336 results about "Dynamic prediction" patented technology

A reduced virtual keyboard system for text input on electronic devices is disclosed. Text input is performed by creating a tracing trajectory. Dynamic prediction solutions are created during the tracing process, thus avoiding the need for a user to complete the entire word trajectory. The system also allows a mixture of tapping actions and sliding motions for the same word. The system may comprise a Long Words Dictionary database having first letters corresponding to predetermined keys of the keyboard. Alternatively, the system uses a Dictionary and a database management tool to find long words.

The invention discloses a method for predicting an hourly cooling load of a central air-conditioner in an office building on line based on indoor temperature and humidity parameters. The method for predicting the cooling load comprises the following steps of: performing time sequence prediction on outdoor meteorological parameters and air-conditioner operation input parameters, establishing an Online support vector regression (SVR) dynamic prediction model of the air-conditioner cooling load by using the data, predicting 24-hour air-conditioner cooling load in the current day in advance, and performing compensation by using a residual sequence of the actual value and the predication value of the 24-hour air-conditioner load in the previous day. The predication data of the air-conditioner cooling load prediction model established by the method is high in reliability; and the method can be applied to occasions for prediction of the hourly cooling load of the central air-conditioner in the office building in a single building or a large range, energy-saving control of a central air-conditioner system, energy consumption prediction of the air-conditioner, power peak clipping in areas and the like.

The invention discloses a system and method for predicating time-varying user dynamic equilibrium network-evolved passenger flow and belongs to the technical field of urban rail traffic safety. The system comprises an AFC (auto fare collection) system, and a video terminal and the like. A network database is sequentially connected with a passenger flow distribution module, a passenger flow correction module and a passenger flow analysis module. The passenger flow video analysis module is connected with the network database module and the passenger flow correction module respectively. The video terminal and the AFC system transmit passenger information data and store the same in a network database. The passenger flow video analysis module analyzes real-time video data, and the passenger flow correction module adopts an AUKF (adaptive unscented Kalman filter) for preprocessing. The passenger flow data are matched and predicated by means of a passenger flow prediction algorithm, and services like an inquiry are provided by a human-computer interaction terminal. The requirements of multiple users for road network short-term prediction under emergency conditions are met, real-time distribution and dynamic prediction for the bounded rationality of the passenger flow are realized, and real-time inquiring, sharing and decision making of enterprises for passenger flow information are met.

The invention provides a four-dimensional flight track dynamic prediction method based on ADS-B information updating. By communicating with networks among ADS-B receivers, a ADS-B data decoding module is adopted to obtain real-time velocity information, height information, longitude information and latitude information of a flight, and consistency check is conducted on a predicted flight track and the real-time velocity, height, longitude and latitude of the flight, so that the dynamic, online and real-time flight track prediction capability is achieved. The method can provide important technical support for developing the automation and intellectualization of air traffic control and achieving the flight-track-based operation.

Provided are methodologies to properly assess and manage operational risks at operations sites, e.g., a manufacturing, production or processing facility, such as a refinery, chemical plant, fluid-catalytic-cracking units, or nuclear energy plant, or a biological or waste management facility, airport or even financial institutions, or at any facility in which operations are often accompanied by risk associated with many high-probability, low-consequence events, often resulting in near-misses. In some operations, processes are monitored by alarms, but the invention operates on either process data or alarm data. The methods are based upon measurement of one or more variables, and / or utilization and management of the concept of “hidden process near-miss(es)” to identify a change or escalation, if any, in probability of occurrence of an adverse incident. The methodologies combine a plurality of subsets (also useful independently) of dynamically calculated leading risk indicators for dynamic risk management.

The invention discloses a four-wheel-drive electric car speed optimization control method. The method considers road grade and curvature information in a travelling path range overall, can minimize energy consumption of the car in a travelling process in a given path on the premise of ensuring the safety of the car. The method includes the following steps: acquiring road grade and curvature information through information systems such as a GPS ( Global Positioning System) and a GIS ( Geographic Information System); considering the road grade information and the car state, establishing a longitudinal dynamics prediction model, and establishing an energy consumption target function; considering the road curvature information, designing a constraint condition of the safety, and describing a model prediction control problem; and using the dynamic programming algorithm to solve the model prediction control problem, and acquiring a car speed optimization track. The four-wheel-drive electric car speed optimization control method can acquire the optimized target electric car speed and torque according to road working condition information, can be used for dynamics control of four-wheel-drive electric cars, and can improve the travelling economic and safe performance.

The present invention provides a fluorescence-based modeling method that is capable of capturing the dynamic changes of different membrane foulant fractions that occur in fluid filtration operations. Principal component analysis is utilized to de-convolute spectral information captured within fluorescence EEMs into principal component scores that are related to different known foulant groups. The principal component scores are then used as states within a system of differential equations representing approximate mass balances of the main foulant groups to obtain a dynamic forecasting of membrane fouling. Based on the fouling dynamics forecasted by this modeling method, an optimization strategy can be developed for estimating the optimal membrane back-washing scenario for minimizing energy consumption while maximizing clean fluid production.

The invention relates to an identification and deviation-detection method for a lane, which comprises the following steps: (1) acquiring a lane image and carrying out pretreatment on the lane image; (2) carrying out Canny operator edge detection on the lane image which is subjected to the pretreatment to obtain lane edge images; (3) determining the position of a lane mark according to the obtained lane edge images and a Kalman predictor-based lane tracking method, selecting Kalman prediction areas, filtering out a set of effective points by using a distance discrimination method, and extracting lane parameters on the basis of optimizing the set of effective points; (4) extracting the lane mark by using the Hough conversion with linear fitting according to the obtained lane parameters; and (5) counting the number of background points and lane mark points in the Kalman prediction areas by using the starting point position and the dynamic prediction of a lane which are determined in the step (3), and solving the ratio of the background points to the lane mark points. With the adoption of the identification and deviation-detection method for the lane provided by the invention, the monitoring for lane condition can be rapidly and stably realized.

The invention relates to a steering early warning auxiliary device for a heavy truck, which includes an in-vehicle early warning component and an external early warning component. The device and the obstacle dynamic prediction module installed on the inner bracket of the instrument panel; the early warning components outside the vehicle include radar detection components and high-definition camera components, and the radar detection components and high-definition camera components are arranged in pairs on the vehicle body corresponding to the blind spot of the truck on the corresponding position. Due to the existence of the obstacle dynamic prediction module and the alarm indicating device, the device can firstly predict the trajectory of the truck and possible dangers, thereby reminding the driver. During the operation of the driver, the device can make accurate and fast judgments again. , In an emergency, the vehicle can be stopped quickly to avoid dangerous situations. The device can be used as a steering warning auxiliary device for heavy trucks, and its use is safe and reliable.

The invention discloses a method for measuring a gas and water relative permeability curve through coal-bed gas well production data. Average reservoir pressure and average water saturation are obtained with a material balance method, and therefore changes between absolute permeability and relative permeability can be obtained; changes of irreducible water saturation are predicted through the relation between irreducible water saturation and porosity; the absolute permeability and the relative permeability generated after end points are calibrated are coupled in the same state, a domain average effective permeability dynamic prediction model can be obtained, and an effective permeability curve can be obtained. The method solves the problem that in a laboratory, the relative permeability curve can not be accurately measured easily. Compared with the prior art, the positive and negative effect of a coal reservoir can be well reflected, the gas phase effective permeability can be effectively improved, and a powerful basis is provided for accurately predicting a gas and water output law of a coal-bed gas well and predicting future yield of a producing well.

The invention is applicable for the field of robots and intelligent control, and provides a robot imitation learning method and device, a robot and a storage medium. The method comprises the steps ofacquiring the pose of an end-effector at the current time when receiving movement instructions, and checking whether the pose at the current time is the target pose; determining that a preset imitation learning task is finished by the end-effector if the pose at the current time is the target pose; or else generating the predicted pose of the end-effector at the next time according to the pose atthe current time and a dynamic prediction model, and adjusting angles of joints according to the predicted pose; and setting the pose after adjustment of the end-effector to the pose at the current time, and skipping to the step of checking whether the pose at the current time is the target pose. The dynamic prediction model is obtained through a limit learning machine model in combination with preset stability constraint condition training, so that the stability, repetition precision and model training speed of robot imitation learning are ensured, and the humanization degree of robot motionis improved effectively.

The invention provides a cloud calculation resource disposition method based on dynamic prediction. Firstly a network jam problem brought by multiple mirror images sharing is changed through increasing quantity of mirror image templates, secondly quantity of mirror image versions in real time is adjusted through dynamic prediction of mirror image demand quantity of a could calculation at different times, further resource waste caused by time delay or excessive mirror images brought by insufficient mirror images is reduced.

The invention discloses a health prediction method and system for a new energy vehicle battery. The method comprises the following steps that: carrying out data analysis processing on vehicle data obtained in real time to obtain vehicle working condition data; independently executing data cleaning, data conversion and data reduction processing on the vehicle working condition data; on the basis of the vehicle working condition data subjected to data preprocessing, adopting a factor analysis method to extract data which influences a battery health degree, adopting a supervised learning method to mine a potential relationship between the data which influences the battery health degree and the vehicle working condition data, and constructing an initial battery health prediction model; carrying out model evaluation and algorithm optimization on the initial battery health prediction model to obtain an optimal battery monitoring prediction model, and finishing battery health prediction under a practical working condition. By use of the method, the dynamic prediction of the health state of the new energy vehicle battery is realized, the dynamic property and the economy of the vehicle can be improved, and the method has the advantages of being simple in operation and easy in implementation.

The invention relates to a method for water inrush prediction and seepage control for underwater-tunnel broken surrounding rocks. The method includes the steps of S1), exploring by adopting a geophysical exploration and advanced-level geological drilling method and performing tests; S2), establishing a saltation prediction model of analytic hierarchy grey correlation of water inrush of the surrounding rocks by adopting an analytic hierarchy grey correlation method; S3), establishing a three-dimensional porous continuous medium fluid-structure coupled finite element model of the underwater-tunnel broken surrounding rocks by adopting an orthogonal back-analysis method; S4), performing dynamic prediction and seepage control on water inflow of the broken surrounding rocks and performing intelligent fuzzy logic control and instability early-warning forecast on high-pressure water inrush of the broken surrounding rocks; S5), adopting comprehensive prevention and control measures. Compared with the prior art, the method has the advantages that instability of water inrush of the underwater-tunnel broken surrounding rocks under high water pressure can be predicted and subjected to economical, reasonable, safe and reliable comprehensive seepage control.

The invention belongs to the field of agricultural remote sensing and relates to a remote sensing, crop model and meteorological forecast fused crop maturity stage prediction method. The method comprises the steps that S1 a crop planting area is partitioned; S2 the WOFOST model parameter of crop growth of each area is marked; S3 a filtering method is used to eliminate cloud pollution in a time series remote sensing image; S4 parameters sensitive to the maturity stage are selected, and a cost function based on normalized MODIS LAI and WOFOST simulation LAI is built to acquire an optimization parameter data set; S5 a WOFOST crop growth model is driven by the acquired optimization parameter data set, and the crop maturity stage is predicted 10 days ahead of schedule; and S6 an area crop maturity stage prediction spatial distribution pattern is generated to guide timely harvesting of the crop. The method provided by the invention fuses the advantages of remote sensing data and the crop model. The maturity stage can be predicted at the area scale, and the prediction accuracy of the crop model is improved. The application of meteorological forecast data improves the accuracy of dynamic prediction, so that the practicality is higher.

The invention discloses a method for dynamically predicting potential productivity of paddy rice based on a geographical information system. The method comprises the following steps of: establishing a model library by using a program language; entering data required by model simulation into a database; progressively calculating photosynthetic potential productivity, light and temperature potential productivity, climatic potential productivity and land potential productivity layer by layer by sequentially selecting models in the model library and connecting the models with the database; counting according to a simulation calculation result; and selecting the most stable model combination for predicting the potential productivity of the paddy rice at the area in the future. By coupling a paddy rice potential productivity calculation model with GIS, the model parameters are systematically processed, the model calculation is more efficient and the potential analysis is more accurate; and thus a more reliable technical method is provided for making decision on the productivity of the paddy rice and increasing both production and income with great significance for guarantee of grain security.

The invention relates to a robust random-weight neural network-based molten-iron quality multi-dimensional soft measurement method which belongs to the blast-furnace smelting automatic control field, in particular to a Cauchy distribution weighted M-estimation random-weight neural network (M-RVFLNs) based method for multi-dimensional parameter-dynamic soft measurement of the molten-iron quality in the blast-furnace smelting process. According to the method of the invention, the principal component analysis (PCA) method is adopted to chose main parameters which affect the blast-furnace molten iron quality as model input variables, a molten-iron quality multi-dimensional dynamic prediction model which has an output self-feedback structure and takes into account input-output data at different moments is constructed, and it is possible to carry out multi-dimensional dynamic soft measurement of the main parameters Si content, P content, S content and molten iron temperature which represent the blast-furnace molten iron quality. The method of the invention comprises the following steps of (1) choosing auxiliary variables and determining model input variables and (2) training and using the M-RVFLNs soft measurement model.

The present invention relates to a rockburst dynamic prediction method based on BP neural network modeling. The method comprises the steps of: determining and acquiring rockburst influence factors; performing quantification processing on qualitative description parts in influence factor indexes, and obtaining an initial population; performing BP neural network training on the eight acquired influence factors separately; optimizing a number of neurons, an algorithm learning rate and momentum factors by using a genetic algorithm, and obtaining an optimal hidden layer node number; and performing prediction on rockburst of a mine by using a BP neural network algorithm model obtained through training, and obtaining a risk level of the rockburst of the mine. The method provided by the present invention has relatively high reliability, overcomes the defect of no association between the rockburst and the influence factors of the rockburst in the current rockburst prediction process, implements middle and short term dynamic prediction on the rockburst, and can be widely applied to the field of mine rockburst prediction.

The invention discloses a dynamic migrating method of a virtual machine based on performance prediction. The method comprises the following steps of obtaining a characteristic vector by using a singular value decomposing principle by extracting system performance data and analyzing the similarity of the singular value to obtain; then, obtaining the performance prediction value at the next moment by a reverse SVD (Singular Value Decomposition) algorithm so as to start a dynamic migrating mechanism of the virtual machine according to future performance prediction values. According to the method, the performance prediction mechanism can make accurate prediction value and the dynamic prediction mechanism can balance the system load. The system can effectively cope with sudden load by effectively analyzing current information of a physical machine and effectively predicting the future load, so that the performance loss caused by unnecessary migration is reduced.

The invention belongs to the technical field of video coding and decoding, in particular to an H.264 based flexible video coding method which realizes that coded video can be output or transmitted in various code rates through realizing that the resolution ratio, the frame sequence length and the quantitative parameter are adjustable in real time in a process of coding the video based on the H.264 standard. The method also realizes that the relevant parameters of loop filter and dynamic prediction are adjustable in a coding process and the coding complexity in the coding process is controlled, thereby reasonably utilizing system resources. The coding method has the characteristics of high efficiency and easiness of implementation, and can be applied to multiple network video transmission and multiple processor systems.

The invention relates to a difference value differential based lithium iron phosphate power battery power loading capacity dynamic prediction method which mainly comprises the following steps: (1), performing measurement and acquisition of data including battery voltage difference value, current difference value, and temperature difference value, and establishing data dependency models in different active sections; (2), constructing data sheets, establishing a dynamic time-variable three quantities based algebraic interpolation function, analyzing an interpolation remainder, and analyzing the differential features of the interpolation remainder; and (3), analyzing the dependency, and revising each battery power loading capacity dynamic model factor in a battery pack. According to the difference value differential based lithium iron phosphate power battery power loading capacity dynamic prediction method, not only are the influences over the battery power loading capacity by the voltage, the current and the stability of a single power battery cell considered, but also influences over the power loading capacity when the batteries dynamically work by the voltage difference value, the current difference value and the temperature difference value of the power battery within a unit time and the autocorrelation and the cross correlation of the difference value variable quantity among the single battery cells of the battery pack are considered, and the discrete value differential analysis method is applied to accurately predict the power loading capacity when the single battery cells of the power battery pack work dynamically.

The invention discloses a dynamic prediction method for wellbore flow in a coal-bed gas well. The dynamic prediction method comprises following steps: sampling liquid in a wellbore oil pipe in order to acquire real solid content of a wellbore; judging the flow pattern of gas-liquid-solid three phase flow in the wellbore and determining modeling parameters for the gas-liquid-solid three phase flow; establishing a gas-liquid-solid three phase flow pressure model in the wellbore based on the real solid content and the modeling parameters in combination with the position of the working fluid level and data of well body configuration; establishing a temperature distribution model based on the gas-liquid-solid three phase flow pressure model, the real solid content and the modeling parameters by combining with heat transfer parameters of a well body; and obtaining distribution results of pressure and temperature of gas-liquid-solid three phase flow pressure in the wellbore along the depth of the wellbore based on the pressure model and the temperature distribution model. The dynamic prediction method for wellbore flow in the coal-bed gas well has the capability of predicting flow state, flow rate, pressure and temperature distribution and other physical property parameters at any position in the wellbore based on liquid production capacity and gas production capacity of a wellhead, casing pressure and other physical property parameters.

The invention discloses a learning behavior dynamic prediction method and device, equipment and a storage medium. The prediction method comprises the following steps: based on the learning behavior data of a user in a historical period, adopting a long-short-time memory cycle neural network as a prediction model for training to obtain an optimal model; and acquiring learning behavior data of the user in the first time period, and outputting a prediction result based on the optimal model. The invention adopts LSTM-RNN as a prediction model to predict the output results, can improve the accuracyof the prediction, and uses an interactive visual analysis mode to display user information data, facilitates viewing and analysis of user data information at the background of the system, so as to help teachers to timely and intuitively know the results of data analysis, and then achieve the ''closed loop'' of the teaching process. The invention can be widely applied to various learning behaviorprediction systems.

The present invention discloses a method for predicting residual deformation of the old goaf in the steeply inclined thick coal seam. The method comprises: analyzing a residual deformation mechanism of the old goaf in the steeply inclined thick coal seam, and then analyzing the mining effect propagation regulation of the steeply inclined thick coal seam; using a changing mining effect propagation angle to describe the special form of rock movement; correcting parameters in a theory model in the traditional probability integral method, and establishing a mining subsidence prediction model based on the change of the mining effect propagation angle; by combining the equivalent mining thickness idea, using the matlab programming to construct the residual movement deformation prediction model; introducing the Kelvin model to analyze the creep characteristics of the old goaf and to construct the dynamic prediction function of the residual settlement, so that dynamic analysis of the residual settlement is carried out. Beneficial effects of the method disclosed by the present invention are that: the method for determining residual deformation generated by further activation of the old goaf under the influence of the external force after the collapse of the goaf of the steeply inclined thick coal seam is stable, and the method can also be applied to the foundation evaluation on the new building above the old goaf.

The invention provides a muscle fatigue dynamic prediction method based on multi-channel sEMG. An sEMG signal is susceptible to external interference, so an average value of all channels is selected to be a reference value; a difference is made between the new reference value and the original multi-channel sEMG, so external interference can be effectively reduced; a time-scale least square method is translated according to time reference to achieve dynamic update and predict muscle fatigue time; MPF and MF parameters are important parameters reflecting muscle fatigue, so reliability is provided for muscle fatigue prediction; the MPF and the MF two parameters are employed for prediction of muscle fatigue time, so instability of single parameter prediction can be avoided and prediction robustness can be enhanced; and the muscle fatigue dynamic prediction method based on multi-channel sEMG has high accuracy, fast calculation speed, simplicity and important application values.

The invention discloses a highway tunnel health status dynamic evaluation method based on the variable fuzzy set theory. The method comprises the steps of constructing a highway tunnel health status evaluation index system with lining fissures, lining strength, lining thickness, corrosion of reinforcement, lining deformation, back cavities, pavement distress, harmful gas and lighting distress as evaluation indexes as well as the qualitative and quantitative criterion of the evaluation grade and each evaluation index of highway health status; and through repeated and regular detection of the highway tunnel evaluation indexes by a tunnel diagnosis and fast repairing integrated car and based on the variable fuzzy set theory, determining highway tunnel detection node health status values and the health status deteriorating speed mean value and establishing a highway tunnel health status dynamic evaluation model by means of repeated detection data of the highway tunnel health status evaluation indexes and the criterion of the evaluation grade and each evaluation index of the highway health status. The highway tunnel health status dynamic evaluation method based on the variable fuzzy set theory not only achieves objective evaluation of the highway tunnel health status, but also can be used for dynamic prediction of the highway tunnel health status.

The present invention is applied to the electric power system field, in particular relates to a gray prediction and support vector machine-based classification type electric vehicle demand temporal-spatial distribution dynamic prediction method. The method comprises the steps of firstly utilizing a high-accuracy improved gray model to predict the numbers of the vehicles of different types; then based on the proportions of the electric vehicles of different types and the nonlinear characteristic of the influence factors, utilizing a support vector machine regression method and the prediction samples to obtain a classification type electric vehicle substitution ratio prediction result, and utilizing an iterative method to correct the prediction result continuously; and finally matching the two prediction results according to the vehicle types, establishing a classification type electric vehicle demand growth prediction model, and combining the user travel rule research to realize the accurate dynamic temporal-spatial prediction of the classification type electric vehicle demands. Therefore, the method of the present invention has the following advantages of fully considering the characteristic that the historical data is insufficient and the influence of different factors on the development of the electric vehicles and combing the user travel rule research to realize the more accurate dynamic prediction.

The invention discloses a travel spot passenger flow dynamic prediction method; the travel spot passenger flow dynamic prediction method combines a statistics method with a nerve network, considers various factor influences on the traveling, and combines a trend extrapolation method, a monthly index method and a fluctuation coefficient method in the statistics with a BPNN; the travel spot passenger flow dynamic prediction method considers various factors affecting the travelling, uses the monthly index to divide history visitors into small scale data, uses the BP to fully study, and finally uses the fluctuation coefficient to dynamically predict the travel spot passenger flow according to the holiday real conditions, thus providing large conveniences for a travel spot manager, providing guidance effect for travelers, and dynamically predicting the holiday passenger flows according to the future holiday real conditions.

The invention discloses a gray model (GM) (1,1) prediction method of orthogonal interpolation based on Markov chain. According to the grey orthogonal method and the principle of the Markov chain, the Gauss-Chebyshev orthogonal thought is used to predict overall trend of time-series data. Accuracy of the prediction is time-varying, the principle of the Markov chain has good advantages during the process of processing a time-varying system, and choosing the GM (1,1) prediction method of the orthogonal interpolation based on the Markov chain can solve the instability of the prediction result better, and therefore the grey Markov orthogonal model is put forward for the prediction of data of electricity consumption, and is suitable for a dynamic prediction process which is of a short-middle term, low in demanded quantity of data and large in data amplitude. The GM (1,1) prediction method of the orthogonal interpolation based on the Markov chain is scientific in inventive concept, simple to calculate, small in work load, and high in prediction accuracy, and good in usage value and wide in application range in the technical field of prediction.