110results about How to "Reduce forecasting costs" patented technology

The invention relates to the field of coal mine safety technique, specifically to a down-hole coal and gas outburst hazard early warning system and early warning method. The coal and gas outburst synthesized early-warning system, uses the existing local area network to connect a synthesized early-warning data server, an early-warning data management system and the existing coal mine safety monitoring system; analyzes the coal and gas outburst early-warning data in the synthesized early-warning data server by an outburst early-warning module; and emits early-warning information based on the analyzed result. The inventive coal and gas outburst synthesized early warning system and early warning method can perform centralized management and comprehensive analysis of the geological structure, coal seam occurrence, gas occurrence, mining production, daily forecast indicators, outburst forecast, gas emission and other security information that originally scatter in various functional sections of coal mine on the geographical information system GIS platform, integrates the existing resources, improves the accuracy of early warning, so that the early warning is both real-time and forward-looking, and can effectively prevent the occurrence of coal and gas outburst in coal mine.

The invention relates to the field of oil-gas field exploration and development, particularly to a quantitative forecasting method of tectonic fissure occurrence. The quantitative forecasting method includes firstly determining a fissure mechanical property and rock mechanics parameters in a research area and restoring a paleotectonic map; secondly performing a numerical simulation of a paleostress field; thirdly selecting an appropriate rock failure principle according to the simulated paleostress field and the fissure mechanical property, and forecasting the best occurrence and the second-best occurrence of paleofissures on the basis of plane shearing strength distribution or profile shearing strength distribution of the stress field in the research area; coupling spatial positions of the paleorock stratum and the current rock stratum based on the simulated ant tracing technique, and then establishing a spatial switching theoretical model of the paleorock stratum and the current rock stratum; performing the quantitative analysis of fissure kinematics characteristics, and forecasting the occurrence of the current fissures according to that of the paleofissures.

The invention relates to the field of oil-gas field exploration and development, in particular to a fractured reservoir permeability tensor and anisotropy quantitative prediction method. On the basis of stress field numerical simulation, a static coordinate system and a dynamic coordinate system are integrated into a geodetic coordinate system by using the current occurrence of fractures, multiple groups of fracture permeability tensor quantitative prediction models are established, quantitative calculation formulas of the permeability principal direction and data are given, and the permeability of fractures in units in different directions is predicted by adjusting the rotation angle of the dynamic coordinate system. The fractured reservoir permeability tensor and anisotropy quantitative prediction method is based on strict mathematical algorithm derivation, a corresponding calculating program can be developed by using computer programming languages, fractured reservoir permeability tensor and anisotropy quantitative prediction is realized, the prediction cost is low, the operability is high, and the prediction result has certain guiding significance on determining the fault block permeability dominant direction, deploying and developing well patterns reasonably, and determining the spatial location relationship between an injection well and a producing well.

The invention relates to the field of exploration and development of oil and gas fields, in particular to a method for forecasting the opening pressure, the opening sequence and the water injection pressure of a reservoir fissure. According to the method, a geomechanical model is determined through geological data, physical experiments and the like, and on the basis of paleo-stress-field numerical simulation, by means of the rock fracturing criterion and the ancient-and-modern rock-mechanics layer evolution characteristics, the present occurrence of different group fissures is forecasted; on the basis of present-stress-field numerical simulation, the work-area rock-mechanics layer distribution regularities are combined, principal-stress vertical gradients of different nodes are obtained with the rock-mechanics layer-top-bottom-face point searching method, ground stress information and fissure information are synthesized, inversion forecast of the opening pressure, the opening sequence and the water injection pressure of the fissure is achieved. The method is composed of strict mathematical algorithm derivation, after corresponding geological information is digitized, the corresponding calculation procedure can be developed with computer programming languages, forecast cost is low, and operability is high.

A method for determining grid cell size in geomechanical modeling of fractured reservoirs including a variation range of mechanical parameters of the reservoir is determined. A three-dimensional fracture discrete network model is established. Mechanical parameters of fracture surface are determined on the basis of fracture surface mechanical test. Equivalent mechanical parameters of models with different sizes are researched by three-cycle method, and size effect and the anisotropy of the mechanical parameters of the fractured reservoir are calculated respectively, and an optimal grid cell size in geomechanical modeling is determined.

The present invention provides a method for predicting AQI (Air Quality Index), comprising the following steps: obtaining historical weather data of a predicted area, wherein the historical weather data comprises historical AQI values, and historical meteorological data; preprocessing the historical weather data, wherein the preprocessing comprises checking compliance, converting the historical weather data into data suitable for computer processing, and generating derived fields; building a plurality of AQI prediction models based on a feature selection model, a regression analysis model, and a time series analysis model; evaluating the built AQI prediction models, and selecting the AQI prediction model with the highest prediction accuracy to serve as the optimal AQI prediction model; deploying the optimal AQI prediction model to the predicted area; and displaying AQI relevant indexes of the predicted area. The method does not need a mass of data and hardware equipment with high configuration, is simple and scientific, and can accurately predict the AQI of the specific area.

The invention discloses a method for predicting traffic flow extracted by an improved C-V model-based remote sensing image road network, which comprises the following steps of: (1) preprocessing an original remote sensing image; (2) selecting a seed point and segmenting a first road network sub-image; (3) extracting a road network area by an improved C-V model-based level set method; (4) extracting a road network central line by a morphological thinning method; (5) segmenting a next road network sub-image by using a sub-image position decision rule and automatically acquiring a road network initial curve in the road network sub-images by a threshold segmentation and morphological method; (6) vectorizing a road network; and (7) predicting the traffic flow. By integrating technology such as remote sensing, geographic information system (GIS), image identification, traffic planning and the like, an urban road network can be more accurately, efficiently and cheaply updated in real time, the traffic flow prediction cost is lower, the traffic flow prediction accuracy is higher and the traffic flow prediction period is shorter, so that decision makers can be effectively assisted in making traffic planning decisions.

The invention relates to the field of exploration and development of oil and gas fields, in particular to a fracture fractal characteristic optimization computation method. After datamation of a facture zone, parameters of statistical boxes are defined by setting boundary parameters and initial positions, the statistical boxes are moved constantly through program writing, fractal dimension values of the positions where the statistical boxes are located are calculated, and therefore programmed calculation of fracture fractal characteristics is realized. The fracture fractal characteristic optimization computation method has high practical value on the aspects of fracture fractal characteristic quantitative evaluation, fracture fractal characteristic quantitative description and the like, is low in prediction cost and high in operability, and greatly reduces the expense of manpower; evaluation results have certain guiding significance in the aspects of predicting the distribution characteristics of oil and gas exploration and development key areas, fracture dominant distribution areas and low-level-sequence faults and the like.

The invention relates to the field of image recognition, and discloses a bone age prediction method and device, a medium and electronic equipment. The method comprises the steps: acquiring to-be-predicted hand bone data; determining the gender of the to-be-predicted hand bone data; according to the gender, inputting the to-be-predicted hand bone data into a convolutional neural network model corresponding to the gender to obtain a predicted bone age output by the convolutional neural network model, wherein the convolutional neural network model is obtained by training in advance based on a triple loss function and a regression loss function. According to the method, the bone age prediction is carried out by utilizing the convolutional neural network model obtained by training based on thetriple loss function and the regression loss function, so that the bone age prediction efficiency is improved, the bone age prediction cost is reduced, and the bone age prediction accuracy is improved. In addition, the hand bone data of the corresponding gender is predicted specially by using the convolutional neural network model of the specific gender, so that the bone age prediction accuracy isfurther improved.

The invention provides a fatigue life prediction method of composite material, an apparatus and electronic equipment thereof, which belong to the fields of material performance prediction and structural design. The method is characterized in that a performance database of a preset angle paving layer unidirectional plate is established, wherein the database comprises fatigue load and fatigue life corresponding to the preset angle paving layer unidirectional plate; a fatigue life curve corresponding to the preset angle paving layer unidirectional plate is constructed according to the performancedatabase; the fatigue life curve of a lamination plate is determined according to the fatigue life curve of the preset angle paving layer unidirectional plate, and the fatigue life of the composite material can be predicted according to the fatigue life curve. The fatigue life prediction method can solve the problems that prediction in the prior art is too conservative, so that the material cannot be fully used, a prediction period is long, and the cost is high.

The invention relates to the field of exploration and development of oil and gas fields, in particular to a lower-order fault development rule quantitative prediction method for an uplift area. On the basis of seismic interpretation, a structural map for petroleum reservoir exploitation is acquired; on the basis of related experiments of analysis of a petroleum reservoir structure, geomechanics modeling and the like, seismic data are combined to identify the local uplift scope, then a geomechanics model is further created to simulate a stress field, the analysis of the orientation of a major principle stress is utilized to quantify the potential tendency of two groups of lower-order faults, and a planar or sectional rock peripheral mechanics experiment is utilized to further determine the tendency of the lower-order fault. The method solves the problems of difficulty in accurate recognition of the lower-order fault through the traditional seismic interpretation, and implements accurate and quantitative predication of lower-order fault of a petroleum reservoir.

The invention discloses a wave height prediction method based on a wavelet decomposition-neural network and belongs to the field of marine monitoring technology. According to the method, a time sequence is generated through buoy data, the time sequence is decomposed and reconstructed, and clutter in the sequence is solved; neural network training sample processing is performed on the buoy data; aneural network model is trained, wavelet decomposition and reconstruction are performed on the time sequence, the number of training samples and wavelet decomposition layers is continuously optimizedduring training, and a feedback neural network is utilized to perform training to establish a corresponding wavelet decomposition-neural network model; and test samples established in the neural network are utilized to perform test sample testing on the wavelet decomposition-neural network model. Through the method, extreme wave height in a future period of time can be predicted to provide a powerful guarantee for offshore operation and offshore navigation.

The invention discloses a method for predicting ground settlement caused by soil bin soil entering and discharge through a soil pressure balance shield. The method comprises the following steps: according to tunneling data and ground settlement data of the shield at the initial tunneling stage, through deducing a relation between a shield tunneling parameter (N/v) and ground loss caused by shield soil discharge, inversely computing screw conveyor soil discharge efficiency eta and ground settlement trough width I; establishing a ground settlement prediction formula during the next tunneling of the shield; selecting a next tunneling parameter and substituting into the formula to compute, so that the prediction of a ground settlement value is realized. The method disclosed by the invention is simple and practical and good in adaptability; the relation between the soil bin soil entering and discharge and the ground settlement is established from a shield tunneling mechanism, so that ground settlement caused by the tunneling parameter can be accurately predicted, and excessive upheavals and settlement values are prevented from being generated on the ground.

The invention relates to a massive open online course (MOOC) quitting prediction algorithm based on semi-supervised learning. Firstly, learning log files of users are acquired from an MOOC website, one part of the acquired users forms a test sample set, and the other part forms a training sample set; secondly, according to the learning log files of the users, behavior features of all samples in the training sample set are counted to obtain n behavior features which most express common features of all samples in the training sample set; thirdly, according to the n behavior features, a semi-supervised learning method is adopted to acquire R classifiers; fourthly, the test sample set is used for testing tagging accuracy of the R classifiers, and the classifier with the highest tagging accuracy is selected; and finally, behavior features of any unmarked user are inputted to the above classifier, and the user is marked. The algorithm of the invention only needs few marking samples, a large amount of manpower and material resources cost for tagging the samples can be reduced, the prediction cost is saved, and the prediction accuracy is also improved.

The invention relates to the field of oil and gas field exploration and development, and particularly relates to a fault and fracture development density and uniformity and combined style evaluation method. The appropriate grid cell length is selected and a fault and fracture development density and uniformity and combined style evaluation model is designed on the basis of point filling through datamation of faults/fractures so that fault and fracture development density and uniformity and combined style quantitative calculation can be realized. The method has high practical value in multiple aspects of statistical calculation of fault/fracture parameters and processing of field geological sketches, and has low prediction cost and high operability so that labor cost can be greatly reduced.

The invention relates to the field of exploration and development of an oil and gas field, and particularly relates to a method for predicting densities of different scales of fracture planes. According to the method disclosed by the invention, after a fracture zone is subjected to datamation processing, representation on the densities of different scales of fracture planes is implemented by analyzing similarities of faults and fractures, selecting a suitable fractal and a suitable side length of a density calculation unit and deducing to design a corresponding algorithm. The method disclosed by the invention has high practical value on the aspects of prediction on the densities of different scales of fracture planes and the like, and is low in prediction cost and high in operability, and an evaluation result of the method has a certain guidance significance on multiple aspects of prediction on an oil and gas exploration key area and a fracture dominant distribution area, representation on a fracture pore penetration parameter in the later period and the like.

The invention provides a method for predicting the residual fatigue life of a composite material containing initial delamination damage. According to the method, a modal frequency-residual fatigue life database is used for training an artificial intelligence algorithm, modal frequency is used as input, fatigue life is used as output, and a fatigue life prediction model of one-to-one mapping of frequency data and fatigue life data is constructed; and then the modal frequency of the to-be-measured sample is measured, and the measured frequency is input into the fatigue life prediction model to obtain the residual fatigue life of the composite material laminated plate. According to the method for predicting the residual fatigue life of the composite material containing the initial delamination damage, only vibration equipment needs to be adopted for collecting the frequency, then the fatigue life is predicted, and the method is easy and convenient to implement; online prediction can be carried out, the composite material is not damaged, the cost is low, and compared with other existing fatigue life prediction methods, operation is easy and convenient, and the prediction precision is good..

The invention discloses a wind power real-time prediction method based on rank set pair analysis, and the method is characterized in firstly enabling wind power raw data to be divided into a plurality of sets for a mode of multi-step rolling prediction, and maintaining subsequent values of sets; secondly carrying out rank conversion of the sets, obtaining a last rank set and all the former sets to form a rank set pair, calculating the connection degree of each set, searching a set closest to the corresponding set according to the maximum rule of the connection degrees, and employing the subsequent value of the set as a prediction value; and finally achieving the multi-step prediction in a mode of rolling. During the determining of the maximum connection degree, the method finally determines that an isometric minimum interval method has the highest accuracy in prediction through experiment comparison. A wind power real-time prediction model based on rank set pair analysis enables set pair analysis with clear concepts and simple calculation to be used in wind power prediction, so the method is suitable for the field of wind power short-term prediction which carries out prediction of future data through historical data, and is high in prediction precision.

An embodiment of the present invention provides a short-term classification prediction method of photovoltaic power based on MIV-BP neural network. The method includes using MIV algorithm to screen the weather factors that have a greater impact on the photovoltaic power under different conditions as the input of the prediction model, and according to the rainfall data in the weather information and data sampling time to establish a classification prediction model for forecasting. At present, most of that method are based on the solar radiation intensity, temperature and humidity as necessary inputs to the prediction model, By decomposing the original data series into rainfall time series and non-rainfall time series according to the rainfall amount in the weather factors, and the average influence value algorithm is used to select the weather factors which have great influence on the photovoltaic power under different conditions as the input of the prediction model. The non-rainfall time series are further decomposed according to the sampling time of the data, and the sub-models are established to forecast each series respectively, which reduces the prediction cost of the photovoltaic power, improves the prediction accuracy of the prediction model in sudden change weather, and improves the adaptability of the model.

The invention discloses construction and application of a winter wheat yield prediction model in Northeast Henan province, and aims to solve the technical problem that an existing method cannot accurately and precisely predict the winter wheat yield. The invention provides a construction method of a winter wheat yield prediction model in a certain region and a winter wheat yield prediction methodin the region. According to the method, the yield of winter wheat in northeast of Henan Province can be accurately and precisely predicted, a new thought is provided for intelligent decision diagnosisof winter wheat production in Henan Province, guidance and suggestions are provided for agricultural production decisions, the agricultural production efficiency can be improved, and unnecessary losses are avoided.

The embodiment of the invention provides an active power prediction method and device for a power transmission and transformation device based on an SVM algorithm. The method comprises the steps that a first eigenvector is acquired, wherein elements in the first eigenvector comprises a first preset number of first historical active power data which are data which meet a preset condition in historical active power data corresponding to a target power transmission and transformation device; and the first eigenvector is input to a pre-built target support vector machine SVM model to acquire the active power prediction value of the target power transmission and transformation device at the next time, wherein a preset time interval is between the next time and a first target time, and the first target time is the time closest to the current time in times corresponding to the first preset number of first historical active power data. According to the embodiment of the invention, the active power of the power transmission and transformation device is predicted, and the prediction cost is reduced.