102 results about "Change prediction" patented technology

The invention relates to a vehicle lane change predicting method, device and system, and aims at solving the problem that lane change prediction is not accurate in the related art. The method comprises that driving data sent by multiple vehicles is obtained; according to the driving data of each vehicle, a present lane of each vehicle on the same road is determined; and the driving data of all thevehicles on the road is combined and analyzed to obtain information of the probability that vehicles change lanes to enter a target lane.

The invention provides a method for controlling output power of a photovoltaic inverter. The method comprises the following steps: detecting the rate of change of the direct current bus voltage of the photovoltaic inverter; and when the direct current bus voltage is reduced and the rate of change is more than the threshold, reducing the output power of the photovoltaic inverter so that the photovoltaic inverter keeps grid-connected. The method is characterized by judging whether the photovoltaic cell pack is shadowed according to the rate of change of the direct current bus voltage based on the power change prediction, reducing the output power at the right time to ensure the photovoltaic cell pack and the photovoltaic inverter to be newly balanced and maintaining the direct current bus voltage to ensure the inverter to be continuously grid-connected. The method has the following advantages: the calculation amount is small; the reliability is high; the photovoltaic inverter can be effectively avoided from breaking away from the grid when being suddenly shadowed; and the method is easily applied in practice.

The invention relates to an on-line monitoring device for oil pollution of a hydraulic system and a monitoring method. By means of on-line monitoring for parameters such as temperature, pressure, oilpollution particles and the like of the hydraulic system, the degree of the oil pollution of the hydraulic system is evaluated by a temperature, pressure and oil pollution particle change prediction curve created by a grey prediction model, inspection and maintenance suggestions are submitted according to correlation of temperature, pressure, abrasive particle content and fault and fed back to a technician, so that the purposes of fault early warning and on-condition maintenance are achieved, potential fault of the hydraulic system can be found in time, follow-up serious accidents are prevented through maintenance, effective operation of equipment is guaranteed, and service life of the equipment is prolonged.

The invention relates to a small wind power generator variable-rate variable-pitch control method and system for teaching. The method includes the steps that the rotating speed of a pitch control is measured; the variable-pitch angle is calculated; a fuzzy algorithm is adopted for calculating the variable-pitch rate based on wind speed change prediction; and a variable-pitch execution mechanism drives blades to achieve variable pitch. The control system comprises a wind power generator information collecting device, a variable-pitch controller and the variable-pitch execution mechanism. According to the small wind power generator variable-rate variable-pitch control method and system, the fuzzy algorithm is adopted for forecasting the wind speed changes and calculating the best variable-pitch rate, the blades are driven by a servo motor to rapidly rotate to specific positions, and the technology is excellent and reliable. On the premise that an existing wind power generator structure is not changed and absorption of the blades on wind energy is not influenced, the biggest wind energy conversion efficiency can be achieved according to the wind speed information in the manner that the blades are driven by the servo motor to rotate to the specific position rapidly.

Methods, systems, and apparatus for predicting the braking or acceleration of a vehicle. The pedal change prediction system includes a braking sensor for providing braking data or an acceleration sensor pedal for providing acceleration data. The pedal change prediction system includes an electronic control unit that is configured to determine a rate of depression of the brake pedal or the acceleration pedal that is associated with a first braking force or a first acceleration force. The electronic control unit is configured to predict a triggering event that is either a braking event or an acceleration event. The electronic control unit predicts the triggering event based on the rate of depression of the brake pedal or the acceleration pedal and causes the vehicle to apply a second braking force or a second acceleration force.

A linear predictive system for a DC-DC converter including a linear predictive controller, first and second adders and a multiplier. The DC-DC converter generates an output signal and includes a digital compensation block that converts a feedback error signal into a main duty cycle signal. The linear predictive controller predicts linear changes of the main duty cycle signal in response to changes of the output signal and provides a predictive duty cycle signal. The first adder subtracts the predictive duty cycle signal from the main duty cycle signal to provide a duty cycle delta. The multiplier multiplies the duty cycle delta by a gain factor to provide a duty cycle delta sample. The second adder adds the duty cycle delta sample to the first duty cycle signal to generate an adjusted duty cycle signal. The linear predictive controller performs an inverse function of DC-DC conversion approximated to the first order

The invention relates to a software function change prediction system and method based on graph mining and belongs to the field of software engineering. The system and method of the invention carry out calculation based on software network function call relational graphs; first, the whole function call relational graph is required to obtain; by comparing the functions of the adjacent versions, modified, deleted, added functions are get and a changed function subgraph is obtained; by means of the graph mining algorithm span, parameters are selected which are mainly span and support degree to obtain corresponding frequent subgraphs, wherein the functions contained in the subgraphs are predicted functions that can be changed.

The invention relates to the field of accurate farming management, and discloses a method for constructing a greenhouse carbon dioxide concentration prediction model in the sunny days of the winter. The temperature and CO2 concentration data of a greenhouse are acquired at the same time interval so as to acquire the time sequence data of the temperature and the CO2 concentration; the time sequence data are segmented and a part of data RA are randomly selected out of the time sequence data for modeling, and the remaining data RB are used for detecting the model; data sets A and B are constructed by using a sliding time window according to RA and RB; a temperature dynamic change prediction model M1 is constructed according to A; a crop aerobic respiration and soil respiration carbon dioxide release rate prediction model M2 is constructed according to A and M1; a crop net photosynthesis carbon dioxide consumption rate prediction model M3 is constructed according to A and M2; and the greenhouse carbon dioxide concentration prediction model M4 in the sunny days of the winter is constructed according to M1, M2 and M3. According to the method for constructing the greenhouse carbon dioxide concentration prediction model in the sunny days of the winter according to the environmental meteorological factors only, the model universality is great and the prediction accuracy is high.

The invention discloses a tire contour measurement method based on camera shooting, and the method comprises the steps: firstly, carrying out the shooting of the same tire tread pattern image at different positions, and extracting a tire tread pattern contour sparse image and a key point feature value from a single two-dimensional image; secondly, establishing a change rate and a change directionkey point characteristic matrix of an image pixel gray value according to the tire tread, and calculating a plurality of same key point characteristic values in two and a plurality of tire tread sparse images; then, comparing and calculating a camera internal parameter and a three-dimensional space camera pose external parameter change prediction value with two or more actual observation values oftwo or more two-dimensional space pixel values, and fitting a three-dimensional tire tread contour space curve; and finally, comparing the actual three-dimensional spatial change data of the tread pattern obtained in any time period, and calculating the use abrasion loss of the tire in the time period. According to the tire tread measurement feedback method provided by the invention, a calculation basis is provided for the tire according to use payment while safe driving of the tire is ensured.

The invention discloses an LED (Light Emitting Diode) lamp brightness change control method suitable for singlechip processing, which comprises the following steps: judging whether an expected duty cycle discrete value EP is equal to a current duty cycle discrete value CP or not, if not equal, calculating the duty cycle change prediction interval time ITC, wherein ITC is equal to FP/CP, and the FP is a discretization value of the 100 percent duty cycle; comparing the ITC with a preset allowable interval time ITM, if the ITC is larger than the ITM, allowing the change interval time IT of the duty cycle with the duty cycle discretization value plus or minus 1 to be equal to ITM; if the ITC is less than or equal to ITM, allowing the IT to be equal to ITC; judging whether the IT is reached or not, if yes, comparing the EP and the CP; if the EP is larger than the CP, adding 1 to the CP; if the EP is less than the CP, subtracting 1from the CP; and repeating steps 1-9 till the CP is equal to the EP. The invention also discloses a device for the realization of the method. According to the invention, less singlechip resource is consumed, and smoother brightness change is obtained.

The invention discloses a device for monitoring and displaying the state of power equipment. The device comprises a monitoring unit, an early warning device, a fault diagnosis module, a comprehensivedisplay unit and a central control unit, wherein the early warning device comprises a trend prediction module and an alarm module, and the trend prediction module is used for generating the operationtrend of the next moment according to the obtained operation state parameters of the power equipment and comparing the operation trend with a monitoring threshold value according to the trend; the alarm module is used for giving an alarm when the trend exceeds a monitoring threshold value or the current operation state parameter exceeds the monitoring threshold value; and the central control unitis used for performing state monitoring, state change prediction, real-time state display and fault grading on the power equipment. By establishing a 3D model for each piece of power equipment and displaying the operation state parameters of each piece of power equipment in real time, the state visualization effect of the power equipment is improved, reliability grading is carried out on all powerequipment, and the management monitoring effect of the power equipment is enhanced.

The invention discloses a green vegetable intelligent identification and leaf color environment change prediction method, which belongs to the field of agricultural planting, and comprises the steps of pattern acquisition, intelligent identification, leaf color information extraction, meteorological data acquisition, day and time regression model establishment, model goodness of fit judgment and prediction accuracy analysis, model determination and the like. According to the invention, facility agriculture field monitoring equipment can automatically identify and cut green vegetable plant images in real time in an open and natural environment, extract related leaf color parameters, and establish a change prediction mode of image information and environmental meteorological factors. The technology has the advantages of intelligent identification, timing automatic focus tracking, rapid and accurate cutting, high-speed parameter extraction and analysis, and high prediction model accuracy,and is suitable for day and time prediction and analysis. The method provides a technical basis for dynamic monitoring and early warning services of facility agriculture.

The invention relates to the fields of software engineering technology and application, and aims to finally output a variable-class sorting list about class change sizes, give a project manager and developers a more granular version evolution result, and save test time and costs. The invention discloses an Android App program evolution change prediction method based on Gaussian process regression.The method includes the following steps: phase 1, carrying out data crawling; phase 2, carrying out data preprocessing; phase 3, obtaining an optimal prediction window size; and phase 4, constructinga Gaussian process regression prediction model, and finally, outputting a next-version class change degree sorting list through the prediction model. The method is mainly applied to software engineering technology occasions.

The invention discloses a shared electric vehicle station user demand prediction method. According to the method, a station is selected as a circle center, two data acquisition subsystems are established by taking a buffer area within a range of square and round one kilometer as a research object, wherein one system acquires characteristic data such as population economic characteristics, employment, entertainment, medical service, traffic modes and road networks in the buffer area, and the other system acquires parking space number data of a station, and travel data of the shared electric vehicle in the continuous time; deep mining and fusion are performed on the two pieces of data to form input data, and finally a whole set of shared electric vehicle station user demand prediction technology is established based on semi-parametric spatial geographic weighting Poisson regression; The technology can provide user demand change prediction support for the design of a berth number change adjustment scheme in the existing site layout, the influence of site surrounding built-up environment change on site user demands and the like.

The invention discloses a user phone-changing prediction method. The method includes: determining first phone-changing user result data according to obtained user bill data and a preset bill phone-changing prediction method; determining second phone-changing user result data and target terminal type data according to obtained search behavior data and a preset search behavior prediction method; comparing the first phone-changing user result data with the second phone-changing user result data, and determining prediction result data according to a comparison result; and determining a user phone-changing prediction list according to the prediction result data and the target terminal type data. The invention also discloses a user phone-changing prediction apparatus, and the tendency of changing a terminal for a user can be more accurately predicted.

The invention belongs to the technical field of steel manufacturing, and particularly relates to a component change prediction method and system for a special steel type mixed casting blank, and particularly relates to a component change prediction method for a special steel type mixed casting blank. The method comprises the following steps of: collecting a mixed casting blank sample, and analyzing the component change of the mixed casting blank sample; acquiring the tundish residual steel quantity and the tundish steel production capacity, and fitting a mixing degree function model according to the component change, the tundish residual steel quantity and the tundish steel production capacity; acquiring the continuous casting pulling speed and the width of the mixed casting blank sample, and fitting a liquid core impact depth function model according to the component change, the continuous casting pulling speed and the width; and according to the mixing degree function model and the liquid core impact depth function model, predicting the initial position and the final position of the mixed casting blank, wherein the mixing degree function model and the liquid core impact depth function model are established without depending on laboratory digital analog calculation or water model experiments, so that the prediction accuracy is high.

The invention relates to the technical field of carbon dioxide flooding oil recovery increase in oil and gas field development, and discloses a carbon dioxide flooding gas front edge dynamic change prediction method. The carbon dioxide flooding gas front edge dynamic change prediction method includes the following processes that an injection-production corresponding condition is judged by comprehensively considering the suction profile result, the injection-production well spacing and the oil well effective condition, the gas injection volume is split in the different effective oil well directions, the splitting coefficient and the gas injection volume in different oil well directions are calculated according to the gas injection efficiency speed, a fan blade model is used for calculatingthe dynamic change of the gas drive front edge position under different gas injection volumes, and carbon dioxide flooding gas front edge dynamic change prediction is realized. By means of the method,only basic data such as production dynamics data, suction profile data and injection-production well spacing are needed, data collection and processing are simple, through gas drive front edge prediction, the advancement speed of CO2 under the oil deposit condition is better grasped, the gas generating time is better predicted, the dynamic change of the miscible range can be quantitatively calculated in combination with the pressure profile, and a basis is provided for CO2 dynamic tracking evaluation and injection-production parameter optimization adjustment.

An apparatus 10 for predicting change in a physical index includes an acquisition unit 13, a setting unit 12, and a calculation unit 18. The acquisition unit 13 acquires the ketone body concentration excreted by a subject. The setting unit 12 sets a set time at a present time or a later time. The calculation unit 18 calculates a predicted value of change in the physical index based on the ketone body concentration and on the set time. The predicted value of change in the physical index is the change in body weight of the subject or in the weight of body fat when the designated time elapses.

The invention relates to a PM2.5 concentration spatio-temporal change prediction method and system based on a spatio-temporal diagram neural network. The method comprises steps of acquiring atmospheric pollutant concentration monitoring historical data of each atmospheric monitoring station, meteorological data of a national meteorological station, predicted meteorological data and elevation data; constructing a sample, and constructing an adjacent matrix M and a weight matrix W by using the longitude and latitude of each atmosphere monitoring station; and constructing a neural network model based on the space-time diagram to predict a prediction result of each station, and obtaining a corresponding PM2.5 concentration prediction value. According to the method, observation data of about 1500 atmospheric monitoring stations in the whole country is taken as a training set, various data sources such as meteorology and elevation are combined, the neural network based on the space-time diagram is used, a unified prediction framework is constructed, the PM2.5 concentration change in a large area can be predicted at the same time, and the prediction precision is improved.

The invention relates to the technical field of vehicle intelligent driving, provides a vehicle lane change steering lamp automatic starting system and a vehicle lane change prediction method, and aims to solve the problem that in reality, drivers always do not turn on steering lamps due to various reasons and accordingly traffic accidents happen. The vehicle lane change steering lamp automatic starting system comprises a signal detection module, a decision control module and a drive control module, wherein the signal detection module is used for detecting road surface lane image information,vehicle speed signals and steering wheel angle signals; the decision control module processes the information obtained through the signal detection module and obtains control signals indicating whether the steering lamps are turned on or not through judgment and decision making; and the driving control module receives the control signals of the decision control module and controls the steering lamps at corresponding positions to be automatically turned on when the steering lamps need to be turned on. The vehicle lane change prediction method is based on the system, has good fault tolerance andflexibility, and has relatively high social use value and application prospects.