29results about How to "Optimize forecast results" patented technology

The invention discloses an ocean engineering structure external corrosion prediction method, which comprises a data acquisition module, a real-time prediction monitoring module, a multi-model integrated learning module and a visualization module, the data acquisition module acquires corrosion data of the ocean engineering structure in real time by using various sensors deployed on the ocean engineering structure, the real-time prediction monitoring module performs initial corrosion prediction by using a prediction model based on key features, and the multi-model integrated learning module performs initial corrosion prediction on the basis of the position of the ocean engineering structure in the ocean. A plurality of training models based on different algorithms are constructed, a visual user interface is provided by a visual module, and an optimized real-time corrosion prediction result is displayed; according to the method, the ocean engineering structure is divided into different areas, different training models are adopted for each area, environmental characteristics and corrosion mechanisms of different areas are fully considered, and the proportion weight of each factor is dynamically adjusted according to the actual conditions of different areas, so that the prediction result is closer to reality.

The invention discloses a temperature-shape collaborative digital precision machining method for an integral forging shaft of a large rotor. According to the method, the geometric error transfer rule model is trained and verified through the training data set and the verification data set which are obtained by performing the cutting simulation experiment through the cutting simulation model, and the geometric error of the workpiece is predicted during machining through the machining parameters, the machining area temperature field detected in real time and the geometric error transfer rule model. And when the prediction result does not meet the preset requirement, optimizing the machining parameters, calculating and analyzing the training data set and the verification data set to obtain the key geometric structure of the workpiece, and performing a dynamic balance performance simulation experiment on the workpiece geometric model introducing the geometric error of the key geometric structure after the workpiece is machined. And dynamic balance performance prediction after workpiece processing is realized. According to the method, on-machine prediction and control of the machining geometric error of the large rotor integral forging shaft can be realized, and prediction of the dynamic balance performance of the large rotor integral forging shaft can be realized.

The invention provides a bird flight trajectory prediction method, system and device and a storage medium, and belongs to the technical field of flight trajectory prediction.The method comprises the steps that feature data in a target time period is obtained, and the feature data represents related information influencing the bird flight trajectory; preprocessing the obtained feature data to obtain processed feature data; inputting the processed feature data into a pre-constructed LSTM (Long Short Term Memory) model for model training; and predicting a bird flight path based on the trained LSTM model, and outputting a prediction result. According to the method, more accurate and real-time bird flight path prediction can be provided, power interruption and equipment damage caused by bird activities are reduced, the safety and reliability of a power system are improved, and meanwhile, the labor cost and the maintenance cost are also reduced.

The invention discloses an energy regulation and control method and system of a virtual power plant based on a prediction model, and relates to the field of virtual power plant operation control, and the method comprises the following steps: collecting energy data in the virtual power plant; integrating the wind power data and the load data, and performing feature extraction on the integrated data; based on the predicted power generation data of the distributed energy and the predicted demand data of the load side resources, constructing a preliminary energy dynamic balance prediction model; performing day-ahead load demand and distributed energy prediction by using the preliminary energy dynamic balance prediction model; according to the preliminary scheduling strategy, using a niche grey wolf optimization algorithm to adjust the operation state of each distributed energy and load side resource in real time; dynamically adjusting and optimizing the energy dynamic balance prediction model; and carrying out load demand and distributed energy prediction again by using the optimized energy dynamic balance prediction model. According to the method, the change of the power system can be responded in advance, and more efficient energy scheduling is realized.

The invention discloses a heat setting process parameter recommendation method and device, computer equipment and a storage medium. The method comprises the steps of obtaining to-be-predicted production order data; preprocessing the to-be-predicted production order data to obtain a preprocessing result; inputting the preprocessing result into a prediction model to perform process parameter prediction so as to obtain a prediction result; wherein the prediction model is obtained by preprocessing production order data, labeling the data as a sample set and training a multi-weight main model formed by stacking a plurality of base models with weights and meta-models, and the weights of the base models are determined by the prediction performance of the base models; a loss function in the training process is added into the quality score of each piece of preprocessed and labeled data; and outputting the prediction result. By implementing the method disclosed by the invention, the effect of enhancing stacking by multiple models can be exerted, the dependence on artificial experience is reduced, the accuracy of process parameters and the one-time success rate of production are improved, and the product repair and production cost is reduced.

The invention discloses a shale TOC prediction method based on logging data feature derivation and machine learning, and relates to the technical field of shale TOC prediction, and the shale TOC prediction method based on logging data feature derivation and machine learning mainly comprises the steps: obtaining shale TOC data through a rock pyrolysis experiment; according to the shale TOC data, using a geological research tool to obtain original logging data and preprocessing the original logging data; and performing feature derivation on the preprocessed logging data to obtain a new data set, training a random forest machine learning model to obtain a shale TOC prediction model, and predicting shale data to be measured to obtain a shale TOC prediction result. By implementing the shale TOC prediction method based on logging data feature derivation and machine learning provided by the invention, the flexibility, applicability and accuracy of shale TOC prediction can be improved.

The invention provides a 360-degree looking-around image assisted reverse radar dynamic obstacle recognition method and system, and relates to the technical field of automobile communication transmission, and the method comprises the steps: fusing a first feature, a second feature and a third feature, and constructing a global pose map; processing through a DBSCAN clustering algorithm to obtain a preliminary recognition result of a dynamic obstacle, and combining a minimum convex hull method with a fuzzy line segment method to obtain an enveloping rectangular frame of the obstacle; inputting the geometric boundary information of the obstacle, the identity and the motion state of the obstacle, the environmental factors influencing the motion of the obstacle and the thermal characteristics of the obstacle into a deep reinforcement learning model for calculation, and obtaining a final optimized motion trail and behavior intention prediction to realize active obstacle avoidance and safe reversing. The method has the beneficial effects that the accuracy and the robustness of dynamic obstacle recognition are remarkably improved, the environment perception capability and the intelligent decision-making capability of the vehicle are enhanced, and important technical support is provided for an auxiliary driving system.

The invention relates to an automatic driving track prediction method based on a driving style, and belongs to the technical field of automatic driving. The method comprises the following steps: acquiring historical track data of a vehicle by using a sensor and a vehicle-mounted system; preprocessing the data to ensure the continuity and precision of the data; a space-time traffic map is constructed by using vehicle track information, and a driving style feature extraction module is constructed to extract driving style features from preprocessed track data; constructing a space attention sub-layer and a time convolution sub-layer to process the trajectory data to obtain interaction features between the vehicles; the style attention module dynamically generates an attention weight and guides the decoding module to predict a future trajectory according to different driving styles; the method is suitable for an automatic driving system, and can effectively improve the track prediction precision and the driving safety.

The invention relates to a method for measuring a crossing line in an overhead transmission line. The method comprises the following steps: collecting geographic data and meteorological data of an area where the crossing line is located and parameter data of the crossing line, and preprocessing the data; based on the meteorological data and the parameter data, calculating the wire sag of the crossing line and calculating the wire height based on the wire sag; calculating an initial net distance of the crossing line based on the conductor height of the crossing line; and judging the spanning structure type according to the geographic data of the area where the crossing line is located, and setting a corresponding structure correction value according to the structure type to correct the initial net distance of the crossing line to obtain the final net distance of the crossing line.

The invention belongs to the field of satellite imaging algorithms, and particularly relates to a method for predicting an earth observation imaging window of an imaging satellite, which is used for imaging an imaging target and comprises the following steps of: 1, roughly searching; step 2, performing imaging estimation; and step 3, performing imaging correction. Compared with the prior art, the imaging satellite task planning method solves the problems that in the prior art, imaging satellite task planning takes little consideration to constraint conditions, calculation errors are large, algorithms are complex, and the imaging effect is poor, and perturbation and errors caused by the factors such as the earth oblateness, the orbit eccentricity rate and the atmospheric resistance are considered in the scheme. And a simple and rapid iterative algorithm is further applied to solve a satellite imaging window, so that the efficiency and the accuracy of an autonomous task are improved.

The invention relates to the technical field of air conditioner load monitoring, and particularly discloses a non-intrusive air conditioner load monitoring method based on Kalman filtering, which utilizes a non-intrusive terminal to collect historical load data of an air conditioner to form a one-dimensional time sequence. By setting delay time and embedding dimension, phase space reconstruction is carried out on the time sequence, and a high-dimensional space trajectory is obtained. Performing sliding sampling on the track by adopting a preset time window, and calculating a local average value of each sampling window to form a local average value sequence; and predicting the air conditioner load at the next moment based on the sequence, calculating Kalman gain in combination with actual measurement data, and correcting a predicted value to obtain an optimized prediction result. In this way, the air conditioner load can be estimated more accurately, prediction errors can be effectively corrected, and the accuracy and real-time performance of load recognition are improved.

The invention discloses a method for preparing a dark plum extract based on a supercritical extraction method. The method comprises the steps of obtaining a first classification result of smoked plums based on the morphology of the smoked plums; the smoked plums are smashed into powder, the characterization value of the smoked plum powder is obtained through an electronic nose method, the characterization value is used for characterizing the relative strength of polar substances in the smoked plum powder, and a second classification result is obtained based on the relative strength; selecting the type and content of an entrainer based on the first classification result and the second classification result, and preparing the dark plum extract by utilizing a supercritical extraction method based on the selected type and content of the entrainer. The method can improve the extraction efficiency of the dark plum extract.

This invention relates to a landslide prediction method based on a multi-scale hierarchical attention mechanism, comprising: acquiring rainfall data to be predicted for a target area; inputting the rainfall data to be predicted into a landslide prediction model for multi-scale feature decomposition to obtain several frequency scales; extracting and fusing features from the several frequency scales through an attention mechanism; and outputting the landslide prediction result for the target area. The landslide prediction model is obtained through training on a training set, which consists of landslide-related rainfall data. This invention uses univariate rainfall time-series data as input and utilizes wavelet transform for multi-scale feature decomposition to extract short-term, medium-term, and long-term rainfall features. Based on this, a hierarchical attention mechanism including expanded attention and sampling channel attention is constructed to achieve the extraction of key time-series features and the dynamic fusion of multi-scale features, respectively. This invention significantly outperforms traditional models in prediction accuracy, providing an effective solution for regional landslide early warning.

The invention discloses a regional short-term air temperature intelligent prediction method based on procedural interpretable analysis, and provides the procedural interpretable analysis of air temperature prediction so as to reveal important factors influencing air temperature procedural prediction. According to the method, secondary training is carried out on the regional air temperature prediction model, and the contribution rate is adopted as the feedback of the input part of the model, so that the understanding of the air temperature prediction process is enhanced, effective feedback is provided for the model, the performance of the model is expected to be improved, and a more accurate regional air temperature prediction result can be obtained.

The invention discloses an intelligent behavior prediction method and system based on a time interest network, and relates to the technical field of software engineering, and the method comprises the steps: receiving a behavior sequence, dividing the behavior sequence through different time periods, and obtaining a behavior sequence of each time period, inputting the behavior sequence of each time period into a pre-established multi-head self-attention mechanism and a position coding model, and outputting to obtain an interest feature vector of each time period; inputting the interest feature vector of each time period into a pre-established Bi-LSTM model, outputting to obtain an interest sequence result, sequentially inputting the interest sequence result into a pre-established residual network and a Dropout layer to obtain an optimized interest sequence result, inputting the optimized interest sequence result into a pre-established MLP layer, and outputting to obtain a behavior prediction result. And the precision and the pre-estimation capability of intelligent behavior prediction are improved.

The invention relates to a method for training an ML model for generating a voxel-based 3D representation of the surroundings of a vehicle, comprising the following steps: generating first image data on the basis of at least one data source representing the surroundings of the vehicle; -extracting at least one image feature from the first image data by means of a trainable ML model; -generating a voxel-based 3D representation of the surroundings of the vehicle by means of a trainable ML model by transforming at least one image feature in the 2D domain into a corresponding voxel feature in the 3D domain, each voxel feature containing information about the occupancy and color information about the 3D position of the voxel feature; rendering the generated 3D representation of the at least one voxel feature based on the color information and the information about the occupancy in order to generate second image data; -comparing the first input image data with the generated second output image data, and in the event of a clear deviation-adjusting at least one parameter of the ML model in order to minimize the determined deviation and thus train the ML model and thereby improve the generated 3D representation of the ML model.

The invention relates to an e-commerce user re-purchase prediction method and system based on big data, and the method comprises the steps: 1, obtaining the original behavior data of a user, and carrying out the preprocessing of the original behavior data, and obtaining the behavior data of the user; 2, constructing user behavior characteristics, and obtaining corresponding user behavior characteristic data according to the behavior data of the user; 3, inputting the user behavior characteristic data into a user re-purchase prediction model for user re-purchase prediction to obtain a user re-purchase prediction result; wherein the user re-purchase prediction model is obtained by fusing an XGBoost prediction model, a Light GBM prediction model and a CatBoost prediction model which are trained on the basis of a voting method. Compared with previous logistic regression models and the like, the e-commerce user re-purchase prediction method based on the big data has the advantages that the prediction efficiency is greatly improved, the prediction precision is higher, related merchants can make corresponding marketing schemes, and accurate pushing to the users is realized.

A dust concentration monitoring device and method based on physical and data dual drive, equipment: the oscillation measurement unit includes a detachable collision separator, an oscillation measurement mechanism, a mass flow controller and a flow pump; the oscillation measurement mechanism is mainly composed of an oscillation tube, a filter membrane holder, a magnetic steel, an electromagnet, an oscillation drive module and a high-precision frequency measurement module; the particle measurement unit includes a particle flight chamber, a high-efficiency filter, a flow pump, a current limiting component, a particle measurement chamber, a light trap, a laser, a photoelectric sensing unit, a temperature and humidity sensor and a mass flow controller; two lasers, two light traps, two filters and two photoelectric sensing units are arranged in the particle measurement chamber. Method: The parameter physical model is combined with the machine learning model, and the outputs of the two are comprehensively calculated through the neural network fusion layer, and the final predicted value of the dust concentration is finally output. The device and method have a high degree of automation, and can realize high-precision monitoring of dust concentration in the environment.

The present application relates to a product demand information prediction method, device, prediction platform and medium based on big data. The method comprises: obtaining a first production data time series corresponding to a target product in historical production data corresponding to the target product, and scaling the first production data time series according to a preset rule to generate a second production data time series; inputting the second production data time series into a trained demand prediction model to obtain target demand prediction data corresponding to the target product; using the constructed EM‑GMM model to process all the daily production demand prediction data of the target demand prediction data to generate a production demand prediction result, wherein the production demand prediction result includes a weekly production demand probability distribution parameter corresponding to the target product, and preprocessing and predicting the historical production data by using a TCN‑LSTM model in combination with a grid search method, thereby improving the accuracy of the target product demand prediction.

The invention relates to a method for predicting the moisture content of cigar tobacco leaves in the air-curing process in a natural suspension state. The method comprises the following steps: acquiring image data of the cigar tobacco leaves to be predicted in a suspension air-curing state; inputting the image data of the cigar tobacco leaves to be predicted into a preset moisture content prediction model to obtain the moisture content of the cigar tobacco leaves; wherein the preset moisture content prediction model is an integrated learning model; the data set is obtained through data set training and verification, and the data set is constructed based on front and back image data of the cigar tobacco leaves in different preset periods in the airing process. According to the method, the moisture content in the cigar tobacco leaf airing process is accurately predicted, and the method also has a good prediction capability for cross-producing-area, cross-year and cross-variety cigar tobacco leaves.

The present disclosure relates to a method, system, device and medium for predicting the mechanical properties of magnetic composite materials, the method comprising the following steps: obtaining multiple basic parameters of the composite magnetic material to be predicted, and using a generalized self-consistent model to calculate the effective bulk modulus and effective shear modulus of equivalent particles of different particle sizes according to the multiple basic parameters of the composite magnetic material; according to the critical magnetic powder content, the thickness, volume fraction and elastic modulus of the interface layer are calculated by the interface layer parameter model; according to the parameters in the above calculation process, the effective elastic modulus of the magnetic composite material is calculated using a multiphase inclusion formula to achieve mechanical property prediction. The present disclosure can quickly obtain the mechanical property prediction of the magnetic composite material, avoiding the complicated and time-consuming material performance testing process, and can improve the mechanical properties of the material by regulating the material microstructure parameters, improving the design efficiency and saving the design cost.

The three-dimensional face reconstruction method, electronic device and computer-readable storage medium provided in the embodiments of the present application relate to the field of image processing technology. The embodiments of the present application divide the target face in the two-dimensional face image into a first part that does not need to be corrected and a second part to be corrected. After predicting the three-dimensional point cloud of the target face, the three-dimensional point cloud of the second part of the target face is corrected to obtain the corrected three-dimensional point cloud of the target face. In this way, the above method can correct the second part with a larger movement amplitude when the overall posture of the face predicted in the three-dimensional face prediction network model fits the actual face shape, optimize the fitting effect of the predicted result of the part with a larger movement amplitude with the actual part, and take into account the fitting effect of the predicted overall posture of the face and the local part.

The invention provides a wind power bearing life prediction method, system and device and a storage medium, and the method comprises the steps: S1, obtaining the life cycle vibration data of a bearing, and converting the life cycle vibration data of the bearing into a feature matrix; s2, inputting the last P rows in the feature matrix into an attention convolution long-short term memory network model to obtain a prediction matrix at the next moment, splicing the prediction matrix and the feature matrix, then normalizing to obtain a prediction value, and then comparing the prediction value with a fault threshold value; and S3, repeating the step S2 until the predicted value is greater than the fault threshold value, and then estimating the service life of the bearing according to the number of repetitions. According to the method, the problems of low training efficiency and low prediction precision generally existing in the prior art when the RUL of the bearing is predicted by a traditional LSTM (Long Short Term Memory) are solved.

The present invention discloses a flow parameter identification method based on an array-type artificial hair sensor, the method comprising the following steps: establishing a geometric model of an artificial hair sensor array consisting of a solid calculation domain and a fluid calculation domain; performing common node meshing on the geometric model, and importing the fluid mesh file into the CFD software and the solid mesh file into the finite element software; simulating a series of flow fields under the magnitude and angle of incoming flow velocities in the CFD software; applying the pneumatic pressure on the surface of the artificial hair sensor obtained by CFD simulation as the main load to its finite element model to obtain the corresponding tip displacement; training a BP neural network using the tip displacement as input and the magnitude and angle of the incoming flow velocity as output, and the trained BP neural network can be used to monitor regional incoming flow. The method may also include a verification step. The method of the present invention can monitor regional incoming flow conditions using artificial hair sensors and artificial neural networks.

The application discloses a method for establishing a short-term building cold load prediction model based on a Transformer model, a prediction method and computer equipment, belongs to the technical field of building cold load prediction, and solves the problem of low prediction accuracy of existing building cold load prediction. The method comprises the following steps: selecting feature variables required for building cold load prediction, wherein the feature variables comprise weather feature variables and time feature variables; obtaining linear correlation of each two feature variables, and selecting feature variables linearly independent with each other as input data of a prediction model; establishing a data set with a sequence information mode according to the input data of the prediction model, and generating a sequence input data set according to the data set with the sequence information mode; dividing the sequence input data set into training data and test data, training a model based on a Transformer network; and obtaining the short-term building cold load prediction model based on the Transformer model according to the model based on the Transformer network after training. The application is suitable for predicting short-term building cold load.

The invention belongs to the field of air quality prediction, and specifically relates to an air quality prediction method that integrates data features from different domains; the method comprises: preprocessing air quality data and meteorological data to obtain input data; performing STFT processing on the input data to obtain time-frequency features, inputting the time-frequency features into a first complex time-frequency module to obtain a time-frequency feature mask, and multiplying the input data and the time-frequency feature mask to obtain a first feature vector; using a time domain module to process the input data to obtain a time domain feature vector; performing STFT processing on the time domain feature vector to obtain a second feature vector; using a channel attention mechanism to process the time-frequency features, the first feature vector and the second feature vector to obtain a fused feature; inputting the fused feature into a second complex time-frequency module for processing to obtain a second time-frequency feature; multiplying the input data and the second time-frequency feature, performing iSTFT processing on the multiplication result to obtain an air quality prediction result; the invention integrates features from different domains and improves the accuracy of the prediction result.

The present disclosure relates to the technical field of bone density value prediction, and proposes a multi-model fusion bone density value prediction method and system, including the following steps: acquiring clinical feature data for bone density prediction; constructing a multi-model fusion prediction model including sequentially connected base learners and meta learners, inputting the acquired features into multiple base learners for prediction and recognition to obtain primary prediction results; adaptively calculating fusion weights according to the prediction accuracy of the base learners, and fusing the primary prediction results of each base learner based on the calculated fusion weights; and transmitting the fused primary prediction results to the meta learners for prediction to obtain the prediction results of the bone density. The present disclosure designs multiple machine learning models as a multi-stage prediction architecture, and each stage of the model learns and optimizes the prediction results of the previous stage and the original input features, thereby gradually improving the accuracy of the prediction.

The application relates to a commodity sales prediction method and system, and belongs to the technical field of sales prediction. The method comprises the following steps: obtaining a historical sales sequence and attribute information of a target commodity, identifying a cold-start commodity based on sequence length; training a time sequence representation encoder through self-supervised learning based on the sales sequence of a non-cold-start commodity, and extracting a time sequence representation representing sales change rules; for the cold-start commodity, extracting the time sequence representation through the encoder and calculating a quality score, determining a similar commodity set based on the attribute information and generating a migration representation, calculating a dynamic historical information proportion according to the historical sales sequence length and the quality score, fusing the time sequence representation and the migration representation to obtain a fused representation, and outputting a future sales prediction value that has been trend calibrated based on the fused representation. Through self-supervised learning, general time sequence rules are extracted, external migration information is dynamically fused based on the historical sales sequence, and the accuracy and stability of commodity sales prediction in a cold-start scenario are effectively improved.

The invention discloses a method for evaluating the effect of rocket rain enhancement operation, comprising: obtaining and cutting the operation cloud data of which the rainfall enhancement amount is to be predicted, and obtaining the rainfall enhancement evaluation interval of the operation cloud; searching the similar non-operation cloud submatrix of the operation cloud according to the operation screening condition of the rainfall enhancement evaluation interval of the operation cloud; applying a pre-constructed general similarity matching retrieval model to obtain a similar cloud similarity ranking list of the operation cloud in the similar non-operation cloud submatrix; tracking the cloud cluster trajectories of the second first calibrated number in the similar cloud similarity ranking list, and constructing a special natural rainfall model for the operation cloud; tracking the operation cloud trajectory of which the rainfall enhancement amount is to be predicted, and calculating the natural rainfall of the operation cloud under non-catalytic conditions by using the constructed special natural rainfall model; and then obtaining the rainfall of the operation cloud under catalytic conditions according to the trajectory, and evaluating the effect of rocket rain enhancement operation. The invention can effectively eliminate the influence of natural precipitation variability and improve the evaluation effect of rocket rain enhancement operation.