A method for fatigue identification and life prediction of tubing hanger of Christmas tree

Abstract

The application discloses a kind of for oil tree oil pipe hanger fatigue identification and life prediction method, belong to marine oil engineering technical field, including the following steps: the fluid vibration evaluation in the deep-sea oil tree oil pipe hanger of marine oil platform is carried out, and heat flux is detected and identified using sensor;Obtain the multimode detection data of oil pipe hanger, and carry out fatigue identification based on the obtained multimode detection data, obtain the multimode fusion fatigue identification result of oil pipe hanger;Based on multimode fusion fatigue identification result, according to stress-strain measurement data, the life of deep-sea oil tree hanger is predicted, and the fatigue life prediction result of oil pipe hanger is obtained;In the application, the overall evaluation and accurate identification of the fatigue damage of oil pipe hanger are realized, compared with single signal analysis method, multimode fusion technology can more effectively eliminate noise interference and signal distortion, improve the accuracy and reliability of fatigue damage identification.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of offshore oil engineering, and particularly relates to a method for fatigue identification and life prediction of a tubing hanger of an offshore tree. BACKGROUND

[0002] The deepwater tubing hanger of an offshore tree is a key equipment for offshore underwater oil and gas exploitation. The offshore tree equipment is located below 500 meters under the sea, and the marine environment is complex and harsh. Therefore, ensuring the safe and stable operation of the tubing hanger of the offshore tree becomes an important technology.

[0003] In the field of offshore oil engineering, the deepwater tubing hanger of an offshore tree is a core equipment for underwater oil and gas exploitation, and its safe and stable operation is crucial to the reliability of the entire production system. At present, with the continuous development of deep-sea oil and gas resources, the marine environment faced by the tubing hanger of the offshore tree is becoming more complex and harsh, including high pressure, low temperature, strong corrosion, and high dynamic load, etc. These factors pose a serious challenge to the structural integrity and service life of the tubing hanger.

[0004] However, the existing fatigue damage identification and life prediction technology of the tubing hanger mainly relies on the analysis of single sensor signals, such as vibration monitoring or stress-strain measurement. This method has obvious limitations: on the one hand, a single signal source may not fully reflect the complex stress state and fatigue damage of the tubing hanger under actual working conditions; on the other hand, due to the complexity and uncertainty of the marine environment, single signal analysis is easily affected by noise interference and signal distortion, resulting in insufficient accuracy of fatigue damage identification and life prediction.

[0005] Therefore, the application designs a method for fatigue identification and life prediction of the tubing hanger of the offshore tree to solve the above problems. SUMMARY

[0006] The purpose of the application is to provide a method for fatigue identification and life prediction of the tubing hanger of the offshore tree to solve the problems in the background.

[0007] To achieve the above purpose, the application adopts the following technical solutions:

[0008] A method for fatigue identification and life prediction of the tubing hanger of the offshore tree, comprising the following steps:

[0009] Obtain multi-modal detection data of the deepwater tubing hanger of the offshore tree, and perform fatigue identification and fatigue position confirmation based on the obtained multi-modal detection data to obtain a multi-modal fusion fatigue identification result of the tubing hanger.

[0010] Based on the multi-mode fusion fatigue identification result, fatigue analysis life prediction is performed on the deep sea Christmas tree tubing hanger according to the stress and strain measurement data, and fatigue life prediction result of the tubing hanger is obtained.

[0011] As a further description of the above technical scheme: the multi-mode detection data of the deep sea Christmas tree tubing hanger is obtained, and fatigue identification is performed based on the obtained multi-mode detection data to obtain the multi-mode fusion fatigue identification result of the tubing hanger, which comprises the following steps:

[0012] The vibration measurement and heat flux measurement are performed on the deep sea Christmas tree tubing hanger to obtain the vibration signal, pipeline vibration modal parameter and heat flux signal, and heat flux change curve of the tubing hanger.

[0013] The vibration signal and heat flux signal of the deep sea Christmas tree tubing hanger are preprocessed to obtain an input vector, which is input into a pre-constructed multi-mode fusion fatigue identification model to obtain a multi-mode fusion fatigue identification result.

[0014] The heat flux change curve of the deep sea Christmas tree tubing hanger is processed to obtain a time-frequency spectrogram, and the pipeline vibration modal parameter and time-frequency spectrogram are preprocessed to obtain an input vector, which is input into a pre-constructed multi-mode fusion fatigue positioning model to obtain a multi-mode fusion fatigue positioning result.

[0015] As a further description of the above technical scheme: the construction method of the multi-mode fusion fatigue identification and fatigue positioning model comprises the following steps:

[0016] The vibration signal and heat flux signal are preprocessed and input into a PNN neural network intelligent model for fatigue identification to obtain a fatigue identification result based on the vibration signal and heat flux signal.

[0017] The pipeline vibration modal parameter and time-frequency spectrogram are preprocessed and input into a deep CNN neural network intelligent model for fatigue positioning to obtain a fatigue positioning result based on the pipeline vibration modal parameter and time-frequency spectrogram.

[0018] The multi-mode fusion fatigue identification model is trained, which takes the fusion vector of the vibration signal, heat flux signal, pipeline vibration modal parameter and time-frequency spectrogram as input, and takes the fusion vector of the fatigue identification result based on the vibration signal and heat flux signal and the fatigue positioning result based on the pipeline vibration modal parameter and time-frequency spectrogram as output, to obtain a multi-mode fusion fatigue identification result.

[0019] As a further description of the above technical scheme: the method for pre-processing the vibration signal and inputting it into a CNN neural network model for fatigue identification to obtain a fatigue identification result based on the vibration signal, which comprises:

[0020] The vibration signal of the deep sea Christmas tree tubing hanger is obtained.

[0021] Based on the modal theory, the obtained vibration signal of the tubing hanger is preprocessed to obtain the modal parameters of the pipeline vibration;

[0022] Based on the heat flux measurement, the heat flux change curve is obtained, and then the time-frequency spectrogram is generated to determine the network output classification result, and the pipeline vibration modal parameters are input into the CNN neural network model for fatigue positioning to obtain the fatigue condition and position.

[0023] As a further description of the above technical solution: the heat flux signal is preprocessed and input into the PNN neural network model for fatigue identification to obtain a method for fatigue identification result based on the heat flux signal, comprising the following steps:

[0024] Based on the Fourier transform, the obtained measurement results are feature extracted to obtain a feature vector;

[0025] The extracted feature vector is compared with the pattern sample in combination with the PNN neural network to obtain the network output classification result;

[0026] Based on the vibration signal extraction of wavelet transform, the vibration signal and the heat flux signal are input into the PNN neural network model to determine the fatigue identification result.

[0027] As a further description of the above technical solution: based on the multi-modal fusion fatigue identification result, the stress and strain measurement data are used to predict the fatigue life of the tubing hanger to obtain the fatigue life prediction result of the key process pipeline, comprising:

[0028] The stress concentration of the tubing hanger is obtained by the stress and strain measurement device;

[0029] The obtained stress is preprocessed, the stress spectrum is prepared by using the rain flow counting method, and the fatigue life of the tubing hanger is evaluated in combination with the linear damage accumulation theory.

[0030] As described above, due to the adoption of the above technical solution, the beneficial effects of the present application are:

[0031] In the present application, by combining vibration signals, heat flux signals, pipeline vibration modal parameters and time-frequency spectrograms and other multiple detection signals, comprehensive evaluation and accurate identification of the fatigue damage of the tubing hanger are realized, compared with the single signal analysis method, the multi-modal fusion technology can more effectively eliminate noise interference and signal distortion, and improve the accuracy and reliability of fatigue damage identification;

[0032] The technical solution utilizes a deep convolutional neural network (CNN) to pre-process and analyze the pipeline vibration modal parameters and time-frequency spectrograms, realizes accurate positioning of the fatigue damage position of the tubing hanger, and enables technical personnel to timely discover and handle potential cracks or damage points, thereby effectively reducing the safety risks in the production process.

[0033] The technical solution is based on multi-modal fusion fatigue identification results and stress-strain measurement data, adopts a rain flow counting method and a linear damage accumulation theory to predict the fatigue life of the tubing hanger, and the prediction result can provide a decision basis for the field, guide technical personnel to reasonably arrange maintenance and maintenance plans, ensure the tubing hanger to operate in a safe state, and thus ensure the safe and stable operation of deep-sea oil and gas exploitation.

[0034] The technical solution realizes automatic processing and analysis of the detection data by compiling a multi-modal fusion oil tree tubing hanger fatigue identification and life prediction software platform, which not only improves the work efficiency, but also reduces the influence of human factors on the analysis result, and further improves the accuracy and reliability of fatigue damage identification and life prediction. BRIEF DESCRIPTION OF DRAWINGS

[0035] Figure 1 is a multi-modal fusion oil tree tubing hanger fatigue identification and life prediction method flowchart provided by an embodiment of the present application;

[0036] Figure 2 is a flowchart of the tubing hanger fatigue positioning method based on the deep convolutional neural network provided by an embodiment of the present application;

[0037] Figure 3 is a flowchart of the tubing hanger fatigue identification method based on the PNN neural network provided by an embodiment of the present application;

[0038] Figure 4 is a PNN neural network fatigue identification flowchart provided by an embodiment of the present application;

[0039] Figure 5 is a CNN neural network damage position determination flowchart provided by an embodiment of the present application. DETAILED DESCRIPTION

[0040] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of protection of the present application.

[0041] Please refer to the drawingsFigure 1 - Appendix Figure 5 The present invention provides a technical solution:

[0042] A method for fatigue identification and life prediction of tubing hangers in wellheads is proposed. Combining existing databases and experimental data, damage and crack locations are identified through the acquisition of field detection signals and a multi-mode fusion network model. Considering the cumulative effect of alternating vibration loads, fatigue life is predicted using stress spectrum analysis. Based on theoretical analysis, a multi-mode fusion software platform for fatigue identification and life prediction of tubing hangers in wellheads is developed. This platform rapidly performs the above analysis by reading detection data and outputs the life of the tubing hanger, thus providing a basis for decision-making in the field.

[0043] This embodiment provides a method for fatigue identification and life prediction of oil well tubing hangers, including the following steps:

[0044] S1. Vibration and heat flux measurements were performed on the deep-sea production tree tubing hanger of an offshore oil platform.

[0045] S2. Obtain multi-mode detection data of the deep-sea production tree tubing hanger, and perform fatigue identification and fatigue localization based on the acquired multi-mode detection data to obtain the fatigue identification and fatigue localization results of the tubing hanger;

[0046] S3. Based on the fatigue identification and positioning results, fatigue life prediction of the tubing hanger is performed according to the stress and strain measurement data, and the fatigue life prediction result of the tubing hanger is obtained.

[0047] In a preferred embodiment, when measuring the vibration of the deep-sea production tree tubing hanger in the offshore oil platform in step S1 above, a combination of fluid vibration assessment, fluid pulsation assessment and high-frequency acoustic methods can be used.

[0048] Specifically, this can be achieved through the following steps:

[0049] S1.1 Conduct fluid analysis to determine the location of the excitation source and the excitation frequency. And pressure pulsation values; perform acoustic characteristic analysis to obtain the natural frequency of the fluid inside the pipe. Structural characteristic analysis was conducted to determine the natural frequencies of the pipeline structure. .

[0050] S1.2 Frequency Avoidance Judgment: Determine the natural frequency of the pipeline structure. Should the frequency of the fluid excitation source be avoided? Determine the natural frequency of the fluid inside the pipe. Should the frequency of the fluid excitation source be avoided? Response analysis is then performed, and if the above frequencies are avoided, the in-pipe fluid acoustic response analysis is performed to calculate the exciting force on the pipeline, and then the forced mechanical response analysis of the pipeline system is carried out.

[0051] S1.3, criterion judgment and iteration: whether the pipeline system vibration criterion is met is verified, if not, the design is modified and the process is returned to determine the basic conditions again; if the vibration criterion is met, whether the fatigue stress criterion is met is further judged, if not, the design is modified and the process is repeated, and if the vibration criterion is met, the vibration analysis is completed.

[0052] For the measurement of heat flux, a heat flux sensor is used to directly measure the heat transferred to the surface on which the sensor is installed, and a common type is a differential temperature thermocouple. Its principle is based on the Seebeck effect, and a temperature difference potential is generated between different metal junctions due to thermal radiation.

[0053] In a preferred embodiment, in the step S2, the method for obtaining the fatigue identification result of the deepwater Christmas tree tubing hanger based on the obtained multi-modal detection data, comprises the following steps:

[0054] S2.1, vibration measurement and heat flux measurement are performed on the deepwater Christmas tree tubing hanger to obtain vibration signals and heat flux signals of the tubing hanger;

[0055] S2.2, the vibration signals and the heat flux signals of the deepwater Christmas tree tubing hanger are pre-processed to obtain an input vector, and a pre-constructed multi-modal fusion fatigue damage identification model is inputted to obtain a multi-modal fusion fatigue damage identification result.

[0056] In a preferred embodiment, in the step S2.2, the method for constructing the multi-modal fusion fatigue identification model, comprises the following steps:

[0057] S2.2.1, the vibration signals and the heat flux signals are pre-processed and inputted into a PNN neural network intelligent model for fatigue identification to obtain a fatigue identification result based on the vibration signals and the heat flux signals;

[0058] S2.2.2, as shown in Figure 2 the pipeline vibration modal parameters and the time-frequency spectrogram results are pre-processed and inputted into a CNN neural network intelligent model for fatigue positioning to obtain a fatigue positioning result based on the pipeline vibration level;

[0059] S2.2.3, the multi-modal fusion fatigue and positioning identification model is trained, the fusion vector of the vibration signals and the heat flux signals is taken as the input, the fusion vector of the fatigue identification results based on the vibration signals and the heat flux signals is taken as the output; the fusion vector of the pipeline vibration modal parameters and the time-frequency spectrogram results is taken as the input, and the fusion vector of the fatigue positioning results based on the vibration modal and the time-frequency spectrogram is taken as the output.

[0060] In a preferred embodiment, the method for pre-processing the vibration signal in step S2.2.1 above and inputting the PNN neural network intelligent model for fatigue identification to obtain the fatigue identification result based on the vibration signal comprises the following steps:

[0061] ①The fluid in the tubing hanger is subjected to vibration evaluation to obtain the vibration evaluation result of the deep-sea Christmas tree tubing hanger; the heat flux is measured by a sensor to obtain the heat flux measurement result of the deep-sea Christmas tree tubing hanger.

[0062] ②The vibration evaluation result is pre-processed based on wavelet variation to extract the vibration signal; the measurement result is extracted as a heat flux signal based on Fourier transform to obtain a heat flux feature vector.

[0063] ③The vibration signal is input into the PNN neural network model for fatigue identification to obtain the fatigue condition of the tubing hanger; the extracted feature vector is compared with a pattern sample by the PNN neural network to obtain a network output classification result for fatigue identification.

[0064] The PNN neural network is a neural network model based on Bayesian decision theory and Parzen window method, and its core idea is to realize pattern classification through probability density function estimation. Specifically, in the embodiment of the present application, the training sample set of the PNN intelligent model is composed of historical oilfield tubing hanger vibration signal data, fatigue calibration experiment data and numerical simulation data. Based on the sample set, the PNN model first performs nonlinear transformation on the input vibration feature vector in the pattern layer, and maps it to a high-dimensional feature space; the summation layer then accumulates and sums the responses of the same pattern to estimate the posterior probability density function of each category; finally, the output layer determines the damage type through the Bayesian decision rule.

[0065] The PNN network structure in the embodiment is composed of an input layer, a pattern layer, a summation layer and an output layer, and the neurons between the layers realize signal transmission through different connection weights. The input layer takes the first ten-order normalized inherent frequency variation ratio (calculated based on the initial inherent frequency under each mode, the structural inherent frequency after damage, etc., and the damping is ignored) as the input, and the output layer takes the fatigue identification as the output.

[0066] In a preferred embodiment, as shown in step S2.2.2 above, Figure 2 the pipeline vibration modal parameter and the time-frequency spectrogram result are pre-processed and input into the CNN neural network model for fatigue positioning to obtain the fatigue positioning result based on the pipeline vibration level; comprising the following steps:

[0067] ①Based on the modal theory, the vibration test of the obtained tubing hanger is processed to obtain the modal parameters of the pipeline vibration; based on the heat flux measurement results, a heat flux change curve is generated.

[0068] ②The vibration modal parameters of the pipeline are preprocessed to obtain the vibration modal vector; based on the heat flux change curve, a heat flux time-frequency spectrogram is further generated.

[0069] ③The vibration modal vector is input into the CNN neural network model for fatigue positioning to obtain the fatigue positioning situation of the tubing hanger; the time-frequency spectrogram is input into the CNN neural network model for fatigue positioning to obtain the fatigue positioning situation or crack damage of the tubing hanger.

[0070] In a preferred embodiment, the above step S3 comprises the following steps:

[0071] S3.1, obtaining the stress level at the primary selected position stress concentration of the key process pipeline through a stress-strain measurement device;

[0072] S3.2, preprocessing the obtained stress level, including removing zero drift, abnormal signals and filtering processing, compiling a stress spectrum by using the rainflow counting method, and evaluating the fatigue life of the key process pipeline in combination with the Palmgren-Miner (linear damage accumulation) theory.

[0073] A processing device corresponding to the method for identifying fatigue and predicting service life of a tubing hanger of a Christmas tree is provided, which can be applied to a processing device of a client, such as a mobile phone, a notebook computer, a tablet computer, a desktop computer, etc., to execute the method for identifying fatigue and predicting service life of a tubing hanger of a Christmas tree.

[0074] The processing device comprises a processor, a memory, a communication interface and a bus, the processor, the memory and the communication interface are connected through the bus to complete the communication among each other. The memory stores a computer program executable on the processor, and the processor executes the computer program to execute the method for identifying fatigue and predicting service life of a tubing hanger of a Christmas tree.

[0075] In some implementations, the memory can be a high-speed random access memory (RAM), and can also include a non-volatile memory, such as at least one disk memory.

[0076] In other implementations, the processor can be a central processing unit (CPU), a digital signal processor (DSP) or various types of general-purpose processors, which are not limited here.

[0077] It should be noted that the flowcharts and block diagrams in the drawings show the architectural, functional and operational aspects of possible implementations of systems, methods and computer program products according to various embodiments of the present application. Each block in the flowcharts or block diagrams can represent a module, a program segment or a portion of code which contains one or more executable instructions for implementing the specified logical function.

[0078] Heat flux: a physical quantity used to describe the rate of heat transfer per unit area per unit time.

[0079] Time-frequency spectrogram: a time-frequency spectrogram, also known as a sound spectrogram, is a graph that represents a signal in both time and frequency dimensions, and can show how the signal changes with time and frequency.

[0080] Since the damage and cracks of tubing hangers are usually difficult to identify, it is necessary to analyze them in combination with detection data to evaluate the state of the tubing hangers. In order to solve the problem that single signal error is difficult to control, a neural network model is used for prediction analysis in combination with multi-modal fusion to accurately evaluate the damage and cracks. The present application takes the field detection signal as the basis for input, carries out various analyses on the basis of signal preprocessing, and completes the life prediction of the tubing hanger.

[0081] The above is only the preferred specific implementation of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can make equivalent replacement or change according to the technical scheme and the inventive concept of the present application within the technical range disclosed by the present application, which should be covered within the protection scope of the present application.

Claims

1. A method for fatigue identification and life prediction of a tubing hanger of an oil tree, characterized in that, Includes the following steps: Conduct fluid vibration assessment within the tubing hanger of the deep-sea production tree of an offshore oil platform, and use sensors to detect and identify heat flux. Multi-mode detection data of the tubing hanger is acquired, and fatigue identification is performed based on the acquired multi-mode detection data to obtain the multi-mode fusion fatigue identification result of the tubing hanger. Based on the multi-mode fusion fatigue identification results, the life prediction of the deep-sea oil production tree hanger is carried out according to the stress and strain measurement data, and the fatigue life prediction result of the tubing hanger is obtained. The method for acquiring multi-mode detection data of the tubing hanger and performing fatigue identification based on the acquired multi-mode detection data to obtain the multi-mode fusion fatigue identification result of the tubing hanger includes the following steps: Vibration and heat flux measurements were performed on the tubing hanger to obtain its vibration and heat flux signals. The vibration signal and heat flux signal of the tubing hanger are preprocessed to obtain the input vector, which is then input into the pre-constructed multi-mode fusion fatigue identification model to obtain the multi-mode fusion fatigue identification result. The method for constructing the multi-modal fusion fatigue recognition model includes the following steps: The vibration signal is preprocessed and then input into the PNN neural network intelligent model for fatigue identification to obtain fatigue identification results based on the vibration signal. The heat flux signal is preprocessed and input into the PNN neural network intelligent model for fatigue identification, resulting in fatigue identification results based on the heat flux signal. The vibration modal parameters of the pipeline are preprocessed and input into a CNN neural network intelligent model for fatigue localization, resulting in fatigue localization results based on the pipeline vibration level. The heat flux measurement results are processed to plot a time-frequency chromatogram, which is then input into a CNN neural network intelligent model for fatigue localization, resulting in fatigue localization results based on the heat flux time-frequency chromatogram. A multi-modal fusion fatigue identification model is trained. The model takes vibration signal, heat flux signal and fusion vector based on pipeline vibration level and heat flux time-frequency chromatogram as input, and takes the fusion result of fatigue identification of vibration signal and heat flux signal and fatigue localization based on pipeline vibration level and heat flux time-frequency chromatogram as output, so as to obtain the multi-modal fusion fatigue identification result.

2. The method for fatigue identification and life prediction of tubing hanger in Christmas tree according to claim 1, characterized in that, The method for preprocessing vibration signals and inputting them into a PNN neural network intelligent model for fatigue identification to obtain fatigue identification results based on vibration signals includes: Vibration assessment of the fluid inside the tubing hanger was conducted to obtain the vibration assessment results of the deep-sea production tree tubing hanger. Vibration signals are extracted by preprocessing vibration assessment results based on wavelet transform. The vibration signal is input into the PNN neural network model for fatigue identification to obtain the fatigue status of the tubing hanger.

3. The method for fatigue identification and life prediction of tubing hanger in Christmas tree according to claim 1, characterized in that, The method for preprocessing heat flux signals and inputting them into a PNN neural network model for fatigue identification to obtain fatigue identification results based on heat flux signals includes: The heat flux measurement results of the deep-sea oil well tubing hanger are obtained by using sensors to measure the heat flux. Based on Fourier transform, the obtained measurement results are used to extract features to obtain the heat flux feature vector; By combining the extracted feature vectors with pattern samples using a PNN neural network, the network output classification results are obtained for fatigue recognition.

4. The method for fatigue identification and life prediction of tubing hanger in Christmas tree of claim 1, wherein, The pipeline vibration modal parameters are preprocessed and input into a CNN neural network intelligent model for fatigue positioning to obtain fatigue positioning results based on pipeline vibration levels, including: The obtained vibration test of the tubing hanger is processed based on modal theory to obtain modal parameters of the pipeline vibration; The pipeline vibration modal parameters are preprocessed to obtain vibration modal vectors; The vibration modal vectors are input into a CNN neural network model for fatigue positioning to obtain tubing hanger fatigue positioning conditions.

5. The method for fatigue identification and life prediction of tubing hanger in Christmas tree of claim 1, wherein, The heat flux measurement results are processed and input into a CNN neural network intelligent model for fatigue positioning to obtain fatigue positioning results based on pipeline vibration levels, including: Based on the heat flux measurement results, a heat flux change curve is generated, and then a heat flux time-frequency spectrogram is generated; The time-frequency spectrogram is input into a CNN neural network model for fatigue positioning to obtain tubing hanger fatigue positioning conditions or crack damage.

6. The method for fatigue identification and life prediction of tubing hanger in Christmas tree of claim 1, wherein, The method for predicting the fatigue life of the deep-sea Christmas tree hanger based on the multi-modal fusion fatigue identification result according to the stress-strain measurement data, including: The stress level of the stress concentration of the key process pipeline is obtained through a stress-strain measurement device; The obtained stress level is preprocessed, a stress spectrum is prepared using the rainflow counting method, and the fatigue life of the tubing hanger is evaluated in combination with the linear damage accumulation theory.

7. A processing device comprising at least a processor and a memory having stored thereon a computer program, characterized in that, The processor runs the computer program to implement the steps of the method for identifying and predicting the fatigue life of the tubing hanger of the Christmas tree as claimed in any one of claims 1-6.

8. A computer storage medium having stored thereon computer readable instructions, characterized in that, The computer read instructions are executed by the processor to implement the method for identifying and predicting the fatigue life of the tubing hanger of the Christmas tree as claimed in any one of claims 1-6.

Images