56 results about "Production forecasting" patented technology

The invention includes a method of scheduling cyclic steaming of a group of petroleum-containing wells including: inputting to a production-predicting means a group of data describing at least in part the past cyclic steaming and resulting production of a group of petroleum-containing wells; processing the data in the production-predicting means and outputting a group of production predictions for the group of wells during a future steaming cycle; inputting the group of production predictions into an optimization means; inputting an initial steaming Optimal Cycle Length schedule for the group of wells into the optimization means; processing the group of production predictions and the initial steaming cycle schedule in the optimization means by the steps including: determining a ranking for the initial steaming cycle schedule for the group of production predictions against a pre-determined ranking criteria; producing a group of new steaming cycle schedules based on the ranking of the initial steaming cycle a schedule optimization algorithm; determining a ranking for the new steaming cycle schedules against the pre-determined ranking criteria; repeating the production of new steaming cycle schedules and determining ranking steps until some pre-determined termination criteria is met; and outputting a final steaming cycle schedule.

The invention discloses a big data agricultural management system. The system includes an Internet of things sensor platform, a big Data Analysis Platform, a meteorological warning and forecasting platform, a Platform for Disease and Pest Control and Disaster Early Warning, a real-time mobile monitoring platform, a Platform for Agricultural Management and Production Forecasting. The large-data agricultural management system realizes the collection of agricultural data in the agricultural greenhouse, data on human nutritional status, Genomic analysis of biological populations, analyzing of therelationship between the parameters of crop growing environment, forecast of weather conditions, the monitoring of agricultural products and food production environment, industrial chain management, pre-production, post-production, warehousing and processing, logistics data, the analysis of agricultural products sales price, sales volume, sales demand, consumer purchase behavior data, the releaseand management of meteorological data and other information, the development of disease and insect pests, the prediction of the scope of influence and the regulation of various equipment.

The present disclosure describes the use of growth models and data driven models that are combined for quickly and efficiently modeling SAGD reservoir oil production. Growth function surrogate models are used for efficient and reliable reservoir modeling and production forecasting as opposed to CPU intensive simulations based on finite difference models. A data-driven technique can then compare the growth function surrogate model with real field data to find discrepancies and inconsistencies between the two, allowing for an updates and improvements of the growth function model.

The embodiment of the invention discloses a big data production planning method. The method is used for solving the technical problems that an existing plan demand analysis system cannot calculate the product production demand in advance and cannot conduct production in advance before a customer places an order. The method comprises the steps of obtaining historical product sales data from a database; working out the product sales forecasting amount according to the historical sales data; obtaining the non-delivery amount, the preparation amount and the to-be-delivered amount of ordered products; obtaining the current inventory and the purchase number of the products; obtaining the product demand amount according to the sales forecasting amount and the non-delivery amount of the ordered products; obtaining the available inventory quantity of the products according to the current inventory, the purchase number, the preparation amount and the to-be-delivered amount; finally, obtaining the production forecasting amount by adding the minimum safety inventory quantity to the difference between the demand amount and the available inventory quantity. The embodiment of the invention further provides a big data production planning system.

The invention relates to a coal gas flow measuring method by utilizing BP NN (technology). A three-layer BP NN is selected as a prototype; a three-layer BP NN model is built to predict the coal gas flow; the method mainly includes the following three steps: 1) collecting sample data: selecting settlement data (including temperature, pressure, pressure difference and flow) with accurate history as a sample; 2) training a BP network: inputting the sample data in the step 1) into the three-layer BP network, training the network, comparing a coal gas flow value inputted by the network with a corresponding sample value until the mean square error for training the network reaches the requirements and confirming the important parameters of weight and the threshold of the network; 3) measuring the coal gas flow: inputting the collected coal gas temperature, pressure and pressure difference into the BP network trained in the step 2) during production prediction, thus being capable of predicting the coal gas flow value. The coal gas flow measuring method applies the BP NN technology into measuring the goal gas flow, thus solving the nondeterminacy problem of flow complementing.

The invention provides a compact reservoir production prediction method and device. The method comprises the steps that a three-dimensional network model of a core sample of a to-be-analyzed region isestablished; fluid flow simulation is carried out on the three-dimensional network model to obtain a permeability relative permeability curve, a permeability capillary pressure curve, a displacementrelative permeability curve and a displacement capillary pressure curve of the three-dimensional network model; according to the permeability relative permeability curve, the permeability capillary pressure curve, the displacement relative permeability curve and the displacement capillary pressure curve, a mine field scale dual-medium model of the to-be-analyzed region is established; a matrix layer and a crack layer of the mine field scale dual-medium model are subjected to crack network encryption and region division respectively, and a mine field scale volume transformation model is obtained; production simulation is conducted according to the mine field scale volume transformation model, and production prediction is performed on the to-be-analyzed region. By utilizing the method, the accuracy of a compact reservoir volume transformation model can be improved, and the accuracy of production and prediction of a compact reservoir is further improved.

Techniques for modelling a production forecast for a well are described. In one embodiment, a method includes calibrating a geological reservoir model by analyzing pressure transient well tests, fitting the geological reservoir model to pressure data to estimate model parameters, and building a simulated history of bottom hole pressure based on the model and measured transient flow data. The calibrating may further include fitting the model to flow rate data, using measured and simulated pressure data as input, to estimate model parameters, and then building a simulated history of downhole flow rate based on the model and change in measured pressure data. The calibrated model can be used to forecast future well production. Additional methods, systems, and devices are also disclosed.

The invention includes a method of scheduling cyclic steaming of a group of petroleum-containing wells including: inputting to a production-predicting means a group of data describing at least in part the past cyclic steaming and resulting production of a group of petroleum-containing wells; processing the data in the production-predicting means and outputting a group of production predictions for the group of wells during a future steaming cycle; inputting the group of production predictions into an optimization means; inputting an initial steaming cycle schedule for the group of wells into the optimization means; processing the group of production predictions and the initial steaming cycle schedule in the optimization means by the steps including: determining a ranking for the initial steaming cycle schedule for the group of production predictions against a pre-determined ranking criteria; producing a group of new steaming cycle schedules based on the ranking of the initial steaming cycle a schedule optimization algorithm; determining a ranking for the new steaming cycle schedules against the pre-determined ranking criteria; repeating the production of new steaming cycle schedules and determining ranking steps until some pre-determined termination criteria is met; and outputting a final steaming cycle schedule.

The system and method described herein relate to production of power from the wind farm that incorporate tunable power production forecasts for optimal wind farm performance, where the wind farm power production is controlled at least in part by the power production forecasts. The system and method use a tunable power forecasting model to generate tunable coefficients based on asymmetric loss function applied on actual power production data, along with tuning factor(s) that tune forecast towards under forecasting or over forecasting. The power production forecasts are generated using the tunable coefficients 34 and power characteristic features that are derived from actual power production data. The power production forecasts are monitored for any degradation, and a control action to regenerate the coefficients or retune the model is undertaken if degradation is observed.

A system and method for hydrocarbon production forecasting which includes creating an integrated production model representative of at least two interconnected subsurface tanks, at least one well, and a surface network, wherein the surface network comprises multiple components including at least one pipeline; parameterizing a subsurface part of the integrated production model by using material balance to characterize the at least two interconnected subsurface tanks; parameterizing a well part of the integrated production model based in part on well geometry; parameterizing the surface network based on the multiple components of the surface network; combining the parameterized subsurface part, the parameterized well part and the parameterized surface network into an improved integrated production model; forecasting hydrocarbon production based on the improved integrated production model and displaying the input, output and intermediary products.

Error information and alarm information transmitted from a construction machine (2) is fetched by a server (8). A replacement possibility determining section (815) in the server (8) determines a utilization area of the construction machine (2) from positional information stored in a positional information database (825), and reads out a load to the parts in the utilization area (lifetime of parts in the utilization area) from a utilization environment load database (827). When the parts having transmitted the error information or alarm information has reached the lifetime limit in the utilization area and accumulated utilization time of the construction machine is not less than a prespecified utilization time, or when times of transmission of the error information is not less than prespecified times or duration of transmission of the alarm information is not less than a prespecified period of time, the replacement possibility determining section (815) determines that the parts having transmitted the error information or alarm information is an object for replacement.

The invention discloses a data analysis and decision making system of a water enterprise. The data analysis and decision making system comprises a data acquisition module, an industry real-time database, a data analysis module, an IE client site and a state inspection module, wherein the data acquisition module is used for collecting data, the industry real-time database is used for compressing and storing the data collected by the data acquisition module, the data analysis module is used for retrieving the data from the industry real-time database and integrating and analyzing the data, the IE client site is connected with the data analysis module and used for issuing analysis results, and the state inspection module is used for inspecting a system. Data acquisition software, storage software and analysis software are organically combined, the data are integrated and efficiently stored through various data communication ports, design tools and third-party language programs, an analytical structure is shown in different modes by adopting a plurality of analysis methods, and production forecasts and fault handling suggestions are provided through data mining.

The invention discloses a microseismic data assisted tight oil and gas reservoir fracture distribution inversion method. According to the method, Hough transform is adopted to transform microseismic data into Hough space, so that a Hough space function can be obtained, and an initial mean value of a Hough space random field can be formed; the sampling of crack distribution in a physical space is generated by adopting Hough inverse transformation; production prediction data corresponding to sampling of crack distribution in a physical space is predicted through numerical simulation; a correlation matrix of the Hough space random field and the production prediction data is obtained by adopting an algebraic statistical method; the posterior probability of the Hough space random field is maximized by using the correlation matrix and adopting a sample set-based iterative algorithm to form a crack distribution inversion method. According to the method, the precision of tight oil and gas reservoir fracture distribution inversion and development well production prediction can be improved.

The invention discloses a production prediction method based on nonlinear regression model parameters. The production prediction method comprises the following steps: S1. obtaining an initial interval of the parameters; S2. carrying out equipartition processing on the initial interval to obtain all small intervals; S3. randomly taking points in each small interval; S4. finding the most suitable point combination according to given standards; S5. according to the found point combination, finding a new initial interval of the parameters; and S6. repeating steps S1 to S5, until the accuracy reaches a predetermined value. The method disclosed by the invention is high in calculation speed, and not high in sensitivity to initial values.

The invention provides a shale oil fractured horizontal well production dynamic mode and productivity comprehensive evaluation method. The method comprises the steps of obtaining productivity level data of a fractured horizontal well in a to-be-studied area and numerical values of potential productivity influence factors; respectively evaluating main control factors of the initial production leveland the cumulative production level of the fractured horizontal well in the research area; calculating the respective weight proportions of the main control factors; establishing an initial production level comprehensive evaluation coefficient and an accumulated production level comprehensive evaluation coefficient of the fractured horizontal well in the research area; establishing a comprehensive evaluation standard of the production dynamic mode of the fractured horizontal well in the research area; establishing an initial production level prediction formula of the fractured horizontal wellin the research area; obtaining a decline index and an initial decline rate under each production dynamic mode; evaluating and researching the production dynamic mode and the initial production levelof the well, establishing a productivity decline formula, and predicting the productivity change rule. The relative error between the predicted productivity and the production data of one shale oil fractured horizontal well is smaller than 5.9%, the requirement for the precision of an oil field is met, and the production prediction requirement can be met.

The invention provides a system and a method for enhancing production capacity. The system comprises an analysis model module and a production forecasting module, wherein the analysis model module is used for collecting historical failure data and inline data of a machine component, so as to establish a forecasting model for failures and the inline data of the machine component; and the production forecasting module is used for forecasting capacity level of a machine by means of the forecasting model, and arranging a priority order of the machine. The system can discover the failures of the machine component timely, thereby enhancing the capacity level and reducing the risk of failure. The method for enhancing the production capacity has the same advantages.

The invention discloses a production forecasting method. The production forecasting method includes the steps of filtering out sample data; respectively counting output data of the sample data by year, month and day; calculating annual weighted output B and monthly average weighted output T0, wherein T0 is equal to B / 12; calculating monthly average weighted output T1 and respectively counting average working day output, average daily output over the weekend and average daily output over holidays; calculating correction factor K, wherein K is equal to T0 / T1; Summing up and calculating monthly forecast total output P; comparing the monthly forecast total output P with real production volume to conduct production control. The production forecasting method has the advantages that with the realproduction volume compared with the forecast value by day, month and accumulative value, whether the current day, the current month output and the cumulative output are up to the standard is respectively judged, so that timely corrective measures can be made to correct deviations from expectations in a timely manner and avoid enlargement of deviations; through comparison of correction coefficientK and 1, whether this year's mission target Y0 is high or low can be obtained, so that correction is adopted to increase or reduce the daily forecast output.

The invention relates to a shale gas well production fitting and prediction method, which belongs to the field of shale gas well productivity evaluation, and solves the problems that shale gas well production prediction errors are large, the process is tedious and the like at present. The shale gas well production fitting and prediction method is characterized by comprising the following steps of:dividing a shale gas reservoir into a fracture system and a matrix system; simultaneously establishing a productivity equation and a material balance equation of the fracture system and the matrix system; carrying out production history fitting on flowing bottomhole pressure and water yield for two production modes of fixed yield and fixed pressure of a shale gas well; and respectively predictingthe gas yield and the water yield of the shale gas well under the two production modes of the fixed yield and the fixed pressure after the fitting is successful. The shale gas well production fittingand prediction method is good in fitting effect, high in prediction precision and high in generalizability.

A method of scheduling cyclic steaming of petroleum-containing wells including: inputting to a production-predictor data describing the past cyclic steaming and resulting production of wells; processing the data in the production-predictor and outputting production predictions for the wells during a future steaming cycle; inputting the production predictions into an optimizer; inputting an initial steaming Optimal Cycle Length schedule for the wells into the optimizer; processing the production predictions and the initial steaming cycle schedule in the optimizer by: determining a ranking for the initial steaming cycle schedule for the production predictions against a pre-determined ranking criteria; producing new steaming cycle schedules based on the ranking of the initial steaming cycle a schedule optimization algorithm; determining a ranking for the new steaming schedules against the ranking criteria; repeating the production of schedules and determining ranking steps until some pre-determined termination criteria is met.

The embodiment of the invention discloses a production prediction method and device for realizing automation of a production prediction device and realizing predictability and controllability on plantproduction. The method in the embodiment comprises steps: a property form of a plant is built; through the property of the plant, an inputted planting plan is received, wherein the planting plan comprises a total planting area, total planting varieties and a target yield; according to the planting plan, a planting strategy for each plant variety is made; according to the planting strategy and a preset algorithm, the target production schedule of each plant variety at each growth stage is calculated; the actual production schedule of each plant variety in the current time period is acquired, and the target production schedule and the actual production schedule are compared; and a comparison result is displayed, and according to the comparison result, prompt information is sent.

Well settings in mature oil field may be configured by generating progressively, a plurality of geological reservoir models by fitting a set of initial geological reservoir models that generate forecasts of fluid injection and production at a well as a function of time, with a subset of historical well data to produce a set of intermediary geological reservoir models, and fitting the set of intermediary geological reservoir models to a next subset of the historical well data. A set of diverse geological reservoir models may be determined from the plurality of geological reservoir models. A mid-term schedule of well settings associated with the well may be generated based on the set of diverse geological reservoir models and an economic model that comprises mid-term estimation of oil sale price and of production costs. The mid-term schedule of well settings may be actuated to control the fluid injection and production at the well.

The invention includes a method of scheduling cyclic steaming of a group of petroleum-containing wells including: inputting to a production-predicting means a group of data describing at least in part the past cyclic steaming and resulting production of a group of petroleum-containing wells; processing the data in the production-predicting means and outputting a group of production predictions for the group of wells during a future steaming cycle; inputting the group of production predictions into an optimization means; inputting an initial steaming cycle schedule for the group of wells into the optimization means; processing the group of production predictions and the initial steaming cycle schedule in the optimization means by the steps including: determining a ranking for the initial steaming cycle schedule for the group of production predictions against a pre-determined ranking criteria; producing a group of new steaming cycle schedules based on the ranking of the initial steaming cycle a schedule optimization algorithm; determining a ranking for the new steaming cycle schedules against the pre-determined ranking criteria; repeating the production of new steaming cycle schedules and determining ranking steps until some pre-determined termination criteria is met; and outputting a final steaming cycle schedule.

The invention discloses a residual oil distribution prediction method based on an autoregressive network model, which belongs to the technical field of oil reservoir development and comprises the following steps: analyzing main influence factors of residual oil distribution from a basic seepage differential equation of fluid flow; constructing a sample library by using a numerical simulator; constructing an autoregressive network model of a convolutional neural network and a convolutional long-short-term memory kernel, and capturing a complex nonlinear mapping relation between input data and output data; training the constructed neural network model in a training set; evaluating the performance of the trained proxy model by using the minimum absolute value error L1 and the relative L1 error in the test sample set; and outputting an autoregression network model which is trained completely and has good evaluation performance, collecting oil reservoir data in real time, inputting the model, and predicting remaining oil distribution in real time. The remaining oil distribution prediction time can be greatly shortened, and then the time of the oil reservoir automatic history fitting process needing multiple oil reservoir production prediction is shortened.

A method for predicting production of shale gas well comprises: constructing a production regularization pseudo-pressure function of a well to be analyzed; according to the production regularization pseudo-pressure function, a double logarithmic plate drawing function is determined based on the cumulative output, and a production regularization pseudo-pressure double logarithmic plate is drawn based on the double logarithmic plate drawing function; according to the measured data obtained from the production regularization pseudo-pressure double logarithm chart or the production regularizationpseudo-pressure double logarithm chart to fit the production regularization pseudo-pressure double logarithm chart or the production regularization pseudo-pressure double logarithm chart, the parameters of shale gas wells to be analyzed are determined according to the fitting results of double logarithm chart and the historical fitting results of production and pressure; based on the preset shalegas well production prediction model, according to the relevant parameters of the shale gas well to be analyzed, the predicted output of the shale gas well to be analyzed is determined. The method improves the reliability of input parameters and ensures the accuracy of production forecasting results.

The invention discloses a temperature-based agricultural production forecasting method, and relates to the technical field of agricultural production forecasting. For the irrigated crops, the mathematical statistics is applied to calculate and forecast the agricultural production time node scientifically based on the historical and real-time agrometeorological temperature observation data and theforecasting data of temperature so as to play an important role in improving the effectiveness and the quantitative level of the regional agrometeorological services, enhancing the predictability andthe practicability, enhancing the pre-evaluation level and the service capacity of the field of the regional agrometeorological services and promoting agricultural production income, disaster prevention and relief.

A system and method for hydrocarbon production forecasting which includes creating an integrated production model representative of at least two interconnected subsurface tanks, at least one well, and a surface network, wherein the surface network comprises multiple components including at least one pipeline; parameterizing a subsurface part of the integrated production model by using material balance to characterize the at least two interconnected subsurface tanks; parameterizing a well part of the integrated production model based in part on well geometry; parameterizing the surface network based on the multiple components of the surface network; combining the parameterized subsurface part, the parameterized well part and the parameterized surface network into an improved integrated production model; forecasting hydrocarbon production based on the improved integrated production model and displaying the input, output and intermediary products.

The invention provides a novel method for predicting oil field output. The method includes preliminary sorting and determining the factors affecting outputs, processing the basic data, whitening independent variables, establishing time sequence model of the independent variables, determining the factors that determine the influence output, and establishing an output prediction model by the time sequence model and detecting the rationality of the model. The method is applied to sorting factors influencing output, output prediction and risk evaluation, identifying the decisive factor of the output of an oil field, predicting the output and carrying risk evaluation on output.