Marine dynamic flexible riser risk assessment method based on fuzzy rule inference network

Abstract

The invention relates to the technical field of flexible riser risk assessment, in particular to an ocean dynamic flexible riser risk assessment method based on a fuzzy rule inference network, which comprises the following steps: acquiring a historical failure data set of a flexible riser, 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 risk assessment on the first assessment result to obtain a second assessment result; and performing feature fusion processing on the first evaluation result based on a preset expert weight standard to obtain a second evaluation result, obtaining a fuzzy feature value based on a Gaussian fuzzy mechanism and the second evaluation result, inputting the fuzzy feature value into a preset fuzzy rule reasoning network model to obtain a fuzzy set output by the fuzzy rule reasoning network model, and obtaining a fuzzy set output by the fuzzy rule reasoning network model. And performing defuzzification processing on the fuzzy set to obtain a flexible riser risk assessment result. According to the method, the multi-factor nonlinear coupling effect in the flexible riser system can be effectively processed through fuzzy rule reasoning network model processing, so that the accuracy of risk assessment is improved.

Description

Technical Field

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

[0002] Marine dynamic flexible risers are core equipment in modern marine oil and gas development. As key equipment connecting sea surface floating production platforms (such as FPSOs, semi-submersible platforms, etc.) with submarine oil and gas production facilities, their main function is to ensure the stable transportation of submarine oil and gas resources, natural gas, crude oil, water and chemical media. Flexible risers are usually composed of multiple layers of materials with different structures. They are exposed to the dynamic marine environment for a long time and face complex loads from waves, currents, climate change, platform movement and deep-sea earthquakes. These dynamic loads not only increase the fatigue damage risk of flexible risers, but also aggravate the physical wear and corrosion aging of the structure, affecting the safety and reliability of the flexible riser life. In addition, the transported medium is highly flammable and explosive. Once a leak or failure occurs, it may lead to catastrophic consequences, seriously endangering the marine ecological environment and the lives of platform workers. Therefore, how to accurately identify, quantify and effectively manage these risks has become a core issue that needs to be urgently addressed in offshore oil and gas production facilities.

[0003] Risk assessment for flexible risers is relatively limited, and existing methods have limitations. Specifically, traditional risk assessment models struggle to analyze the multi-factor nonlinear coupling effects and time-scale risk propagation mechanisms within flexible riser systems. This results in low risk assessment accuracy and an inability to effectively address the complexity and uncertainty inherent in actual operations. Furthermore, traditional methods often rely on deterministic data and fail to fully account for data uncertainty and ambiguity, resulting in low reliability in risk assessment results. Summary of the Invention

[0004] The purpose of the present invention is to provide a marine dynamic flexible riser risk assessment method based on fuzzy rule reasoning network to solve the problems of low accuracy and reliability of risk assessment in the prior art.

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

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

[0007] S2. Perform failure evaluation on the historical failure data set based on the five-level risk scoring standard to obtain a first evaluation result, and perform feature fusion processing on the first evaluation result based on a preset expert weight standard to obtain a second evaluation result;

[0008] S3, obtaining a fuzzy feature value based on the Gaussian fuzzy mechanism and the second evaluation result;

[0009] S4, inputting the fuzzy eigenvalue into a preset fuzzy rule reasoning network model to obtain a fuzzy set output by the fuzzy rule reasoning network model;

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

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

[0012] Obtain the operating status of the flexible riser collected by the monitoring equipment based on the sensors on the flexible riser, and determine the historical failure mode of the flexible riser based on the image recognition algorithm;

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

[0014] In some embodiments of the present application, in S2, failure evaluation is performed on the historical failure data set based on the five-level risk scoring standard, and the first evaluation result obtained includes:

[0015] Perform failure assessments on the occurrence, severity, and detectability data in the historical failure data set based on a five-level risk scoring standard, and obtain a first assessment result generated by failure assessment scores based on the occurrence, severity, and detectability data;

[0016] Among them, the five-level risk scoring standards include: very high risk level, high risk level, medium risk level, low risk level, and very low risk level.

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

[0018] Based on the preset expert weight standard, the first evaluation result is subjected to feature fusion processing by using the weighted fusion method to obtain a second evaluation result after feature fusion processing;

[0019] Among them, the expert weight standard is obtained through a comprehensive evaluation based on the expert's position, work experience and educational background, and the calculation formula is:

[0020]

[0021] Among them, WE j is the expert weight standard of the jth expert, e c (j) is the score of the jth expert under the cth evaluation criterion, and n is the total number of experts.

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

[0023] The second evaluation result is converted into a fuzzy value based on the Gaussian fuzzy function. Specifically, the evaluation result of the k-th fault mode under the risk evaluation index r∈(O, S, D) is fuzzified. The risk evaluation index level is defined as 5 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, represents the membership value of the k-th failure mode corresponding to the fuzzy level l under the risk index r, x is the clear value of the k-th risk factor in the second evaluation result, σ represents the standard deviation, c l It is the central value corresponding to the fuzzy level l under the index r.

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

[0027]

[0028] in, is the output fuzzy value after activation adjustment of the kth fault mode under the action of the i-th fuzzy rule in the fuzzy rule reasoning network model, α i is the activation degree of the i-th rule, Under the action of the i-th fuzzy rule, the output membership is obtained by combining the fuzzy characteristics of occurrence, severity and detectability through fuzzy reasoning, which represents the output fuzzy characteristic value of fault mode k. ⊙ is the causal mechanism in the fuzzy rule reasoning network model, which is usually defined as the product of the minimum value;

[0029]

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

[0031] In some embodiments of the present application, in S5, defuzzification processing is performed on the fuzzy set to obtain a flexible riser risk assessment result including:

[0032] The fuzzy set is defuzzified using the centroid method to obtain the clear value FRPN cv , the expression is:

[0033]

[0034] FRPN based on clarity value cv The risk assessment results of flexible risers are obtained.

[0035] The advantages and beneficial effects of the present invention over the prior art are:

[0036] 1. The present invention uses a five-level risk scoring standard to perform failure assessment on a historical failure data set. This method can quantify complex failure data into relatively intuitive levels, facilitating subsequent processing. It also combines the first assessment results with preset expert weight standards to perform feature fusion processing, fully considering the importance of different failure factors. It utilizes a Gaussian fuzzy mechanism to obtain fuzzy eigenvalues, which are then processed through a fuzzy rule inference network model. This method can effectively address the multi-factor nonlinear coupling effects in the flexible riser system, thereby improving the accuracy of risk assessment.

[0037] 2. The present invention fully considers the uncertainty and ambiguity of data. In the marine environment, the conditions in which flexible risers are located are often uncertain. The Gaussian fuzzy mechanism of the present invention can convert this uncertainty into fuzzy eigenvalues. When processing these fuzzy eigenvalues, the fuzzy rule inference network model can better adapt to the ambiguity of the data. The fuzzy-processed model comprehensively considers various possible situations, greatly improving the reliability of the evaluation results.

[0038] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 Schematic diagram of the steps of a marine dynamic flexible riser risk assessment method based on a fuzzy rule inference network in an embodiment of the present invention;

[0040] Figure 2 Schematic diagram of severity-occurrence of marine dynamic flexible riser confidence rules according to an embodiment of the present invention;

[0041] Figure 3 Schematic diagram of occurrence degree-detectability of the marine dynamic flexible riser confidence rule according to an embodiment of the present invention;

[0042] Figure 4Schematic diagram of severity-detectability of the marine dynamic flexible riser confidence rule according to an embodiment of the present invention. DETAILED DESCRIPTION

[0043] In the description of the present invention, it should be noted that the terms "upper", "lower", "inside", "outside" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, or the orientations or positional relationships in which the inventive product is usually placed when in use. These are only for the convenience of describing the present invention and simplifying the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, they cannot be understood as limitations on the present invention. In the description of the present invention, it should also be noted that, unless otherwise expressly specified and limited, the terms "setting", "installation" and "connection" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or an indirect connection through an intermediate medium, or it can be a communication between the internal parts of two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

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

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

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

[0047] S2. Perform failure evaluation on the historical failure data set based on the five-level risk scoring standard to obtain a first evaluation result, and perform feature fusion processing on the first evaluation result based on a preset expert weight standard to obtain a second evaluation result.

[0048] S3. Obtain a fuzzy feature value based on the Gaussian fuzzy mechanism and the second evaluation result.

[0049] S4. Input the fuzzy eigenvalues ​​into a preset fuzzy rule reasoning network model to obtain a fuzzy set output by the fuzzy rule reasoning network model.

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

[0051] The advantages and beneficial effects of the present invention over the prior art are:

[0052] 1. The present invention uses a five-level risk scoring standard to perform failure assessment on a historical failure data set. This method can quantify complex failure data into relatively intuitive levels, facilitating subsequent processing. It also combines the first assessment results with preset expert weight standards to perform feature fusion processing, fully considering the importance of different failure factors. It utilizes a Gaussian fuzzy mechanism to obtain fuzzy eigenvalues, which are then processed through a fuzzy rule inference network model. This method can effectively address the multi-factor nonlinear coupling effects in the flexible riser system, thereby improving the accuracy of risk assessment.

[0053] 2. The present invention fully considers the uncertainty and ambiguity of data. In the marine environment, the conditions in which flexible risers are located are often uncertain. The Gaussian fuzzy mechanism of the present invention can convert this uncertainty into fuzzy eigenvalues. When processing these fuzzy eigenvalues, the fuzzy rule inference network model can better adapt to the ambiguity of the data. The fuzzy-processed model comprehensively considers various possible situations, greatly improving the reliability of the evaluation results.

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

[0055] Obtain the operating status of the flexible riser collected by the monitoring equipment based on the sensors on the flexible riser, and determine the historical failure mode of the flexible riser based on the image recognition algorithm;

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

[0057] In some embodiments of the present application, in S2, failure evaluation is performed on the historical failure data set based on the five-level risk scoring standard, and the first evaluation result obtained includes:

[0058] Perform failure assessments on the occurrence, severity, and detectability data in the historical failure data set based on a five-level risk scoring standard, and obtain a first assessment result generated by failure assessment scores based on the occurrence, severity, and detectability data;

[0059] Among them, the five-level risk scoring standards include: very high risk level, high risk level, medium risk level, low risk level, and very low risk level.

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

[0061] Based on the preset expert weight standard, the first evaluation result is subjected to feature fusion processing by using the weighted fusion method to obtain a second evaluation result after feature fusion processing;

[0062] Among them, the expert weight standard is obtained through a comprehensive evaluation based on the expert's position, work experience and educational background, and the calculation formula is:

[0063]

[0064] Among them, WE j is the expert weight standard of the jth expert, e c (j) is the score of the jth expert under the cth evaluation criterion, and n is the total number of experts.

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

[0066] The second evaluation result is converted into a fuzzy value based on the Gaussian fuzzy function. Specifically, the evaluation result of the k-th fault mode under the risk evaluation index r∈(O, S, D) is fuzzified. The risk evaluation index level is defined as 5 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, represents the membership value of the k-th failure mode corresponding to the fuzzy level l under the risk index r, x is the clear value of the k-th risk factor in the second evaluation result, σ represents the standard deviation, c l It is the central value corresponding to the fuzzy level l under the index r.

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

[0070]

[0071] in, is the output fuzzy value after activation adjustment of the kth fault mode under the action of the i-th fuzzy rule in the fuzzy rule reasoning network model, α i is the activation degree of the i-th rule; Under the action of the i-th fuzzy rule, the output membership is obtained by combining the fuzzy characteristics of occurrence, severity and detectability through fuzzy reasoning, which represents the output fuzzy characteristic value of fault mode k. ⊙ is the causal mechanism in the fuzzy rule reasoning network model, which is usually defined as the product of the minimum value;

[0072]

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

[0074] In some embodiments of the present application, in S5, defuzzification processing is performed on the fuzzy set to obtain a flexible riser risk assessment result including:

[0075] The fuzzy set is defuzzified using the centroid method to obtain the clear value FRPN cv , the expression is:

[0076]

[0077] FRPN based on clarity value cv The risk assessment results of flexible risers are obtained.

[0078] The beneficial effects of the present invention are as follows: the present invention proposes a risk assessment method for marine dynamic flexible risers based on rule reasoning, which aims to overcome the limitations of existing risk assessment methods when facing complex marine engineering environments. A fuzzy rule reasoning network is constructed based on expert experience, fuzzy logic and a confidence rule base to comprehensively evaluate the occurrence, severity and detectability of failure modes of flexible risers. Through this evaluation framework, fuzzy numbers are converted into clear values ​​to achieve accurate risk priority sorting, thereby providing a scientific basis for risk management, decision-making and safety analysis in marine engineering. In addition, the risk assessment method of the present invention has strong adaptability and adjustability, is applicable to different types of marine engineering systems, and has broad application prospects.

[0079] The following describes the implementation of the present invention in detail 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 ocean load risks.

[0081] Step 1: Data collection and analysis:

[0082] Marine dynamic flexible risers operate in a complex marine environment and are subject to the influence of various dynamic factors. Therefore, an in-depth analysis of the working characteristics and working loads of flexible risers is the key to ensuring their safety and reliability. The analysis process aims to identify potential weak links and foresee risk factors that may lead to failure of flexible risers or safety accidents. First, through comprehensive data collection, the failure data of flexible risers are obtained to gain an in-depth understanding of the performance of flexible risers under different marine conditions. The data sources include historical data, field test data and literature data. The second is data analysis, focusing on the key marine load factors that affect the performance of flexible risers, especially the changes in loads caused by currents, waves, wind, etc. and the potential impact of these loads on the structure and function of flexible risers. On this basis, a fuzzy reasoning model is constructed, and a systematic analysis is carried out based on the working principle and structural characteristics of the flexible riser and combined with the FMEA method. Define the input parameters O, S and D to comprehensively evaluate potential risk factors from multiple dimensions. In addition, such as Figure 2-4 As shown, an extended confidence rule base is used to reveal the nonlinear relationship between ocean loads and risk states, optimizing inference accuracy. Within the fuzzy inference framework for flexible risers, the risk states of potential risk factors are used as outputs, enabling quantitative reasoning about risk levels under different operating conditions under uncertainty. This example proposes to analyze 16 risk factors, as shown in Table 1.

[0083] Table 1 Failure mode number and description

[0084] Serial number Failure Mode Serial number Failure Mode X1 Wave loads X9 Typhoon and other extreme environments X2 Water depth X10 Internal multiphase flow X3 Seawater corrosion X11 Temperature changes X4 Wind load X12 Touching the seabed X5 erosion X13 Acid and alkaline environment erosion X6 heat fatigue X14 Internal pressure load X7 Biological adhesion X15 Falling object risk X8 Current loads X16 Floating body load

[0085] Step 2: Construction of fuzzy inference 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 standard (very high = 5 points, high = 4 points, medium = 3 points, low = 2 points, and very low = 1 point) was used for the three input variables of the flexible riser. Each expert scored the above input variables based on their own experience and judgment of the system status. According to the expert weight standard specified in Table 1, the weights were calculated using the formula. For example, the weight results of 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 fusion results are shown in Table 2-3.

[0087] Table 2 Summary of expert evaluation results

[0088]

[0089] Table 3 Evaluation results of integrated expert opinions

[0090]

[0091]

[0092] By introducing Gaussian function, the clear input value is converted into a fuzzy value. The Gaussian function used is divided into five levels: c l is the central value corresponding to the fuzzy level l under the index r, σ represents the standard deviation, and the curves show continuous intersection. The value of σ is selected as 0.677.

[0093]

[0094] in, represents the membership value of the k-th failure mode corresponding to the fuzzy level l under the risk index r, and x is 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, an “IF-THEN” type of fuzzy reasoning rule was constructed as the core component of the reasoning engine. Each rule converts the fuzzy value of the input variable into the corresponding output value through a membership function, thus forming an input-to-output mapping relationship. To ensure the accuracy and reliability of the rules, each rule is assigned a corresponding activation degree, which reflects the expert’s confidence in the applicability of the rule. Given that the input variable contains five different states and the output variable also has five different risk states, a total of 125 rules were defined to construct a comprehensive rule database (only 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: 16 identified complex factors of ocean loads were analyzed in depth. Clear values ​​of O, S, and D were input and converted into fuzzy numbers through a formula. The fuzzy numbers were matched with the 125 rule preconditions in the rule base, and the rules that met the conditions were activated. Through aggregation and defuzzification, the final risk ranking was output. The results are shown in Table 4.

[0098] Table 4 Failure mode ranking

[0099]

[0100] As shown in Table 4, wave loads, current loads, and temperature changes rank in the top three risk rankings. This indicates that these three risk factors pose a serious threat to the safety of flexible risers, with a high risk level, threatening the long-term stability and operational efficiency of flexible risers. Wave loads, due to their periodic impact and random characteristics, are prone to induce fatigue damage; current loads, due to fluid dynamics, may induce vortex-induced vibrations and local buckling; and temperature changes, through thermal expansion and contraction effects, exacerbate material aging and stress concentration. 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 the present invention are as follows: the present invention proposes a risk assessment method for marine dynamic flexible risers based on rule reasoning, which aims to overcome the limitations of existing risk assessment methods when facing complex marine engineering environments. A fuzzy rule reasoning network is constructed based on expert experience, fuzzy logic and a confidence rule base to comprehensively evaluate the occurrence, severity and detectability of failure modes of flexible risers. Through this evaluation framework, fuzzy numbers are converted into clear values ​​to achieve accurate risk priority sorting, thereby providing a scientific basis for risk management, decision-making and safety analysis in marine engineering. In addition, the risk assessment method of the present 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 those skilled in the art to which this application belongs. In the event of any inconsistency, the meaning described in this specification or the meaning derived from the contents recorded in this specification shall prevail. In addition, the terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0103] 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 the same. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solutions of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A risk assessment method for marine dynamic flexible risers based on fuzzy rule inference network, characterized in that: The following steps are involved: S1. Obtain a historical failure data set of the flexible riser; wherein the historical failure data set includes occurrence, severity, and detectability data of historical failure modes of the flexible riser; S2. Perform failure evaluation on the historical failure data set based on the five-level risk scoring standard to obtain a first evaluation result, and perform feature fusion processing on the first evaluation result based on a preset expert weight standard to obtain a second evaluation result; S3, obtaining a fuzzy feature value based on the Gaussian fuzzy mechanism and the second evaluation result; S4, inputting the fuzzy eigenvalue into a preset fuzzy rule reasoning network model to obtain a fuzzy set output by the fuzzy rule reasoning network model; S5. Defuzzify the fuzzy set to obtain the flexible riser risk assessment result.

2. The marine dynamic flexible riser risk assessment method based on fuzzy rule inference network according to claim 1 is characterized in that: In S1, obtaining a set of historical failure data of flexible risers includes: Obtain the operating status of the flexible riser collected by the monitoring equipment based on the sensors on the flexible riser, and determine the historical failure mode of the flexible riser based on the image recognition algorithm; A comprehensive analysis is conducted on the operating status and historical failure modes of the flexible riser, and a historical failure data set generated based on the occurrence, severity and detectability data of the historical failure modes of the flexible riser is obtained according to the comprehensive analysis results.

3. The marine dynamic flexible riser risk assessment method based on fuzzy rule inference network according to claim 2 is characterized in that: In S2, the failure evaluation of the historical failure data set is performed based on the five-level risk scoring standard, and the first evaluation result obtained includes: Perform failure assessments on the occurrence, severity, and detectability data in the historical failure data set based on a five-level risk scoring standard, and obtain a first assessment result generated by failure assessment scores based on the occurrence, severity, and detectability data; Among them, the five-level risk scoring standards include: very high risk level, high risk level, medium risk level, low risk level, and very low risk level.

4. The marine dynamic flexible riser risk assessment method based on fuzzy rule inference network according to claim 3 is characterized in that: In S2, the first evaluation result is subjected to feature fusion processing based on a preset expert weight standard to obtain a second evaluation result including: Based on the preset expert weight standard, the first evaluation result is subjected to feature fusion processing by using the weighted fusion method to obtain a second evaluation result after feature fusion processing; The expert weight standard is obtained through a comprehensive evaluation based on the expert's position, work experience, and educational background. The calculation formula is: Among them, WE j is the expert weight standard of the jth expert, e c (j) is the score of the jth expert under the cth evaluation criterion, and n is the total number of experts.

5. The marine dynamic flexible riser risk assessment method based on fuzzy rule inference network according to claim 4 is characterized in that: In S3, obtaining the fuzzy feature value based on the Gaussian fuzzy mechanism and the second evaluation result includes: The second evaluation result is converted into a fuzzy value based on the Gaussian fuzzy mechanism. The evaluation result of the k-th fault mode under the risk assessment index r∈(O, S, D) is fuzzified. The risk assessment index level is defined as 5 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: in, represents the membership value of the k-th fault mode corresponding to the fuzzy level l under the risk index r, x k is the clear value of the kth risk factor in the second assessment result, σ represents the standard deviation, c l It is the central value corresponding to the fuzzy level l under the index r.

6. The marine dynamic flexible riser risk assessment method based on fuzzy rule inference network according to claim 5 is characterized in that: In said S4, a fuzzy inference rule base of the IF-THEN type is constructed for the fault mode, and the fuzzy feature value is input into the preset fuzzy rule inference network model to obtain the fuzzy set expression output by the fuzzy rule inference network model: in, is the output fuzzy value after activation adjustment of the kth fault mode under the action of the i-th fuzzy rule in the fuzzy rule reasoning network model, α i is the activation degree of the i-th rule, is the output membership obtained by fuzzy reasoning under the action of the i-th fuzzy rule, combining the fuzzy characteristics of occurrence, severity and detectability, representing the output fuzzy characteristic value of fault mode k. ⊙ is the causal mechanism in the fuzzy rule reasoning network model, which is usually defined as the product of the minimum value; Among them, μ agg (FRPN) is the final fuzzy set output after maximum aggregation.

7. The marine dynamic flexible riser risk assessment method based on fuzzy rule inference network according to claim 6 is characterized in that: In S5, the fuzzy set is defuzzified to obtain the flexible riser risk assessment results including: The fuzzy set is defuzzified using the centroid method to obtain the clear value FRPN cv , the expression is: FRPN based on clarity value cv The risk assessment results of flexible risers are obtained.

Images