63results about How to "Guaranteed prediction accuracy" patented technology

The invention relates to the technical field of medical information, and discloses a pancreatic cancer risk prediction method based on machine learning and multi-modal data, and the method comprises the steps: obtaining the multi-modal data of a target user; performing time sequence deduction on the molecular biological detection data to generate a virtual molecular time sequence; time sequence signals are extracted from the virtual molecule time sequence and the time sequence behavior monitoring data; calculating the dynamic coupling strength between the two time sequence signals to obtain a space-time coupling coefficient; weighted fusion is carried out on the features, and unified multi-modal feature representation is constructed; carrying out multi-modal feature representation training to obtain a special risk prediction model for the target user; and obtaining a risk quantitative score, and identifying a key risk driving factor which contributes to the score most. According to the invention, through multi-modal time sequence fusion and personalized modeling, early-stage, dynamic and explainable and evaluable pancreatic cancer risks are realized.

The application discloses a tunnel or mine gushing water space-time prediction method and system coupled with a water power numerical model, and the method comprises the following steps: based on the identified and verified underground water numerical model, outputting multi-source data, complementing the missing measured data, quantifying the difference between fault and normal stratum permeability characteristics and coupling to the data system, and incorporating the tunnel or mine excavation space data. An LSTM-isolation forest-K nearest neighbor regression coupled model is constructed, and a multifunctional module is configured to realize common training of multi-scene data. The pretreated multivariate time series data is divided into a training set and a test set, hidden features are extracted through the coupled model, abnormal detection results are fused, a residual correction model is trained synchronously, and the hyperparameters and weights are adaptively optimized according to the multi-project prediction error feedback. Based on the trained coupled model, a window rolling strategy is adopted to carry out synchronous gushing water space-time prediction, residual correction is combined, and prediction data meeting the engineering precision is output. Reliable technical support is provided for engineering construction safety control.

This invention relates to a physical information neural network-based intelligent performance prediction method and system for automated multi-material fiber placement on complex curved surfaces in aircraft. The invention includes: collecting fiber placement process parameters; performing standardized preprocessing and physical constraint-enhanced sampling to obtain an enhanced training dataset; constructing a high-order nonlinear sparse regression candidate library based on the enhanced training dataset; jointly identifying piecewise smooth physical differential equation systems and their mode switching logic using sparse Bayesian regression and Hidden Markov Models to obtain an embeddable inverse mechanism model; constructing a Physical Information Embedded Generative Adversarial Network (PI-GAN); collaboratively optimizing the generator and discriminator through adversarial training to output surface defect indices and mechanical performance indices; and initiating incremental self-learning when introducing new process scenarios to achieve model self-evolution. This invention achieves end-to-end accurate prediction of multi-dimensional quality indices such as surface defects and mechanical performance.

The present application relates to a method for predicting fatigue crack propagation rate of a diffusion bonded dissimilar titanium alloy laminate structure, which is based on the mechanical properties of the constituent materials of the dissimilar titanium alloy laminate structure, i.e., the quasi-static tensile properties of the two titanium alloy plies. The method for predicting fatigue crack propagation rate of the diffusion bonded dissimilar titanium alloy laminate structure first establishes the relationship between the fatigue crack propagation rate of the laminate structure and the mechanical properties of the laminate structure, and then establishes the relationship between the mechanical properties of the laminate structure and the mechanical properties of the dissimilar titanium alloy single ply, thereby describing the relationship of the fatigue crack propagation rate of the laminate structure. Compared with the prior art, the method of the present application has the advantages of simple and convenient test, engineering precision, rapid and practical, etc., and effectively reduces the test cost and test time required for crack propagation test of the dissimilar titanium alloy laminate structure processed from different parameters.

The application provides a three-dimensional anisotropic composite material heat conductivity coefficient prediction method and system, and relates to the technical field of heat analysis, and comprises the following steps: establishing a heat transfer unit cell model of a to-be-detected three-dimensional composite material in different directions based on structure parameters and material parameters of the to-be-detected three-dimensional composite material; the to-be-detected three-dimensional composite material is a three-dimensional orthogonal structure; the material parameters comprise first heat conductivity coefficients of each material; taking solid heat conduction as a current heat transfer form, determining equivalent thermal resistances corresponding to the heat transfer unit cell model of different regions by using an equivalent thermal resistance method and the first heat conductivity coefficients, establishing a heat transfer connection relationship between each equivalent thermal resistance by combining a Fourier equation and a thermal resistance network method, and determining first total thermal resistances along each heat transfer direction of the to-be-detected three-dimensional composite material; the heat transfer connection relationship comprises series connection and parallel connection; converting the first total thermal resistances based on overall size parameters of the heat transfer unit cell model, and determining an equivalent heat conductivity coefficient of a target direction.

This application provides a method, apparatus, electronic device, and storage medium for predicting battery heat generation power. It acquires multiple first average heat generation powers of the battery when charged and discharged at different rates at a target temperature, and multiple second average heat generation powers of the battery when charged and discharged at the target rate at different temperatures. The target temperature includes the middle temperature of the battery's operating temperature range, and the target rate includes the rate at the middle position of the battery's rate range and the rate at the beginning and / or end positions. The multiple first average heat generation powers and multiple second average heat generation powers are fitted to obtain a relationship between the heat generation power of the battery when charged and discharged at different rates at different temperatures. Based on the obtained heat generation power relationship, the heat generation power of the battery when charged and discharged at any rate at any temperature is determined. This application can save testing time and resources while ensuring prediction accuracy.

The present application relates to the technical field of bearing life prediction, in particular to a kind of gradient composite coating sliding bearing life prediction method, comprising the following steps: step one, build the coating degradation physical simulation model of multi-field coupling;Step two, adopt active learning algorithm to build high-precision proxy model, design active learning query strategy;Step three, online monitoring and multi-domain feature extraction;Step four, real-time state mapping and life prediction based on transfer learning;Step five, prediction result output and model updating.The present application can improve the accuracy of gradient composite coating sliding bearing life prediction, greatly reduce the operation load, and improve the prediction efficiency of bearing life.

This invention discloses a data-driven method for monitoring marine phytoplankton abundance using underwater acoustic networks. The method includes: constructing and training a multi-level spatiotemporal feature ensemble model based on historical marine phytoplankton abundance and corresponding marine environmental data to determine the optimal spatial location and monitoring time window of the underwater acoustic network nodes; constructing a teacher model for channel prediction, including a multi-layer cascaded structure and residual modules, and compressing the teacher model into a student model using spatiotemporal knowledge distillation; training the student model to achieve real-time channel state prediction at the underwater acoustic network nodes; matching suitable underwater acoustic communication devices and seasonal optimal routing strategies to each underwater acoustic network node based on the optimal spatial location and real-time predicted channel state, and performing adaptive modulation and coding at the link level, while simultaneously monitoring phytoplankton abundance using the underwater acoustic network. This invention can improve data throughput and prediction accuracy under strict energy consumption constraints.

The application discloses a scene generation method and device based on source-load uncertainty and equipment, and relates to the technical field of energy scheduling. The method comprises the following steps: acquiring real-time source-load data of a power system; processing the real-time source-load data based on a target prediction model to obtain a multi-time-scale source-load prediction result, wherein the target prediction model is obtained by compressing the weights of a long short-term memory network prediction model; generating a collaborative scheduling strategy of source-load resources under the multi-time-scale source-load prediction result based on a multi-agent scheduling decision model; and generating a hydropower source-load scene set of the power system at different time stages under the source-load uncertainty based on the collaborative scheduling strategy. In the foregoing manner, the prediction link and the decision optimization link are closely coupled, the multi-time-scale prediction result is used to dynamically guide the reinforcement learning decision, the adaptability of the system to the source-load uncertainty is enhanced, and the organic collaboration of the multi-time-scale and the accurate generation of the uncertainty scene are realized.

The application provides an aircraft wing skin corrosion depth prediction method based on a GAN and an improved LightGBM algorithm, which comprises the following steps: S1, data enhancement: four fully connected layers are used to extract feature information between columns; S2, an improved condition generator and discriminator are used, and parameters are updated; S3, the LightGBM algorithm is improved, and the aircraft wing skin corrosion depth is predicted. The aircraft wing skin corrosion depth prediction method using the generative adversarial network for data enhancement and the gradient regression model for sample regression can accurately predict small sample data. Meanwhile, the gradient regression model LightGBM algorithm is improved, which is more suitable for the prediction of the aircraft wing skin corrosion depth, and can greatly improve the prediction accuracy of the aircraft wing skin corrosion depth prediction.

This invention discloses a short-window gamma-gamma turbulence parameter prediction method for space-to-ground laser communication, belonging to the technical field of space-to-ground laser communication and atmospheric turbulence channel parameter prediction. This method addresses the problems of traditional methods, such as strong dependence on long observation windows, significant degradation in prediction accuracy under short-window scenarios, and insufficient robustness under low signal-to-noise ratio conditions. It establishes a short-window observation model for the space-to-ground optical link and a gamma-gamma channel statistical model, constructs time-dependent short-window training data, and designs a short-window gamma-gamma network. Temporal features are extracted through a convolutional backbone, and a scintillation exponential physical regularization auxiliary head is used to achieve joint parameter prediction under physical constraints, outputting predicted gamma-gamma distributed parameters. This method can achieve high accuracy and good stability in parameter prediction under short observation windows and low signal-to-noise ratio conditions, and can be used for turbulence channel state characterization at the space-to-ground laser communication receiver.

The application discloses a crack rock mass tunnel stability evaluation method and system based on finite elements and machine learning, and belongs to the technical field of geotechnical engineering, and comprises the following steps: acquiring tunnel geometric parameters to construct a finite element model, calculating the type I and type II stress intensity factor values of a crack tip, checking and removing abnormal data through multi-path integration, constructing an effective data set, constructing a Kan neural network model and training until convergence, inputting target tunnel parameters into the model, outputting stress intensity factor prediction values, calculating the equivalent fracture toughness of the crack tip, determining the crack initiation position based on the size relationship between the upper and lower equivalent fracture toughnesses of the crack tip, selecting a fracture criterion according to rock mass characteristic parameters, calculating the crack initiation direction and completing stability evaluation. The application realizes rapid and accurate prediction of the crack initiation behavior of a crack rock mass tunnel, and can provide a reliable basis for engineering stability evaluation.

This application relates to the field of automotive technology, and more particularly to a method, apparatus, device, and storage medium for adjusting a model. The method includes: obtaining a first collision simulation result based on a whole-vehicle collision model of a vehicle; the first collision simulation result includes at least the impact force of a first barrier and a protective beam in the vertical direction and a first acceleration of the non-deformed position of the protective beam in the vertical direction; determining the equivalent mass that generates the impact force based on the impact force and the first acceleration; controlling a second barrier included in the simplified collision model to impact the protective beam included in the simplified collision model with the impact force based on a simplified collision model of the vehicle and the equivalent mass, thereby obtaining a second collision simulation result; determining a first distance based on the first collision simulation result; determining a second distance based on the second collision simulation result; and adjusting the simplified collision model based on the difference between the first distance and the second distance.

The present application relates to a kind of computing method for realizing wide range dynamic noise map system fast update, comprising the following steps: using the data information of system database, based on existing day and night period and city road grade, simplify the structure of traditional road sound level mechanism model;Using big data technology, using hybrid modeling method, regression each grade road sound source (day and night) sound level contribution amount prediction model;Road noise fast calculation method based on sound level contribution amount prediction model is constructed, the fast update of dynamic noise map is realized.Compared with prior art, while ensuring the calculation precision, the operation and update efficiency of noise map system is greatly improved, and the technical constraints of foreign core computing software are broken, the localization of noise map core computing technology is realized, which provides technical support for wide range deep development of noise map.

The present application provides a kind of river embankment wave climb observation equipment and its use method, including river embankment wave climb observation equipment and wave height instrument probe assembly, the river embankment wave climb observation equipment includes the main support base of supporting effect at bottom, the top of the main support base is fixedly installed with vertical main stand, the top of the main stand is installed with installation base, and the top of the installation base is fixed with main control box.The present application realizes the synchronous collaborative observation of wave climb, wave height and river embankment dynamic stress by integrating capacitive climb instrument, wave height instrument, stress sensor array and wind sensor, compared with traditional single hydrological monitoring equipment, the present application can construct "climb-stress" coupling database, comprehensively evaluates river embankment safety from two dimensions of wave action intensity and structure response state, both prevent overtopping and prevent embankment collapse, significantly improve the comprehensiveness and scientificity of dike safety monitoring.

The invention belongs to the related technical field of ink-jet printing, and particularly relates to a vacuum drying cavity flow field regulation and control method for ink-jet printing, which comprises the following steps of: uniformly configuring a plurality of independently controlled auxiliary air exhaust pipelines around a vacuum drying cavity; collecting cavity flow field data in real time, calculating a current flow field uniformity coefficient of the cavity, and if the current flow field uniformity coefficient does not meet a preset requirement, adopting a pre-trained proxy prediction model to optimize a key parameter combination value according to a multi-target rolling optimization target function; the key parameters are various parameters which influence the film forming uniformity and are determined in advance through feature importance analysis, and comprise the flow of each auxiliary air exhaust pipeline and related parameters of component layout in the cavity; the multi-objective rolling optimization objective function is the sum of the minimum uniformity lifting amplitude, the parameter adjusting amplitude and the parameter adjusting frequency. The problem that in an existing vacuum drying system, due to uneven flow field distribution, the film drying consistency is poor can be solved.

The application provides a battery health state evaluation method, system, computer device and medium, and belongs to the technical field of battery health management and life prediction. The method comprises the following steps: performing full-life cycle cyclic charging and discharging test on a reference battery, collecting data samples at fixed sampling intervals, and extracting a fusion feature vector of the reference battery sample; training a reference prediction model by using the reference data sample; collecting a fusion feature vector of a target battery to be tested, calculating the distribution distance of the features of the target battery and the reference battery by using an MMD algorithm, combining the prediction loss of the reference battery to establish a double-loss function, taking the minimization of the total loss as the target, iteratively adjusting the reference model parameters by using back propagation, and obtaining an optimized model suitable for the target battery; and the SOH value of the target battery can be accurately predicted based on the optimized model. The method greatly reduces the data collection cost and model deployment period in the migration stage, and realizes the migration of the prediction model in different battery devices at a low cost and high precision.

The invention discloses a saline-alkali soil corn growth index dynamic monitoring method based on unmanned aerial vehicle multispectral remote sensing, relates to the technical field of unmanned aerial vehicle remote sensing, and aims to realize efficient monitoring of corn growth conditions by synchronously acquiring multispectral images and three-dimensional point cloud data by using an unmanned aerial vehicle remote sensing platform. The method comprises the following steps: acquiring saline-alkali grade and growth period information of a target corn field block, calculating a salinity index and a vegetation index based on a multispectral image, and extracting canopy structure parameters through three-dimensional point cloud data. A corresponding target monitoring model is called from a preset monitoring model library, a corn growth index prediction value is generated in combination with salt and alkali grades and growth period information, and finally a growth condition grading early warning graph based on the prediction value is formed. According to the method, the growth difference of the corn under different saline-alkali soil conditions can be accurately identified, effective decision support is provided for farming intervention, and the method has high practical application value.

The application provides a floor internal stress prediction method and system, specifically, a floor image is acquired, finite element analysis is performed in combination with macroscopic load and boundary conditions to generate an initial stress field; visual key points in the image are extracted, key points in a high gradient area are selected as sparse key points according to a gradient of the initial stress field, and multi-modal feature representation is generated by fusing visual features and local stress features of the sparse key points; sparse key points are taken as nodes, a stress correlation graph with a weighted edge is constructed according to a spatial distance, the stress correlation graph and the multi-modal feature representation are input into a graph neural network, and stress values of each node are predicted; and a continuous internal stress distribution graph covering the entire floor is generated through a spatial interpolation algorithm.

The application discloses a dynamic human body falling detection method based on future human body time sequence posture prediction, and the method comprises the following steps: automatically calibrating the ground in a monitoring scene to obtain ground plane parameters; detecting, cropping and tracking the human body target in a video image to obtain a human body image sequence; performing single-person 3D posture estimation on the human body image sequence frame by frame to obtain a historical 3D skeleton sequence; constructing a skeleton motion flow feature according to the historical 3D skeleton sequence, and extracting a current human body state feature by using a time sequence feature coding model; predicting a future H-frame human body 3D skeleton sequence based on the current human body state feature; determining whether the human body has a risk of falling soon according to the included angle between the human body trunk vector in the future 3D skeleton and the ground plane normal vector, and combining the distance information of the skeleton key point to the ground plane; and outputting a warning signal when a preset condition is met, and the method is suitable for security monitoring, old-age care, public safety and the like.

This invention discloses a method and system for predicting lower limb joint angles, comprising the following steps: collecting first original joint angle time series from multiple healthy test subjects continuously performing various typical movements; collecting second original joint angle time series from multiple healthy test subjects performing any type of typical movement; standardizing the first original joint angle time series to obtain standard samples, wherein a portion of the standard samples constitutes the training set, and the remaining standard samples serve as the first samples; standardizing the second original joint angle time series to obtain second samples; using both the first and second samples as test samples, and all test samples constitute the test set. This invention can effectively improve the prediction accuracy and real-time computation efficiency of the prediction model, and enhances the cross-scene adaptability of the prediction model while ensuring prediction accuracy, facilitating practical use.

The invention discloses a water-rich rock mass fracture precursor identification method based on a lightweight neural network, and belongs to the technical field of deep rock mass engineering safety monitoring, and the method comprises the steps: collecting pulse waves and interference waves of deep rock mass fracture to form a data pair, building a waveform library based on the data pair, building a lightweight model for predicting rock fracture, and carrying out the prediction of rock fracture. The method comprises the following steps of: extracting and splicing data pairs to obtain a fused feature map, extracting local features, fusing to obtain a time sequence feature map, compressing by utilizing global pooling, converting into a nonlinear channel association vector, normalizing to obtain a weight vector, combining with the time sequence feature map, and compressing to obtain a channel statistical vector; and performing nonlinear feature transformation and numerical regularization by using a full connection layer, and obtaining ternary probability distribution through a Softmax function. According to the invention, key technical support is provided for real-time monitoring, and urgent demands of water-rich rock mass engineering on intelligent, real-time, high-reliability and safe monitoring are precisely met.

This invention discloses an adaptive distributed support vector regression method to combat Byzantine faults. First, the objective function of the SVR model is smoothed to construct an empirical risk minimization objective function. Then, with t=1, the master machine obtains initial parameter estimates on its local data. In the t-th iteration, a MOM-based aggregation method is used to obtain the MOM estimate, which is then used as the global gradient estimate. Subsequently, a robust global gradient is obtained based on the global gradient estimate. After obtaining the robust global gradient, the master machine updates the global parameters using gradient descent. Finally, it checks whether the convergence condition is met. If the convergence condition is not met, the above steps are repeated; otherwise, the globally optimal parameter estimate is obtained. By introducing a robust aggregation mechanism based on the MOM method, it can effectively suppress the influence of abnormal machines, significantly improving the stability and robustness of the system while ensuring prediction accuracy. It can be widely applied to various practical distributed systems.

The invention discloses a text prompt type heart function intelligent evaluation method based on a visual language large model. The method comprises the following steps that 1, an echocardiography mark data set is constructed; 2, dividing four chambers of the heart; step 3, hierarchical feature learning; 4, performing multi-scale feature fusion; and 5, predicting the cardiac function (ejection fraction). According to the method, the heart can be modeled into a multi-scale semantic system, and features from macroscopic chamber dynamics to microstructure motion are captured through a hierarchical feature learning mechanism. Deep integration of imaging data and clinical knowledge is realized by aligning hierarchical visual features with professional medical descriptions in a shared semantic space. The method has excellent performance in the aspect of ejection fraction prediction.

The application discloses a biological age evaluation method and system based on whole life cycle DNA methylation and application, and belongs to the technical field of bioinformatics. First, the obtained original DNA methylation data is subjected to quality control and standardization processing; then, differential methylation sites significantly related to calendar age are screened as features; next, taking calendar age as a target variable, a regression model is constructed by adopting a LightGBM gradient boosting framework to obtain a methylation clock model; subsequently, the model is used to predict the DNA methylation age of an individual, and an epigenetic age acceleration value is calculated based on the deviation of the DNA methylation age from the calendar age; finally, the age acceleration value is subjected to correlation analysis with health or physiological indexes in different life stages, so as to evaluate the biological aging state of the individual and predict related health risks. The application covers the whole life cycle, is suitable for Chinese population, and can provide an effective tool for clinical disease risk prediction, health management and anti-aging intervention effect evaluation.

This invention discloses a video prediction model compression method and system based on optical flow-guided knowledge distillation, belonging to the field of computer vision technology. The method includes: generating optical flow distillation loss by constraining the optical flow prediction distribution of the student network to be consistent with that of the teacher network; generating channel alignment loss by aligning the channel attention distributions of the teacher and student networks using divergence; generating pixel-level reconstruction loss based on the difference in pixel values ​​between the generated image predicted by the student network and the real image; generating perceptual loss based on the difference in high-level semantic feature space between the generated image predicted by the student network and the real image; and obtaining the trained student network based on the optical flow distillation loss, channel alignment loss, pixel-level reconstruction loss, and perceptual loss. This invention can solve the performance degradation problem caused by neglecting spatiotemporal characteristics in existing compression methods for video prediction tasks.

The invention belongs to the crossing field of artificial intelligence and geophysics, and particularly discloses a transient electromagnetic forward modeling method and system considering an induced polarization effect based on deep learning, and the method comprises the steps: inputting Cole-Cole key parameters representing the induced polarization effect into a CNN-LSTM mixed deep learning network model for forward modeling, and obtaining transient electromagnetic response data; wherein Cole-Cole key parameters representing the induced polarization effect serve as multi-dimensional input features of the CNN-LSTM mixed deep learning network model, transient electromagnetic response data of a corresponding time channel serve as output, and the CNN-LSTM mixed deep learning network model is trained by adopting a segmented weighted mean square error loss function. According to the method, the segmented weighted mean square error loss function is adopted in the training stage, higher weights are given to the symbol inversion points and the prediction errors of the adjacent time windows, and the reliability of all-time response prediction is guaranteed.

The invention relates to the technical field of electric field grid-connected control, in particular to a wind power plant unit grid-connected synchronous detection and debugging system which comprises a data acquisition module, a synchronous detection algorithm module, a historical data training module, a self-adaptive compensation debugging module and a cooperative control module. The data acquisition module synchronously acquires original electrical parameters of a power grid side and a unit side; the synchronous detection algorithm module adopts an improved second-order generalized integrator phase-locked loop algorithm, filters out harmonic waves, extracts fundamental wave parameters and calculates four types of detection parameters; the historical data training module establishes a mapping model of power grid fluctuation and compensation amount through machine learning, and outputs an optimal compensation coefficient combination; the self-adaptive compensation debugging module is combined with a dynamic compensation and feed-forward pre-judgment algorithm to output the excitation current and the rotating speed adjustment amount of the unit; and the cooperative control module establishes closed-loop linkage until the detection parameter meets the grid-connected threshold value, and outputs a grid-connected ready signal.

The invention discloses a pre-flood hydrological forecasting factor rapid identification method and system based on environmental perception, and the method abandons a conventional forecasting mode which depends on a hysteresis index after a flood occurs, and achieves the rapid and accurate identification of a hydrological forecasting factor through sensing a key environmental factor before the flood occurs. The design system comprises an environment factor sensing module, a data preprocessing module, a factor rapid screening module, a model training optimization module and an identification result output module, and the pre-flood environment data such as the soil water content, the early-stage accumulated rainfall and the vegetation coverage are collected and preprocessed, and then a multi-algorithm fusion screening strategy is adopted. The method can quickly lock the core forecasting factor with strong relevance to flood generation, provides advance support for hydrological forecasting, and solves the technical problems that the traditional hydrological forecasting factor is lagged in identification and poor in timeliness. The hydrological forecasting method remarkably improves the perspectiveness and accuracy of hydrological forecasting, and is suitable for scenes such as basin flood early warning and water resource scheduling.