A method and system for failure prediction of an FPSO riser support system

Abstract

The application discloses a kind of FPSO riser support system's failure prediction method and system, it is related to failure prediction technical field, obtain current failure data about FPSO riser support system failure state and obtain final failure type in combination with historical failure data, obtain maintenance importance coefficient, pollution coefficient and production reduction coefficient calculated according to each final failure type corresponding historical data;According to maintenance importance coefficient, pollution coefficient and production reduction coefficient, the key coefficient of each failure type is calculated, and the maintenance urgency of the failure type of each FPSO riser support system is judged according to the key coefficient;In this way, the failure of FPSO riser support system can be predicted at multiple levels, to ensure the accuracy of failure prediction;And in the case where multiple failures may occur simultaneously, it can accurately determine which failure is the most urgent and critical, and reasonably allocate resources for priority maintenance and processing.

Description

Technical Field

[0001] The present invention relates to the technical field of fault prediction, and in particular to a fault prediction method and system for an FPSO riser support system. Background Art

[0002] Fault prediction for FPSO (Floating Production Storage and Offshore) riser support systems typically involves predicting potential failures or damage through real-time monitoring, data analysis, and machine learning. These systems operate offshore, subject to extreme marine conditions, including wind and waves, temperature fluctuations, and seawater corrosion. Therefore, fault prediction can be achieved by monitoring the health of key components of the riser support system (such as support structures, connection points, and sensors), collecting data such as vibration, stress, and displacement, and analyzing potential risk points. When abnormal patterns are detected, the system issues timely warnings, providing decision support for maintenance personnel and preventing potential equipment failures or safety incidents.

[0003] However, the above-mentioned prediction methods often only predict FPSO riser support system failures, considering only the failure of a single system or component. FPSO riser support system failures may be caused by multiple factors, and a single fault prediction may lead to low fault prediction accuracy. In addition, when multiple faults may occur simultaneously, how to accurately determine which fault is the most urgent and critical, and how to allocate resources for priority repair and treatment, are also difficult problems that have not been fully solved in current prediction methods. Summary of the Invention

[0004] The purpose of the present invention is to solve the above-mentioned problems and provide a fault prediction method and system for an FPSO riser support system.

[0005] In a first aspect of the present invention, a method for predicting a failure of an FPSO riser support system is first proposed, the method comprising:

[0006] Acquire data on the fault status of the FPSO riser support system as current fault data, calculate similarity with each type of historical fault data of the FPSO riser support system, and predict the fault type of the FPSO riser support system as a final fault type;

[0007] For each final fault type, obtain the historical maintenance data corresponding to each fault type, and calculate the maintenance importance coefficient based on the historical maintenance data;

[0008] Obtain historical pollution data corresponding to each fault type and calculate the pollution coefficient based on the historical pollution data;

[0009] Obtaining historical production reduction data corresponding to each fault type, and calculating a production reduction coefficient according to historical maintenance data;

[0010] According to the maintenance importance coefficient, the pollution coefficient and the production reduction coefficient, a key coefficient of each fault type is calculated, and the maintenance urgency of the fault type of the FPSO riser support system is determined according to the key coefficient.

[0011] Optionally, the similarity of each historical fault data of the FPSO riser support system is calculated, and the fault type of the FPSO riser support system is predicted as the final fault type, comprising:

[0012] Each type of historical fault data is recorded as target historical fault data, and the current fault data and the target historical fault data are preprocessed;

[0013] A distance matrix is constructed, and each element in the distance matrix is the distance between the current fault data point and the target historical fault data point;

[0014] The shortest path in the distance matrix is calculated by using a dynamic programming algorithm to find the best match between the current fault data sequence and the target historical fault data sequence;

[0015] According to the calculated shortest path, the current fault data sequence and the target historical fault data sequence are aligned;

[0016] According to the aligned current fault data sequence and the target historical fault data sequence, the similarity between them is calculated;

[0017] The calculated similarity is compared with a similarity threshold value, and if the similarity is greater than the similarity threshold value, the corresponding historical fault type is taken as the predicted fault type;

[0018] All predicted fault types are taken as the final fault type.

[0019] Optionally, the maintenance importance coefficient is calculated according to historical maintenance data, comprising:

[0020] For each final fault type, the number of times of occurrence of the fault type in the historical data is obtained, and the maintenance time spent each time the fault occurs is obtained, and the average maintenance time is calculated as a maintenance time coefficient;

[0021] The average time interval of maintenance is obtained, and the time interval between the current time and the last maintenance is obtained, and the average maintenance time interval is subtracted from the time interval between the current time and the last maintenance to obtain a maintenance interval coefficient;

[0022] The maintenance importance coefficient is calculated according to the maintenance time coefficient and the maintenance interval coefficient, and the formula for calculation is:

[0023] ;

[0024] wherein, is a maintenance importance coefficient, are a maintenance time coefficient, a maintenance interval coefficient and a total number of occurrences of the fault type, respectively, are preset proportion coefficients of , and are all greater than 0.

[0025] Optionally, the calculating of the pollution coefficient according to the historical pollution data comprises:

[0026] For each final fault type, the number of occurrences of the fault type in the historical data is obtained, and the volume of the oil discharged into the seawater at each occurrence of the fault is obtained, and the volume of the oil discharged into the seawater at each occurrence of the fault is marked as , represents the ordinal number of the volume of the oil discharged into the seawater at each occurrence of the fault, and , is the total number of occurrences of the fault, and is a positive integer;

[0027] The average volume of the oil discharged into the seawater is calculated as , and the formula for the calculation is: ;

[0028] The pollution coefficient is calculated as , and the formula for the calculation is: ,

[0029] wherein, is the total number of occurrences of the fault type, are preset proportion coefficients of , and are all greater than 0.

[0030] Optionally, the obtaining of the historical production reduction data corresponding to each fault type and the calculating of the production reduction coefficient according to the historical maintenance data comprise:

[0031] For each final fault type, the number of occurrences of the fault type in the historical data is obtained, and the difference between the preset production of oil and the actual production of oil at each occurrence of the fault is obtained as the production reduction of oil of the time;

[0032] All the production reductions of oil at each occurrence of the fault are added to obtain the production reduction coefficient.

[0033] Optionally, the calculating of the key coefficient of each fault type according to the maintenance importance coefficient, the pollution coefficient and the production reduction coefficient and the judging of the maintenance urgency of the fault type of each FPSO riser support system according to the key coefficient comprise:

[0034] ;

[0035] wherein, is a key coefficient of the failure type, are respectively a maintenance importance coefficient, a pollution coefficient and a production reduction coefficient; are respectively is a preset proportion coefficient, and are all greater than 0;

[0036] According to the size of the key coefficient, the failure types of each FPSO riser support system are sorted from high to low in terms of maintenance urgency.

[0037] In the second aspect of the embodiment of the present application, a failure prediction system of an FPSO riser support system is provided, and the system comprises:

[0038] a final failure type module: obtaining data about the failure state of the FPSO riser support system as current failure data, and calculating the similarity of each type of historical failure data of the FPSO riser support system, and predicting the failure type of the FPSO riser support system as a final failure type;

[0039] a maintenance importance module: for each final failure type, obtaining historical maintenance data corresponding to each failure type, and calculating a maintenance importance coefficient according to the historical maintenance data;

[0040] a pollution module: obtaining historical pollution data corresponding to each failure type, and calculating a pollution coefficient according to the historical pollution data;

[0041] a production reduction module: obtaining historical production reduction data corresponding to each failure type, and calculating a production reduction coefficient according to the historical maintenance data;

[0042] a maintenance module: calculating a key coefficient of each failure type according to the maintenance importance coefficient, the pollution coefficient and the production reduction coefficient, and judging the maintenance urgency of the failure type of each FPSO riser support system according to the key coefficient.

[0043] The present application has the following beneficial effects:

[0044] The application provides a failure prediction method and system for an FPSO riser support system. BRIEF DESCRIPTION OF DRAWINGS

[0045] The application will be further described below with reference to the drawings.

[0046] Figure 1 A flowchart of the failure prediction method for the FPSO riser support system is provided.

[0047] Figure 2 A framework diagram of the failure prediction system for the FPSO riser support system is provided. DETAILED DESCRIPTION

[0048] The technical solutions in the embodiments of the application will be clearly and completely described below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, rather than all the embodiments of the application. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative work fall within the protection scope of the application.

[0049] Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative work fall within the protection scope of the application.

[0050] The application provides a failure prediction method for an FPSO riser support system. Figure 1 , Figure 1 A flowchart of the failure prediction method for the FPSO riser support system is provided. The method comprises the following steps:

[0051] acquire data about a failure state of the FPSO riser support system as current failure data, and calculate a similarity with each type of historical failure data of the FPSO riser support system, and predict a failure type of the FPSO riser support system as a final failure type;

[0052] For each final failure type, historical maintenance data corresponding to each failure type is acquired, and a maintenance importance coefficient is calculated according to the historical maintenance data;

[0053] Historical pollution data corresponding to each failure type is acquired, and a pollution coefficient is calculated according to the historical pollution data;

[0054] Historical production reduction data corresponding to each failure type is acquired, and a production reduction coefficient is calculated according to the historical maintenance data;

[0055] A key coefficient of each failure type is calculated according to the maintenance importance coefficient, the pollution coefficient and the production reduction coefficient, and maintenance urgency of the failure type of each FPSO riser support system is judged according to the key coefficient.

[0056] The failure prediction method of the FPSO riser support system provided in the embodiments of the present application can predict the failure of the FPSO riser support system in multiple levels through the above manner, and ensure the accuracy of the failure prediction; and in the case that multiple failures may occur at the same time, it can accurately judge which failure is the most urgent and critical, and reasonably allocate resources for priority maintenance and processing.

[0057] In one embodiment, calculating a similarity with each historical failure data of the FPSO riser support system and predicting a failure type of the FPSO riser support system as a final failure type comprises:

[0058] Each type of historical failure data is recorded as target historical failure data, and the current failure data and the target historical failure data are preprocessed;

[0059] A distance matrix is constructed, in which each element is a distance between a current failure data point and a target historical failure data point;

[0060] A shortest path in the distance matrix is calculated by using a dynamic programming algorithm to find the best match between the current failure data sequence and the target historical failure data sequence;

[0061] According to the calculated shortest path, the current failure data sequence and the target historical failure data sequence are aligned;

[0062] According to the aligned current failure data sequence and the target historical failure data sequence, a similarity between them is calculated;

[0063] The calculated similarity is compared with a similarity threshold value, and if the similarity is greater than the similarity threshold value, the corresponding historical fault type is taken as the predicted fault type.

[0064] All the predicted fault types are taken as the final fault type.

[0065] It should be noted that the similarity threshold value is set by professionals according to actual conditions, and the specific implementation is not limited and described.

[0066] It should be noted that the fault state data in the FPSO riser support system can include various key parameters such as vibration, stress, displacement, temperature, corrosion degree, load change, current data, etc., which can reflect the operation health status of the riser support system. Through sensors and monitoring devices installed on various components of the system, these data can be collected in real time. These sensors usually include strain gauges, accelerometers, temperature sensors, pressure sensors, vibration sensors, etc. The real-time monitoring data related to faults is transmitted to the central processing system through the data acquisition system for analysis and prediction. Through regular or real-time data analysis, potential faults can be discovered in time to ensure the safe and reliable operation of the FPSO riser support system.

[0067] It should be noted that the purpose of data preprocessing is to transform the data into a form suitable for calculating similarity. The preprocessing steps include: data cleaning: removing outliers, noise data, etc.; standardization or normalization: unifying the scale of data to avoid the adverse effects of differences between different dimensions on the calculation results; time series alignment: ensuring that the time window of the current fault data and the target historical fault data is consistent, which may require time interpolation or resampling of historical data; based on the preprocessed current fault data and target historical fault data, the fault type prediction and determination of the FPSO riser support system are performed.

[0068] In one implementation, the FPSO riser support system has a significant benefit by determining the potential fault type through the above method. First, it can accurately predict the potential fault type based on the similarity between historical fault data and real-time monitoring data, rather than simply relying on experience or pre-set fault models, thereby greatly improving the accuracy and foresight of the prediction; second, this method can identify subtle changes and evolution trends in fault patterns, helping maintenance personnel to discover hidden faults and potential risks in time, avoiding major safety accidents and equipment damage due to failure to discover faults in time; in addition, this method can predict multiple fault types of the FPSO riser support system, compared with single fault type prediction, this method can identify multiple potential fault types at the same time, thereby providing more comprehensive fault warning, reducing the risk of missed diagnosis due to single fault prediction, and ensuring more accurate and comprehensive maintenance decisions.

[0069] In one implementation, the application of the fault prediction method based on the dynamic time warping (DTW) algorithm in the FPSO riser support system has significant advantages. First, by accurately matching the current fault data with the historical fault data, it can identify potential risks similar to historical fault patterns, thereby providing early warning and helping maintenance personnel to timely discover possible fault types. This method does not rely on simple threshold judgment, but considers the time series characteristics of fault evolution by calculating the shortest path and similarity, and can deal with complex and nonlinear fault patterns. Secondly, the dynamic programming algorithm enables the system to handle cases where the length of the time series is inconsistent or the data is noisy, enhancing the robustness and accuracy of the prediction.

[0070] In one embodiment, calculating the maintenance importance coefficient according to historical maintenance data includes:

[0071] For each final fault type, the number of times the fault type occurs in the historical data is obtained, and the maintenance time taken each time the fault occurs is obtained, and the average maintenance time is calculated as the maintenance time coefficient;

[0072] The average time interval of maintenance is obtained, and the time interval between the current time and the last maintenance is obtained. The average maintenance time interval is subtracted from the time interval between the current time and the last maintenance to obtain the maintenance interval coefficient;

[0073] The maintenance importance coefficient is calculated according to the maintenance time coefficient and the maintenance interval coefficient, and the formula for calculation is:

[0074] ;

[0075] In the formula, is the maintenance importance coefficient, is the maintenance time coefficient, the maintenance interval coefficient, and the total number of times the fault type occurs, respectively, is a preset proportion coefficient, and are all greater than 0.

[0076] It should be noted that is set by professionals according to actual conditions. Generally, and are 1, and are not limited and described in detail;

[0077] ​It should be noted that the data involved in the above calculation can be obtained in various ways. First, the number of failures and the repair time spent each time is usually derived from the maintenance records and failure logs of the system, which are generated and archived by on-site engineers or automated monitoring systems in real time. The repair time can be obtained through the work order or repair report recorded by the maintenance personnel. In addition, the average time interval of repair can be statistically analyzed based on the historical repair data, and the repair time interval after each failure of the system is calculated. For the current time of failure and the time interval of the last repair, the time stamp of each failure needs to be captured and recorded in real time by the failure monitoring system. All these data are usually collected through sensors, maintenance management systems (such as CMMS, EAM systems) or automated monitoring systems, and stored in the database of the enterprise for subsequent analysis and calculation.

[0078] It should be noted that the greater the repair importance coefficient of each final failure type, the more urgent and critical the corresponding failure type of the FPSO riser support system failure is, and the more it needs to be repaired and handled in priority, because the greater the repair importance coefficient of each final failure type, the higher the frequency of this failure type in historical repair data, the longer the repair time required, and the shorter the repair interval, indicating that this type of failure not only occurs frequently, but also has a greater impact on the system and higher repair difficulty each time it occurs. If not handled in time, it may cause the system to be out of service for a long time or cause more serious damage. In addition, the larger value of the repair interval coefficient may also indicate that this failure has higher recurrence and accumulation, and once it fails to be repaired in time, it may exacerbate the wear and tear of the equipment or prolong the repair time. Therefore, the greater the repair importance coefficient, the higher the potential risk of this failure type in the system operation, which means that it needs to prioritize repair resources and take measures as soon as possible to avoid more serious failures or downtime of the system, thereby ensuring the safety and stability of the system.

[0079] In one implementation, the analysis of the repair importance coefficient has the following benefits for determining which failure is the most urgent and critical when multiple failures of the FPSO riser support system may occur at the same time, and how to allocate resources for priority repair and handling:

[0080] The maintenance importance coefficient can provide a quantitative standard to help decision-makers accurately identify the most urgent and critical fault types in the case of multiple faults occurring simultaneously. By considering the frequency of fault occurrence, maintenance time, and maintenance interval, the maintenance importance coefficient gives each fault type a clear priority. In the case of multiple faults occurring simultaneously, faults with higher maintenance importance coefficients usually indicate that they have a greater impact on the system, longer recovery time, or higher probability of occurrence. Therefore, prioritizing the repair of these faults can minimize potential safety risks and economic losses. Such prioritization not only avoids the neglect of minor faults due to incorrect processing order, but also ensures the most effective use of limited maintenance resources. By scientifically allocating resources, maintenance personnel can focus on solving the most critical fault problems, ensuring the stability and reliability of the FPSO riser support system, while improving overall operational efficiency, reducing downtime, and reducing maintenance costs.

[0081] In one embodiment, calculating the pollution coefficient according to historical pollution data comprises:

[0082] For each final fault type, the number of times the fault type occurs in the historical data is obtained, and the volume of oil discharged into seawater at each fault occurrence is obtained. The volume of oil discharged into seawater at each fault occurrence is designated as , , where n represents the sequence number of the volume of oil discharged into seawater at each fault occurrence, and , is the total number of fault occurrences, and is a positive integer;

[0083] The average volume of oil discharged into seawater is calculated as , and the formula for calculating is: ;

[0084] The pollution coefficient is calculated as , and the formula for calculating is: ,

[0085] In the formula, is the total number of fault occurrences, are preset proportion coefficients of , and are all greater than 0.

[0086] It should be noted that is set by professionals according to actual conditions. Generally, is 1, and specific limitations and elaborations are not made;

[0087] It should be noted that the number of historical failures and the volume of oil discharged into seawater by the storage can be obtained through a maintenance management system (such as a CMMS or EAM system) or an accident report database.

[0088] It should be noted that the greater the pollution coefficient of each final failure type, the more urgent and critical the corresponding failure type of FPSO riser support system failure is, and the more it needs to be repaired and handled in priority, because the greater the pollution coefficient of each final failure type means that a large amount of oil will be discharged into seawater once this failure type occurs, causing serious environmental pollution. This not only has a great negative impact on the marine ecosystem, but also may trigger legal, regulatory penalties and strong public opinion, affecting the company's reputation and long-term operation. In addition, pollution accidents usually require more resources and time for emergency treatment and cleanup, increasing the company's additional economic burden and risk. Therefore, failure types with high pollution coefficients are often proportional to the severity of environmental damage, and timely repair of these failures not only effectively prevents pollution accidents and reduces damage to the ecological environment, but also maximizes economic losses and legal risks. For this reason, failure types with high pollution coefficients should be considered the most urgent and critical failure types, and should be repaired and handled in priority, thereby ensuring the stable operation of the system, protecting the environment, and improving the company's social responsibility and sustainable development capabilities.

[0089] In one implementation, analyzing the pollution coefficient helps to accurately determine which failure is the most urgent and critical when multiple failures of the FPSO riser support system may occur simultaneously, and how to allocate resources for priority repair and handling. The benefits of this are: in the case of multiple failures that may occur simultaneously, the pollution coefficient can provide clear priority ranking for decision-makers, helping to accurately determine which failure types are the most urgent and critical. Higher pollution coefficient failures usually mean that they pose a greater potential threat to the environment and may trigger serious ecological pollution, environmental disasters and their chain reactions, such as legal proceedings, economic losses and damage to the company's public image. Therefore, using the pollution index to assess the environmental impact of failures can help the repair team focus resources on the failures that need to be addressed immediately, avoiding irreparable losses from neglecting high-pollution-risk failures. At the same time, this method helps to allocate limited repair resources reasonably, ensuring that the most environmentally risky failures are repaired first to prevent catastrophic consequences and improve the emergency response efficiency and overall sustainability of the FPSO riser support system. Through such resource allocation strategies, not only can the marine environment be protected and corporate social responsibility be fulfilled, but also the negative impacts and potential high costs caused by environmental pollution can be minimized, ensuring the stability and long-term healthy operation of the system.

[0090] In one embodiment, the historical production reduction data corresponding to each failure type is obtained, and the production reduction coefficient is calculated according to the historical maintenance data, including:

[0091] For each final failure type, the number of times the failure type occurs in the historical data is obtained, and the difference between the preset production oil amount and the actual production oil amount at each failure occurrence is obtained as the production reduction oil amount of this time;

[0092] The production reduction oil amounts at each failure occurrence are added to obtain the production reduction coefficient.

[0093] It should be noted that the above-mentioned preset production oil amount is set by a professional according to the actual situation, and the specific implementation is not limited and described in detail.

[0094] It should be noted that the actual production oil amount is collected by a real-time production monitoring system or an oil and gas metering device on the FPSO platform. The device, such as a flow meter, a pressure sensor, and a temperature sensor, can record the production change in real time. These monitoring devices and data acquisition systems automatically record the difference between the actual production oil amount and the preset target at each failure occurrence, the occurrence of historical failures, and the related production reduction data can be queried through failure reports and maintenance records in the production management system (such as the SCADA system) or the maintenance management system (such as the CMMS).

[0095] It should be noted that the larger the production reduction coefficient of each final failure type is, the more urgent and critical the corresponding failure type of the FPSO riser support system is, and the more it needs to be repaired and handled in priority. Because the larger the production reduction coefficient of each final failure type is, the more serious the impact of the failure on the production capacity of the FPSO riser support system is, and the greater the loss of production is. In offshore oil production, production is directly related to the economic benefit of the enterprise, therefore, any production decline caused by failure can have a significant impact on profitability and production targets. When the production reduction coefficient of the failure type is large, it means that the production capacity has decreased significantly when the failure occurs, which may cause long-term shutdown or reduced efficiency, and thus cause greater economic losses and safety hazards. Therefore, repairing and handling these failures with large production reduction coefficients in priority not only can restore production in time and reduce losses, but also can ensure the stability and reliability of the FPSO riser support system, and ensure the smooth operation of the entire production chain. This priority allocation method can help resources to be used most effectively, and reduce the overall risk caused by failure.

[0096] In one implementation, analyzing the production reduction coefficient can help determine how to accurately determine which failure is the most urgent and critical when multiple failures of the FPSO riser support system may occur at the same time, and how to allocate resources for priority repair and handling.

[0097] The production reduction coefficient plays an important role in determining the simultaneous occurrence of multiple failures in the FPSO riser support system. When multiple failures occur simultaneously, the production reduction coefficient provides a quantitative basis to help prioritize the identification of those failures that have the most severe impact on production. By calculating the production reduction coefficient for each failure type, it is clear which failures result in the greatest loss of production, allowing resources to be focused on repairing these critical failures first, thereby avoiding further declines in production efficiency. This not only ensures that production is restored as soon as possible, but also optimizes the allocation of maintenance resources, reduces downtime and maintenance costs, and improves the overall operational efficiency of the system. Through this mechanism, the rational allocation of resources can maximize benefits and ensure that the most urgent production problems are addressed promptly in emergency situations.

[0098] In one embodiment, the key coefficient of each failure type is calculated according to the maintenance importance coefficient, the pollution coefficient and the production reduction coefficient, and the maintenance urgency of the failure type of each FPSO riser support system is determined according to the key coefficient, including:

[0099] ;

[0100] wherein, is the key coefficient of the failure type, are the maintenance importance coefficient, the pollution coefficient and the production reduction coefficient, respectively; are preset proportion coefficients of , and are all greater than 0;

[0101] According to the size of the key coefficient, the failure types of each FPSO riser support system are ranked from high to low in terms of maintenance urgency.

[0102] It should be noted that is set by professionals according to actual conditions, and in general cases, the sum of is 1, for example may be 0.4, 0.3, and 0.3, respectively, or other numbers, without limitation; in addition, common normalization methods include Min-Max normalization, Z-Score standardization, etc., and the specific method is selected by professionals according to actual conditions, without limitation or elaboration;

[0103] In one implementation, the key coefficient of each failure type is calculated according to the maintenance importance coefficient, the pollution coefficient and the production reduction coefficient, and the maintenance urgency of each failure type is determined according to the key coefficient, which can help to accurately identify the most urgent and critical failure type. By sorting various failures, those failures that have a greater impact on production and environment are processed first, which can maximize the reduction of potential risks and losses caused by failures. First, the maintenance importance coefficient helps to evaluate the maintenance difficulty and historical impact of the failure, the pollution coefficient reflects the potential threat of the failure to the environment, and the production reduction coefficient directly reveals the size of the production loss. Considering these factors comprehensively can help to comprehensively evaluate the urgency of different failures, ensure that resources are preferentially invested in the most needed problems, avoid waste of maintenance resources, and maximize the reduction of system downtime and production interruption. Finally, this method can improve the efficiency and accuracy of the entire maintenance decision, optimize the maintenance and management of the FPSO riser support system, and ensure the long-term stable operation of the equipment.

[0104] Based on the same inventive concept, the embodiments of the present application also provide a failure prediction system of an FPSO riser support system. Referring to Figure 2 , Figure 2 A block diagram of a failure prediction system of an FPSO riser support system is provided for the embodiments of the present application. The system comprises:

[0105] The final failure type module: acquires data about the failure state of the FPSO riser support system as current failure data, and calculates the similarity between the current failure data and the historical failure data of each type of the FPSO riser support system, and predicts the failure type of the FPSO riser support system as the final failure type;

[0106] The maintenance importance module: for each final failure type, acquires the historical maintenance data corresponding to each failure type, and calculates the maintenance importance coefficient according to the historical maintenance data;

[0107] The pollution module: acquires the historical pollution data corresponding to each failure type, and calculates the pollution coefficient according to the historical pollution data;

[0108] The production reduction module: acquires the historical production reduction data corresponding to each failure type, and calculates the production reduction coefficient according to the historical maintenance data;

[0109] The maintenance module: calculates the key coefficient of each failure type according to the maintenance importance coefficient, the pollution coefficient and the production reduction coefficient, and determines the maintenance urgency of each failure type of the FPSO riser support system according to the key coefficient.

[0110] Based on the fault prediction system of the FPSO riser support system provided by the embodiment of the application, the fault of the FPSO riser support system can be predicted in multiple levels through the above manner, and the accuracy of fault prediction is ensured; and in the case that multiple faults may occur at the same time, which fault is the most urgent and critical can be accurately judged, and resources are reasonably allocated for priority maintenance and processing.

[0111] The above describes one embodiment of the application in detail, but the content is only the preferred embodiment of the application, and cannot be artificially used to limit the implementation range of the application. Any equivalent changes and improvements made within the scope of the application are still within the scope of the patent coverage of the application.

Claims

1. A method for predicting a failure of an FPSO riser support system, characterized in that: The following steps are involved: Acquire data on the fault status of the FPSO riser support system as current fault data, calculate similarity with each type of historical fault data of the FPSO riser support system, and predict the fault type of the FPSO riser support system as a final fault type; For each final fault type, obtain the historical maintenance data corresponding to each fault type, and calculate the maintenance importance coefficient based on the historical maintenance data; Obtain historical pollution data corresponding to each fault type and calculate the pollution coefficient based on the historical pollution data; Obtain historical production reduction data corresponding to each fault type and calculate the production reduction coefficient based on historical maintenance data; Calculate the critical coefficient of each fault type based on the maintenance importance coefficient, pollution coefficient and production reduction coefficient, and judge the maintenance urgency of each FPSO riser support system fault type based on the critical coefficient; The similarity between the data and each historical fault data of the FPSO riser support system is calculated, and the fault type of the FPSO riser support system is predicted as the final fault type, including: Record each type of historical fault data as target historical fault data, and pre-process the current fault data and the target historical fault data; Construct a distance matrix where each element is the distance between the current fault data point and the target historical fault data point; A dynamic programming algorithm is used to calculate the shortest path in the distance matrix to find the best match between the current fault data sequence and the target historical fault data sequence; Based on the calculated shortest path, align the current fault data sequence with the target historical fault data sequence; Calculate the similarity between the aligned current fault data sequence and the target historical fault data sequence; Compare the calculated similarity with the similarity threshold. If the similarity is greater than the similarity threshold, the corresponding historical fault type is used as the predicted fault type. All predicted fault types are taken as final fault types; The critical coefficient of each fault type is calculated based on the maintenance importance coefficient, pollution coefficient and production reduction coefficient. The maintenance urgency of each FPSO riser support system fault type is determined based on the critical coefficient. ； Where, is the critical coefficient of the fault type, They are maintenance importance coefficient, pollution coefficient and production reduction coefficient; They are The preset scaling factor of All are greater than 0; According to the magnitude of the critical coefficient, the fault types of each FPSO riser support system are ranked from high to low in terms of maintenance urgency; Calculation of maintenance importance coefficient based on historical maintenance data includes: For each final fault type, obtain the number of times the fault type occurs in the historical data, obtain the maintenance time spent on each fault, and calculate the mean maintenance time as the maintenance time coefficient; Obtain the average maintenance interval and the time interval between the current time and the last maintenance of the fault. Subtract the time interval between the current time and the last maintenance from the average maintenance interval to obtain the maintenance interval coefficient. The maintenance importance coefficient is calculated based on the maintenance time coefficient and the maintenance interval coefficient. The calculation formula is: ； Where, is the maintenance importance factor, are the maintenance time coefficient, maintenance interval coefficient and the total number of occurrences of the fault type, They are The preset scaling factor of All greater than 0; Calculation of pollution coefficients based on historical pollution data includes: For each final fault type, obtain the number of times the fault type occurs in the historical data, and obtain the volume of seawater discharged from the oil storage each time the fault occurs. The volume of seawater discharged from the oil storage each time the fault occurs is calibrated as , The order number represents the volume of seawater discharged from the oil storage each time a failure occurs, and , is the total number of faults that occurred, and is a positive integer; Calculate the average volume of seawater discharged from oil storage , the calculation formula is: ; Calculate the pollution coefficient , the calculation formula is: , Where, is the total number of times the fault type occurs, They are The preset scaling factor of Both are greater than 0.

2. A fault prediction method for an FPSO riser support system according to claim 1, characterized in that: Obtaining historical production reduction data corresponding to each fault type and calculating the production reduction coefficient based on historical maintenance data includes: For each final fault type, obtain the number of times the fault type occurs in the historical data, and obtain the difference between the preset oil production volume and the actual oil production volume when the fault occurs each time, as the oil production reduction volume for that time; The production reduction coefficient is obtained by adding up all the oil production reductions when each failure occurs.

3. A fault prediction system for an FPSO riser support system, used to implement the fault prediction method for an FPSO riser support system according to any one of claims 1 to 2, characterized in that: The system comprises: Final fault type module: obtains data on the fault status of the FPSO riser support system as current fault data, calculates the similarity with each type of historical fault data of the FPSO riser support system, and predicts the fault type of the FPSO riser support system as the final fault type; Maintenance importance module: For each final fault type, obtain the historical maintenance data corresponding to each fault type and calculate the maintenance importance coefficient based on the historical maintenance data; Pollution module: obtains historical pollution data corresponding to each fault type and calculates the pollution coefficient based on the historical pollution data; Production reduction module: obtains historical production reduction data corresponding to each fault type and calculates the production reduction coefficient based on historical maintenance data; Maintenance module: Calculates the critical coefficient of each fault type based on the maintenance importance coefficient, pollution coefficient and production reduction coefficient, and determines the maintenance urgency of each FPSO riser support system fault type based on the critical coefficient.

Images