110results about How to "Simple forecasting method" patented technology

Systems and methods are provided for knowledge discovery in spatial data as well as to systems and methods for optimizing recipes used in spatial environments such as may be found in precision agriculture. A spatial data analysis and modeling module is provided which allows users to interactively and flexibly analyze and mine spatial data. The spatial data analysis and modeling module applies spatial data mining algorithms through a number of steps. The data loading and generation module obtains or generates spatial data and allows for basic partitioning. The inspection module provides basic statistical analysis. The preprocessing module smoothes and cleans the data and allows for basic manipulation of the data. The partitioning module provides for more advanced data partitioning. The prediction module applies regression and classification algorithms on the spatial data. The integration module enhances prediction methods by combining and integrating models. The recommendation module provides the user with site-specific recommendations as to how to optimize a recipe for a spatial environment such as a fertilizer recipe for an agricultural field.

The invention belongs to the technical field of material science and engineering and relates to a forecasting method of the creep life of a high-temperature material. With the rise of working temperature, the probability of creep failure of high-temperature equipment and high-temperature mechanisms and the ponderance of accidents caused by the creep failure in modern industry are both increased greatly. The forecasting method of the creep life of the high-temperature material comprises the following steps of: acquiring data of material at different temperatures, wherein each test point comprises temperature, stress and fracture time; calculating the test data to obtain a P value that each test stress Sigma corresponds to according to a formula; conducting LH parametric method curvilinear regression to obtain a main curve of an LH regression curve, wherein the mathematical expression of the regression curve is lg Sigma=A0+AIP+A2P2+...; and calculating creep life under different temperatures and stress conditions on the regression curve. The invention has the advantages of improving the forecasting precision of the creep life of the material and the reliability of life assessment and having wide application range and simple forecasting method.

The invention discloses an urban dynamic route travel time predication method. The method comprises the steps of analyzing historical traffic data; extracting traffic modes from the historical traffic data, including the correlation of segment links; acquiring a historical information based recommended route on the basis of input starting point and ending point and the travel time; inputting the real-time traffic event when driving a vehicle; predicating again on the basis of a new staring point; and modifying the recommended route, so as to apply the predication method to a real-time dynamic navigation system. The urban dynamic route travel time predication method has the advantages that the historical urban traffic modes are effectively integrated into account, so as to effectively predicate the urban dynamic route travel time; the method is simple and easily conducted; the operation conditions are easily met; the urban dynamic route travel time can be predicated to guide to select a reasonable travel route for the vehicle; and the method plays a key role in relieving urban traffic jam, and is easily popularized and used in large and medium size cities.

The invention provides a flow-speed matching model and a travel time forecasting method and system. The method includes the steps of firstly, calculating theoretical travel time and traffic flow average speed of a road section; secondly, calculating the error between the theoretical travel time and actually-measured travel time, conducting feeding and adjusting on the traffic flow average speed according to the error, and renewing flow-speed data of the corresponding road section; thirdly, repeating the first step and the second step till the error is smaller than a preset threshold value, and storing the errors as a flow-speed matching model; fourthly, directly conducting matching in the flow-speed matching model through forecasted flow to obtain the average speed, and then calculating the travel time according to the average speed. According to the flow-speed matching model and the travel time forecasting method and system, the travel time is calculated according to the traffic wave principle, feeding and adjusting are conducted on the average speed, the calculation result is corrected unceasingly, and the flow-speed matching model is renewed; the travel time forecasting method is simple, and meanwhile the flow-speed matching model can be enriched and optimized in the travel time forecasting process so that the forecasting model can be higher in accuracy.

The invention discloses a method for predicting a time sequence of number of people served by base stations based on space-time transfer probabilities of mobile phones. The method comprises the following steps: calculating the total number of people within base station service areas of the mobile phones within an equal time period by using space-time orbit data of the mobile phones; dividing people moving orbits by using the space-time orbit data of the mobile phones, and calculating the number of people coming back and forth between the base stations within adjacent time periods in a research area; based on related theory of Bayesian and Markov chains, calculating the transfer probabilities of mobile phone users within target base stations to occur in the base stations at a current moment according to historical data; calculating the transfer probabilities of the mobile phone users within the target base stations to occur in the base stations within different time periods to construct a complete space-time transfer probability matrix in the research area; and predicting the number of people served within the base station ranges of the mobile phones in the research area with the relatively stable total number of people by using the complete space-time transfer probability matrix. The method disclosed by the invention has the advantages of low data acquisition cost, simple model structure and high prediction efficiency.

The invention relates to a power prediction method based on a wind-solar hybrid model. According to the prior art, wind power and photovoltaic power are predicted separately, however, according to the power prediction method based on the wind-solar hybrid model, only one BP neural network prediction model is adopted to achieve prediction of the output power of a wind power plant and the output power of a photovoltaic power station of a whole area at the same time, prediction accuracy is improved while the prediction method is simplified, and therefore the method has higher engineering application value.

The invention discloses a method for predicting a manufacture result of ion beam polishing according to consistency on mathematic model in a modification processing course and a dimension filtering course. The method firstly confirms a removal function of polishing process, then confirms an equivalent low pass filter pulse response function according to the removal function, detects error for a optical mirror by using face form detection device, calculates face form residual according to the detected face form error and the filter pulse respond function, realizes a prediction of ion beam polishing processing result according to the calculated face form residual. On this basis, the method also can predict variance situation of each space frequency component before and after the processing according to the filter pulse respond function. The predictor method of the invention is more easy and maneuverable, and the prediction result is more visual reliable and all-round.

A method for predict that life of momentum wheel includes such step as:1, taking power consumption of momentum wheel as characteristic performance parameter of momentum wheel, establish a performancedegradation model of a momentum wheel by one-dimensional Wiener process; 2, obtaining that drift coefficient and the diffusion coefficient in the performance degradation model of the momentum wheel byadopting a maximum likelihood estimation method; Step S3, setting the performance failure threshold of the momentum wheel, and obtaining the expectation and variance of the life of the momentum wheelaccording to the failure threshold. The invention solves the problem that, due to the restriction of the cost and the progress, the life test of the large sample and the long time can not be carriedout on the ground, and the statistical conclusion that it is difficult to obtain the failure data required for the life prediction can not accurately evaluate the life of the momentum wheel with longlife.

The invention discloses a cellular automaton river bed evolution prediction method based on a natural selection ant colony algorithm. The method includes the steps of obtaining data and establishing a corresponding database, wherein the database includes river bed evolution property data and geographic space data; establishing a river bed evolution prediction model, predicting and analyzing river bed evolution, and finally outputting a prediction result; establishing the ant colony algorithm through the river bed evolution prediction model, optimizing the ant colony algorithm through a natural selection strategy, establishing a cellular automaton algorithm model through the optimized ant colony algorithm, and applying the established model to river bed evolution prediction. The advantage that an improved cellular automaton is fully used for better simulating the space information is fully used, and the prediction method is simple and high in efficiency.

The invention discloses an extremely high water-containing period cumulative oil production and recovery rate prediction method, which comprises the following steps: 1) carrying out an extremely high water-containing period oil-water phase permeability experiment to obtain a new phase permeability curve equation; 2) obtaining the specific numerical values of parameters in an extremely high water-containing period water-drive characteristic curve equation; 3) importing a limit moisture content, and forming an extremely high water-containing period cumulative oil production prediction equation; and 4) importing original geological reserves into the extremely high water-containing period cumulative oil production prediction equation to predict an extremely high water-containing period recovery rate. The invention provides the new extremely high water-containing period cumulative oil production and recovery rate prediction method. The new extremely high water-containing period cumulative oil production and recovery rate prediction method improves the accuracy of a reservoir engineering technology prediction aspect, can avoid errors brought to a reservoir numerical value simulation prediction result since a reservoir stratum can not be clearly seen, is simple and convenient, can predict the cumulative oil production and the recovery rate of the reservoir only by the acquisition of the basic data of reservoir rock samples, and performs an active driving function on reservoir development.

The invention relates to a relay individual working life predicting and screening method based on early life performance. The relay individual working life predicting and screening method based on early life performance is characterized by comprising the following steps that under an environment temperature C1, the performance parameters C ={C2,C3, ...,Cn} and the working life D of a relay sample at the early life are acquired according to the service life test of the relay sample; a relay individual working service decision table is established based on a rough set theory and an equal probability criterion by using the C as condition attributes and using the D as decision attributes; a set of association rules with respect to the early life performance and the service life of relay individuals are extracted by the aid of attribute reduction; afterwards, for the individuals of the same specifications, the service life of the individuals can be predicted by only measuring the performance parameters of the individuals at the early life, and therefore relays can be screened. According to the method, when the working life of the relay individuals are predicted and products are screened, only the early life performance of the relay individuals is needed, no more information is needed, the time and cost for acquiring information are greatly saved, the calculation is small, and the effective service life of the relays can also not excessively shortened.

The invention relates to an underground coal mine stress field principal stress direction predicting method. The method is mainly characterized by including the steps that a regional stress field type is preliminarily predicted according to the regional structure evolution history and the modern structure movement characteristics; crossed tunnels with the basically same supporting type in the same stratum are selected for further judging and observing the regional stress field type; the maximum horizontal principal stress direction of the stress field at an observation site is judged according to the underground stress trace geometrical characteristics; through the combination of the stress field type and the maximum horizontal principal stress direction, the maximum principal stress direction, the intermediate principal stress direction and the minimum principal stress direction of the stress field are judged. By means of the method, the problems that an existing coal mine stress field testing method is high in engineering cost and complicated in process are solved; by means of the relations of tunnel deformation, stress trace characteristics, stress field type and principal stress direction, the economical, practical and effective underground coal mine stress field principal stress direction predicting method is put forward.

A method for carrying out in-frame prediction of intensified layer includes confirming low layer macro block corresponded by current macro block and carrying out in-frame prediction for current macro block according to peripheral reconstructed pixel value of low layer macro block for raising in-frame prediction accuracy of intensified layer.

The invention discloses a method for predicting a water flooding sweep efficiency of a low-viscosity crude oil reservoir. The method comprises the following steps: selecting a water flooding developedlow-viscosity crude oil reservoir as a target oil field, and making a linear relation curve between the target oil field and the water flooding developed low-viscosity crude oil reservoir within therange of 0.02-1.00 according to oil-water relative permeability of the target oil field, so as to obtain a starting point and an end point of the linear relation curve; delineating the water floodingcontrol geological reserves of a target oil field or a single well of the target oil field by integrating the production dynamics, and then determining the water flooding movable oil reserves; fittingactual production dynamic data of the target oil field by utilizing the water flooding sweep efficiency calculation model shown in the formula (1) to obtain values of constants A and B in the formula(1); and obtaining the water flooding sweep efficiency of the target oil field at different water-oil ratios by utilizing the water flooding sweep efficiency calculation model shown in the formula (1). According to the method, the problems that uncertainty is brought to reservoir numerical simulation prediction due to unclear reservoir understanding, and a numerical simulation method is complex in process, high in cost, long in period and the like are solved.

The invention relates to a ground source heat pump system performance prediction method. The method comprises the steps of (1) preprocessing and carrying out seasonal decomposition on the heat transfer performance data of a GSHP system; (2) constructing a data structure with GSHP system working parameter input in a seasonal month-by-month manner; (3) constructing a decision tree set model which has external system working parameter input and can be used for time sequence regression prediction, namely a prediction model; (4) carrying out data reconstruction on test set data by adopting the samemethod as the step (2), and carrying out performance prediction by adopting an autoregressive mode and the decision tree set model obtained by training in the step (3); and (5) comparing the prediction data obtained by the test set through the decision tree set model with the real data, and measuring the prediction effect of the decision tree set model. The prediction method is simple and is easyto operate. The method also solves the problem that the traditional time sequence analysis method cannot predict the time sequence with out-of-band partial parameters.

The invention discloses a method for predicting the take-off and landing amount of a large busy airport terminal area containing a planned airport. The method comprises the following steps: firstly, proposing a concept of annual average aviation travel times and passenger population in a region, and obtaining a formula of takeoff and landing sorties through a conversion relation between takeoff and landing amounts and throughput capacities; determining a traffic circle of a large busy airport terminal area, allocating passenger plane population in the traffic circle, and correcting the passenger plane population; predicting the annual average aviation travel frequency and the passenger plane population of the region, and obtaining predicted values of annual and daily average take-off and landing sorties through a formula. Besides, a concept of airspace quadrant division is provided, an existing airport time table is used as a reference time table, and the flight quantity and distribution of each hour of a predicted day are obtained through the flight quantity and quadrant distribution of the airspace quadrant division and the flight quantity expansion speed of the terminal area. The method fills up the blank of the flow prediction method containing the planned airport terminal area, is accurate in flow prediction, and can provide data support for airspace planning of the largebusy airport terminal area.

The invention discloses a vehicle OD prediction method which comprises the steps: obtaining a vehicle trajectory data sample, obtaining vehicle parking point data according to the trajectory data sample, and inputting the vehicle parking point data into a DBSCAN model for clustering, generating a clustered class cluster, constructing OD priori data according to the class cluster, constructing an OD prediction model through the OD priori data and a Bayesian formula, and predicting the vehicle OD through the OD prediction model. With application of the method, the vehicle OD can be predicted according to the vehicle trajectory data, prediction of trucks with large trajectory data volume and long time span is particularly more accurate and the implementation mode is simpler.

The invention relates to the technical field of agriculture, and provides a crop yield prediction method and system, a storage medium and electronic equipment. The method comprises the following steps: acquiring a specific value of each parameter related to the growth of a preset crop; and inputting the specific values of all the parameters into a progressive water-salt embedded neural network model to obtain a predicted value of the yield of the preset crop, wherein the progressive water-salt embedded neural network model comprises two layers of progressive causal relationships. According to the invention, the predicted value of the yield of the preset crop is obtained; the influence of different irrigation amounts and other climate and growth factors under a field straw deep burying condition on water-salt migration of soil and production benefits of the crop can be simulated; and tests show that the progressive water-salt embedded neural network model has relatively high precision, can effectively represent the comprehensive conditions of preset crop growth, namely the double-layer progressive causal relationship among each associated parameter, water and salt content migration in the soil and the yield of the preset crop, captures the internal dependency relationship of each parameter, and can be used for simulating the water and salt migration rule of an irrigated area.

The invention relates to a regional photovoltaic monthly power generating capacity prediction method based on normalization fitting. The method comprises the following steps: firstly summarizing the power generating data and installed capacity data of all photovoltaic power stations in a region, and calculating the monthly utilization hours; solving a fitting polynomial by utilizing a least squaremethod and taking months as independent variables; and finally, calculating the power generating capacity of the predicted month in combination with the newly added installed capacity of regional photovoltaic planning. The method only needs to use the power generating capacity and the abandoned power amount data of the region, does not need the data of each photovoltaic single station, is small in dependence on the data amount, and is also suitable for regions where new photovoltaic power stations are continuously built and the installed capacity is rapidly increased. The method is simple andpractical, and has very strong operability and promotion and application values.

The invention discloses a maximum output prediction method and system capable of quickly responding to a coal-fired unit. According to the method, a real-time coal load curve is obtained through a reference coal load curve, the maximum output capable of being responded quickly of the coal-fired unit is predicted according to the real-time coal load curve, and the reference coal load curve and thereal-time coal load curve are dynamically updated; the method for obtaining the real-time coal load curve through the reference coal load curve comprises the step of adding a real-time correction itemto the reference coal load curve to obtain the real-time coal load curve. The method can accurately predict the maximum output of the coal-fired unit capable of rapidly responding under the current operation condition, is simple in prediction method, facilitates the real-time determination of the maximum adjustment capability of the coal-fired unit on an electric power system, and improves the coordination of a power supply and a power grid.

The invention, which belongs to the technical field of mechanical equipment, relates to a method and device for predicting the fatigue failure of a drive shaft of a horizontal conveying device. According to the method, stress data of a drive shaft are collected periodically by a sensor based on the actual working condition of the drive shaft; whether the stress data collected in each period exceeda preset range is determined; if so, damge values are accumulated; and then when the accumulated damage value is determined to reach a threshold value, warning sent out. Therefore, on the basis of sensor information acquisition, big data modeling and data calculation, a fatigue failure prediction model of a drive shaft is established; and thus the service life is predicted based on the actual operating condition, so that the accuracy and convenience of the prediction are improved substantially. Moreover, the method and device for predicting the fatigue failure of a drive shaft of a horizontalconveying device have advantages of simple implementation, low cost, and wide application range.