135 results about "Intelligent modeling" patented technology

A computer aided hidden tooth deformity correcting system is composed of a data acquisition subsystem, an intelligent tooth sleeve modelling subsystem, transparent tooth sleeve manufacture subsystem and data bus.

Embodiments of an intelligent modeling method and system monitor and perform analysis of semiconductor processing equipment as well as predict future states of that equipment based on the analysis, predict failures of the semiconductor processing equipment and/or determine equipment maintenance schedules.

The invention relates to an urban inland inundation intelligent modeling and analysis method based on a GIS and an SWMM. The method comprises the following steps: constructing a simulation system based on the GIS and the SWMM; carrying out automatic preprocessing on the model data and automatically identifying topology errors; calculating a hydrological-hydrodynamic coupling model based on the SWMM by combining rainfall, calculating the amount of rainwater converged into a drainage pipe network system, simulating to obtain actual condition information in the drainage pipe network, and obtaining pipe point overflow data; performing surface water inundation analysis according to the pipe point overflow data, simulating the surface water to obtain the depth of the surface water, and distributing the surface water flow based on a window method; performing early warning analysis on waterlogging of surface water, comprehensively considering prediction of the surface water, automatically dividing waterlogging risk levels of different areas according to a calculation result of a hydrological-hydrodynamic coupling model and a result of surface water inundation analysis, and providing an early warning scheme for drainage waterlogging prevention emergency. The method has the advantages of being low in construction cost, high in model construction automation degree and accurate in analysisresult.

The health of a tool is predicted based on temporally ordered input data representing parameters indicative of tool health. A sliding time window is used to partition input data into temporally displaced data sets. Non-linear regression models determine, based on the data sets, a set of predictive values relating to tool health at a future time. A tool-health metric is then determined based on one or more of the predictive values.

The invention discloses a shortcut method of nerve network decoupling based on the adaptive control multiple-variable system in the complex system intelligent modeling and decoupling control technique domain, which is characterized by the following: adapting on-line identification and decoupling of nerve network; guiding the other two-phase control signal into the input end of nerve network identifier as two signal reference and identification when certain one phase of the three-phase electrode system is on-line identifying; decoupling and controlling the three-phase electrode.

The invention discloses a boiler combustion optimization system and method based on CFD numerical simulation and intelligent modeling. The boiler combustion optimization system comprises a DCS controlsystem interface, a CFD computing cluster, a sample database cluster, an intelligent modeling cluster, a central processing cluster and a human-computer interface. Real-time matching of the optimal air distribution types of the unit along with variation of network load instructions, coal as fired quality characters and excess air coefficients by storing, modeling and optimizing a CFD simulation sample and a history running sample. The modeling accuracy is improved by using a CFD numerical simulation technology, a DCS control system can be directly called to realize closed-loop control in optimization, the air distribution way is enabled to quickly respond to the load change, and the unit combustion heat efficiency and the NOx emission are optimized in a real-time manner.

The invention provides a model output method and device for intelligent modeling, and a storage medium. The method comprises the steps of pre-establishing a model factor library used as model traininginput factors; obtaining historical data, and training the historical data according to a preset modeling process, thereby obtaining a model training result; and if it is detected that survey task flow is received, performing function operation by taking the selected model factors in the model factor library and case data corresponding to the survey task flow as inputs of the model training result to obtain a score result corresponding to the survey task flow. According to the method, the model training result obtained by training according to an SMP is deployed; when the factors of the modelfactor library and the survey task flow are received by a model deployment platform, case risk scoring is performed directly by the model training result; and functions deployed in a model deploymentplatform can be subjected to optimization iteration at any time.

The invention relates to an intelligent modeling method during the industrial polyester production process. Firstly, a mechanism model of the polyester production process based on reaction kinetics is established according to the mechanism of polyester reaction process; and then, parameters in the technical mechanism model are optimized by a multiple-target distribution estimation algorithm, so as to describe the actual operation characteristic of the industrial polyester production process exactly. At the same time, considering the influence on the reaction during the pre-polycondensation stage caused by catalyst, influence factor of the catalyst is added in reaction speed constant of the mechanism model, and a model between the catalyst and the reaction speed constant is established by a least square method; in a final polycondensation reactor, the mass transfer rate is reduced, and the influence on the process speed is increased, so that an artificial neural network is used for establishing an empirical model while the influence of mass transfer is considered, and the process speed is expressed in a form of resistance equation while combining with the reaction speed to ensure that the model is exacter. The modeling method can be applied to the modeling during three-reaction and five-reaction technical process during the industrial polyester production process at present.

A soft measurement system and method for the quality index of blast furnace multi-element molten iron, the system includes: a data acquisition unit, a data preprocessing unit, and a soft measurement unit; Filter, remove noise and normalize the parameters required by the dynamic soft measurement of the quality index; use the dynamic soft measurement model of the quality index of the blast furnace multicomponent molten iron to perform dynamic soft measurement of the quality index of the blast furnace multicomponent The parameters required for the dynamic soft measurement of the molten iron quality index are used as input, and the multivariate molten iron quality index of the blast furnace is output as the output, and the output self-feedback is adopted to dynamically and online recursively predict the multivariate molten iron quality index of the blast furnace. The invention considers the hysteresis characteristics of the blast furnace smelting process and the time series relationship between input and output variables, and utilizes the recursive subspace intelligent modeling technology to realize the dynamic online soft measurement of the multivariate molten iron quality indicators in the blast furnace smelting process.

The invention provides a data modeling based wind turbine generator system state monitoring system data compressing method. Monitoring data are subjected to mathematical modeling in a local wind turbine generator system so as to extract strong features and compress and restore data in a high compression ratio mode. The method includes the following steps of wind power state monitoring data collection, wind turbine generator system operation condition identification, wind power state monitoring data screen, monitoring data information local settlement, wind power state storage mode selection, intelligent modeling structure identification matching, intelligent modeling structure parameter estimation, monitoring data local primary processing, and upper monitoring terminal secondary processing. By means of the wind turbine generator system state monitoring system data compressing method, problems existing in on-line transmission and long-term continuous monitoring and storage of mass data are solved.

The invention relates to a 3D intelligent modeling method and system and a flexible manufacturing system of a 3D model. A single photograph or picture is converted into a 2D shadow picture; after a 3D model is constructed, the information of the 2D shadow picture is hidden in the 3D model, a shadow presented by the 3D model with the hidden information of the 2D shadow picture through illumination angle projection is in an original picture or photograph shape, and 3D intelligent modeling can be realized by methods, such as accumulation, splicing, stretching, extrusion and the like. The flexible manufacturing system of the 3D model enables a user to integrally experience the processes of 3D modeling and 3D printing, 3D modeling compatible data is created, stored, transmitted and managed for a user, and the user is guaranteed to carry out 3D printing at any time and place so as to realize the flexible manufacture of the 3D model.

The invention provides a spare power automatic switching simulation method of a power grid. The method comprises the following steps of: searching and identifying a substation topology structure according to a network topology structure and a real-time operation state of a substation, and generating equipment interval information required by a spare power automatic switching simulation; generating condition parameters required by the spare power automatic switching simulation according to the network topology structure and preset rules, wherein the parameters comprises a charge condition, a discharge condition, an action condition, a locking condition and an action sequence; and carrying out the spare power automatic switching simulation according to the equipment interval information and the condition parameters, so as to obtain the simulation result. With the adoption of the spare power automatic switching simulation method, the intelligent modeling and the automatic generation of a spare power automatic switching model are realized according to a real-time state of a power grid and different topology structures of grid frames in the substation, the maintenance working quantity of a simulation system is reduced, the construction and the use of a power grid simulation training system are facilitated, and the practical application level is further improved.

The invention relates to the field of relay protection systems, in particular to a modeling method for a relay protection setting calculation system. The modeling method comprises the steps of formation of an original model by using artificial intelligence, conventional graphic modeling, automatic network topology analysis and the like. The modeling method has the effects that the modeling efficiency is greatly improved and the time occupied for system maintenance is greatly reduced; the system safety is greatly improved, the accuracy of the established model is fully guaranteed and a feasible and powerful technical supporting means is provided for effectively avoiding incorrect setting; and according to the actual needs, the effect of unifying power systems of a whole province and even the whole nation into one grid can be very easily realized through modeling, the intelligent modeling advantage is more remarkable when the grid is larger, and the large grid can be easily managed.

The invention discloses an overhead crane neural network modeling method based on an RNA genetic algorithm of a hairpin mutation operation, and belongs to the field of intelligent modeling. An overhead crane is a highly non-linear under-actuated complicated system, and the establishment of a high-precision overhead crane system model is a crucial foundation for achieving the purpose of effective control. The invention, for the problem in overhead crane modeling precision, provides overhead crane nonlinear regression models based on a position and an angle of an RBF (Radial Basis Function) neural network. Under the inspiration of a hairpin structure, the RNA genetic algorithm of the hairpin mutation operation is abstracted, and the RBF center of the RBF neural network for the position and the swing angle of the overhead crane is optimized by running the RNA genetic algorithm of the hairpin mutation operation, so that a neural network model of the overhead crane is obtained. The modeling method has the characteristic of high modeling precision, and is also suitable for modeling other complicated nonlinear systems.

The invention provides an intelligent modeling method and device for a digital twinning system in a complex industrial process, equipment and a storage medium. The intelligent modeling method for thedigital twin system in the complex industrial process comprises the following steps: establishing a mechanism model of the complex industrial process, wherein the mechanism model comprises an identifiable model and an unmodeled dynamic model; estimating parameters of the identifiable model to obtain an identification model; adopting an identification model error and the unmodeled dynamics to forman unknown nonlinear dynamic system; establishing an intelligent model of the unknown nonlinear dynamic system; establishing an intelligent model of the complex industrial process digital twin systemby adopting the identification model and the intelligent model of the unknown nonlinear dynamic system, wherein the identification model error is a model output error caused when parameters in the identifiable model are replaced by identification values of the parameters. Aiming at the problem that the precision of a digital twinning system in a complex industrial process is difficult to guarantee, a system identification method based on a mechanism model is combined with a deep learning method based on big data, and an intelligent model of the digital twinning system in the complex industrialprocess is established by adopting an end-to-side cloud cooperation mode. The modeling problem of a digital twin system in a complex industrial process is solved, and the modeling precision is improved.

The invention discloses a big data intelligent modeling system and a method based on dynamic metadata. The system comprises a metadata acquisition module, a metadata algorithm library module, an abnormity detection module, a visualization module and a big data engine module. The method has the beneficial effects that (1) an intelligent modeling strategy based on metadata is provided, the whole data mining conversion process is simulated on the premise that actual data does not need to be loaded and even a big data mining engine does not need to be started, an output result of a current computing node is estimated in real time, modeling operation of an operator is assisted, and the technical threshold of big data modeling is reduced; and (2) an abnormity detection mechanism is further developed based on metadata, real data is replaced by the metadata, and matching detection is performed on data transmission forms and contents between upper and lower nodes, so that the method has the advantages of good real-time performance and high reliability compared with inspection of a big data set, thereby realizing real-time early warning of wrong process connection and improving the modelingefficiency.

The invention, which belongs to the intelligent modeling field, discloses a cuckoo-behavior-RNA-GA-based bridge crane neural network modeling method. The bridge crane is a complicated under-actuated non-linear system; and effective control realization is based on establishment of a high-precision bridge crane model. With the Cuckoo-behavior RNA genetic algorithm, optimizing is carried out on a radial basis function center of a bridge crane neural network model, thereby obtaining a corresponding RBF neural network model. According to the method, an ideal effect is realized during testing. And the method is suitable for modeling of other complicated non-linear systems.

The invention provides a method for compressing data of a status monitoring system of a wind turbine generator system. Strong features are extracted in the mode that mathematical modeling is conducted on the monitoring data locally in the wind turbine generator system, and data compression and recovery are conducted according to a high compression ratio. The method comprises the following steps of collection of the wind electricity status monitoring data, identification of operating conditions of the wind turbine generator system, filtration of the wind electricity status monitoring data, local collating of monitoring data information, wind electricity status storage mode selection, identification and matching of intelligent modeling structures, estimation of parameters of the intelligent modeling structures, local primary processing of the monitoring data and upper monitoring terminal secondary processing. By means of the method, mass data on-line transmission and long-term continuous monitoring storage are achieved.

The invention, which relates to the technical fields of model establishment and controlling of the chemical engineering process industrial system model, discloses an intelligent sensitive plate temperature modeling method based on mixed elite captivity optimization. Being different from the natual-calculation-based optimization algorithm, an optimization algorithm based on mixed elite captivity introduces the artificial captivity concept to cultivate expected key species with great effort. The temperature of a sensitive plate in a rectifying tower is adjusted by adjusting the opening of a valve of a reboiler heat source; and the control loop is one first-order plus dead-time link. When the algorithm is applied to the model identification of the first-order plus dead-time system, the precision of model identification of the sensitive plate temperature control loop of the rectifying tower can be improved well; and the solid foundation is laid for using the advance control plan on the type of device. The method is operated simply; the searching power is high and the convergence is accelerated; the trapping in local optimum is prevented; the time is saved for the optimization problem and the system identification requirement is met completely.

The invention discloses an underground reinforced concrete structure carbonization life intelligent modeling method based on big data. The method comprises the steps: selecting main factors influencing the carbonization life of an underground reinforced concrete structure according to the carbonization mechanism of the reinforced concrete structure and the consideration of an actual engineering situation; according to different factors influencing the carbonization life of the underground reinforced concrete structure and a theoretical model, establishing three-factor and seven-factor sample data; compiling an intelligent genetic algorithm program based on MATLAB, obtaining a corresponding carbonization life model through training according to different sample data, comparing and verifyingcalculation values of a three-factor carbonization life model and a seven-factor carbonization life model with an actual value of the data, and proving the robustness of the intelligent genetic algorithm program for establishing the models and the reasonability of the modeling method ; and finally, collecting actual engineering data in a carbonization environment, establishing a structural carbonization life model considering multiple factors of engineering by utilizing an intelligent algorithm (GP) program, and verifying the engineering practicability of the model by utilizing the actual engineering data.

The invention discloses a bridge crane modeling method adopting a hairpin mutation operation RNA genetic algorithm and belongs to the field of intelligent modeling. A bridge crane is a highly nonlinear complicated system, and building a high-precision bridge crane system model is a fatal basis for the purpose of effectively control. For high bridge crane modeling precision, a bridge crane nonlinear regression model based on the position and the angle of an RBF nerve network. Under inspiration of a hairpin structure, the hairpin mutation operation RNA genetic algorithm is abstracted and applied to optimize the radial basis function center of the bridge crane RBF nerve network so as to obtain a nerve network model of the bridge crane. The bridge crane modeling method has the characteristic of high modeling precision and is also suitable for modeling other complicated nonlinear systems.