81 results about "Order reduction" patented technology

The present application relates to the field of nuclear reactor simulation. Disclosed are a fast simulation method and system for multi-physical field coupling and a storage medium. The method comprises: at intervals of a first preset interval time, collecting state information of each physical field of a nuclear reactor in a transient process, so as to obtain physical field snapshots of a plurality of physical fields, the transient process being simulated by a reactor simulation model corresponding to the nuclear reactor; stitching the physical field snapshots of the plurality of physical fields, so as to obtain a fully-concatenated physical field; constructing a matrix on the basis of the fully-concatenated physical field; performing order reduction processing on the matrix, so as to construct a timing model corresponding to the fully-concatenated physical field; and decomposing the timing model corresponding to the fully-concatenated physical field, so as to obtain timing models corresponding to the plurality of physical fields. The fast simulation method for multi-physical field coupling of the present application can reduce the inconsistency between different physical fields while increasing the computation speed.

The invention discloses an order early-warning method and system based on index configuration, and the method comprises the steps: carrying out the structural processing of early-warning demands, determining the type of an early-warning index to which each early-warning demand belongs, and generating an early-warning index according to the early-warning demands after the structural processing; configuring an early warning rule according to the early warning index and the early warning rule template; extracting an order corresponding to the trigger event, and determining a target order corresponding to each early warning rule; performing early warning judgment on the order data of the target order to obtain an early warning index result; and if the early warning index result is that the order data of the target order meets the trigger logic in the early warning index, performing order early warning on the target order, generating an early warning record, and sending an early warning notification. According to the method and the corresponding system, the early warning delay of a large number of orders can be reduced, the query pressure of an order database is reduced, the data consistency of hundred million-level orders is ensured, and the early warning efficiency of hundred million-level risk orders is effectively improved.

The invention relates to the technical field of computational fluid mechanics and biological microfluidic design, in particular to a model order reduction method for rapid optimization of a circulating tumor cell (CTC) sorting structure, which comprises the following steps of: constructing a three-dimensional full-order computational fluid mechanics model by collecting channel geometric structure parameters and fluid working condition parameters, and generating a training data set; organizing a flow field snapshot into a matrix form, extracting a dominant mode, constructing a low-dimensional modal space by taking the dominant mode as a base vector, establishing a low-dimensional ordinary differential model through Galerkin projection, and training a parameter-modal coefficient mapping relation by adopting a deep neural network to form a complete reduced-order model; and finally, constructing a multi-objective optimization problem based on the reduced-order model, carrying out optimization iteration by adopting an evolutionary algorithm, and returning an optimization result to the full-order model for verification, so that rapid optimization design of the CTC sorting structure is realized, and an effective solution is provided for intelligent design of a biomedical microfluidic device.

The invention discloses a wind power plant broadband oscillation suppression method and system based on amplitude-phase characteristic remodeling. The method comprises the following steps: respectively establishing a frequency domain impedance model of each wind turbine generator set and performing dynamic order reduction, analyzing amplitude-frequency and phase-frequency characteristics of wind power plant multi-machine parallel coupling based on the order reduction model, determining an interaction rule of a module value and a phase angle, designing additional damping control and active damping control, and determining a wind power plant multi-machine parallel coupling amplitude-frequency and phase-frequency characteristic of the wind power plant multi-machine parallel coupling amplitude-frequency and phase-frequency characteristic. A weak position of a system is positioned based on an s-domain node admittance matrix method, a function is set by taking improvement of amplitude-phase characteristics as a target and optimizing and setting control parameters for a target wind turbine generator corresponding to the position, the optimized parameters are applied to the target generator, and effective suppression of broadband oscillation is realized. According to the application, the broadband oscillation problem caused by high-proportion new energy grid connection can be systematically solved by synergistically remodeling the frequency domain amplitude-phase characteristics of the wind power plant.

This invention relates to the field of contract reconciliation management technology, specifically disclosing a contract settlement and automatic reconciliation system and method that deeply integrates business and financial data. After acquiring business performance data sequences and financial settlement data sequences, the system maps them into a two-dimensional time-series directed graph. Upon receiving an abnormal settlement trigger instruction, it traces back along the flow of funds and penetrates forward along the business-finance mapping to capture affected node clusters. Then, based on the comparison results between the accounting period identifier and the current closing time, it generates inter-period reversal action instructions and original order reduction action instructions, constructs alternative reversal path chains, and imports them into a virtual sandbox memory for verification. When the updated amount value is lower than a preset lower threshold, it triggers backtracking and reorganization until a legal reversal path scheme is selected. Finally, it calculates a physical disturbance score by combining the total number of nodes and the total number of inter-period actions, selects the scheme with the lowest score, and outputs it to the accounting platform to complete the synchronous update of business-finance reconciliation.

The application provides a precise simplification method and system of a passive parasitic parameter network. The method comprises the following steps: obtaining a passive parameter parasitic network of a to-be-processed circuit; obtaining device information of all parasitic parameters; labeling node names of active device ports according to an active device naming rule; if a current parasitic parameter crosses multiple active device ports, deleting the current parasitic parameter; if a branch where the current parasitic parameter is located is an open circuit, deleting the branch and the parasitic parameters thereon; after traversing all parasitic parameters, obtaining a precise passive parasitic parameter network; and performing order reduction processing on the precise passive parasitic parameter network to obtain a simplified passive parasitic parameter network. The method precisely processes the passive parasitic parameter network, excludes active device ports and invalid ports, so that the passive parasitic parameter network can be correctly processed during simplification and order reduction processing, and the efficiency and accuracy of the order reduction and simplification processing are improved due to the exclusion of invalid paths.

This application discloses a method, apparatus, equipment, medium, and product for predicting damage evolution based on dynamic order reduction, relating to the field of aero-engine health management and monitoring. The method includes: conducting finite element fatigue / creep-fatigue simulation tests on structural components covering stress states under various operating conditions, and extracting the time-physics field matrix from the finite element fatigue simulation results under each operating condition; dynamically reducing the order of the time-physics field matrix to reduce its dimension, obtaining a reduced-order matrix; constructing a reduced-order model; restoring the equivalent stress field distribution based on the reduced-order model to obtain the reduced-order physical field; predicting the damage distribution evolution and fatigue life under fatigue or creep-fatigue loading based on the reduced-order physical field, and making corrections based on the fatigue life prediction model. This application can improve the efficiency and universality of life prediction.

The invention discloses a vulnerability analysis method of a multi-time-scale micro-grid under FDI attack, which comprises the following steps: decomposing system dynamics of a direct current micro-grid into a fast boundary layer subsystem and a slow order reduction subsystem by using a singular perturbation theory, respectively deducing stability conditions of each subsystem under a false data injection attack condition, and analyzing the vulnerability of the multi-time-scale micro-grid under the false data injection attack condition; and the input state stability of the low-speed subsystem under the FDI attack is proved. The worst deviation of the system state under the attack condition is calculated by constructing a zootope reachable set analysis framework, and the maximum allowable attack amplitude capable of ensuring safe operation of the system is quantified. According to the method, through numerical simulation and hardware experiment verification, a novel attack surface introduced by multi-time scale characteristics can be effectively revealed, and theoretical support and guidance are provided for safe and stable control of the DC micro-grid.

The application belongs to the technical field of simulation analysis, and particularly relates to a switch cabinet condensation margin evaluation method based on simulation analysis and order reduction reconstruction, steps of which comprise: establishing a simulation analysis model of the switch cabinet, adding a physical field and performing physical field coupling and mesh partitioning; solving the simulation analysis model to obtain the temperature and humidity distribution inside the switch cabinet; optimizing the simulation analysis model; replacing electromagnetic heat with loss data as a heat source input into a non-isothermal flow field; constructing a physical field snapshot library for order reduction model training; processing the physical field snapshot library based on a POD method to construct an order reduction model; training a Kriging model to reconstruct the temperature and humidity field of the switch cabinet; constructing a condensation margin evaluation cloud map; in the actual operation process of the switch cabinet, calculating an actual dynamic dew point temperature to generate an actual operation condensation margin cloud map, and completing online real-time evaluation. The application can realize efficient and accurate reconstruction of the temperature and humidity field inside the switch cabinet and efficient evaluation of the condensation margin of the switch cabinet.

The invention discloses a doubly-fed motor loss and temperature digital twin model establishment method and system based on finite element simulation, and relates to the field of motor loss simulation, and the method comprises the steps: constructing a finite element simulation model of a doubly-fed motor; carrying out electromagnetic loss calculation based on the finite element simulation model; performing temperature loss calculation based on the finite element simulation model; and based on a result of the electromagnetic loss calculation and a result of the temperature loss calculation, constructing a digital twin model of the loss and the temperature of the doubly-fed motor. According to the method, a finite element simulation model of a motor is established, loss and temperature distribution data under limited working conditions are used for establishing a data set, a reduction method is used for extracting space information of a loss field and a temperature field, flow field characteristics of a three-dimensional flow field are described through a few modes and mode coefficient combinations, and the flow field characteristics of the three-dimensional flow field are analyzed. Meanwhile, the invention provides a simulation order reduction method in which the POD-KAN algorithm is combined with the ARBF algorithm, so as to achieve the rapid prediction of the physical quantity to be researched of the equipment.

The invention discloses a river and lake hydrodynamic model reduced-order inversion initialization method for intelligent water conservancy, and the method comprises the steps: dividing a computational domain into a plurality of sub-domains according to hydraulic characteristics, building a physical constraint equation represented by reduced-order description parameters, and determining an independent to-be-inverted parameter set through the analysis of the degree of freedom; estimating an initial state of a part of sub-domains by using observation information or a priori value at a starting moment; determining an inversion window according to the hydraulic disturbance propagation time; constructing an agent model, and performing joint inversion on the to-be-inverted parameters and the boundary process line parameters to minimize the cost function; and driving the proxy model to generate a global initial state by using the optimal parameter obtained by inversion, mapping the global initial state to a basic model grid, and taking the global initial state as an initial condition after free evolution and boundary smoothing processing. According to the method, actual measurement data are fused through order reduction-inversion, global initial field construction can be rapidly and accurately completed, and the requirement of an intelligent water conservancy system for cold start of a hydrodynamic model is met.

The invention discloses a transient multi-physics field reduced-order reconstruction method and device driven by a time sequence working condition, and relates to the technical field of digital twinning and calculation simulation acceleration. The method comprises the following steps: performing Latin hypercube sampling on monitoring working condition parameters to obtain a working condition parameter combination covering a sample space; establishing a high-fidelity finite element model to obtain geometric topology information; establishing a working condition parameter amplitude curve, performing batch finite element calculation in combination with the high-fidelity finite element model to obtain transient multi-physics field response data, and constructing a graph data structure; the training graph neural network auto-encoder comprises an encoder and a decoder; and training a time sequence neural network, establishing a mapping relation from time sequence working condition parameters to low-dimensional latent variables, and realizing rapid prediction and reconstruction from the time sequence working condition parameters to transient multi-physical field whole-field distribution in combination with a graph neural network decoder. According to the method, online rapid prediction of the transient physical field of the high-temperature turbine component can be realized, and the method has the advantages of high prediction precision, fast calculation response, strong cross-working-condition generalization capability and the like.

This invention relates to the field of intelligent equipment technology, and particularly to a time-optimal speed planning method and application with anti-envelope linear constraints. The method involves solving for control point deviations using the anti-envelope interval as a constraint condition, and then superimposing these deviations with the initial control points to obtain combined control points. An analytical model of the control points with linear constraint factors is constructed and converted into linear equations. Iterative solutions are used to obtain the linear constraint factors and corresponding linear control points. These linear control points are compared and adjusted with the initial control points and the control points corresponding to the maximum feed rate to obtain the final control points. Based on these final control points, an optimal feed rate curve satisfying all constraints is generated. By compensating for order reduction errors through anti-envelope calculations, and combining analytical solutions of linear constraint factors with iterative correction of control points, the method fully exploits constraint margins, achieving time-optimal, more uniform speed, and higher processing quality for large curvature sections while satisfying trajectory error and motor dynamic performance constraints.

The invention provides a motor electromagnetic-thermal coupling field inversion method based on a missing field POD, and the method comprises the following steps: carrying out the electromagnetic-steady-state thermal field finite element simulation calculation of a plurality of operation conditions of a motor through employing a load current and a cogging angle as parameters, and respectively constructing a magnetic field POD reduced-order model and a temperature field POD reduced-order model; a temperature sensor is arranged on the outer surface of the stator, the temperature is measured, and motor temperature distribution is obtained through inversion with a missing field POD method; based on the temperature distribution, the load current of the motor is determined through SVR; and calling a magnetic field POD order reduction model based on the load current and the cogging angle parameter, calculating the magnetic field distribution of the motor, and realizing inversion of the electromagnetic-thermal coupling field of the motor. The method can consider the influence of the material parameter change caused by the temperature on the electromagnetic field distribution, and enables the motor electromagnetic characteristics obtained through inversion to be more accurate.

The application discloses a radial magnetic bearing displacement vibration suppression method based on a phase shift reduced-order generalized integrator, and comprises the following steps: firstly, a magnetic bearing system model containing rotor mass imbalance is established; then, a synchronous displacement vibration suppression algorithm based on a phase shift reduced-order generalized integrator is designed, the orthogonal relationship of X / Y radial displacement error signals of the magnetic bearing is utilized, and the simultaneous extraction and compensation of double-channel synchronous components are realized; finally, the system stability is analyzed, and the phase shift angle parameters are designed in sections; the phase shift angle is introduced to adjust the phase without changing the amplitude characteristics at the synchronous frequency, so that the system stability is expanded. The application adopts the reduced-order generalized integrator structure, has less state quantity and lower calculation amount, and is suitable for high-speed real-time implementation of DSP / FPGA; the phase shift angle is introduced for phase advance adjustment, so that the stable working range of the algorithm can be effectively expanded; the orthogonal characteristics of the displacement signals are utilized to realize the unified implementation of X / Y double-channel synchronous compensation, and the structure is more simple.

This invention proposes a method and system for reducing the order of FPSO models by integrating time-recurrent neural networks and fuzzy logic, belonging to the field of marine engineering structural analysis and intelligent modeling technology. Addressing the problem of large degrees of freedom and low computational efficiency in FPSO finite element models, this invention extracts key degrees of freedom from the high-dimensional finite element model to construct low-dimensional feature vectors. It then uses a fuzzy logic system to perform regularized modeling of the dominant mechanical properties of the structure, achieving initial order reduction. Furthermore, a time-recurrent neural network is introduced to compensate for high-order residual effects that are difficult to accurately characterize using the fuzzy logic model, ultimately resulting in a low-dimensional, high-fidelity reduced-order model. The proposed method significantly reduces the degree of freedom and parameter dimension of the finite element model while maintaining the main mechanical properties of the structure, effectively reducing computational complexity and improving the model's applicability and practical engineering value in applications such as rapid finite element analysis, online structural response prediction, and engineering decision support.

This invention discloses a method and system for order reduction and decoupling of high-dimensional stochastic systems based on stochastic approximation conjugacy, belonging to the field of complex system modeling and analysis technology. This method acquires multi-condition state data of the high-dimensional system, constructs a reduced-order analysis framework including embedding mapping, a low-dimensional decoupled dynamic model, and lifting mapping. Using stochastic approximation conjugacy as a constraint, it minimizes the total loss function to complete joint model training. After solving the system's stochastic response characteristics within a low-dimensional feature manifold, it maps back to the high-dimensional space to complete dynamic behavior analysis. The corresponding system includes modules for data acquisition, model construction, model training, low-dimensional solution, and mapping analysis. This invention solves the curse of dimensionality problem of traditional methods, ensures the reliability and interpretability of the reduced-order model, has strong versatility, and can be widely applied to intelligent operation and maintenance and control optimization of major engineering systems.

This application discloses a method, device, terminal, and storage medium for simulating the electrical characteristics of integrated circuits. The method includes acquiring a model of the integrated circuit to be simulated; meshing the model to obtain an integrated circuit mesh dataset composed of multiple mesh cells; constructing corresponding charge basis functions and current basis functions based on the mesh cells; using the charge basis functions as the fusion object, progressively merging and updating the charge basis functions; simultaneously, merging and updating the current basis functions through geometric mapping; after all fusion and updates are completed, acquiring the integrated circuit basis function dataset; and performing electrical characteristic simulation on the integrated circuit to be simulated based on the integrated circuit basis function dataset. This achieves rapid updating and low-order representation of complex coupling capacitance matrices, reducing the theoretical complexity from O(n^2) to O(n^2) of traditional back-end order reduction methods. 3 The time complexity is reduced to O(n), while the model accuracy and order reduction effect are maintained, and the efficiency of model order reduction is greatly improved.

The invention discloses a method and a system for suppressing low-frequency oscillation of a network construction type energy storage converter, and belongs to the technical field of energy storage, and the method comprises the following steps: constructing a small-signal impedance model of the network construction type energy storage converter based on virtual admittance control by using a small-signal modeling method; order reduction simplification is carried out on the impedance model, key characteristics of a 0.1-10Hz synchronous frequency band are reserved, and oscillation core inducements in a current steady-state value matrix are identified; and adding a q-axis voltage feedforward control link, introducing a regulation coefficient, and modifying the regulation coefficient to enable the modified regulation coefficient to be negative to counteract oscillation inducements. The method can effectively suppress the interactive oscillation of the grid-forming type energy storage converter and the power grid at the low frequency band, improves the system stability, is suitable for various operation conditions, and has important engineering application value.

This invention discloses a dimension-reduction reliability assessment method for switched reluctance motors (SRMs) that considers repairability. This method analyzes the faults of the SRM at structural levels, comprehensively converting the failure probabilities of each underlying component into overall system state transition parameters. Based on this, the repairability rate is calculated according to the actual periodic maintenance cycle of the equipment, and a Markov state transition equation system containing maintenance recovery paths is established. To avoid complex calculus operations involving high-order matrices, this invention utilizes Laplace transform to convert the dynamic process into algebraic calculations in the complex frequency domain, achieving analytical order reduction of the model. By performing algebraic analysis on the complex frequency domain function, the dynamic reliability function and mean time between failures (MTBF) of the system are directly obtained. This invention overcomes the shortcomings of traditional models, such as cumbersome computation and unrealistic lifespan predictions. While effectively reducing the computational complexity of microcontrollers, it significantly improves the accuracy of lifespan prediction for motor drive systems and enhances their engineering application value.

The invention belongs to the technical field of power systems, and particularly discloses a singular perturbation-reactive decoupling-based order reduction method and device for a network construction type converter. According to the invention, the original state space model is converted; on the basis of a singular perturbation strategy, order reduction processing is carried out according to target variable characteristics; order reduction processing is carried out on a voltage dynamic equation in a reactive power control outer ring, reactive power decoupling is carried out in the mode that a voltage state variable is introduced into an active power control state equation, and a differential equation based on the phase angle relation is established. Through the above mode, aiming at the electromagnetic dynamic process of the fast subsystem, order reduction processing is carried out on the electromagnetic dynamic state variable based on the singular perturbation strategy, order reduction processing is carried out on the voltage dynamic equation in the reactive power control outer loop, high-order dynamic items are eliminated, main dynamic characteristics in the state space are reserved, the model order and the solving complexity are obviously reduced, and the reliability of the system is improved. Therefore, the model order can be systematically reduced on the premise of ensuring key dynamic characteristics and stability analysis precision.

The invention provides a woven composite material multi-scale analysis method based on clustering order reduction, and belongs to the technical field of composite material multi-scale damage evolution evaluation. The method comprises the following steps: 1, defining a microscopic damage constitutive model; defining a fiber damage constitutive equation and a matrix damage constitutive equation; 2, solving an RVE damage problem by using an SCA method; the method comprises the following steps: for a composite material RVE region, converting a control equation of elastic mechanics into a solving L-S equation by introducing reference stiffness; the SCA method comprises an offline stage and an online stage. Step 3, establishing an FE-SCA2 concurrent three-scale model; and the numerical value is solved. According to the method, the problem of low three-scale calculation efficiency is relieved while nonlinear calculation high precision is achieved, and the method has high application value in the field of composite material structure multi-scale calculation.

The invention discloses an uncertainty model order reduction and damage identification method based on a neural network and a substructure, and belongs to the field of civil engineering, and the method comprises the steps: obtaining physical parameters of the substructure of a finite element model, obtaining an uncertainty main mode of the substructure through uncertainty analysis, building an uncertainty substructure price reduction model, and carrying out the calculation of the uncertainty main mode of the substructure; training the uncertainty substructure reduced-order model under the structure parameters with different mean values and standard deviations through a neural network to obtain a parameterized uncertainty substructure reduced-order model; constructing a parameterized uncertainty overall structure reduced-order model, and obtaining an overall structure dynamic response statistical moment according to the parameterized uncertainty overall structure reduced-order model; and correcting the finite element model according to the dynamic response statistical moment, and identifying the uncertain structural damage in the finite element model based on the dynamic response statistical moment to obtain a damage identification result so as to realize rapid and effective analysis and damage identification of the uncertain factors of the civil engineering structure.

The application provides a common-mode interference modeling and analysis method for an SLLC resonant converter, and belongs to the technical field of power electronics and electromagnetic compatibility; by extracting key parasitic parameters of a circuit, combining a transmission line theory and an equivalent circuit modeling technology, constructing a high-precision common-mode interference propagation path model, and introducing complex high-frequency line parasitic parameters, the application describes the propagation characteristics of common-mode currents; aiming at the calculation complexity problem caused by high-dimension modeling, the application proposes a model simplification strategy, effectively reduces the calculation complexity while ensuring the analysis accuracy through equivalent transformation and frequency domain order reduction processing; the application has the advantages of high precision, high efficiency, strong universality and the like, and is suitable for common-mode interference modeling analysis and electromagnetic compatibility design of the SLLC resonant converter and other various high-frequency power electronic devices.

The invention discloses a mechanical system dynamics modeling method, and relates to the technical field of mechanical dynamics, and the method comprises the steps: decomposing a target mechanical system into a set of a plurality of structural components; performing finite element modeling on each structural component to obtain a finite element model of each structural component; performing dynamic order reduction processing on the finite element model to obtain a polycondensation model of each structural component; integrating and coupling the polycondensation model into a system body dynamic model based on the motion parameters of each motion axis of the target mechanical system and the system assembly relationship; and coupling the dynamical model of the end effector with the system body dynamical model to obtain a target system dynamical model. The whole machine is decomposed into components, order reduction processing is carried out on the components respectively, dynamic integration is carried out according to real-time motion parameters, real dynamic behaviors of a mechanical system in different working spaces are accurately reflected, and limitation of traditional static modeling is overcome.

The invention discloses an AUV (Autonomous Underwater Vehicle) velocity field reduction method based on intrinsic orthogonal decomposition and neural network fusion, which comprises the following steps: constructing a velocity field snapshot matrix of an AUV, each velocity field snapshot being a multi-dimensional velocity field obtained by training sample simulation; preprocessing the speed field snapshot matrix, and then performing matrix decomposition by using a POD method to obtain a standard orthogonal basis matrix and a diagonal matrix; setting a truncation coefficient, determining the number of singular values needing to be reserved from the diagonal matrix by using the truncation coefficient, performing dimensionality reduction on the standard orthogonal basis matrix by taking the number as a dimensionality reduction order, and determining an order reduction coefficient matrix based on the standard orthogonal basis matrix after dimensionality reduction; constructing a working condition matrix, wherein the working condition matrix comprises working conditions of different dimensions; and fitting a mapping relation between the working condition matrix and the reduced-order coefficient transpose matrix by using a neural network so as to predict the velocity field under the to-be-predicted working condition.

This invention discloses an adaptive self-triggered optimal control method for catalytic rod reactors, specifically comprising: a temperature field model of the catalytic rod reaction process described by a high-dissipation partial differential equation system based on the control input of the cooling material under time triggering, and obtaining a low-order slow subsystem characterizing the high-dissipation partial differential equation system after order reduction processing; constructing a corresponding Hamiltonian function based on the performance index of the low-order slow subsystem, obtaining the optimal control strategy under time triggering control based on the Hamiltonian function, and then obtaining the optimal control strategy under self-triggered control, converting the Hamiltonian function into HJB equations; constructing a self-triggered controller based on an evaluation-execution dual-network structure using data-driven adaptive dynamic programming, and outputting the adaptive self-triggered optimal strategy based on the optimal value function of the HJB equations.

The invention discloses a simulation prediction method based on reduced-order model machine learning, and relates to the technical field of crossing of computer-aided engineering simulation and machine learning, in particular to a simulation prediction method based on reduced-order model machine learning, which comprises the following steps: firstly, performing finite element simulation on automobile parts (such as an anti-collision beam) to obtain simulation data; secondly, selecting sample points by adopting a Latin hypercube sampling method, and verifying that a data set meets an order reduction requirement; then, carrying out dimension reduction processing on the data by applying an order reduction model (such as intrinsic orthogonal decomposition (POD) or singular value decomposition (SVD)); and finally, predicting the data after order reduction by using a Kriging method machine learning model, and evaluating the prediction precision by using a decision coefficient R2 and a root mean square error RMSE. According to the method, through combination of the reduced-order model and machine learning, the simulation calculation efficiency is effectively improved, meanwhile, the accuracy of a prediction result is ensured, and the method is suitable for rapid simulation optimization in automobile design.

The application provides a cold-rolling and pickling mill group flatness control method and system based on multi-source collaborative optimization, relates to the technical field of metallurgical automation and metal pressure processing, and the method comprises the following steps: sequentially performing pretreatment and hot skin pass treatment on steel with a preset chemical composition, performing cold rolling on the steel after the hot skin pass treatment to obtain a cold-rolled sheet; in the cold rolling stage, flatness control parameters and actuator parameters of the cold-rolled sheet are acquired, a collaborative control evaluation function is established, and an iterative order reduction optimization algorithm based on gradient information is used to solve optimal adjustment amounts. The method solves the problems of high-strength steel flatness control difficulty, slow adjustment speed, unstable precision, and scratch defects caused by inlet wave shape, and improves the flatness quality, surface quality and production stability of the cold-rolled sheet. The cold-rolling and pickling mill group flatness control system based on multi-source collaborative optimization is applied to the cold-rolling and pickling mill group flatness control method based on multi-source collaborative optimization.

The invention discloses a submarine cable state remote wireless telemetering system and method based on LoRa, and belongs to the technical field of cable laying state monitoring, and the system comprises a plurality of state monitoring nodes arranged on a submarine cable, a relay node and a shipborne monitoring center. The analysis computer adaptively adopts different compensation strategies according to the monitored packet loss and missing proportion; during light packet loss, trend filling is executed by using the change rate of effective nodes and spatial correlation; during moderate packet loss, confidence weight dynamically attenuating along with interruption time is introduced into the reconstruction model; and during severe packet loss, extracting feature sub-blocks of the spatial physical association constraint matrix to execute order reduction calculation, and recovering data in combination with a spatial interpolation method. According to the method, the problem of data missing caused by unstable wireless communication under the extreme sea condition is solved through a hierarchical compensation mechanism, it is ensured that the state distribution of the whole submarine cable can be stably and accurately reconstructed and early warning can be output under the working conditions of different degrees of packet loss, and the robustness and construction safety of a submarine cable monitoring system are remarkably improved.