603 results about "Predictive methods" patented technology

The invention relates to a dynamic adjust gyroscope life forecasting method based on gray model. By data collection of vibration effective value, random drift and environmental temperature parameter which are preprocessed using radial neural networks, influence of environmental temperature on vibration effective value and random drift is eliminated and random drift and effective value just related to time are obtained by subtracting drift constant value term, then trend term of vibration effective value and random drift are extracted by using wavelet transformation and gray model are built separately for their trend term. The smaller data in two values of life predicted of dynamic adjust gyroscope unless two predicted values exceeding performance parameter limitation when dynamic adjust gyroscope is considered losing effect. The invention uses performance parameter of life probative period of product to predict its life, showing discipline of performance parameter and life of dynamic adjust gyroscope. It is easy and convenient economical and reliable.

The application provides a base station traffic prediction method and related equipment, and relates to the field of communication, wherein the base station traffic prediction method comprises the following steps: determining the adjacent base stations of a to-be-predicted base station according to the geographical distance information between base stations; determining the neighbor base stations in the adjacent base stations, and the historical traffic records of the neighbor base stations and the historical traffic record of the to-be-predicted base station have a causal relationship; performing feature extraction on the historical traffic records of the to-be-predicted base station and the neighbor base stations to obtain feature data; and predicting the predicted traffic of the to-be-predicted base station according to the feature data. In the screening process of the feature data object, the spatial factor is fully considered to avoid the singularity of feature data selection, and the causal relationship between the base station traffics is fully considered, so that the blindness of feature data selection is avoided, the redundant feature interference is reduced, the effectiveness of feature selection is improved, and the base station traffic prediction accuracy and efficiency are improved.

本发明实施例公开了一种基于蛋白质组学的脓毒症休克患者液体管理策略预测方法。所述方法包括：收集脓毒症休克患者的血浆样本，检测蛋白质标志物的表达水平，所述蛋白质标志物为GAL、NFASC、MICB_MICA、MAP2K6、JCHAIN和CSF3的组合；基于亚组识别模型计算效益得分，获得脓毒症休克患者的液体管理策略结果。本发明通过收集脓毒症休克患者的临床数据和蛋白质表达数据，采用LASSO回归分析，构建基于上述蛋白质标志物的亚组识别模型，进而获得效益评分，基于效益评分能预测患者液体管理策略方案的适用性，为脓毒症休克患者的液体治疗提供了可靠的方案，实现个体化和精准的液体治疗，在临床具有较好的应用前景。

The application provides a charging demand dynamic prediction method and system applied to a charging station, which comprises the following steps: collecting the available capacity of the charging station and the state attributes and road network traffic resistance of vehicles on the way in the surrounding road network; according to the vehicle state and the traffic resistance, the dynamic mapping delay of each vehicle on the way to the station is calculated, and a plurality of demand aggregation peaks are generated by fitting on the future time axis; the peak separation margin between adjacent peaks is calculated in real time, and when the margin is lower than a threshold, a plurality of time sequence price adjustment gradients are generated, and the target price adjustment gradient that makes the margin return to a safe level is screened out through iterative simulation, and the peak reshaping track before and after the price adjustment is displayed on the terminal to guide the station to dynamically guide the flow. The application solves the technical problem that the prediction method based on historical data cannot capture and respond to the instantaneous charging demand fluctuation caused by real-time traffic flow.

A program and the like capable of predicting a film temperature during molding with high accuracy is provided.A program causes a computer to execute processing of: acquiring measurement data during molding that is detected by a detection device and that indicates a state of a film molding machine performing extrusion molding or a state of a film being molded by the film molding machine; and predicting a film temperature during molding based on the acquired measurement data.

The present application relates to the technical field of fault detection, more particularly, the present application relates to a LED automobile lamp fault prediction method and system based on data analysis, comprising: acquiring multi-dimensional time series data of LED automobile lamps in running state; constructing direction drift index of each moment, for quantifying the direction consistency of signal drift in the corresponding window at this moment; based on the correlation between multi-dimensional time series data in each detection window, the multi-dimensional linkage coefficient of each moment is constructed. The present application combines the physical degradation mechanism to construct the direction drift index and the multi-dimensional linkage coefficient, accurately quantifies the consistency and synchronism of multi-dimensional parameter degradation, and then adaptively divides the degradation stage and evaluates the learning difficulty of each stage; In the training of the fault prediction model, the stage difficulty is used as the weight to dynamically correct the gradient. This effectively overcomes the problem of extremely unbalanced data ratio, realizes the sensitive capture and accurate early warning of the weak degradation characteristics of the lamp.

This invention relates to the field of wind power output prediction technology, and particularly to a method, system, device, and storage medium for predicting offshore wind power output change windows based on typhoon forecasts. The method includes acquiring deterministic typhoon forecast data; calculating the time-series wind speed at the turbine hub height of the target offshore wind farm within the future forecast period based on a preset typhoon parameter model; setting a feathering shutdown wind speed threshold and a power generation recovery wind speed threshold for the turbines; traversing the time-series wind speeds to obtain the predicted shutdown start point and the predicted power generation recovery point, marking the period between the predicted shutdown start point and the predicted power generation recovery point as the initial output change window period; based on the initial output change window period, backtracking to verify the persistence of the upward trend of wind speed before the predicted shutdown start point to determine the precise start point of the window period; and extending backward to verify the stable recovery trend of wind speed after the predicted power generation recovery point to determine the precise end point of the window period.

This invention presents a cloud-based fault prediction method for intelligent driving vehicle powertrain systems based on causal physical information. The method constructs an inverted Transformer prediction model that fuses causal and physical information. By fusing variable-centered embedding, causal topological masks, and physical law residual terms, it achieves collaborative prediction and diagnosis driven by data and constrained by physical limitations. After offline training using historical data, the prediction model is deployed on a cloud server for real-time online prediction. This invention effectively overcomes spurious correlations in complex driving environments, significantly improves the fault diagnosis accuracy and early warning capability of autonomous vehicle powertrain systems, and provides reliable support for predictive maintenance of autonomous vehicles.

The application discloses a trajectory prediction method and device, equipment, vehicle, medium and product. The method comprises the following steps: acquiring motion information of a target intelligent agent at a current collection time, wherein the target intelligent agent refers to a moving object in an environment of a target vehicle; determining a motion label of the target intelligent agent according to the motion information of the target intelligent agent and motion information of the target vehicle, wherein the motion label is used for identifying a motion scene of the target intelligent agent; and performing trajectory prediction on the target intelligent agent according to the motion label of the target intelligent agent and the motion information of the target intelligent agent, so as to obtain a target prediction trajectory of the target intelligent agent at the current collection time, wherein the target prediction trajectory is used for providing a reference for driving path planning of the target vehicle. The accuracy of trajectory prediction of the target intelligent agent can be improved.

This invention provides a method and system for predicting the state of power equipment based on online testing adaptation, comprising: collecting power equipment state data in real time through sensors and forming test samples; filtering a set of adapted historical samples from a historical sample memory bank that meet preset conditions in terms of similarity to the test samples in the latent space through a transferable historical sample selection module, wherein the historical sample memory bank stores historical power equipment state data; performing time-frequency domain hybrid data augmentation on the test samples and the adapted historical sample set through a transferable online augmentation module to generate an augmented sample set; inputting the augmented sample set into a pre-trained power equipment state prediction model for batch training, dynamically adjusting the model parameters to adapt to the distribution shift; and fusing the output of the dual-stream predictor of the power equipment state prediction model to generate the power equipment state prediction result for the next time period. This invention can perform power equipment state prediction.

This invention provides a bearing life prediction method based on adaptive physical information and KAN networks, belonging to the field of mechanical fault diagnosis and predictive maintenance technology. Addressing the problems of static physical model parameters leading to model defects and spectral bias causing oversmoothing in deep learning models, this invention constructs a prediction model based on a divide-and-conquer prediction framework. It identifies time-varying physical parameters in real time through adaptive physical branches and calculates the global physical trend component; it uses the learnable spline activation function of the KAN network to capture local residual components; and it predicts the remaining life by fusing the global physical trend component and local residual components, applying Bayesian inference to quantify uncertainty. This invention exhibits higher prediction accuracy and robustness under complex operating conditions, effectively solving the challenges of physical consistency and high-frequency feature extraction in rolling bearing remaining life prediction.

This invention discloses a day-ahead power prediction method for a single photovoltaic power plant based on a spatiotemporal graph model, belonging to the field of new energy power prediction technology. The method includes: constructing the power prediction task of a single photovoltaic power plant as a graph learning problem; designing a unified spatiotemporal graph structure containing three types of nodes: historical observation nodes integrating historical meteorological and power data, future meteorological forecast nodes, and future power nodes; explicitly fusing the dynamic correlation between meteorological and power data in the temporal and spatial dimensions through this structure; and introducing a graph attention network and a dynamic multi-head attention mechanism to aggregate node information and extract features to capture nonlinear dependencies across time and space, ultimately achieving high-precision day-ahead power prediction. This invention can effectively model the complex "meteorological-power" spatiotemporal coupling mechanism in photovoltaic output, significantly improving prediction accuracy and stability, and providing a reliable basis for power system dispatch and consumption.

A computer-implemented method trains an artificial intelligence model based on neural networks to predict physical features of a brake caliper from a geometric representation, such as a mesh. The method provides for receiving geometric representations of brake calipers, each comprising local regions such as vertices and faces, and local information relating to the geometry. The artificial intelligence model is trained using input data comprising the received local information and output data relating to physical features of the brake caliper, including fields of stresses due to the pressure of brake fluid and the friction force, and the integral of the elastic deformation energy. The system comprises an input interface to access training data and a processor module configured to train the artificial intelligence model. The trained artificial intelligence model predicts physical features of a brake caliper from the geometric representation, providing output data such as stress fields and deformation energy.

The application discloses a power grid power flow prediction method and system based on a physical constraint graph convolution network, and relates to the technical field of power system power flow prediction.The method comprises the following steps: acquiring the topological structure and operation data of a power grid to be analyzed, constructing an adjacency matrix, and constructing a node feature matrix and an edge label matrix; inputting the node feature matrix into a graph convolution network for topological perception learning, and acquiring node representation; mapping the node representation into initial branch power flow prediction values through a bus-branch correlation mapping layer; adjusting the initial branch power flow prediction values through a node power balance correction layer by using a correction matrix, and obtaining corrected branch power flow prediction values; and combining a root mean square error and a physical regularization loss function to iteratively update model parameters, obtaining a power flow prediction model, and performing online reasoning.The application solves the problem of node power imbalance of a traditional data-driven model, and significantly improves the physical consistency and accuracy of power flow prediction.

A first domain controller (9) is capable of performing data communication with a server (4) that learns statistical quantities including data obtained while a vehicle is traveling and calculates feature quantities necessary for predicting energy consumption of the vehicle. The first domain controller (9) includes: a link information acquisition unit (12a) that acquires link information indicating links included in map information; a statistical quantity calculation unit (12b) that calculates statistical quantities for each link indicated by the link information; a statistical quantity transmission unit (12c) that causes the statistical quantities to be transmitted to the server; a feature quantity acquisition unit (12d) that acquires feature quantities from the server; and an energy consumption prediction unit (12g) that predicts energy consumption of the vehicle on the basis of the feature quantities.

The application discloses a cancer survival prediction method and device based on whole-slice pathological images, and relates to the technical field of medical artificial intelligence and digital pathological image analysis. The method comprises the following steps: acquiring whole-slice pathological images and patient survival information, and performing pretreatment; performing cell detection on the whole-slice pathological images to obtain cell structure data; dividing the whole-slice pathological images into a plurality of image regions, and determining regions of interest; screening the cell structure data in each region of interest to construct a cell subset; sorting the cell structure data according to the distribution relationship of cells in space to construct a cell structure sequence; constructing a cell structure modeling model, performing feature modeling on the cell structure sequence, and obtaining tissue structure features capable of representing the microstructure of tumor tissues; and inputting the tissue structure features into a survival prediction model to predict the survival risk of the patient. The application can improve the accuracy and stability of cancer survival prediction.

This invention discloses a deep learning-based method for predicting orthodontic outcomes, belonging to the field of artificial intelligence-assisted technology. The method includes acquiring multimodal initial data of the target patient, comprising craniofacial CBCT 3D images, intraoral 3D scan models, and a digital design scheme for orthodontic appliances containing target tooth displacement data. Based on the CBCT 3D images, macroscopic geometric features of the jawbone are extracted using a macroscopic morphological encoder, and microscopic tissue features of the periodontal region are extracted using a microscopic tissue feature encoder. The macroscopic morphological encoder is a 3D convolutional neural network, and the microscopic tissue feature encoder is a local window attention network based on a visual Transformer. This invention can predict the dynamic effects of the interaction between tooth movement and adaptive skeletal remodeling, and is particularly suitable for predicting orthodontic outcomes in adolescents during their growth and development period, addressing the industry pain point of large systematic biases in static models in such scenarios.

To improve growth stage prediction accuracy.SOLUTION: A growth prediction device 4 comprises a stage prediction unit 6 that predicts a growth stage for a crop and a definition unit 7 that, when the period from a reference date to the arrival date of the growth stage includes a specific growth stage, defines a threshold value that indicates a prediction date for the specific growth stage with respect to transition data for the growth stage predicted by the stage prediction unit 6. When predicting a next growth stage, the stage prediction unit 6 predicts the date on which transition data for the next growth stage reaches the threshold value as the specific growth stage.SELECTED DRAWING: Figure 1

Methods of predicting whether a subject with chronic myelogenous leukaemia (CML) is at risk of relapse following cessation of a treatment for CML, whether a subject with CML will achieve TFR following cessation of a treatment for CML, and selecting a subject for treatment, wherein the subject has CML or has been diagnosed with CML are disclosed herein. The methods comprise determining the expression of one or more genes regulated by PRC1. Also provided are kits and antigen-binding molecules suitable for use in the disclosed methods.

This invention discloses a method, apparatus, device, and medium for predicting groundwater levels. The method includes: acquiring historical water level data for each sub-region of a target area; for any sub-region, determining the influence coefficient of each influencing factor based on the historical water level difference of the sub-region and preset water level influence data; for any influencing factor, determining the total influence of the influencing factor on water level changes during a preset observation period based on the influence coefficient and preset water level influence data; determining the influence weight of each influencing factor based on the total influence of each influencing factor; and determining the groundwater level change trend of the target area based on the total influence of each influencing factor and the influence weight. The technical solution provided by this invention can accurately predict groundwater level trends.

The application is suitable for the technical field of vehicle health monitoring, and provides a vehicle health degree prediction method and system based on geographic information positioning, which comprises the following steps: extracting real-time geographic semantic features of a target vehicle currently located according to real-time position data; generating a geographic semantic feature sequence containing a plurality of road segments along a planned path based on the planned path and the real-time geographic semantic features; determining expected working condition threshold values corresponding to each monitoring parameter in vehicle operation data according to the real-time geographic semantic features; comparing the vehicle operation data with the expected working condition threshold values to identify abnormal operation events; and determining a basic health degree loss amount according to the abnormal operation events, and predicting the health degree of the target vehicle after passing through the planned path in combination with the geographic semantic feature sequence. The application can fundamentally eliminate false positive warning problems caused by geographic environment, and simultaneously realize health degree quantitative evaluation with clear physical meaning and future path health degree forward prediction.

This invention discloses a method for predicting the application volume of inter-provincial high-voltage direct current (HVDC) channels based on multi-source fusion and probability, belonging to the field of data processing technology. The method includes the following steps: S1, determining the prediction period and basic parameters; S2, determining the final available capacity based on the basic parameters; S3, calculating energy priority based on the final available capacity; S4, constructing a pass rate prediction model based on the final available capacity; S5, determining the output results for the prediction period based on the pass rate prediction model and energy priority. This invention is the first to model channel capacity calculation as a deterministic optimization problem with physical constraints, combining a probabilistic correction factor for meteorological risk to achieve a hybrid modeling of determinism and stochasticity, supporting risk attribution, outperforming black-box prediction, and improving the application pass rate.

This invention relates to the field of relay monitoring, and in particular to a method, medium, and device for predicting relay anomalies. The method acquires voltage and current waveform data of the relay's operation process via an IO-Link interface, extracts features such as breaking arc, closing bounce, and steady-state contact resistance; determines health factors based on contact resistance, calculates single-instance damage values ​​by combining arc and bounce characteristics, and determines remaining lifespan by comparing cumulative damage values ​​with a threshold. This method shifts from counting incidents to counting damage, improving assessment accuracy through multi-dimensional damage quantification and adaptive aging of health factors; real-time online data acquisition avoids lag, ensuring prediction accuracy under different operating conditions, and providing technical support for industrial predictive maintenance.

The application discloses a kind of shale oil reservoir's attenuation-elastic-electricity combined modeling and parameter prediction method, belong to geophysical exploration and oil and gas reservoir evaluation technical field.First, obtain mineral components, pore structure and elastic-attenuation-electricity full-dimensional experimental data through core experiment, determine attenuation and resistivity as high sensitivity parameter after sensitivity analysis;Again, based on Hashin-Shtrikman boundary, differential equivalent medium theory, triple-pore medium wave propagation equation, construct the acoustic and electrical rock physics model of completely consistent micro-pore structure;Finally, establish longitudinal wave impedance-attenuation coefficient-resistivity three-dimensional joint rock physics chart, after multi-band correction, simultaneously quantitative prediction reservoir porosity, shale content and fracture porosity.The application breaks through the limitation of conventional acoustic-electricity combined model, significantly reduces the multi-solution of reservoir parameter prediction, and is suitable for fine evaluation of various shale oil tight reservoirs.

The invention belongs to the technical field of oil and gas field exploration and development, and discloses a fractured-vuggy reservoir ground stress prediction method and system based on discrete elements and finite elements. And taking the obtained boundary stress direction and size as boundary conditions, and combining with a pre-constructed fusion model to obtain the three-dimensional stress of the research area, thereby completing the fracture-vuggy reservoir crustal stress prediction process. The construction process of the fusion model comprises the steps that firstly, a discrete fracture network model and a geomechanical grid model are established, then the discrete fracture network model and the geomechanical grid model are fused, after fusion, three-dimensional heterogeneous parameters are given to the fusion model, and the construction process of the fusion model is completed. The method can accurately and efficiently simulate the three-dimensional distribution rule of the current stress field of the fracture-vug type reservoir, and is of great significance to oil-gas exploration and development.

This invention belongs to the interdisciplinary field of artificial intelligence and geological resource assessment, specifically relating to a method and system for predicting the energy storage potential of salt caverns based on multi-source geological information. It aims to address the problems of low prediction accuracy and difficulty in balancing breadth and precision in existing technologies due to single-source data, static models, and lack of adaptive capabilities. The method includes: acquiring multi-source data such as seismic, well logging, core, and geostress data; constructing a geological feature fusion vector containing seven core parameters; establishing a high-dimensional nonlinear mapping model driven by a deep neural network; dynamically adjusting the prediction range based on data coverage density and confidence level; and achieving continuous model iteration through online incremental learning. The system integrates data quality assessment, anomaly handling, and distributed computing modules. By adopting the above technical solutions, this application can achieve a significant improvement in prediction accuracy and adaptive intelligent adjustment of the prediction range.

The application relates to the field of photovoltaic technology and discloses a photovoltaic system power prediction method, which comprises the following steps: acquiring multi-source time sequence data of each photovoltaic component to determine first coupling coefficient time sequence data and second coupling coefficient time sequence data, combining the multi-source time sequence data to construct coupling characteristic vector time sequence data, inputting the coupling characteristic vector time sequence data into a preset power prediction model to obtain component predicted power time sequence data of each photovoltaic component within a preset future time length, and finally superimposing all the component predicted power time sequence data to obtain predicted total power time sequence data of the photovoltaic system within the preset future time length. The method considers multi-factor coupling and component individual differences, effectively solves the problems of low prediction accuracy, significant calculation error and power estimation under complex working conditions caused by insufficient consideration of multi-factor coupling and neglect of component individual differences in the prior art, improves the power prediction accuracy, reduces the calculation error and power estimation deviation under complex working conditions, and the like.