221results about How to "Reliable predictions" patented technology

The invention discloses a multi-time scale forecasting method for a road traffic running situation. Highway traffic parameters in different time scales are analyzed according to the running time-space characteristics of highway traffic flow; the highway road traffic running situations in different time scales are forecast by an exponential smoothing algorithm, a weighted average algorithm and a Kalman filtering method respectively; a highway road traffic running situation evaluation index system and a multi-time scale highway traffic flow running situation forecasting technology are constructed to implement the conversion from experience guide to science guide for the highway running management and the preliminary conversion from passive management to active management. Therefore, the running efficiency of a road traffic running situation forecasting system can be increased effectively, the running cost of the system is reduced, the coordination degree between road traffic guidance and management can be improved obviously, and an optimal policy is provided for improving a traffic management and control measure and planning a travel plan for a road traffic manager and a user to a large extent.

The invention discloses a bus load prediction method. The method comprises the following steps: correcting abnormal values in historical load data by use of a transverse comparison method, and determining key influence factors of bus load by use of a grey relation projection method; putting load curves with similar features in the same category by use of an improved K-Means clustering method to get a plurality of typical load patterns, building a random forest classification model, and establishing the mapping relationship between influence factors and clustering results; for each load pattern, training a plurality of prediction models by use of a multivariate linear regression method; and determining the category of a day under test, and selecting a matching regression model to realize load prediction. A data mining method is introduced to analyze the changing rules of bus load, and a prediction model library is built. Model matching is realized based on the category of a day under test. The accuracy and real-time performance of short-term bus load prediction are improved. More accurate decision support is provided for power grid planning and real-time dispatching.

The invention provides a multivariable support vector machine prediction method for aero-engine rotor residual life. According to the method, service time, a load spectrum, rotation speed and vibration signal characteristics of an aero-engine rotor are selected to be as input parameters of a life prediction model. A multivariable support vector machine prediction model for the residual life is established based on a multivariable prediction method, sample parameters are input to the model to be trained and then output, and prediction for the residual life of the aero-engine rotor is achieved under a small sample condition. The method is simple and practical, reliable in result, good in instantaneity and is suitable for quantitatively calculating the residual life of the aero-engine rotor under the small sample condition.

The present invention discloses a multi-layer oil reservoir overall yield prediction method. The method comprises: dividing a multi-layer oil reservoir into a plurality of blocks, determining a reservoir stratum type, a formation factor Kh and an evaluated reserve volume of each small layer of each block; selecting, from the plurality of blocks, a block representing a multi-layer oil reservoir geological feature as a representative block, establishing a fine geological model of the representative block; establishing a corresponding fine numerical simulation model according to the fine geological model of the representative block, determining a typical mining curve of different types of reservoir strata in different development manners; determining a relationship curve between a single well injection amount and Kh in the multi-layer oil reservoir, and a relationship curve between a produced quantity and Kh; and predicting a multi-layer oil reservoir yield according to the typical mining curve, the relationship curve between the injection amount and Kh, the relationship curve between the produced quantity and Kh, and the reservoir stratum type, Kh and evaluation reserve volume of each small layer of each block. According to the multi-layer oil reservoir overall yield prediction method, the prediction accuracy of the multi-layer oil reservoir overall yield is improved, and further, working efficiency is improved.

The invention discloses a power load prediction method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring historical power consumption data, and performing empirical mode decomposition on the historical power consumption data to obtain a series of intrinsic mode function components and residual components; learning the residual component by using a single-layer LSTM network, and outputting a trend prediction result; learning a series of intrinsic mode function components by using a CNN-BiLSTM network fused with an attention mechanism, and outputting a series of corresponding fluctuation prediction results; and reconstructing a series of corresponding fluctuation prediction results and trend prediction results to obtain a final power consumption prediction result. The prediction model is constructed to learn the historical power consumption data, the trend prediction result and the fluctuation prediction result based on the historical power consumption data are obtained, and the obtained prediction result is reconstructed to obtain the final prediction result, so that the final prediction result is accurate and reliable.

The invention provides a power battery system residual available life prediction method based on a relevance vector machine and particle filter; the method comprises the following steps: using the relevance vector machine to extract collected power battery capacity declining characteristic vector values; building a power battery system aging model; using a particle filter theory to predict the power battery system residual available life through the aging model. The method can effectively reduce the training data bulk, can improve the algorithmic prediction precision, can ensure the RUL estimator stability, and can be expected to obtain accurate and reliable prediction results in real applications.

The invention provides an automatic blog writer interest and character identifying method based on a support vector machine. The automatic blog writer interest and character identifying method includes building an interest classified training sample set and a character classified training sample set at first; respectively processing the two training sample sets by a Chinese morphology analyzer to obtain a candidate interest feature item set and a candidate character feature item set; then analyzing the two candidate feature item sets by the aid of a statistics method; building an interest classified feature item set and a character classified feature item set; displaying the interest classified training sample set and the character classified training sample set into vector forms by the two feature item sets; and finally respectively using two groups of training interest classifiers and character classifiers. The classifiers are used for identifying interests and characters of other writers. By the aid of the automatic blog writer interest and character identifying method, the interests and the characters of the writers can be accurately identified, the method is applied to various personal services based on information of the writers, service providers can sufficiently know users, service quality is improved, and the method has an extremely high practical value.

The invention relates to the field of rock fracture prediction, in particular to a shale hydraulic fracture propagation prediction method. The method comprises the steps that 1, the normal direction,tangential stress and effect stress of an inclined fracture under the action of the external stress and water pressure are calculated; 2, a strain energy density function is obtained according to thetype of the fracture; 3, a strain energy density factor is obtained according to the strain energy density function; 4, the propagation direction and propagation angle of the fracture are judged according to a strain energy density criterion; 5, influences of stratification, natural fractures and the like on the propagation direction of hydraulic fractures are obtained through numerical simulation, so that fracture propagation under the effect of shale hydraulic pressure is predicted. The prediction method is based on fracture mechanics, a hydraulic condition factor is introduced, and the influences of different stratification directions on the propagation direction of the shale hydraulic fractures are obtained by researching the relation between the fracture propagation direction and themagnitude of the hydraulic pressure and utilizing an extended finite element method, so that accurate prediction of hydraulic fracture propagation is achieved, and higher prediction accuracy is obtained.

The invention belongs to the wind power generation technical field, and especially relates to a wind power plant cluster wind speed prediction method comprising the following steps: a wind power plant clustering step; a wind speed correlation hierarchy analysis step; an adjacent wind power plant wind speed prediction step. The wind power plant cluster wind speed prediction method is strong in operationality and practicality, accurate and reliable in prediction result, thus greatly accelerating wind power engineering progress.

The invention belongs to the field of concrete compressive strength prediction, and particularly discloses a method for predicting concrete compressive strength based on a random forest and an intelligent algorithm. The method comprises the following steps: establishing an original sample set of a concrete compressive strength index system, taking a training number set as the input of a random forest regression model to carry out importance evaluation on influence factors forming the concrete compressive strength index system, carrying out feature selection, and selecting an influence factor set with the minimum error as an optimal feature variable set; training the least squares support vector machine model by taking the test data set as the input of the least squares support vector machine model and taking the concrete 28d compressive strength value as the output, and verifying the prediction result of the trained least squares support vector machine model by adopting the test data set; and performing error analysis on a prediction result. The invention improves the precision of the prediction model, enables the prediction result to be more accurate and stable, and can serve as an effective tool for quickly predicting the concrete compressive strength.

The invention discloses a clustering and neural network-based power quality prediction method for a power distribution network containing a distributed power supply. The method comprises the steps oftraining data acquisition and normalization processing; performing clustering division on the historical input data set; dividing a training set and a verification set; enabling BP neural network prediction to perform model training; Solving an optimal training set division mode; obtaining predicted input variable values and normalizing the predicted input variable values; determining cluster affiliation of the input variable value; performing electric energy quality prediction output and reverse normalization; making a power quality prediction result assessment. The method has the advantagesthat 1, the BP neural network is used for effectively predicting the power quality of the DG-containing power distribution network; 2, a k-means algorithm is used to carry out classification preprocessing on the neural network training set by using a means clustering algorithm, and providing different prediction models for each class, so as to overcome the defect that a BP neural network is easy to fall into a local optimal solution, and obviously reduce the prediction error; and 3, the training set, the verification set division mode and the hidden layer node number N are circularly changed for multiple times, and the probability of obtaining the optimal model is improved.

The invention provides a method for predicting the key industrial electricity consumption based on an industrial condition index. The method comprises the following steps: (1) obtaining the key industrial condition index and historical electricity consumption data; (2) performing seasonal adjustment and a stationary test on the data; (3) judging whether the industrial condition index and the industrial electricity consumption have a causal relationship or not through a Granger causality test and determining an optimal lag period of the condition index; (4) creating a time sequence ARIMA (autoregressive integrated moving average) model of the key industrial electricity consumption, introducing the key industrial condition index into an original ARIMA model, and creating a regressive model; (5) on the basis of an AIC (Akaike information criterion), screening out an optimal model; (6) performing model popularization and application, and predicting the industrial electricity consumption in the future. The key industrial electricity consumption is taken as a study object, the electricity consumption and the influence of the industrial condition index on the electricity consumption are studied by introducing the industrial condition index, the key industrial electricity consumption is accurately predicted in combination with the time sequence model, and a basis is provided for development and planning of electricity industry in the future.

The invention discloses a shale gas well yield prediction method, which comprises the following steps that: S1: according to a shale gas well analysis model, constructing the double logarithmic plateof theoretical model data; S2: obtaining the actual measurement data of a shale gas well to be analyzed, and constructing the double logarithmic plate of data according to the actual measurement data;S3: carrying out fitting on the double logarithmic plate of theoretical model data and the double logarithmic plate of the actual measurement data, an determining the yield prediction model parameterof the shale gas well to be analyzed; and S4: according to a preset shale gas well yield prediction model and the yield prediction model parameter of the shale gas well, determining the prediction yield of the shale gas well to be analyzed. The method is suitable for the shale gas well with irregular cracks, parameter input reliability during yield prediction is improved, the accuracy of a yieldprediction result is guaranteed, and the method performs an important function on evaluating the fracturing transformation effect, the production dynamics and the economic benefit of the shale gas well.

The invention discloses a product potential user mining method and device. The product potential user mining method comprises the following steps: collecting user data to be predicated; for the user data to be predicated, carrying out prediction of potential users by utilizing a prediction model pre-established based on a machine learning algorithm; and outputting a prediction result. According tothe technical scheme, product potential users are obtained through the prediction model pre-established based on the machine learning algorithm, so that compared with a manual screening mode, the method greatly improves screening efficiency of the potential users, and effectively saves labor and time cost.

The invention provides a landslide displacement prediction method based on wavelet transform-rough set-support vector regression (WT-RS-SVR) combination. By means of the method, according to the characteristics of the influence factors of landslide displacement, the complex displacement process and landslide displacement monitor data measured in real time, accumulative displacement of a typical monitor point is decomposed into trend-term displacement and periodic-term displacement through WT, and a trend-term displacement prediction function is obtained through curve fitting; screening is conducted on the influence factors of the landslide displacement through an RS algorithm, and selected factor sets are used as input factor sets of an SVR machine, accordingly a landslide displacement optimization prediction model based on WT-RS-SVR combination is established, and the precision of a prediction result is analyzed and evaluated. The prediction result of the landslide displacement prediction method can well embody the development and change tendency of the landslide displacement. The landslide displacement prediction method has high prediction capacity, and is accurate, effective and practical.

The invention provides a sulfur deposition prediction method for an acidic natural gas pipeline. According to the technical scheme of the invention, based on a sulfur solubility model, the classic nucleation theory and a particle motion equation, a thermodynamic model and a dynamical model for sulfur precipitation and deposition are established. Meanwhile, the saturated distance, the supersaturated distance and the particle maximal migration distance are calculated, while the sulfur deposition position, the sulfur deposition yield and the sulfur deposition average thickness of the acidic natural gas pipeline are figured out. In this way, the sulfur deposition prediction for the acidic natural gas pipeline can be realized. Based on the above method, a supersaturated distance L2 exists between a saturation point and the appearance location of sulfur particles, so that the precipitation location of sulfur particles can be calculated more accurately. The motion trajectory of sulfur particles can be figured out based on the particle motion equation, and then the maximal migration distance L3 of particles is determined. In view of the mechanism, the above method is more reasonable in predicting the deposition location of sulfur particles, compared with the conventional sulfur deposition prediction method based on a critical velocity calculation model for sulfur particles in a vertical well bore. In this way, the prediction result is more scientific, more accurate and more reliable.

The invention discloses a prediction method of crack initiation life of a coking tower. The method comprises the steps that a probability distribution model of the strain amplitude of the wall of the coking tower is built; based on the model, a strain amplitude data circulation sample is sampled according to a monte-carlo random method, and fatigue life and fatigue damage corresponding to each crack initiation of a given circulating period are calculated; if the fatigue damage of the given circulating period is accumulated to or above 1.0 under given iteration times, the fatigue damage is considered as crack initiation; according to the ratio of the crack initiation cumulative number to the given iteration times, the crack initiation probability is obtained; according to the given circulating period, the crack initiation probability and the given confidence degree, the relation between the crack initiation probability of the wall of the coking tower and the residual life is calculated and predicted. The invention further comprises a prediction method of crack propagation life of the coking tower. A probability distribution model of the stress amplitude is built to predict the crack propagation life of the coking tower on active duty. The method is low in cost and can evaluate risks of coking tower service.

The invention discloses a transportation mode recognition method based on mobile phone grid data. A mobile phone user transportation sequence is constructed based on mobile phone grid data and time characteristics, distance characteristics and speed characteristics of the sequence are obtained; on the basis of a penalty factor, the obtained mobile phone user transportation sequence data are cleaned to remove noise data; according to the obtained cleaned mobile phone user transportation sequence, sub mobile phone user transportation sequences are divided based on a speed clustering method; according to the obtained sub transportation sequences, a mobile phone user transportation chain is generated and time characteristics, distance characteristics and speed characteristics of the transportation chain are obtained; multi-mode transportation modes of the mobile phone user transportation chain are identified; and on the basis of the identified multi-mode transportation mode proportion of the mobile phone user transportation chain, a main transportation mode of the all-day transportation period of the user is identified. According to the invention, the transportation mode of the individual user can be obtained based on the on-aggregation level, so that the complexity of the model is reduced and the prediction accuracy is improved.

The invention discloses a semi-supervised semantic segmentation method based on maximum confidence, and the method comprises the steps: selecting a part of images from an existing training data set asmarked images, and taking the remaining images as unmarked images; constructing a network model, and predicting prediction class probability graphs of the marked images and the unmarked images through a segmentation network in the network model; maximizing the confidence coefficient of the marked image prediction class probability graph by adopting supervised learning and adversarial generation modes; predicting a segmentation error region in the unmarked image prediction class probability graph by adopting an unsupervised learning mode; training the network model by combining loss of supervised learning and loss of unsupervised learning; and in a test stage, inputting an unmarked image to be segmented into the trained network model to obtain a segmented semantic image. According to the scheme provided by the embodiment of the invention, semantic segmentation can be accurately carried out on the unmarked image.

The invention relates to a method for rapidly detecting the salt content in Fuling pickled mustard by using near-infrared spectroscopy. The detection steps of the method of the invention include sample collection, standard determination of the salt content of each sample, collection of each sample spectrum establishment, inspection model, product detection and classification, and the like. The method of the present invention has the characteristics of no need for pretreatment, no pollution, on-line detection, and simultaneous determination of multiple components, and is more environmentally friendly, fast, simple and quick, and can use chemometrics to establish a qualitative and quantitative method for determining the salt content in pickled vegetables such as Fuling mustard. quantitative model. The innovation of the present invention is that the near-infrared spectrum cannot reflect the characteristic absorption peak of inorganic table salt, but different Na+ and Cl- ions are released due to the different content of table salt in the sample, which affects the absorption peak of water, so the content of table salt can be quickly determined by modeling , and at the same time perform clustering according to the salt content into low-salt, medium-salt and high-salt beneficial effects.

The invention discloses a distribution network layering load forecasting method based on topology. A distribution network is layered according to a topology connection relation, forecasting is conducted on the layers respectively, a total forecasting result is obtained by summing in an optimizing mode, summarizing load data of a 10 kV outgoing line switch are read, and contrastive analysis is conducted on the data and the forecasting result. Forecasting accuracy is improved obviously, an intelligent distribution network system is utilized effectively, deep mining based on big data is achieved, the immunity to the data is improved, and lean management of the distribution network is achieved easily.

The invention relates to a geological disaster prediction and forecast technology, and aims to provide a rainfall threshold analysis method causing basin landslide risks. The method comprises the following steps: establishing a three-dimensional grid according to DEM topographic data and soil layer thickness data of a target watershed, and generating boundary conditions and initial conditions required by an RIRM hydrological model; calculating space-time changes of hydrological elements in the drainage basin and drainage basin slope stability reference indexes of any three-dimensional positionin the drainage basin; drawing a relation curve that the safety factor SF, the landslide volume and the landslide area respectively change along with time under the conditions of different rainfall durations and different rainfall intensities; analyzing the relationship between landslide deformation damage and rainfall to obtain rainfall thresholds causing basin landslide risks under different conditions. According to the method, natural basin geomorphic hydrological response characteristics are reserved, and prediction errors can be effectively reduced; drainage basin hydrology and slope stability analysis can be carried out simultaneously, the actual occurrence process of drainage basin landslide disasters is met, and the prediction result is more real and reliable.

The invention discloses a NOx emission dynamic soft-sensing method for a power station boiler. The method comprises the steps of acquisition and preprocessing of data, initialization of a self-adaptive particle swarm algorithm and the like. According to the method, related operating and state parameters of a boiler combustion system serve as the input of a model, the nitrogen oxide emission concentration serves as the output of the model, historical operating data are selected as training samples, a support vector regression machine serves as a soft-sensing modeling tool, the idea of a non-linear auto-regression moving average model is combined, the orders of input variables and output variables of the model are considered, and therefore the soft-sensing model has the capability of describing the dynamic change process. By means of the method, the change of NOx emission in the boiler combustion dynamic operating process can be effectively traced and predicted, and the method has important significance on safe and optimized operation of the power station boiler.

To provide efficient and effective modeling of data set, the data set is initially separated into several subsets which can then be processed independently. The subsets themselves are chosen to have some internal commonality, thus providing effective independent tools where possible. This commonality may include correlation between variables or interaction amongst the variables in the subset. Once separated, each subset is independently modeled, creating a subset model having predictive qualities related to the data subset. Next, the subset models themselves are aggregated to generate a overall final model. This final model is predictive of outcomes based upon all data in the data set, thus providing a more robust stable model.

The invention provides a method for predicting annual power consumption based on an elastic coefficient. The method comprises the following steps: (1) selecting a base year and reading historical data; (2) calculating the electric elastic coefficient of each year in a historical sample interval based on the base year comparable price; (3) calculating the added value ratios of two of three main industries of each year in the historical sample interval; (4) establishing a regression model of the electric elastic coefficient of the added value ratios of the two main industries; (5) predicting the electric elastic coefficient of a target year via the regression model; (6) calculating the social power consumption of the target year via the predicted electric elastic coefficient and the GDP (Gross Domestic Product). According to the method, a new electric elastic coefficient is calculated based on the base year comparable price, the regression model is established by using the electric elastic coefficient and the added value ratios of two of three main industries, and the prediction of the social power consumption of the target year is based on a theoretical model, so that the prediction accuracy is increased.

The invention provides a method for comparing stability expansion capabilities of casing treatment schemes. According to the method, control volume analyzing measures are used, single-channel numerical simulation is relied on, the whole characteristic lines of various circumferential groove schemes do not need to be calculated, comparative analysis is only conducted on different circumferential groove treatment cases under the flow near the stall point of a smooth wall, and the stability expansion capabilities of all the schemes can be rapidly and accurately obtained through comparison. The method has good universality, the advantages and the disadvantages of different casing treatment schemes for a compressor can be rapidly and reliably compared, the pertinence of initial stage design can be greatly improved, and time and developing cost are saved.

The invention discloses a natural gas reservoir physical property analysis technology and relates to a method for calculating the irreducible water saturation of the low-permeability tight sandstonewhich comprises the following steps: screening a rock sample of the low-permeability tight sandstone, and acquiring characteristic parameters of a pore structure of the rock sample by adopting a physical experiment method; establishing a three-dimensional pore physical model by adopting a digital core technology according to the pore structure parameters; according to the actual given simulation temperature and pressure of the gas reservoir, determining water-phase and gas-phase high-pressure physical property parameters; and completely saturating the three-dimensional pore physical model withwater, setting a displacement pressure difference, simulating a gas-driven water process, and calculating the water saturation in the model after displacement is stabilized. The irreducible water saturation of the low-permeability tight sandstone gas reservoir under different temperatures and pressures can be effectively predicted, the test and analysis period can be greatly shortened, the defects and shortcomings of an existing experimental analysis method are overcome, a large amount of test and assay expenses are saved, and a foundation is laid for comprehensive evaluation, seepage law research, reserve calculation and the like of the tight sandstone gas reservoir.

The invention discloses a kit and system for prognosis prediction of a metastatic colorectal cancer and relates to the field of biomedicine. The kit comprises a reagent for detecting the expression level of a target gene, wherein the target gene is selected from one or more genes in the group consisting of ACOT11, C12orf45, CHDH, COX17, CTNNB1, CYP2S1, DDTL, DUSP18, FAM221A, FGFR4, KLC4, LARS2, PFDN6, SLC27A3 and TNFRSF11A, the expression levels of the target genes are detected by using the kit, the prognosis condition of the metastatic colorectal cancer can be stably predicted according to the detection result, the prediction result is reliable, the kit has a clinical application prospect, and a new prediction thought or strategy is provided for the prognosis of the metastatic colorectal cancer.

An embodiment of the invention discloses a user churn prediction method and device. The method comprises the following steps: obtaining service consumption feature data, position activity feature data and social network feature data of a user within a first preset time, wherein the position activity feature data refers to relevant data obtained when the user is communicated with each base station within the first preset time, and the social network feature data refers to relevant data obtained when the user is communicated with other users in a social network within the first preset time; and inputting the obtained service consumption feature data, the position activity feature data and the social network feature data to a pre-trained classifier for calculation and outputting a calculation result, wherein the calculation result is the user churn prediction result. The user churn prediction method and device can improve accuracy of user churn prediction.

The present invention discloses a traffic accident prediction method based on the PCA and the BP neural network. The method comprises the following steps: constructing a traffic accident prediction model based on the PCA and the BP neural network, introducing a traffic accident data set in the vehicle network into the model, and selecting the feature vector of the traffic accident data set by using the model; performing decorrelation processing on the feature vector by using the PCA to obtain a preset number of linearly independent features in the feature vector; inputting the linearly independent features into the BP neural network for training, and obtaining new independent features for determining whether a traffic accident will occur; and inputting real-time traffic data, and predicting whether the traffic accident will occur according to the new independent features by using the prediction model. According to the traffic accident prediction method based on the PCA and the BP neural network provided by the present invention, accuracy rate for traffic accident prediction is higher, and the occurrence of traffic accidents can be effectively prevented.