Intelligent health diagnosis and maintenance decision-making system and method for complex equipment
By building regional seasonal Wiener process models and intelligent maintenance decision-making methods, the problems of complex equipment performance degradation and failure prediction are solved, real-time health monitoring and optimized maintenance are achieved, and the reliability and service life of equipment are improved.
Patent Information
- Application Number
- CN202411778166.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-05
- Publication Date
- 2025-08-08
AI Technical Summary
The prior art is difficult to effectively deal with performance degradation and failure prediction of complex equipment, especially in water weapons and aircraft that consider seasonal effects. Traditional models are not very applicable and cannot achieve real-time health monitoring and optimized maintenance.
A regional seasonal Wiener process model is constructed for complex equipment, combined with linear regression and linear interpolation methods, perform performance degradation trend fit and residual life prediction, form a state-based health evaluation method, and formulate intelligent maintenance decisions.
Real-time health status monitoring and failure time prediction of complex equipment are realized, optimized maintenance strategies are provided, and the reliability and service life of equipment are improved, and maintenance costs and downtime are reduced.
Smart Images
Figure CN120449397A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of intelligent diagnosis and maintenance decision-making of complex equipment, and in particular to an intelligent health diagnosis and maintenance decision-making system and method for complex equipment. Background Art
[0002] Complex equipment such as underwater weapons and aircraft plays an important role in the modern military industry. Their operating environment is complex, and the quality of their health status directly affects the combat readiness and mission success of the equipment. Real-time monitoring and fault diagnosis are of great significance. Traditional fault diagnosis methods are difficult to effectively deal with the performance degradation and fault prediction problems of complex equipment. Existing technologies mainly rely on regular inspections and experience-based maintenance strategies, which cannot effectively predict the failure time of equipment and optimize maintenance plans. Complex equipment usually goes through multiple stages such as storage, transportation, duty, and maintenance throughout its life cycle. The events experienced during this period will vary due to individual differences. The various stresses such as temperature, vibration, and impact experienced will show obvious stress randomness due to the randomness of the events. Within a certain range of quantitative values, the performance degradation trends caused to complex equipment show different patterns.
[0003] The Wiener process, also known as Brownian motion, is used to describe a continuous-time random process in which a random variable changes over time. It can describe the random characteristics exhibited in performance degradation. China has a long maritime area and a continental coastline that stretches 18,000 kilometers, stretching from the Yalu River estuary in the north to the Beilun River estuary in the south, spanning 23 dimensions. Complex equipment deployed in different regions exhibits significant regional seasonality. Traditional Wiener process models do not account for the performance degradation effects of seasonality. Therefore, constructing a seasonal Wiener process model can achieve state-based prediction of the remaining life and health status of complex equipment, which has great application prospects.
[0004] At present, there is no mature health management method for complex equipment such as underwater weapons and aircraft, and the existing technical basis is still a traditional model with low applicability. Therefore, it is necessary to build an intelligent health management and maintenance decision-making method for complex equipment with a wider range of applicability. Summary of the Invention
[0005] This invention provides an intelligent health diagnosis and maintenance decision-making method for complex equipment using an improved Wiener process, addressing shortcomings in existing technologies. This method enables real-time monitoring of equipment health, predicting performance degradation and failure onset, and developing optimized maintenance strategies, improving equipment reliability and efficiency.
[0006] An embodiment of the present invention provides an intelligent health diagnosis and maintenance decision-making system for complex equipment, including:
[0007] The data module includes an acquisition module and a processing module, which is used to collect the specific performance parameter types, data formats and processing methods of complex equipment;
[0008] The health evaluation module, including the performance degradation module and the health assessment module, is used to build a Wiener process model that takes regional seasonality into account. Based on the model, performance degradation trend fitting and remaining life prediction are carried out to form a state-based health evaluation method.
[0009] Maintenance decision module, used for intelligent maintenance decision-making method based on health assessment report.
[0010] In some embodiments, the specific performance parameter types, data formats, and processing methods of the complex equipment are collected, including:
[0011] Step A1: Based on the FMECA, FTA, and FHA analysis results of the complex equipment, select all failure modes that may affect the equipment's mission completion after a failure occurs, and form a key product list;
[0012] Step A2: Based on the sorted key product information and combined with the test diagnosis plan for complex equipment, a data collection method and interface information requirement table for key products are developed, and data collection work is carried out accordingly;
[0013] Step A3: Collect performance data of key products and use linear regression method to perform preliminary model fitting on the data, identify key characteristic parameters of complex equipment, and use these parameters as monitoring objects for performance degradation.
[0014] In some embodiments, the construction of a Wiener process model that takes regional seasonality into consideration, performing performance degradation trend fitting and remaining life prediction based on the model, and forming a state-based health assessment method include:
[0015] Step B1, based on the Wiener process model, introduce the regional seasonal factor model, which is defined as the "regional seasonal Wiener model";
[0016] Step B2: extract seasonal data, place different seasonal data into a data matrix, match the time history with the measured performance data, and complete Wiener process fitting of different seasonal data to fit the degradation model and draw the degradation curve to obtain the drift coefficient and diffusion coefficient of each model;
[0017] Step B3: Based on the performance threshold of the key components and the degradation curve and model fitted in step B2, calculate the time history required to reach the failure threshold in each season and calculate the remaining life;
[0018] Step B4: Calculate the drift coefficient and diffusion coefficient of the future deployment area using a linear interpolation method based on the drift coefficient and diffusion coefficient for different seasons calculated in step B2, and fit a new degradation curve and model.
[0019] Step B5: Based on the future deployment area model and degradation curve established in step B4, and also based on the performance threshold, calculate the time required for the future deployment area to reach the failure threshold;
[0020] Step B6: extract the fitting model and calculation results in steps B2 to B5, complete the fault prediction and remaining life prediction, and form a health status assessment report.
[0021] In some embodiments, the intelligent maintenance decision-making method based on the health assessment report includes:
[0022] Step C1, extracting the health status of the complex equipment according to the health status assessment report generated by the health assessment module, and constructing an extraction model based on the extraction factors;
[0023] Step C2: Based on the items determined in step C1, an intelligent guarantee decision table is formed, and the order in the decision table is sorted according to the size of the sorting factor;
[0024] Step C3: Based on the intelligent guarantee decision table and combined with the product maintenance and repair manuals, a specific maintenance implementation plan is formed;
[0025] Step C4, completing intelligent maintenance judgment of this type of complex equipment;
[0026] Step C5: After the maintenance and repair work is completed, the product information is updated and the health status assessment is completed again based on the test information to achieve real-time monitoring effect.
[0027] An embodiment of the present invention provides an intelligent health diagnosis and maintenance decision-making method for complex equipment, the method comprising:
[0028] Collect specific performance parameter types, data formats and processing methods of complex equipment;
[0029] Construct a Wiener process model that takes regional seasonality into account, conduct performance degradation trend fitting and remaining life prediction based on the model, and form a state-based health assessment method;
[0030] Intelligent maintenance decision-making method based on health assessment report.
[0031] In some embodiments, the specific performance parameter types, data formats, and processing methods of the complex equipment are collected, including:
[0032] Step A1: Based on the FMECA, FTA, and FHA analysis results of the complex equipment, select all failure modes that may affect the equipment's mission completion after a failure occurs, and form a key product list;
[0033] Step A2: Based on the sorted key product information and combined with the test diagnosis plan for complex equipment, a data collection method and interface information requirement table for key products are developed, and data collection work is carried out accordingly;
[0034] Step A3: Collect performance data of key products and use linear regression method to perform preliminary model fitting on the data, identify key characteristic parameters of complex equipment, and use these parameters as monitoring objects for performance degradation.
[0035] In some embodiments, the construction of a Wiener process model that takes regional seasonality into consideration, performing performance degradation trend fitting and remaining life prediction based on the model, and forming a state-based health assessment method include:
[0036] Step B1, based on the Wiener process model, introduce the regional seasonal factor model, which is defined as the "regional seasonal Wiener model";
[0037] Step B2: extract seasonal data, place different seasonal data into a data matrix, match the time history with the measured performance data, and complete Wiener process fitting of different seasonal data to fit the degradation model and draw the degradation curve to obtain the drift coefficient and diffusion coefficient of each model;
[0038] Step B3: Based on the performance threshold of the key components and the degradation curve and model fitted in step B2, calculate the time history required to reach the failure threshold in each season and calculate the remaining life;
[0039] Step B4: Calculate the drift coefficient and diffusion coefficient of the future deployment area using a linear interpolation method based on the drift coefficient and diffusion coefficient for different seasons calculated in step B2, and fit a new degradation curve and model.
[0040] Step B5: Based on the future deployment area model and degradation curve established in step B4, and also based on the performance threshold, calculate the time required for the future deployment area to reach the failure threshold;
[0041] Step B6: extract the fitting model and calculation results in steps B2 to B5, complete the fault prediction and remaining life prediction, and form a health status assessment report.
[0042] In some embodiments, the intelligent maintenance decision-making based on the health assessment report includes:
[0043] Step C1, extracting the health status of the complex equipment according to the health status assessment report, and constructing an extraction model based on the extraction factors;
[0044] Step C2: Based on the items determined in step C1, an intelligent guarantee decision table is formed, and the order in the decision table is sorted according to the size of the sorting factor;
[0045] Step C3: Based on the intelligent guarantee decision table and combined with the product maintenance and repair manuals, a specific maintenance implementation plan is formed;
[0046] Step C4, completing intelligent maintenance judgment of this type of complex equipment;
[0047] Step C5: After the maintenance and repair work is completed, the product information is updated and the health status assessment is completed again based on the test information to achieve real-time monitoring effect.
[0048] An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by one or more processors, the method described in any of the above embodiments is implemented.
[0049] An embodiment of the present invention provides an electronic device, including: one or more processors;
[0050] A storage device stores one or more programs thereon, and when the one or more programs are executed by the one or more processors, the method described in any of the above embodiments is implemented.
[0051] The beneficial effects of the above embodiment include:
[0052] This invention builds a Wiener performance degradation model suitable for seasonal variations in complex equipment, along with an intelligent maintenance decision-making method. This model can quantitatively predict equipment failure time and remaining lifespan, providing optimized maintenance strategies that improve equipment reliability and service life while reducing maintenance costs and downtime. This intelligent health diagnosis and maintenance decision-making system, built using this invention, enables users to monitor equipment status in real time and take timely maintenance measures to ensure safe and efficient operation. BRIEF DESCRIPTION OF THE DRAWINGS
[0053] The accompanying drawings illustrate generally, by way of example and not limitation, various embodiments discussed herein.
[0054] Figure 1 This is a method processing flow chart for data module A;
[0055] Figure 2 This is the method processing flow chart for health assessment module B;
[0056] Figure 3 This is a method processing flow chart for the intelligent maintenance decision module C;
[0057] Figure 4 This is the performance degradation curve at 50℃;
[0058] Figure 5 This is the performance degradation curve at 30℃;
[0059] Figure 6 This is the performance degradation curve at -30℃. DETAILED DESCRIPTION
[0060] In order to enable a more detailed understanding of the features and technical contents of the embodiments of the present application, the implementation of the embodiments of the present application is described in detail below with reference to the accompanying drawings. The attached drawings are for reference only and are not used to limit the embodiments of the present application.
[0061] In the description of the embodiments of this application, it should be noted that, unless otherwise specified and limited, the term "connection" should be understood in a broad sense. For example, it can be an electrical connection, or it can be the internal connection between two components. It can be a direct connection or an indirect connection through an intermediate medium. For ordinary technicians in this field, the specific meaning of the above terms can be understood according to the specific circumstances.
[0062] It should be noted that the terms "first, second, and third" in the embodiments of the present application are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It is understood that the terms "first, second, and third" can be interchanged to represent a specific order or precedence where permitted. It should be understood that the objects distinguished by "first, second, and third" can be interchanged where appropriate, such that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.
[0063] An embodiment of the present invention provides an intelligent health diagnosis and maintenance decision-making system for complex equipment, including:
[0064] The data module includes an acquisition module and a processing module, which is used to collect the specific performance parameter types, data formats and processing methods of complex equipment.
[0065] The health evaluation module, including the performance degradation module and the health assessment module, is used to construct a Wiener process model that takes regional seasonality into consideration, and to carry out performance degradation trend fitting and remaining life prediction based on the model to form a state-based health evaluation method.
[0066] Maintenance decision module, used for intelligent maintenance decision-making method based on health assessment report.
[0067] In some embodiments, the specific performance parameter types, data formats, and processing methods of complex equipment are collected, including:
[0068] In step A1, based on the FMECA, FTA, and FHA analysis results of complex equipment, all failure modes that affect the completion of equipment missions after a failure occurs are selected to form a key product list information.
[0069] Step A2: Based on the sorted key product information and combined with the test diagnosis plan of complex equipment, a data collection method and interface information requirement table for key products are formed, and data collection work is carried out accordingly.
[0070] Step A3: Collect performance data of key products and use linear regression method to perform preliminary model fitting on the data, identify key characteristic parameters of complex equipment, and use these parameters as monitoring objects for performance degradation.
[0071] In some embodiments, a Wiener process model that takes regional seasonality into account is constructed, and performance degradation trend fitting and remaining life prediction are performed based on the model to form a state-based health assessment method, including:
[0072] Step B1, based on the Wiener process model, introduces a regional seasonal factor model, which is defined as the "regional seasonal Wiener model".
[0073] Step B2: Extract seasonal data, put different seasonal data into the data matrix, make one-to-one correspondence between the time history and the measured performance data, complete the Wiener process fitting of different seasonal data, fit the degradation model and draw the degradation curve, and obtain the drift coefficient and diffusion coefficient of each model.
[0074] In step B3, based on the performance threshold of the key components and the degradation curve and model fitted in step B2, the time history required to reach the failure threshold in each season is calculated to calculate the remaining life.
[0075] In step B4, based on the drift coefficient and diffusion coefficient in different seasons calculated in step B2, a linear interpolation method is used to calculate the drift coefficient and diffusion coefficient of the future deployment area, and a new degradation curve and model are fitted.
[0076] In step B5, based on the future deployment area model and degradation curve established in step B4, the time required for the future deployment area to reach the failure threshold is calculated based on the performance threshold.
[0077] Step B6: extract the fitting model and calculation results in steps B2 to B5, complete the fault prediction and remaining life prediction, and form a health status assessment report.
[0078] In some embodiments, a smart maintenance decision-making method based on a health assessment report includes:
[0079] Step C1: extract the health status of the complex equipment according to the health status assessment report generated by the health evaluation module, and construct an extraction model based on the extraction factors.
[0080] In step C2, an intelligent guarantee decision table is formed based on the items determined in step C1, and the order in the decision table is sorted according to the size of the sorting factor.
[0081] Step C3: Based on the intelligent guarantee decision table and combined with the product maintenance and repair manual, a specific maintenance implementation plan is formed.
[0082] Step C4, complete the intelligent maintenance judgment of this type of complex equipment.
[0083] Step C5: After the maintenance and repair work is completed, the product information is updated and the health status assessment is completed again based on the test information to achieve real-time monitoring effect.
[0084] An embodiment of the present invention provides an intelligent health diagnosis and maintenance decision-making method for complex equipment, the method comprising:
[0085] Collect specific performance parameter types, data formats and processing methods of complex equipment.
[0086] A Wiener process model that takes regional seasonality into consideration is constructed, and performance degradation trend fitting and remaining life prediction are carried out based on the model to form a state-based health assessment method.
[0087] Intelligent maintenance decision-making method based on health assessment report.
[0088] In some embodiments, the specific performance parameter types, data formats, and processing methods of complex equipment are collected, including:
[0089] In step A1, based on the FMECA, FTA, and FHA analysis results of complex equipment, all failure modes that affect the completion of equipment missions after a failure occurs are selected to form a key product list information.
[0090] Step A2: Based on the sorted key product information and combined with the test diagnosis plan of complex equipment, a data collection method and interface information requirement table for key products are formed, and data collection work is carried out accordingly.
[0091] Step A3: Collect performance data of key products and use linear regression method to perform preliminary model fitting on the data, identify key characteristic parameters of complex equipment, and use these parameters as monitoring objects for performance degradation.
[0092] In some embodiments, a Wiener process model that takes regional seasonality into account is constructed, and performance degradation trend fitting and remaining life prediction are performed based on the model to form a state-based health assessment method, including:
[0093] Step B1, based on the Wiener process model, introduces a regional seasonal factor model, which is defined as the "regional seasonal Wiener model".
[0094] Step B2: Extract seasonal data, put different seasonal data into the data matrix, make one-to-one correspondence between the time history and the measured performance data, complete the Wiener process fitting of different seasonal data, fit the degradation model and draw the degradation curve, and obtain the drift coefficient and diffusion coefficient of each model.
[0095] In step B3, based on the performance threshold of the key components and the degradation curve and model fitted in step B2, the time history required to reach the failure threshold in each season is calculated to calculate the remaining life.
[0096] In step B4, based on the drift coefficient and diffusion coefficient in different seasons calculated in step B2, a linear interpolation method is used to calculate the drift coefficient and diffusion coefficient of the future deployment area, and a new degradation curve and model are fitted.
[0097] In step B5, based on the future deployment area model and degradation curve established in step B4, the time required for the future deployment area to reach the failure threshold is calculated based on the performance threshold.
[0098] Step B6: extract the fitting model and calculation results in steps B2 to B5, complete the fault prediction and remaining life prediction, and form a health status assessment report.
[0099] In some embodiments, intelligent maintenance decision-making based on health assessment reports includes:
[0100] Step C1: extract the health status of complex equipment according to the health status assessment report, and build an extraction model based on the extraction factors.
[0101] In step C2, an intelligent guarantee decision table is formed based on the items determined in step C1, and the order in the decision table is sorted according to the size of the sorting factor.
[0102] Step C3: Based on the intelligent guarantee decision table and combined with the product maintenance and repair manual, a specific maintenance implementation plan is formed.
[0103] Step C4, complete the intelligent maintenance judgment of this type of complex equipment.
[0104] Step C5: After the maintenance and repair work is completed, the product information is updated and the health status assessment is completed again based on the test information to achieve real-time monitoring effect.
[0105] An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by one or more processors, the method of any of the above embodiments is implemented.
[0106] An embodiment of the present invention provides an electronic device, including: one or more processors.
[0107] A storage device stores one or more programs thereon, and when the one or more programs are executed by one or more processors, the method of any of the above embodiments is implemented.
[0108] This invention provides an intelligent health diagnosis and maintenance decision-making method for complex equipment using an improved Wiener process, addressing shortcomings in existing technologies. This method enables real-time monitoring of equipment health, predicting performance degradation and failure onset, and developing optimized maintenance strategies, improving equipment reliability and efficiency.
[0109] The technical solution of the present invention is:
[0110] This solution describes an intelligent health diagnosis and maintenance decision-making system for complex equipment, which includes a data module A (including an acquisition module and a processing module), a health evaluation module B (including a performance degradation module and a health assessment module) and a maintenance decision-making module C.
[0111] Data module A: The specific performance parameter type, data format and processing method of a complex equipment are collected. See the method flow for details. Figure 1 , mainly including the following steps:
[0112] Step A1: Based on the FMECA, FTA, and FHA analysis results of complex equipment, select all failure modes that affect the equipment's mission completion after a failure occurs and generate a key product list (including product name, key failure mode, characterization parameters, and index requirements, etc.) in the following format;
[0113] Serial number Key product names Key failure modes Characterization parameters Index requirements
[0114] Table 1 Preliminary key product list information
[0115] Step A2: Based on the sorted key product information and combined with the test diagnosis plan for complex equipment, a table of data collection methods and interface information requirements for key products is formed (see Table 2 for the format). Data collection is then carried out accordingly.
[0116]
[0117] Table 2 Data collection method and interface information requirements
[0118] Step A3: Following Steps A1 and A2, collect performance data for key products. Use linear regression to perform a preliminary model fit on the data, further clarifying the key characteristic parameters of complex equipment and using these parameters as indicators for performance degradation monitoring. See Table 3 for the data collection details.
[0119]
[0120] Table 3 Determine the key characteristic parameter information table
[0121] Health Assessment Module B: A Wiener process model considering regional seasonality is constructed, and performance degradation trend fitting and remaining life prediction are carried out based on the model to form a state-based health assessment method. The method flow is shown in Figure 2 , mainly including the following steps:
[0122] Step B1: Based on the Wiener process model, introduce the regional seasonal factor model, which is defined as the "regional seasonal Wiener model". The specific modeling process is as follows:
[0123] The mathematical definition of the general Wiener process is:
[0124] X(t)=X(0)+μt+σW(t)
[0125] Where: X(0) is the initial state (initial healthy state); μ is the average drift rate during the degradation process (indicating the average speed of product degradation); σ is the diffusion coefficient (indicating random fluctuations during the degradation process).
[0126] Based on the different deployment areas of complex equipment, the regional seasonal factors are introduced to improve the Wiener model. The "regional seasonal Wiener model" is as follows:
[0127] X(t)=X(0)+μt+σW(t)+γsin(wt+φ)
[0128] where γsin(wt+φ) represents the seasonal variation term; γ is the amplitude of seasonal variation; w is the seasonal period; and φ is the phase.
[0129] Step B2: Extract seasonal data according to Table 3, put different seasonal data into the data matrix, and make a one-to-one correspondence between the time history and the measured performance data. According to the "regional seasonal Wiener model" in step B1, complete the Wiener process fitting of different seasonal data, fit the degradation model and draw the degradation curve, and obtain the drift coefficient μ of each model i and the diffusion coefficient σ i ;
[0130] Step B3: Based on the performance thresholds of key components and the degradation curves and models fitted in Step B2, calculate the time history required to reach the failure threshold in each season and calculate the remaining life;
[0131] Step B4: According to the drift coefficient μ in different seasons calculated in step B2 i and the diffusion coefficient σ i , using the linear interpolation method, calculate the drift coefficient μ of the future deployment area (i.e., the seasonality of the future region) x and the diffusion coefficient σ x , and fit a new degradation curve and model;
[0132] Step B5: Based on the future deployment area model and degradation curve established in step B4, and also based on the performance threshold, calculate the time required for the future deployment area to reach the failure threshold;
[0133] Step B6: Extract the fitting model and calculation results in steps B2 to B5, complete the fault prediction and remaining life prediction, and form a health status assessment report.
[0134] Maintenance decision module C: The intelligent maintenance decision method based on health assessment report, the process is shown in Figure 3 , mainly including the following steps:
[0135] Step C1: Extract the health status of complex equipment based on the health report generated by the health assessment module B, and build an extraction model based on the extraction factor Q to determine:
[0136]
[0137] Where: X i is the measured value of a key performance indicator; M is the failure threshold of the indicator; T RUL is the remaining life expectancy estimated according to the health model; T i1 It is the usage time of the i-th key component of complex equipment within one mission cycle. One mission cycle is determined according to the actual equipment profile, such as the torpedo loading cycle is one year or three years. K is the margin coefficient, which is determined according to the actual needs of the equipment and is generally 1.3 to 1.5.
[0138] Extraction factor description: "2" represents a fault, which is a mandatory item; "0" represents sufficient performance margin, which is not a mandatory item; "1" represents insufficient performance, which is a mandatory item.
[0139] Step C2: Based on the items determined in step C1, an intelligent guarantee decision table is formed based on the extracted items. The order in the decision table is sorted according to the size of the sorting factor P. The sorting factor P is defined as follows:
[0140]
[0141]
[0142] Table 4 Intelligent security decision table
[0143] Step C3: Based on the intelligent support decision table and combined with the product maintenance and repair manuals, a specific maintenance implementation plan is developed. The implementation plan should at least cover the following:
[0144] a) List of repair and maintenance items;
[0145] b) Repair and maintenance level;
[0146] c) Handling of faulty parts or parts with performance degradation;
[0147] d) Maintenance spare parts status, including inventory status, production unit, purchase cycle, price, etc.;
[0148] e) Maintenance operations and required tools, equipment, consumables, personnel, etc.;
[0149] f) Estimated completion period.
[0150] Step C4: According to Figure 3 The process requirements are met to complete the intelligent maintenance judgment of this type of complex equipment.
[0151] Step C5: After the maintenance and repair work is completed, the product information is updated and the health status assessment is completed again based on the test information to achieve real-time monitoring effect.
[0152] Assuming that a certain type of complex equipment has completed the tasks of obtaining a preliminary key product list, collecting key product data, and collecting interface information requirements in accordance with data module A, a table of key characteristic parameter information is formed, as shown in Table 5. The failure threshold is assumed to be lower than 30 m / s.
[0153]
[0154] Table 5 Determination of key characteristic parameter information table
[0155] According to steps B2, B3, and B4, the regional seasonal Wiener model fitting, performance degradation curve fitting, and remaining life prediction are completed at 50℃, 30℃, and -30℃ respectively. At the same time, the seasonal Wiener model, performance degradation curve, and remaining life expected in the -30℃ area in the future are predicted, such as Figure 4 、 Figure 5 and Figure 6 shown.
[0156] If the component works at 50℃ to 90℃, it has entered the end stage of performance degradation according to the performance degradation curve. It is necessary to make intelligent maintenance decisions or optimize deployment in a new area. For example, deploying it to an area with a temperature of 30℃ can further extend its service life.
[0157] According to the requirements of step C1, the component extraction factor Q is calculated to be 1, indicating insufficient performance degradation, which is a mandatory item. After completing the performance data fitting of all key components, the components are compared and ranked (based on the ranking factor P). In conjunction with the maintenance manual, a maintenance implementation plan for this type of equipment is formed. The content of the implementation plan is formed according to the elements specified in step C3.
[0158] After completing the maintenance and repair work according to the implementation plan, re-evaluate the health and predict the next maintenance time to achieve intelligent maintenance decision management.
[0159] The technical solutions described in the embodiments of this application can be combined arbitrarily unless there is any conflict.
[0160] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.
Claims
1. An intelligent health diagnosis and maintenance decision system for complex equipment, characterized by: include: The data module includes an acquisition module and a processing module, which is used to collect the specific performance parameter types, data formats and processing methods of complex equipment; The health evaluation module, including the performance degradation module and the health assessment module, is used to build a Wiener process model that takes regional seasonality into account. Based on the model, performance degradation trend fitting and remaining life prediction are carried out to form a state-based health evaluation method. Maintenance decision module, used for intelligent maintenance decision-making method based on health assessment report.
2. The intelligent health diagnosis and maintenance decision system for complex equipment according to claim 1 is characterized in that: The specific performance parameter types, data formats and processing methods of the complex equipment collected include: Step A1: Based on the FMECA, FTA, and FHA analysis results of the complex equipment, select all failure modes that may affect the equipment's mission completion after a failure occurs, and form a key product list; Step A2: Based on the sorted key product information and combined with the test diagnosis plan for complex equipment, a data collection method and interface information requirement table for key products are developed, and data collection work is carried out accordingly; Step A3: Collect performance data of key products and use linear regression method to perform preliminary model fitting on the data, identify key characteristic parameters of complex equipment, and use these parameters as monitoring objects for performance degradation.
3. The intelligent health diagnosis and maintenance decision system for complex equipment according to claim 2 is characterized in that: The Wiener process model considering regional seasonality is constructed, and performance degradation trend fitting and remaining life prediction are carried out based on the model to form a state-based health assessment method, including: Step B1: Based on the Wiener process model, a regional seasonal factor model is introduced, which is defined as the "regional seasonal Wiener model"; Step B2: extract seasonal data, place different seasonal data into a data matrix, match the time history with the measured performance data, and complete Wiener process fitting of different seasonal data to fit the degradation model and draw the degradation curve to obtain the drift coefficient and diffusion coefficient of each model; Step B3: Based on the performance threshold of the key components and the degradation curve and model fitted in step B2, calculate the time history required to reach the failure threshold in each season and calculate the remaining life; Step B4: Calculate the drift coefficient and diffusion coefficient of the future deployment area using a linear interpolation method based on the drift coefficient and diffusion coefficient for different seasons calculated in step B2, and fit a new degradation curve and model. Step B5: Based on the future deployment area model and degradation curve established in step B4, and also based on the performance threshold, calculate the time required for the future deployment area to reach the failure threshold; Step B6: extract the fitting model and calculation results in steps B2 to B5, complete the fault prediction and remaining life prediction, and form a health status assessment report.
4. The intelligent health diagnosis and maintenance decision system for complex equipment according to claim 3 is characterized in that: The intelligent maintenance decision-making method based on the health assessment report includes: Step C1, extracting the health status of the complex equipment according to the health status assessment report generated by the health assessment module, and constructing an extraction model based on the extraction factors; Step C2: Based on the items determined in step C1, an intelligent guarantee decision table is formed, and the order in the decision table is sorted according to the size of the sorting factor; Step C3: Based on the intelligent guarantee decision table and combined with the product maintenance and repair manuals, a specific maintenance implementation plan is formed; Step C4, completing intelligent maintenance judgment of this type of complex equipment; Step C5: After the maintenance and repair work is completed, the product information is updated and the health status assessment is completed again based on the test information to achieve real-time monitoring effect.
5. An intelligent health diagnosis and maintenance decision-making method for complex equipment, characterized by: The method comprises: Collect specific performance parameter types, data formats and processing methods of complex equipment; Construct a Wiener process model that takes regional seasonality into account, conduct performance degradation trend fitting and remaining life prediction based on the model, and form a state-based health assessment method; Intelligent maintenance decision-making method based on health assessment report.
6. The intelligent health diagnosis and maintenance decision-making method for complex equipment according to claim 5 is characterized in that: The specific performance parameter types, data formats and processing methods of the complex equipment collected include: Step A1: Based on the FMECA, FTA, and FHA analysis results of the complex equipment, select all failure modes that may affect the equipment's mission completion after a failure occurs, and form a key product list; Step A2: Based on the sorted key product information and combined with the test diagnosis plan for complex equipment, a data collection method and interface information requirement table for key products are developed, and data collection work is carried out accordingly; Step A3: Collect performance data of key products and use linear regression method to perform preliminary model fitting on the data, identify key characteristic parameters of complex equipment, and use these parameters as monitoring objects for performance degradation.
7. The intelligent health diagnosis and maintenance decision-making method for complex equipment according to claim 6 is characterized in that: The Wiener process model considering regional seasonality is constructed, and performance degradation trend fitting and remaining life prediction are carried out based on the model to form a state-based health assessment method, including: Step B1: Based on the Wiener process model, a regional seasonal factor model is introduced, which is defined as the "regional seasonal Wiener model"; Step B2: extract seasonal data, place different seasonal data into a data matrix, match the time history with the measured performance data, and complete Wiener process fitting of different seasonal data to fit the degradation model and draw the degradation curve to obtain the drift coefficient and diffusion coefficient of each model; Step B3: Based on the performance threshold of the key components and the degradation curve and model fitted in step B2, calculate the time history required to reach the failure threshold in each season and calculate the remaining life; Step B4: Calculate the drift coefficient and diffusion coefficient of the future deployment area using a linear interpolation method based on the drift coefficient and diffusion coefficient for different seasons calculated in step B2, and fit a new degradation curve and model. Step B5: Based on the future deployment area model and degradation curve established in step B4, and also based on the performance threshold, calculate the time required for the future deployment area to reach the failure threshold; Step B6: extract the fitting model and calculation results in steps B2 to B5, complete the fault prediction and remaining life prediction, and form a health status assessment report.
8. The intelligent health diagnosis and maintenance decision-making method for complex equipment according to claim 7, characterized in that: The intelligent maintenance decision-making based on the health assessment report includes: Step C1, extracting the health status of the complex equipment according to the health status assessment report, and constructing an extraction model based on the extraction factors; Step C2: Based on the items determined in step C1, an intelligent guarantee decision table is formed, and the order in the decision table is sorted according to the size of the sorting factor; Step C3: Based on the intelligent guarantee decision table and combined with the product maintenance and repair manuals, a specific maintenance implementation plan is formed; Step C4, completing intelligent maintenance judgment of this type of complex equipment; Step C5: After the maintenance and repair work is completed, the product information is updated and the health status assessment is completed again based on the test information to achieve real-time monitoring effect.
9. A computer-readable storage medium, characterized in that A computer program is stored thereon, and when the computer program is executed by one or more processors, the method according to any one of claims 5 to 8 is implemented.
10. An electronic device, characterized in that: include: one or more processors; A storage device having one or more programs stored thereon, which implements the method according to any one of claims 5 to 8 when the one or more programs are executed by the one or more processors.