of the cavity using a PVD process. The aramid fiber buffer layer is located between the silicon nitride ceramic coating and the Hastelloy alloy lining. It exists in the form of a flexible composite fiber grid or a pressed gasket with a thickness range of 1mm and is fixed by molded composite or adhesive laying. The Hastelloy lining is the outermost layer, which is a highly corrosion-resistant nickel-based alloy. It fits tightly to the inner wall of the flange and is installed and fixed by thread locking. The thickness is 0.8mm.

[0009] Among them, a reserved cavity is set in the non-pressure-bearing area of ​​the wellhead flange, and the sensor device is embedded in it to collect the three-axis vibration acceleration, displacement, frequency and temperature data of the wellhead in real time. The sensor device is a three-axis vibration sensor and an industrial-grade temperature sensor, which are installed in the reserved cavity of the wellhead flange and fixed by a flange. Its axis is kept consistent with the center axis of the wellhead and is filled with shock-absorbing silicone material.

[0010] Among them, the edge computing node receives the data collected by the sensor device, processes the data, and makes local early warning judgments based on preset thresholds. Edge computing nodes are deployed inside the well site network base station and the instrument vehicle control terminal at the fracturing well site. They have data preprocessing, caching and breakpoint resumption capabilities, support multi-protocol access and remote management, and the communication delay between the edge computing node and the sensor device is less than 20ms, realizing local primary warning logic judgment and log recording.

[0011] The processed data is transmitted to the IoT cloud platform, and a stream processing engine is used to integrate and analyze multi-source data. The wellhead health scoring model is used to evaluate the wellhead status, and the uplift caused by thermal expansion and foundation settlement is distinguished based on the uplift trend identification model. The IoT cloud platform adopts a distributed stream processing architecture, which supports structured processing, unit normalization and outlier removal of access data. The IoT cloud platform has built a wellhead health scoring model and an uplift trend identification model to realize the classification judgment and trend prediction of different types of wellhead deformation behaviors.

[0012] The analysis results are pushed to the client in real time, and the three-axis vibration scatter plot, trend curve and temperature change are dynamically displayed. According to the health score and trend analysis results, graded warnings are triggered. The client supports user-defined alarm thresholds, real-time data visualization, three-axis vibration scatter plot drawing, trend curve analysis, early warning information push and historical data graphic comparison functions.

[0013] A multi-parameter real-time visualization analysis system for monitoring fracturing wellhead lift includes a sensor device, an edge computing node, an Internet of Things cloud platform, and a client, wherein the edge computing node is connected to the sensor device, the Internet of Things cloud platform is connected to the edge computing node, and the client is connected to the Internet of Things cloud platform; The sensor device is used to integrate a triaxial vibration sensor and a temperature sensor, and is embedded in the reserved cavity of the non-pressure-bearing area of ​​the wellhead flange to collect the triaxial vibration acceleration, displacement, frequency and temperature data of the wellhead in real time; The edge computing node is used to receive data collected by the sensor device, process the data, and make local early warning judgments based on preset thresholds; The IoT cloud platform is used to perform fusion analysis on multi-source data using a stream processing engine, evaluate wellhead status using a constructed wellhead health scoring model, and distinguish uplift caused by thermal expansion from uplift caused by foundation settlement based on an uplift trend recognition model; The client is used to dynamically display a three-axis vibration scatter plot, trend curve and temperature change, and trigger a graded warning based on the health score and trend analysis results.

[0014] The present invention provides a multi-parameter real-time visualization analysis method and system for monitoring fracturing wellhead uplift. This method employs a reserved cavity with a triple-composite protective structure (silicon nitride ceramic coating, aramid fiber buffer layer, and Hastelloy lining) in the non-pressure-bearing area of ​​the wellhead flange, into which a triaxial vibration sensor and a temperature sensor are embedded for real-time data collection. After encrypted transmission and preprocessing via edge computing nodes, the data is then analyzed using the stream processing engine of the IoT cloud platform. Intelligent analysis is achieved through the wellhead health scoring model and uplift trend identification model. Finally, visual results, such as triaxial vibration scatter plots and trend curves, are dynamically displayed on the client, triggering graded warnings. This method effectively addresses the problems of traditional monitoring technologies, such as a single monitoring dimension, insufficient real-time performance, and poor environmental adaptability. It enables real-time monitoring of three-dimensional deformation, stable operation in high-temperature and high-pressure environments, precise differentiation between thermal expansion and foundation settlement, and collaborative analysis and visualization of multiple parameters, significantly improving the accuracy and reliability of wellhead safety monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art.

[0016] Figure 1 This is a flowchart of the steps of the multi-parameter real-time visual analysis method for monitoring fracturing wellhead lift according to the first embodiment of the present invention.

[0017] Figure 2 It is a schematic diagram of the three-axis vibration displacement of the visualization result of the first embodiment of the present invention.

[0018] Figure 3 It is a schematic diagram of the three-axis vibration frequency of the visualization result of the first embodiment of the present invention.

[0019] Figure 4 It is a schematic diagram of the three-axis vibration velocity of the visualization result of the first embodiment of the present invention.

[0020] Figure 5It is a schematic diagram of the three-axis vibration acceleration of the visualization result of the first embodiment of the present invention.

[0021] Figure 6 3. It is a schematic diagram of three-axis scatter points of the visualization result of the first embodiment of the present invention.

[0022] Figure 7 FIG. 4 is a schematic diagram of the temperature visualization result according to the first embodiment of the present invention.

[0023] Figure 8 This is a schematic diagram of a multi-parameter real-time visual analysis system for monitoring fracturing wellhead lift according to a second embodiment of the present invention.

[0024] Figure 9 Schematic diagram of the position of the reserved cavity at the wellhead flange according to the second embodiment of the present invention.

[0025] Figure 10 Schematic diagram of the position of the protective structure of the second embodiment of the present invention.

[0026] In the figure: 1-sensor device, 2-well site network base station, 3-edge computing node, 4-IoT cloud platform, 5-client, 6-reserved cavity, 7-protection structure. DETAILED DESCRIPTION

[0027] The embodiments of the present invention are described in detail below. Examples of the embodiments are shown in the accompanying drawings. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, but should not be understood as limiting the present invention.

[0028] The first embodiment of this application is: See also Figures 1 to 7 ,in, Figure 1 This is a flowchart of the steps of the multi-parameter real-time visual analysis method for monitoring fracturing wellhead lift according to the first embodiment of the present invention. Figure 2 It is a schematic diagram of the three-axis vibration displacement of the visualization result of the first embodiment of the present invention. Figure 3 It is a schematic diagram of the three-axis vibration frequency of the visualization result of the first embodiment of the present invention. Figure 4 It is a schematic diagram of the three-axis vibration velocity of the visualization result of the first embodiment of the present invention. Figure 5 It is a schematic diagram of the three-axis vibration acceleration of the visualization result of the first embodiment of the present invention. Figure 6 3. It is a schematic diagram of three-axis scatter points of the visualization result of the first embodiment of the present invention. Figure 7 FIG. 4 is a schematic diagram of the temperature visualization result according to the first embodiment of the present invention.

[0029] The present invention provides a multi-parameter real-time visual analysis method for monitoring fracturing wellhead lift, comprising the following steps: S101: A reserved cavity 6 is provided in the non-pressure-bearing area of ​​the wellhead flange, and a sensor device 1 is embedded therein to collect the triaxial vibration acceleration, displacement, frequency, and temperature data of the wellhead in real time; Specifically, a reserved cavity 6 is pre-set in the non-pressure-bearing area of ​​the wellhead flange. The cavity dimensions should be designed based on the overall dimensions of the embedded sensor device 1 and its multi-layer protective structure 7. The sensor dimensions are: length (Ls), width (Ws), height (Hs), and the thickness of the single-sided protective layer (t). The present invention provides a calculable and adjustable cavity size design method. Using the formulas Lc = Ls + 2t, Wc = Ws + 2t, and Hc = Hs + 2t, this method achieves spatial matching between the embedded sensor and the triple composite protective structure, effectively improving the sensor installation reliability and monitoring stability of the wellhead flange in extreme environments. The beneficial effect is that the cavity is located in the non-pressure-bearing area of ​​the flange, with a minimum distance from the flange edge of no less than the radius of the sensor device 1 plus 5 mm or 1.5 times the flange thickness, thereby balancing the protection of the sensor device 1 with the safety of the flange structure. The cavity serves as the embedded installation space for the sensor device 1. Its internal structure includes, in sequence, a silicon nitride ceramic coating, an aramid fiber buffer layer, and a Hastelloy alloy liner. The silicon nitride ceramic coating is the innermost layer with a thickness range of 1mm. A dense film is formed on the inner wall surface of the metal cavity using the PVD process. The aramid fiber buffer layer is located between the silicon nitride layer and the metal lining. This layer exists in the form of a flexible composite fiber mesh or a pressed gasket. The thickness range is 1mm and can be fixed by molded composite or adhesive laying. The Hastelloy alloy lining serves as the outermost protective structure 7. Hastelloy is a typical nickel-based alloy with high corrosion resistance. The metal lining fits tightly to the inner wall of the flange and is installed and fixed by threaded locking with a thickness of 0.8mm. It plays a full-range environmental sealing and protection role. The beneficial effects are: the silicon nitride ceramic coating provides high-strength rigid support and heat-resistant isolation, which can effectively isolate the high-temperature environment transmitted from the wellhead, prevent thermal stress from damaging the sensor core chip, and has excellent resistance to mechanical shock. The aramid fiber buffer layer offers excellent elastic cushioning, vibration damping, and penetration resistance. It boasts extremely high specific strength and thermal stability, and is highly resistant to impact energy. This effectively disperses stress concentration under wellhead vibration and impact loads, preventing sensor displacement or damage within the cavity. This design ensures stable sensor operation in extreme wellsite environments such as high temperature, high pressure, and intense vibration. The Hastelloy alloy lining is designed to withstand the corrosive environments of acidic fluids, chemicals, and high humidity encountered during fracturing operations. It is resistant to chloride ion stress corrosion, pitting corrosion, and crevice corrosion, and offers excellent machinability and mechanical strength. This creates an integrated, triple-layered protective structure that provides explosion protection, thermal insulation, vibration resistance, and corrosion resistance. Sensor device 1 integrates a high-precision MEMS triaxial vibration sensor and an industrial-grade temperature sensor. Sensor device 1 is installed within the flanged wellhead cavity 6, secured by a flange plate to align its axis with the wellhead's center axis. It is then filled with a shock-absorbing silicone material.

[0030] S102: Receive data collected by the sensor device 1 through the edge computing node 3, process the data, and make a local early warning judgment based on a preset threshold; Specifically, edge computing node 3 is deployed within wellsite network base station 2 and the instrument vehicle control terminal at the fracturing wellsite. It provides data preprocessing, caching, and breakpoint resuming capabilities, supporting multi-protocol access and remote management. Communication latency between it and sensor device 1 is less than 20ms, enabling local primary warning logic and logging, ensuring the system maintains basic operational capabilities even in unstable network environments. Data collected by sensor device 1 is encrypted and encapsulated via a WiFi module and transmitted in real time to edge computing node 3 via dual-band wireless communication supporting IEEE802.11b / g / n / ac protocols.

[0031] S103: The processed data is transmitted to the IoT cloud platform 4, and a stream processing engine is used to perform fusion analysis on the multi-source data. The wellhead status is evaluated using the constructed wellhead health scoring model, and the uplift caused by thermal expansion and foundation settlement is distinguished based on the uplift trend identification model. Specifically, IoT Cloud Platform 4 uses the Alibaba Cloud platform. Designed based on a distributed stream processing architecture, IoT Cloud Platform 4 supports access, cleaning, and structured processing of encrypted data at the edge. It features a wellhead health assessment model, an uplift trend identification model, data visualization and push services, and historical record backlog capabilities. The platform communicates with Visualization Client 5 via an API protocol, enabling dynamic display of multi-parameter wellhead data, event alerts, and report generation. It also supports multi-user permission management and data security. This effectively distinguishes structural displacement caused by foundation settlement from thermally induced uplift caused by casing thermal expansion, improving the accuracy of identifying wellhead uplift anomalies. Asynchronous communication and message queue mechanisms are used to manage various data streams, ensuring high throughput and high reliability of data processing.

[0032] S104: The analysis results are pushed to the client 5 in real time, and a three-axis vibration scatter plot, trend curve and temperature change are dynamically displayed, and a graded warning is triggered according to the health score and trend analysis results.

[0033] Specifically, the visualization client 5 provides real-time display and early warning response. The visualization client 5 is the user interaction terminal of the system and can be deployed on various devices such as PCs, instrument vehicles, and dispatch center hosts. Client 5 establishes a stable communication connection with the cloud platform via the API protocol, subscribes to analysis results in real time, and displays them graphically. The beneficial effects are: real-time visualization of multi-parameter data, including: vibration displacement: amplitude, the jitter amplitude of the vibration point at the moment of wellhead vibration. Vibration frequency: the number of times the wellhead vibrates per unit time during vibration. Vibration velocity: the moving speed of the vibration position at the moment of monitored wellhead vibration. Other visualization parameters such as three-axis vibration position scatter plots. Temperature: the operating temperature of the sensor. Configure multi-level early warning thresholds. When a parameter is detected to reach the set threshold, the system automatically triggers the alarm mechanism and simultaneously sends an email. Historical data query and trend analysis: users can search and compare historical records by time range, parameter type, or alarm event.

[0034] This invention proposes a multi-parameter real-time visualization and data analysis method for monitoring fracturing wellhead lift. By integrating wellhead flange cavity reservation, wireless communication, and intelligent analysis technology, it achieves a comprehensive upgrade in safety monitoring for oil and gas fracturing and natural gas wellheads. The widespread application of this invention will effectively prevent safety accidents caused by fracturing wellhead lift, reduce unplanned production downtime losses, and provide an innovative solution for intelligent safety monitoring in oil and gas fields.

[0035] The second embodiment of this application is: Based on the first embodiment, please refer to Figures 8 to 10 ,in, Figure 8 This is a schematic diagram of a multi-parameter real-time visual analysis system for monitoring fracturing wellhead lift according to a second embodiment of the present invention. Figure 9 1 is a schematic structural diagram of a cavity 6 reserved at a wellhead flange according to a second embodiment of the present invention. Figure 10 FIG. 1 is a schematic diagram showing the position of the protective structure 7 according to the second embodiment of the present invention.

[0036] The multi-parameter real-time visual analysis system for monitoring fracturing wellhead lift in this embodiment includes a sensor device 1, an edge computing node 3, an Internet of Things cloud platform 4 and a client 5.

[0037] For this specific embodiment, the edge computing node 3 is connected to the sensor device 1, the IoT cloud platform 4 is connected to the edge computing node 3, and the client 5 is connected to the IoT cloud platform 4; The sensor device 1 is used to integrate a triaxial vibration sensor and a temperature sensor, and is embedded in the reserved cavity 6 in the non-pressure-bearing area of ​​the wellhead flange to collect the triaxial vibration acceleration, displacement, frequency and temperature data of the wellhead in real time; The edge computing node 3 is used to receive data collected by the sensor device 1, process the data, and make local early warning judgments based on preset thresholds; The IoT cloud platform 4 is configured to perform fusion analysis on multi-source data using a stream processing engine, evaluate the wellhead status using a constructed wellhead health scoring model, and distinguish between uplift caused by thermal expansion and foundation settlement based on an uplift trend recognition model; The client 5 is used to dynamically display a three-axis vibration scatter plot, a trend curve and temperature changes, and trigger a graded warning based on the health score and trend analysis results.

[0038] A multi-parameter real-time visualization analysis system for monitoring fracturing wellhead uplift is used in accordance with the present embodiment. The edge computing node 3 is connected to the sensor device 1 via wireless communication, the IoT cloud platform 4 is connected to the edge computing node 3 via an encrypted network, and the client 5 is connected to the IoT cloud platform 4 via an API interface. The sensor device 1 integrates a triaxial vibration sensor and a temperature sensor, and is embedded in a reserved cavity 6 in the non-pressure-bearing area of ​​the wellhead flange to collect triaxial vibration acceleration, displacement, frequency, and temperature data of the wellhead in real time. The edge computing node 3 is deployed in the wellsite base station and the instrument vehicle, and is configured with a data cache module and a breakpoint resume function to receive sensor data and perform noise reduction processing and local early warning judgment. The IoT cloud platform 4 adopts a distributed stream processing architecture, with a built-in wellhead health scoring model and an uplift trend identification model to realize real-time fusion analysis and trend prediction of multi-source data. The client 5 supports multi-terminal access, provides visual displays such as triaxial vibration scatter plots and multidimensional trend curves, and implements graded early warning push based on the analysis results of the cloud platform. It can effectively solve the problems of poor environmental adaptability and single analysis dimension existing in traditional monitoring technologies, and realize real-time monitoring and accurate early warning of wellhead uplift risks.

[0039] The above disclosure is merely one or more preferred embodiments of the present application and is not intended to limit the scope of the present application. A person skilled in the art will understand that all or part of the processes of the above embodiments and equivalent changes made in accordance with the claims of the present application are still within the scope of the present application.

Claims

1. A multi-parameter real-time visualization analysis method for monitoring fracturing wellhead lift, characterized in that: The following steps are involved: A reserved cavity is set in the non-pressure-bearing area of ​​the wellhead flange, and a sensor device is embedded in it to collect the wellhead's triaxial vibration acceleration, displacement, frequency and temperature data in real time; Receive data collected by sensor devices through edge computing nodes, process the data, and make local early warning judgments based on preset thresholds; The processed data is transmitted to the IoT cloud platform, where a stream processing engine is used to integrate and analyze multi-source data. The wellhead health scoring model is used to assess the wellhead status, and an uplift trend recognition model is used to distinguish between uplift caused by thermal expansion and foundation settlement. The analysis results are pushed to the client in real time, dynamically displaying the three-axis vibration scatter plot, trend curve and temperature changes, and triggering graded warnings based on the health score and trend analysis results.

2. The multi-parameter real-time visual analysis method for monitoring fracturing wellhead lift according to claim 1, characterized in that: A reserved cavity is set in the non-pressure-bearing area of ​​the wellhead flange, and the sensor device is embedded in it to collect the three-axis vibration acceleration, displacement, frequency and temperature data of the wellhead in real time. The calculation formula for the size of the reserved cavity is: Lc=Ls+2t, Wc=Ws+2t, Hc=Hs+2t, where Ls is the length of the sensor device, Ws is the width of the sensor device, Hs is the height of the sensor device, t is the thickness of the single-sided protective layer, Lc is the length of the reserved cavity, Wc is the width of the reserved cavity, and Hc is the height of the reserved cavity.

3. The multi-parameter real-time visual analysis method for monitoring fracturing wellhead lift according to claim 2, characterized in that: A reserved cavity is set in the non-pressure-bearing area of ​​the wellhead flange, and the sensor device is embedded in it to collect the three-axis vibration acceleration, displacement, frequency and temperature data of the wellhead in real time. The internal structure of the reserved cavity consists of a silicon nitride ceramic coating, an aramid fiber buffer layer, and a Hastelloy alloy lining. The silicon nitride ceramic coating is the innermost layer with a thickness of 1 mm. A dense film is formed on the inner wall surface of the cavity using a PVD process. The aramid fiber buffer layer is located between the silicon nitride ceramic coating and the Hastelloy alloy lining. It exists in the form of a flexible composite fiber grid or a pressed gasket with a thickness range of 1mm and is fixed by molded composite or adhesive laying. The Hastelloy lining is the outermost layer, which is a highly corrosion-resistant nickel-based alloy. It fits tightly to the inner wall of the flange and is installed and fixed by thread locking. The thickness is 0.8mm.

4. The multi-parameter real-time visual analysis method for monitoring fracturing wellhead lift according to claim 3, characterized in that: A reserved cavity is set in the non-pressure-bearing area of ​​the wellhead flange, and the sensor device is embedded in it to collect the three-axis vibration acceleration, displacement, frequency and temperature data of the wellhead in real time. The sensor device is a three-axis vibration sensor and an industrial-grade temperature sensor, which are installed in the reserved cavity of the wellhead flange and fixed by a flange. Its axis is kept consistent with the center axis of the wellhead and is filled with shock-absorbing silicone material.

5. The multi-parameter real-time visual analysis method for monitoring fracturing wellhead lift according to claim 4, characterized in that: The edge computing node receives data collected by the sensor device, processes the data, and makes local early warning judgments based on preset thresholds. Edge computing nodes are deployed inside the well site network base station and the instrument vehicle control terminal at the fracturing well site. They have data preprocessing, caching and breakpoint resumption capabilities, support multi-protocol access and remote management, and the communication delay between the edge computing node and the sensor device is less than 20ms, realizing local primary warning logic judgment and log recording.

6. The multi-parameter real-time visual analysis method for monitoring fracturing wellhead lift according to claim 5, characterized in that: The processed data is transmitted to the IoT cloud platform. The stream processing engine is used to integrate and analyze multi-source data. The wellhead health scoring model is used to evaluate the wellhead status. The uplift trend identification model is used to distinguish between uplift caused by thermal expansion and foundation settlement. The IoT cloud platform adopts a distributed stream processing architecture, which supports structured processing, unit normalization and outlier removal of access data. The IoT cloud platform has built a wellhead health scoring model and an uplift trend identification model to realize the classification judgment and trend prediction of different types of wellhead deformation behaviors.

7. The multi-parameter real-time visual analysis method for monitoring fracturing wellhead lift according to claim 6, characterized in that: The analysis results are pushed to the client in real time, and the three-axis vibration scatter plot, trend curve and temperature change are dynamically displayed. According to the health score and trend analysis results, graded warnings are triggered. The client supports user-defined alarm thresholds, real-time data visualization, three-axis vibration scatter plot drawing, trend curve analysis, early warning information push and historical data graphic comparison functions.

8. A multi-parameter real-time visualization analysis system for monitoring fracturing wellhead uplift, applicable to the multi-parameter real-time visualization analysis method for monitoring fracturing wellhead uplift according to claim 1, characterized in that: It includes a sensor device, an edge computing node, an Internet of Things cloud platform and a client, wherein the edge computing node is connected to the sensor device, the Internet of Things cloud platform is connected to the edge computing node, and the client is connected to the Internet of Things cloud platform; The sensor device is used to integrate a triaxial vibration sensor and a temperature sensor, and is embedded in the reserved cavity of the non-pressure-bearing area of ​​the wellhead flange to collect the triaxial vibration acceleration, displacement, frequency and temperature data of the wellhead in real time; The edge computing node is used to receive data collected by the sensor device, process the data, and make local early warning judgments based on preset thresholds; The IoT cloud platform is used to perform fusion analysis on multi-source data using a stream processing engine, evaluate wellhead status using a constructed wellhead health scoring model, and distinguish uplift caused by thermal expansion from uplift caused by foundation settlement based on an uplift trend recognition model; The client is used to dynamically display a three-axis vibration scatter plot, trend curve and temperature change, and trigger a graded warning based on the health score and trend analysis results.

Images