21results about How to "Reduce forecasting costs" patented technology

The invention discloses a water quality prediction method based on graph neural network and spatial-temporal feature fusion, and the method comprises the steps: obtaining hydrological data and water quality data of a plurality of monitoring stations in a preset drainage basin in a preset time period, representing the monitoring stations as nodes of a graph, and representing the adjacency relation between the monitoring stations as edges of the graph, a graph topology network mapping multiple monitoring station pollutant data is constructed, a spatial-temporal feature fusion module is adopted to perform feature extraction and fusion on the graph topology network to obtain water pollution spatial-temporal feature data, and the spatial-temporal feature fusion module is obtained by training a graph convolutional network, a gating circulation unit and a self-attention mechanism. And performing fusion processing on the extracted feature data to form a time sequence data set of a graph topology structure, and finally predicting the data set through a graph time sequence prediction model to obtain water quality prediction results of the plurality of monitoring stations in a target time period. The method can effectively deal with the spatial and temporal change process of water pollution, reduce the water quality prediction cost and improve the water quality prediction precision.

The invention discloses a transformer health prediction system under multi-dimensional monitoring data fusion, and relates to the technical field of electric power engineering, and the system comprises a step of constructing a global prediction model configured on a cloud platform according to a multi-dimensional initial monitoring index set. And performing distillation dimension reduction on the global prediction model, creating a simplified prediction model, and distributing the simplified prediction model to edge prediction equipment, the simplified prediction model including a plurality of hierarchical simplified prediction models. And activating the multi-source monitoring equipment, performing normal multi-source monitoring on the target transformer, and obtaining a real-time multi-source monitoring data set. And transmitting the real-time data set to edge prediction equipment for binary risk discrimination, calling a global prediction model according to a discrimination result for full-dimensional positioning prediction, and outputting a health prediction result. Therefore, the technical effects of improving the prediction responsiveness and accuracy and reducing the prediction cost are achieved.

The invention relates to a prediction model training method, a prediction method and a prediction system for predicting the residual mechanical life of a circuit breaker, a readable storage medium and a computer program product, and belongs to the technical field of circuit breakers. The method comprises the following steps of: performing weighted average on first mechanical life data and second mechanical life data, and sequencing according to a set sequence to obtain a sample sequence as an original time sequence for establishing a gray model, and performing one-time accumulation on the sample sequence to generate an incremental sequence meeting a quasi-exponential law; solving a grey model established by the progressive increase sequence to obtain a prediction model; or performing one-time cumulative subtraction on the sample sequence to generate a decline sequence meeting the quasi-exponential law, and then solving the grey model established by the decline sequence to obtain the prediction model. According to the method, the first mechanical life data and the second mechanical life data are sorted after weighted averaging, the grey theoretical model is established by using the grey system theory, the grey theoretical model is solved to obtain the prediction model, and the model training is simple.

The invention provides an ozone concentration prediction method and device, electronic equipment and a readable storage medium, and belongs to the technical field of environmental monitoring, the method comprises the following steps: determining target ozone concentration data in a target area, the target area being an area where a monitoring point corresponding to the target ozone concentration data is located; determining a target fitting regression equation matched with the target ozone concentration data according to the monitoring points and the meteorological data corresponding to the monitoring points; and inputting the target ozone concentration data into the target fitting regression equation to obtain predicted ozone concentration data of the target area. According to the ozone concentration prediction method and device, the electronic equipment and the readable storage medium provided by the invention, the ozone concentration prediction accuracy can be improved.

The invention provides a distributed training time prediction method, a distributed training time prediction device, computing equipment and a computer readable storage medium. The method comprises the following steps: constructing a communication network simulation model according to actual measurement information of an actual training scene for distributed training; receiving training task information, and analyzing a communication task from the training task information; inputting the communication task into the communication network simulation model, and calculating communication time; and predicting the time of distributed training according to the communication time. According to the method and the device, the communication network simulation model with a high simulation degree can be quickly constructed, so that an accurate prediction result of the distributed training time can be quickly obtained.

The invention discloses an S-type pitot tube calibration coefficient prediction method based on CFD, and the method is realized through the following steps: S1, carrying out CFD numerical simulation based on parametric modeling, and obtaining a calibration coefficient set of an S-type pitot tube under different installation angle deviations, flow velocity range conditions and environmental parameters; s2, integrating simulation data, and constructing a feature vector data set of the key influence parameters; s3, dividing the data set into a training set and a test set; s3, based on an RBF algorithm, constructing a high-precision nonlinear prediction model by using the training set; and S4, verifying the performance of the model by using the test set, and judging whether the prediction accuracy meets the expectation or not. A CFD simulation technology and a machine learning algorithm are integrated, the problem that a traditional real flow calibration device is limited in capacity and cannot reproduce on-site complex conditions is solved, and a solution is provided for high-precision prediction and correction of calibration coefficients under on-site complex installation conditions and a non-uniform flow field.

This disclosure relates to the field of battery technology, and more particularly to a method, apparatus, electronic device, and storage medium for predicting the cycle life of a battery cell. The method includes: during the cyclic charging and discharging of the battery cell under test, data is collected at intervals of a sampling time threshold to obtain a data set; the cell capacity reduction value is determined based on the data set; and the corresponding cell cycle life is determined based on the cell capacity reduction value. Using this disclosure can reduce the prediction cost and improve the accuracy of predictions for lithium-ion batteries.

The application discloses a kind of beam bridge girder static load deflection prediction methods based on improved AVOA-GRNN network, comprising:1, establish vehicle bridge finite element model and add vehicle bridge uncertainty simulation bridge dynamic static load test, collect dynamic static load test data;2, the above data is selected using the characteristic of pearson linear correlation coefficient;3, using dynamic static load experimental data training GRNN neural network model, and construct the parameter of improved African vulture algorithm optimization GRNN, obtain the corresponding smooth factor when average absolute error is minimum;4, the dynamic load test data of prediction set is substituted into improved AVOA-GRNN network model and carries out static load deflection prediction.The application can use beam bridge girder dynamic load test data to predict corresponding static load deflection, so as to effectively solve the problems, such as high cost of predicting beam bridge static load test, great influence on traffic and easily causing damage to bridge structure.

The present invention discloses an efficient method for predicting the dynamic response of an uncertain flexible multi-body system, which belongs to the field of dynamics of uncertain flexible multi-body systems. The implementation method of the present invention is: using the absolute node coordinate formula ANCF to establish the differential-algebraic equations of the dynamics of a deterministic flexible multi-body system. Introducing the uncertainty parameters into the equations of the flexible multi-body system model to form uncertain differential-algebraic equations. Using the signal decomposition method, the output response of the system is decomposed into a plurality of single-component signals in the form of vibrations and a trend term signal, and then each single-component signal is characterized in the form of instantaneous amplitude and instantaneous phase. Based on compressed sensing, sparse polynomial proxy models of instantaneous amplitude, instantaneous phase and trend term are established at each moment. According to the constructed proxy model, a high-precision and high-efficiency prediction of the dynamic response of an uncertain flexible multi-body system is achieved. The present invention is particularly suitable for the prediction of the dynamic response of large and complex systems.

The invention discloses a shale gas field yield prediction method. The method comprises the following steps: 1, establishing a shale gas field yield prediction initial model which only takes time as an independent variable parameter; 2, obtaining a yield fitting value of the shale gas field according to the shale gas field yield prediction initial model; 3, drawing a yield prediction curve according to the yield fitting value and the corresponding development time; 4, dividing the yield prediction curve into an ascending section yield prediction curve and a descending section yield prediction curve; 5, respectively processing the ascending section yield prediction curve and the descending section yield prediction curve to obtain a final shale gas field yield prediction model; and 6, predicting the yield of the shale gas field according to the final shale gas field yield prediction model. According to the method, a shale gas field yield prediction model is established through a mathematical method which only takes time as an independent variable parameter, so that more accurate yield prediction can be realized on the basis of fewer parameters, and the technical problems that the existing yield prediction method obtains more parameters, and the parameters are difficult to obtain and inaccurate to obtain are solved.

The invention relates to the technical field of deciduous forest pest prediction, and discloses a method for predicting pest population density distribution patterns in deciduous forests. The method comprises the following steps: step 1, collecting historical information of pest density at a predicted local point; step 2, predicting a spatial distribution pattern according to the historical information of pest density in the local area; step 3, when data are distributed in two different intervals, xl and xh are respectively used to represent the midpoints of the two intervals, and s=xh-xl represents the distance between the two midpoints; step 4, Ul and Uh are respectively used to represent half of the width of the two intervals; step 5, the midpoints xl and xh of the two intervals are regarded as two states, and Ul and Uh respectively represent the uncertainty of the two states; step 6, calculating K=(Ul+Uh) / s, and the spatial distribution structure of the pests can be obtained according to the value of K.

The objective of the invention is to provide a TFT-based crusher lining plate use state prediction method and system in order to solve the problems of the existing crusher lining plate service life prediction technology. In the invention, the TFT is used as a core backbone structure of the model, and an improved module for explicit alignment and multi-task prediction is added on the basis. The method comprises the following steps: obtaining time sequence data and scalar data by obtaining and preprocessing data related to lining plate consumption; and constructing a life prediction model, and performing feature extraction and prediction on the obtained data to obtain a prediction result. According to the method, a lining plate sensor does not need to be adopted, the cost of the method for predicting the service life of the lining plate is reduced, the prediction accuracy is improved, the state and the use condition of the crusher lining plate can be analyzed in real time, the situation that equipment is shut down abnormally due to abrasion of the lining plate is greatly reduced, and then production is improved and stabilized.

The present invention discloses a multi-scenario adjustment and control method for an intelligent electric bed based on artificial intelligence, including detecting the user's behavioral intention, when determining that the arrival probability is greater than a preset value, inputting the current time and user identity information into a scene prediction model, matching a first configuration scheme according to the output scene type, to configure the use parameters of the intelligent electric bed; detecting the user's posture change data and the duration of each posture, analyzing the user's use status according to the duration, adjusting the first configuration scheme according to the use status analysis result, and generating a second configuration scheme; predicting the force tendency of the user's intelligent electric bed during use according to the user's posture change data, and optimizing the second configuration scheme, and adjusting the intelligent electric bed according to the optimized scheme. The present invention can adaptively adjust the parameters of the electric bed for different users in different use scenarios, meet the user's personalized use needs, and improve the user experience.

This invention provides a method and apparatus for predicting obstacle trajectories, an unmanned vehicle, and a storage medium. The obstacle trajectory prediction method includes: determining the target road scene currently occupied by the unmanned vehicle based on location information; if the target obstacle's number is among multiple obstacle numbers in the obstacle prediction queue, then determining the target obstacle's motion constraint boundary conditions in the target road scene based on a preset correspondence between the road scene, the obstacle, and the obstacle's motion constraint boundary conditions; if the target obstacle's motion information satisfies the target motion constraint boundary conditions, then obtaining target motion observation information based on the location information and the target obstacle's motion information; and predicting the target obstacle's trajectory within a specified time based on the target motion observation information and size information, thereby improving the effectiveness of the predicted trajectory and reducing prediction costs.

The application provides a life prediction method and device of a circuit breaker contact, a circuit breaker and a medium, and relates to the technical field of low-voltage electrical apparatuses. The method comprises: obtaining an impedance correction coefficient of a contact group in the circuit breaker; obtaining a current thermal capacity of the contact group according to the impedance correction coefficient and a breaking current of the circuit breaker, the breaking current being a current of a closed loop before the circuit breaker performs a breaking operation; and determining a residual life parameter of the contact group according to an initial thermal capacity and a current thermal capacity of the contact group, so that the residual life parameter of the contact group can be determined according to the initial thermal capacity and the current thermal capacity of the contact group based on the impedance correction coefficient of the contact group, and compared with the prior art, the life prediction method can reduce the prediction cost without making great changes to the structure of the circuit breaker.

The invention discloses an unconventional oil and gas well casing deformation control method, which comprises the following steps of: evaluating casing deformation risks existing in a gas well single section, and judging which casing deformation risks exist in the gas well single section; the casing deformation risk comprises fault development, natural fracture development, micro-structure development, frequent crossing, poor well cementation quality and well diameter expansion; and executing corresponding regulation and control methods according to different quantities of risk types. According to the method, effective control of casing deformation is realized on the premise that geological modeling and fracturing simulation are not carried out and a high-cost monitoring instrument is not put down.

The present application relates to the field of oil and gas field exploration and development, especially a structural fracture connectivity prediction model and a method thereof. By calculating the ratio of single well isotope intensity and logging natural gamma, the water injection profile type is divided; by calculating the single well rock mechanics parameters, the size and direction of the paleostress in the study area are determined in combination with the rock internal friction angle and the fracture trend. By establishing a single well geomechanics model, the paleostress size in the fracture formation period is simulated, a structural fracture connectivity database model is established, a structural fracture connectivity prediction model is established through correlation analysis, and finally the structural fracture connectivity is predicted, and the result reliability is verified by using dynamic development data. The present application proposes a structural fracture connectivity prediction model and a method thereof, and the prediction result has certain reference significance for fracture genetic mechanism interpretation, fracture connectivity prediction, geological sweet spot evaluation and other aspects.

The present disclosure provides an ozone concentration prediction method and device, electronic device, and readable storage medium, which belong to the field of environmental monitoring technology. The method includes: determining target ozone concentration data in a target area, where the target area is the area where the monitoring point corresponding to the target ozone concentration data is located; determining a target fitting regression equation that matches the target ozone concentration data based on the monitoring point and the meteorological data corresponding to the monitoring point; inputting the target ozone concentration data into the target fitting regression equation to obtain the predicted ozone concentration data of the target area. The ozone concentration prediction method and device, electronic device, and readable storage medium provided by the present disclosure can improve the accuracy of ozone concentration prediction.

The present invention discloses a pulse extraction column process simulation method, device, verification method and system. The simulation method comprises: obtaining equipment attribute information, initialization information and extraction information of the pulse extraction column, wherein the equipment attribute information comprises the number of plates and equipment parameters. According to the number of plates of the pulse extraction column, a plurality of single plate models are established. The plurality of single plate models are combined to obtain an extraction calculation model of the pulse extraction column. According to the equipment parameters, initialization information and extraction information, the extraction calculation model is solved to obtain operation simulation data of the pulse extraction column. The simulation method can simulate the process of the pulse extraction column to predict the actual production status of the pulse extraction column and reduce the prediction cost.

The invention relates to the technical field of cutter life prediction, and discloses a crushing equipment cutter life prediction method based on finite element analysis, and the method comprises the steps: S10, determining a material of a crushing object with the maximum shearing acting force; s20, constructing a geometric model of the crushing equipment cutter according to the structure of the crushing equipment cutter; s30, obtaining a data set for finite element analysis according to the material of the crushing object and the cutter of the crushing equipment; s40, the position of the maximum stress borne by the crushing equipment cutter, the maximum stress value sigma max of the crushing equipment cutter rotating by one circle and the maximum acting force fmax borne by the crushing equipment cutter are determined; s50, finite element analysis is conducted on the position with the maximum stress through finite element analysis software, and the single-circle abrasion loss vmax generated when the cutter of the crushing equipment rotates by one circle is obtained; s60, simulating the crushing process through finite element analysis to obtain the abrasion loss Vmax of the cutter of the crushing equipment when the cutter is scrapped; and S70, calculating the service life of the cutter of the crushing equipment.