101 results about "Reliability model" patented technology

The invention belongs to the technical field of wind turbine generator maintenance, and particularly relates to an offshore wind turbine generator two-stage rolling maintenance method considering subsystem correlation, which comprises the following steps: S1, constructing a comprehensive reliability model; s2, taking the minimization of the total maintenance cost in the operation cycle of the wind turbine generator as a target, and forming a target optimization problem based on the comprehensive reliability model; solving the target optimization problem to form a first-stage long-term maintenance strategy; s3, when an operation window meeting the storm accessibility condition appears, determining a subsystem of which the current reliability is lower than a preventive maintenance threshold value; s4, the opportunity maintenance benefit ratio is calculated, and if the opportunity maintenance benefit ratio is larger than a processing threshold value, advanced maintenance of the subsystem is triggered; and S5, after the advanced maintenance is executed each time, the optimal preventive maintenance time point is solved again so as to dynamically update the subsequent maintenance plan. According to the method, the fault coupling and degradation evolution law between subsystems can be accurately described, and the storm accessibility window is actively utilized to dynamically adjust the maintenance plan.

The invention relates to the technical field of parameter extraction, and provides a reliability parameter extraction method based on a Lifetime equation and parameter mapping, and the method comprises the steps: S1, building a Lifetime degradation formula, and obtaining a Lifetime model capable of describing the degradation trend of a device based on a physical mechanism of the device; s2, judging whether a user has a parameter mapping formula or not, if so, extracting degradation parameters through an automatic reliability parameter extraction tool and a customized reliability model interface, and entering step S5; s3, if the user does not have the parameter mapping formula, collecting degradation data and extracting a parameter degradation curve through an automatic parameter extraction tool; s4, selecting a machine learning model to obtain a parameter mapping relationship, fusing physical constraints, taking a known physical relationship as an initial item input model, obtaining a reliability formula, and then entering the step S2; and S5, extracting a formula and verifying the formula, evaluating prediction precision in a test set, and performing extrapolation verification under a stress condition outside a training data range. The parameter degradation modeling time can be shortened, and the automatic parameter extraction efficiency can be improved.

The invention relates to a numerical control machine tool reliability modeling method and system considering a fault trend. The method comprises the following steps: checking the homogeneity of a numerical control machine tool based on the fault trend; constructing an AMSAA model of the multiple samples subjected to truncation at unequal time; evaluating the precision of the reliability model; aiming at the problem of insufficient reliability model precision of a multi-sample condition of a numerical control machine tool, a multi-sample AMSAA model modeling method of the numerical control machine tool considering a fault trend is provided, sample data classification is carried out through trend inspection and homotype inspection, and fault data of same-type machine tools are preprocessed by adopting a fault total time method; adopting a maximum likelihood method to estimate AMSAA model parameters of the same-type machine tool, and using Cramer-Von Mises to test the goodness of fit of the model; evaluating the precision of the reliability model by taking an average absolute percentage error (MAPE) of an instantaneous MTBF point estimation value and an MTBF observation value as an index; compared with a multi-sample AMSAA model established by a direct maximum likelihood method, the method is higher in prediction precision.

The application relates to a failure prediction maintenance method and device with a preventable strategy, and relates to the field of equipment prediction and maintenance technology. In view of the problems in the prior art that a traditional two-state reliability model is difficult to accurately describe the degradation degree, failure condition and maintenance state of a system in a service life, the calculation process is relatively single, and the result error is relatively large, the technical scheme is as follows: the failure prediction maintenance method with the preventable strategy comprises the following steps: collecting a probability distribution obeyed by the residual life of a system; collecting maintenance time and maintenance cost; establishing an optimization model; iteratively processing the model to obtain an optimal failure prediction interval and a residual life threshold value; when the optimal failure prediction interval is reached, the residual life of the system is predicted, the residual life is compared with the threshold value, and if the residual life is lower than the threshold value, the system is subjected to corrective maintenance, and if the residual life is higher than the threshold value, the system is subjected to preventive maintenance. The application is suitable for application in preventive maintenance work, and establishes a new research basis for the research of preventive maintenance work.

This invention provides a high-end scientific instrument reliability analysis and design method based on SysML, belonging to the field of instrument reliability analysis technology. The method includes: constructing a system model of the target instrument using SysML, the system model including a requirements diagram, internal block diagram, and attribute library; extracting all failure modes from all failure mode libraries and assigning them global numbers to establish a failure mode mapping matrix; performing failure mode and impact analysis (FMEA) for the target instrument based on the system model to obtain a failure mode and impact analysis table; establishing a parameterized reliability model for each functional path; calculating the reliability constraints of each functional path based on the system model and the impact analysis table; and performing reliability analysis based on the measured attributes and reliability constraints of sub-components to generate an optimization scheme. The advantages of this invention are improved accuracy, consistency, and automation of reliability analysis.

The invention discloses an underwater vehicle control system competitive failure reliability evaluation method, belongs to the technical field of underwater vehicle reliability evaluation, and is used for evaluating the underwater vehicle control system competitive failure reliability and preprocessing multi-source monitoring of an underwater vehicle control system. Constructing an underwater vehicle control system reliability model; constructing a non-time-delay parameter and a time-delay related parameter, and calculating estimated values of the non-time-delay parameter and the time-delay related parameter by using a least square method, a statistical inference method and a time-delay structure identification method; and introducing an alternating iterative optimization mechanism to carry out parameter estimation, and calculating the reliability of the underwater vehicle control system. According to the method, accurate modeling and reliability evaluation of the competitive failure degradation process and the impact coupling effect of the underwater vehicle control system are realized by constructing a dynamic adaptive feature extraction model and a time-delay related degradation theory and adopting a parameter estimation and alternate iteration optimization strategy.

A closed-loop selective attention system for resolving conflicts in multi-source or multi-speaker environments, including a plurality of internal attention models, each outputting a probability distribution over candidate sources and an associated confidence score, a fuser detecting conflicts when two or more of said attention models output high-confidence predictions that disagree, a selective sampling policy querying one or more external agents, wherein each external agent possesses a knowledge base, a reliability model, and a communication protocol, a trust and reliability module assigning and updating dynamic trust scores for internal and external agents based on past performance, an efficiency optimizer minimizing communication overhead and decision delay by balancing token usage cost and latency cost, and a dynamical system formulator ensuring convergence of the conflict resolution process under bounded trust, decaying step size, and limited sampling.

The invention discloses an open source big data system software reliability model with fault removal efficiency obeying Weibull distribution, and belongs to the technical field of software reliability analysis. Performance fitting and prediction experiments are carried out through eight fault data sets and nine software reliability models, 95% confidence interval analysis is carried out, and results show that the model provided by the invention has better fault fitting and fault prediction performance than other models. The model provided by the invention can effectively and accurately evaluate the reliability of the open source big data system software, and has certain guiding significance for actual software development and testing.

The invention provides an unmanned system cluster task importance analysis method based on task reliability. The method comprises the following steps: constructing a task scene through unmanned system cluster constituent elements; based on the task scene, performing task reliability calculation according to the unmanned system cluster constituent elements to obtain an unmanned system cluster task reliability model; performing importance calculation on the unmanned system cluster task reliability model through an equipment state and a cluster killing chain to obtain an unmanned system cluster task importance analysis model; and performing maintenance optimization sorting according to the unmanned system cluster task reliability model and the unmanned system cluster task importance analysis model to obtain an unmanned system cluster optimization strategy. According to the method, reliability and importance analysis is carried out on the unmanned system cluster, and key task node identification and maintenance priority ranking are realized, so that the task execution flexibility, robustness and cost effectiveness of the unmanned system are remarkably improved.

The application discloses a kind of dynamic multi-energy coupling and conversion comprehensive energy system reliability evaluation method.Establish the multi-state reliability model of multi-energy production element considering dynamic multi-energy coupling, establish the multi-state reliability model of multi-energy conversion element considering dynamic multi-energy conversion, establish the multi-state reliability model of multi-energy transmission element considering dynamic multi-energy coupling, according to the multi-state reliability model of three kinds of elements, the multi-state reliability model of three kinds of subsystems is constructed;According to the multi-state reliability model of three kinds of subsystems, the reliability of comprehensive energy system considering multi-energy coupling and conversion is obtained by using improved general production function method, and reliability evaluation is realized.The dynamic characteristics of the comprehensive energy system can be more accurately characterized by using the multi-state model, and the reliability of the comprehensive energy system that meets the accuracy requirements is accurately calculated.

The application discloses a kind of multi-energy coupling and conversion comprehensive energy system multi-state reliability evaluation method.Establish the multi-state reliability model of multi-energy conversion element considering multi-energy conversion, using clustering algorithm reliability aggregation, and mapping formation aggregated multi-state reliability model;Multi-state reliability model of multi-energy coupling element considering multi-energy coupling is established, and then using Gaussian approximation and sampling approximation reliability approximation processing in sequence obtains multi-state approximate reliability model;The aggregated multi-state reliability model and multi-state approximate reliability model are processed according to the fast reliability evaluation method to obtain the reliability of the comprehensive energy system, and the reliability evaluation is realized.The application improves the traditional reliability evaluation method from time and accuracy, reduces the calculation time, and quickly and effectively realizes the estimation of system reliability.

This invention discloses a method for generating operation and maintenance schemes for deep-water explosive containers based on generative adversarial networks (CGANs), relating to the field of deep-water explosive container safety operation and maintenance technology. Based on the maximum strain prediction value output by the optimal GRU strain prediction model, the fuzziness of material performance parameters is first processed using a fuzzy interval reliability model to obtain a reliability interval. Then, using this reliability interval as input, a random interval hybrid reliability model is combined to fuse the randomness of the predicted strain, calculating a reliability index η used to quantify the container's safety status. This invention generates virtual data that conforms to the real distribution and has physical rationality through conditional generative adversarial networks (CGANs), effectively compensating for the lack of historical data under extreme conditions such as high explosive dosage and high water pressure, enhancing the generalization ability of data-driven models, and significantly improving strain prediction accuracy in scarce sample intervals.

The application discloses a kind of based on digital twinning unmanned mine car reliability rapid early warning method, system, it is related to unmanned mine car technical field, including the following steps: the digital twin simulation model of unmanned mine car is constructed;Based on the digital twin simulation model, the digital twin reliability model that the reliability state change of each module of the unmanned mine car is characterized is constructed;Based on the measured data of the unmanned mine car, the consistency of the digital twin simulation model and the digital twin reliability model is judged, and after judging consistent, reliability state database is constructed;Based on the reliability state database, digital twin reliability rapid early warning model is obtained by training, and the early warning model is used to identify and output the current reliability state of the unmanned mine car according to real-time acquisition vehicle-mounted sensor observation data, to realize early warning.The reliability state of each subsystem and module of unmanned mine car is rapidly and accurately warned.

The invention belongs to the technical field of reliability modeling of fiber-optic gyroscopes, and particularly relates to a definite reliability modeling and analysis method of a high-precision fiber-optic gyroscope, which is based on performance margin and considers a degradation mechanism and uncertainty, and can accurately evaluate the reliability of the fiber-optic gyroscope. The problem that degradation and uncertainty are not considered in the prior art is solved. The method comprises the following steps: S1, performing function, performance and margin analysis on the fiber-optic gyroscope, and determining key performance parameters and threshold values of the fiber-optic gyroscope; determining the type of the key performance parameter in combination with the threshold value of the key performance parameter and a product design specification; s2, aiming at key performance parameters of the fiber-optic gyroscope, establishing a disciplinary cross equation of performance, internal dependent variables, external dependent variables and reversible time; s3, establishing a corresponding margin equation according to the type of the key performance parameter; s4, constructing a performance margin degradation equation based on the margin equation; and S5, on the basis of a performance margin degradation equation, considering internal and external cause uncertainty, and further constructing a definite reliability model.

The application discloses a kind of multi-stage system task reliability modeling evaluation methods considering complex dynamic characteristics, belong to system reliability modeling and evaluation technical field, including: according to the structure of system component unit, function principle and task flow, establish system function model and stage model;Based on the finite state machine with constraint, the state-transition model of each structure component unit is established respectively;According to the task activity of each stage and the success and failure criterion of task, the task flow model of system in the corresponding stage is constructed;Integrate the above steps, obtain the reliability model of multi-stage task, carry out task reliability simulation, calculate the occurrence probability of the structure component unit state or structure component unit state combination concerned.This application guarantees the efficient and stable operation of complex dynamic multi-stage system.

A method for generating a training data set includes receiving, by a processing circuit, warranty claim data associated with one or more building devices or building device components; processing, by the processing circuit, the warranty claim data using natural language processing to generate a training data set comprising one or more causes and solutions associated with failure of the one or more building devices or the building device components; and training, by the processing circuit, a component reliability model using the training data set to produce a trained model.

The invention provides a fastening connection system reliability dynamic modeling method which comprises the following steps: establishing a reliability model of fracture failure and loosening failure of a single threaded connection pair to obtain the reliability of the single threaded connection pair in different failure modes; based on a multi-competitive failure mode of a single threaded connection pair, establishing a dynamic reliability model of the fastening connection system under consideration of dynamic degradation by introducing an exponential decay model; wherein the exponential decay model is used for representing the decay process of the bolt pre-tightening force and strength along with time; and constructing a general generation function of each threaded connection pair for performing dynamic reliability calculation on the dynamic reliability model of the fastening connection system, and determining an optimal maintenance interval. According to the method, the multi-competition failure problem of fracture failure and loosening failure of a single threaded connection layer is effectively solved, the method better conforms to engineering practice, calculation is convenient and easy, implementation is easy, and engineering technicians can conveniently master the method.

A method and system are provided for monitoring operation and predicting service life of an active suspension system or another component or assembly. Sensor data representing operating conditions such as pressure, current, temperature, or actuator position are processed to generate usage indicators derived from binned or weighted values according to a damage function reflecting stress intensity or the frequency of high-load events. Usage indicators may be stored locally or in a cloud-based database and used by a controller to estimate component degradation or remaining service life in real time or retrospectively, and to communicate maintenance recommendations or update reliability models.

The invention discloses a whole life cycle carbon emission prediction method for a solid waste-based concrete structure, and the method comprises the steps: extracting historical production process characteristics, calculating historical production process carbon emission, building a production process carbon emission prediction model, and obtaining a production process carbon emission prediction amount. The method comprises the following steps: constructing a solid waste cementing material service performance evolution function and a full-life-cycle material reliability model, determining aging repair times, calculating a service process carbon emission predicted quantity, extracting historical dismantling process characteristics, calculating historical dismantling process carbon emission, and constructing a dismantling process carbon emission prediction model to obtain a dismantling process carbon emission predicted quantity. And determining the full-life-cycle carbon emission predicted quantity of the solid waste-based concrete structure. According to the method, not only is the crossing from static evaluation to dynamic prediction and from segmented calculation to full-period integration realized, but also an accurate and reliable quantification tool and decision support are provided for low-carbon design, material optimization and sustainable operation and maintenance of the solid waste-based concrete structure.

The invention belongs to the technical field of offshore wind power operation and maintenance and reliability engineering, and discloses an offshore wind turbine generator system-level health degree evaluation method based on dynamic weight distribution, and the method comprises the following steps: S1, collecting and preprocessing the multi-source data of an offshore wind turbine generator; s2, constructing a layered health degree evaluation index system; s3, fusing the mechanism model, the data driving model and the statistical reliability model, and constructing a subsystem degradation model to obtain a subsystem health degree; s4, performing weight fusion in combination with the static weight and the dynamic correction factor to obtain a dynamic weight; s5, fusing the subsystem health degree and the dynamic weight to obtain a system-level health degree; and S6, performing confidence interval sorting and risk grade division according to the system-level health degree. According to the evaluation method provided by the invention, through fusion of a mechanism model, a data driving model and a statistics model, the physical interpretability is reserved, the fitting capability of nonlinearity and coupling degradation is improved, and the misjudgment and missed judgment risks are reduced.

The present invention belongs to the technical field of applications of heterogeneous multi-core systems, in particular relates to a task scheduling method capable of realizing energy consumption sensing under reliability constraints. The method comprises: constructing a heterogeneous multi-core system model, comprising a task model, an energy consumption model and a reliability model; on the basis of the heterogeneous multi-core system model, determining the execution priority of a task; performing first-stage task duplication on the task, ensuring that the reliability value of each subtask is higher than a system reliability requirement, and obtaining the initial number of copies of the task; if an actual reliability value of a system is less than the system reliability requirement, performing second-stage task duplication on the task, so as to obtain the final number of copies of the task; and on the basis of the execution priority of the task, assigning all the copies of the task to corresponding processor cores, and then on the basis of DPM technique use conditions, switching the processor cores from an idle mode to a sleep mode, so as to reduce power consumption. The present invention realizes the joint optimization scheduling for a heterogeneous multi-core system with respect to reliability and low power consumption, and has wide application prospects in heterogeneous multi-core systems.

The invention relates to the technical field of constellation system optimization, and provides an optimization design method, system, equipment and medium for a constellation system, and the method comprises the steps: respectively building reliability models of a satellite and the constellation system for two schemes, obtaining key parameters, inputting parameters, and calculating the system reliability and total cost of a product-level backup scheme; based on the reliability of the product-level backup scheme, the system reliability and total cost of the satellite-level backup scheme are calculated, the reliability and cost advantages of the satellite-level backup scheme are verified by comparing the total cost of the two schemes, and an optimal target scheme is output according to the reliability and cost advantages. The reliability mathematical model is established, the appropriate number of satellites required by the constellation satellite-level redundancy scheme with the reliability better than that of a constellation satellite product-level redundancy scheme is accurately calculated, and under the condition, the total cost of the satellite-level backup scheme is compared with the total cost of the product-level backup scheme, so that the reliability of the constellation satellite-level redundancy scheme is improved. Therefore, the optimal backup strategy scheme of the satellite constellation system is searched.

This invention discloses a probabilistic-nonprobabilistic-probabilistic box hybrid reliability model and solution method. It employs truncated probability variables to describe uncertain parameters with sufficient samples in the structure; nonprobabilistic interval variables to describe uncertain parameters with insufficient sample numbers in the structure; and probabilistic box variables to describe uncertain parameters with both cognitive and random uncertainties. Based on interval analysis of interval variables, a decoupling method for probabilistic box variables is proposed, and then the double-nested problem is optimized and solved. A hybrid reliability index is introduced to represent the hybrid reliability analysis results, and a hybrid optimization algorithm combining an outer genetic algorithm and an inner interior point method is used to solve the problem, avoiding solution errors caused by getting trapped in local optima. Finally, the failure probability interval and the corresponding hybrid reliability index interval are obtained.

According to the reliability distribution method and system considering the design margin and the development cost, the margin coefficient is introduced in the reliability design stage while economic indexes are considered, the average life-cost model of parts is constructed, and the reliability model of complex equipment is constructed based on the Bayesian network. On the premise that the task reliability requirement of considering the design margin is met, an optimization model of reliability distribution considering the design margin is established by taking the minimization of the total development cost as an optimization target, the optimal balance point of reliability and cost is searched based on the Monte Carlo random algorithm, and the reliability distribution optimization model of the design margin is established. And generating an optimal reliability allocation scheme of the complex equipment which meets the task reliability requirement and has the minimum development cost. According to the method, the overall reliability of the complex equipment is ensured, meanwhile, the proper design margin is reserved to cope with possible improvement or uncertainty factors in the future, effective control over the cost and reasonable distribution of the design margin are achieved, and the market competitiveness of the complex equipment and the use satisfaction degree of users can be improved.

The application provides a shipborne electronic compact system reliability index verification method and system, and a storage medium. The shipborne electronic compact system reliability index verification method comprises the following steps: acquiring basic information of a shipborne electronic compact system; acquiring external input requirements of the shipborne electronic compact system; judging whether reliability evaluation is needed according to the external input requirements; when the reliability evaluation is not needed, performing reliability index verification based on an L-M method; when the reliability evaluation is needed, judging whether a reliability distribution result is confirmed by review; when the reliability distribution result is not confirmed by review, performing reliability index verification based on a compact ratio K; and when the reliability distribution result is confirmed by review, performing reliability index verification based on a reliability model backstepping. Through the technical scheme, the product reliability index verification is completed, the test time is shortened, the test cost of a research and development unit is reduced, and the research and development progress of equipment is ensured.

The invention discloses a distributed intelligent power distribution network reliability influence factor analysis method and system, and relates to the technical field of influence factor analysis, and the method comprises the following steps: obtaining the operation state of a power distribution network in a target region, and constructing a topology-control mode table; performing uncertainty labeling on the key equipment to form a structural uncertainty matrix; coupling the structural uncertainty matrix with node operation data, establishing a reliability model, calculating the sensitivity of each uncertain structural unit to the reliability index of the whole system, and generating a structural sensitivity vector; and combining the structural sensitivity vector with real-time operation data to form a dynamic reliability influence factor table, and constructing a topology-control mode table. According to the method, the dynamic reliability influence factor table is generated by establishing the structure-state coupling reliability model, so that the problem that key influence factors are inaccurately identified due to the fact that the influence of topological change and control mode switching on the system reliability is not comprehensively considered in the prior art is solved.

The invention provides an HMM (Hidden Markov Model)-based fan generator reliability modeling and residual life prediction method under impact influence, and belongs to the technical field of fan reliability evaluation. Comprising the following steps: fitting an equipment performance degradation function according to state monitoring data of a component, and updating a traditional hidden Markov model HMM into a hidden Markov model DHMM related to performance degradation by using a degradation law to obtain a time sequence state transition probability matrix with degradation characteristics; introducing the influence of random impact into the state transition probability to obtain a state transition probability matrix of each stage in the DHMM under the impact influence; reliability modeling: constructing a soft failure reliability model; building a soft failure reliability model under the impact influence; constructing a hard failure reliability model under the impact influence; building a competitive failure reliability model under impact influence; performing RUL prediction; according to the method provided by the invention, the reliability evaluation and the RUL prediction result can better conform to the actual operation condition.

The invention relates to a process reliability modeling method for boring a connecting rod, and relates to the technical field of manufacturing processes. The method comprises the following steps: acquiring a pre-constructed connecting rod boring process simulation model, wherein the connecting rod boring process simulation model is used for representing the interaction of a plurality of model parameters in a boring process; determining an input parameter matrix of the connecting rod boring process simulation model, and executing a simulation task based on the input parameter matrix to obtain an output result matrix; constructing a process reliability model based on the input parameter matrix and the output result matrix; obtaining a to-be-tested input parameter, and determining a prediction result matrix corresponding to the to-be-tested input parameter based on the process reliability model; and determining the process reliability and local sensitivity of the connecting rod boring process according to the prediction result matrix. The simulation model constructed by the invention can comprehensively represent the interaction effect of each failure factor in the boring process; and prediction of processing reliability under complex working conditions can be realized.

The present application relates to the technical field of pipeline structure reliability analysis, in particular to a pipeline structure reliability analysis method under interval uncertainty, comprising: collecting basic parameters affecting the vibration fatigue life of the pipeline structure; establishing a function function in reliability analysis; standardizing the input vector and the function function; establishing a reliability model of the pipeline structure under interval uncertainty with the standard function function as a constraint; introducing an intermediate variable for equivalent conversion; solving by using the dichotomy combined with the random search feasibility judgment method to obtain the reliability index of the pipeline structure. The present application solves the problems of difficulty in solving the black box function and difficulty in ensuring global convergence in the vibration fatigue life analysis of the engine pipeline structure by using the interval reliability analysis framework of the dichotomy combined with the random search feasibility judgment.

The invention discloses a capacity optimization configuration method and system for an electrochemical energy storage power station of an urban guaranteed power grid, and solves the technical problem that the quality of a finally generated configuration scheme is poor due to the fact that the capacity scale is determined only from a single dimension in the current optimization configuration research aiming at the planning of the electrochemical energy storage power station. The method comprises the following steps: when the capacity optimization configuration of the electrochemical energy storage power station of the urban guaranteed power grid needs to be carried out, constructing a target function by taking the full-life-cycle economic benefit maximization of the electrochemical energy storage power station as a target, and constructing constraint conditions in combination with parameters of energy storage equipment; constructing an electrochemical energy storage power station reliability model according to energy storage power station component parameters, power grid topological data and disaster related data; solving capacity configuration by using a particle swarm algorithm, and generating target optimal electrochemical energy storage power station capacity configuration parameters; and finally, based on the model, generating a target electrochemical energy storage power station capacity configuration scheme in combination with an urban guaranteed power grid architecture.