11 results about "Reliability methods" patented technology

The invention discloses an offshore wind turbine supporting structure reliability evaluation method based on a reduced-order digital twin model, and the method comprises the steps: obtaining the response data of an offshore wind turbine supporting structure through multi-dimensional load analysis; and finally, setting a limit state function of the offshore wind turbine support structure in an extreme state, and calculating the failure probability of the offshore wind turbine support structure through a first-order reliability method under the condition of combining response data of the offshore wind turbine support structure so as to evaluate the reliability of the offshore wind turbine support structure. According to the method, the problems of insufficient model precision, calculation efficiency bottleneck, reliability evaluation limitation and the like of an existing reliability evaluation method for the offshore wind turbine supporting structure can be solved, and the requirements of offshore wind power engineering for high precision, high efficiency and comprehensiveness of reliability evaluation of the supporting structure can be met.

The invention discloses a decoupling design method and system for reliability optimization of an angular contact ball bearing. The method comprises the following steps: determining initial design parameters of the angular contact ball bearing; constructing a reliability optimization design model which takes maximization of the rated dynamic load as a target and comprises probability reliability constraint processed by a penalty function; constructing a design variable and failure probability mapping agent model, specifically, identifying and quantifying uncertainty parameters, constructing a quasi-statics model and a limit state function, calculating the failure probability of a sample point through a probability reliability method, and training the agent model taking the design variable as input and the failure probability as output; and based on the proxy model, solving the reliability optimization design model by using an optimization algorithm, and outputting optimal bearing design parameters. According to the method, the reliability analysis process and the optimization iteration process are decoupled, so that the optimization efficiency is greatly improved while the design robustness is ensured.

The invention relates to the technical field of offshore wind power, and discloses a limit turbulence prediction method and device, electronic equipment, a medium and a product, and the method comprises the steps: obtaining a plurality of actually measured wind data subsets of an offshore wind plant; extracting a plurality of average wind speed values and a plurality of wind speed standard deviation values in the plurality of actually measured wind data subsets, and constructing a real-time two-dimensional data set; and on the basis of the real-time two-dimensional data set, through processing of a target Gaussian mixture model and an inverse first-order reliability method, a limit turbulence prediction result of the offshore wind plant is obtained, and the target Gaussian mixture model is used for fitting joint probability distribution of average wind speed and turbulence intensity. By implementing the method, accurate and reliable limit turbulence prediction is realized, and the application requirements of an offshore wind plant are met.

The application belongs to the technical field of electric power, and discloses a substation intelligent inspection rule generation and research method, which is characterized by comprising the following steps: based on ontology analysis of substation operation and maintenance regulations and fault cases, a hierarchical and graded semantic rule template library containing a device layer, an inspection layer and a defect layer is constructed; through a multi-level tabular parameter configuration interface, executable inspection rules are generated; multi-source heterogeneous monitoring data is standardized pretreated and subjected to feature engineering, and a device operation feature vector is extracted; a multi-dimensional model adopting weighted fuzzy comprehensive judgment and multi-feature fusion decision is used for abnormal research and judgment, and a defect level is output; rule effects are automatically evaluated according to defect disposal results, and rule parameters are iteratively optimized by using a self-adaptive genetic algorithm. The application has the following main beneficial technical effects: operation and maintenance efficiency is improved, cost is reduced, research and judgment accuracy and reliability are improved, the method automatically adapts to continuous evolution, standardized management and control are realized, and scale promotion is supported.

The invention relates to the technical field of digital twinning, and discloses a data processing method and system in the virtual production switching process of a production line so as to improve the production switching efficiency and reliability. The method comprises the steps that when all equipment models on a current production line are packaged, the function relation that structural parameters of parts of a sealing part vary along with the change of geometric parameters of a machined object is increased; after a user modifies geometric parameters of processing objects corresponding to all equipment models in a task scheduler on a copy of a current production line according to an actual production switching task, an initial production switching production line is automatically generated according to modification of the task scheduler; executing automatic deformation of structural parameters of part of parts of the equipment model reserved in the production line according to the packaged function relationship along with the change of geometric parameters of a processing object; and then outputting a simulation result for a user to determine the existing resources to be reused and the new resources to be introduced.

The application discloses a first-order reliability method based on a Copula theory in geotechnical engineering, and comprises the following steps: analyzing a geotechnical structure to determine a function function Z of the geotechnical structure and related random variables and independent random variables of the function function Z; determining an edge probability distribution function of the related random variables and a Copula function under a calculation working condition according to engineering experience and measured data; determining an edge probability distribution function of the independent random variables under the calculation working condition according to the engineering experience and the measured data; and calculating a reliability index, a design value and a failure probability of the geotechnical structure according to the edge probability distribution function of the related random variables, the Copula function and the edge probability distribution function of the independent random variables. The application can directly implement the first-order reliability method based on the Copula theory in the original space of the random variables familiar to geotechnical practitioners, and does not involve conversion of additional random variables, so that the complexity of reliability calculation is greatly reduced.

The application relates to the technical field of digital twinning, and discloses a data processing method and system in a virtual change production process of a production line, so as to improve change production efficiency and reliability. The method comprises the following steps: when encapsulating each device model on the current production line, a function relationship that a structure parameter of a part in an increase encapsulation part is changed with a geometric parameter of a machining object is encapsulated; after a user modifies the geometric parameters of machining objects corresponding to each device model in a task scheduler according to an actual change production task on a copy of the current production line, an initial change production line is automatically generated according to the modification of the task scheduler, and the structure parameter of the part of the device model retained in the change production line is automatically changed with the geometric parameter of the machining object according to the encapsulated function relationship; and then simulation results are output for the user to determine existing resources to be reused and new resources to be introduced.

The application provides a reliability evaluation method based on a regularization flow generative model, belongs to the fields of artificial intelligence and reliability evaluation technology, and comprises the following steps: S1, determining a performance function; S2, based on the regularization flow generative model and observation data, performing probability modeling on a multi-dimensional parameter joint distribution to obtain a multi-dimensional parameter joint distribution probability space conversion model; S3, combining the regularization flow generative model with a traditional reliability method to form the reliability evaluation method based on the regularization flow generative model; and S4, based on the multi-dimensional parameter joint distribution probability space conversion model and the performance function, performing iterative reliability calculation through the reliability evaluation method based on the regularization flow generative model to obtain a failure probability. The application can more reasonably consider the nonlinear correlation between random variables, is more accurate and efficient in the reliability problem of a multi-dimensional parameter joint distribution with a nonlinear correlation structure, and has a good application prospect.

The present application relates to the technical field of ocean engineering, and discloses a mining vehicle laying and recovering method and system based on umbilical slack prediction mechanism, which can predict the slack risk in advance and ensure the reliability of intelligent response. The method comprises the following steps: inputting the preprocessed real-time heave data into a heave data prediction model to obtain a heave motion prediction result of the ship stern in the future target time, so as to predict the umbilical slack length D at the next moment in advance; judging whether D is still in a slack state after considering the passive compensation range corresponding to the current sea state; if yes, starting the active compensation system to collect the cable in advance, and the cable length is equal to the length D; otherwise, acquiring real-time umbilical tension data and comparing it with a preset tension threshold value, if the real-time tension exceeds the tension threshold value, starting the active compensation system to execute the winch cable laying adjustment action, and when the umbilical tension data decreases to the tension threshold value range, switching the active compensation system to a dormant state.

The present application relates to computer system monitoring and operation and maintenance automation, and discloses a health management method and system based on multi-element heterogeneous monitoring data to improve the intelligence and reliability of operation and maintenance. The method comprises the following steps: based on the current value of the to-be-optimized parameter vector, the dynamic weight vector of each index in the current evaluation period is calculated according to the current state of each index in the index state matrix, combined with the basic weight, the abnormal timeliness, the running context and the index coupling relationship, and then the health prediction result of the current running state of the system is output according to the index state matrix and the dynamic weight vector; a "prediction result-real state" paired sample set is constructed combined with the subsequent actual operation and maintenance events, fault handling results and business impact records; a residual error vector is formed according to each paired sample, and then the to-be-optimized parameter vector is updated according to the parameter sensitivity matrix, the weight of each sample pair and the residual error vector, with the minimum loss function as the target.

The invention provides a liquid hydrogen storage tank structure system two-process reliability evaluation method based on a hybrid model, and relates to the technical field of reliability engineering and evaluation.The method comprises the steps that a thermal-mechanical coupling analysis model is used for analyzing the specific structure and the operation working condition of a large liquid hydrogen storage tank, and a simulation result is obtained; identifying key factors influencing the reliability of the storage tank by utilizing a simulation result in combination with expert knowledge, historical data and failure physical analysis to obtain key failure risk factors; constructing the key failure risk factors into a polymorphic fault tree structure, and mapping the polymorphic fault tree structure to obtain a dynamic Bayesian network model; and performing double-process quantitative reliability evaluation on the simulation result by using a dynamic Bayesian network model and a mixed agent model to obtain a hierarchical reliability evaluation result. According to the method, the problem that the reliability of the large liquid hydrogen storage tank is difficult to comprehensively and accurately assess by the existing single system reliability method or structure reliability method is solved.