135 results about "Multiscale modeling" patented technology

The invention discloses a big data-driven hydrogen fluoride purification risk entropy assessment and multi-parameter monitoring system, which relates to the technical field of chemical process monitoring, comprises a multi-mode heterogeneous sensor network, and realizes high-precision detection and three-dimensional monitoring by using a nanowire FET (Field Effect Transistor) and the like. The space-time tensor decomposition module extracts features and identifies a causal relationship; the risk entropy manifold learning module evaluates the risk; the self-adaptive twin network monitors the abnormity and simulates and disposes the abnormity; and a knowledge graph-reinforcement learning system decision making subsystem and a plurality of subsystems such as an optical monitoring subsystem and a multi-scale modeling subsystem are also provided, so that whole-process risk management and control are realized. The hydrogen fluoride purification monitoring level is greatly improved, the detection sensitivity and the anomaly detection accuracy are remarkably improved, risk early warning is more timely, decision response is accelerated, the production efficiency is improved, energy consumption is reduced, the system has self-repairing and self-power-supply capabilities, data are safe and traceable, reliable operation of the system is guaranteed, and economic losses and potential safety hazards are reduced.

The invention discloses a fracture structure multi-scale modeling method based on multi-source data fusion, and belongs to the field of geological modeling, and the method comprises the following steps: S1, collecting and preprocessing multi-source data; s13, aligning the data, and integrating the data from different sources together; s2, three-dimensional geologic modeling: S21, generating an initial three-dimensional grid by using geologic modeling software to obtain an initial three-dimensional geologic body model; s22, dynamically adjusting the density of the initial three-dimensional grid by using a self-adaptive grid division technology; s23, using a machine learning algorithm to identify and classify faults; s3, expanding the three-dimensional geologic body model macroscopically and microcosmically; and S4, performing dynamic simulation and prediction by using the three-dimensional geologic body model. By adopting the fracture structure multi-scale modeling method based on multi-source data fusion, the accuracy and reliability of the fracture structure model are improved by integrating multiple data sources and multi-scale analysis.

The invention discloses a mechanical property prediction method of a composite material based on an improved sparrow algorithm-random forest, and belongs to the technical field of composite material property prediction, and the method comprises the following steps: carrying out finite element multi-scale simulation on a carbon fiber composite material to obtain an elastic constant matrix; connecting the elastic constant matrix material to a macroscopic model for macroscopic simulation to obtain sample data; a random forest RF model is constructed in Matlab software; an improved sparrow search algorithm is introduced into a random forest RF model to construct a CFSSA-SF prediction model; training a CFSSA-SF prediction model by using the training set data; and inputting test set data into the CFSSA-SF prediction model to obtain a prediction result. According to the method, the finite element method is adopted to carry out multi-scale modeling, the improved sparrow algorithm is combined with the random forest to construct the fusion CFSSA-RF prediction model, and the mechanical properties of the carbon fiber composite material under different parameters are effectively predicted.

The invention provides a construction method of an urban low-altitude wind field digital twinning system, which comprises the following steps: constructing an urban basic road network skeleton and performing region division, generating a building block model with real textures by using oblique photography data, and forming an urban three-dimensional space geometric model library; capturing atmospheric information in real time through a radar to generate high-resolution three-dimensional wind field scanning data covering a target area; processing detection data of the laser wind finding radar, performing simulation calculation on a wind field in combination with an urban three-dimensional space geometric model, and generating sub-meter gridding dynamic wind field data of an urban low-altitude area; and performing three-dimensional reduction and vivid representation on the obtained dynamic wind field data by using a visual rendering technology to form an interactive urban low-altitude wind field digital twin system. By integrating multi-scale modeling, laser wind finding radar, wind field simulation and visual rendering technologies, real-time monitoring, dynamic simulation and visual display of an urban low-altitude three-dimensional wind field are achieved, and low-altitude flight safety and operation efficiency are improved.

The invention discloses a pavement throwing detection method and device based on deep learning, electronic equipment and a program product. The method is realized through a trained detection model, the model adopts an LMSADet detection head, a multi-scale feature extraction and space attention mechanism is introduced into a task branch, and multi-scale modeling is decoupled from a backbone network and a neck network and integrated to the detection head so as to fit a detection task to directly optimize local details and scale differences of a throwing target. In order to suppress background interference and improve the recognition effect of fuzzy boundaries, the neck network is added into an MSHA module so as to efficiently capture the semantic relation between the thrown object and the background and enhance the regional understanding ability. A C3ESP module is introduced into the backbone network, deep features are extracted through stacking depth separable convolution, and information loss is avoided in combination with residual optimization fusion; meanwhile, a PEMA attention mechanism is introduced, the importance of different receptive field features is dynamically adjusted, the model focuses on key features, data information is captured more comprehensively, and therefore the detection performance is remarkably improved.

The invention discloses a multivariate time sequence prediction method based on timestamps and multi-scale modeling, and the method comprises the steps: extracting features through multi-scale feature fusion, carrying out the convolution operation of an input time sequence through employing convolution kernels of different scales, extracting and splicing short, medium and long-term features, and carrying out the fusion through employing a multi-head attention mechanism. Therefore, local details and global trends in the time sequence are captured, and the modeling capability of the model on a complex time mode is improved; timestamps are coded into high-dimensional vectors, the high-dimensional vectors are mapped through an encoder, the complex relation between the timestamps is captured, and the prediction capacity of the model for periodic and tendency changes is enhanced; a self-defined loss function is adopted to carry out model training, so that the model robustness is improved, and meanwhile, relatively high prediction precision is kept; and applying the trained model weight to a test set. Through combination of multi-scale feature fusion, timestamp feature extraction and a self-defined loss function, the precision and robustness of multivariate time sequence prediction are remarkably improved.

The invention discloses a complete machine variable-dimension simulation method based on a circumferential average flow model, belongs to the technical field of aero-engine numerical simulation and multi-scale modeling, and solves the problem that complete machine simulation efficiency and local flow detail precision are difficult to consider at the same time in the prior art. And traditional full-three-dimensional computing is too high in resource consumption and cannot quickly evaluate the performance of the whole machine. According to the method, a zero-dimensional complete machine and component two-dimensional model of the aero-engine is firstly established, dimensionality reduction is carried out by using a circumferential average N-S equation, the two-dimensional model is embedded into the zero-dimensional model, an equivalent replacement variable reconstruction equation set is solved, synchronous convergence of the complete machine and component models is realized, and simulation precision and efficiency are improved. According to the method, a full coupling mode is adopted, two-dimensional dimension reduction modeling is combined, minute-level convergence is achieved, the simulation error is not larger than 5%, the simulation precision is improved, the calculation efficiency is improved, rich S2 flow field information can be provided, and the research and development cost and period are reduced.

The invention relates to multi-scale modeling and mechanical and thermodynamic property simulation of a particle reinforced biological composite material, and belongs to the crossing field of biology, material science and computer simulation. The method specifically comprises the following steps: constructing a polyether-ether-ketone (PEEK) high-molecular polymer and a graphene reinforced composite material model thereof through a cross-linking algorithm under a microscopic scale, and simulating and calculating the mechanical and thermodynamic properties of the model by adopting molecular dynamics; in the microscopic scale, constructing a representative volume element model of the microstructure artificial skeleton, inputting property parameters calculated by molecular dynamics into a microscopic model, and calculating microscopic mechanical and thermodynamic properties of the model by adopting a substance point method; and inputting the property parameters obtained under the microscale into the macroscopic model, and calculating the overall macromechanical and thermodynamic behavior response of the material by adopting a finite element method. According to the method, mechanical and thermodynamic responses of the biological composite material are finally simulated through transmission of property parameters of different scales, and theoretical support is provided for research and formula design of the particle reinforced biological composite material.

The invention discloses a short temporary rainfall forecasting method based on a CAMS-Unet model. The method comprises the steps that original radar echo image data are acquired and preprocessed; a CAMS-Unet short temporary rainfall forecast model is constructed; based on the target radar echo image data, training optimization is carried out on the CAMS-Unet short temporary rainfall forecasting model, and a target CAMS-Unet short temporary rainfall forecasting model is obtained; and obtaining a to-be-predicted radar echo image, inputting the to-be-predicted radar echo image into the target CAMS-Unet short temporary rainfall forecasting model, and outputting to obtain a predicted radar echo image. According to the method, the radar echo image is preprocessed through three stages of data set screening, abnormal value and vacancy value processing, denoising and data enhancement processing; by constructing a CAMS-Unet model comprising a global feature extraction module CAMM and a local feature extraction module MSFM, the problems of multi-scale modeling imbalance and insufficient space-time isomerism capture are solved.

The invention relates to the technical field of neuromodulation and rehabilitation treatment, and discloses an intelligent magnetic field neuromodulation rehabilitation system, which comprises a signal acquisition and feature extraction module for acquiring brain signals of a patient and extracting multi-scale variables including microscopic neuron membrane potential, mesoscopic brain region synchronism and macroscopic cognitive state; the magnetic field adjusting module is used for generating and outputting magnetic field stimulation signals according to the optimization result, and the magnetic field stimulation signals comprise frequency, intensity and waveform parameters of a magnetic field; the dynamic optimization module is used for calculating an optimal path of the magnetic field stimulation signal based on the input multi-scale variable and the constraint condition; and the closed-loop feedback control module is used for receiving the real-time brain signal to update the system state and adjusting the parameters of the magnetic field stimulation signal based on feedback. Through multi-scale modeling, real-time feedback regulation and control and man-machine interaction technologies, precise regulation and control, efficient adaptability and visual clinical operation effects of the nervous system are achieved.

The invention discloses a spinning forming dislocation evolution prediction and process optimization method based on multi-scale modeling, which combines three calculation methods with different scales and levels, namely macroscopic finite element simulation, microcosmic crystal plasticity simulation and microcosmic dislocation dynamics simulation. A complete perspective from macroscopic mechanical behaviors to microscale mechanical response and dislocation density evolution and then to microscale single dislocation motion and interaction mechanism can be provided, so that the plastic forming process of the metal material can be understood more comprehensively. Not only are the prediction precision and reliability improved, but also the understanding depth of the material deformation behavior and the influence factors thereof is enhanced. By integrating information of different scales, key characteristics such as macroscopic stress, strain distribution, grain deformation response, dislocation density evolution and movement and interaction of a single dislocation of the material in the plastic forming process can be predicted more accurately. Meanwhile, in combination with multi-scale simulation, process parameters can be optimized to obtain better forming quality and performance.

The invention discloses a muck treatment capacity monitoring method and a muck treatment capacity monitoring system, and relates to the technical field of shield construction and muck treatment capacity prediction treatment, and the method comprises the following steps: collecting operation parameters of a shield tunneling machine deslagging and conveying link, calculating a muck flow coupling index, evaluating a deslagging link coupling state, and carrying out optimization; the load coupling index of the shield tunneling machine is calculated, the energy distribution balance is judged, and dynamic adjustment is conducted according to the unbalance state; calculating the energy consumption deslagging propulsion efficiency, evaluating the matching degree, and optimizing the power and conveying parameters of each link; a CNN and LSTM combined multi-scale modeling method is adopted to predict the future muck handling capacity, and online correction is carried out through a sudden change adaptive network; and finally, fusing the standardized data set with the actual operation parameters to generate a unit time muck handling capacity sequence. By means of the method, the deslagging and propelling matching degree of the shield tunneling machine can be improved, the energy utilization efficiency is optimized, and high-precision prediction and real-time regulation and control of the muck handling capacity are achieved.

The invention provides a method for predicting strong wind along a high-speed rail based on multi-scale modeling and time-frequency feature fusion. The method comprises the following steps: step 1, collecting and preprocessing historical data of wind speed monitoring stations along the high-speed rail; step 2, carrying out decomposition algorithm processing and down-sampling processing on the preprocessed data; step 3, constructing a multi-scale time-frequency fusion prediction network; the multi-scale time-frequency fusion prediction network comprises a TCN network layer, an LSTM network layer and a cross attention mechanism; step 4, training the multi-scale time-frequency fusion prediction network; and 5, performing future wind speed prediction by using the trained multi-scale time-frequency fusion prediction network. The method is suitable for a multi-time scale prediction task in a complex wind speed time sequence scene, and can be used for strong wind early warning in the running process of a high-speed train.

The invention discloses a new energy missing data completion method and system based on multi-model fusion. The method comprises the following steps: performing linear and nonlinear correlation two-stage feature screening on a collected new energy data set; normalizing the data set, constructing a missing data mask according to a missing proportion parameter, and dividing the data set; the designed AFMFormer model is constructed and trained; a self-adaptive frequency domain feature extraction module constructed in the model utilizes a data-driven dominant frequency extraction and frequency spectrum noise suppression mechanism to enhance the modeling capability of the model for a long-sequence dominant mode structure; the multi-granularity time sequence coding module realizes semantic consistent feature fusion through short-term features and long-term trends of a multi-scale modeling time sequence and through a learnable weight and an adaptive alignment mechanism, and generalization ability training of the model under a complex time sequence structure is further improved. Compared with a traditional method, the method shows higher precision, robustness and generalization ability in a high-fluctuation and high-missing-rate data scene.

The invention belongs to the technical field of cross-modal image-text retrieval, and discloses an image-text cross-modal retrieval method based on an embedded sparse gate expert hybrid model, which comprises the following steps of: cross-modal multi-scale modeling: extracting multi-scale image features of an image by utilizing a cavity space pyramid pooling module ASPP, dynamically weighting text features by utilizing a multi-scale activation factor, and carrying out multi-scale multi-scale modeling; image-text cross-modal multi-scale semantic alignment is realized; multi-scale cross-modal feature fusion: designing a multi-scale cross-modal router, fusing image and text features through cross attention, and extracting cross-modal joint features in a scale division manner through an expert network; and two-way triple loss calculation: adopting a two-way triple loss function, and combining with intra-scale and cross-scale constraint optimization feature space to realize joint optimization of multi-scale and cross-modal levels to obtain a final cross-modal retrieval result. According to the method and the device, the precision and the efficiency of cross-modal image-text retrieval are improved.

The invention discloses a system and a method for predicting reaction conditions of a menthane carboxamide cooling agent, and aims to optimize the reaction conditions, improve the experiment efficiency, reduce the production cost and ensure the stable product quality through an intelligent method. According to the system, the design experiment DoE and the response surface method RSM technology are combined, the relation between reaction conditions and products is systematically analyzed, multi-scale modeling is utilized, a molecular reaction mechanism and a macroscopic reactor model are combined, seamless connection from a laboratory to an industrial scale is achieved, and challenges in the amplification process are solved. By means of real-time data monitoring and feedback adjustment, the system can dynamically optimize the reaction process, controllability and stability of the production process are improved, the scientificity and intelligent level of reaction optimization are improved, and an efficient, controllable and environment-friendly solution is provided for large-scale production of the menthane carboxamide cooling agent.

The invention relates to the technical field of ocean current data analysis, in particular to a multi-scale modeling and verification method and system based on ocean current spring layer structure analysis. And obtaining the thermocline and halocline parameters of the target sea area and carrying out abnormal value elimination and spatial interpolation to form a thermocline data set. A convolutional neural network is used to extract spring layer space structure features, and based on Gaussian curvature quantification boundary complexity, a thermocline and halocline equivalent geometric model is constructed. On the basis, taking the equivalent geometric model as a boundary condition, and performing multi-scale decomposition on the Navier-Stokes equation set to generate a dynamic approximate equation; and then inputting the approximate equation and the equivalent geometric model into a physical information neural network for constraint training to obtain a multi-scale flow field prediction model, and comparing the multi-scale flow field prediction model with actually measured flow field data to complete verification. According to the method, automation, refinement and multi-scale coupling of spring layer structure modeling are achieved, and scientificity and engineering applicability of ocean current modeling are improved.

The invention relates to the technical field of eye fundus image processing, and particularly discloses an eye fundus image multi-label classification model and method, and the method comprises the steps: extracting the features of eye fundus images from RGB and gray eye fundus images through two branch structures based on TransNeXt; the multi-scale space-channel attention mechanisms are respectively embedded in the two branch structures, modeling is carried out after each feature extraction stage of each branch structure, and multi-scale modeling is carried out on a feature map of each stage; and the feature interaction module is used for realizing communication between the two branches, integrates a large-selectivity module to detect local details and global context information of modeling, performs feature extraction through standard convolution and expansion convolution by using a double-path architecture, and performs splicing, dimension reduction, aggregation and compression processes in sequence after feature extraction, so as to obtain the communication between the two branches. And a final output result is generated, so that the problems confronted by fundus image multi-label classification at present are solved.

The invention discloses a bearing fault noise immunity diagnosis method based on IPDSCS and Swin Transformer, and the method comprises the steps: collecting vibration signals of a bearing under different working conditions, and obtaining a plurality of groups of original vibration signal data; performing wavelet transform on the original vibration signal data, and converting the original vibration signal data into a time-frequency image; constructing a feature extraction model based on an improved inverted pyramid depth separable convolution sequence, and extracting the time-frequency image to obtain a multi-dimensional feature vector; using the feature vector as input data, performing model training based on a Swin Transform deep learning network, and establishing a bearing fault diagnosis model; and inputting a to-be-diagnosed bearing vibration signal into the bearing fault diagnosis model, and outputting a corresponding fault category. According to the method, the noise immunity of signal processing is improved through wavelet transform denoising and an IPDSCS feature extraction method; a Swin Transform network is adopted to carry out multi-scale modeling on the multi-dimensional features, so that the accuracy and robustness of fault diagnosis are remarkably improved; and high-precision diagnosis of bearing faults is realized.

The invention discloses a prediction method for identifying a protein-protein interaction site. According to the method, a deep learning framework is constructed based on protein chain hierarchical graph construction and double-branch graph neural network learning. The method comprises the following steps: firstly, constructing a corresponding hierarchical graph for each protein chain, including a residue-level graph and an atomic-level graph; next, the method constructs an isotropic graph neural network (EGNN) module to extract residue-level embedding with isotropic features. After a GraphSAGE module is further used for extracting atomic-scale embedding, the method integrates layered graph features by using a comparative learning strategy so as to learn residue-scale and atomic-scale consistency embedding. Finally, an improved gated multi-head attention mechanism is used for fusion embedding weighting, and residue-level interaction classification prediction is performed through a multi-layer perceptron. A comprehensive evaluation result on a plurality of data sets shows that the method is remarkably superior to an existing method. In conclusion, according to the method, various advanced technologies such as graph structure denaturation, multi-scale modeling and comparative learning are fused, and an accurate and steady solution with expansion potential is provided for protein interaction prediction. The method can assist researchers in deeply recognizing key protein acting sites and promoting analysis work of cell signal channels and metabolic networks.

The invention provides a human skeleton behavior recognition method based on an improved space-time diagram convolutional network (ST-GCN). According to a traditional ST-GCN method, structural relations of joint points are modeled through space graph convolution, dynamic changes are captured in combination with time convolution, however, the problems that a topological structure is fixed, time sequence modeling is limited and channels have no difference weighting exist, and the recognition precision and adaptability of the traditional ST-GCN method are limited. According to the method, a joint channel attention module (JCA) and a multi-scale path attention residual network (MSPARN) are introduced on the basis of an ST-GCN architecture, so that the adaptive weighting capability of a feature channel and the multi-scale modeling capability of a time sequence dynamic feature are respectively improved. Specifically, the JCA module strengthens the response of the key channel by dynamically adjusting the channel weight; the MSPARN module utilizes multi-scale cavity convolution and a path attention mechanism to enhance the processing ability of the model to complex time sequence dynamics. Experiments show that the method has strong robustness in a complex background and a multi-person scene, and has wide application prospects, especially in the fields of intelligent security and protection, health monitoring, human-computer interaction and the like.

The invention discloses an equipment early warning method and equipment based on intelligent diagnosis and a medium, and belongs to the technical field of equipment monitoring and early warning. The method comprises the following steps: deploying a temperature sensor network to a to-be-detected device to obtain original temperature time sequence data; normalizing the original temperature time sequence data to generate a normalized temperature value; determining a weighted second order gradient entropy feature based on the normalized temperature value; constructing an end-to-end fault diagnosis model; updating the fault prototype vector weight according to the equipment working condition change of the to-be-detected equipment; determining a confidence score; inputting temperature data collected in real time into the trained end-to-end fault diagnosis model to obtain fault probability distribution; and when the confidence score exceeds a confidence threshold and the fault probability is higher than a preset probability threshold, early warning is performed. According to the method, the technical effects of feature retention of non-stationary temperature data, cooperative detection of composite faults, multi-scale modeling and optimization of dynamic adaptability are achieved.

The invention provides a real-time three-dimensional greening maintenance system, method and device based on multi-sensor fusion and a medium, and the method comprises the following steps: S1, collecting multi-modal data of a target area through multiple sensors, including point cloud, environmental parameters and multi-view images; s2, performing space-time registration, noise filtering and feature fusion on the multi-modal data to generate a vegetation three-dimensional data set; s3, performing multi-scale modeling on the data set based on a Gaussian mixture model (GMM) to generate a dynamically updated vegetation three-dimensional model; s4, adopting a hierarchical data structure and a GPU parallel rendering technology to realize real-time visualization of more than 30FPS in a dynamic scene; and S5, generating a vegetation health assessment report and an automatic maintenance decision in combination with the environmental parameters and the model data, thereby solving the defects of the existing method in frame rate, illumination simulation and detail modeling, reducing the manual intervention cost, and meeting multiple requirements for real-time performance and authenticity in the actual greening maintenance process.

The invention provides a nickel-based high-temperature alloy cutting microstructure prediction method based on a dislocation gradient model, and aims to realize optimization of process parameters through multi-scale modeling. The method comprises the following steps: firstly, calculating dislocation mobility under different temperature and pressure conditions by utilizing molecular dynamics simulation; and a dislocation generation and annihilation rate model is established in combination with a dislocation dynamics theory, so that a dynamic relationship between cutting strain and dislocation evolution is disclosed. And further through data fitting, a constitutive equation between the dislocation density and the material hardening behavior is constructed, and the evolution law of the dislocation cell structure is described emphatically. On an ABAQUS platform, a two-dimensional cutting model containing a thermal coupling effect is established, a dislocation density constitutive equation is embedded into a user-defined material module, and closed-loop correlation of macroscopic cutting parameters and microstructure evolution is achieved. According to the method, the dislocation density is creatively used as a cross-scale bridge, the understanding of a dynamic recrystallization and dislocation motion coupling mechanism in the cutting process is deepened, a prediction model is provided for technological parameter optimization, and the method has important engineering guiding significance for improving the integrity of the machined surface of the high-temperature alloy part.

The invention provides a pathology image report generation method combining hierarchical visual fusion and prototype alignment, and the method comprises the steps: collecting a pathology image and a diagnosis report as a data set, and carrying out the preprocessing of the pathology image in the data set; hierarchical visual context information fusion is carried out by constructing a hierarchical relation matrix; converting a lexical element sequence in a diagnosis report into a decoder target sequence and text embedding, inputting the text embedding and the fused visual features into a prototype mediated cross-modal semantic alignment module, taking the fused visual features and the text embedding as queries, and respectively taking a preset learnable prototype as a key and a value at the same time; training and cross-modal semantic alignment are carried out through a cross attention mechanism, and a pathological image report is generated. According to the method, the multi-scale modeling and semantic understanding capabilities of the model are remarkably improved through a dual mechanism of hierarchical visual fusion and prototype alignment, and a reliable path is provided for automatic pathological auxiliary diagnosis.

The invention discloses a piezoelectric ceramic fatigue life analysis method based on macro and micro multi-scale. The method comprises the following steps: firstly, automatically establishing a microcosmic unit cell model based on a Python script, realizing automatic assignment of material parameters and application of periodic boundary conditions, and calculating microcosmic unit cell homogenization mechanical parameters; then constructing a macroscopic driver model, inputting microscopic parameters as material attributes, and performing macroscopic fatigue life prediction and damage distribution simulation in combination with a Miner linear damage accumulation theory; and finally, through macro-micro coupling analysis, transmitting the strain of the macroscopic maximum stress unit to the micro model, and researching the intergranular stress distribution characteristics and the interface damage evolution law of the piezoelectric ceramic. According to the method, a multi-scale modeling strategy is adopted, cross-scale fatigue performance prediction from the micro grain scale to the macro structure scale is achieved, and an effective means is provided for reliability design and service life evaluation of the piezoelectric ceramic driver.

The invention provides a typhoon path prediction method and system fusing physical constraint and path mutation recognition. The method comprises the steps that a multi-dimensional input feature tensor is obtained through a feature tensor generation module; performing time modeling through a multi-scale modeling module to obtain a deep feature tensor, and performing significance guidance through a significance guidance module to obtain a prediction path sequence; the bending event identification module identifies a bending angle to obtain a plurality of path abnormal scores, the adversarial disturbance analysis module introduces a plurality of preset disturbances to determine the path confidence, and the path prediction output module outputs a path prediction result. According to the technical scheme of the embodiment of the invention, refined modeling can be carried out on the typhoon path, the PINNs physical constraint module is utilized to ensure that the prediction result meets the physical conservation principle, the path mutation detection capability is enhanced through bending event recognition, uncertainty evaluation is realized through disturbance analysis, and the accuracy of the typhoon path detection is improved. And a typhoon path prediction result which is more accurate and credible and has physical consistency is output.

The invention provides a long-term multivariable time sequence prediction method and device based on multistage decomposition and Mamba, a terminal, a medium and a product. The method comprises the following steps: acquiring a target multivariable time sequence; and inputting the target multivariable time sequence into a trained prediction model based on multilevel decomposition and Mamba to obtain a predicted long-term time sequence. The prediction model based on multi-level decomposition and Mama is composed of a preprocessing module, an adaptive time channel decomposition module, a multi-level decomposition module of mixed frequency and time domain, a multi-scale Mama modeling module and a prediction generation module. According to the method, deep mining and efficient combined modeling of the multivariable time sequence are realized, the prediction precision is improved, the computing resources are saved, and the system robustness is enhanced.

The invention provides a multi-step temperature prediction method for a low-temperature catalytic desulfurization and denitrification integrated device, and belongs to the technical field of temperature prediction based on deep learning. The method comprises the following steps: firstly, collecting nine kinds of data including reaction conditions, equipment states and an optimal reaction temperature sequence; secondly, a designed data processing module is adopted to carry out noise reduction decomposition on original time series data, key features are reserved, and data quality is improved; inputting a designed and trained multi-step prediction model fusing the hierarchical ESN reserve pool and the self-attention mechanism, and generating a temperature multi-step prediction result to guide the device to regulate and control in advance; during model training, model parameters are optimized by using an improved sparrow algorithm, and efficient search of a parameter space is realized by dynamically updating a strategy through population classification. According to the method, through the synergistic effect of data enhancement, multi-scale modeling and intelligent optimization, the reaction efficiency and the operation stability are remarkably improved, and the bottleneck of traditional single-model prediction precision is broken through.

The invention provides a building material detection and acceptance method and system, and the method comprises the steps: receiving related data of a to-be-detected building material; based on the data and a preset multi-dimensional acceptance standard, a virtual environment is constructed, parameters of the virtual environment are optimized, and it is ensured that simulation conditions are close to an actual use scene; in the optimized virtual environment, stress distribution of the material is calculated through finite element analysis, the degradation rate is predicted in combination with a machine learning algorithm, and a degradation rate predicted value is obtained; according to the predicted value, relevant data are adjusted through a multi-scale modeling technology and a random event triggering mechanism, and a response data set is determined; a support vector machine classifier is used for evaluating whether the response data set meets the acceptance standard or not, and an improvement suggestion report is generated for the non-conformity condition; and comprehensively improving the suggestion report, the response data set and the evaluation result, and generating a non-tampering detection report by means of a block chain technology. According to the invention, efficient and accurate detection and quality control of the building material are realized.