Method for risk assessment of marine dynamic flexible riser based on fuzzy rule-based inference network

Abstract

This invention relates to the field of flexible riser risk assessment technology, and more particularly to a method for risk assessment of marine dynamic flexible risers based on fuzzy rule inference networks. The method includes: acquiring a set of historical failure data for flexible risers; conducting a failure assessment on the historical failure data set based on a five-level risk scoring standard to obtain a first assessment result; performing feature fusion processing on the first assessment result based on a preset expert weight standard to obtain a second assessment result; obtaining fuzzy feature values ​​based on a Gaussian fuzzy mechanism and the second assessment result; inputting the fuzzy feature values ​​into a preset fuzzy rule inference network model to obtain a fuzzy set output by the fuzzy rule inference network model; and defuzzifying the fuzzy set to obtain the flexible riser risk assessment result. This invention, through the processing of a fuzzy rule inference network model, can effectively handle the multi-factor nonlinear coupling effects in flexible riser systems, thereby improving the accuracy of risk assessment.

Description

Technical Field

[0001] This invention relates to the field of flexible riser risk assessment technology, and in particular to a marine dynamic flexible riser risk assessment method based on fuzzy rule reasoning network. Background Technology

[0002] Marine dynamic flexible risers are core equipment in modern offshore oil and gas development. As a key component connecting surface floating production platforms (such as FPSOs and semi-submersible platforms) to subsea oil and gas production facilities, their primary function is to ensure the stable transport of subsea oil and gas resources, natural gas, crude oil, water, and chemical media. Flexible risers are typically composed of multiple layers of materials with different structures and are constantly exposed to the dynamic marine environment, facing complex loads from waves, currents, climate change, platform movement, and deep-sea earthquakes. These dynamic loads not only increase the risk of fatigue damage to the flexible risers but also exacerbate physical wear and corrosion aging, affecting the safety and reliability of their lifespan. Furthermore, the transported media are highly flammable and explosive; leaks or malfunctions could lead to catastrophic consequences, seriously endangering the marine ecosystem and the lives of platform personnel. Therefore, accurately identifying, quantifying, and effectively managing these risks has become a critical issue that urgently needs to be addressed in offshore oil and gas production facilities.

[0003] In the current technology, there is relatively little research on risk assessment of flexible risers, and existing research methods also have certain limitations. Specifically, traditional risk assessment models struggle to analyze the multi-factor nonlinear coupling effects and risk propagation mechanisms over time in flexible riser systems, resulting in low accuracy of risk assessments and an inability to effectively address the complexity and uncertainty of actual operations. Furthermore, traditional methods typically rely on deterministic data, failing to adequately consider the uncertainty and ambiguity of the data, leading to low reliability of risk assessment results. Summary of the Invention

[0004] The purpose of this invention is to provide a risk assessment method for marine dynamic flexible risers based on fuzzy rule reasoning networks, which solves the problem of low accuracy and reliability of risk assessment in existing technologies.

[0005] To achieve the above objectives, this invention provides a risk assessment method for marine dynamic flexible risers based on fuzzy rule reasoning networks, comprising the following steps:

[0006] S1. Obtain the historical failure data set of the flexible riser; the historical failure data set includes the occurrence, severity, and detectability data of the historical failure modes of the flexible riser;

[0007] S2. Based on the five-level risk scoring standard, the failure data set is evaluated to obtain the first evaluation result. Based on the preset expert weight standard, the first evaluation result is processed by feature fusion to obtain the second evaluation result.

[0008] S3. Based on the Gaussian fuzzy mechanism and the second evaluation result, the fuzzy feature value is obtained;

[0009] S4. Input the fuzzy feature values ​​into the preset fuzzy rule inference network model to obtain the fuzzy set output by the fuzzy rule inference network model;

[0010] S5. Defuzzify the fuzzy set to obtain the risk assessment results for the flexible riser.

[0011] In some embodiments of this application, in S1, obtaining the historical failure data set of the flexible riser includes:

[0012] The monitoring equipment obtains the operating status of the flexible riser based on the sensors on the flexible riser, and determines the historical failure modes of the flexible riser based on the image recognition algorithm;

[0013] A comprehensive analysis of the operating status and historical failure modes of flexible risers is conducted, and a set of historical failure data is generated based on the occurrence, severity, and detectability data of historical failure modes of flexible risers.

[0014] In some embodiments of this application, in S2, the failure assessment of the historical failure data set based on the five-level risk scoring standard is performed to obtain the first assessment result, including:

[0015] Based on the five-level risk scoring standard, the occurrence, severity, and detectability data in the historical failure dataset are assessed for failure, and a first assessment result is generated based on the failure assessment scores of the occurrence, severity, and detectability data.

[0016] The five-level risk rating standard includes: very high risk, high risk, medium risk, low risk, and very low risk.

[0017] In some embodiments of this application, in step S2, the first evaluation result is subjected to feature fusion processing based on a preset expert weighting standard to obtain a second evaluation result, including:

[0018] Based on the preset expert weighting criteria, and using the weighted fusion method to perform feature fusion processing on the first evaluation result, a second evaluation result after feature fusion processing is obtained;

[0019] The expert weighting standard is derived from a comprehensive evaluation based on the expert's position, work experience, and educational background, and is calculated as follows:

[0020]

[0021] Among them, WE j Let e ​​be the expert weight standard for the j-th expert. c (j) It is the score of the j-th expert under the c-th evaluation criterion, and n is the total number of experts.

[0022] In some embodiments of this application, in S3, obtaining the fuzzy feature value based on the Gaussian fuzzing mechanism and the second evaluation result includes:

[0023] The second evaluation result is converted into a fuzzy value based on a Gaussian fuzzy function. Specifically, the evaluation result of the k-th failure mode under the risk assessment index r∈(O, S, D) is fuzzified. The risk assessment index level is defined as five fuzzy levels l∈(VL, L, M, H, VH). The fuzzy value is calculated based on the distance between the evaluation value and the center of each level.

[0024]

[0025] in, This represents the membership value of the k-th failure mode under the risk index r, where x is the sharpness value of the k-th risk factor in the second assessment result, σ represents the standard deviation, and c... l Let be the center value corresponding to the fuzzy level l under index r.

[0026] In some embodiments of this application, in step S4, a fuzzy inference rule base of type "IF-THEN" is constructed for the fault mode. The fuzzy feature values ​​are input into a preset fuzzy rule inference network model to obtain the expression of the fuzzy set output by the fuzzy rule inference network model:

[0027]

[0028] in, In the fuzzy rule inference network model, the k-th fault mode is activated by the i-th fuzzy rule, resulting in the adjusted output fuzzy value, α. i Let i be the activation value of the i-th rule. Under the action of the i-th fuzzy rule, the output membership degree is obtained by fuzzy inference calculation combining the fuzzy features of occurrence, severity and detectability. It represents the output fuzzy feature value of fault mode k. ⊙ is the causal mechanism in the fuzzy rule inference network model, which is usually defined as the product of the minimum values.

[0029]

[0030] Where, μ agg (FRPN) is the final fuzzy set output after maximum aggregation.

[0031] In some embodiments of this application, in step S5, the fuzzy set is defuzzified to obtain the flexible riser risk assessment result, including:

[0032] The centroid method is used to defuzzify the fuzzy set to obtain the sharp value FRPN. cv The expression is:

[0033]

[0034] Based on clarity value FRPN cv The risk assessment results for the flexible riser were obtained.

[0035] The advantages and beneficial effects of this invention compared to the prior art are:

[0036] 1. This invention employs a five-level risk scoring standard to assess the failure of historical failure data sets, quantifying complex failure data into relatively intuitive levels for easier subsequent processing. Furthermore, it combines preset expert weighting standards to perform feature fusion processing on the first assessment results, fully considering the importance of different failure factors. By utilizing a Gaussian fuzzy mechanism to obtain fuzzy feature values, and then processing them through a fuzzy rule-based inference network model, it can effectively handle the multi-factor nonlinear coupling effects in flexible riser systems, thereby improving the accuracy of risk assessment.

[0037] 2. This invention fully considers the uncertainty and fuzziness of data. In the marine environment, the conditions of flexible risers are often uncertain. The Gaussian fuzzy mechanism of this invention can transform this uncertainty into fuzzy feature values. When processing these fuzzy feature values, the fuzzy rule inference network model can better adapt to the fuzziness of the data. By comprehensively considering various possible situations through the fuzzy processing model, the reliability of the evaluation results is greatly improved.

[0038] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0039] Figure 1 This is a schematic diagram illustrating the steps of a marine dynamic flexible riser risk assessment method based on a fuzzy rule reasoning network in an embodiment of the present invention.

[0040] Figure 2 This is a severity-occurrence diagram of the confidence rule for marine dynamic flexible risers according to an embodiment of the present invention;

[0041] Figure 3 This is a schematic diagram of the occurrence-detectability of the confidence rule for marine dynamic flexible riser in an embodiment of the present invention.

[0042] Figure 4This is a schematic diagram of the severity-detectability of the marine dynamic flexible riser confidence rule in an embodiment of the present invention. Detailed Implementation

[0043] In the description of this invention, it should be noted that the terms "upper," "lower," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship commonly used when the product is in use. These terms are used only for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. In the description of this invention, it should also be noted that, unless otherwise explicitly specified and limited, the terms "set," "install," and "connect" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal communication between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0044] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0045] like Figure 1 As shown, this invention provides a risk assessment method for marine dynamic flexible risers based on fuzzy rule inference networks, comprising the following steps:

[0046] S1. Obtain the historical failure data set of the flexible riser; the historical failure data set includes the occurrence (O), severity (S), and detectability (D) of the historical failure modes of the flexible riser.

[0047] S2. Based on the five-level risk scoring standard, the failure data set is evaluated to obtain the first evaluation result. Based on the preset expert weight standard, the first evaluation result is processed by feature fusion to obtain the second evaluation result.

[0048] S3. Based on the Gaussian fuzzing mechanism and the second evaluation result, the fuzzy feature value is obtained.

[0049] S4. Input the fuzzy feature values ​​into the preset fuzzy rule inference network model to obtain the fuzzy set output by the fuzzy rule inference network model.

[0050] S5. Defuzzify the fuzzy set to obtain the risk assessment results for the flexible riser.

[0051] The advantages and beneficial effects of this invention compared to the prior art are:

[0052] 1. This invention employs a five-level risk scoring standard to assess the failure of historical failure data sets, quantifying complex failure data into relatively intuitive levels for easier subsequent processing. Furthermore, it combines preset expert weighting standards to perform feature fusion processing on the first assessment results, fully considering the importance of different failure factors. By utilizing a Gaussian fuzzy mechanism to obtain fuzzy feature values, and then processing them through a fuzzy rule-based inference network model, it can effectively handle the multi-factor nonlinear coupling effects in flexible riser systems, thereby improving the accuracy of risk assessment.

[0053] 2. This invention fully considers the uncertainty and fuzziness of data. In the marine environment, the conditions of flexible risers are often uncertain. The Gaussian fuzzy mechanism of this invention can transform this uncertainty into fuzzy feature values. When processing these fuzzy feature values, the fuzzy rule inference network model can better adapt to the fuzziness of the data. By comprehensively considering various possible situations through the fuzzy processing model, the reliability of the evaluation results is greatly improved.

[0054] In some embodiments of this application, in S1, obtaining the historical failure data set of the flexible riser includes:

[0055] The monitoring equipment obtains the operating status of the flexible riser based on the sensors on the flexible riser, and determines the historical failure modes of the flexible riser based on the image recognition algorithm;

[0056] A comprehensive analysis of the operating status and historical failure modes of flexible risers is conducted, and a set of historical failure data is generated based on the occurrence, severity, and detectability data of historical failure modes of flexible risers.

[0057] In some embodiments of this application, in S2, the failure assessment of the historical failure data set based on the five-level risk scoring standard is performed to obtain the first assessment result, including:

[0058] Based on the five-level risk scoring standard, the occurrence, severity, and detectability data in the historical failure dataset are assessed for failure, and a first assessment result is generated based on the failure assessment scores of the occurrence, severity, and detectability data.

[0059] The five-level risk rating standard includes: very high risk, high risk, medium risk, low risk, and very low risk.

[0060] In some embodiments of this application, in step S2, the first evaluation result is subjected to feature fusion processing based on a preset expert weighting standard to obtain a second evaluation result, including:

[0061] Based on the preset expert weighting criteria, and using the weighted fusion method to perform feature fusion processing on the first evaluation result, a second evaluation result after feature fusion processing is obtained;

[0062] The expert weighting standard is derived from a comprehensive evaluation based on the expert's position, work experience, and educational background, and is calculated as follows:

[0063]

[0064] Among them, WE j Let e ​​be the expert weight standard for the j-th expert. c (j) It is the score of the j-th expert under the c-th evaluation criterion, and n is the total number of experts.

[0065] In some embodiments of this application, in S3, obtaining the fuzzy feature value based on the Gaussian fuzzing mechanism and the second evaluation result includes:

[0066] The second evaluation result is converted into a fuzzy value based on a Gaussian fuzzy function. Specifically, the evaluation result of the k-th failure mode under the risk assessment index r∈(O, S, D) is fuzzified. The risk assessment index level is defined as five fuzzy levels l∈(VL, L, M, H, VH). The fuzzy value is calculated based on the distance between the evaluation value and the center of each level.

[0067]

[0068] in, This represents the membership value of the k-th failure mode under the risk index r, where x is the sharpness value of the k-th risk factor in the second assessment result, σ represents the standard deviation, and c... l Let be the center value corresponding to the fuzzy level l under index r.

[0069] In some embodiments of this application, in step S4, a fuzzy inference rule base of type "IF-THEN" is constructed for the fault mode. The fuzzy feature values ​​are input into a preset fuzzy rule inference network model to obtain the expression of the fuzzy set output by the fuzzy rule inference network model:

[0070]

[0071] in, In the fuzzy rule inference network model, the k-th fault mode is activated by the i-th fuzzy rule, resulting in the adjusted output fuzzy value, α. i Let be the activation degree of the i-th rule; Under the action of the i-th fuzzy rule, the output membership degree is obtained by fuzzy inference calculation combining the fuzzy features of occurrence, severity and detectability. It represents the output fuzzy feature value of fault mode k. ⊙ is the causal mechanism in the fuzzy rule inference network model, which is usually defined as the product of the minimum values.

[0072]

[0073] Where, μ agg (FRPN) is the final fuzzy set output after maximum aggregation.

[0074] In some embodiments of this application, in step S5, the fuzzy set is defuzzified to obtain the flexible riser risk assessment result, including:

[0075] The centroid method is used to defuzzify the fuzzy set to obtain the sharp value FRPN. cv The expression is:

[0076]

[0077] Based on clarity value FRPN cv The risk assessment results for the flexible riser were obtained.

[0078] The beneficial effects of this invention are as follows: This invention proposes a rule-based reasoning-based risk assessment method for marine dynamic flexible risers, aiming to overcome the limitations of existing risk assessment methods in complex marine engineering environments. A fuzzy rule-based reasoning network is constructed based on expert experience, fuzzy logic, and a confidence rule base to comprehensively assess the occurrence, severity, and detectability of failure modes of flexible risers. This assessment framework converts fuzzy numbers into clear values, achieving accurate risk prioritization, thereby providing a scientific basis for risk management, decision-making, and safety analysis in marine engineering. Furthermore, the risk assessment method of this invention has strong adaptability and adjustability, is applicable to different types of marine engineering systems, and has broad application prospects.

[0079] The embodiments of the present invention will be described in detail below with reference to specific examples.

[0080] In one embodiment, the main process provided by the present invention includes the construction of a flexible riser rule base module, the construction of a fuzzy reasoning logic framework, and the reasoning of complex marine load risks.

[0081] Step 1: Data Collection and Analysis

[0082] Marine dynamic flexible risers operate in complex marine environments and face the influence of various dynamic factors. Therefore, in-depth analysis of the working characteristics and loads of flexible risers is crucial to ensuring their safety and reliability. This analysis process aims to identify potential weaknesses and anticipate risk factors that may lead to flexible riser failure or safety accidents. First, comprehensive data collection is conducted to obtain failure data of flexible risers and gain a deeper understanding of their performance under different marine conditions. Data sources include historical data, field test data, and literature data. Second, data analysis focuses on key marine load factors affecting the performance of flexible risers, particularly the changes in loads caused by ocean currents, waves, and wind, and the potential impact of these loads on the structure and function of flexible risers. Based on this, a fuzzy inference model is constructed, and a systematic analysis is conducted based on the working principle and structural characteristics of flexible risers, combined with the FMEA method. Input parameters O, S, and D are defined to comprehensively evaluate potential risk factors from multiple dimensions. Furthermore, such as... Figure 2-4 As shown, an extended confidence rule base is used to reveal the nonlinear relationship between marine loads and risk status, thereby optimizing inference accuracy. Within the fuzzy inference framework of the flexible riser, the risk status of potential risk factors is used as the output, enabling quantitative inference of risk levels under different operating conditions under uncertainty. This embodiment intends to use 16 risk factors for analysis, as shown in Table 1.

[0083] Table 1 Failure Mode Numbers and Descriptions

[0084] Serial Number Failure Mode Serial Number Failure Mode X1 wave load X9 Extreme environments such as typhoons X2 water depth X10 Internal multiphase medium flow X3 Seawater corrosion X11 Temperature change X4 Wind load X12 Seabed X5 erosion X13 Acid and alkaline environment erosion X6 thermal fatigue X14 Internal pressure load X7 Bioattachment X15 Risk of falling objects X8 Ocean current load X16 Floating load

[0085] Step 2: Construction of the fuzzy reasoning system:

[0086] (1) Input Transformation: Three experts with extensive experience in oil and gas development were invited to evaluate the failure modes and their indicators. A five-level scoring system was used for the three input variables of the flexible riser (high = 5 points, high = 4 points, medium = 3 points, low = 2 points, very low = 1 point). Each expert scored the above input variables based on their experience and judgment of the system state. Weights were calculated using a formula according to the expert weighting standards specified in Table 1. For example, the weights for the three experts were 0.3704, 0.2963, and 0.3333, respectively. A weighted fusion method was used for comprehensive evaluation. The expert evaluation results and the fused results are shown in Tables 2-3.

[0087] Table 2 Summary of Expert Evaluation Results

[0088]

[0089] Table 3. Evaluation Results of Expert Opinions

[0090]

[0091]

[0092] By introducing a Gaussian function, sharp input values ​​are converted into blurred values. The Gaussian function used is divided into five levels, c l Let σ be the center value corresponding to the fuzzy level l under index r, σ represent the standard deviation, and σ is selected as 0.677 to indicate that the curves intersect continuously.

[0093]

[0094] in, Let represent the membership value of the k-th failure mode under the risk index r corresponding to the fuzzy level l, and let x be the clear value of the k-th risk factor in the second assessment result.

[0095] (2) Fuzzy Rule Establishment: Based on the expert domain knowledge base, "IF-THEN" type fuzzy inference rules were constructed as the core component of the inference engine. Each rule transforms the fuzzy value of the input variable into the corresponding output value through a membership function, thus forming an input-output mapping relationship. To ensure the accuracy and reliability of the rules, each rule is assigned a corresponding activation degree, reflecting the expert's level of trust in the rule's applicability. Given that the input variables contain five different states, and the output variables also have five different risk states, a total of 125 rules were defined, constructing a comprehensive rule database (rule 1 is used as an example).

[0096] Rule 1:IF Ois VL and Sis VL and Dis VH THEN FRPNis VL.

[0097] (3) Fuzzy Risk Reasoning: In-depth analysis of 16 identified complex factors of marine loads was conducted. Clear values ​​of O, S, and D were input and converted into fuzzy numbers through formulas. The fuzzy numbers were matched with the preconditions of 125 rules in the rule base, and the rules that met the conditions were activated. Through aggregation and defuzzification, the final risk ranking number was output. The results are shown in Table 4.

[0098] Table 4 Failure Mode Ranking

[0099]

[0100] As shown in Table 4, wave load, ocean current load, and temperature change rank among the top three in terms of risk ranking. This indicates that these three risk factors pose a serious threat to the safety of flexible risers, possessing a high risk level and threatening the long-term stability and operational efficiency of the flexible risers. Among them, wave load, due to its periodic impact and random characteristics, is prone to inducing fatigue damage; ocean current load, due to hydrodynamic effects, may cause vortex-induced vibration and local buckling; while temperature changes exacerbate material aging and stress concentration through thermal expansion and contraction. These high-ranking risks should be given priority attention, and targeted measures should be taken in design optimization, operation monitoring, and maintenance strategies to reduce potential hazards and ensure the safety and reliability of the system.

[0101] The beneficial effects of this invention are as follows: This invention proposes a rule-based reasoning-based risk assessment method for marine dynamic flexible risers, aiming to overcome the limitations of existing risk assessment methods in complex marine engineering environments. A fuzzy rule-based reasoning network is constructed based on expert experience, fuzzy logic, and a confidence rule base to comprehensively assess the occurrence, severity, and detectability of failure modes of flexible risers. This assessment framework converts fuzzy numbers into clear values, achieving accurate risk prioritization, thereby providing a scientific basis for risk management, decision-making, and safety analysis in marine engineering. Furthermore, the risk assessment method of this invention has strong adaptability and adjustability, is applicable to different types of marine engineering systems, and has broad application prospects.

[0102] In this application, unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. In case of any inconsistency, the meaning set forth in this specification or derived from the content described herein shall prevail. Furthermore, the terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit the scope of this application.

[0103] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the technical solutions of the present invention, and these modifications or equivalent substitutions cannot cause the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for risk assessment of marine dynamic flexible riser based on fuzzy rule-based inference network, characterized in that, The method comprises the following steps: S1, obtaining a historical failure data set of the flexible riser; wherein the historical failure data set comprises occurrence degree O, severity S and detectability data D of the historical failure mode of the flexible riser; S2, performing failure assessment on the historical failure data set based on a five-level risk scoring standard to obtain a first assessment result, and performing feature fusion processing on the first assessment result based on a preset expert weight standard to obtain a second assessment result; Wherein the five-level risk scoring standard comprises: very high risk level, high risk level, medium risk level, low risk level, and very low risk level; S3, based on the Gaussian blur mechanism and the second evaluation results get fuzzy characteristic value; based on the Gaussian blur mechanism will be the second evaluation results into fuzzy value, the first k Risk evaluation index r The evaluation results of the risk evaluation index under the risk evaluation index l ∈ (VL, L, M, H, VH) are defined as five fuzzy levels S4, inputting the fuzzy feature value into a preset fuzzy rule inference network model to obtain a fuzzy set output by the fuzzy rule inference network model; In S4, an IF-THEN type fuzzy inference rule base is constructed for the failure mode, and the expression for inputting the fuzzy feature value into the preset fuzzy rule inference network model to obtain the fuzzy set output by the fuzzy rule inference network model is: ； ； in, Indicates the first k Each failure mode in risk indicators r The corresponding fuzzy level l membership value, It is the first in the fuzzy rule-based reasoning network model k The failure mode is in the first i Under the influence of the fuzzy rules, the adjusted output fuzzy value is activated. For the first i The activation degree of the rule, For the first i Under the influence of fuzzy rules, and combining the fuzzy features of occurrence, severity, and detectability, the output membership degree is calculated through fuzzy inference, representing the fault mode. k The output fuzzy feature value, The causal mechanism in a fuzzy rule-based reasoning network model is usually defined as the product of minimum values; ； wherein, is the final fuzzy set outputted by the maximum aggregation. S5, performing defuzzification processing on the fuzzy set to obtain the flexible riser risk assessment result.

2. The method according to claim 1, wherein, In S1, obtaining the historical failure data set of the flexible riser comprises: Obtaining the running state of the flexible riser collected by the monitoring device based on the sensors on the flexible riser, and determining the historical failure mode of the flexible riser based on failure mechanism analysis; Comprehensively analyzing the running state of the flexible riser and the historical failure mode, and obtaining the historical failure data set generated based on the occurrence degree, severity and detectability data of the historical failure mode of the flexible riser according to the comprehensive analysis result.

3. The method according to claim 2, wherein, In S2, performing failure assessment on the historical failure data set based on the five-level risk scoring standard to obtain the first assessment result comprises: Performing failure assessment on the occurrence degree, severity and detectability data in the historical failure data set based on the five-level risk scoring standard to obtain the first assessment result generated based on the failure assessment scores of the occurrence degree, severity and detectability data.

4. The method according to claim 3, wherein, In S2, performing feature fusion processing on the first assessment result based on the preset expert weight standard to obtain the second assessment result comprises: Performing feature fusion processing on the first assessment result based on the preset expert weight standard by using a weighted fusion method to obtain the second assessment result after feature fusion processing; Wherein the expert weight standard is obtained based on comprehensive assessment of the positions, work experience and educational background of experts, and the calculation formula is: ； wherein, is the weight of the jth expert, j is the weight of the jth expert, is the score of the jth expert under the ith criterion, is the score of the jth expert under the ith criterion, c is the score of the jth expert under the ith criterion, n is the total number of experts.

5. The method of claim 4, wherein, In S3, obtaining the fuzzy feature value based on the Gaussian fuzzy mechanism and the second assessment result comprises: According to the distance between the evaluation value and each level center, the fuzzy value is calculated as follows: ； wherein, represents the membership value of the k th failure mode corresponding to the fuzzy level r under the risk indicator l , x k is the crisp value of the k th risk factor in the second assessment result, σ represents the standard deviation, c l is the center value corresponding to the fuzzy level l under the indicator r.

6. The method of claim 5, wherein, In S5, performing defuzzification processing on the fuzzy set to obtain the flexible riser risk assessment result comprises: The fuzzy set is de-fuzzified by using the barycenter method to obtain a clear value FRPN cv The expression is: ； Based on the clear value FRPN cv A flexible riser risk assessment result is obtained.

Images