Reliability evaluation method and device for ship iterative mechanical product, medium and product

Abstract

The invention discloses a reliability evaluation method and device for a ship iterative mechanical product, a medium and a product, and relates to the field of reliability evaluation of ship mechanical products, and the method comprises the steps: obtaining a historical degradation and failure data set of a similar product of a target product; the historical degradation and failure data set is preprocessed; obtaining a degradation trend model of the similar product based on the preprocessed historical degradation and failure data set; acquiring supplementary test data of the target product; based on the supplementary test data, improving the degradation trend model to obtain a target product degradation trend model; and performing reliability evaluation on the target product based on the target product degradation trend model to obtain a multi-dimensional reliability evaluation index of the target product. According to the invention, the reliability evaluation efficiency, accuracy and real-time performance of the ship mechanical product can be improved.

Description

Technical Field

[0001] This application relates to the field of reliability assessment of marine machinery products, and in particular to a reliability assessment method, equipment, medium and product for iterative marine machinery products. Background Technology

[0002] Marine machinery plays a crucial role in the modern shipbuilding industry. With rapid technological iteration and upgrades, marine machinery products often require localized improvements or optimized designs to meet higher performance requirements or adapt to new working environments. While such iterative improvements enhance product functionality, they also bring significant challenges in reliability assessment.

[0003] Currently, reliability assessments of marine machinery products largely rely on traditional methods that use thousands of hours of full-lifecycle testing data. These methods are ill-suited to the rapidly iterative demands of R&D, with a severe disconnect between testing cycles and product update speeds, resulting in assessment results that often lag behind actual design improvements. Current methods significantly underutilize historical data, leaving a large amount of valuable degradation information idle, while the lack of modeling for multi-factor coupling effects further reduces assessment accuracy. Especially for improved products, limited small sample data is insufficient to support reliability analysis using traditional statistical methods. This systemic deficiency not only increases R&D costs but may also mask potential failure risks of critical components. This gap between the assessment system and engineering practice is hindering the improvement of innovation efficiency in electromechanical products; therefore, there is an urgent need to establish a more intelligent and efficient new paradigm for reliability assessment. Summary of the Invention

[0004] The purpose of this application is to provide a reliability assessment method, equipment, medium, and product for iterative marine mechanical products. It addresses the technical challenges of traditional full-life reliability testing cycles leading to severe delays in assessment during the iterative improvement of electromechanical products, as well as the difficulty of existing methods in effectively utilizing historical data from similar products, accurately modeling multi-factor coupling effects, and accurately assessing the reliability of improved products under small-sample supplementary testing conditions. This application can improve the efficiency, accuracy, and real-time performance of reliability assessment for marine mechanical products.

[0005] To achieve the above objectives, this application provides the following solution: Firstly, this application provides a reliability assessment method for iterative ship machinery products, the reliability assessment method for iterative ship machinery products including: Obtain a historical degradation and failure dataset of similar products to the target product; the historical degradation and failure dataset includes: mechanical performance parameters, electrical performance parameters, and environmental response parameters; The historical degradation and failure dataset is preprocessed; the preprocessing includes data cleaning and state parameter correlation analysis. Based on the preprocessed historical degradation and failure dataset, a degradation trend model for similar products is obtained; Obtain supplementary test data for the target product; the supplementary test data is obtained through multi-stress synergistic accelerated degradation testing. Based on the supplementary test data, the degradation trend model is improved to obtain the target product degradation trend model; and based on the target product degradation trend model, the reliability of the target product is evaluated to obtain the multidimensional reliability evaluation index of the target product; the multidimensional reliability evaluation index includes mean time before failure, reliability function, failure probability density function and remaining service life distribution.

[0006] Optionally, the preprocessing of the historical degradation and failure dataset specifically includes: Based on the characteristic degradation curves of electromechanical products, invalid, abnormal, or missing data in historical degradation and failure datasets are eliminated. Based on the cleaned historical degradation and failure dataset, the Pearson correlation coefficient method was used to filter out data whose correlation with the system operating status was greater than a threshold.

[0007] Optionally, the degradation trend model of similar products specifically includes: a deep belief network feature extraction module, a degradation trajectory prediction module, a multi-factor coupling impact assessment module, and a Bayesian update fusion module; The deep belief network feature extraction module is used for nonlinear feature extraction; The degradation trajectory prediction module is a long short-term memory network with a forgetting gate used to capture the temporal evolution characteristics of the degradation process; The multi-factor coupling impact assessment module integrates an attention mechanism to dynamically adjust the weights of each state parameter in degradation prediction. The Bayesian update fusion module is used to fuse historical degradation and failure data using the Bayesian update algorithm to obtain a comprehensive degradation trend prediction result; the comprehensive degradation trend prediction result serves as a multidimensional reliability assessment index.

[0008] Optionally, the multi-stress synergistic accelerated degradation test includes mechanical stress, electrical stress, and environmental stress.

[0009] Optionally, the improvement of the degradation trend model based on the supplementary experimental data to obtain the target product degradation trend model specifically includes: Based on the supplementary experimental data, the degradation trend model was improved using transfer learning techniques; Construct a degradation prediction model based on the Wiener process; The parameters of the degradation prediction model are dynamically corrected using a Bayesian algorithm to obtain the degradation trend model of the target product, and the probability distribution of the remaining useful life is calculated.

[0010] Optionally, the construction of the degradation prediction model based on the Wiener process specifically includes: Using formula Determine the degradation prediction model based on the Wiener process ; in, and These are all drift coefficients, corresponding to the average degradation rates of the data-driven path and the mechanism-driven path, respectively. This is an equivalent runtime function constructed from historical degradation and failure data, used to characterize the cumulative effect of operating load and runtime. For the mechanism parameter vector of the iterative product, This is the equivalent stress cumulative function obtained based on the mechanism parameters. The diffusion coefficient of the Wiener process is used to characterize the intensity of random fluctuations during the degradation process. For This is a standard Brownian motion process on a time scale.

[0011] Secondly, this application provides a reliability assessment device for iterative ship machinery products, the reliability assessment device for iterative ship machinery products comprising: The dataset acquisition unit is used to acquire historical degradation and failure datasets of similar products to the target product; the historical degradation and failure datasets include: mechanical performance parameters, electrical performance parameters, and environmental response parameters; The preprocessing unit is used to preprocess the historical degradation and failure dataset; the preprocessing includes data cleaning and state parameter correlation analysis. The degradation trend model determination unit for similar products is used to obtain the degradation trend model of similar products based on the preprocessed historical degradation and failure dataset; A supplementary test data acquisition unit is used to acquire supplementary test data for the target product; the supplementary test data is obtained through multi-stress synergistic accelerated degradation testing. The reliability assessment unit is used to improve the degradation trend model based on the supplementary test data to obtain the target product degradation trend model; and to conduct a reliability assessment of the target product based on the target product degradation trend model to obtain a multi-dimensional reliability assessment index of the target product; the multi-dimensional reliability assessment index includes mean time before failure, reliability function, failure probability density function and remaining service life distribution.

[0012] Thirdly, this application provides a computer device, including: 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 aforementioned reliability assessment method for iterative marine machinery products.

[0013] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the aforementioned reliability assessment method for iterative marine machinery products.

[0014] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the aforementioned reliability assessment method for iterative marine machinery products.

[0015] According to the specific embodiments provided in this application, this application has the following technical effects: This application provides a reliability assessment method, equipment, medium, and product for iterative marine mechanical products. By integrating degradation and failure data from similar products (multiple generations), a precise prediction model considering multi-field coupling of mechanical, electrical, and environmental factors is established—a degradation trend model for the target product. This enables engineers to accurately identify potential weaknesses in design improvements. The rapid assessment feature of this application significantly shortens the verification cycle, allowing for simultaneous improvement in product iteration speed and reliability assurance, effectively avoiding design rework due to assessment delays. Furthermore, the dynamic assessment capability based on real-time monitoring data can provide early warnings of performance degradation trends in key components, offering a scientific basis for preventative maintenance. This significantly reduces unplanned downtime losses, improves overall equipment availability, and provides solid technical support for the innovative development of high-end equipment manufacturing. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a schematic diagram of a reliability assessment method for iterative ship machinery products according to one embodiment of this application; Figure 2 A schematic diagram of the degradation trend model structure for similar products; Figure 3 This is a schematic diagram of a reliability assessment device for iterative ship machinery products according to one embodiment of this application. Detailed Implementation

[0018] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0019] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0020] In one exemplary embodiment, such as Figure 2 As shown, a reliability assessment method for iterative ship machinery products is provided, comprising the following steps S101 to S105: Wherein: S101, Obtain historical degradation and failure datasets of similar products to the target product; the historical degradation and failure datasets include: mechanical performance parameters, electrical performance parameters, and environmental response parameters; the mechanical performance parameters, electrical performance parameters, and environmental response parameters constitute multi-dimensional monitoring data; Among them, the degradation and failure numbers of multivariate time series of similar products to the target product (preferably previous generation products and products with similar functional structures to the target product) are collected; the degradation and failure numbers cover mechanical performance parameters (vibration amplitude, modal frequency), electrical performance parameters (insulation resistance, partial discharge) and environmental response parameters (temperature rise curve, corrosion rate).

[0021] The historical degradation and failure datasets were divided into two parts: the training dataset was used to train a degradation trend prediction model for similar products; and the validation dataset was used to evaluate the generalization ability and final performance of the trained model.

[0022] S102, Preprocess the historical degradation and failure dataset; the preprocessing includes data cleaning and state parameter correlation analysis; S102 specifically includes: S21. Based on the characteristic degradation curves of electromechanical products (such as vibration energy accumulation trend and insulation resistance attenuation threshold), invalid, abnormal or missing data in historical degradation and failure data are removed. S22. Based on the historical degradation and failure dataset after data cleaning, the Pearson correlation coefficient method is used to filter out data whose correlation with the system operating status is greater than a threshold.

[0023] The Pearson correlation coefficient method was used to screen for strongly correlated parameters (|r|>0.6) and retain highly correlated parameters (|r|>0.8). The formula for calculating the Pearson correlation coefficient is as follows: ; Where X and Y represent random variables of any two state parameters (such as any two vibration indices, temperature indices, or electrical performance indices). For the common expectation of X and Y, Let X be the expectation. Let Y be the expected value. When the total values ​​of samples X and Y are both N, the formula for calculating the correlation coefficient between the total samples X and Y is as follows: ; in, The total number of samples, Yes Standard scores of the sample The standard deviation of the sample is 1. This is the sample average.

[0024] S103. Based on the preprocessed historical degradation and failure dataset, a degradation trend model for similar products is obtained. like Figure 2 As shown, the degradation trend model of similar products specifically includes: a deep belief network feature extraction module, a degradation trajectory prediction module, a multi-factor coupling impact assessment module, and a Bayesian update fusion module; The deep belief network feature extraction module is used for nonlinear feature extraction; the degradation trajectory prediction module is a long short-term memory network with a forgetting gate used to capture the temporal evolution features of the degradation process; the multi-factor coupling influence evaluation module integrates an attention mechanism to dynamically adjust the weights of each state parameter in degradation prediction; the Bayesian update fusion module uses a Bayesian update algorithm to fuse historical degradation and failure data to obtain a comprehensive degradation trend prediction result; the comprehensive degradation trend prediction result serves as a multi-dimensional reliability evaluation index.

[0025] The deep belief network feature extraction module constructs an initial degradation model framework for a deep belief network (DBN) consisting of an input layer, several hidden layers, and an output layer. The number of nodes in the input layer corresponds to the number of strongly correlated state parameters selected. The hidden layers are formed by stacking several restricted Boltzmann machines (RBMs) for nonlinear feature extraction of multidimensional state parameters. The output layer is used to output the degradation feature representation. Unsupervised pre-training is performed using a training dataset, and a layer-by-layer greedy algorithm is employed to optimize the network weights. Based on this, the output of the deep belief network is used as the input of an LSTM network with a forgetting gate to capture the temporal features of the degradation process, thus constructing a degradation trajectory prediction module. An attention mechanism is introduced between the output of the LSTM network and each state parameter to dynamically adjust the weight distribution of each state parameter, establishing a multi-factor coupled impact assessment module. The deep belief network feature extraction module, degradation trajectory prediction module, and multi-factor coupled impact assessment module are connected in sequence, and the Bayesian update algorithm in the Bayesian update fusion module is used to fuse multi-source monitoring data such as mechanical, electrical, and environmental data, ultimately forming a comprehensive degradation trend model.

[0026] S104, Obtain supplementary test data for the target product; the supplementary test data is obtained through multi-stress synergistic accelerated degradation testing. S104 specifically includes: Design a multi-stress synergistic accelerated degradation test to determine the key stress types and loading spectrum. The multi-stress synergistic accelerated degradation test covers mechanical stress (vibration frequency 0-2000Hz, acceleration 5-20g), electrical stress (voltage fluctuation ±15%, current surge 2-5 times the rated value), and environmental stress (temperature cycling -40℃~85℃, humidity 20%-95%RH).

[0027] A multi-sensor synchronous acquisition system was adopted to acquire mechanical performance parameters (vibration amplitude, modal frequency, damping coefficient), electrical performance parameters (insulation resistance, dielectric loss, partial discharge), and environmental response parameters (temperature rise curve, damp heat deformation, corrosion rate) at a sampling frequency of not less than 1 kHz. The mapping relationship between experimental data and historical data was established, and the data fusion weight was determined by similarity measurement. S105, based on the supplementary test data, the degradation trend model is improved to obtain the target product degradation trend model; and based on the target product degradation trend model, the reliability of the target product is evaluated to obtain the multidimensional reliability evaluation index of the target product; the multidimensional reliability evaluation index includes mean time before failure, reliability function, failure probability density function and remaining service life distribution.

[0028] S105 specifically includes: S51, Based on the supplementary experimental data, the degradation trend model is improved using transfer learning technology; the bottom feature extraction layer of the model is frozen, and the top regression prediction layer is fine-tuned; S52, Construct a degradation prediction model based on the Wiener process; S52 uses a Bayesian algorithm to dynamically correct the parameters of the degradation prediction model, obtains the degradation trend model of the target product, and calculates the probability distribution of the remaining useful life.

[0029] This application, while retaining the original transfer learning framework, innovatively integrates the design mechanism parameters of iterative products into the data-driven model, achieving collaborative optimization of physical mechanisms and data intelligence. The specific steps are divided into the following two parts.

[0030] 1. Parametric fusion of design mechanisms Key design improvement parameters for iterative products (such as material fatigue coefficient) Structural redundancy Electrical insulation enhancement index (etc.) are constructed into mechanistic feature vectors The existing data-driven model of similar products is injected into it in the following way: During the transfer learning fine-tuning phase, the data is injected into the model. Characteristics of monitoring data Concatenate as mixed input This significantly improves the model's ability to perceive design changes; the design mechanism-guided attention mechanism dynamically allocates weights. : ; in, The attention alignment matrix quantifies the correlation between data features and mechanistic features, and determines the weight allocation of each parameter in the decision-making process. This is a data feature transformation matrix, which transforms the original monitoring data. Mapping to a high-dimensional feature space, key patterns of the degradation process are extracted. A weight matrix is ​​used for the mechanism parameters to enable the model to focus on the degradation mode variation caused by design improvements.

[0031] 2. Bayesian dual-path correction Constructing a dual-source driven Wiener degradation process model: ; Among them, the drift coefficient Explicitly expressed as For example, insulation strengthening index With respect to the rate of electrolytic corrosion degradation Relationship, among which, and These are all drift coefficients, corresponding to the average degradation rates of the data-driven path and the mechanism-driven path, respectively. This is an equivalent runtime function constructed from historical degradation and failure data, used to characterize the cumulative effect of operating load and runtime. This is a vector of mechanistic parameters for iterative products (such as material fatigue coefficient, structural redundancy, electrical insulation strengthening index, etc.). This is the equivalent stress cumulative function obtained based on the mechanism parameters. The diffusion coefficient of the Wiener process is used to characterize the intensity of random fluctuations during the degradation process. For This is a standard Brownian motion process on a time scale.

[0032] Based on supplementary experimental data, a Bayesian hierarchical update algorithm was adopted: ; in, This is a parameter vector for the data path. This is a parameter vector representing the mechanistic path, used to achieve bidirectional correction between data and mechanisms. This is an observational dataset obtained based on supplementary experiments; In the given data Model parameters under conditions The posterior probability density, and These respectively represent the given data parameters Mechanism parameters Time observation data The likelihood function, For model parameters The prior probability density. The rapid reliability assessment method for iterative marine mechanical products provided in this application significantly improves the timeliness of reliability assessment by constructing a knowledge transfer mechanism that integrates degradation characteristics of similar products. This enables synchronous matching between the design iteration cycle and reliability verification, effectively solving the assessment lag problem caused by traditional full-life testing. This method achieves breakthrough accuracy assessment with limited supplementary test data, significantly reducing reliance on destructive testing and providing a scientific basis for rapid product iteration.

[0033] This application establishes a scientifically sound and comprehensive accelerated degradation test specification by combining it with multi-stress co-loading technology. This significantly reduces verification costs, and the Bayesian update mechanism enables dynamic correction of model parameters, giving the reliability assessment results of the improved product practical engineering value and providing a reliable basis for life prediction of key components.

[0034] The cross-generational product data fusion architecture provided in this application effectively solves the evaluation challenge under small sample conditions through the synergistic application of a similarity-weighted algorithm and a degradation feature knowledge graph. This method maximizes the potential value of historical data, significantly improves data utilization efficiency, and its constructed Monte Carlo uncertainty quantification system enhances the credibility of the evaluation results, providing an innovative solution for the reliability design of high-end equipment.

[0035] Based on the same inventive concept, this application also provides a reliability assessment device for ship-based iterative mechanical products, used to implement the aforementioned reliability assessment method for ship-based iterative mechanical products. The solution provided by this device is similar to the implementation described in the above method. Therefore, the specific limitations of one or more embodiments of the reliability assessment device for ship-based iterative mechanical products provided below can be found in the limitations of the reliability assessment method for ship-based iterative mechanical products described above, and will not be repeated here.

[0036] In one exemplary embodiment, such as Figure 3 As shown, a reliability assessment device for iterative marine mechanical products is provided, comprising: The dataset acquisition unit is used to acquire historical degradation and failure datasets of similar products to the target product; the historical degradation and failure datasets include: mechanical performance parameters, electrical performance parameters, and environmental response parameters; The preprocessing unit is used to preprocess the historical degradation and failure dataset; the preprocessing includes data cleaning and state parameter correlation analysis. The degradation trend model determination unit for similar products is used to obtain the degradation trend model of similar products based on the preprocessed historical degradation and failure dataset; A supplementary test data acquisition unit is used to acquire supplementary test data for the target product; the supplementary test data is obtained through multi-stress synergistic accelerated degradation testing. The reliability assessment unit is used to improve the degradation trend model based on the supplementary test data to obtain the target product degradation trend model; and to conduct a reliability assessment of the target product based on the target product degradation trend model to obtain a multi-dimensional reliability assessment index of the target product; the multi-dimensional reliability assessment index includes mean time before failure, reliability function, failure probability density function and remaining service life distribution.

[0037] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal. The computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is connected to the system bus via the I / O interfaces. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The I / O interfaces of the computer device are used for exchanging information between the processor and external devices. The communication interface of the computer device is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a reliability assessment method for iterative marine mechanical products.

[0038] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0039] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0040] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0041] 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, data stored, data displayed, 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 the relevant data must comply with relevant regulations.

[0042] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this 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 can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0043] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0044] In this application, all actions to acquire signals, information, or data are carried out in compliance with the relevant data protection laws and policies of the country where the location is situated, and with the authorization granted by the owner of the relevant device.

[0045] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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.

[0046] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A reliability assessment method for iterative ship machinery products, characterized in that, The reliability assessment method for ship-based iterative mechanical products includes: Obtain a historical degradation and failure dataset of similar products to the target product; the historical degradation and failure dataset includes: mechanical performance parameters, electrical performance parameters, and environmental response parameters; The historical degradation and failure dataset is preprocessed; the preprocessing includes data cleaning and state parameter correlation analysis. Based on the preprocessed historical degradation and failure dataset, a degradation trend model for similar products is obtained; Obtain supplementary test data for the target product; the supplementary test data is obtained through multi-stress synergistic accelerated degradation testing. Based on the supplementary test data, the degradation trend model is improved to obtain the target product degradation trend model; and based on the target product degradation trend model, the reliability of the target product is evaluated to obtain the multidimensional reliability evaluation index of the target product; the multidimensional reliability evaluation index includes mean time before failure, reliability function, failure probability density function and remaining service life distribution.

2. The reliability assessment method for iterative ship machinery products according to claim 1, characterized in that, The preprocessing of the historical degradation and failure dataset specifically includes: Based on the characteristic degradation curves of electromechanical products, invalid, abnormal, or missing data in historical degradation and failure datasets are eliminated. Based on the cleaned historical degradation and failure dataset, the Pearson correlation coefficient method was used to filter out data whose correlation with the system operating status was greater than a threshold.

3. The reliability assessment method for iterative ship machinery products according to claim 1, characterized in that, The degradation trend model for similar products specifically includes: a deep belief network feature extraction module, a degradation trajectory prediction module, a multi-factor coupling impact assessment module, and a Bayesian update fusion module; The deep belief network feature extraction module is used for nonlinear feature extraction; The degradation trajectory prediction module is a long short-term memory network with a forgetting gate used to capture the temporal evolution characteristics of the degradation process; The multi-factor coupling impact assessment module integrates an attention mechanism to dynamically adjust the weights of each state parameter in degradation prediction. The Bayesian update fusion module is used to fuse historical degradation and failure data using the Bayesian update algorithm to obtain a comprehensive degradation trend prediction result; the comprehensive degradation trend prediction result serves as a multidimensional reliability assessment index.

4. The reliability assessment method for iterative ship machinery products according to claim 1, characterized in that, The multi-stress synergistic accelerated degradation test includes mechanical stress, electrical stress, and environmental stress.

5. The reliability assessment method for iterative ship machinery products according to claim 1, characterized in that, The improvement of the degradation trend model based on the supplementary experimental data to obtain the target product degradation trend model specifically includes: Based on the supplementary experimental data, the degradation trend model was improved using transfer learning techniques; Construct a degradation prediction model based on the Wiener process; The parameters of the degradation prediction model are dynamically corrected using a Bayesian algorithm to obtain the degradation trend model of the target product, and the probability distribution of the remaining useful life is calculated.

6. The reliability assessment method for iterative ship machinery products according to claim 5, characterized in that, The construction of the degradation prediction model based on the Wiener process specifically includes: Using formula Determine the degradation prediction model based on the Wiener process ; in, and These are all drift coefficients, corresponding to the average degradation rates of the data-driven path and the mechanism-driven path, respectively. This is an equivalent runtime function constructed from historical degradation and failure data, used to characterize the cumulative effect of operating load and runtime. For the mechanism parameter vector of the iterative product, This is the equivalent stress cumulative function obtained based on the mechanism parameters. The diffusion coefficient of the Wiener process is used to characterize the intensity of random fluctuations during the degradation process. For This is a standard Brownian motion process on a time scale.

7. A reliability assessment device for iterative ship machinery products, characterized in that, The reliability assessment equipment for iterative ship mechanical products includes: The dataset acquisition unit is used to acquire historical degradation and failure datasets of similar products to the target product; the historical degradation and failure datasets include: mechanical performance parameters, electrical performance parameters, and environmental response parameters; The preprocessing unit is used to preprocess the historical degradation and failure dataset; the preprocessing includes data cleaning and state parameter correlation analysis. The degradation trend model determination unit for similar products is used to obtain the degradation trend model of similar products based on the preprocessed historical degradation and failure dataset; A supplementary test data acquisition unit is used to acquire supplementary test data for the target product; the supplementary test data is obtained through multi-stress synergistic accelerated degradation testing. The reliability assessment unit is used to improve the degradation trend model based on the supplementary test data to obtain the target product degradation trend model; and to conduct a reliability assessment of the target product based on the target product degradation trend model to obtain a multi-dimensional reliability assessment index of the target product; the multi-dimensional reliability assessment index includes mean time before failure, reliability function, failure probability density function and remaining service life distribution.

8. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the reliability assessment method for ship-based iterative mechanical products according to any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the reliability assessment method for iterative marine mechanical products as described in any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the reliability assessment method for iterative marine mechanical products as described in any one of claims 1-6.

Images