Process pipeline fatigue damage identification and prediction methods, systems, equipment and media

Abstract

The present invention relates to a process pipeline fatigue damage identification and prediction method, system, equipment and medium, the method comprising: calculating the failure probability coefficient of each process pipeline of an offshore oil platform, determining the key process pipeline of multi-mode signal detection; obtaining multi-mode detection data of the key process pipeline, and performing damage identification based on the obtained multi-mode detection data to obtain damage identification results of the key process pipeline; based on the damage identification results, performing fatigue life prediction on the key process pipeline according to stress-strain measurement data to obtain fatigue life prediction results of the key process pipeline. The present invention classifies and identifies the key process pipelines of the offshore platform in combination with process flow parameters, noise levels and vibration parameters, and carries out corresponding fatigue analysis, which can be widely used in the fields of offshore oil safety assessment, prediction analysis and safe production technology.

Description

Technical Field

[0001] The present invention relates to the field of offshore oil safety assessment, prediction analysis and safe production technology, and in particular to a process pipeline fatigue damage identification and prediction method, system, equipment and medium based on multi-mode fusion. Background Art

[0002] The processing media of offshore oil platforms are all flammable and explosive hydrocarbons, and the process has a certain pressure, even high pressure. Once a leak occurs, it will lead to a large amount of hydrocarbon leakage, causing fire and explosion and other accident risks. According to incomplete statistics, oil and gas leakage accounts for more than 1 / 3 of offshore oil accident statistics, and is the main cause of major accident risks in offshore oil development.

[0003] The design life of an offshore oil platform is generally more than 20 years. Offshore oil platforms that have reached their design life are often still in service beyond their service life. However, life extension assessments or regular special inspections do not involve the inspection and assessment of process pipelines. The strength and structure of key process pipelines will be weakened or damaged under long-term oil and gas corrosion, vibration effects, and time effects, which will bury the hidden dangers of failure and leakage of key process pipelines.

[0004] However, it is difficult to achieve comprehensive coverage of process pipeline damage by non-destructive testing technology, mainly because the pipeline configuration is complex, the location is changeable, and it is impossible to combine the load for prediction and analysis. The single-factor sensor signal recognition has the problem of unguaranteed accuracy and single data source signal. Summary of the invention

[0005] In view of the above problems, the purpose of the present invention is to provide a method, system, equipment and medium for identifying and predicting fatigue damage of process pipelines based on multi-mode fusion, combining multiple sensor signals for fusion analysis, so as to effectively identify damage to key process pipelines of long-term offshore oil platforms and perform fatigue prediction analysis, so as to know the safety status of key process pipelines, facilitate corresponding control and intervention in advance, and prevent sudden failure of process pipelines, thereby causing fire and explosion accidents.

[0006] To achieve the above object, the present invention adopts the following technical solutions:

[0007] In a first aspect, the present invention provides a method for identifying and predicting fatigue damage of a process pipeline, which comprises the following steps:

[0008] Calculate the failure probability coefficient of each process pipeline on the offshore oil platform and determine the key process pipeline for multi-mode signal detection;

[0009] Acquire multi-mode inspection data of key process pipelines, and perform damage identification based on the acquired multi-mode inspection data to obtain damage identification results of key process pipelines;

[0010] Based on the damage identification results, the fatigue life of the key process pipeline is predicted according to the stress-strain measurement data to obtain the fatigue life prediction results of the key process pipeline.

[0011] Furthermore, the method for calculating the failure probability coefficient of each process pipeline of the offshore oil platform and determining the key process pipeline for multi-mode signal detection includes:

[0012] Conduct fluid vibration assessment, fluid pulsation assessment and high-frequency acoustic vibration assessment in the process pipeline of the offshore oil platform to obtain the failure probability coefficient of each process pipeline;

[0013] Based on the obtained failure probability coefficient of each process pipeline, the weak position of the offshore oil platform process pipeline is determined as the key process pipeline for multi-mode signal detection.

[0014] Further, the method of acquiring multi-mode detection data of a key process pipeline, and performing damage identification based on the acquired multi-mode detection data to obtain a damage identification result of the key process pipeline comprises the following steps:

[0015] Conduct vibration measurement and acoustic emission measurement on key process pipelines to obtain vibration signals and acoustic emission signals of key process pipelines;

[0016] The vibration signals and acoustic emission signals of the key process pipelines are preprocessed to obtain input vectors, which are then input into the pre-built multi-mode fusion damage identification model to obtain the multi-mode fusion damage identification results.

[0017] Furthermore, the method for constructing the multi-mode fusion damage identification model includes the following steps:

[0018] Preprocess the vibration signal and input it into the BP neural network intelligent model for damage identification to obtain the damage identification result based on the vibration signal;

[0019] Preprocess the acoustic emission signal and input it into the PNN neural network model for damage identification to obtain the damage identification result based on the acoustic emission signal;

[0020] A multi-mode fusion damage identification model is trained. The model takes the fusion vector of the vibration signal and the acoustic emission signal as input and takes the fusion vector of the damage identification result based on the vibration signal and the damage identification result based on the acoustic emission signal as output.

[0021] Further, the vibration signal is preprocessed and input into the BP neural network intelligent model for damage identification, and the method for obtaining the damage identification result based on the vibration signal includes:

[0022] Obtain vibration signals of key process pipelines;

[0023] Based on modal theory, the vibration signals of key process pipelines are preprocessed to obtain pipeline vibration modal parameters.

[0024] The pipeline vibration modal parameters are input into the BP neural network model for damage location to obtain the damage situation and location.

[0025] Further, the acoustic emission signal is preprocessed and input into the PNN neural network model for damage identification, and the method for obtaining the damage identification result based on the acoustic emission signal includes the following steps:

[0026] Based on wavelet transform and EMD decomposition, feature extraction is performed on the acquired acoustic emission signal to obtain feature vectors;

[0027] Combined with the PNN neural network, the extracted feature vector is compared with the pattern sample to obtain the network output classification result;

[0028] The signal time difference is obtained based on the acoustic emission signal, and the network output classification result is judged by the signal time difference to determine the noise or crack damage during damage identification.

[0029] Furthermore, based on the damage identification result, fatigue life prediction is performed on the key process pipeline according to the stress-strain measurement data, and a method for obtaining fatigue life prediction results of the key process pipeline includes:

[0030] Obtain stress levels at stress concentration points of key process pipelines through stress and strain measurement devices;

[0031] The obtained stress level is preprocessed, and the stress spectrum is compiled using the rain flow counting method. The fatigue life of the key process pipeline is evaluated in combination with the linear damage accumulation theory.

[0032] In a second aspect, the present invention provides a process pipeline fatigue damage identification and prediction system, which includes:

[0033] The preliminary location determination module is used to calculate the failure probability coefficient of the key process pipeline and determine the key process pipeline for multi-mode signal detection;

[0034] The multi-mode fusion identification module is used to obtain multi-mode detection data of key process pipelines, and perform damage identification based on the obtained multi-mode detection data to obtain damage identification results of key process pipelines;

[0035] The fatigue prediction module is used to predict the fatigue life of the key process pipeline according to the stress-strain measurement data to obtain the fatigue life prediction results of the key process pipeline.

[0036] In a third aspect, the present invention provides a processing device, which includes at least a processor and a memory, wherein a computer program is stored in the memory, and when the processor runs the computer program, the computer program is executed to implement the steps of the process pipeline fatigue damage identification and prediction method.

[0037] In a fourth aspect, the present invention provides a computer storage medium having computer-readable instructions stored thereon, wherein the computer-readable instructions can be executed by a processor to implement the steps of the process pipeline fatigue damage identification and prediction method.

[0038] Due to the adoption of the above technical solution, the present invention has the following advantages: the present invention combines the multi-mode fusion method to process and predict the detection signal to analyze the damage and cracks of the key process pipeline and locate them. The fatigue life of the pipeline is predicted by the stress spectrum to determine the safety status of the pipeline, thereby realizing the safety assessment of the process pipeline of the in-service platform. Therefore, the present invention can be widely used in the fields of marine oil safety assessment, prediction analysis and safe production technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Throughout the accompanying drawings, the same reference numerals are used to represent the same components. In the accompanying drawings:

[0040] Figure 1 It is a flow chart of a process pipeline fatigue damage and prediction method based on multi-mode fusion provided by an embodiment of the present invention;

[0041] Figure 2 It is a fluid to vibration assessment process provided by an embodiment of the present invention;

[0042] Figure 3 This is a fluid pulsation quantitative evaluation process provided by an embodiment of the present invention;

[0043] Figure 4 This is a high-frequency acoustic vibration AIV evaluation process provided by an embodiment of the present invention;

[0044] Figure 5 is a comparison LOF table provided in an embodiment of the present invention;

[0045] Figure 6 is a quantitative evaluation criterion for the main pipeline provided by an embodiment of the present invention;

[0046] Figure 7 is a branch pipeline quantitative evaluation criterion provided by an embodiment of the present invention;

[0047] Figure 8is a quantitative evaluation criterion for hot well pipelines provided in an embodiment of the present invention;

[0048] Fig. 9 A damage location method based on vibration sensing analysis provided by an embodiment of the present invention;

[0049] Fig.10 A neural network structure based on vibration damage identification provided by an embodiment of the present invention;

[0050] Fig.11 It is a damage identification and analysis process based on acoustic emission provided by an embodiment of the present invention;

[0051] Fig.12 It is a multi-mode fusion network structure provided by an embodiment of the present invention;

[0052] Fig.13 is a modal analysis provided by an embodiment of the present invention;

[0053] Fig.14 is a flow chart of determining damage location using a BP neural network provided by an embodiment of the present invention;

[0054] Figure 15a to Figure 15d The vibration information recognition BP network neural model and damage fitting result provided by the embodiment of the present invention;

[0055] Fig.16a and Fig.16b It is the rain flow counting statistics provided by the embodiment of the present invention. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solution and advantages of the embodiment of the present invention clearer, the technical solution of the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings of the embodiment of the present invention. Obviously, the described embodiment is a part of the embodiment of the present invention, not all of the embodiments. Based on the described embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field belong to the scope of protection of the present invention.

[0057] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0058] Because damage and cracks in process pipelines are usually difficult to confirm, it is necessary to analyze them in combination with detection data to evaluate the pipeline status. In order to solve the problem that single signal errors are difficult to control, a multi-mode fusion method is combined to perform predictive analysis through a neural network model to accurately evaluate damage and cracks. The present invention uses on-site detection signals as the basic input, and conducts a variety of analyses based on signal preprocessing, attempting to propose an identification and analysis of weak links in process pipelines without affecting production, so as to take timely measures for weak links in pipelines and prevent various accidents and losses caused by sudden failure of pipelines.

[0059] Some embodiments of the present invention disclose a method for identifying and predicting fatigue damage of process pipelines based on multi-mode fusion. In combination with existing databases and test data, the damage and crack positions are located by collecting on-site detection signals and using a multi-mode fusion network model. For undamaged and cracked pipelines, fatigue life is predicted by stress spectra in view of the cumulative effect of vibration alternating loads. Based on theoretical analysis, a multi-mode fusion process pipeline fatigue damage and prediction software platform is compiled. By reading the detection data, the above analysis is quickly completed, and the weak links or remaining life of the pipeline are output, thereby providing a basis for decision-making on site.

[0060] Correspondingly, some other embodiments of the present invention provide a process pipeline fatigue damage identification and prediction system, equipment and medium.

[0061] Example 1

[0062] like Figure 1 As shown, this embodiment provides a method for identifying and predicting fatigue damage of a process pipeline, comprising the following steps:

[0063] S1. Calculate the failure probability coefficient (LOF) of each process pipeline of the offshore oil platform and determine the key process pipeline for multi-mode signal detection;

[0064] S2. Acquire multi-mode detection data of key process pipelines, and perform damage identification based on the acquired multi-mode detection data to obtain damage identification results of key process pipelines;

[0065] S3. Based on the damage identification results, fatigue life prediction of key process pipelines is performed according to stress-strain measurement data to obtain fatigue life prediction results of key process pipelines.

[0066] In a preferred embodiment, in the above step S1, when calculating the failure probability coefficient of the process pipeline of the offshore oil platform, a method combining fluid pulsation and high-frequency acoustics can be used.

[0067] This can be achieved by following the steps below:

[0068] S1.1. Conduct fluid vibration assessment, fluid pulsation assessment and high-frequency acoustic vibration assessment in the process pipelines of offshore oil platforms respectively to obtain the failure probability coefficient of each process pipeline;

[0069] S1.2. Based on the obtained failure probability coefficient of each process pipeline, the weak position of the offshore oil platform process pipeline is determined as the key process pipeline for multi-mode signal detection.

[0070] In a preferred embodiment, Figure 2 As shown, in the above step S1.1, the method for evaluating the vibration of the fluid in the process pipeline of the offshore oil platform includes the following steps:

[0071] ① Determine the fluid quality in a process pipeline of an offshore oil platform, i.e. ρv 2 , where ρ is the fluid density and v is the fluid velocity;

[0072] ② Determine the fluid viscosity coefficient FVF in the process pipeline;

[0073] ③ Determine the support layout of the process pipeline, and determine the vortex frequency F of the process pipeline according to the determined support layout. V ;

[0074] ④ According to the determined fluid mass, fluid viscosity coefficient and Fv, the disturbance LOF coefficient caused by the flow is calculated, and the disturbance LOF coefficient is corrected to obtain its failure possibility coefficient; when correcting the failure possibility coefficient, an advanced screening method is used, specifically, the basic natural frequency of the advanced screening method is set to 1-3Hz;

[0075] ⑤ Repeat steps ① to ④ to calculate the failure probability coefficients of other process pipelines in the offshore oil platform.

[0076] Among them, according to the bracket arrangement type as shown in Table 1 below, F V The calculation method is shown in Table 2 below.

[0077] Table 1 Bracket arrangement

[0078]

[0079] Table 2 Calculation method of Fv

[0080]

[0081] In a preferred embodiment, Figure 3 As shown, the method for evaluating fluid pulsation of each process pipeline of an offshore oil platform comprises the following steps:

[0082] ① Determine the critical diameter of a process pipeline in an offshore oil platform;

[0083] Among them, the calculation formula for the critical diameter of a process pipeline is:

[0084]

[0085] Where, d crit is the critical diameter.

[0086] ② Determine the relationship between the diameter of the process pipeline and the critical diameter. If the diameter of the process pipeline is smaller than the critical diameter, the LOF value of the process pipeline is 0.2. If the diameter of the process pipeline is greater than or equal to the critical diameter, proceed to step ③.

[0087] ③ Determine whether the Reynolds number flowing through the process pipeline is greater than the preset value (e.g. 1.6×10 7 ), if it is greater, go to step ④, otherwise go to step ⑤;

[0088] ④ Calculate the Strouhal number S of the process pipeline according to the following formula;

[0089]

[0090] Among them, d int is the inner diameter of the branch pipeline and D int The inner diameter of the main line.

[0091] ⑤ Calculate according to the following formula and obtain the S of the process pipeline after correction:

[0092]

[0093] Where Re is the Reynolds number.

[0094] ⑥ Calculate the Fv of the process pipeline based on the S of the branch pipe;

[0095] ⑦ Compare the calculated Fv with the acoustic natural frequency Fs, and obtain the LOF coefficient of the process pipeline based on the comparison result;

[0096] The calculation formula of Fs is:

[0097]

[0098] When Fv is greater than or equal to Fs, the LOF coefficient of the process pipeline is 1; when Fv is greater than Fs, the LOF coefficient of the process pipeline is 0.29.

[0099] ⑧ Repeat steps ① to ⑧ to calculate the LOF coefficient of each process pipeline.

[0100] In a preferred embodiment, Figure 4As shown, the high frequency acoustic vibration evaluation method comprises the following steps:

[0101] ① Calculate the noise level at the sound source;

[0102] The calculation formula is:

[0103]

[0104] Wherein, P1 is the inlet pressure value of the pressure reducing facility; P2 is the outlet pressure value of the pressure reducing facility; T e is the inlet temperature; M W is the molar mass of the medium; W is the mass flow rate; SFF is the sonic flow correction factor.

[0105] ② Determine whether the valve core adopts low noise mode when the valve is the excitation source. If so, proceed to step ③, otherwise proceed to step ④;

[0106] ③According to the data provided by the valve manufacturer, correct the noise level at the sound source and proceed to step ④;

[0107] For example, if the low noise valve core is reduced by 15dB, this value should be subtracted from the calculated PWL. When using this method, the PWL provided by the valve manufacturer must not be used;

[0108] ④ Compare whether the noise value is greater than or equal to a preset threshold (e.g. 155 decibels). If it is less than, the LOF value of the point is set to 0.29, otherwise proceed to step ⑤;

[0109] ⑤ Go to the next welding discontinuity point (such as SBC, welding tee or welding support, etc.) and calculate the attenuated noise value;

[0110] The calculation formula is:

[0111]

[0112] Among them, L dis is the distance between the excitation source and the weld discontinuity.

[0113] ⑥ Determine whether there are other excitation sources. If not, proceed to step ⑦. If yes, consider all excitation sources, calculate the attenuated noise value at the discontinuity, and then proceed to step ⑦;

[0114] ⑦ Compare the noise value at this time with the preset value (e.g. 155 decibels). If the noise value is greater than or equal to the preset value, calculate the LOF value at the discontinuity. If the noise value is less than the preset value, the main line LOF is equal to the maximum discontinuity location LOF from the source to that location, and the LOF of the subsequent length of the pipeline = 0.29.

[0115] In a preferred embodiment, in the above step S1.2, the method for determining the weak position of the offshore oil platform process pipeline based on the obtained failure probability coefficient is: based on the calculated failure probability coefficient (LOF) of each process pipeline, comparing the LOF table (see Figure 5 ) and the key assessment acceptance form (see Figure 6-8 ), identify the weak locations of offshore oil platform process pipelines as key process pipelines that need to be analyzed in depth.

[0116] In a preferred embodiment, in the above step S2, the method of obtaining multi-mode detection data of the key process pipeline, and performing damage identification based on the obtained multi-mode detection data to obtain the damage identification result of the key process pipeline includes the following steps:

[0117] S2.1. Perform vibration measurement and acoustic emission measurement on key process pipelines to obtain vibration signals and acoustic emission signals of key process pipelines;

[0118] S2.2. Preprocess the vibration signals and acoustic emission signals of the key process pipeline to obtain input vectors, which are input into the pre-built multi-mode fusion damage identification model to obtain multi-mode fusion damage identification results.

[0119] In a preferred embodiment, in the above step S2.2, the method for constructing the multi-modal fusion damage identification model includes the following steps:

[0120] S2.2.1. Preprocess the vibration signal and input it into the BP neural network intelligent model for damage identification to obtain the damage identification result based on the vibration signal;

[0121] S2.2.2, preprocessing the acoustic emission signal and inputting it into the PNN neural network model for damage identification, thereby obtaining a damage identification result based on the acoustic emission signal;

[0122] S2.2.3. Train a multi-modal fusion damage identification model, which takes the fusion vector of the vibration signal and the acoustic emission signal as input and takes the fusion vector of the damage identification result based on the vibration signal and the damage identification result based on the acoustic emission signal as output.

[0123] In a preferred embodiment, in the above step S2.2.1, if Fig. 9 As shown, the vibration signal is preprocessed and input into the BP neural network intelligent model for damage identification, and the method for obtaining the damage identification result based on the vibration signal includes the following steps:

[0124] ① Obtain vibration signals of key process pipelines;

[0125] ② Based on the modal theory, the vibration signals of key process pipelines are preprocessed to obtain pipeline vibration modal parameters, which mainly include natural frequency, mode and damping;

[0126] ③ Input the pipeline vibration modal parameters into the BP neural network model for damage location to obtain the damage condition and location.

[0127] Among them, the BP neural network is a neural network with error back propagation, and different neurons have different weights and thresholds. By combining the learning and training samples of big data, the weights and thresholds are repeatedly iterated and modified to establish an accurate mapping relationship between input and output. Specifically, in the embodiment of the present invention, the learning and training samples of the BP neural network intelligent model are vibration signal big data composed of previous oil field field detection data and test simulation data. The constructed BP neural network intelligent model is trained based on the vibration signal big data to obtain a trained BP neural network intelligent model for damage identification.

[0128] like Fig.10 As shown, the BP neural network intelligent model in this embodiment includes an input layer, a hidden layer and an output layer. The input layer uses the first ten-order normalized natural frequency change ratio (calculated based on the initial natural frequency of each mode, the structural natural frequency after damage, etc., and the damping is ignored) as input, and the output layer uses the damage position as output.

[0129] In a preferred embodiment, in the above step S2.2.3, if Fig.11 As shown, the method for preprocessing the acoustic emission signal and inputting it into the PNN neural network model for damage identification to obtain the damage identification result based on the acoustic emission signal includes the following steps:

[0130] ① Based on wavelet transform and EMD decomposition, feature extraction is performed on the acquired acoustic emission signal to obtain feature vectors;

[0131] ② Combined with the PNN neural network (probabilistic neural network), the extracted feature vector is compared with the pattern sample (taken from the database and test sample data), the matching relationship between the input sample and the pattern sample is analyzed at the pattern layer, and the probabilities of different categories are processed at the summation layer to obtain the network output classification result;

[0132] ③ Based on the acoustic emission signal, the signal time difference is obtained, and the network output classification result is judged by the signal time difference to determine the noise or crack damage during damage identification.

[0133] In a preferred embodiment, in the above step S2.2, if Fig.12As shown, the collected and processed vibration and acoustic emission signals are preprocessed to obtain 11-dimensional data, namely, the standardized frequency change rate of the first ten orders + the data after acoustic emission recognition processing, which are input into the multi-mode fusion damage identification model for fatigue crack location to obtain the multi-mode fusion damage identification result.

[0134] In a preferred embodiment, the above step S3 includes the following steps:

[0135] S3.1. Obtain the stress level at the stress concentration point of the primary selected position of the key process pipeline through the stress and strain measurement device;

[0136] S3.2. Preprocess the obtained stress level, including removing zero drift, abnormal signals and filtering, compile the stress spectrum using the rain flow counting method, and evaluate the fatigue life of key process pipelines in combination with the Palmgren-Miner (linear damage accumulation) theory.

[0137] Example 2

[0138] This embodiment provides a detailed description of the process pipeline fatigue damage and prediction method provided in Example 1. The implementation method mainly includes the following steps:

[0139] (1) Collect on-site process flow parameters, noise levels, and vibration parameters, and combine Figure 2-Figure 4 The process is to conduct a preliminary analysis of the offshore oil platform process pipeline, calculate the LOF value, and then Figure 5-Figure 8 Conduct preliminary scope screening of offshore oil platform process pipelines to identify key process pipelines.

[0140] (2) Arrange vibration measurement points for the selected key process pipelines. After processing the vibration signal, select the measurement points where the energy exceeds the specification through the energy method, analyze the pipeline modal characteristics, and obtain the modal parameters: natural frequency, mode, damping, etc. ( Fig.13 shown).

[0141] (3) The BP network neural model trained with vibration big data is used to analyze the data after detection. Since the frequency change rate is related to the damage location and damage degree, the frequency change rate is:

[0142] FFC=g(r)f(ΔK,ΔM) (7)

[0143] After Taylor series expansion, it can be transformed into:

[0144]

[0145] Its positioning is defined using input parameters as follows:

[0146] {input}={NFCR1, NFCR2,..., NFCR i , ..., NFCR m} (9)

[0147] The analysis process of damage location identification based on BP neural network improved by genetic algorithm is shown in Fig.14 shown.

[0148] (4) Arrange acoustic emission detection devices at key process pipelines. Decompose signal features through EMD and wavelet packets to extract characteristic signals. On this basis, analyze parameters through the PNN neural network intelligent model.

[0149] (5) Figure 15a to Figure 15d As shown in the figure, the vibration modal parameters and the data obtained by acoustic emission are fused and analyzed using the time difference method combined with the BP neural network to provide a preliminary damage location. The acoustic emission data are further identified by the PNN neural network, and the preliminary damage location is compared to determine the location of the damage and cracks.

[0150] (6) When no damage or cracks are identified during the inspection, stress and strain measurements are performed on the key process pipelines identified in step (1).

[0151] (7) Fig.16a and Fig.16b As shown, after filtering the collected data, the stress amplitude results are statistically analyzed using the rain flow counting method. On this basis, the accumulated damage is calculated to evaluate the remaining life of the key pipeline under the current working condition.

[0152] An embodiment of the present invention provides a process pipeline fatigue damage and prediction method based on multi-mode fusion, which realizes the identification of damage and cracks of key process pipelines and the evaluation of fatigue life based on the collection and processing of multiple sensor data, thereby effectively evaluating the safety of key process pipelines in service for a long time and providing a decision-making basis for preventing various accidents or incidents caused by pipeline failure.

[0153] Example 3

[0154] The above-mentioned embodiment 1 provides a method for identifying and predicting fatigue damage of a process pipeline. Correspondingly, this embodiment provides a system for identifying and predicting fatigue damage of a process pipeline. The system provided in this embodiment can implement a method for identifying and predicting fatigue damage of a process pipeline in embodiment 1. The identification system can be implemented by software, hardware, or a combination of software and hardware. For example, the system may include integrated or separate functional modules or functional units to execute the corresponding steps in each method of embodiment 1. Since the identification system of this embodiment is basically similar to the method embodiment, the process described in this embodiment is relatively simple. For relevant matters, please refer to the partial description of embodiment 1. The embodiment of the system of this embodiment is merely illustrative.

[0155] This embodiment provides a process pipeline fatigue damage identification and prediction system, including:

[0156] The preliminary location determination module is used to calculate the failure probability coefficient of the key process pipeline and determine the key process pipeline for multi-mode signal detection;

[0157] The multi-mode fusion identification module is used to obtain multi-mode detection data of key process pipelines, and perform damage identification based on the obtained multi-mode detection data to obtain damage identification results of key process pipelines;

[0158] The fatigue prediction module is used to predict the fatigue life of the key process pipeline according to the stress-strain measurement data to obtain the fatigue life prediction results of the key process pipeline.

[0159] Example 4

[0160] This embodiment provides a processing device corresponding to the process pipeline fatigue damage identification and prediction method provided in this embodiment 1. The processing device can be a processing device for a client, such as a mobile phone, a laptop computer, a tablet computer, a desktop computer, etc., to execute the method of embodiment 1.

[0161] The processing device includes a processor, a memory, a communication interface and a bus, and the processor, the memory and the communication interface are connected through the bus to complete mutual communication. The memory stores a computer program that can be run on the processor, and the processor executes a process pipeline fatigue damage and prediction method provided in this embodiment 1 when running the computer program.

[0162] In some implementations, the memory may be a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk memory.

[0163] In some other implementations, the processor may be a central processing unit (CPU), a digital signal processor (DSP), or other general-purpose processors of various types, which are not limited herein.

[0164] Example 5

[0165] A process pipeline fatigue damage identification and prediction method of this embodiment 1 can be specifically implemented as a computer program product. The computer program product may include a computer-readable storage medium on which computer-readable program instructions for executing the process pipeline fatigue damage identification and prediction method described in this embodiment 1 are loaded.

[0166] Computer readable storage media can be tangible devices that hold and store instructions used by instruction execution devices. Computer readable storage media can be, for example, but not limited to, electronic storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any combination thereof.

[0167] It should be noted that the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple embodiments of the present application. Each box in the flowchart or block diagram may represent a module, a program segment or a part of the code, and the module, program segment or a part of the code contains one or more executable instructions for implementing the specified logical functions.

[0168] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

[0169] The above embodiments are only used to illustrate the present invention, wherein the components, devices or steps and sequences of the embodiments can be changed, and each implementation mode can be combined or deleted as needed. Not all components in the drawings are necessary. The general principles defined in this application can be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application will not be limited to the embodiments described herein, and any equivalent transformations and improvements based on the technical solution of the present invention should not be excluded from the protection scope of the present invention.

Claims

1. A method for identifying and predicting fatigue damage of a process pipeline, characterized in that: The method comprises the following steps: Calculate the failure probability coefficient of each process pipeline on the offshore oil platform and determine the key process pipeline for multi-mode signal detection; The method for calculating the failure probability coefficient of each process pipeline of an offshore oil platform and determining the key process pipeline for multi-mode signal detection includes: Conduct fluid vibration assessment, fluid pulsation assessment and high-frequency acoustic vibration assessment in the process pipeline of the offshore oil platform to obtain the failure probability coefficient of each process pipeline; Based on the obtained failure probability coefficients of each process pipeline and the preset criteria, the weak positions of the process pipelines of the offshore oil platform are determined as the key process pipelines for multi-mode signal detection; Acquire multi-mode inspection data of key process pipelines, and perform damage identification based on the acquired multi-mode inspection data to obtain damage identification results of key process pipelines; The method of acquiring multimode detection data of a key process pipeline, and performing damage identification based on the acquired multimode detection data to obtain a damage identification result of the key process pipeline comprises the following steps: Conduct vibration measurement and acoustic emission measurement on key process pipelines to obtain vibration signals and acoustic emission signals of key process pipelines; The vibration signals and acoustic emission signals of key process pipelines are preprocessed to obtain input vectors, which are then input into the pre-built multi-mode fusion damage identification model to obtain multi-mode fusion damage identification results. The method for constructing a multi-mode fusion damage identification model includes the following steps: Preprocess the vibration signal and input it into the BP neural network intelligent model for damage identification to obtain the damage identification result based on the vibration signal; Preprocess the acoustic emission signal and input it into the PNN neural network model for damage identification to obtain the damage identification result based on the acoustic emission signal; Training a multi-mode fusion damage identification model, which takes the fusion vector of the vibration signal and the acoustic emission signal as input and takes the fusion vector of the damage identification result based on the vibration signal and the damage identification result based on the acoustic emission signal as output; Based on the damage identification results, the fatigue life of the key process pipeline is predicted according to the stress-strain measurement data to obtain the fatigue life prediction results of the key process pipeline.

2. A process pipeline fatigue damage identification and prediction method according to claim 1, characterized in that: The method of preprocessing the vibration signal and inputting it into the BP neural network intelligent model for damage identification to obtain the damage identification result based on the vibration signal includes: Obtain vibration signals of key process pipelines; Based on modal theory, the vibration signals of key process pipelines are preprocessed to obtain pipeline vibration modal parameters. The pipeline vibration modal parameters are input into the BP neural network model for damage location to obtain the damage situation and location.

3. A process pipeline fatigue damage identification and prediction method according to claim 1, characterized in that: The method of preprocessing the acoustic emission signal and inputting it into the PNN neural network model for damage identification to obtain the damage identification result based on the acoustic emission signal comprises the following steps: Based on wavelet transform and EMD decomposition, feature extraction is performed on the acquired acoustic emission signal to obtain feature vectors; Combined with the PNN neural network, the extracted feature vector is compared with the pattern sample to obtain the network output classification result; The signal time difference is obtained based on the acoustic emission signal, and the network output classification result is judged by the signal time difference to determine the noise or crack damage during damage identification.

4. A process pipeline fatigue damage identification and prediction method according to claim 1, characterized in that: Based on the damage identification results, the fatigue life of the key process pipeline is predicted according to the stress and strain measurement data, and the method for obtaining the fatigue life prediction result of the key process pipeline includes: Obtain stress levels at stress concentration points of key process pipelines through stress and strain measurement devices; The obtained stress level is preprocessed, and the stress spectrum is compiled using the rain flow counting method. The fatigue life of the key process pipeline is evaluated in combination with the linear damage accumulation theory.

5. A process pipeline fatigue damage identification and prediction system, characterized in that: include: The preliminary location determination module is used to calculate the failure probability coefficient of the key process pipeline and determine the key process pipeline for multi-mode signal detection, including: Conduct fluid vibration assessment, fluid pulsation assessment and high-frequency acoustic vibration assessment in the process pipeline of the offshore oil platform to obtain the failure probability coefficient of each process pipeline; Based on the obtained failure probability coefficients of each process pipeline and the preset criteria, the weak positions of the process pipelines of the offshore oil platform are determined as the key process pipelines for multi-mode signal detection; The multi-mode fusion identification module is used to obtain multi-mode detection data of key process pipelines, and perform damage identification based on the obtained multi-mode detection data to obtain damage identification results of key process pipelines, including: Conduct vibration measurement and acoustic emission measurement on key process pipelines to obtain vibration signals and acoustic emission signals of key process pipelines; The vibration signals and acoustic emission signals of key process pipelines are preprocessed to obtain input vectors, which are then input into the pre-built multi-mode fusion damage identification model to obtain multi-mode fusion damage identification results. The construction of the multi-mode fusion damage identification model includes: Preprocess the vibration signal and input it into the BP neural network intelligent model for damage identification to obtain the damage identification result based on the vibration signal; Preprocess the acoustic emission signal and input it into the PNN neural network model for damage identification to obtain the damage identification result based on the acoustic emission signal; Training a multi-mode fusion damage identification model, which takes the fusion vector of the vibration signal and the acoustic emission signal as input and takes the fusion vector of the damage identification result based on the vibration signal and the damage identification result based on the acoustic emission signal as output; The fatigue prediction module is used to predict the fatigue life of the key process pipeline according to the stress-strain measurement data to obtain the fatigue life prediction results of the key process pipeline.

6. A processing device, comprising at least a processor and a memory, wherein a computer program is stored in the memory, wherein: When the processor runs the computer program, the processor executes the steps of the process pipeline fatigue damage identification and prediction method according to any one of claims 1 to 4.

7. A computer storage medium, characterized in that: Computer-readable instructions are stored thereon, and the computer-readable instructions can be executed by a processor to implement the steps of the process pipeline fatigue damage identification and prediction method according to any one of claims 1 to 4.

Images