128 results about "Dynamic modelling" patented technology

The present application belongs to the technical field of intelligent control and modeling of steel metallurgy process, and relates to a kind of converter decarburization reaction kinetics prediction model construction method and system, comprising: constructing converter end steel composition TSO prediction model;According to the real production data and the steel composition TSO prediction model, the TSO content prediction result of the converter end steel composition is obtained by prediction;Introducing control parameter to correct the preset decarburization reaction kinetics basic model;Each TSO content prediction result is used as end constraint, the parameter iterative optimization of decarburization reaction kinetics basic model is carried out, and based on the corrected decarburization reaction kinetics basic model and the optimal result of parameter, the optimized converter decarburization reaction kinetics prediction model is obtained.The present application realizes the adjustable dynamic modeling of converter decarburization process, can accurately capture the influence of control parameter change on converter smelting decarburization reaction, realizes the closed-loop iteration mechanism of prediction, feedback and correction, and guarantees the continuous leading of model performance.

This invention discloses a fault handling method and apparatus based on main and distribution network coordination, belonging to the field of power system automation technology. The method includes: using a graph neural network to perform topology identification and fault location of the power grid, generating fault impact features; based on the spatial range and electrical connection relationships of the fault impact features, obtaining the switches at both ends of the faulty section of the power grid, and performing fault isolation through remote control tripping; analyzing the fault isolation information using topology impact analysis; and, combined with changes in the current topology of the power grid, generating a power grid protection strategy migration mechanism and initiating a fault recovery process to restore power supply. This invention achieves dynamic modeling of the power grid topology and accurate identification of faulty sections by using a graph neural network to embed the power grid graph and combining multi-channel time series information to generate node potential state vectors, thus improving the real-time performance and accuracy of fault location.

This invention relates to the field of industrial automation control technology and discloses a method for energy consumption balance control of glass fiber surface desizing based on dynamic modeling. The method includes: collecting real-time load data and temperature zone environmental parameters of the glass fiber desizing production line; calculating the theoretical desizing energy consumption and environmental heat loss to generate a basic power command; calculating the temperature zone dynamic hysteresis constant using a thermal inertial observer and superimposing it as a phase offset onto the basic power command to generate an initial power command sequence; extracting power boundary thresholds to verify the initial command amplitude; if there is an amplitude exceeding the limit, calling the power timing allocation logic to backfill the excess energy integral value to the preceding adjacent control cycle, generating a compensated power command sequence that meets physical boundary constraints and driving the heating output component. This invention maintains the spatiotemporal alignment of the control command center of gravity with load fluctuations, eliminates phase mismatch caused by thermal hysteresis, and ensures sufficient enthalpy change of the material.

This invention discloses an adaptive thermal management system for energy storage containers, specifically relating to the field of thermal management technology for energy storage containers. By constructing a joint probabilistic model that integrates multi-source data, introducing Gaussian process regression and multi-precision CFD simulation fusion, and combining chaotic feature extraction and anomaly identification mechanisms, it achieves high-confidence dynamic modeling of complex airflow and temperature fields within the energy storage container and accurate identification of abnormal areas, thereby improving the adaptive control capability of the thermal management system. Furthermore, by collecting temperature and humidity data, constructing a condensation early warning mechanism and micro-airflow intervention strategy, and combining edge computing and reinforcement learning, it achieves real-time identification of condensation risks and optimization of control strategies, effectively solving the defects of traditional solutions such as slow response and control lag in thermal runaway and condensation problems, and improving the safety and reliability of the adaptive thermal management system for energy storage containers under dynamic operating conditions.

The method for analyzing incomplete channel EEG signals based on adaptive orthogonal regression belongs to the field of EEG signal analysis and pattern recognition technology. This invention proposes an embedded feature selection framework for incomplete channel EEG data, enabling robust modeling directly without channel completion and effectively reducing the impact of missing channels on the analysis results. By introducing a channel missingness perception mechanism and an adaptive channel weighting strategy, this invention achieves dynamic modeling of the contribution of information from different channels, significantly improving the model's stability in multi-channel and high-missing-rate scenarios. The orthogonal regression-based feature selection mechanism can maintain the integrity of discriminative information while suppressing redundant features, making it suitable for high-dimensional EEG data analysis tasks. This method has good versatility and can be adapted to different channel scales (such as few channels and high-density channels) and single-modal or multi-modal fusion scenarios, possessing high engineering application value.

This invention relates to the field of artificial intelligence technology and proposes a deep AI-driven method for data anomaly detection and self-healing. The steps include: constructing a data governance and preprocessing platform to preprocess multi-source heterogeneous data and obtain high-quality data sources; employing a multi-algorithm fusion mechanism to detect anomalies in the data sources; constructing a dynamic modeling and self-learning engine to rapidly adapt model parameters based on meta-learning and to automatically search and optimize the model structure based on reinforcement learning to adapt to changes in data distribution and business environment; and providing an intelligent repair and self-healing mechanism for detected abnormal data, automatically correcting, repairing, and performing root cause analysis on data source anomalies, geographical location anomalies, data push failures, and system operation failures. This invention achieves high-precision detection of complex anomalies through a cascaded multi-algorithm fusion detection framework and realizes fully automatic model evolution through a collaborative adaptive engine of meta-learning and reinforcement learning.

This invention discloses an automatic identification and evaluation system for cable-stayed bridge cable forces based on dynamic modeling, specifically relating to the field of dynamic modeling. The system includes: a sensor preprocessing module, a baseline modeling module, a hybrid prediction module, an evaluation and early warning module, and a self-optimizing iterative module. It proposes a pure data-driven AI model that integrates multi-source data fusion. This model fuses vibration signal data features with prior knowledge of string vibration through a dual-channel architecture and is trained using a composite loss function constrained by physics and rate of change, achieving intelligent identification of cable forces under complex working conditions. Furthermore, it constructs an intelligent evaluation framework with online cross-validation, trend prediction, and multi-source correlation, achieving model self-optimization and long-term adaptation through incremental learning. Addressing the problems of weak generalization, physical inconsistency, and poor adaptability of data-driven AI in engineering, this invention proposes a general architecture integrating multiple technologies to achieve accurate identification of tension states in multiple scenarios.

The application discloses a three-dimensional human body posture estimation method based on dynamic modeling and bone topological consistency, multi-modal input construction and feature extraction, feature extraction is respectively performed on input RGB images, two-dimensional joint coordinates and skeleton structure diagrams, and each mode feature after extraction is uniformly mapped to the same dimension, thereby providing a basis for subsequent multi-modal fusion; by sequentially executing five core processes of multi-modal input construction and feature extraction, dynamic credibility modeling and adaptive fusion, bone topological guided repair, multi-scale detail enhancement and three-dimensional regression, and loss function joint optimization, the problem that a static strategy is adopted for multi-modal fusion of an existing three-dimensional human body posture estimation method and the mode contribution proportion cannot be dynamically adjusted according to a scene is effectively solved.

This invention discloses a carbon neutrality analysis method and system, relating to the field of carbon neutrality technology. The method includes the following steps: S1, Enterprise carbon emission tracking: setting up data collection points at various stages of an enterprise to collect carbon emission data in real time, and integrating and storing it through a blockchain platform; S2, Full gas coverage monitoring and accounting; S3, Dynamic modeling and prediction. This carbon neutrality analysis method and system employs system dynamics to construct a dynamic carbon neutrality analysis model, capable of capturing the dynamic interactions between factors such as carbon emissions, carbon absorption, technological progress, and policy changes. By simulating the evolution of carbon neutrality paths under different scenarios, the model can predict and analyze the achievement paths and feasibility of carbon neutrality targets under different scenarios, providing valuable decision support for policymakers and enterprises, and contributing to the successful achievement of climate goals.

This invention relates to the field of dynamic modeling technology, specifically to a method and system for displaying a bridge structure BIM model, solving the technical problem of low model loading and rendering efficiency in existing technologies. The method includes: acquiring the state data of the bridge structure's BIM model within a display observation window; the state data includes model analysis pressure data, attribute query load data, and component dynamic association data; the component dynamic association data is used to characterize the association relationship between dynamic monitoring data and components; based on the state data, determining the attribute refresh frequency correction coefficient for each component in the BIM model; the attribute refresh frequency correction coefficient is used to characterize the correction magnitude of the component's attribute refresh frequency; correcting the attribute refresh frequency of the corresponding component based on the attribute refresh frequency correction coefficient, and loading and displaying the BIM model's attributes according to the corrected attribute refresh frequency.

The application discloses a kind of dynamic graph convolution network roll temperature field prediction methods based on physical guidance, belong to metal rolling process intelligent prediction technical field, this method will roll be discretized into physical node, introduce virtual dynamic heat source node, establish static edge according to adjacency relationship, form initial dynamic calculation graph;Build physical guidance dynamic graph convolution layer, determine neighbor set, aggregate information based on attention mechanism, embed priori knowledge by physical relationship encoder, introduce physical residual correction and learnable gating mechanism, integrate data-driven prediction and physical law;Multiple dynamic graph convolution layers are connected in series according to time step to build multi-step rolling prediction network;End-to-end training is carried out through loss function, and the timing accurate prediction of temperature field is realized.The application effectively solves the problem of temperature field dynamic modeling under the action of moving heat source, has high precision, strong generalization ability and real-time performance, and is suitable for online prediction and control optimization of roll induction heating process.

The invention discloses a tumble risk assessment method and system based on individualized information, and relates to the technical field of medical assessment and artificial intelligence, and the method comprises the following steps: a data acquisition step, a support period detection step, an individualized feature fusion step, a gait period segmentation step, a feature extraction step, and a time sequence coding step. A risk assessment step; firstly, multi-channel plantar pressure time sequence data of a subject and individualized information of the subject are obtained, and then through five-layer progressive processing, the problems of supporting period self-adaptive detection, gait cycle precise segmentation, multi-dimensional feature extraction, time sequence dynamic modeling and self-adaptive model training are solved respectively. And finally, accurate individual fall risk assessment is realized. Thresholds are automatically adapted for subjects with different physiological features, the gait deterioration trend caused by fatigue is captured through periodic-level double-flow time sequence modeling, and self-adaptive personalized feature learning is achieved through cascaded personalized information layer-by-layer fusion.

The present application relates to a kind of cabin foam filling protection method and system based on collision perception, belong to vehicle manufacturing technical field, method includes establishing passenger-cabin dynamic topology model based on real-time sensing data, can adapt to any passenger posture, such as semi-lie, roll, be favorable to solve the failure problem of traditional air bag in automatic driving scene, from collision prediction to foam solidification completion, total delay is shorter, meet the protection time limit requirement of extreme collision, the energy absorption efficiency of chemical foaming material unit volume is higher, be favorable to significantly reduce the peak acceleration of passenger, by dynamic modeling and gap filling, be favorable to realize the filling of all gaps between the body of passenger and interior, improve protection coverage, effectively reduce the risk of limb impact interior trim.

This invention relates to the field of multi-source coordinated control technology in distribution networks, and discloses an automatic switching method and system for multiple power sources in a distribution network. The switching method includes: dynamically modeling the transient power flow of the main power source and distributed power sources in a multi-source distribution network, and performing dynamic response analysis of topology changes; evaluating the system energy obtained from the dynamic modeling using the transient energy function method, calculating the kinetic and potential energy components before and after the switching, and determining the system energy balance state based on the comparison result of the energy difference and the critical energy threshold; and executing phased soft switching control based on the energy evaluation result, through sequential control logic of synchronization stage, power sharing stage, and switching transition stage, and performing gradual power transition between the main power source and distributed power sources according to a predictive control algorithm. This invention achieves real-time power flow reconstruction under topology changes, energy-driven switching decisions, and smooth power transition, reducing voltage fluctuations and transient impacts caused by switching.

The application discloses a flue gas desulfurization emission concentration control method, related device and system, relates to the flue gas purification technical field, and will run process variable time series data be input into the pre-trained deep learning prediction model, eliminate sequence non-stationarity and variable scale difference by the normalization layer, the embedding layer converts the time series data into the time series slice embedding vector which retains semantic information, the decoding layer extracts the causal characteristics between the running variables and the emission concentration by dynamically modeling the dependency relationship between each time series slice through the attention mechanism, and the output layer outputs the emission concentration prediction value through the pooling and linear transformation. The prediction value replaces the current measured value and is input into the PID control module, so that the control loop knows the change trend of the emission concentration in advance, the absorbent addition amount is adjusted before the actual change of the concentration, time delays introduced by the reaction process, equipment execution and measurement points are effectively compensated, the timeliness and accuracy of the absorbent adjustment are improved, standard flue gas emission is ensured, and the absorbent consumption is reduced.

The application provides a method, device and equipment for constructing a power system model based on a large language model, relates to the technical field of model construction, and solves the defect that the comprehensive performance of a model obtained by dynamic modeling of a power system is poor. The method comprises the following steps: based on the operation data of the power system under a disturbance working condition, a plurality of differential equation candidate models are constructed and iteratively trained to determine the comprehensive evaluation parameters of each differential equation candidate model; in the case that at least one differential equation candidate model meets a convergence condition, a target differential equation candidate model with optimal comprehensive evaluation parameters is determined; based on target algebraic variables and target input variables corresponding to the target differential equation candidate model, a plurality of algebraic equation candidate models are constructed and iteratively trained to determine a target algebraic equation candidate model with optimal comprehensive evaluation parameters; and based on the target differential equation candidate model and the target algebraic equation candidate model, a power system model is constructed.

A dynamic modeling collaborative optimization control method for malware propagation relates to an industrial internet network security control method, and the present application is based on the average field theory to couple the network structure and dynamics, and constructs a propagation model for quantifying the heterogeneity of infection rate. Specifically, the variable infection rate beta is introduced by using the DomiRank centrality index, a high-level heterogeneous SIS model is established, and its stability is analyzed. By comparing the heterogeneous propagation models based on Degree, PageRank and DomiRank three centrality indexes, the superiority of DomiRank index is verified. Then, the collaborative optimal control strategy is introduced to hinder the propagation. Experimental verification shows that on different network topologies, the model can reduce the propagation risk, inhibit the propagation scale and quantify the threshold change; the collaborative control strategy realizes the minimization of the propagation scale and the minimum of the cumulative total cost.

This invention discloses a method for dynamic modeling of the temperature field and prediction of overheating risk in cable connectors, relating to the field of electrical equipment condition monitoring and thermal management technology. The method includes constructing the connector's geometric domain and establishing a fully coupled electro-magnetic-thermal-mechanical initial value model containing Lorentz force correction terms and eddy current loss heat source terms; jointly assembling the Lorentz force and eddy current loss terms to form a magneto-thermal coupling correction matrix, calculating the equivalent heat source field of a strong magnetic field; solving the temperature field and updating the conductivity and permeability distributions in reverse, forming a bidirectional coupled iterative loop until a converged temperature field is output; extracting hot spot trajectories and temperature gradient vector fields based on the converged temperature field, inputting them into the thermal aging kinetic model of the insulation material to generate a multidimensional indicator surface for overheating risk, determining the risk level and outputting a warning signal. This invention improves the accuracy of connector temperature field prediction and the reliability of overheating risk warning under strong magnetic field environments through bidirectional coupled iterative correction and fully coupled modeling.

This invention relates to the field of metal welding inspection technology, specifically to an intelligent inspection method for metal welding processing based on industrial vision. The method includes: constructing a multimodal welding process tensor characterizing the coupling relationship between welding energy, material state, and metallurgical behavior; inputting this tensor into a reasoning computation network based on physical information constraints to forward deduce the evolution of the molten pool morphology and temperature gradient field; simultaneously executing a state inversion algorithm using multispectral fused images as observation data and welding process parameters as boundary conditions to optimize the intrinsic parameters of the welding heat source model; and fusing the forward deduction and inverse optimization results to construct a dynamic digital twin of the welding process. The method calculates the solidification rate, thermal cycle curve, and latent heat of phase transformation at each point on the welding line in real time, compares each point with the standard values ​​of the qualified process window, identifies abnormal locations, and outputs a structured inspection report containing coordinates and deviation types. This invention achieves coupled characterization and dynamic modeling of the welding process, improving the accuracy and real-time performance of the inspection.

This invention discloses a method and system for detecting cable condition anomalies based on dynamic modeling, relating to the field of power system condition monitoring and fault diagnosis technology. The method includes acquiring signals synchronously collected by multiple sensors on the cable, detecting abnormal events using the root mean square value of a sliding window, extracting abnormal signal segments, and calculating the arrival time difference and intensity difference of the same signal between different sensors. These differences are compared with a pre-built database of external interference and internal fault propagation features to determine the signal source. If it is external interference, adaptive filtering is used to remove interference components, obtaining a purified signal. Finally, the purified signal, combined with cable body temperature and load current parameters, is input into a cable condition assessment model to output a health score. This method achieves accurate differentiation and adaptive filtering of external electromagnetic interference and internal faults. Combined with multi-parameter fusion assessment, it significantly reduces the false alarm rate and improves the accuracy and reliability of anomaly detection.

The application provides a dynamic modeling method and system for multi-field skill AI automatic semantic labeling, and relates to information retrieval, medical health and cross-field skill fusion scene. Through nonlinear dynamic modeling and biomedical stability control, the semantic label automatic generation and real-time matching of talent skill and health intervention effectiveness are realized. The application innovatively integrates the sound wave frequency of fetal brain promoting music method, maternal action instruction and blood type nutrition scheme into the "skill-time" frequency domain space, combines the Gevrey smoothing operator and fractional derivative evolution equation, accurately separates the temporary fetal movement fluctuation and low-frequency core characteristics, and breaks through the characterization limitation of traditional models on nonlinear biological coupling effect. By introducing the "intervention effect-time" frequency domain component and local dependency constraint, the short-term effectiveness and long-term value of music intervention on fetal neurodevelopment are quantified, and the model distortion problem caused by extreme data or cross-field parameter resonance in traditional methods is solved.

The application discloses a fall risk assessment method and system based on individual information, and relates to the technical field of medical assessment and artificial intelligence, and comprises the following steps: a data acquisition step, a support period detection step, an individual feature fusion step, a gait cycle segmentation step, a feature extraction step, a time sequence coding step, and a risk assessment step. First, multi-channel foot pressure time sequence data of a subject and individual information of the subject are acquired, then through five-layer progressive processing, problems of support period adaptive detection, gait cycle accurate segmentation, multi-dimensional feature extraction, time sequence dynamic modeling and adaptive model training are solved respectively, and finally precise individual fall risk assessment is realized. The application automatically adapts to the threshold of subjects with different physiological characteristics, captures the gait deterioration trend caused by fatigue through cycle-level double-flow time sequence modeling, and realizes adaptive personalized feature learning through layer-by-layer fusion of cascaded individual information.

This invention discloses a method and system for collaborative identification of hydraulic fracturing construction anomalies and fracturing effectiveness. It collects geological data of the fracturing reservoir and multi-source construction data, and performs standardized preprocessing. The fracturing construction process is divided into multiple core stages, and real-time stage status identification is performed. Multi-source dimensional features are extracted for each identification stage, and fracturing initiation confidence index, expansion effectiveness index, and anomaly risk index are constructed and calculated. Based on the three core indices and stage status variables, the types of construction anomalies are classified and identified. Simultaneously, a comprehensive score for fracturing effectiveness is calculated and effectiveness levels are assigned. Finally, matching construction and treatment suggestions are output in a linked manner. This invention achieves collaborative identification of rapid anomaly conditions and real-time evaluation of fracturing effectiveness during fracturing construction. It relies only on low-cost monitoring parameters easily obtained in underground coal mines. Through phased dynamic modeling, it significantly reduces the cross-stage misjudgment rate, fully meeting the on-site engineering needs of "construction, identification, and adjustment simultaneously" in underground coal mine fracturing.

The application relates to the technical field of intelligent fire station, in particular to an intelligent modular prefabricated cabin type tunnel fire station terminal dynamic early warning system based on edge computing and multi-source sensing. The system comprises a multi-source data acquisition unit, an edge computing processing unit, an intelligent early warning analysis unit and a data management unit. The edge computing processing unit is used for real-time fusion and dynamic modeling of the collected data, multi-source data are fused based on Kalman filtering and LSTM, and a risk evolution model with fast and slow dynamic components is constructed by adopting singular perturbation theory. The improved long short-term memory network adopts a parallel GRU branch to construct a multi-scale feature extraction architecture: a short-term branch captures second-level fast features such as flame flickering and smoke concentration sudden change, a long-term branch captures minute-level slow change trends such as temperature gradient rise, and an adaptive attention mechanism is combined to give dynamic weights to different time scale features. The design improves the pertinence and accuracy of feature extraction in complex scenes.

The application discloses a kind of intelligent eccentric wheel design method and system based on pulse wave waveform, which comprises the following steps: step 1, receive pulse waveform image and adopt multi-mode extraction algorithm to process, obtain the feature point set containing waveform amplitude data sequence and waveform angle data sequence, simultaneously obtain three-dimensional printing material attribute data and dynamic load damping parameter;Step 2, the waveform angle data sequence is mapped as polar angle, the waveform amplitude data sequence is mapped as polar radius, an initial polar coordinate radius sequence is generated after interpolation processing, and initial eccentric wheel profile data is generated accordingly.The radial displacement response of the eccentric wheel profile under the actual operating environment is dynamically modeled, and the reverse compensation factor is extracted accordingly.This mechanism injects compensation gain in advance through dynamic modeling during the digital design phase, ensuring that the eccentric wheel can still accurately reproduce the target pulse wave under pressure movement, and achieving high consistency between mechanical output and medical atlas.

The present application relates to the field of water pollution control and treatment, in particular to an ecological filter rural water purification system, which comprises a data acquisition module, an optimal state feedback module, a dynamic modeling module and an optimal control parameter output module. The data acquisition module collects water quality parameters through multiple sensors, generates water quality time series data through synchronization, anomaly identification and distortion data reconstruction, and simultaneously collects and standardizes structural parameters; the optimal state feedback module obtains relevant indexes based on the fuzzy PID algorithm, and then outputs them through firefly algorithm optimization; the dynamic modeling module respectively constructs ammonia nitrogen degradation models in the aerobic zone and COD degradation models in the anaerobic zone, correlates the two zones by hydraulic retention time, and incorporates environmental disturbance correction models; the optimal control parameter output module outputs control parameter intervals through a decision tree, and particle swarm optimization algorithm is used to search for optimal parameters in the intervals and output them; the system can efficiently purify rural water sources and provide precise control basis for the water purification process.