51results about How to "Improve predictive reliability" patented technology

The coal petrographic dynamic calamity real-time monitoring prediction device and prediction method relate to a technique for continuously monitoring coal petrographic concrete deformation break'up electromagnetic radiation information and its device. Said device includes preamplifier, A/D converter, buffer, CPU, program memory, data memory, display, RS485 communication interface, standard signal output circuit and keyboard formed monitoring main machine, also includes antenna, power supply, KJ system branch station and KJ system center machine. Said invention also provides its real-time monitoring prediction method.

The invention relates to a modeling method for medium and long term power load forecasting. The modeling method comprises the following steps: dividing power demand in multiple layers according to industry and trade, extracting history data to form a forecasting matrix, and constructing an initial load trend model; extracting influence factors and analyzing the degree of correlation of forecasts, and determining the important influence factors of each forecast; forming a forecasting method base; extracting maximum load Pmax, annual average load and annual minimum load Pmin as key load indexes, and analyzing the characteristics and rules appearing in Pmax and Pmin and a forecasting method thereof; selecting the forecasting method to forecast the forecasts in a combined mode, carrying out curve fitting on forecasting results and the history data to obtain the development trend of the forecasts, and constructing a load trend model; amending the parameters of the load trend model and the weight of the forecasting method according to load influence factors and influence weights, and establishing a comprehensive load forecasting model. The modeling method has great advantages for improving the reliability of the power load forecasting and analyzing the inherent law of power load.

The invention discloses a multi-line multi-public transport vehicle priority control method at a signal intersection. Aiming at the condition that a multi-line multi-public transport vehicle priority request collision problem at the signal intersection of a trunk line is increasingly prominent at present and the control effect of the present method is bad, the method selects two indexes of public transport passenger delay and passenger waiting delay at a downstream bus station to measure priority levels of the multiple priority requests. Then the delay corresponding to the multiple public transport vehicles of multiple lines applying for the same priority strategy is added. The priority level corresponding to the priority request with the large delay is high, and a higher passing priority is given. Thus the multi-priority request collision problem is solved. The control efficiency of the public transport priority is raised. The service level and the operation efficiency of the city public transport are improved. More passengers are attracted.

The invention belongs to the technical field of short term power load forecasting, and discloses a power load forecasting method based on improved exponential smoothing and a gray model. The method includes the following steps: inputting original power load real-time data, and conducting a single exponential smoothing on the original power load real-time data, weakening the randomness of the original power load real-time data, such that the original power load real-time data approaches exponential development trend; predicting a smoothed sequence by using a gray forecasting model which optimizes background value; conducting inverse exponential smoothing on the forecasting result and returning the result to original power load data and a forecasting value at a next forecasting moment; determining whether the result reaches the requirements of knitting fitting errors, and outputting a forecasting result. According to the invention, the method expands the application range of the gray forecasting model, shortens search intervals, has higher forecasting reliability as high as 97%, can the meet requirements for maintaining the average error of short term power load forecasting at approximately 3% so as to address the problem of short term power load forecasting in future development of intelligent power grids.

The invention discloses a secondary protein structureprediction method based on a deep learning andneural network method, and relates to the technical field of neural networks and secondary protein structureprediction. The method comprises the steps of inputting a protein characteristic sequence, and predicting a space secondary structure of an amino acid residue at each site of the sequence through a designed deep recurrent neural network model. The method provided by the invention realizes automatic predication of the secondary structure based on input characteristics, has better generalization ability, and can train a specific model and realize secondary structure predication with high accuracy according to the different input characteristics.

The invention relates to a method for predicting the aging failure rule and the service life of a polymer material under multiple environmental factors, belonging to the field of high polymer materials. According to the method, a lifetime characteristic index-aging time curve of the polymer material under an acceleration condition is obtained based on an accelerated aging test under the multiple environmental factors, corresponding aging failure acceleration factors are calculated by virtue of an Arrhenius formula, a reciprocity method and a superposition rule, an aging failure curve in a normal service environment (with multiple aging factors) is extrapolated from the failure curve under the acceleration condition by virtue of the aging failure acceleration factors, and the aging failure rule of the polymer material is predicted. The method has the beneficial effects of short test cycle, good repeatability, simplicity in theoretical derivation and high prediction reliability.

The invention relates to a deep sea video quality objective assessment model based on a spatial-temporal feature. The assessment model comprises the steps as follows: S1, a deep sea video sample set performs time domain learning, and extracts a feature vector based on a time domain dimension; S2, the deep sea video sample set performs spatial domain learning, and extracts a feature vector based ona spatial domain dimension; S3, the feature of the time domain is integrated with the feature of the spatial domain to form a final deep sea video quality classification data set; S4, classificationof a deep sea video quality classifier is semi-supervised; and S5, the deep sea video quality objective assessment model is built. The model has the advantage that the deep sea video quality objectiveassessment model is built, and an objective quality assessment service is provided for the public. The effect of various underwater image/ video enhancement algorithms applied to improving deep sea video quality is assessed, and the work efficiency based on deep sea video research is improved.

The invention belongs to the technical field of network traffic prediction, and particularly relates to a combined network traffic prediction method based on ensemble empirical mode decomposition, which comprises the following steps: obtaining original traffic data and preprocessing the original traffic data; decomposing the network flow into IMF components with single frequency on different timescales through ensemble empirical mode decomposition; determining the stationarity of the IMF component sequence through autocorrelation and partial autocorrelation analysis; predicting the stable IMFcomponent by using a linear ARMA model; predicting the non-stationary IMF component by using a nonlinear Elman neural network; summing the predicted values of the IMF component sequences to obtain apredicted value of the network traffic; According to the method, the actual network flow is described and predicted more accurately and comprehensively, so that the prediction precision is improved, and the prediction reliability is improved.

The invention discloses an estimation method for a state of health (SOH) of a battery. The method specifically comprises the following steps of: 10, establishing a database which is composed of a battery SOH value and the maximum peak of a battery charging ICA curve corresponding to the battery SOH value; 20, constant-current charging the battery on line, thus acquiring the maximum peak of an online charging ICA curve; 30, finding whether the database has the SOH value corresponding to the maximum peak; 41, when the database has the SOH value corresponding to the maximum peak, acquiring the SOH value corresponding to the maximum peak; and 42, when the database does not have the SOH value corresponding to the maximum peak, finding the SOH values corresponding to the two maximum peaks close to the maximum peak, computing the SOH value corresponding to the maximum peak according to the SOH values corresponding to the two maximum peaks close to the maximum peak by using a linear interpolation method.

The invention provides a method and a device for predicting pore pressure of a three-dimensional shale reservoir, and an electronic device. The method comprises the steps that an overlying strata pressure and a longitudinal wave modulus of the shale reservoir in a region to be predicted are determined according to a density logging curve and a longitudinal wave velocity logging curve; the really-measured pore pressure value of the shale reservoir is taken as a constraint condition, and the longitudinal wave velocity logging curve, a shale-reservoir equivalent stress and the longitudinal wave modulus are fitted through the way of multiple linear regression to obtain fitting parameters; a wave impedance data volume, a density data volume and a longitudinal wave velocity data volume of the region to be predicted are obtained through a logging-constrained wave impedance inversion; a reservoir overlying strata pressure data volume, a longitudinal wave modulus data volume and a shale-reservoir equivalent stress data volume are further determined; and the pore pressure of the shale reservoir is determined finally. According to the device, the prediction accuracy and reliability of the pore pressure are improved, the application range is wide and the prediction results are visible.

The invention discloses a multi-scale Gaussian-Markov random field model-based lower limb motion identification method. The method comprises the steps of 1, collecting original data of C motion modesof human lower limbs, performing preprocessing on the original data, and constructing a data feature graph; 2, performing multi-scale decomposition and feature field modeling of a signal; 3, setting an iterative frequency Q, and iteratively updating a first-layer scale image observation field Gaussian model parameter {mu c, sigma c, pi c}; and 4, performing matching on a classification result anda standard set of each motion mode to judge mode attribution, and according to a voting rule, eliminating the problem of boundary fuzziness of a time sequence segmentation region of different motion modes. According to the method, a stable signal local feature can be extracted, and the signal noise influence caused by motion instability can be eliminated, so that the identification accuracy and the prediction reliability of the lower limb motion modes are improved, and the technical support is provided for stable control of an auxiliary motion system.

The invention discloses a hospital logistics operation management ecological platform, and relates to the technical field of hospital logistics data management. The system comprises a user side and a server side, wherein the server side comprises a data management unit, a data analysis unit, an application center, a service provider management unit, an ecological service access management unit and an ecological technology access management unit; the user side displays different interfaces according to different user types, and the user types comprise decision makers, supervisors and business users. The system is an open platform, can realize standard and rapid access and plug-and-play of a third-party service, and meets the rapid online requirements of a hospital party on diversified, customized and specialized logistics application service subsystems; the business operation and maintenance service management unit can realize unified management and unified display of multiple independent systems and data interaction among the multiple systems, and can effectively solve the problems of difficulty in hospital logistics management, business splitting, information isolation and high cost of independent deployment of the multiple systems in the prior art.

The invention belongs to the technical field of prediction or optimization, and discloses a prediction method for a power load under complex characteristic influence, and a computer information processing system. The method comprises the steps: inputting historical power load characteristics and influence factor data thereof; carrying out the standardization of an original data sequence, so as toeliminate the interference caused by the difference of units; carrying out the PCA (principal component analysis) of the standardized sequence, and obtaining a PCA expression; calculating the scores of all principal components and an integrated score, obtaining a new data sequence, and carrying out the gray scale correlation analysis of the new data sequence; determining the weight value of each correlation coefficient according to a rule that the weight value is larger for a closer correlation coefficient; carrying out the ordering of the obtained weighted correlation degrees, substituting the weighted correlation degrees into a prediction model, and obtaining a power load characteristic prediction value. The method reduces the analysis complexity of a plurality of influence factors, solves a problem that the information in the influence factors are overlapped, is high in prediction reliability, can meet the requirements of the prediction of the power loads under the complex characteristic influence, so as to solve a problem of accurate planning and scheduling optimization in a power grid in future.

The invention discloses a pipe network big data detection system which is composed of a pipe network parameter acquisition platform and a pipe network safety big data processing subsystem, the pipe network parameter acquisition platform detects pipe network parameters, the pipe network safety big data processing subsystem classifies pipe network safety, and pipe network operation benefits and reliability are improved; the method effectively solves the problems that an existing pipe network has no influence on pipe network safety according to nonlinearity and large lag of pipe network parameter changes, large pipe network area, complex parameter changes and the like, pipe network parameters are not predicted, and pipe network safety is not pre-warned, so that reliable operation and intelligent management of the pipe network are greatly influenced.

The invention discloses a method for predicting overpressure of an undercompaction and hydrocarbon generation mixed formation cause, and aims to provide a method for carrying out quantitative formation pressure prediction in a development area which has two cause mechanisms of undercompaction and hydrocarbon generation at the same time and jointly causes overpressure of formation pores. Accordingto the new method, stratum TOC content pre-stack earthquake prediction is creatively correlated with hydrocarbon generation pressurization on the basis of calculating the under-compaction factor overpressure contribution by taking speed reduction as the basis by adopting the thought of quantitatively characterizing and finally stacking the under-compaction factor overpressure contribution and thehydrocarbon generation overpressure cause contribution respectively. The invention provides a new hybrid cause overpressure prediction method which is simpler, more convenient and more intuitive thanthe existing methods based on the loading/unloading theory, such as power and the like. According to the method, the risk that the prediction precision is reduced due to the fact that parameters of anunder-compaction or hydrocarbon generation prediction model are adjusted to be approximate to a mixed cause result conventionally is avoided, the complex regional parameter determination step of a power loading/unloading curve overpressure prediction method is also avoided, and a calculation result is more stable.

The invention discloses a crystal-scale dolomite corrosion pore formation evolution simulation method and device. The method comprises the following steps: preparing a dolomite crystal sample; carrying out a corrosion simulation experiment on the dolomite crystal sample by utilizing a pre-prepared fluid for a simulation experiment; collecting a crystal characteristic image of the dolomite crystal sample before a corrosion simulation experiment and a plurality of crystal characteristic images after multiple corrosion simulation experiments; and according to the crystal characteristic image of the dolomite crystal sample before the corrosion simulation experiment and a plurality of crystal characteristic images after multiple corrosion simulation experiments, determining evolution characteristic information in the dolomite corrosion pore forming process. According to the method, the formation process of the corrosion pores can be accurately analyzed, the development law of the corrosion pores can be known, and the reservoir prediction reliability can be improved.

The invention discloses a livestock and poultry house environment big data detection system, which comprises a livestock and poultry house environment parameter acquisition and control platform and a livestock and poultry house environment big data processing subsystem, and is used for detecting and adjusting livestock and poultry environment parameters and predicting the yield. The system effectively solves the problems that an existing livestock and poultry breeding environment has no influence on the yield of the livestock and poultry breeding environment according to nonlinearity and large lag of livestock and poultry breeding environment parameter changes, the livestock and poultry breeding environment is large and complex in area, the yield of the livestock and poultry breeding environment is not predicted, and livestock and poultry breeding environment parameters are not accurately detected and adjusted; therefore, yield prediction and production management of the livestock and poultry breeding environment are greatly influenced.

The invention provides a novel random user balance day-by-day path traffic flow prediction method considering the influence of overlapping paths. The method can simulate a day-by-day evolution processof traveler path flow under random user balance. According to the method, through an initial network path flow mode obtained through investigation, a path flow mode on an arbitrary N(th) day thereafter can be predicted, so that guiding opinions are provided for formulation and implementation of traffic control measures in a future period of time. Through the method, the influence of path overlapping on a traveler path selection behavior is considered by defining overlapping cost, therefore, a model is more approximate to the actual situation, and the reliability of flow prediction is improved; besides, the value of a flow regulation ratio can be regulated automatically along with development of the evolution process; and therefore, the trouble of investigation is omitted, and the method better conforms to the actual situation.

The invention discloses a slope stability prediction and evaluation method. The method comprises the following steps: 1, selecting a slope stability judgment index and determining an allowable safety coefficient [K]; 2, constructing a slope model according to a to-be-predicted slope, and obtaining a data set of judgment indexes and corresponding stability results by utilizing engineering simulation software; 3, performing maximum value and minimum value normalization processing on the data set; 4, constructing a slope stability prediction model based on an integrated learning algorithm according to the normalized data set; and 5, during evaluation, obtaining actual judgment index data of a slope to be detected, and substituting the actual judgment index data into the slope stability prediction model to obtain a slope stability prediction result. According to the method, the stability and safety prediction of the slope can be realized on the basis of not damaging the soil structure, and the method has the advantages of high prediction reliability and good precision.

The invention discloses an electrical load prediction method and system based on k-means clustering and a BI-LSTM neural network. The method comprises the following steps: preprocessing historical electrical load data through k-means clustering; taking historical electrical load data under the action of the same influence factor as original data through the clustering model to predict the electrical load in a certain time period in the future under the condition of the same influence factor, wherein the predicted data is closer to real data under the real condition, and the prediction reliability is high; on the other aspect, establishing the BI-LSTM neural network model is established to process the data, predicting the current state by using the historical data, and predicting the current state by considering the future condition, so that the basic LSTM neural network is considered, the influence of the hyper-parameter optimization model on the formation of each superposition layer is reduced, and the prediction precision is improved.

The invention relates to an analysis method for judging the coal mine heading face gas explosion overpressure and belongs to the technical field of coal mine gas analysis. The method includes the following steps that S1, the total energy of gas explosion at the different initial states is figured out; S2, a heading face gas explosion overpressure prediction model is established in combination withthe explosion gas dynamics knowledge and prediction calculation is performed; S3, the overpressure prediction module is corrected in combination with experimental data and a gas compression equation;and S4, actual measured explosion overpressure data of a large-size roadway are compared with the overpressure prediction data, and then a gas explosion overpressure correction prediction model is obtained. The analysis method is used for performing probability analysis and intensity analysis prediction of gas explosion in combination with the historical conditions and actual conditions of each mine, and pertinence controlling measures are designed in advance for preventing harm caused by gas explosion impact.

The present disclosure relates to a device (10) for route planning for an electric vehicle (26), comprising: an input interface (12) for receiving an up-to-date charge level of an energy storage (24)of the electric vehicle and a planned route (32) for the electric vehicle; a database interface (14) for receiving charging station information with locations of charging stations; an energy planningunit (16) for determining an estimated status of the charge level of the energy storage, based on the up-to-date charge level of the energy storage and the planned route; a charging planning unit (18)for selecting a charging station based on the estimated status of the charge level, the charging station information and the planned route; a matching unit (20) for determining at least one customized route (34) passing through the location of the selected charging station (40) based on the planned route.

The invention discloses a method for predicting the service life of a glass fiber reinforced plastic pipe. The glass fiber reinforced plastic pipe is subjected to a soaking test. The influence of thecorrosivity of a conveying medium on the service life of the pipe is considered. Tensile strength data of the glass fiber reinforced plastic pipe soaked in the corrosive medium at different times areutilized, a corrosion internal pressure attenuation equation of the glass fiber reinforced plastic pipe is established through a hydrostatic test and a hydraulic bursting test, and on the other hand,the influence of long-term internal pressure borne by the pipe on the pipe bursting strength is considered, a long-term strength and time relation equation of the pipe in a corrosive medium is established, and the service life of the pipe is obtained by setting different safety critical pressure values. The method provided by the invention is established on the basis of test data, the test periodis relatively short, the implementation is convenient, the method is tightly combined with the pipe service condition, and the prediction reliability is high.