Naval vessel equipment task reliability quantitative prediction method, equipment, medium and product

Abstract

The invention discloses a ship equipment task reliability quantitative prediction method, equipment, a medium and a product, and relates to the field of ship equipment design and evaluation. The method comprises the following steps: constructing an equipment state matrix based on an equipment state model, constructing an equipment state and reliability combined matrix, and setting a corresponding equipment reliability block diagram for tasks in the combined matrix. Based on the block diagram, fault criteria are formulated for each task stage; determining a system state value based on the constructed joint matrix, constructing a Monte Carlo simulation framework, and obtaining a task reliability index based on a fault criterion and the system state value by adopting the framework; and constructing a task reliability optimal index intelligent selection model, and inputting the task reliability index into the model to obtain a task reliability prediction result. According to the method, the accuracy of quantitative analysis of the reliability of the ship equipment task can be remarkably improved, and solid data support is provided for maintenance and management of the ship equipment, so that the overall operation efficiency and safety of the ship are improved.

Description

Technical Field

[0001] The present application relates to the field of ship equipment design and evaluation, and in particular to a method, equipment, medium and product for quantitatively predicting the mission reliability of ship equipment. Background Art

[0002] Considering the complexity of ship systems, the diversity of equipment types, and the variability of task execution, it is difficult for traditional methods to construct a quantitative prediction model of ship equipment mission reliability that is consistent with the actual operating conditions. In a non-steady-state environment, the reliability data obtained by traditional methods usually deviate significantly from the actual situation. At present, quantitative prediction of reliability in a non-steady-state environment mainly relies on physical inspection and manual observation. This method is inefficient and difficult to process large-scale data. At the same time, the accuracy needs to be improved, and it is difficult to meet the reliability assessment needs of ship equipment in a complex and changing environment. Therefore, it is urgent to develop a more efficient and accurate reliability quantitative prediction method to significantly improve the accuracy and reliability of the predicted data. The new method needs to break through the limitations of traditional methods, fully adapt to the complexity of ship systems, the diversity of equipment types, and the variability of task execution, and provide solid technical support for the reliability assessment of ship equipment in a non-steady-state environment. Summary of the invention

[0003] The purpose of this application is to provide a method, equipment, medium and product for quantitative prediction of ship equipment mission reliability, which can significantly improve the accuracy of quantitative analysis of ship equipment mission reliability, and then provide solid data support for the maintenance and management of ship equipment, thereby improving the overall operational efficiency and safety of the ship.

[0004] To achieve the above objectives, this application provides the following solutions:

[0005] In a first aspect, the present application provides a method for quantitatively predicting the mission reliability of ship equipment, comprising:

[0006] Build equipment status model according to the working status of ship equipment in actual operation;

[0007] Constructing an equipment state matrix based on the equipment state model; the equipment state matrix is ​​used to reflect the working state of each ship equipment in each mission;

[0008] Based on the equipment status matrix, the reliability parameters and status information of the ship equipment are combined to construct a joint matrix of equipment status and reliability;

[0009] For each task in the equipment state and reliability joint matrix, setting an equipment reliability block diagram corresponding to the task;

[0010] Analyze the equipment reliability block diagram and formulate failure criteria for each mission stage of the mission profile;

[0011] Determine a system state value based on the device state and reliability joint matrix;

[0012] Constructing a Monte Carlo simulation framework based on the equipment status and reliability joint matrix;

[0013] Using the Monte Carlo simulation framework to obtain a task reliability index based on the fault criterion and the system state value;

[0014] Build an intelligent selection model for the best indicators of task reliability based on deep learning;

[0015] The mission reliability index is input into the mission reliability optimal index intelligent selection model to obtain a mission reliability prediction result.

[0016] Optionally, the equipment status model includes: connection and operation relationship between ship equipment and working status between ship equipment.

[0017] Optionally, each row in the equipment status and reliability joint matrix represents the working status of a single ship equipment in a multi-task environment; each column in the equipment status and reliability joint matrix represents the working status and reliability index of all ship equipment in a set mission.

[0018] Optionally, the reliability parameters of the ship equipment include equipment failure distribution function, maintenance distribution function, repair probability of maintenance personnel and equipment spare parts satisfaction rate.

[0019] Optionally, based on the equipment status matrix, the reliability parameters and status information of the ship equipment are combined to construct a joint matrix of equipment status and reliability, including:

[0020] Determine the complex association relationship between ship equipment based on the equipment state matrix; the complex association relationship between ship equipment includes a series relationship, a parallel relationship and a parallel dependency relationship;

[0021] Based on the complex correlation between ship equipment, the reliability parameters and status information of ship equipment are combined to construct a joint matrix of equipment status and reliability.

[0022] Optionally, the task reliability optimal indicator intelligent selection model includes a feature extraction module, an enhancement module, a fusion module and a classification module connected once.

[0023] Optionally, in the feature extraction module, a convolution layer is used in combination with multiple filter kernels to extract local features from the input data, a batch normalization layer is used to improve the stability of data distribution, and a linear rectification function activation layer is used to enhance the representation ability of the features;

[0024] In the feature enhancement module, a serial selective kernel network layer is used to receive and enhance the features output by the feature extraction module, and the receptive field is adaptively adjusted through the attention mechanism to achieve multi-scale feature enhancement;

[0025] In the feature fusion module, the features of multiple information domains output by the feature extraction module are horizontally fused through a splicing layer, and then the horizontally fused features are deeply fused using a convolution layer, a batch normalization layer, and a linear rectification function activation layer;

[0026] In the classification module, the global average pooling layer is used to calculate the average value of the feature matrix of each channel to generate a feature vector, which is then input into the normalized exponential function layer for classification.

[0027] In a second aspect, the present application provides a computer device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method for quantitatively predicting the mission reliability of ship equipment described in any one of the above.

[0028] In a third aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method for quantitatively predicting the mission reliability of ship equipment described in any one of the above.

[0029] In a fourth aspect, the present application provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of any of the above-mentioned methods for quantitatively predicting the mission reliability of ship equipment.

[0030] According to the specific embodiments provided in this application, this application has the following technical effects:

[0031] The present application provides a method, equipment, medium and product for quantitative prediction of mission reliability of ship equipment, and constructs a simulation framework (i.e., Monte Carlo simulation framework) based on the joint matrix of equipment status and reliability, which can significantly improve the comprehensiveness and accuracy of evaluation by integrating multi-source information. Then, by constructing an intelligent selection model for the best indicator of mission reliability, using deep learning technology to intelligently screen key indicators, accurately capturing equipment status changes, and more accurately reflecting the reliability status of equipment, it can not only significantly improve the accuracy of quantitative prediction of mission reliability of ship equipment, but also provide solid data support for the maintenance and management of ship equipment, thereby improving the overall operational efficiency and safety of the ship, and providing strong guarantees for the safe navigation and combat capability of the ship. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0033] Figure 1 A flowchart of a method for quantitatively predicting mission reliability of ship equipment provided in one embodiment of the present application;

[0034] Figure 2 A flow chart of a quantitative prediction model for mission reliability of ship equipment provided in an embodiment of the present application;

[0035] Figure 3 A device reliability block diagram provided for an embodiment of the present application;

[0036] Figure 4 A diagram of a device collaboration workflow provided in an embodiment of the present application;

[0037] Figure 5 A simulation framework diagram based on a joint matrix of device status and reliability provided in an embodiment of the present application;

[0038] Figure 6 A flowchart for selecting the best indicator for task reliability based on deep learning provided in one embodiment of the present application;

[0039] Figure 7 A schematic diagram of the structure of a deep learning module provided in one embodiment of the present application;

[0040] Figure 8 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0042] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0043] In an exemplary embodiment, Figure 1As shown, a method for quantitatively predicting the reliability of ship equipment missions is provided. The method is executed by a computer device, and can be executed by a computer device such as a terminal or a server alone, or by a terminal and a server together. In the embodiment of the present application, the method is applied to a server as an example for explanation, and includes the following steps 100 to 109. Among them:

[0044] Step 100: Construct an equipment status model according to the working status of the ship equipment in actual operation.

[0045] The equipment status model deeply analyzes the division of the ship's mission phases, and elaborates on the collaborative workflow and interaction mechanism between the various ship equipment (hereinafter referred to as equipment) in each mission phase. This equipment status model closely fits the actual mission profile of the ship, and through precise data analysis and simulation, it shows the specific working status of each ship equipment in different mission phases. Among them, the specific working status includes but is not limited to the performance and interaction relationship of the equipment in each phase such as startup, operation, standby and shutdown. The establishment of this equipment status model helps researchers to fully and deeply understand the operating status of ship equipment and provide a scientific basis for optimizing the ship's combat effectiveness. At the same time, through the prediction and analysis of equipment failure modes, the equipment status model can also provide strong technical support for fault prevention and rapid response, ensuring that the ship can maintain the best working state and the highest combat effectiveness when performing tasks.

[0046] Step 101: construct a device state matrix based on the device state model.

[0047] The construction of this equipment state matrix aims to provide a comprehensive and detailed perspective to reflect the specific working status of each device in task i. The construction logic of the equipment state matrix is ​​rigorous. Each row accurately records the working details of a single device in a multi-task environment and shows the performance of the equipment between different tasks. At the same time, each column focuses on a specific task i and summarizes the operating status of all equipment on the ship in the task, thereby achieving a comprehensive grasp of the performance of the equipment group. By constructing this equipment state matrix, we can more accurately understand the state changes of the equipment in actual operation, and provide strong data support for the optimization management, fault prediction and performance improvement of the equipment. This achievement not only helps to improve the operating efficiency of the ship, but also lays a solid foundation for the development of future equipment status monitoring technology. In the process of constructing the equipment state matrix, special emphasis is placed on the fixedness and uniqueness of its form to ensure that the matrix expression for a specific task is consistent and accurate. This design principle ensures the uniqueness of the equipment state matrix under a specific task, thereby accurately reflecting the working status and state mode of each ship equipment under a specific task profile. This certainty is crucial to the analysis process. It effectively avoids confusion and errors and ensures that each simulation and prediction is based on the same and accurate state matrix. Through this rigorous design, the relationship between equipment status and reliability can be analyzed more accurately, providing solid data support for the ship's combat effectiveness evaluation and maintenance decisions.

[0048] Step 102: Based on the equipment status matrix, the reliability parameters and status information of the ship equipment are combined to construct a joint matrix of equipment status and reliability.

[0049] In this step, after an in-depth analysis of the general quality parameters of the equipment, the reliability parameters of the equipment are combined with the status information to construct a joint matrix of equipment status and reliability. The construction of the joint matrix of equipment status and reliability takes into account the basic reliability characteristics of the equipment, while fully incorporating the maintenance and support capabilities of the equipment, thus providing a more comprehensive and accurate equipment performance evaluation framework. The joint matrix of equipment status and reliability continues the clarity and intuitiveness of the status matrix in form. Each row still represents the working status of a single device in a multi-task environment, while each column is further expanded to show the working status and reliability indicators of all equipment in a specific task. This enables researchers to more accurately evaluate the performance of equipment in actual tasks, which not only provides data support for the improvement of ship combat effectiveness, but also lays a solid foundation for fault prevention, system optimization and decision analysis.

[0050] Among them, the reliability parameters of ship equipment are obtained based on the equipment reliability parameter model, which includes multiple core elements, such as equipment failure distribution function, maintenance distribution function, repair probability of maintenance personnel, and equipment spare parts satisfaction rate, etc. These core elements jointly describe the reliability performance of equipment in a complex working environment.

[0051] Step 103: For each task in the equipment status and reliability joint matrix, set the equipment reliability block diagram corresponding to the task.

[0052] These equipment reliability diagrams not only accurately reflect the reliability status of the ship when performing the corresponding tasks, but also directly serve as the key basis for evaluating the reliability of the ship during the mission stage. In the process of constructing the joint matrix of status and reliability, the complex associations between equipment can also be fully considered. Among them, the complex associations between equipment include but are not limited to series relationships, parallel relationships, and parallel dependencies. Through the in-depth analysis and application of these complex associations, the reliability performance of ship equipment can be described and analyzed more carefully and accurately within the framework of the joint matrix of status and reliability.

[0053] In this step, combining the equipment reliability block diagram, equipment status and reliability joint matrix can realize the effective identification and judgment of ship equipment failures in different mission stages of the mission profile, which not only helps to improve the combat effectiveness of ships in complex mission environments, but also provides scientific and reasonable decision-making support for ship maintenance, management and fault prevention.

[0054] Step 104: Analyze the equipment reliability block diagram and formulate failure criteria for each mission stage of the mission profile.

[0055] Step 105: Determine the system state value based on the device state and reliability joint matrix.

[0056] Step 106: Construct a Monte Carlo simulation framework based on the joint matrix of equipment status and reliability. By constructing the Monte Carlo simulation framework, detailed analysis and accurate prediction of equipment reliability can be achieved.

[0057] Step 107: Using a Monte Carlo simulation framework to obtain a task reliability index based on fault criteria and system status values.

[0058] After the Monte Carlo simulation framework is constructed in step 106, the single task and number of simulations are strictly determined according to the accuracy requirements to ensure the accuracy and reliability of the obtained results. In the simulation process, a variety of key factors are fully considered, including the probability of equipment failure, the maintainability of the failure, and the satisfaction of spare parts for the failure. These key factors have a vital impact on the reliability of ship equipment, so they are included in the simulation framework for comprehensive and detailed consideration. Reliability prediction simulation is carried out based on the Monte Carlo simulation framework. This Monte Carlo simulation framework closely combines the status information of the equipment with the reliability parameters, which can more realistically reflect the performance of the equipment in actual operation. Through simulation, the reliability prediction results of the equipment in different mission stages and different working conditions are obtained. These simulation results not only provide strong support for the evaluation of the combat effectiveness of the ship, but also provide an important basis for the maintenance decision of the ship. Through in-depth analysis of these results, the reliability performance of the equipment in actual operation can be more accurately understood, so as to formulate more scientific and reasonable maintenance and management strategies to ensure the efficient and stable operation of the ship.

[0059] Step 108: Construct an intelligent selection model for the best task reliability indicator based on deep learning. This step aims to achieve the best intelligent selection of reliability indicators to ensure the accuracy of the selection and reduce the data volume requirement.

[0060] Step 109: Input the task reliability index into the task reliability optimal index intelligent selection model to obtain the task reliability prediction result.

[0061] The input of the task reliability best indicator intelligent selection model (referred to as the model) is a combination of reliability indicators. Through a series of modules such as feature extraction module, enhancement module, fusion module and classification module, the diagnostic accuracy (i.e., task reliability prediction result) is finally obtained, thereby intelligently screening out key reliability indicators. Among them, different reliability indicators have different effects on evaluating whether a device has failed, which will also lead to different diagnostic effects. In order to obtain the most accurate diagnostic accuracy, it is necessary to screen out the most representative ones from multiple reliability indicators.

[0062] The structure of each module is as follows Figure 7As shown in the figure. In the feature extraction module, the convolution layer is combined with multiple filter kernels to extract local features from the input data, the batch normalization layer is used to improve the stability of data distribution, and the linear rectification function activation layer is used to further enhance the representation ability of the features. The feature enhancement module uses a serial selective kernel network layer to receive and enhance the features output by the feature extraction module, and adaptively adjusts the receptive field through the attention mechanism to achieve multi-scale feature enhancement, reduce redundant features, and improve information utilization efficiency. The feature fusion module horizontally fuses the features of multiple information domains through the splicing layer, and then uses the convolution layer, batch normalization layer and linear rectification function activation layer for deep fusion to make full use of the complementary information of different information domains and enhance the model's ability to understand data. In the classification module, the global average pooling layer is used to replace the traditional fully connected layer. The feature vector is generated by calculating the average value of each channel feature matrix and directly input into the normalized exponential function layer for classification. This structure not only retains the key features, but also enhances the generalization ability of the model, which helps to understand how the model extracts key features from the input data and realizes fault diagnosis. Overall, this model achieves the best intelligent selection of reliability indicators through accurate data transmission and efficient processing flow, providing strong support for fault diagnosis.

[0063] In an exemplary embodiment of the present application, the device state model includes two parts: the first part determines the connection and operation relationship between the various devices in the whole, such as series operation, parallel operation, etc. (such as Figure 3 The second part determines the specific status of each device in the process of achieving a certain task (such as Figure 4 After the task starts, if any route can reach the end, the task is considered to be successfully completed.

[0064] Based on the above description, this application aims to quantify and estimate the reliability data of ship equipment, provide reliable data support for the maintenance and management of ship equipment, and thus improve the overall operational efficiency and safety of the ship.

[0065] In an exemplary embodiment of the present application, the equipment failure distribution function is expressed as f(x):

[0066] f(x)=λe -λx . Where λ is the failure rate parameter and x is the device state.

[0067] The maintenance distribution function is expressed as G(T):

[0068] G(T)=1-e -λT . Where T is the maintenance time.

[0069] The repair probability of the maintenance personnel is expressed as P r (t):

[0070] Where t is the total repair time, N r is the number of successful repairs, N t is the total number of repairs.

[0071] The equipment spare parts satisfaction rate is expressed as S:

[0072] Among them, n h is the number of equipment spare parts that can actually be provided, n t It is the actual number of equipment spare parts required.

[0073] In an exemplary embodiment of the present application, the implementation process of the above step 102 can be described as follows:

[0074] The complex associations between ship equipment are determined based on the equipment status matrix. The complex associations between ship equipment include series, parallel and parallel dependency.

[0075] Based on the complex correlation between ship equipment, the reliability parameters and status information of ship equipment are combined to construct a joint matrix of equipment status and reliability.

[0076] In another exemplary embodiment of the present application, 10 equipment and 5 tasks of a ship are used as examples to demonstrate how to establish a detailed equipment status model. It should be emphasized that the examples given are only illustrative. In actual applications, the model building process should be flexibly adjusted and optimized according to the specific conditions of the ship, including but not limited to the type and quantity of equipment and the specific content and requirements of the tasks. In this embodiment, the constructed ship equipment task reliability quantitative prediction model is as follows: Figure 2 Based on this model, the quantitative prediction method for ship equipment mission reliability provided in this application includes:

[0077] Step 1: Based on the working status of the ship's equipment in actual operation for various tasks, an accurate equipment status model is constructed. This model describes in detail how the various equipment works together to achieve optimal efficiency when the ship performs a specific task. Figure 4 It intuitively demonstrates the collaborative working status of various equipment under different tasks, providing a strong theoretical basis for the efficient operation of ships and equipment management.

[0078] Step 2: Based on the device status model, a device status matrix is ​​constructed. The construction of this matrix strictly follows the logical relationship between tasks and device status. Each row accurately reflects the working status of a single device in a specific task, and each column comprehensively displays the working status of all devices in the same task. Each element in the matrix is ​​accurately assigned a value through the device status function S(i). Specifically, when the device needs to work in task i, the status function S(i) is assigned a value of 1. If the device does not need to work in task i, the status function S(i) is assigned a value of -1. When the device fails in task i, the status function S(i) is assigned a value of 0. Based on this, the status function can be expressed as:

[0079]

[0080] According to the above definition, the equipment state matrix can be obtained. The construction of this matrix strictly follows the mapping relationship between tasks and equipment states. For a specific fixed task, the behavior state matrix of the whole ship system equipment should be unique to ensure the consistency between the task and the equipment state. Figure 3 As shown in Figure 1, when the task is determined, the working state of each device should also be fixed, which reflects the stability and reliability of the device state matrix. The device state matrix can be expressed as ES ( 10,5 ):

[0081] in, Tj (j=1,2,...,5),E i (i=1,2,...,10) and S both represent device state matrix elements.

[0082] Step 3: In-depth analysis of equipment failure distribution function and maintenance distribution function, combined with key quality parameters such as equipment crew-level repair probability and equipment spare parts satisfaction rate, accurately construct the equipment status and reliability joint matrix. The equipment status and reliability joint matrix can be expressed as J(i):

[0083]

[0084] Step 4: Based on the detailed analysis of the equipment reliability block diagram and the collaborative workflow, clear fault criteria are defined for different mission stages. When starting mission i, if the ship equipment can maintain a healthy operating state, it is determined that no related faults have occurred. However, if the ship equipment fails to maintain a healthy working state after starting mission i, it can be determined that the equipment E related to mission i i In this case, refer to Figure 3 and Figure 4The information shown is used to find the most suitable replacement equipment, and further diagnose the specific location of the equipment failure and evaluate its maintainability. If the equipment failure is repairable, the repair operation will be carried out immediately, and the entire repair process and results will be recorded in detail to ensure the smooth progress of subsequent work. The replacement relationship is as follows:

[0085]

[0086] Step 5: Based on the joint matrix of equipment status and reliability, build a Monte Carlo simulation framework. The specific process is as follows:

[0087] First, a probabilistic statistical model is constructed, which will serve as the basis for simulation analysis. Next, data of each variable involved in the model is collected, and the probability distribution function of the objective function is determined based on these data. Then, the number of simulations is determined based on the accuracy requirements of the objective function. In order to ensure the randomness of the simulation, a method for extracting random variables needs to be established, which will be used to generate the required number of random times. Next, the core of the simulation is entered. It is determined whether N sample values ​​that meet the conditions have been generated. If the number of samples has reached the requirement, these sample values ​​will be statistically analyzed to estimate key indicators such as their mean and standard deviation. However, if the number of samples has not reached N, the simulation will continue. Specifically, random samples will be taken from the probability distribution of each variable, and these sampled values ​​will be substituted into the previously established mathematical model. This process is repeated until the required number of samples is met. The entire process constitutes the basic framework of Monte Carlo simulation, which allows the solution of complex problems or the performance of specific systems to be estimated through simulation and statistical analysis of random variables. When setting the number of simulations, we strictly follow the accuracy requirements and take into account general quality characteristics such as equipment failure, maintainability of failure, and availability of spare parts. Using this framework, we conduct accurate reliability prediction simulations. The simulation process is as follows: Figure 5 During the whole simulation process, multiple simulations were conducted for the five tasks, and finally the reliability indicators of each task were collected to ensure the integrity and accuracy of the data.

[0088] The Monte Carlo method can be used to evaluate the reliability of equipment. During the construction process, when the equipment transitions between different states, this state transition process can be represented by establishing a joint matrix of equipment state and reliability.

[0089] Step 6: Build an intelligent selection model for the best task reliability index based on deep learning technology. This model takes multiple combinations of reliability indicators as input and processes them through a series of carefully designed modules (see the description of each module above). Reliability indicators include vibration information, current, voltage, etc. of the equipment. Figure 6 As shown, the specific process is as follows:

[0090] First, the input task reliability indicators IN1, IN2, IN3 to INn are received, which will provide basic data for subsequent analysis. Then, the feature extraction module is used to accurately extract the key features in the task reliability indicators. Subsequently, the feature enhancement module will further enhance these features to ensure the effective transmission of key information. Then, in the feature fusion module, multiple feature matrices are selectively fused. This step aims to integrate the information in different feature matrices to form a more comprehensive and accurate feature representation. Finally, through the classification module, the equipment fault is diagnosed based on the fused features, and the diagnosis accuracy is calculated. After this series of processing, the model finally outputs the diagnosis accuracy, thereby intelligently screening out key reliability indicators. This innovative model provides strong support for the accurate evaluation of task reliability.

[0091] Based on the above description, this application first constructs a simulation framework based on the joint matrix of equipment status and reliability, which significantly improves the comprehensiveness and accuracy of the evaluation by fusing multi-source information. Then, a deep learning-based task reliability optimal indicator selection model is introduced, which uses deep learning technology to intelligently screen key indicators and accurately capture equipment status changes, thereby more accurately reflecting the reliability status of the equipment. The implementation of this application not only significantly improves the accuracy of quantitative prediction of ship equipment mission reliability, but also provides solid data support for the maintenance and management of ship equipment. Through the application of this application, the overall operational efficiency and safety of the ship will be effectively improved, providing a strong guarantee for the safe navigation of the ship and the performance of its combat capability.

[0092] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 8 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store quantitative prediction processing data of ship equipment mission reliability. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a quantitative prediction method for ship equipment mission reliability is implemented.

[0093] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components. In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0094] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0095] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0096] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0097] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0098] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0099] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0100] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A quantitative prediction method for mission reliability of ship equipment, characterized in that: The quantitative prediction method for mission reliability of ship equipment includes: Build equipment status model according to the working status of ship equipment in actual operation; Constructing an equipment state matrix based on the equipment state model; the equipment state matrix is ​​used to reflect the working state of each ship equipment in each mission; Based on the equipment status matrix, the reliability parameters and status information of the ship equipment are combined to construct a joint matrix of equipment status and reliability; For each task in the equipment state and reliability joint matrix, setting an equipment reliability block diagram corresponding to the task; Analyze the equipment reliability block diagram and formulate failure criteria for each mission stage of the mission profile; Determine a system state value based on the device state and reliability joint matrix; Constructing a Monte Carlo simulation framework based on the equipment status and reliability joint matrix; Using the Monte Carlo simulation framework to obtain a task reliability index based on the fault criterion and the system state value; Build an intelligent selection model for the best indicators of task reliability based on deep learning; The mission reliability index is input into the mission reliability optimal index intelligent selection model to obtain a mission reliability prediction result.

2. The method for quantitatively predicting the mission reliability of ship equipment according to claim 1 is characterized in that: The equipment status model includes: the connection and operation relationship between ship equipment and the working status between ship equipment.

3. The method for quantitatively predicting the mission reliability of ship equipment according to claim 1 is characterized in that: Each row in the equipment status and reliability joint matrix represents the working status of a single ship equipment in a multi-task environment; each column in the equipment status and reliability joint matrix represents the working status and reliability index of all ship equipment in a set task.

4. The method for quantitatively predicting the mission reliability of ship equipment according to claim 1 is characterized in that: The reliability parameters of the ship equipment include equipment failure distribution function, maintenance distribution function, repair probability of maintenance personnel and equipment spare parts satisfaction rate.

5. The method for quantitatively predicting the reliability of ship equipment mission according to claim 1 is characterized in that: Based on the equipment status matrix, the reliability parameters and status information of the ship equipment are combined to construct a joint matrix of equipment status and reliability, including: Determine the complex association relationship between ship equipment based on the equipment state matrix; the complex association relationship between ship equipment includes a series relationship, a parallel relationship and a parallel dependency relationship; Based on the complex correlation between ship equipment, the reliability parameters and status information of ship equipment are combined to construct a joint matrix of equipment status and reliability.

6. The method for quantitatively predicting the mission reliability of ship equipment according to claim 1 is characterized in that: The optimal task reliability indicator intelligent selection model includes a feature extraction module, an enhancement module, a fusion module and a classification module that are connected once.

7. The method for quantitatively predicting the mission reliability of ship equipment according to claim 6 is characterized in that: In the feature extraction module, a convolutional layer is used in combination with multiple filter kernels to extract local features from input data, a batch normalization layer is used to improve data distribution stability, and a linear rectification function activation layer is used to enhance the representation capability of features; In the feature enhancement module, a serial selective kernel network layer is used to receive and enhance the features output by the feature extraction module, and the receptive field is adaptively adjusted through the attention mechanism to achieve multi-scale feature enhancement; In the feature fusion module, the features of multiple information domains output by the feature extraction module are horizontally fused through a splicing layer, and then the horizontally fused features are deeply fused using a convolution layer, a batch normalization layer, and a linear rectification function activation layer; In the classification module, the global average pooling layer is used to calculate the average value of the feature matrix of each channel to generate a feature vector, which is then input into the normalized exponential function layer for classification.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for quantitatively predicting the mission reliability of ship equipment according to any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for quantitatively predicting the mission reliability of ship equipment described in any one of claims 1 to 7 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for quantitatively predicting the mission reliability of ship equipment described in any one of claims 1 to 7 is implemented.

Images