Ship system state evaluation method and device based on evidence correlation and timeliness

Abstract

The application belongs to the technical field of ship state evaluation, and specifically discloses a ship system state evaluation method and device based on evidence correlation and timeliness, which comprises the following steps: selecting a plurality of information sources related to the ship system as evidence bodies, and constructing a basic probability assignment function of each evidence body under each state of the ship system; calculating the Pearson correlation coefficients between the evidence bodies, and calculating the first credibility corresponding to each evidence body based on the Pearson correlation coefficients; calculating the second credibility corresponding to each evidence body based on the generation time of the information of each evidence body and the preset information half-life; performing weighted correction on the basic probability assignment function of each evidence body under each state of the ship system based on the first credibility and the second credibility, and obtaining the corrected evidence body; and fusing the corrected evidence body by using the Dempster combination rule to obtain an evaluation result. The method can improve the accuracy of ship system state evaluation.

Description

Technical Field

[0001] This application belongs to the field of ship condition assessment technology, and more specifically, relates to a ship system condition assessment method and apparatus based on evidence relevance and timeliness. Background Technology

[0002] Modern naval systems are evolving towards high performance, multifunctionality, and high structural integration, resulting in a complex array of internal equipment and numerous, technologically advanced auxiliary systems. Based on system function, naval systems can be categorized into propulsion systems, steering systems, electrical systems, and navigation systems, among others. Furthermore, the marine environment in which ships perform missions is complex and ever-changing, with highly dynamic operating conditions. Therefore, achieving accurate and dynamic assessment of the service status of naval systems is crucial for ensuring navigational safety, enhancing combat effectiveness, optimizing resource allocation, and supporting refined management throughout the entire lifecycle. Specifically, effective naval system service status assessment provides timely and reliable status information for operational command, guides crew members in implementing scientific equipment operation and maintenance procedures, enables precise and on-demand allocation of support resources, and ultimately establishes a closed-loop management mechanism throughout the entire service life of the ship.

[0003] For comprehensive status assessment of ship systems, existing technologies can be mainly categorized into three types: index weight aggregation methods (such as weighted synthesis and analytic hierarchy process), uncertainty information processing methods (such as grey system evaluation and fuzzy comprehensive evaluation), and data-driven intelligent modeling methods (artificial neural networks, etc.). However, facing the increasing system complexity and dynamic operational requirements of modern ships, the above-mentioned existing assessment methods generally have the following limitations: 1. Insufficient information completeness: Single-source data (such as equipment sensor data and maintenance records) often have missing parts or low accuracy. 2. Failure to consider information real-time performance: System information data has real-time and non-real-time differences, and traditional methods do not consider the changes in information reliability over time. 3. Difficulty in handling conflicts between multi-source data: Data from different sources may be contradictory; for example, detection data may be normal, but the assessment results of technicians may be abnormal. This leads to low accuracy in ship system status assessment. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this application aims to provide a ship system status assessment method and apparatus based on evidence relevance and timeliness, thereby solving the problems of low accuracy in ship system status assessment caused by insufficient information completeness, failure to consider information real-time performance, and difficulty in handling conflicts between multiple data sources in existing assessment methods.

[0005] To achieve the above objectives, in a first aspect, this application provides a ship system status assessment method based on the relevance and timeliness of evidence, including: Multiple information sources related to the ship system are selected as evidence, and a basic probability allocation function for each evidence in each state of the ship system is constructed. Calculate the Pearson correlation coefficient between each piece of evidence, and calculate the first confidence level corresponding to each piece of evidence based on the Pearson correlation coefficient; Calculate the second credibility of each piece of evidence based on the generation time and preset information half-life of each piece of evidence. Based on the first credibility and the second credibility, the basic probability allocation function of each piece of evidence in each state of the ship system is weighted and modified to obtain the modified piece of evidence; The modified evidence body was fused using Dempster's combination rule to obtain the evaluation results.

[0006] This application achieves multi-source information fusion assessment by selecting multiple information sources as evidence and constructing a basic probability allocation function, thus improving the problem of insufficient information integrity of single-source data. By quantifying the correlation between each piece of evidence based on the Pearson correlation coefficient and calculating the first credibility accordingly, the credibility of the data source can be adjusted based on information consistency, reasonably avoiding the problem of multi-source information conflict. By introducing the concept of information half-life, the second credibility is calculated based on the generation time of the evidence information, taking into account the change of information credibility over time, making the assessment results more consistent with the actual characteristics of information timeliness. Finally, after weighting and correcting the basic probability allocation function based on the first and second credibility, the Dempster combination rule is used for fusion, so that evidence with high relevance and strong timeliness receives higher weight in the fusion, thereby achieving a more comprehensive, objective, real-time and accurate assessment of the service status of ship systems and improving the accuracy of ship system status assessment.

[0007] According to the ship system status assessment method based on evidence relevance and timeliness provided in this application, the selection of multiple information sources related to the ship system as evidence includes: The status of critical equipment clusters on ships, the status of pre-departure inspections, and the status of graded maintenance were selected as evidence.

[0008] This application selects three information sources as evidence: the status of critical equipment clusters on the ship, the status of pre-departure inspections, and the status of graded maintenance. It constructs a complete evaluation index system from three dimensions: equipment operating parameters, preventive maintenance records, and planned maintenance files. This ensures that the selected evidence has a significant functional correlation with the ship system evaluation objectives, effectively reflects the real-time operating status of the ship system, and guarantees the systematic and comprehensive nature of the evaluation information sources.

[0009] According to the ship system status assessment method based on evidence relevance and timeliness provided in this application, the method further includes: The original data of each piece of evidence were cleaned and standardized.

[0010] This application cleans and standardizes the raw data of each evidence body, which can eliminate the interference of missing values, outliers, and inconsistent dimensions in the raw data on subsequent evaluation calculations, ensuring the quality of data entering the evidence fusion process, thereby improving the accuracy and reliability of subsequent Pearson correlation coefficient calculation and basic probability assignment function construction.

[0011] According to the ship system status assessment method based on evidence relevance and timeliness provided in this application, the calculation of the Pearson correlation coefficient between each piece of evidence, and the calculation of the first credibility corresponding to each piece of evidence based on the Pearson correlation coefficient, includes: Calculate the Pearson correlation coefficient between each pair of evidence bodies; Based on the Pearson correlation coefficient between each pair of evidence, the support level of each evidence is calculated. Divide the support of each piece of evidence by the sum of the support of all pieces of evidence to obtain the first credibility of each piece of evidence.

[0012] This application calculates the Pearson correlation coefficient between each pair of pieces of evidence and uses this coefficient to calculate the support level of each piece of evidence. The result is then normalized to obtain the first credibility level, thus achieving a quantitative description of the consistency between the pieces of evidence. Evidence with high support levels indicates high consistency with other pieces of evidence and is therefore assigned higher credibility. This effectively suppresses the adverse effects of highly conflicting evidence on the evaluation results during the fusion process, improving the accuracy of evidence combination.

[0013] According to the ship system status assessment method based on evidence relevance and timeliness provided in this application, the calculation of the second credibility corresponding to each piece of evidence based on the generation time and preset information half-life of each piece of evidence includes: The decay factor is calculated based on the preset information half-life of each piece of evidence. Calculate the timeliness weight based on the decay factor, the current time, and the time when the evidence information was generated; Divide the statute of limitations weight of each piece of evidence by the sum of the statute of limitations weights of all pieces of evidence to obtain the second credibility of each piece of evidence.

[0014] This application calculates a decay factor based on the information's half-life and combines the current time with the time the evidence was generated to calculate a timeliness weight. This is then normalized to obtain a second credibility level, resulting in higher credibility for newly generated evidence, while its credibility gradually decays over time. This scheme introduces a quantitative description of information from its creation to decay, enabling the evaluation process to dynamically reflect the real-time differences between different pieces of evidence, and making the evaluation results closer to the current actual state of the system.

[0015] According to the ship system state assessment method based on evidence relevance and timeliness provided in this application, the basic probability allocation function of each piece of evidence in each state of the ship system is weighted and corrected based on the first credibility and the second credibility to obtain the corrected piece of evidence, including: Based on the first credibility and the second credibility, the final credibility of each piece of evidence is determined; The final credibility is normalized to obtain the weight coefficient of each piece of evidence; The basic probability allocation function of each piece of evidence under each state of the ship system is weighted and modified based on the weight coefficient of each piece of evidence to obtain the modified piece of evidence.

[0016] This application determines the final credibility by combining the first and second credibility levels, then normalizes the results to obtain weighting coefficients. These weighting coefficients are then used to weight and correct the basic probability allocation function, organically integrating the credibility of the two dimensions of information relevance and timeliness into a unified weighted index. This weighted correction mechanism ensures that highly relevant and timely evidence plays a dominant role in the final Dempster fusion, directly embedding conflict avoidance and timeliness correction into the core process of evidence fusion, thereby improving the rationality and accuracy of the final evaluation results.

[0017] Secondly, this application provides a ship system status assessment device based on evidence relevance and timeliness, comprising: The module is used to select multiple information sources related to the ship system as evidence bodies and construct the basic probability allocation function of each evidence body in each state of the ship system. The first calculation module is used to calculate the Pearson correlation coefficient between each piece of evidence, and to calculate the first credibility of each piece of evidence based on the Pearson correlation coefficient. The second calculation module is used to calculate the second credibility of each piece of evidence based on the generation time and preset information half-life of each piece of evidence. The correction module is used to perform a weighted correction on the basic probability allocation function of each piece of evidence in each state of the ship system based on the first credibility and the second credibility, so as to obtain the corrected piece of evidence. The evaluation module is used to fuse the modified evidence body using Dempster's combination rules to obtain the evaluation results.

[0018] Thirdly, this application provides an electronic device, comprising: at least one memory for storing a program; and at least one processor for executing the program stored in the memory. When the program stored in the memory is executed, the processor is used to execute the ship system status assessment method based on evidence relevance and timeliness described in the first aspect or any possible implementation of the first aspect.

[0019] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when run on a processor, causes the processor to execute the ship system status assessment method based on evidence relevance and timeliness described in the first aspect or any possible implementation of the first aspect.

[0020] Fifthly, this application provides a computer program product that, when run on a processor, causes the processor to execute the ship system status assessment method based on evidence relevance and timeliness described in the first aspect or any possible implementation of the first aspect.

[0021] It is understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here.

[0022] Overall, the technical solutions conceived in this application have the following advantages compared with the prior art: This application achieves multi-source information fusion assessment by selecting multiple information sources as evidence and constructing a basic probability allocation function, thus improving the problem of insufficient information integrity of single-source data. By quantifying the correlation between each piece of evidence based on the Pearson correlation coefficient and calculating the first credibility accordingly, the credibility of the data source can be adjusted based on information consistency, reasonably avoiding the problem of multi-source information conflict. By introducing the concept of information half-life, the second credibility is calculated based on the generation time of the evidence information, taking into account the change of information credibility over time, making the assessment results more consistent with the actual characteristics of information timeliness. Finally, after weighting and correcting the basic probability allocation function based on the first and second credibility, the Dempster combination rule is used for fusion, so that evidence with high relevance and strong timeliness receives higher weight in the fusion, thereby achieving a more comprehensive, objective, real-time and accurate assessment of the service status of ship systems and improving the accuracy of ship system status assessment. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a flowchart illustrating the ship system status assessment method based on evidence relevance and timeliness provided in the embodiments of this application; Figure 2 This is a schematic diagram of the structure of the ship system status assessment device based on evidence relevance and timeliness provided in the embodiments of this application; Figure 3 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0026] In this article, the term "and / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. The symbol " / " in this article indicates that the related objects are in an "or" relationship; for example, A / B means A or B.

[0027] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0028] In the description of the embodiments of this application, unless otherwise stated, "multiple" means two or more, for example, multiple processing units means two or more processing units, multiple elements means two or more elements, etc.

[0029] Next, combined Figure 1 This application introduces a ship system status assessment method based on evidence relevance and timeliness, as provided in the embodiments of this application.

[0030] Figure 1This is a flowchart illustrating the ship system status assessment method based on evidence relevance and timeliness provided in the embodiments of this application, as follows: Figure 1 As shown, the method includes the following steps: Step S1: Select multiple information sources related to the ship system as evidence bodies, and construct the basic probability allocation function for each evidence body in each state of the ship system; To address the problem of insufficient information completeness in existing technologies, namely the frequent occurrence of missing data in single-source data, this application uses multi-source information related to ship systems to construct an evidence body, quantifies it into system state membership, realizes multi-source information fusion evaluation, and improves the problem of insufficient information completeness.

[0031] Optionally, the selection of evidence should follow the principle of system relevance, that is, the selected indicators must have a clear functional relationship with the target system, and the number and type of evidence should be dynamically adjusted in combination with the structural characteristics and actual working conditions of the system being evaluated.

[0032] Optionally, based on the characteristics of the ship's systems and actual operational needs, system states are divided, and these system states are assembled into an identification framework. The identification framework comprises all possible outcomes for a given decision problem. Recognition framework It is usually a non-empty set, defined as:

[0033] in, A 1. A 2… A m This refers to the service status level of the ship's systems to be evaluated.

[0034] In one embodiment of this application, the standard service status classification of the ship's propulsion system is shown in Table 1. The "status scoring range" in Table 1 refers to the comprehensive status scoring range obtained after preprocessing and comprehensive calculation based on relevant status indicators of the propulsion system. The scoring range is set from 0 to 10, with a larger value indicating a worse system status. The identification framework is constructed as {healthy, sub-healthy, unhealthy, faulty}.

[0035] Table 1 Standard Service Status of Ship Propulsion Systems

[0036] Optionally, the basic probability allocation function of the evidence body in each state of the ship system can be obtained through data statistics or expert experience. For example, for indicators with rich historical data, the support of each state can be determined by failure rate statistics, performance degradation trend analysis or threshold segmentation method; for indicators that rely on expert experience, a fuzzy rule base or expert scoring rules can be constructed by combining domain knowledge, the language evaluation can be converted into the support of each state, and the corresponding basic probability allocation function can be obtained after normalization.

[0037] Optionally, the raw data can be converted into support for the four standard states according to the correspondence between each piece of evidence and the four standard states of "healthy", "sub-healthy", "unhealthy" and "faulty". Finally, the support is normalized so that the sum of the allocation values ​​of the same piece of evidence in each state is 1, thus obtaining the basic probability allocation function of each piece of evidence in each state of the ship system.

[0038] Step S2: Calculate the Pearson correlation coefficient between each piece of evidence, and calculate the first credibility of each piece of evidence based on the Pearson correlation coefficient. This application quantifies the correlation between information by calculating the Pearson correlation coefficient between multiple sources, and adjusts the first confidence level of the data source based on the correlation to ensure reasonable avoidance of conflicts. The Pearson correlation coefficient is mainly used to measure the degree of correlation between two vectors.

[0039] Step S3: Calculate the second credibility of each piece of evidence based on the generation time and preset information half-life of each piece of evidence. When fusing multiple pieces of evidence, there may be situations where the evidence has different time limits, i.e., there are evidence with real-time characteristics and evidence without real-time characteristics. For evidence without real-time characteristics, various uncertain events may occur over time, and therefore its credibility will decrease over time. Therefore, this application proposes a second credibility calculation for evidence based on the time limit of evidence.

[0040] Step S4: Based on the first credibility and the second credibility, the basic probability allocation function of each piece of evidence in each state of the ship system is weighted and modified to obtain the modified piece of evidence; Optionally, the credibility of the evidence body is determined by combining the Pearson correlation coefficient and the statute of limitations of the evidence, and after normalization, it is used as the weight coefficient of the evidence body. The basic probability allocation function of the original evidence body is then weighted and modified using this weight to form the modified evidence body.

[0041] Step S5: The modified evidence body is fused using Dempster's combination rule to obtain the evaluation result.

[0042] According to Dempster's combination rule, the modified evidence is recursively fused, that is, the first two evidence are fused first, and then the fusion result is fused with the next evidence until all evidence is fused, so as to obtain the final evaluation result.

[0043] The ship system status assessment method based on evidence relevance and timeliness provided in this application achieves multi-source information fusion assessment by selecting multiple information sources as evidence bodies and constructing a basic probability allocation function, thereby improving the problem of insufficient information integrity of single-source data. By quantifying the correlation between each evidence body based on the Pearson correlation coefficient and calculating the first credibility accordingly, the credibility of the data source can be adjusted according to information consistency, reasonably avoiding the problem of multi-source information conflict. By introducing the concept of information half-life, the second credibility is calculated based on the generation time of the evidence body information, taking into account the change of information credibility over time, making the assessment results more consistent with the actual characteristics of information timeliness. Finally, after weighting and correcting the basic probability allocation function based on the first and second credibility, the Dempster combination rule is used for fusion, so that evidence with high relevance and strong timeliness receives higher weight in the fusion, thereby achieving a more comprehensive, objective, real-time and accurate assessment of the ship system's service status and improving the accuracy of ship system status assessment.

[0044] In some embodiments, selecting multiple information sources related to the ship system as evidence in step S1 includes: The status of critical equipment clusters on ships, the status of pre-departure inspections, and the status of graded maintenance were selected as evidence.

[0045] Select the status of the critical device cluster ( ), Pre-departure check status ( ) and maintenance status ( The above three aspects of status were selected as evidence based on the following considerations: the selected evidence is significantly relevant to the evaluation objective and can effectively reflect the real-time operating status of the ship's power system; the three types of evidence construct a complete evaluation indicator system from three dimensions: equipment operating parameters (critical equipment clusters), preventive maintenance records (pre-departure inspection), and planned maintenance records (graded maintenance).

[0046] Among them, the data for the status evidence of critical equipment clusters can be quantifiable operating parameters such as main engine speed, exhaust temperature, lubricating oil pressure, and vibration value; the data for the status evidence of pre-departure inspection can be the inspection conclusions of technical personnel on key components, fault symptom records, and maintenance recommendations; and the data for the status evidence of graded maintenance can be the time of the most recent graded maintenance, the completion status of maintenance items, and the cumulative operating time after maintenance.

[0047] In one embodiment of this application, the status of critical equipment clusters is evaluated using a cloud model assessment method; the pre-departure inspection status is evaluated using an expert two-layer linguistic fuzzy set semantic assessment; and the graded maintenance status is evaluated using a maintenance degradation function. The evaluation results of each piece of evidence are shown in Table 2 below. The values ​​in Table 2 represent the membership degree or support degree of the evidence to the corresponding status. The larger the value, the more likely the evidence is to support the corresponding status, and the sum of the membership degrees of the same piece of evidence across the four statuses is 1. For example, The membership degree for the "sub-healthy" state is 0.8915, indicating that the evidence body of the critical equipment cluster status provides the strongest support for the system being in a "sub-healthy" state. It should be noted that different systems and data sources should employ appropriate system indicator data preprocessing methods based on specific circumstances. The final system indicator data processing result should represent the membership degree of the system under different standard service states.

[0048] Table 2 Evaluation Results of Each Evidence Entity

[0049] In some embodiments, the method further includes: The original data of each piece of evidence were cleaned and standardized.

[0050] Optionally, the raw data of each piece of evidence can be preprocessed, including handling missing values, correcting outliers, unifying dimensions, and standardizing.

[0051] In some embodiments, step S2 specifically includes: Step S21: Calculate the Pearson correlation coefficient between each pair of evidence bodies; Step S22: Calculate the support level of each piece of evidence based on the Pearson correlation coefficient between each pair of evidence pieces; Step S23: Divide the support of each piece of evidence by the sum of the support of all pieces of evidence to obtain the first credibility of each piece of evidence.

[0052] Traditional evidence theory suffers from the flaw of illogical fusion results when fusing highly conflicting evidence. Therefore, this application improves the accuracy of evidence combination by weighting the basic probability assignment functions of each piece of evidence based on their credibility. The Pearson correlation coefficient is primarily used to measure the degree of correlation between two vectors. Suppose there are two samples... and Represented as a vector and Each sample has Each element can be represented as a component of a vector, therefore a vector... and Represented as , Pearson correlation coefficients among different evidence bodies The calculation formula is:

[0053] In the formula, This represents the correlation coefficient between two vectors; This represents the covariance of two vectors; and Representing vectors respectively and The standard deviation.

[0054] The value range of is [-1, 1]. When When the two vectors are positively correlated, it indicates that they are positively correlated; when... When, it means the two vectors are uncorrelated; when When the two vectors are negatively correlated, it indicates that they are negatively correlated; when... The larger the value, the higher the correlation between the two vectors.

[0055] Assume there is a total Each piece of evidence is represented as Calculate the correlation coefficient and construct the Pearson correlation coefficient matrix. .

[0056]

[0057] When two pieces of evidence are combined, if they conflict significantly, the subsequent calculations of support and credibility for each piece of evidence may result in negative values, rendering the results meaningless. Therefore, the Pearson correlation coefficient of two pieces of evidence with high conflict is corrected, and the elements of the Pearson correlation coefficient matrix satisfy the following constraints:

[0058] The support level for each piece of evidence was calculated based on the Pearson correlation coefficient matrix. Calculate the credibility of each piece of evidence based on the Pearson correlation coefficient. The calculation formula is:

[0059]

[0060] In some embodiments, step S3 specifically includes: Step S31: Calculate the decay factor based on the preset information half-life of each piece of evidence; Step S32: Calculate the timeliness weight based on the decay factor, the current time, and the time when the evidence information was generated; Step S33: Divide the statute of limitations weight of each piece of evidence by the sum of the statute of limitations weights of all pieces of evidence to obtain the second credibility of each piece of evidence.

[0061] When fusing multiple pieces of evidence, there may be situations where the evidence has different time limits, i.e., there are evidence with real-time characteristics and evidence with non-real-time characteristics. For non-real-time evidence, various uncertain events may occur over time, thus its credibility will decrease over time. Therefore, this application proposes a method for calculating the credibility of evidence based on its time limit. The specific steps for calculating the credibility of evidence using its time limit are as follows: 1a. Calculate the attenuation factor With time weighting function : To describe the process of evidence decay from its creation, we introduce the concept of information half-life, which is the time required for information to decrease in credibility to half after its creation. Let the half-life be denoted as . As shown in the following formula:

[0062] From the above formula, it can be seen that the evidence body has been in existence for a period of time. The reliability is halved afterward, hence the definition of a decay factor. :

[0063] Thus, the time-weighted function is derived. :

[0064] In the formula, ; The current time; The time at which the evidence information was generated. Time-weighted function. In the independent variable When the value is positive, its function value remains between (0,1], and it increases with time. It decreases as it increases.

[0065] 2a. Calculate the statute of limitations weight of the evidence. : Calculate the first using a time-weighted function The weight of timeliness of each piece of evidence :

[0066] In this application, half the time of the evidence information cycle is taken as the half-life of the evidence information.

[0067] 3a. Calculate the first The credibility of individual pieces of evidence based on the statute of limitations. The calculation formula is:

[0068] In some embodiments, step S4 specifically includes: Step S41: Determine the final credibility of each piece of evidence based on the first credibility and the second credibility. Step S42: Normalize the final credibility to obtain the weight coefficient of each piece of evidence; Step S43: Based on the weight coefficient of each piece of evidence, the basic probability allocation function of each piece of evidence in each state of the ship system is weighted and corrected to obtain the corrected piece of evidence.

[0069] The credibility of each piece of evidence is determined by combining the Pearson correlation coefficient and the timeliness of the evidence, and then normalized to serve as the weight coefficient for that evidence. The specific fusion process is as follows: The credibility of each piece of evidence based on relevance and timeliness (i.e., the first credibility and the second credibility) is combined to obtain the final credibility of each piece of evidence. Then, the final credibility is normalized to obtain the weight coefficient, which is used to weight and modify the basic probability assignment function of the original evidence, forming a modified evidence. Finally, the modified evidence is recursively fused according to the Dempster combination rule: first, the first two pieces of evidence are fused, then the fusion result is combined with the next piece of evidence, and so on, until all evidence is fused, thus obtaining the final evaluation result. In the final fusion result, the assignment value corresponding to each state represents the overall support level for the system belonging to that state. The specific steps are as follows: 1b. Determine the first The ultimate credibility of each piece of evidence :

[0070] 2b. Normalize the credibility of each piece of evidence to obtain the first... Weight of each piece of evidence :

[0071] 3b. Based on the weighted coefficients, combine the evidence to obtain the revised evidence. :

[0072] 4b. Given n pieces of evidence, use Dempster's combination rule to fuse the modified pieces of evidence n-1 times to obtain the final fusion result. The final fusion result is still the basic probability assignment on each standard state, and its assignment value on each state is the fused membership degree or support. The maximum membership degree is the largest of the assignment values ​​corresponding to each state, and the standard state corresponding to this maximum value is taken as the service status assessment result of the dynamic system.

[0073] In one embodiment of this application, the final credibility and weighting coefficient of the evidence body are calculated based on the Pearson correlation coefficient and the credibility obtained from the statute of limitations, as shown in Table 3 below: Table 3. Final Credibility and Weighting Coefficients of Evidence

[0074] In one embodiment of this application, the Dempster combination rule is used to aggregate the modified integrated evidence body n-1 times to obtain the final fusion result. In the final fusion result, the four values ​​of "healthy," "sub-healthy," "unhealthy," and "faulty" represent the fusion membership degree of the power system belonging to the corresponding state, i.e., the relative support degree after integrating all evidence, and the sum of each component is 1. The state with the largest value among the four components is taken as the final service state evaluation result of the power system. The fusion results are shown in Table 4 below: Table 4 Final Service Status Assessment Results

[0075] As can be seen from the table, the current service status of the ship's propulsion system has the highest fusion membership degree in the "sub-healthy" state, at 0.9665. Therefore, assessing the current service status of the ship's propulsion system as sub-healthy indicates that the current performance of the ship's propulsion system is relatively good and it can operate normally.

[0076] In summary, to address the issue of insufficient information completeness, i.e., the frequent occurrence of missing data in single-source data, this application uses multi-source information to construct evidence bodies, quantifies them into system state membership degrees, and achieves multi-source information fusion assessment, thus improving the problem of insufficient information completeness. Regarding the issue of the real-time nature of system information data, this application corrects the system information sources through a timeliness function, considering the changes in information credibility over time, which is more in line with reality. To address the issue of multi-source information conflicts, this application quantifies the correlation between information by calculating the Pearson correlation coefficient between multi-source information, and adjusts the data source credibility based on the correlation to ensure reasonable avoidance of conflicts. This application treats multi-source information as multiple evidence bodies, and then assigns high credibility or weight to reliable evidence bodies based on the relevance and timeliness of the information. After determining the credibility of the evidence bodies, a weighted average is performed on the basic probability allocation function of each evidence body before evidence body fusion, thereby solving the problems existing in the current assessment of the service status of ship systems.

[0077] The ship system status assessment device based on evidence relevance and timeliness provided in this application is described below. The ship system status assessment device based on evidence relevance and timeliness described below can be referred to in correspondence with the ship system status assessment method based on evidence relevance and timeliness described above.

[0078] Figure 2 This is a schematic diagram of a ship system status assessment device based on evidence relevance and timeliness, provided in an embodiment of this application. Figure 2 As shown, the device 200 includes: Module 210 is used to select multiple information sources related to the ship system as evidence bodies and construct the basic probability allocation function of each evidence body in each state of the ship system. The first calculation module 220 is used to calculate the Pearson correlation coefficient between each piece of evidence, and to calculate the first credibility of each piece of evidence based on the Pearson correlation coefficient. The second calculation module 230 is used to calculate the second credibility of each piece of evidence based on the generation time and preset information half-life of each piece of evidence. The correction module 240 is used to perform a weighted correction on the basic probability allocation function of each piece of evidence in each state of the ship system based on the first credibility and the second credibility, so as to obtain the corrected piece of evidence. Evaluation module 250 is used to fuse the modified evidence body using Dempster's combination rules to obtain evaluation results.

[0079] It should be understood that the above-described device is used to execute the methods in the above embodiments. The implementation principle and technical effect of the corresponding program modules in the device are similar to those described in the above methods. The working process of the device can be referred to the corresponding process in the above methods, and will not be repeated here.

[0080] Based on the methods in the above embodiments, Figure 3 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 3 As shown in the illustration, this application provides an electronic device that may include a processor 310, a communications interface 320, a memory 330, and a communication bus 340. The processor 310, communications interface 320, and memory 330 communicate with each other via the communication bus 340. The processor 310 can call logical instructions stored in the memory 330 to execute the ship system status assessment method based on evidence relevance and timeliness described in the above embodiment.

[0081] Furthermore, the logical instructions in the aforementioned memory 330 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the ship system status assessment method based on evidence relevance and timeliness described in the various embodiments of this application.

[0082] Based on the methods in the above embodiments, this application provides a computer-readable storage medium storing a computer program. When the computer program runs on a processor, it causes the processor to execute the ship system status assessment method based on evidence relevance and timeliness in the above embodiments.

[0083] Based on the methods in the above embodiments, this application provides a computer program product that, when run on a processor, causes the processor to execute the ship system status assessment method based on evidence relevance and timeliness in the above embodiments.

[0084] It is understood that the processor in the embodiments of this application can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. A general-purpose processor can be a microprocessor or any conventional processor.

[0085] The method steps in this application embodiment can be implemented in hardware or by a processor executing software instructions. The software instructions can consist of corresponding software modules, which can be stored in random access memory (RAM), flash memory, read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, portable hard disks, CD-ROMs, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can reside in an ASIC.

[0086] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially as a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0087] It is understood that the various numerical designations used in the embodiments of this application are merely for the convenience of description and are not intended to limit the scope of the embodiments of this application.

[0088] Those skilled in the art will readily understand that the above description is merely a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for assessing the state of a ship system based on the relevance and timeliness of evidence, characterized in that, include: Multiple information sources related to the ship system are selected as evidence, and a basic probability allocation function for each evidence in each state of the ship system is constructed. Calculate the Pearson correlation coefficient between each piece of evidence, and calculate the first confidence level corresponding to each piece of evidence based on the Pearson correlation coefficient; Calculate the second credibility of each piece of evidence based on the generation time and preset information half-life of each piece of evidence. Based on the first credibility and the second credibility, the basic probability allocation function of each piece of evidence in each state of the ship system is weighted and modified to obtain the modified piece of evidence; The modified evidence body was fused using Dempster's combination rule to obtain the evaluation results.

2. The ship system status assessment method based on evidence relevance and timeliness according to claim 1, characterized in that, The selection of multiple information sources related to the ship's systems as evidence includes: The status of critical equipment clusters on ships, the status of pre-departure inspections, and the status of graded maintenance were selected as evidence.

3. The ship system status assessment method based on evidence relevance and timeliness according to claim 1 or 2, characterized in that, The method further includes: The original data of each piece of evidence were cleaned and standardized.

4. The ship system status assessment method based on evidence relevance and timeliness according to claim 1, characterized in that, The calculation of the Pearson correlation coefficient between each piece of evidence, and the calculation of the first credibility corresponding to each piece of evidence based on the Pearson correlation coefficient, includes: Calculate the Pearson correlation coefficient between each pair of evidence bodies; Based on the Pearson correlation coefficient between each pair of evidence, the support level of each evidence is calculated. Divide the support of each piece of evidence by the sum of the support of all pieces of evidence to obtain the first credibility of each piece of evidence.

5. The ship system status assessment method based on evidence relevance and timeliness according to claim 1, characterized in that, The calculation of the second credibility of each piece of evidence based on the generation time and preset information half-life includes: The decay factor is calculated based on the preset information half-life of each piece of evidence. Calculate the timeliness weight based on the decay factor, the current time, and the time when the evidence information was generated; Divide the statute of limitations weight of each piece of evidence by the sum of the statute of limitations weights of all pieces of evidence to obtain the second credibility of each piece of evidence.

6. The ship system status assessment method based on evidence relevance and timeliness according to claim 1, characterized in that, The basic probability allocation function for each piece of evidence under various states of the ship system is weighted and modified based on the first credibility and the second credibility to obtain the modified evidence, including: Based on the first credibility and the second credibility, the final credibility of each piece of evidence is determined; The final credibility is normalized to obtain the weight coefficient of each piece of evidence; The basic probability allocation function of each piece of evidence under each state of the ship system is weighted and modified based on the weight coefficient of each piece of evidence to obtain the modified piece of evidence.

7. A ship system status assessment device based on evidence relevance and timeliness, characterized in that, include: The module is used to select multiple information sources related to the ship system as evidence bodies and construct the basic probability allocation function of each evidence body in each state of the ship system. The first calculation module is used to calculate the Pearson correlation coefficient between each piece of evidence, and to calculate the first credibility of each piece of evidence based on the Pearson correlation coefficient. The second calculation module is used to calculate the second credibility of each piece of evidence based on the generation time and preset information half-life of each piece of evidence. The correction module is used to perform a weighted correction on the basic probability allocation function of each piece of evidence in each state of the ship system based on the first credibility and the second credibility, so as to obtain the corrected piece of evidence. The evaluation module is used to fuse the modified evidence body using Dempster's combination rules to obtain the evaluation results.

8. An electronic device, characterized in that, include: At least one memory for storing computer programs; At least one processor is configured to execute a program stored in the memory, wherein when the program stored in the memory is executed, the processor is configured to perform the ship system status assessment method based on evidence relevance and timeliness as described in any one of claims 1-6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is run on the processor, the processor performs the ship system status assessment method based on evidence relevance and timeliness as described in any one of claims 1-6.

10. A computer program product, characterized in that, When the computer program product is run on a processor, the processor performs the ship system status assessment method based on evidence relevance and timeliness as described in any one of claims 1-6.

Images