WO2021218003A1 - Système de gestion de santé intégré à un radar - Google Patents

Système de gestion de santé intégré à un radar Download PDF

Info

Publication number
WO2021218003A1
WO2021218003A1 PCT/CN2020/115767 CN2020115767W WO2021218003A1 WO 2021218003 A1 WO2021218003 A1 WO 2021218003A1 CN 2020115767 W CN2020115767 W CN 2020115767W WO 2021218003 A1 WO2021218003 A1 WO 2021218003A1
Authority
WO
WIPO (PCT)
Prior art keywords
radar
evaluation
fault
maintenance
health
Prior art date
Application number
PCT/CN2020/115767
Other languages
English (en)
Chinese (zh)
Inventor
吕永乐
詹进雄
渠浩
Original Assignee
中国电子科技集团公司第十四研究所
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 中国电子科技集团公司第十四研究所 filed Critical 中国电子科技集团公司第十四研究所
Publication of WO2021218003A1 publication Critical patent/WO2021218003A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
    • G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
    • G01S7/40—Means for monitoring or calibrating
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2455—Query execution
    • G06F16/24564—Applying rules; Deductive queries
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N7/00—Computing arrangements based on specific mathematical models
    • G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/20—Administration of product repair or maintenance

Definitions

  • the invention belongs to the technical field of radar management, and specifically relates to a radar embedded health management system.
  • phased array technology With the rapid development and large-scale application of phased array technology, the complexity of military and civilian radar systems is getting higher and higher, and higher requirements are put forward for its comprehensive support capabilities.
  • the purpose of the present invention is to provide a radar embedded health management system, which can realize the multi-dimensional analysis of radar health data, covers the main functional elements of health management, and can adapt to the health management requirements of radars in different fields.
  • the present invention provides a radar embedded health management system, including:
  • the data layer is used to obtain and access the raw data of the management radar
  • Application layer used for multi-dimensional analysis and maintenance guidance of radar health data, including condition monitoring module and fault diagnosis module;
  • the state monitoring module monitors the radar test parameters and outputs the monitoring results to the fault diagnosis module;
  • the fault diagnosis module searches and matches the received monitoring results according to the diagnosis rules, and judges whether there is a fuzzy group according to the searched and matched rules, if there is no fuzzy group, then outputs the diagnosis conclusion; if there is a fuzzy group, starts Bayesian Network for diagnosis;
  • the presentation layer is used to present the results of each functional module.
  • diagnosis rules include specifying the format of each failure mode, the hazard level of the failure mode, the code of the failure mode, the logic judgment when the failure occurs, and the failure part number, which are defined by the diagnosis model file.
  • the specific method for starting the Bayesian network for diagnosis includes:
  • the network parameter learning algorithm is used to calculate the conditional probability of the occurrence of the fault symptom
  • the posterior probability of each fault type is calculated according to the Bayesian formula, and the fault corresponding to the largest posterior probability is used as the result of starting the Bayesian network for diagnosis.
  • the method for calculating the prior probability is to extract the occurrence frequency information of each fault type from the historical state data of the radar equipment, and the failure rate ⁇ calculated by the following formula is used as the fault type
  • the prior probability :
  • the specific method for obtaining the prior probability includes:
  • R i represents the evaluation of the possibility of the occurrence of the fault type caused by the influencing factor u i
  • r ij represents the possibility of making the j-th evaluation for the i-th influencing factor, where 0 ⁇ r ij ⁇ 1, and m represents the influence
  • the number of factors, n represents the number of reviews in the evaluation set;
  • the fuzzy comprehensive evaluation matrix B is calculated and the evaluation result is obtained.
  • the fuzzy comprehensive evaluation matrix B is:
  • the probability value corresponding to the largest parameter in the fuzzy comprehensive evaluation matrix B is taken as the prior probability of the fault type.
  • the application layer further includes a health evaluation module, the health evaluation module receives the output result of the fault diagnosis module, and judges the output result as follows:
  • the hazard level corresponding to the fault is level IV or level III, the health index of the whole radar system is further calculated from the health index calculation model and performance input parameters, and the corresponding equipment maintenance is carried out according to the health index value.
  • the sample data is in the form of (x i ,y), and x i is the performance input parameter of the health index calculation model, y is the radar health index, ⁇ is the adjustment coefficient, and the value range is between 1 and 2, which is used to make the radar health index y range from 0 to 1; w T is the set of weight coefficients of each performance parameter.
  • Each performance parameter index is divided into several important levels according to its importance; each level may contain several evaluation indexes, and the difference in importance between these same-level indexes is much smaller than the difference in cross-level indexes; the judgment rules for determining w i are as follows:
  • the application layer also includes a maintenance decision-making module; the maintenance decision-making module receives the output data of the fault diagnosis module and the health evaluation module, and judges the state of the radar system, that is, whether there is a fault that affects the execution of the task; if it exists, then Directly notify the maintenance personnel to repair; if there is no such failure, then further determine whether the system health status meets the task requirements; if it is satisfied, the maintenance decision-making process is directly ended, if it is not satisfied, the maintenance decision-making judgment is executed, which is based on the efficacy
  • the coefficient radar decision model gives the optimal maintenance plan.
  • i 1,2,3...q ⁇ ; assuming that the radar equipment has a total of p maintenance plans in the fault state ⁇ f i
  • i 1,2,3...p ⁇ , f i represents the first i maintenance plan, x ij represents the j-th evaluation index in the f i maintenance plan; the maintenance plan set in the equipment failure state is F, and then according to the definition of the maintenance plan:
  • the difference measure of each index is converted into a unified efficiency coefficient through the efficiency coefficient model, and the total efficiency coefficient calculated by each maintenance plan is used as the criterion, and each maintenance plan is carried out. Sort, the maintenance plan corresponding to the maximum total efficiency coefficient is the optimal maintenance plan.
  • the application layer also includes a trend prediction module; the trend prediction module performs long-term monitoring and recording around the key parameters of the radar system and each subsystem, and performs statistical analysis and predictive modeling of historical data to predict the key parameters. Parameter development trend in the next period of time.
  • the radar embedded health management software based on the domestic platform of the present invention realizes multi-dimensional analysis of radar health data, generates lean and efficient maintenance strategies, covers the main functional elements of health management, and can adapt to the health management needs of radars in different fields:
  • the fault diagnosis module implements a rule-based and Bayesian network-based fusion diagnosis method, and proposes a method to re-update and calculate the prior probability based on the fault frequency of the component, so as to solve the problem that the radar equipment lacks monitoring information and cannot be further diagnosed;
  • the health evaluation module is constructed based on the qualitative evaluation of the fault hazard level and the quantitative evaluation method based on the performance index. It evaluates the health status of the equipment from the two dimensions of the fault hazard level and the comprehensive evaluation of the performance index.
  • the health index calculation model and the calculation method of the weight coefficient are given to break through the health of the equipment. Status evaluation problem;
  • the maintenance decision module combines several maintenance indicators of the radar to propose the optimal decision-making process of the radar maintenance plan based on the efficiency coefficient, and clarifies the optimal plan selection plan in the maintenance plan decision based on the maintenance index, reduces support costs and improves support efficiency.
  • Fig. 1 is an architecture diagram of a radar embedded health management system according to an embodiment of the present invention.
  • Fig. 2 is a schematic diagram of the relationship between the data structure of application layer function modules in an embodiment of the present invention.
  • Fig. 3 is a working flow chart of the fault diagnosis module of the embodiment of the present invention.
  • Fig. 4 is a working flow chart of the health evaluation module of the embodiment of the present invention.
  • Fig. 5 is a basic processing flowchart of a maintenance decision-making module according to an embodiment of the present invention.
  • An embodiment of the present invention is a radar embedded health management system.
  • the present invention constructs radar embedded health management software based on a domestic platform in view of the insufficient capabilities of the existing radar health management software and the demand for localization.
  • the software composition level is shown in Figure 1, including data layer, application layer and presentation layer.
  • the platform layer provides a suitable environment for software operation, and consists of a localized Godson CPU, a localized Kylin operating system, and a localized Kingbase database.
  • the radar data is sent to the software data layer through the platform layer.
  • the data layer is used to obtain and access and manage the raw data of the radar, including Kingbase data services, data organization and management modules.
  • the application layer realizes multi-dimensional analysis of radar health data and maintenance guidance, including business modules such as condition monitoring, fault diagnosis, health evaluation, trend prediction, maintenance decision-making, and statistical analysis.
  • the presentation layer is used to present the results of each functional module, including status lists, fault information, statistical charts, maintenance lists, etc.
  • the fault diagnosis module at the application layer adopts rule-based fast diagnosis and Bayesian network in-depth diagnosis methods to achieve rapid isolation of existing fault modes, and at the same time, the fuzzy evaluation method based on expert experience obtains the prior probability of each fault type to achieve higher Isolation accuracy;
  • the health evaluation module is constructed based on the qualitative evaluation of the fault hazard level and the quantitative evaluation method based on the performance index, and the health index model is used to achieve the quantitative evaluation of the overall health of the radar;
  • the maintenance decision module is based on the radar maintenance based on the efficiency coefficient and combined with the multi-attribute optimal Decision-making method, combining task requirements and maintenance efficiency and other factors to give the optimal maintenance plan.
  • the data service module in the data layer adopts the Kingbase database, and other domestic databases can achieve equivalent functions.
  • the data service module has data access and maintenance functions.
  • the data sources include radar calibration mode, normal working mode, automated testing and other processes.
  • the data organization and management module of the data layer is responsible for realizing various data structure management to meet the requirements of various application layer modules. Data scheduling request and data maintenance requirements.
  • the data structure relation of each function module of the application layer is shown in Figure 2.
  • the data structure composition of the condition monitoring module includes parameters such as test item number, test item result, test item status (normal or abnormal), and these parameters are sent to the subsequent fault diagnosis module, health evaluation module, trend prediction module, maintenance decision module, these modules It is necessary to rely on these data for subsequent fault diagnosis, health evaluation, trend prediction, and maintenance decision-making.
  • the data structure of the fault diagnosis module includes fault item number, fault occurrence flag, fault hazard level, etc. Failure hazard level refers to the degree of damage to the system after a specific failure occurs. It is generally divided into four levels from I to IV. The corresponding descriptions are catastrophic, fatal, moderate, and mild.
  • the relevant data items of the fault diagnosis module are output and sent to the health evaluation module, the trend prediction module, and the maintenance decision-making module.
  • the fault hazard level is the basis for the health evaluation module to evaluate the system health level.
  • the data structure of the health evaluation module includes evaluation item number, system health level, system health coefficient, etc.
  • the system health level is divided into three categories: healthy, sub-healthy, and unable to work.
  • the result of judging the system health level directly affects the subsequent maintenance decision. For example, if the system health level is not working, it needs to be repaired immediately, otherwise, if it is sub-healthy, further judgment is required.
  • the system health coefficient refers to the percentage of the coefficient in the current state of the radar compared to the intact state, and generally ranges from 0 to 1.
  • the corresponding relationship between the hazard level of the fault diagnosis module and the health level of the health evaluation module is as follows: Levels I and II correspond to the health level of not working, level III corresponds to the sub-health level of the health level, and level IV corresponds to the health level of the health level.
  • the relevant data output of the health evaluation module is sent to the trend prediction module and the maintenance decision-making module to be used as the data on which the maintenance decision-making judgment depends.
  • the data structure of the trend prediction module includes prediction parameter numbers, meaning of prediction parameters (such as gear wear status, rolling bearing life, etc.), parameter history data, prediction results, etc.
  • the relevant data of the trend prediction module is output to the maintenance decision-making module to provide decision-making judgments on potential trend failures.
  • the data structure composition of the maintenance decision module includes the output of the aforementioned modules, maintenance costs, failure loss, failure maintenance time, maintenance mode number, etc. Maintenance cost, failure loss, and failure repair time are all relevant indicators to measure the cost of failure repair.
  • the data structure of the statistical analysis module includes statistical parameter numbers, statistical time numbers, etc.
  • the analysis data required by the statistical analysis module is obtained from the database, and the data structures that can be analyzed include component failure times, parameter historical data, analysis of the proportion of sub-system status, etc. .
  • the status monitoring module in each functional module is the start of the function, and the subsequent four modules (fault diagnosis, health evaluation, trend prediction, maintenance decision-making) are executed according to user needs.
  • the statistical analysis module is independent of the aforementioned five functional modules (condition monitoring module, fault diagnosis module, health evaluation module, trend prediction module, maintenance decision-making module), and runs independently and is not affected by these five modules.
  • the fault diagnosis module of the application layer constructs a rapid diagnosis based on rule matching and a deep diagnosis strategy of Bayesian network.
  • the module workflow is shown in Figure 3.
  • the fault diagnosis module uses the test item number of the status monitoring module to search and match the diagnosis rules parsed from the diagnosis model file, and judge whether there is ambiguity based on the matched rules. Group.
  • the judgment method is that if the number of faulty LRUs (line replaceable units) isolated in a single rule on the match is not greater than 1, then it is considered that there is no fuzzy group and the diagnosis conclusion is output; if the number is greater than 1, then it is considered There is a fuzzy group, start Bayesian network diagnosis:
  • failure mode refers to the specification description of the failure phenomenon that can be observed or measured in the product;
  • the fault corresponding to the largest posterior probability is the diagnosis result obtained by further judgment, and the corresponding component fault information is stored in In the database, and output the diagnosis result.
  • the fault diagnosis module outputs the diagnosis results to the health evaluation module and the data organization and management module.
  • the diagnosis model file is an xml file
  • the diagnosis rules stipulate the format of each failure mode in the diagnosis model file, the hazard level of the failure mode, the code of the failure mode, the logic judgment when the failure occurs, the number of the failure part, etc.
  • the following example illustrates the elements contained in the xml configuration file.
  • the failure part number ⁇ FAULTID> is LRU001, which means the part is broken;
  • the test item number corresponds to a certain test item, that is, corresponds to a certain test parameter, that is, the number of the test item that needs to determine whether a failure occurs, is T1;
  • the failure item number corresponds to a certain test item, that is, corresponds to a certain test parameter, that is, the number of the test item that needs to determine whether a failure occurs, is T1;
  • ⁇ FAULTCODE> is F_00_01, which is consistent with the meaning of the fault item code in the FMECA form.
  • ⁇ FAULTRELATED> represents the number of other fault items associated with the fault mode.
  • ⁇ FAULTREASON> represents the cause of the failure, and
  • ⁇ FAULTGRADE> represents the hazard level of the failure mode, which is consistent with the failure level in the FMECA table.
  • the failure mode and the hazard level of the failure mode can be obtained from the product FMECA table.
  • the information in this table needs to be filled out by each designer in accordance with the actual situation.
  • T1 and T2 are test item numbers, [] is test item status, and when the preset value and actual value of the test item are both satisfied, it means A failure occurred. Take T1[0]*T2[1] as an example.
  • the judgment rule is that the fault occurs when T1 is normal and T2 is abnormal.
  • the judgment process is to judge whether the measured values of test items T1 and T2 are the same as the expression If the preset is the same, the fault will occur if the same is the same.
  • the Bayesian network needs to determine the relationship between the parent node (fault type) and the child node (fault symptom), and these relationships are obtained through the FMECA table and expert experience.
  • the connection of the directed edge between the parent node and the child node represents the causal relationship between the fault type and the fault symptoms.
  • the prior probability of the fault type is based on the historical fault data of the radar equipment, and the probability of each fault type is counted as the prior probability; the conditional probability of the fault symptom is based on the probability of the fault symptom after the fault type occurs.
  • conditional probability is based on the prior probability and is calculated by using existing common network parameter learning algorithms (such as Bayesian estimation, maximum likelihood estimation); the posterior probability is the probability of the occurrence of the failure type in the case of the occurrence of a fault sign, through Bayesian Calculated by the S formula.
  • common network parameter learning algorithms such as Bayesian estimation, maximum likelihood estimation
  • the frequency information of each fault type is directly extracted from its historical status database, and the calculated failure rate ⁇ is used as the prior probability of the fault type.
  • the specific calculation formula is:
  • the present invention proposes to use a fuzzy evaluation method based on expert experience to obtain the prior probability of each fault type.
  • the specific implementation steps are as follows:
  • R i represents the evaluation of the possibility of the occurrence of the fault type caused by the influencing factor u i
  • r ij represents the possibility of making the j-th evaluation for the i-th influencing factor, where 0 ⁇ r ij ⁇ 1, and m represents the influence
  • r ij can give specific results through specific expert experience.
  • A ⁇ a 1 ,a 2 ,a 3 ,a i ...a m ⁇ ,
  • m the number of influencing factors
  • the determination of the weight matrix directly affects the evaluation results of the possibility.
  • the specific calculation methods are usually divided into two categories.
  • One is the expert experience method, which gives the matrix value composition through collective experience and expert setting, and the other is the use of professional It is calculated by mathematical methods, such as the AHP method (Analytic Hierarchy Process, Analytic Hierarchy Process).
  • b i represents the evaluation value of the i-th level of the probability of occurrence of the fault type obtained after weighting
  • the maximum value of the n bi parameters is taken as the level of the possibility of the fault type, and the probability corresponding to the level of the possibility is taken as the prior probability of the fault type.
  • the maximum value of the bi parameter (b 2 0.5)
  • the health evaluation module of the application layer realizes the qualitative evaluation based on the fault hazard level and the quantitative evaluation based on the performance index.
  • the health evaluation process is shown in Figure 4. First, the health evaluation module receives the output result of the fault diagnosis module, and judges the output result as follows:
  • the conclusion of system health is directly output, and the end; if there is a fault, it is further judged whether the corresponding hazard level of the fault is level I or level II. If it is level I or level II, it will directly output the conclusion that the radar is shut down for maintenance and end; if the hazard level corresponding to the fault is level IV or level III, the health index calculation formula is further used for judgment, specifically:
  • the health index of the whole radar system is calculated through the health index calculation formula (formula (2)), and the equipment maintenance is guided according to the health index value. For example, when the health factor is 0.9 to 1, it will not affect task execution and normal work; when the health factor is 0.6 to 0.9, the basic functions will not be affected, and the task will be shut down for maintenance after the task is completed; when the health factor is 0.4 to 0.6, Shut down and manually switch to redundant equipment; when the health coefficient is 0 to 0.4, it must be shut down for maintenance.
  • the health evaluation module finally outputs the relevant data such as health level and health coefficient and sends it to the trend prediction module and maintenance decision-making module.
  • the calculation of the health index relies on the health index calculation model and performance input parameters.
  • the performance input parameter information is shown in Table 1, and the parameters listed in the list are all well-known parameters in the art.
  • the formula of the radar health index y calculation model is as follows:
  • the sample data is in the form of (x, y), which is the input data, and the specific expression form is: x i is the performance input parameter of the health index calculation model, ⁇ is the adjustment coefficient, and the value range is between 1 and 2, which is used to make the radar health index y range from 0 to 1.
  • w T is the set of weight coefficients of each performance parameter.
  • the weight coefficient is generally determined by the expert assignment method or the influence assignment method.
  • the expert assignment method fully considers the influence of various performance parameters on the state of the radar system.
  • the radar design expert assigns different weights to the above selected performance parameters through his own design experience, but the expert assignment method may have the determination of the weight coefficient There is a certain degree of subjective arbitrariness.
  • the influence assignment method determines the size of the index weight coefficient according to the attribute difference of the index to the evaluation conclusion.
  • the so-called difference in conclusion attributes refers to the fact that the different states of the indicator will lead to the opposite or greater difference in the evaluation conclusions.
  • this embodiment integrates the expert assignment weight coefficient and the influence assignment weight coefficient to determine the final evaluation weight coefficient w i , the expression of w i is:
  • the performance input parameters of the health index calculation model in Table 1 are divided into several levels according to their importance.
  • the parameter importance level for evaluating the parameter index is divided into P1, P2, P3,..., Pk, and its level importance can be represented by P1>P2>P3...>Pk.
  • the P1 level index is the most important, and the P2 level index The importance is greater than P3, and the rest is similar.
  • Each level may contain several evaluation indicators, and the difference in importance between these same-level indicators is much smaller than the difference in cross-level indicators.
  • the judgment rules for determining w i are as follows:
  • the order of the weight coefficients obtained by the expert assignment method and the order of the weight coefficients obtained by the influence assignment method are not exactly the same (there is the same in the ordering, but only a part of it is different, for example, the arrangement of the expert assignment method
  • the order is a>b>c>d, and the order of the influence assignment method is a>c>b>d), but the evaluation index corresponds to the same importance rank order, then the weights obtained by the expert assignment method and the influence assignment method are the same.
  • the order of the weight coefficients obtained by the expert assignment method and the order of the weight coefficients obtained by the influence assignment method are not the same (the arrangement is completely different, and even the reverse order appears, for example, the arrangement of the expert assignment method
  • the order is a>b>c>d
  • the order of the influence assignment method is c>b>d>a)
  • the weight coefficient of the evaluation index corresponds to the importance level and the order is inconsistent, indicating that the basis of the influence assignment method is not based on the importance level of the evaluation index It does not have reference significance
  • the trend prediction module focuses on the radar system and the key parameters of each subsystem (such as gear wear status, rolling bearing life, etc.) for long-term monitoring and recording, and statistical analysis of historical data, predictive modeling, and the development of predictive parameters in the next period of time Trends, provide reference information for preventive maintenance.
  • the predictive modeling algorithms that can be used, such as neural networks, gray theory, etc., need to be combined with data characteristics to adopt corresponding algorithm models.
  • the trend prediction results are sent to the maintenance decision-making module and the data organization and management module.
  • the maintenance decision-making module of the application layer combines the use characteristics of in-service radars to propose an optimal radar maintenance decision-making method based on efficiency coefficients, which can reduce support costs and improve support efficiency.
  • the basic processing flow of this module is shown in Figure 5.
  • the maintenance decision-making module receives the output data of the fault diagnosis module and the health evaluation module, and judges the state of the radar system, that is, judges whether there is a fault that affects the execution of the task. If it does, the maintenance staff will be directly notified to repair it; if there is no such failure, it will be further judged whether the system health status meets the task requirements. If it is satisfied, the maintenance decision-making process is directly ended. If it is not satisfied, the maintenance decision-making judgment is executed, that is, the radar decision-making model based on the efficiency coefficient gives the optimal maintenance plan and guides the maintenance personnel to perform the optimal maintenance process.
  • the radar decision-making model based on the efficiency coefficient is the core of the maintenance decision-making module.
  • the evaluation indicators related to the determination of maintenance tasks are called decision-making indicators. For the needs of maintenance tasks, determine the task-related decision-making indicators ⁇ x j
  • j 1, 2, 3...q ⁇ . Assuming that the equipment has a total of p maintenance plans ⁇ f i
  • i 1, 2, 3...p ⁇ in the fault state, f i represents the i-th maintenance plan, and x ij represents the j-th evaluation index in the f i maintenance plan. In the fault state, the maintenance plan set is F, and then according to the definition of the maintenance plan:
  • the decision-making indicators explicitly involved in this maintenance task include maintenance labor costs, material costs, failure loss, failure maintenance time, task emergency, and equipment health value added value. Other indicators related to maintenance support can be expanded based on actual conditions, and are not limited to these six indicators.
  • the function of defining the maintenance plan set F is to facilitate the analysis through the optimal decision method.
  • Standardization processing realizes the normalization of indicators of different dimensions to obtain dimensionless indicators.
  • indicators can be divided into two categories: positive indicators and negative indicators.
  • the positive index means that the larger the index value is, the better, and the negative index means that the smaller the index value is, the better.
  • the range transformation method is used to process to form dimensionless indicators.
  • f ista to represent the i-th standardized evaluation index set obtained after range transformation, and define y ij as the j-th standardized evaluation index in the i-th f ista.
  • the standardized decision matrix F sta obtained after the range transformation is defined as follows:
  • the weighting coefficient of each index is determined by the entropy weighting method.
  • the principle of determining the weight coefficient is based on the entropy value, the larger the entropy, the smaller the weight coefficient. Normalize the decision matrix F sta obtained by the standardization process to obtain the normalization coefficient It is defined as:
  • I a constant
  • I a single normalization coefficient in the above-mentioned normalization coefficient matrix L
  • p represents a total of p rows
  • q represents a total of q columns.
  • q represents the number of parameters w j.
  • q represents the number of parameters w j , which is consistent with the definition of q in the w j formula.
  • the difference measure of each index is converted into a unified efficiency coefficient through the efficiency coefficient model pair, so as to comprehensively evaluate the optimal maintenance plan.
  • the power coefficient ⁇ ij of each index parameter is defined as:
  • index satisfaction value in Is the index satisfaction value, The value is not allowed for the indicator.
  • Efficacy index coefficient ⁇ ij satisfaction value of 100, index values allowed efficacy coefficient ⁇ ij is 60.
  • the efficiency coefficient matrix ⁇ is defined as:
  • i 1 to p.
  • w j in the expression is the weight coefficient of each index calculated in (3).
  • the maintenance decision-making module uses the total efficiency coefficient calculated by each maintenance plan as the criterion, and ranks the optimality of each maintenance plan.
  • the larger the total efficiency coefficient the more priority the maintenance plan corresponding to the total efficiency coefficient will be arranged for implementation, otherwise, the lower the priority.
  • the statistical analysis module reads and analyzes the various types of health data stored in the record, and the form of expression supports charts, broken lines, pie charts, etc., and mainly interacts with the data organization and management module, and the database.
  • the presentation layer is used to present the results of each functional module, including status lists, fault information, statistical charts, maintenance lists, etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Marketing (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Tourism & Hospitality (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)
  • Mathematical Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • Computing Systems (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Remote Sensing (AREA)
  • Computational Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Computational Linguistics (AREA)
  • Databases & Information Systems (AREA)
  • Algebra (AREA)
  • Probability & Statistics with Applications (AREA)
  • Game Theory and Decision Science (AREA)
  • Testing And Monitoring For Control Systems (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

La présente invention, qui se rapporte au domaine technique de la gestion des radars, concerne un système de gestion de santé intégré à un radar. Le système est construit au niveau d'une couche de plate-forme et comprend : une couche de données, qui est utilisée pour acquérir des données brutes d'un radar de gestion à partir de la couche de plate-forme et pour accéder auxdites données ; une couche d'application qui est utilisée pour effectuer une analyse multidimensionnelle et un guidage d'entretien sur des données de santé du radar et qui comprend un module de surveillance d'état et un module de diagnostic de défaillances. Le module de surveillance d'état surveille un paramètre d'essai du radar et émet le résultat de surveillance au module de diagnostic de défaillances ; le module de diagnostic de défaillances recherche et met en correspondance le résultat de surveillance reçu selon une règle de diagnostic, détermine s'il existe un groupe approximatif pour une règle recherchée et mise en correspondance, et émet une conclusion de diagnostic si un groupe approximatif n'existe pas ; par contre, si un groupe approximatif existe, un réseau bayésien est mis en œuvre pour le diagnostic. Le système met en œuvre une analyse multidimensionnelle de données de santé de radars, recouvre des éléments fonctionnels principaux de gestion de santé, et peut s'adapter à des exigences de gestion de santé de radars dans différents domaines.
PCT/CN2020/115767 2020-04-27 2020-09-17 Système de gestion de santé intégré à un radar WO2021218003A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010343224.8A CN111553590B (zh) 2020-04-27 2020-04-27 一种雷达嵌入式健康管理系统
CN202010343224.8 2020-04-27

Publications (1)

Publication Number Publication Date
WO2021218003A1 true WO2021218003A1 (fr) 2021-11-04

Family

ID=72007712

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/115767 WO2021218003A1 (fr) 2020-04-27 2020-09-17 Système de gestion de santé intégré à un radar

Country Status (2)

Country Link
CN (1) CN111553590B (fr)
WO (1) WO2021218003A1 (fr)

Cited By (61)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114065109A (zh) * 2021-11-17 2022-02-18 国网浙江省电力有限公司杭州供电公司 一种电力系统需求响应聚合用户的优选方法
CN114091268A (zh) * 2021-11-24 2022-02-25 南京航空航天大学 一种基于节点重要度与层次分析法的无人机健康状况评估方法
CN114091618A (zh) * 2021-11-30 2022-02-25 重庆允成互联网科技有限公司 工业设备健康状态诊断管理方法、装置及服务器
CN114266436A (zh) * 2021-11-10 2022-04-01 上海航天控制技术研究所 星敏感器在轨健康评估方法以及存储介质和电子设备
CN114330006A (zh) * 2021-12-31 2022-04-12 中国电子产品可靠性与环境试验研究所（（工业和信息化部电子第五研究所）（中国赛宝实验室）） 可抑制虚警的多故障诊断的方法、系统及计算机设备
CN114357893A (zh) * 2022-01-27 2022-04-15 西安交通大学 基于多特征融合som的车载天线传动系统健康评估方法
CN114389231A (zh) * 2021-12-31 2022-04-22 广东电网有限责任公司茂名供电局 一种基于配电网保护及设备实时数据的负荷预测诊断方法
CN114384896A (zh) * 2022-01-12 2022-04-22 北京交通大学 轨道交通列控车载设备模拟电路级健康度预测方法及系统
CN114399220A (zh) * 2022-01-20 2022-04-26 江苏徐工工程机械研究院有限公司 工程机械维修性评价方法和装置、计算机装置和存储介质
CN114400776A (zh) * 2022-01-10 2022-04-26 北京四方继保工程技术有限公司 基于数字镜像的变电站自动化设备状态诊断方法和系统
CN114418412A (zh) * 2022-01-24 2022-04-29 浙江中烟工业有限责任公司 卷烟厂动力车间设备运维健康评价方法
CN114444972A (zh) * 2022-02-24 2022-05-06 湖南大学 基于图神经网络的电力变压器健康状态评估方法
CN114493334A (zh) * 2022-02-15 2022-05-13 北京航空航天大学宁波创新研究院 电子油泵故障诊断优先级划分方法和系统
CN114580886A (zh) * 2022-03-01 2022-06-03 西南交通大学 一种隧道健康监测方法
CN114638021A (zh) * 2022-03-18 2022-06-17 北京邮电大学 物联网轻量级区块链系统安全性评价方法
CN114662834A (zh) * 2021-11-19 2022-06-24 中国矿业大学 一种矿用带式输送机健康状态在线评估方法
CN114688926A (zh) * 2022-03-22 2022-07-01 中国运载火箭技术研究院 一种运载火箭健康检测验证评估系统和方法
CN114826945A (zh) * 2022-04-27 2022-07-29 浙江广联有线电视传输中心 广电主干网传输系统健康状态评估方法
CN114818270A (zh) * 2022-03-31 2022-07-29 北京航天飞行控制中心 一种遥测重要事件的确定方法和系统
CN114861973A (zh) * 2022-03-24 2022-08-05 三峡大学 一种计及多源因素的风力发电系统风险评估方法
CN114925441A (zh) * 2022-01-30 2022-08-19 中国人民解放军空军工程大学 一种机载分布式phm计算建模方法
CN114925468A (zh) * 2022-05-06 2022-08-19 中国北方车辆研究所 一种基于历史数据的修正系数可靠性分配方法
CN115034364A (zh) * 2022-06-07 2022-09-09 西北工业大学 一种利用ahp与自动编码器的分布式孔径评估方法
CN115049299A (zh) * 2022-07-01 2022-09-13 湖北博华自动化系统工程有限公司 基于报警时间序列的故障诊断与健康评估方法
CN115090514A (zh) * 2022-06-24 2022-09-23 北京建工资源循环利用投资有限公司 一种垃圾筛分系统的控制方法、装置、电子设备及介质
CN115186013A (zh) * 2022-07-25 2022-10-14 中国人民解放军陆军航空兵学院 一种基于航空装备数据采集及分析方法
CN115331403A (zh) * 2022-10-14 2022-11-11 浙江万胜智能科技股份有限公司 一种供电线路的故障数据可视化分析方法及系统
CN115352493A (zh) * 2022-08-26 2022-11-18 交控科技股份有限公司 全线车载控制器系统健康度计算方法及装置
CN115712840A (zh) * 2022-11-15 2023-02-24 中国人民解放军陆军工程大学 一种电子信息系统多故障诊断方法及系统
CN115796623A (zh) * 2023-02-07 2023-03-14 浪潮通用软件有限公司 一种基于物联网的焊机管理评估方法、设备及介质
CN115795922A (zh) * 2023-02-06 2023-03-14 浪潮通用软件有限公司 一种基于设备健康度的设备运行管理方法、系统及介质
CN115893811A (zh) * 2022-12-01 2023-04-04 平华 一种回收玻璃混合加工的热融控制方法及系统
CN115936309A (zh) * 2022-11-29 2023-04-07 青岛理工大学 基于多特征因素集成评价的建筑物健康监测方法及系统
CN115993138A (zh) * 2023-03-23 2023-04-21 中国人民解放军火箭军工程大学 一种多表冗余激光惯组故障诊断方法及系统
CN116071051A (zh) * 2023-04-06 2023-05-05 中国人民解放军火箭军工程大学 惯导系统最优更换时机确定方法、系统、电子设备及介质
CN116086537A (zh) * 2023-02-08 2023-05-09 杭州安脉盛智能技术有限公司 一种设备状态监测方法、装置、设备及存储介质
CN116187725A (zh) * 2023-04-27 2023-05-30 武汉新威奇科技有限公司 一种用于锻造自动线的锻造设备管理系统
CN116351545A (zh) * 2023-04-03 2023-06-30 未必然数据科技(北京)有限公司 一种基于lstm的磨煤机故障预警方法
CN116414360A (zh) * 2023-06-09 2023-07-11 杭州易靓好车互联网科技有限公司 基于人工智能的应用系统集成管理方法及系统
CN116452154A (zh) * 2023-06-14 2023-07-18 北京创客创想科技有限公司 一种适用于通信运营商的项目管理系统
CN117038048A (zh) * 2023-10-09 2023-11-10 江苏优创生物医学科技有限公司 一种用于医疗器械的远程故障处理方法及系统
CN117082462A (zh) * 2023-08-28 2023-11-17 深圳市欣易辰信息科技有限公司 一种短信平台健康监控系统
CN117114248A (zh) * 2023-10-23 2023-11-24 北京万维盈创科技发展有限公司 一种水质监测系统健康度评价方法、计算机设备及介质
CN117155402A (zh) * 2023-10-31 2023-12-01 山东大数据医疗科技有限公司 基于rpa技术的公卫健康智能体检服务系统
CN117192502A (zh) * 2023-11-06 2023-12-08 中华人民共和国连云港海事局后勤管理中心 基于目标雷达的锚泊船只走锚监测系统
CN117275701A (zh) * 2023-11-21 2023-12-22 拓庄医疗科技有限公司 基于人工智能的ct设备故障诊断数据分析系统及方法
CN117390402A (zh) * 2023-12-11 2024-01-12 青岛可颂食品有限公司 一种混合奶油生产管理系统
CN117662510A (zh) * 2024-01-02 2024-03-08 徐州中矿科光机电新技术有限公司 一种风机故障诊断系统及其方法
CN117743805A (zh) * 2024-02-19 2024-03-22 浙江浙能技术研究院有限公司 基于健康度评估反馈的发电机励磁系统分层级判别方法
CN117753182A (zh) * 2023-12-15 2024-03-26 无锡海莱德智能科技有限公司 一种等离子体尾气能源回收系统
CN117875936A (zh) * 2023-12-28 2024-04-12 中国人民解放军陆军装甲兵学院 一种基于不同修理方法的多种装备维修管理系统
CN118051743A (zh) * 2024-04-15 2024-05-17 北京航空航天大学 一种航空发动机气路故障诊断方法和装置
CN118332453A (zh) * 2024-06-12 2024-07-12 西安航天动力研究所 一种液体火箭发动机故障诊断策略的评价方法和系统
CN118378179A (zh) * 2024-06-24 2024-07-23 湖南工程学院 分布式新能源储能网络的优化调控方法
CN118396130A (zh) * 2024-04-12 2024-07-26 中国人民解放军火箭军士官学校 一种基于ibrb的航空继电器故障诊断专家系统鲁棒性分析方法
CN118467949A (zh) * 2024-07-12 2024-08-09 中国铁路设计集团有限公司 电气化铁路供电设备在线诊断数据预处理方法及系统
CN118503769A (zh) * 2024-07-22 2024-08-16 南通盼尔福包装科技有限公司 一种包装打扣机运行故障自动诊断系统
CN118607584A (zh) * 2024-08-06 2024-09-06 烟台初心航空科技有限公司 基于异构网络的雷达健康状态智能预测方法
CN118628098A (zh) * 2024-08-14 2024-09-10 南京南自华盾数字技术有限公司 一种综合能源运维的厂区异常数据监测系统
CN118628095A (zh) * 2024-08-12 2024-09-10 山东京博控股集团有限公司 一种储罐维护策略的自适应制定方法、设备及介质
CN118708944A (zh) * 2024-08-27 2024-09-27 成都易电云商工程服务有限公司 集成局放检测和红外成像的手持智能巡检仪及方法

Families Citing this family (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111553590B (zh) * 2020-04-27 2021-09-24 中国电子科技集团公司第十四研究所 一种雷达嵌入式健康管理系统
CN112325918A (zh) * 2020-10-19 2021-02-05 中国电子科技集团公司第三十八研究所 一种标准仪器的状态预测处理系统
CN112308300A (zh) * 2020-10-19 2021-02-02 中国电子科技集团公司第三十八研究所 一种大型电子产品状态预测管理系统
CN112540358A (zh) * 2020-12-02 2021-03-23 中国电子科技集团公司第三十八研究所 一种基于状态预测的功能自修复雷达系统
CN113434358B (zh) * 2021-04-27 2023-10-13 中国电子科技集团公司第十四研究所 一种软件化雷达信息处理软件的监测方法
CN113110245B (zh) * 2021-05-17 2022-07-22 河南中烟工业有限责任公司 机器人的运行状态监测方法
CN113554224B (zh) * 2021-07-20 2022-11-25 上海航天测控通信研究所 多点统计与健康趋势预测相结合的故障诊断方法和系统
CN113780788B (zh) * 2021-09-02 2024-04-12 青岛联众芯云科技有限公司 一种用于嵌入式设备健康评价的建模方法
CN114481141B (zh) * 2022-02-10 2023-10-13 深圳国能宸泰科技有限公司 海上风电机组阴极保护方法、设备及存储介质
CN114780732B (zh) * 2022-06-22 2022-09-13 天津市天锻压力机有限公司 基于贝叶斯分类模型的锻造液压机预测性维护方法及系统
CN115187927B (zh) * 2022-07-27 2024-03-26 上海志远生态园林工程有限公司 一种观景座椅远程监测管理方法及系统
CN115564298A (zh) * 2022-10-29 2023-01-03 北京远舢智能科技有限公司 产线设备健康度评价方法、系统、智能终端和存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105718327A (zh) * 2016-02-18 2016-06-29 谭晓栋 一种基于测试性模型和贝叶斯推理的故障深度隔离方法
CN107656518A (zh) * 2016-11-30 2018-02-02 中国航空工业集团公司沈阳飞机设计研究所 一种系统故障推理方法
CN110286333A (zh) * 2019-06-18 2019-09-27 哈尔滨理工大学 一种锂动力电池系统故障诊断方法
CN110645153A (zh) * 2018-06-27 2020-01-03 北京金风科创风电设备有限公司 风力发电机组故障诊断方法、装置和电子设备
CN111553590A (zh) * 2020-04-27 2020-08-18 中国电子科技集团公司第十四研究所 一种雷达嵌入式健康管理系统

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102663537A (zh) * 2012-03-13 2012-09-12 凯里供电局 一种基于风险评估的电力设备检修系统
US10151825B2 (en) * 2014-08-15 2018-12-11 Htc Corporation Radar detection system
CN106529581B (zh) * 2016-10-24 2019-08-20 杭州电子科技大学 一种基于贝叶斯网络的桥式起重机故障诊断方法
CN109116319B (zh) * 2018-11-13 2023-02-28 北京无线电测量研究所 雷达系统的故障检测方法
CN109809149B (zh) * 2018-12-17 2020-10-02 北斗天地股份有限公司山东分公司 一种工业生产设备故障预警系统及方法
CN110427015A (zh) * 2019-08-02 2019-11-08 广东职业技术学院 一种锅炉余热爆炸故障诊断分析方法
CN110456199B (zh) * 2019-08-14 2021-03-23 四川大学 一种多传感器系统的剩余寿命预测方法
CN110855521B (zh) * 2019-11-12 2022-06-14 中国电子科技集团公司第十四研究所 基于网络化的测试系统在线监测与故障诊断软件平台

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105718327A (zh) * 2016-02-18 2016-06-29 谭晓栋 一种基于测试性模型和贝叶斯推理的故障深度隔离方法
CN107656518A (zh) * 2016-11-30 2018-02-02 中国航空工业集团公司沈阳飞机设计研究所 一种系统故障推理方法
CN110645153A (zh) * 2018-06-27 2020-01-03 北京金风科创风电设备有限公司 风力发电机组故障诊断方法、装置和电子设备
CN110286333A (zh) * 2019-06-18 2019-09-27 哈尔滨理工大学 一种锂动力电池系统故障诊断方法
CN111553590A (zh) * 2020-04-27 2020-08-18 中国电子科技集团公司第十四研究所 一种雷达嵌入式健康管理系统

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
LYU YONGLE, PANG ZHUO, ZHOU CHUANG, ZHAO PENG: "Prognostics and health management technology for radar system", MATEC WEB OF CONFERENCES, 4 March 2020 (2020-03-04), XP055862204, DOI: 10.1051/matecconf/202030 *

Cited By (87)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114266436A (zh) * 2021-11-10 2022-04-01 上海航天控制技术研究所 星敏感器在轨健康评估方法以及存储介质和电子设备
CN114065109A (zh) * 2021-11-17 2022-02-18 国网浙江省电力有限公司杭州供电公司 一种电力系统需求响应聚合用户的优选方法
CN114662834A (zh) * 2021-11-19 2022-06-24 中国矿业大学 一种矿用带式输送机健康状态在线评估方法
CN114091268A (zh) * 2021-11-24 2022-02-25 南京航空航天大学 一种基于节点重要度与层次分析法的无人机健康状况评估方法
CN114091618A (zh) * 2021-11-30 2022-02-25 重庆允成互联网科技有限公司 工业设备健康状态诊断管理方法、装置及服务器
CN114330006A (zh) * 2021-12-31 2022-04-12 中国电子产品可靠性与环境试验研究所（（工业和信息化部电子第五研究所）（中国赛宝实验室）） 可抑制虚警的多故障诊断的方法、系统及计算机设备
CN114389231A (zh) * 2021-12-31 2022-04-22 广东电网有限责任公司茂名供电局 一种基于配电网保护及设备实时数据的负荷预测诊断方法
CN114400776B (zh) * 2022-01-10 2024-05-10 北京四方继保工程技术有限公司 基于数字镜像的变电站自动化设备状态诊断方法和系统
CN114400776A (zh) * 2022-01-10 2022-04-26 北京四方继保工程技术有限公司 基于数字镜像的变电站自动化设备状态诊断方法和系统
CN114384896A (zh) * 2022-01-12 2022-04-22 北京交通大学 轨道交通列控车载设备模拟电路级健康度预测方法及系统
CN114399220A (zh) * 2022-01-20 2022-04-26 江苏徐工工程机械研究院有限公司 工程机械维修性评价方法和装置、计算机装置和存储介质
CN114418412A (zh) * 2022-01-24 2022-04-29 浙江中烟工业有限责任公司 卷烟厂动力车间设备运维健康评价方法
CN114357893A (zh) * 2022-01-27 2022-04-15 西安交通大学 基于多特征融合som的车载天线传动系统健康评估方法
CN114357893B (zh) * 2022-01-27 2024-04-19 西安交通大学 基于多特征融合som的车载天线传动系统健康评估方法
CN114925441A (zh) * 2022-01-30 2022-08-19 中国人民解放军空军工程大学 一种机载分布式phm计算建模方法
CN114925441B (zh) * 2022-01-30 2024-06-07 中国人民解放军空军工程大学 一种机载分布式phm计算建模方法
CN114493334A (zh) * 2022-02-15 2022-05-13 北京航空航天大学宁波创新研究院 电子油泵故障诊断优先级划分方法和系统
CN114444972A (zh) * 2022-02-24 2022-05-06 湖南大学 基于图神经网络的电力变压器健康状态评估方法
CN114580886A (zh) * 2022-03-01 2022-06-03 西南交通大学 一种隧道健康监测方法
CN114638021A (zh) * 2022-03-18 2022-06-17 北京邮电大学 物联网轻量级区块链系统安全性评价方法
CN114688926B (zh) * 2022-03-22 2024-06-04 中国运载火箭技术研究院 一种运载火箭健康检测验证评估系统和方法
CN114688926A (zh) * 2022-03-22 2022-07-01 中国运载火箭技术研究院 一种运载火箭健康检测验证评估系统和方法
CN114861973A (zh) * 2022-03-24 2022-08-05 三峡大学 一种计及多源因素的风力发电系统风险评估方法
CN114818270A (zh) * 2022-03-31 2022-07-29 北京航天飞行控制中心 一种遥测重要事件的确定方法和系统
CN114818270B (zh) * 2022-03-31 2023-04-07 北京航天飞行控制中心 一种遥测重要事件的确定方法和系统
CN114826945B (zh) * 2022-04-27 2024-01-23 浙江广联有线电视传输中心 广电主干网传输系统健康状态评估方法
CN114826945A (zh) * 2022-04-27 2022-07-29 浙江广联有线电视传输中心 广电主干网传输系统健康状态评估方法
CN114925468A (zh) * 2022-05-06 2022-08-19 中国北方车辆研究所 一种基于历史数据的修正系数可靠性分配方法
CN115034364A (zh) * 2022-06-07 2022-09-09 西北工业大学 一种利用ahp与自动编码器的分布式孔径评估方法
CN115034364B (zh) * 2022-06-07 2024-03-08 西北工业大学 一种利用ahp与自动编码器的分布式孔径评估方法
CN115090514A (zh) * 2022-06-24 2022-09-23 北京建工资源循环利用投资有限公司 一种垃圾筛分系统的控制方法、装置、电子设备及介质
CN115049299A (zh) * 2022-07-01 2022-09-13 湖北博华自动化系统工程有限公司 基于报警时间序列的故障诊断与健康评估方法
CN115186013A (zh) * 2022-07-25 2022-10-14 中国人民解放军陆军航空兵学院 一种基于航空装备数据采集及分析方法
CN115352493B (zh) * 2022-08-26 2024-04-26 交控科技股份有限公司 全线车载控制器系统健康度计算方法及装置
CN115352493A (zh) * 2022-08-26 2022-11-18 交控科技股份有限公司 全线车载控制器系统健康度计算方法及装置
CN115331403A (zh) * 2022-10-14 2022-11-11 浙江万胜智能科技股份有限公司 一种供电线路的故障数据可视化分析方法及系统
CN115331403B (zh) * 2022-10-14 2023-04-28 浙江万胜智能科技股份有限公司 一种供电线路的故障数据可视化分析方法及系统
CN115712840B (zh) * 2022-11-15 2023-06-13 中国人民解放军陆军工程大学 一种电子信息系统多故障诊断方法及系统
CN115712840A (zh) * 2022-11-15 2023-02-24 中国人民解放军陆军工程大学 一种电子信息系统多故障诊断方法及系统
CN115936309B (zh) * 2022-11-29 2024-02-13 青岛理工大学 基于多特征因素集成评价的建筑物健康监测方法及系统
CN115936309A (zh) * 2022-11-29 2023-04-07 青岛理工大学 基于多特征因素集成评价的建筑物健康监测方法及系统
CN115893811A (zh) * 2022-12-01 2023-04-04 平华 一种回收玻璃混合加工的热融控制方法及系统
CN115795922A (zh) * 2023-02-06 2023-03-14 浪潮通用软件有限公司 一种基于设备健康度的设备运行管理方法、系统及介质
CN115796623B (zh) * 2023-02-07 2023-05-05 浪潮通用软件有限公司 一种基于物联网的焊机管理评估方法、设备及介质
CN115796623A (zh) * 2023-02-07 2023-03-14 浪潮通用软件有限公司 一种基于物联网的焊机管理评估方法、设备及介质
CN116086537A (zh) * 2023-02-08 2023-05-09 杭州安脉盛智能技术有限公司 一种设备状态监测方法、装置、设备及存储介质
CN115993138A (zh) * 2023-03-23 2023-04-21 中国人民解放军火箭军工程大学 一种多表冗余激光惯组故障诊断方法及系统
CN116351545A (zh) * 2023-04-03 2023-06-30 未必然数据科技(北京)有限公司 一种基于lstm的磨煤机故障预警方法
CN116071051A (zh) * 2023-04-06 2023-05-05 中国人民解放军火箭军工程大学 惯导系统最优更换时机确定方法、系统、电子设备及介质
CN116187725B (zh) * 2023-04-27 2023-08-04 武汉新威奇科技有限公司 一种用于锻造自动线的锻造设备管理系统
CN116187725A (zh) * 2023-04-27 2023-05-30 武汉新威奇科技有限公司 一种用于锻造自动线的锻造设备管理系统
CN116414360A (zh) * 2023-06-09 2023-07-11 杭州易靓好车互联网科技有限公司 基于人工智能的应用系统集成管理方法及系统
CN116414360B (zh) * 2023-06-09 2023-10-03 杭州易靓好车互联网科技有限公司 基于人工智能的应用系统集成管理方法及系统
CN116452154A (zh) * 2023-06-14 2023-07-18 北京创客创想科技有限公司 一种适用于通信运营商的项目管理系统
CN116452154B (zh) * 2023-06-14 2023-09-05 北京创客创想科技有限公司 一种适用于通信运营商的项目管理系统
CN117082462B (zh) * 2023-08-28 2024-05-07 深圳市欣易辰信息科技有限公司 一种短信平台健康监控系统
CN117082462A (zh) * 2023-08-28 2023-11-17 深圳市欣易辰信息科技有限公司 一种短信平台健康监控系统
CN117038048B (zh) * 2023-10-09 2023-12-26 江苏优创生物医学科技有限公司 一种用于医疗器械的远程故障处理方法及系统
CN117038048A (zh) * 2023-10-09 2023-11-10 江苏优创生物医学科技有限公司 一种用于医疗器械的远程故障处理方法及系统
CN117114248A (zh) * 2023-10-23 2023-11-24 北京万维盈创科技发展有限公司 一种水质监测系统健康度评价方法、计算机设备及介质
CN117114248B (zh) * 2023-10-23 2024-01-19 北京万维盈创科技发展有限公司 一种水质监测系统健康度评价方法、计算机设备及介质
CN117155402A (zh) * 2023-10-31 2023-12-01 山东大数据医疗科技有限公司 基于rpa技术的公卫健康智能体检服务系统
CN117155402B (zh) * 2023-10-31 2024-02-09 山东大数据医疗科技有限公司 基于rpa技术的公卫健康智能体检服务系统
CN117192502A (zh) * 2023-11-06 2023-12-08 中华人民共和国连云港海事局后勤管理中心 基于目标雷达的锚泊船只走锚监测系统
CN117192502B (zh) * 2023-11-06 2024-01-26 中华人民共和国连云港海事局后勤管理中心 基于目标雷达的锚泊船只走锚监测系统
CN117275701A (zh) * 2023-11-21 2023-12-22 拓庄医疗科技有限公司 基于人工智能的ct设备故障诊断数据分析系统及方法
CN117275701B (zh) * 2023-11-21 2024-02-02 拓庄医疗科技有限公司 基于人工智能的ct设备故障诊断数据分析系统及方法
CN117390402A (zh) * 2023-12-11 2024-01-12 青岛可颂食品有限公司 一种混合奶油生产管理系统
CN117390402B (zh) * 2023-12-11 2024-03-08 青岛可颂食品有限公司 一种混合奶油生产管理系统
CN117753182A (zh) * 2023-12-15 2024-03-26 无锡海莱德智能科技有限公司 一种等离子体尾气能源回收系统
CN117875936A (zh) * 2023-12-28 2024-04-12 中国人民解放军陆军装甲兵学院 一种基于不同修理方法的多种装备维修管理系统
CN117875936B (zh) * 2023-12-28 2024-06-11 中国人民解放军陆军装甲兵学院 一种基于不同修理方法的多种装备维修管理系统
CN117662510A (zh) * 2024-01-02 2024-03-08 徐州中矿科光机电新技术有限公司 一种风机故障诊断系统及其方法
CN117662510B (zh) * 2024-01-02 2024-06-07 徐州中矿科光机电新技术有限公司 一种风机故障诊断系统及其方法
CN117743805B (zh) * 2024-02-19 2024-04-30 浙江浙能技术研究院有限公司 基于健康度评估反馈的发电机励磁系统分层级判别方法
CN117743805A (zh) * 2024-02-19 2024-03-22 浙江浙能技术研究院有限公司 基于健康度评估反馈的发电机励磁系统分层级判别方法
CN118396130A (zh) * 2024-04-12 2024-07-26 中国人民解放军火箭军士官学校 一种基于ibrb的航空继电器故障诊断专家系统鲁棒性分析方法
CN118051743A (zh) * 2024-04-15 2024-05-17 北京航空航天大学 一种航空发动机气路故障诊断方法和装置
CN118332453A (zh) * 2024-06-12 2024-07-12 西安航天动力研究所 一种液体火箭发动机故障诊断策略的评价方法和系统
CN118378179A (zh) * 2024-06-24 2024-07-23 湖南工程学院 分布式新能源储能网络的优化调控方法
CN118467949A (zh) * 2024-07-12 2024-08-09 中国铁路设计集团有限公司 电气化铁路供电设备在线诊断数据预处理方法及系统
CN118503769A (zh) * 2024-07-22 2024-08-16 南通盼尔福包装科技有限公司 一种包装打扣机运行故障自动诊断系统
CN118607584A (zh) * 2024-08-06 2024-09-06 烟台初心航空科技有限公司 基于异构网络的雷达健康状态智能预测方法
CN118628095A (zh) * 2024-08-12 2024-09-10 山东京博控股集团有限公司 一种储罐维护策略的自适应制定方法、设备及介质
CN118628098A (zh) * 2024-08-14 2024-09-10 南京南自华盾数字技术有限公司 一种综合能源运维的厂区异常数据监测系统
CN118628098B (zh) * 2024-08-14 2024-10-08 南京南自华盾数字技术有限公司 一种综合能源运维的厂区异常数据监测系统
CN118708944A (zh) * 2024-08-27 2024-09-27 成都易电云商工程服务有限公司 集成局放检测和红外成像的手持智能巡检仪及方法

Also Published As

Publication number Publication date
CN111553590A (zh) 2020-08-18
CN111553590B (zh) 2021-09-24

Similar Documents

Publication Publication Date Title
WO2021218003A1 (fr) Système de gestion de santé intégré à un radar
CN111539515B (zh) 一种基于故障预测的复杂装备维修决策方法
US20050060323A1 (en) Diagnosis of equipment failures using an integrated approach of case based reasoning and reliability analysis
CN111624986A (zh) 基于案例库的故障诊断方法和系统
CN113343581B (zh) 基于图马尔可夫神经网络的变压器故障的诊断方法
CN113485305B (zh) 一种飞机外勤故障诊断系统与方法
CN113254249A (zh) 冷站故障分析方法、装置、及存储介质
CN111915192A (zh) 电力设备故障管理系统的建立方法和系统、计算机设备
CN112818525A (zh) 一种水电机组状态评价方法及其系统
CN117689373A (zh) 一种柔性直流牵引供电系统能量路由器维护决策支持方法
CN115688016A (zh) 一种用于大型数据库智能运维的一体化方法
CN116823008A (zh) 一种园区能源利用效率评估方法、系统、设备和存储介质
CN112990703A (zh) 国际工程市场匹配度评价方法、电子设备及存储介质
CN116452154B (zh) 一种适用于通信运营商的项目管理系统
CN115114124A (zh) 主机风险的评估方法及评估装置
CN111126750B (zh) 一种关键单元确定方法、装置和存储介质
CN114091618A (zh) 工业设备健康状态诊断管理方法、装置及服务器
CN113872780A (zh) 一种故障根因分析方法、装置及存储介质
CN112380641A (zh) 一种应急柴油机健康状态评价方法及计算机终端
Tarba et al. Analysis on quality of diagnostic processes in power electrical engineering using combined methods of lead six sigma and fuzzy approaches
CN118467523B (zh) 针对配电网量测装置的量测数据质量评价方法及系统
CN118469405B (zh) 家居供应链数据的处理方法、装置、设备及存储介质
Nakamura Predicting Time-to-Failure of Industrial Machines with Temporal Data Mining
CN114393994B (zh) 一种电动化底盘多目标协同健康管理方法及系统
CN118394561B (zh) 服务器故障的诊断方法、装置、存储介质及电子设备

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20933002

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20933002

Country of ref document: EP

Kind code of ref document: A1