74results about How to "Reliable prediction" patented technology

The invention provides an energy consumption prediction and anomaly detection method and system based on digital twinning, and the method comprises the steps: collecting physical parameters in real time through a sensor, and the physical parameters comprise the cell temperature, the total current of a battery pack, the total voltage of the battery pack, the gradient, the vehicle speed and the mass; collecting battery state parameters by using a battery management system, wherein the battery state parameters comprise real-time energy consumption; the collected physical parameters are input into a Simulink and Cruise combined model for simulation, and model output prediction energy consumption is obtained; wherein the Simulink is used for establishing an equivalent circuit model of a power battery, and the control system, the sensor simulation module and the Cruise simulation model are used for establishing a whole-vehicle simulation model of the pure electric vehicle; comparing the model output energy consumption with the real-time energy consumption, and obtaining an energy consumption deviation value; whether the energy consumption deviation value exceeds a preset range or not is judged, and if yes, energy consumption is judged to be abnormal; and if not, evaluating the energy consumption of the whole vehicle so as to solve the technical problem that the actual energy consumption analysis, energy management and endurance mileage evaluation of the whole vehicle are difficult.

The invention, which relates to the technical field of offshore wave simulation, discloses a wave hydrodynamic numerical simulation method for a sea area with a breakwater, comprising the following steps: S1, determining a target sea area, and collecting sea chart data and water depth topographic data of the target sea area; s2, determining a shoreline position of the target sea area, and establishing a water depth terrain database of the target sea area; s3, setting grid precision, and constructing a wave hydrodynamic two-dimensional model of the target sea area; s4, setting boundary conditions for driving the wave hydrodynamic two-dimensional model, and setting initial parameters; and S5, based on the wave hydrodynamic two-dimensional model constructed in the S3, performing numerical simulation on the target sea area by using a sub-grid method to obtain the characteristic wave height and periodic data of the target sea area. According to the method provided by the invention, the calculation efficiency can be ensured, the wave transmission characteristics of the open type oyster reef are considered, and the influence of open type oyster reef construction on the wave hydrodynamic environment field can be accurately simulated.

The invention relates to a vehicle track prediction method based on interactive perception and map adaptation, and belongs to the technical field of automatic driving. The method comprises the steps of collecting a historical track and geographical semantic information of a vehicle; the method comprises the following steps of: modeling interaction between dynamic objects by utilizing Transform, and fusing map information when a state sequence is decoded; a hierarchical attention mechanism is adopted, the future state of the vehicle is considered, and the consistency and accuracy of prediction are ensured; in addition, a multi-resolution map coding module is also constructed, the module fully utilizes a Vision Transform module to efficiently capture local and global scene context information, and then map representation is closely associated with a vehicle state to accurately model an interaction process of a vehicle and a scene, so that a more reasonable future trajectory prediction result is generated. The method shows wide application potential, can effectively improve the calculation performance, and is suitable for a more complex traffic environment.

The invention relates to a mechanism data collaboratively driven dam safety state intelligent diagnosis method and system. The method comprises the steps of collecting environmental quantity data, dam deformation data and corresponding monitoring point coordinates; a PINN model is constructed, the PINN model comprises an input layer, a hidden layer and an output layer, the input layer receives the collected data, and the output layer outputs a predicted value of a deformation component; the PINN model is trained, the weight and bias of the PINN model are adjusted by minimizing a comprehensive loss function, and the comprehensive loss function comprises a data driving loss function, a physical constraint loss function and a boundary condition loss function; using the trained PINN model to predict a deformation field; and comparing the prediction result with the monitoring index to obtain an abnormal region, and performing abnormality diagnosis on the abnormal region. Through the mechanism data synergistic effect, it is guaranteed that model prediction follows the physical law, actual monitoring data can be better fitted, and high-precision dam safety state prediction and diagnosis are achieved.

The invention discloses a short-term power load prediction method based on deep learning, and the method comprises the steps: S1, collecting historical power load data and corresponding weather and holiday and festival information, S2, carrying out the preprocessing of the historical data based on the historical power load data and the change of a power utilization behavior mode of a user, reducing the data inconsistency, and carrying out the prediction of a short-term power load. The method comprises the following steps: S1, processing historical power load data, weather information and holiday and festival information, S3, constructing a deep learning model which inputs processed historical power load data, weather information and holiday and festival information, S4, training the constructed deep learning model by using a training data set and optimizing model parameters, and S5, carrying out short-term power load prediction by using the trained deep learning model and generating a prediction result. According to the short-term power load prediction method based on deep learning, the problem of inconsistency of historical data caused by frequent change of power utilization habits of users in a changeable user behavior mode in the prior art is solved.

The invention discloses a molecular property prediction large language model construction method based on a knowledge graph. The method comprises a plurality of steps: firstly, acquiring pre-training corpora by using a high-throughput data acquisition technology, including related data such as molecular attributes and metabolic pathways; then, a knowledge graph about fourteen end points is constructed based on the data, and the knowledge graph represents the relation between the molecules and the attributes and the end points of the molecules in a triple form; thirdly, pre-training the large language model by using a LoRA technology, optimizing the model by adopting an incremental learning strategy, and forming an expert large model; then, a triple related to the target endpoint is retrieved from the knowledge graph through the RAG technology, and retrieval results are sorted; and filtering the retrieved triple through cue word design and an expert large model, and extracting key information. And finally, converting the filtered triple list into a natural language, inputting the natural language into an expert large model, generating a prediction result of molecular properties, and providing a reasoning basis. According to the method, the accuracy and efficiency of molecule and endpoint chemical reaction prediction are remarkably improved.

The invention relates to a touch all-in-one machine interaction control method and device, computer equipment and a medium, and the method comprises the steps: receiving image data through a preset video stream protocol, and obtaining a corresponding image data stream; acquiring a real-time network bandwidth condition, and then performing adaptive compression processing on the image data stream based on the real-time network bandwidth condition, and dynamically adjusting image transmission parameters; comprehensively analyzing the image data stream by using a deep learning algorithm, extracting operation characteristics of a user, generating an output control instruction based on the operation characteristics, and further controlling and adjusting image display and / or an equipment state; content information is extracted from the image data stream, and content analysis is carried out by adopting a corresponding content analysis strategy according to the content information, so that real-time display and / or storage are / is carried out according to the analyzed content; and obtaining a user interaction behavior, generating a corresponding adjustment feedback instruction based on the user interaction behavior, and performing personalized adjustment on the user interface. The method has the effect of improving the image transmission quality.

The invention discloses a food safety traceability detection method and system based on machine learning, and relates to the technical field of food safety supervision, the food safety traceability detection method based on machine learning comprises the following steps: obtaining corresponding detection feature data; obtaining a food safety risk detection index; constructing a food safety risk prediction model; performing safety detection on the food sample; and starting a traceability program according to a safety detection result, and taking corresponding measures. According to the method, key factors influencing food safety can be accurately identified by analyzing the detection characteristic data, so that whether a food sample meets food safety standards or not can be accurately judged by continuously testing and comparing key safety parameters while the detection quality is ensured, and the detection accuracy is improved. Therefore, unsafe food is effectively prevented from entering the market, and the health of consumers is protected.

The invention discloses a carbon emission integrated prediction method considering driving factor fluctuation, equipment and a medium, and relates to the technical field of carbon emission prediction. The prediction method comprises the following steps: establishing an integrated prediction model of the carbon emission based on a time sequence model and a multi-factor model; a Monte Carlo method is adopted to carry out dynamic scene simulation on the driving factors influencing the carbon emission, and the fluctuation range of the driving factors is obtained; performing random sampling on the driving factors in the fluctuation range to obtain a plurality of groups of sampling results; the multiple sets of sampling results are input into an integrated prediction model for prediction, and carbon emission prediction results corresponding to the multiple sets of sampling results are obtained; and obtaining a predicted carbon emission interval based on the confidence interval of the carbon emission prediction result. According to the method, the carbon emission integrated prediction model combining different time sequence methods and a multi-factor prediction method is constructed, the uncertainty of future carbon emission influence factors is considered through Monte Carlo simulation, and the accuracy and stability of carbon emission prediction are improved.

The invention relates to a crack sensitive parameter prediction method and device based on anisotropic gradient modeling, and the method comprises the following steps: S1, obtaining the normal crack weakness and tangential crack weakness of a characterization crack based on a linear sliding model; s2, establishing an initial model of the fracture weakness by constructing a relationship between the fracture anisotropy gradient and the fracture weakness; s3, obtaining an azimuth difference longitudinal wave reflection coefficient equation based on the PP wave linear approximate reflection coefficient; and S4, estimating the tangential crack weakness according to the seismic azimuth amplitude difference, and constraining the data of the tangential crack weakness by using the initial model of the crack weakness. According to the technical scheme, the relationship between the fracture anisotropy gradient and the fracture weakness is constructed, the initial model of the fracture weakness is established, the model is reasonable and reliable, and the data of the tangential fracture weakness can be constrained and inverted, so that the seismic inversion precision of the fracture weakness is improved, and the seismic inversion accuracy of the fracture weakness is improved. The method can be used for reliable prediction of the carbonate reservoir fracture development area.

The invention discloses a wave hydrodynamic numerical simulation method for a sea area provided with a hedge shrub dam, and relates to the technical field of offshore wave simulation, and the method comprises the following steps: S1, determining a target sea area, and collecting actually measured water depth topographic data and chart water depth data of the target sea area, the target sea area being a salt marsh beach sea area where the hedge shrub dam is planned to be arranged; s2, setting grid precision, and constructing a wave hydrodynamic two-dimensional model of the target sea area by using a structured grid; s3, setting boundary conditions for driving the wave hydrodynamic two-dimensional model, and setting initial parameters; and S4, based on the wave hydrodynamic two-dimensional model constructed in the S2, performing numerical simulation on the target sea area by using a sub-grid method to obtain the characteristic wave height and periodic space-time distribution of the target sea area. According to the method, the calculation efficiency can be guaranteed, the wave transmission characteristics of the hedge shrub dam are considered, and the influence of construction of the hedge shrub dam on the wave hydrodynamic environment field can be accurately simulated.

The invention belongs to the technical field of software engineering, particularly relates to an automatic driving system performance enhancement method based on an expert hybrid architecture, and aims to solve the core problems that an end-to-end automatic driving system is confronted with semantic fuzziness to cause unreliable decision, multi-task interference hinders optimization planning, too long reasoning delay increases driving risks and the like. According to the method, an ExpertAD framework is provided, task key features are amplified through a perception adapter (PA), and the relevance of scene context understanding is guaranteed; related driving tasks are dynamically activated through a sparse expert mixture (MoSE), and task interference is minimized; and in combination with a customized training loss function, collaborative optimization of planning effectiveness and reasoning efficiency is realized. Experiments show that compared with an existing method, the method has the advantages that the average collision rate is reduced by 20%, the reasoning delay is reduced by 25%, higher multi-skill planning capacity is achieved in rare scenes (such as accident handling and first-aid vehicle avoiding), and good generalization is achieved for unseen urban environments.

The invention provides a predictive maintenance model management method for a communication information system, belongs to the field of artificial intelligence, and realizes predictive maintenance of equipment and network nodes by utilizing real-time data in a communication network and combining a PPO algorithm. The method is suitable for a dynamic environment of a large-scale communication network, integrates multi-source data through a data sharing platform, and optimizes the learning and prediction capabilities of the model. Comprising distributed data acquisition, dynamic model updating, maintenance strategy generation, model optimization and real-time data synchronization. The problem that traditional centralized model management cannot adapt to communication network complexity and dynamic change is solved. Through distributed data processing and adaptive optimization of the PPO algorithm, the prediction precision and response speed of the system are improved, and the operation efficiency and maintenance capability of the communication information system are significantly improved.

The invention provides a personality detection method and device, electronic equipment, a storage medium and a program product, and the personality detection method comprises the steps that state data of a target object is acquired, and the state data comprises human body heart rate variability data of the object detected through a millimeter wave radar in the task state that the object executes a detection task; and processing the state data of the target object by using a personality detection model to obtain predicted personality information of the target object, the personality detection model being obtained by training through a supervised method. According to the method, a reliable basis can be provided for personality detection by obtaining the state data including the human body heart rate variability data. The human body heart rate variability data are detected through the millimeter wave radar, and the authenticity, accuracy and reliability of the obtained data can be guaranteed. By using the personality detection model to process the state data, the rule of the state data can be mined by means of the model, and reliable prediction of personality information is realized.

The present invention provides a risk warning method for hot work in a tank area of ​​a chemical enterprise, comprising: obtaining accident precursors; based on the accident precursors, obtaining corresponding accident hazards and accident consequences in the OSHA case library, and establishing a hot work accident chain based on the accident hazard source, the event precursors, and the accident consequences; based on the hot work accident chain, determining the nodes of a Bayesian network; quantifying the Bayesian network nodes based on a triangular fuzzy number evaluation method; according to the Bayesian network, calculating the posterior probability by quantizing the nodes, and establishing a hot work risk warning model based on the Bayesian network; using the accident precursors as variables, inputting them into the hot work risk warning model to achieve risk prediction. The present invention improves prediction accuracy and reliability.

The invention discloses an active power distribution area line loss prediction method, system and device and a storage medium, and relates to the technical field of line loss detection, and the method comprises the steps: decomposing the historical line loss data of an active power distribution area into the line loss data of each ammeter in the active power distribution area; performing correlation analysis on the active power distribution area line loss influence factors and the electric meter line loss data to obtain the weight of each influence factor on the influence of the electric meter line loss data; and predicting the line loss of the electric meter by adopting a multi-classifier and a bidirectional long-short-term memory network, and carrying out superposition and reconstruction to obtain a line loss prediction result of the active power distribution area. According to the invention, accurate prediction of the line loss of the active power distribution area with high-proportion DG access is realized.

The invention belongs to the technical field of load distribution of gas-steam combined cycle units, and discloses a load distribution method of a gas-steam combined cycle unit. The load distribution method comprises the steps that a steady-state working condition data set of each unit serves as data input, and a gas consumption rate prediction model of each unit is established; and taking the minimum total gas consumption rate of the whole plant as an output target, applying the gas consumption rate prediction model of each unit to obtain a global optimal solution set, and carrying out load distribution on the multiple units according to the global optimal solution set. According to the load distribution method of the gas-steam combined cycle unit, the load distribution of each unit is carried out through the generated global optimal solution, so that each unit can operate under the conditions of the most efficient and the highest energy under the condition of stable and safe operation, the performance of each unit is fully mobilized, and the load distribution efficiency of each unit is improved. And energy conservation and consumption reduction are realized while the productivity efficiency is improved.

The invention provides a medium and long term electricity price prediction method and device, electronic equipment and a storage medium, and belongs to the technical field of data prediction, and the method comprises the steps: determining a first feature set based on the correlation between a multi-dimensional market boundary condition feature and a market clearing electricity price, and carrying out the data processing of the first feature set, and obtaining a second feature set; training the initial electricity price prediction model based on the second feature set to obtain a target electricity price prediction model; and on the basis of the historical data of the first time before the to-be-measured time point and the target electricity price prediction model, obtaining an electricity price prediction result of the second time after the to-be-measured time point. According to the medium-and-long-term electricity price prediction method and device, the electronic equipment and the storage medium provided by the invention, the accuracy of medium-and-long-term electricity price prediction can be improved.

The invention discloses a main shock and aftershock sequence earthquake response prediction method based on a knowledge enhancement deep learning model, and belongs to the technical field of building structure earthquake response prediction. The method solves the problems that an existing deep learning model is scarce in training data, poor in capacity of capturing long sequence global correlation and incapable of processing input vibration with different lengths and sampling frequencies. The method specifically comprises the following steps: step 1, establishing a target structure finite element model, and selecting and adjusting seismic oscillation records of main and aftershocks; step 2, constructing a training data set based on the finite element model and the seismic oscillation record; 3, building a knowledge enhancement deep learning model comprising a consistency input coding module, an encoder, a decoder and a linear layer, designing a knowledge enhancement loss function, and training the model by using the training data set; and step 4, inputting the actual main shock and aftershock seismic oscillation sequence into the trained model to obtain a structure displacement response and structure restoring force prediction result. The method can be applied to earthquake response prediction.

The invention relates to the technical field of wildlife monitoring data prediction and simulation, in particular to a wildlife migration path prediction method based on environmental factor data and monitoring site data, which comprises the following steps: S1, carrying out systematic digital extraction work of site and path information; s2, obtaining a digital orthograph (DOM) and preprocessing the DOM; s3, environment factor data are sorted out; s4, integrating the environment factor data and the wild animal group appearing and disappearance point and migration path data to form a wild animal group migration database; s5, establishing a migration path simulation model by adopting a mode of constructing a resource selection probability-resource steering path algorithm (RSF-RGPA); s6, analyzing point locations on the basis of the model obtained in the S5, and continuously iterating until an end point to form a path; according to the method, environmental factor data and wild animal appearing and diving point data are systematically integrated, and the accuracy of migration path prediction is greatly improved by utilizing a constructed resource selection probability-resource guide path algorithm (RSF-RGPA).

The present invention aims to develop and validate a prediction model for sepsis within 7 days after LT in liver transplant recipients. Data of 786 patients who underwent LT from January 2015 to January 2020 were retrospectively extracted from the big data platform of the Third Affiliated Hospital of Sun Yat-sen University. Seven ML models were developed to predict post-LT sepsis. Our results showed that a larger amount of red blood cell transfusion, ascites, blood loss and gastric drainage, less crystalloid infusion and urine output, longer anesthesia time, and higher preoperative TBIL level were the top 8 important indicators affecting postoperative sepsis. Among the 7 ML models developed in the study, the random forest classifier (RF) model showed the best overall performance in predicting post-LT sepsis.

The invention discloses an optical network routing and spectrum allocation algorithm based on a GCN-LSTM, and the algorithm comprises the steps: S1, defining an optical network environment, initializing the algorithm, and constructing a basic framework of a traffic prediction GCN-LSTM model; s2, according to historical traffic data in the network, network traffic data prediction is carried out in combination with a machine learning method; s3, predetermining an optimal modulation format based on the predicted flow result; and S4, performing efficient RSA decision according to the determined modulation format. According to the optical network routing and spectrum allocation algorithm based on the GCN-LSTM, optimization and improvement are carried out in the aspects of flow data prediction, flow dynamic threshold setting, modulation format determination and the like, and the problems that in a traditional heuristic algorithm, the spectrum resource utilization rate is low and the like can be solved.

Method and device for operating a vehicle to avoid or eliminate traffic jams. The invention relates to an improved possibility of avoiding or eliminating traffic jams. In particular, the invention relates to a method for operating a vehicle (100), wherein a dynamic object (200) is predicted to intersect at least part of a first traffic area portion (140) occupied by the vehicle (100), wherein the vehicle (100) is in a waiting state for release to continue driving. A trajectory (150) of the vehicle (100) is then determined, which trajectory (150) at least eliminates or avoids the intersection of the dynamic object (200) with the first traffic area portion (140). Furthermore, the invention relates to a device for operating a vehicle, a program element and a computer-readable medium having such a program element.

This application provides a method, apparatus, and computer equipment for predicting the carbon dioxide diffusion coefficient in heavy oil enhanced oil recovery, relating to the field of oil and gas development technology. The method is based on Fick's law and the law of conservation of mass. It determines the saturated carbon dioxide concentration in heavy oil through carbon dioxide diffusion experiments. Simultaneously, it considers the volume expansion of heavy oil caused by carbon dioxide dissolving in it, and the oil relative flow opposite to the carbon dioxide diffusion direction caused by this volume expansion. Based on this, a partial differential equation is established to obtain a carbon dioxide diffusion model. The experimentally obtained saturated carbon dioxide concentration in heavy oil is used as the constraint condition for constructing the carbon dioxide diffusion model. The carbon dioxide diffusion model considers the volume expansion change of heavy oil as a one-dimensional expansion change, that is, the volume expansion change of heavy oil is considered through the change in the heavy oil liquid level. Finally, an iterative method is used to obtain a numerical solution. The above method achieves reliable and accurate prediction of the carbon dioxide diffusion coefficient.

The invention relates to a simulation part design method for simulating a disc forging pre-rotation process, and belongs to the field of aero-engine tests. The method solves at least one problem that the existing pre-rotation process simulation method for the high-temperature alloy large disc forge piece has a large gap between the simulation result and the actual simulation result, the simulation efficiency is low, and the mechanical property change of the pre-rotated material is difficult to accurately evaluate. The simulation part design method comprises the following steps: S1, establishing an initial model; s2, simplifying the model; s3, judging whether linear elastic mechanical analysis results of the initial model and the simplified model are consistent or not; s4, optimizing the rotating speed in linear elastic mechanical analysis, or adjusting the simplified model, and taking the simplified model and the rotating speed which can generate consistent results as a simulation part model and a process test rotating speed; and S5, making a simulation part based on the simulation part model, and carrying out a pre-rotation test at a process test rotating speed. According to the invention, the stress-strain and performance change of the actual disc forge piece in the pre-rotation process can be accurately and efficiently simulated.

The embodiment of the invention belongs to the technical field of image processing, and relates to a vehicle maintenance scheme prediction method and device, computer equipment and a storage medium, and the method comprises the steps: constructing a model training set according to historical maintenance data and annotation information; respectively taking the damaged position information, the historical maintenance scheme and the damaged part as a damaged position label, a maintenance scheme label and a damaged part label when the loss is calculated by the initial yolov7 detection model; inputting the model training set into the initial yolov7 detection model, and performing model training operation on the initial yolov7 detection model according to a damaged position loss function, a maintenance scheme loss function and a part category loss function to obtain a trained maintenance scheme prediction model; and inputting a to-be-detected damaged image into the trained maintenance scheme prediction model to carry out maintenance scheme prediction operation so as to obtain a maintenance scheme prediction result. According to the method, more robust and more reliable prediction of the loss assessment results of different parts of the whole scheme is realized.

The invention discloses a domestic satellite full-space-time continuous atmospheric formaldehyde analysis and completion method and device, and the method comprises the steps: obtaining formaldehyde concentration data, meteorological data, related substance emission data and humanistic geographic data obtained through the observation and inversion of a domestic satellite, and constructing earth space-time information data after the data are matched and aligned; performing partial random masking on formaldehyde concentration data in the earth spatio-temporal information data, inputting the formaldehyde concentration data into a neural operator designed according to a data type, and performing formaldehyde concentration data completion on the random mask through calculation of the neural operator; semi-supervised learning is carried out based on a reconstruction error between the complemented formaldehyde concentration data and the observed formaldehyde concentration data, and neural operator parameters are optimized; and analyzing and complementing the observed formaldehyde concentration data by using a parameter-optimized neural operator to realize efficient and reliable prediction of the observed formaldehyde concentration data.

The invention discloses a method for predicting a metabolic pathway through a secondary mass spectrum fragment tree based on deep learning. According to the method, a training data set is constructed based on initial data matching, an initial prediction model is trained based on deep learning, model parameters with the highest accuracy are selected through cross validation, and data to be measured are input to obtain a path prediction result. The method effectively solves the problem that at present, metabolic pathway information in spectroscopic data must be obtained through compound identification, so that the information utilization rate is insufficient. Compared with an existing method, the method has the advantages that experimental mass spectrum data and metabolic pathways are effectively associated, and biological function explanation based on metabonomics data is facilitated. The method has the advantages that the path prediction accuracy is high; the method can be used for efficient utilization of metabolome data, and is convenient for enrichment of metabolic pathways.

The application discloses a battery pack energy state estimation method, device, equipment, storage medium and product, which are used for accurately and reliably estimating the energy state of a battery pack. The method comprises the following steps: acquiring a first operation data sequence of a first battery pack, wherein the first operation data sequence comprises operation data of the first battery pack at multiple time points; inputting the first operation data sequence into a first model to output a first energy state of the first battery pack; wherein the first model is obtained by training based on a second operation data sequence and a second energy state of a second battery pack, the single cell parameter distribution of the second battery pack is similar to the single cell parameter distribution of the first battery pack, and the single cell parameter distribution of the battery pack is obtained by a second model based on an operation data sequence of the battery pack.

The invention discloses a lattice design and performance prediction method based on deep learning. The method comprises the following steps: S1, constructing a lattice data set; s2, constructing a deep learning framework, and training the deep learning framework by using the lattice data set to obtain a pseudo-physical enhanced neural network model which comprises a backbone network for preliminarily learning the relationship between the input features and the output features and a pseudo-physical information extraction network for extracting pseudo-physical information of explicit input features and output features; and S3, inputting the geometric parameters of the lattice structure with unknown performance into the physical enhancement model, outputting the corresponding mechanical performance and the explicit physical relationship, and further carrying out lattice structure design according to the physical relationship. According to the method, a deep learning model and an algorithm are utilized, effective features are extracted from geometric data of the lattice structure, and efficient, accurate and reliable prediction of mechanical properties of different structures is achieved.