640 results about "Line model" patented technology

The invention provides a vehicle line walking method and system based on machine vision. The line walking method comprises the following steps: an image acquisition module acquires an RGB color image of a road surface; an image processing module converts the RGB color image into a grayscale image; a binarization module obtains a binarization image to separate a lane line; an edge detection module obtains an edge image containing an inner edge and an outer edge of the lane line; a processor acquires parameters of the lane line to establish a lane line model, acquires lane position data of a vehicle in a world coordinate system through inversely perspective conversion, and determines a driving mode of the vehicle according to road surface image information; parameter adjustment of a steering engine and a motor can be realized by using acquired vehicle corner parameters and distance parameters, adopting the driving mode of the vehicle, and utilizing a sectional adaptive control strategy so as to realize real-time control of driving directions and driving speed of the vehicle. According to the method and system, provided by the invention, the line walking speed in the driving process of the vehicle can be increased, the line walking can be completed within the time of 10 milliseconds, and the stability in the driving process of the vehicle is strong.

The invention relates to a digital twin system of an intelligent production line, which comprises a physical space layer, an information layer and a virtual space layer. The physical space layer is composed of a physical production line, intelligent sensing devices and an industrial control network. The information layer includes a data conversion module, a data analysis module and a production line information database. The virtual space layer can adapt to a variety of platforms and environments including personal computers and handheld devices, is used for generating a virtual production line consistent with the physical production line by a 3D visual engine through online real-time and offline non-real-time rendering under the driving of the production line information database of the information layer, and has the functions of multi-angle of view visual display, natural interaction, state monitoring and so on. The real-time state information of the physical production line is collected by various intelligent sensing devices, and based on the information, a three-dimensional visual engine is driven to generate a virtual production line model consistent with the physical production line through rendering, thereby realizing the twin mirror image of the virtual production line and the physical production line.

The invention relates to a road edge detection method based on a laser radar and a camera, and belongs to the field of intelligent traffic. The method comprises the steps: acquiring road edge point cloud data through the laser radar; acquiring road image data through the camera; separately preprocessing the radar data and the camera data, and performing joint calibration; processing each frame ofradar point cloud data, and extracting candidate road edge feature points for each scanning line according to the linear features of a road edge through a method based on a distance; processing each frame of image data, and detecting a lane line in the image through a mature method, and extracting a lane line model; carrying out the fitting of the extracted candidate feature points through the lane line model; determining the distances between the candidate road edge points and a fitting line, correcting the fitting line through the road edge points, and obtaining a road edge detection result.The method can make the most of the advantages of the laser radar and the camera to precisely and stably detect the road edge.

The invention relates to a fault monitor and diagnosis method of a continuous annealing unit, in particular to a PCA (Principle Component Analysis) model based furnace temperature and tension monitoring of a continuous annealing unit, mainly comprising the following steps of firstly, according to process variable data obtained in the field, and establishing a temperature and tension monitor modelby utilizing a principle component analysis PCA method; secondly, establishing an off-line model and calculating the T2 statistics quantity and the SPE statistics quantity as well as contributed control limits thereof by utilizing the data, obtained in step one, when process variable is in a normal work condition; thirdly, applying an on-line model, calculating the T2 statistics quantity and the SPE statistics quantity of current data, monitoring whether a current state is normal or not according to information supplied by the off-line model, and giving alarm signals if abnormal; fourthly, determining a leading variable which causes a fault by utilizing contribution of the T2 statistics quantity and contribution of the SPE statistics quantity. The invention monitors the furnace temperature and tension in real time in the production process and traces back a fault reason for leading to system abnormality when the abnormality occurs.

The invention provides a Wi-Fi location fingerprint map building method and a system based on crowd-sourcing. The method comprises the steps as follows: acquiring relevant crowd-sourcing data; using a dead reckoning approach to calculate the relative motion trajectory of a user based on the crowd-sourcing data; identifying specific behaviors of the user including a plurality of behavior types through machine learning; building a behavior sequence model formed by the types of the specific behaviors in the relative motion trajectory and the relative spatial relationship between the specific behaviors; generating a point-line model of an indoor map, and matching the point-line model with the behavior sequence model through a hidden Markov model to obtain the indoor map coordinate information of the relative motion trajectory; and finally, building a Wi-Fi location fingerprint map based on the indoor location coordinate information and the crowd-sourcing data. The Wi-Fi location fingerprint map is built and updated automatically based on the crowd-sourcing data.

In one example, we describe methods and systems for automated online merchant charity donations. In one embodiment, a donation agent interacting with a merchant website can offer an online user an option to allocate at least a portion of a payment for or price of a purchase, associated with a transaction made by the user via the merchant website, to be donated by a merchant corresponding to the merchant website on behalf of the user to a charity of the user's choosing. If the online user exercises the option, the donation agent can calculate an amount of the donation to be made and store the calculated donation amount in a database. The donation agent can disburse the calculated donation amount to the charity selected by the customer. The method also works for the off-line model. The points earned can be combined with a college scholarship award mechanism.

The invention provides an optimized scheduling method of a semiconductor production line based on a Petri net and immune algorithm. The method utilizes the Petri net for carrying out modeling to the semiconductor production line, comprising a path scheduling model, an equipment group scheduling model and an equipment scheduling model; and the immune algorithm is embedded in the Petri net model as the scheduling strategy. By the Petri net model, all possible acts of the semiconductor manufacturing system can be described, such as work-piece processing, equipment failure, batch processing, defected wafer rework and the like. The chromosome of the immune algorithm can be directly structured out of search nodes of the Petri net model, and each gene of each chromosome records the scheduling strategy of each equipment group. A better chromosome is obtained by the simulation of the Petri net model, and therefore a sub-optimal scheduling strategy is generated. The optimized scheduling method has the advantages of reducing the complexity of the model and improving the reusability of the model and the scheduling algorithm.

The invention belongs to the technical field of power systems and discloses a system for monitoring a secondary circuit model on line in real time based on a protection device. The system comprises a network communication module, a model resolution module, a graph generation module, a model storage module and a real-time comparison module, wherein the model resolution model is connected with the graph generation module and the model storage module and outputs a substation configuration description (SCD) static model and a resolved configured IED description (CID) on-line model respectively; the real-time comparison module is connected with the network communication module and the model storage module, receives a generic object oriented substation event (GOOSE) real-time model, a verified SCD static model and a resolved CID on-line model, compares and outputs a comparison result to the network communication module, and the comparison result is uploaded to a background system to realize real-time on-line monitoring. By the system, a phenomenon that a virtual terminal and a secondary circuit of the protection device make mistakes due to SCD file modification, CID configuration errors, secondary circuit real-time connection obstacles corresponding to GOOSE messages and the like can be timely found, so that operational risks of a substation are reduced.

The invention relates to a strip steel quality forecasting, furnace condition early-warning and fault diagnosis method, in particular to a strip steel quality forecasting, furnace condition early-warning and fault diagnosis method based on partial least square, comprising the following steps: model selection: multiple models are adopted to describe the process characteristics of corresponding steel types; data preprocessing: data alignment based on the model is carried out, synchronization relation of process input and quality output is built and data dimensionless treatment is carried out to eliminate effect of process data on modeling precision owning to non-unity of physical units; an off-line model building; a PLS (partial least square) model for strip steel quality and process variable is built by utilizing a great amount of historical data in normal working conditions; determining control limit of an monitor-control index; determining variable quantity control limit; and on-line forecasting and on-line detection and fault diagnosis. In the invention, the model for the strip steel quality and the process variable is built by PLS algorithm, so as to realize real-time quality forecasting, process monitoring and fault diagnosis.

The invention relates to a comprehensive control method for the outlet temperatures of a heating furnace, belonging to the field of furnace temperature control technology. The invention is characterized in that branch balance control makes the outlets temperatures of a multi-branch heating furnace uniform, and automatic load lifting and dropping can be realized. By using state feedback prediction control of measured states and feedforward control, the method effectively improves the anti-interference ability. A state space model of the heating furnace is obtained by mechanism modeling, in no need of testing devices. An on-line model is self-adaptive, which effectively overcomes process characteristic change and improves the rate of putting into operation. Low-value fuel can realize idea valve location interval control, thus saving high-value fuel. The comprehensive control of the outlet temperatures ensures the uniform and stable outlet temperatures of the heating furnace, which is easy to operate and economical.

A risk management platform a steel trade financial business is a universal integrated risk management service platform which can automatically perform dynamic identification, real-time analysis, risk result processing and evaluation and quantifying the risk according to the data on the risks that are related in a steel trade financial business process based on a risk identification rule. The risk management platform comprises a risk management client frontend unit, a risk management channel gateway unit, a risk management core real-time service unit, a risk management background management service unit, a risk management offline service unit, a risk management near-line service unit and a risk management data service unit. The risk management platform and the risk management method have advantages of realizing abstract universal data model, integrating a rule engine which can be dynamically managed and changed, separating a real-time processing data according to a scene chronergy characteristic, realizing near-line model processing and offline model processing, finishing full-scene coverage of a risk management business, realizing independence between a client and a gateway architecture, reducing impact of business system change to a risk management back-end core, and flexibly decoupling a risk management logic and a business logic.

A method characterizes a customer line for data transmission. The method includes measuring electrical properties of the customer line from a central location, identifying a line model from the measurements, and identifying a modem model for a modem selected for use with the customer line. The modem model gives performance data for the selected modem. The method also predicts performance data for the customer line when operated with the selected modem by combining the line and modem models.

The invention discloses a power line extracting and modeling method based on airborne LiDAR data. The power line extracting and modeling method includes the steps of (1) LiDAR point cloud data obtaining, wherein the LiDAR point cloud data are obtained through an airborne LiDAR measuring system; (2) power line extracting and modeling, wherein the step (201) of power line extracting includes the substeps that Hough transformation straight line detection is used for detection to obtain a plurality of straight line point sets, single-power-line detection is carried out on all the straight line point sets until all power lines are detected out, and the single-power-line detection process includes least square method straight line fitting and single-power-line point cloud data recognition; the step (202) of power line modeling includes the substeps that with a parabola as a modeling model, the least square method is adopted for curve fitting to obtain a power line model. The power line extracting and modeling method is simple in step, convenient to implement and good in using effect, the extraction precision of the power lines is high, the built power line model is accurate, and the problems that according to an existing power line extracting and modeling method, power line recognition is inaccurate, and requirements for data quality are high can be effectively solved.

The invention discloses a lane line detection method. The method comprises the steps that a lane image in front of a driving vehicle is acquired; the acquired lane image is preprocessed to acquire lane line pixels in the lane image; a coordinate value corresponding to each line pixel in the lane image is acquired; each acquired coordinate value is put into a preset straight line lane line model to generate a lane line of the lane image. The invention further discloses a lane line detection device. According to the invention, the accuracy of lane line detection is improved.

The invention relates to a main steam temperature predictive control method of an ultra supercritical unit of a thermal power plant. A layered control structure is arranged, the layered control structure consists of a bottom direct control layer and an upper guide optimization layer, and the upper guide optimization layer realizes model parameter identification, prediction optimization and PID (Proportion Integration Differentiation) parameter setting control; and the bottom direct control layer is in a cascade system structure and comprises main loop control and assistant loop control, and a PID controller orienting a DCS (distributed control system) is directly controlled. The control method can be used for replacing a control engineer to set PID parameters, on-line model identification and control parameter setting methods are directly adopted to achieve the purpose of main steam temperature self-adaptive control, the application of an advanced control technology and an intelligent optimization technology under a DCS is realized, the stability and the robustness are stronger, and a changing process of a controlled object model of the main steam temperature under a variable load can be adapted.

In the lane line detection performed by a left-right similar object detection module, changes in brightness in the road width direction in a image plane are evaluated, a point group serving as a lane line candidate is extracted, and a lane line model is generated by calculating the parallax of left and right lane line candidate points and transforming the result into real space coordinates. A camera displacement diagnosis module determines a camera displacement by calculating a diagnostic value based on a difference between the parallaxes of the left and right lane lines in the same horizontal line between reference comparative images captured by a stereo camera unit. Where the camera displacement has occurred, a vehicle control device is instructed to stop the control function or make a transition to failsafe control, and a warning is issued instructing a user to take the vehicle to a maintenance site for inspection.

To determine the temperature profile (Tm(t)) of a hot-rolled material (1) in a cooling line (5), a heat conduction equation which takes the following form $\frac{\partial e}{\partial t}-\mathrm{div}\left[\frac{\lambda \left(e,p\right)}{\rho }·\mathrm{grad}T\left(e,p\right)\right]=0$

where e is the enthalpy, λ the thermal conductivity, p the degree of phase transformation, ρ the density and T the temperature of the rolled material at the rolled-material location and t is the time, is solved in a cooling-line model (4).

A three-dimensional (3D) electric power line model building method includes that a 3D virtual geographic scene is established according to topographic data and image data; an electric power pole-tower model and other electric transmission equipment models are established; electric transmission line structural data are obtained, and the position and the direction of an electric power pole-tower are determined according to the electric transmission line structural data; the electric power pole-tower model and the other electric transmission equipment models are uploaded into the 3D virtual geographic scene; and a 3D electric power line model is established according to the electric transmission line structural data and the position of the electric power pole-tower in the 3D virtual geographic scene, and the sag degree of an electric transmission line is calibrated. According to the 3D electric power line model building method and a building device, the 3D electric power line model is applicable for different 3D virtual geographic scenes, the flexibility of the 3D electric power line model configuration is improved, the electric power line model is high in biofidelity, manual modeling of the electric transmission line is not required, and modeling efficiency is improved.

The invention provides an automobile suspension parameterization design method. A hard point meter is used for driving point and line models of all components of a suspension, the point and line models of the components are used for building a point and line DMU (diesel multiple unit) model of the suspension, the point and line DMU module drives the suspension components to move, the DMU model of a suspension system is formed, and then, the DMU model of the suspension system is subjected to movement checking. When the method is implemented, the components, the MDU model, detail digital analog data of each component and the like are automatically changed during the suspension hard point change. The remodeling is not needed, the development period of a suspension product is greatly shortened, different automobile types can share the DMU model, the work efficiency can be greatly improved, and the development time can be shortened.

The invention provides a robot control method based on an off-line model pre-training learning DDPG algorithm, and the method comprises the following steps: collecting the training data of a 2D dummy in an off-line environment, and carrying out the preprocessing of the training data to obtain a training data set; constructing and initializing an artificial neural network and initializing parameters; pre-training the evaluation network and the action network offline by using the training data set; initializing a target network by using the pre-trained evaluation network, and storing state conversion data into a storage buffer by the intelligent agent to serve as an online data set for training an online network; training an online strategy network and an online Q network by using the online data set, and updating the online strategy network and the online Q network by using a DDQN structure; carrying out soft updating, and controlling the state of the 2D dummy. According to the method, the efficiency is higher, the generated Q value is more accurate, the average reward value is higher, the learning strategy is more stable and reliable, the convergence rate is increased, the obtained accumulated reward value reaches a higher level, and the robot can quickly arrive at the destination.

The invention provides an operation and maintenance alarm system and method. The system comprises an off-line model training module, an on-line detection module and an alarm module, wherein the off-line model training module is used for updating required parameters of a detection algorithm used by the online detection module on the basis of machine learning and detecting the distribution of index data on the basis of analysis results of historical data, the on-line detection module is used for receiving index data to be detected and detecting the index data by using a preset detection algorithm on the basis of prediction results of the index data distribution, and the alarm module determines whether to give an alarm or not on the basis of preset alarm rules according to a detection result of the on-line detection module. The operation and maintenance alarm system and method can achieve the automatic operation and maintenance alarm.

The invention discloses a lightning stroke characteristic assessment method which includes the following steps of: (1) determining a lightning stroke model; (2) determining a tower model and impulse grounding resistance; (3) determining an insulator model and flashover criteria of the insulator model; (4) selecting a line model and a matched load; (5) changing the neutral point grounding modes; (6) measuring zero sequence current values and neutral point potentials in different grounding modes. The lightning stroke characteristic assessment method has the advantage of being capable of being used for accurately assessing the effect of difference of the neutral point grounding modes in a 10kV lightning stroke characteristic on the lightning stroke characteristic.

The invention provides a method for real-time lane line detection based on vision under complex lighting conditions and belongs to the field of computer vision and unmanned intelligent driving. During image preprocessing, light estimation and light color correction are conducted on different light images so that the images can recover under standard white light; noise which is introduced in the image acquisition process is eliminated through Gaussian filtering, and then the images are binarized and subjected to edge extraction; the original images are divided in the extraction process; improved Hough transform is used for obtaining a lane candidate line, and a dynamic interesting region (ROI) is built; through Hough transform based on the dynamic interesting region (ROI) and kalman filtering, a lane line is tracked in real time to realize constraint and update of a lane line model. An algorithm is added into a lane line detection failure judgment module to improve the reliability of detection. The method is high in speed and good in robustness, a good lane line detection effect is obtained under the complex lighting conditions, the dynamic lane line identifying ability of a vehicle is improved, and the safety of unmanned vehicle driving is improved.

The invention relates to a finite element modeling method for the welding line of a soldering board based on vehicle crash simulation, belonging to the vehicle computer-aided design technique field, comprising the following steps: first, baseplate modeling, which comprises baseplate hard spot arrangement, baseplate reseau partition, and baseplate reseau translation; second, building a double-beam welding line model, which comprises space nodes arrangement, a double-beam manufacturing, and connection of the beam and baseplate; third, the attribute assignment of the double-beam unit, which comprises the attribute assignment of beam unit material and the attribute assignment of the beam unit section; fourth, moving the built welding line model of the soldering board and the baseplate reseau model into an impact finite element computational model. The invention considers the material attributes of the welding line, as well as considers the shape of the welding line, can accurately simulate the deformational behavior of the welding line in crash simulation, enhances the simulation accuracy of vehicle crash, is rapid and effective, and is easy to master technicist.

The invention provides an accurate grid sampling method used for recognizing a QR code. According to the method, a pixel value of a coordinate, corresponding to the center position of each depth module in the QR code, in an image, and a large frame of grid sampling is set up by using a central point A of a low right corner point of a top left corner view finding graph, a central point B of a left lower corner point of a top right corner viewing finding graph, a central point C of a top right corner point of a low left corner view finding graph and a central point D of a low right corner correction image; then sampling points of the upper side line and the left side line of a sampling grid can be located accurately and precisely by utilizing the rule that horizontal and perpendicular locating line models alternate in a deep and shallow mode; finally, according to the perspective deformation correction principle, sampling points of the right side line and the lower side line are calculated, so that the sampling grid of the whole graph is obtained. For the QR code with a plurality of correction graphs to be sampled, the method can be adopted for arranging the network in a subsection mode. The method has the advantages of being accurate in location, wide in application, simple in calculation, and completely suitable for an embedded system.