410 results about "Theory based" patented technology

The invention provides a fault predicting and diagnosing method suitable for a dynamic complex system. The method can be applied in the field of fault prediction and diagnosis of dynamic complex systems of spacecrafts and the like. The method comprises the following steps of: performing failure mode and effect analysis (FMEA) on the dynamic complex system to obtain a main fault mode and corresponding performance detection parameters, dividing the performance detection parameters into slowly variable data and fast variable data, pre-processing the performance detection parameters, establishingan autoregressive moving average model (ARMA) aiming at the slowly variable data to perform time sequence prediction, establishing a multi-resolution wavelet neural network aiming at the fast variable data to perform time sequence prediction, performing fault early warning on the time sequence prediction results by establishing a prediction interval model, and performing fault diagnosis by establishing a D-S (Dempster-Shafer) evidence theory-based multi-signal fusion model. The method can be used for predicting and diagnosing the faults of the dynamic complex system with high precision, and has strong universality.

The invention provides a compressed sensing theory-based reconstruction method of a magnetic resonance random sampled K space data image. The reconstruction method applies a contourlet conversion and iterative soft thresholding method to realize reconstruction of a magnetic resonance image. The method comprises the following steps: collecting K space data in a magnetic resonance image scanner according to a preset observation matrix phi to generate a measurement value, and keeping y; acquiring y from a coil of the magnetic resonance image scanner, and transmitting y to a computer; and finallyconstructing a same phi, constructing any orthogonal transformation psi, and recovering from y by adopting a compressed sensing theory-based magnetic resonance random sampled K space data image reconstruction method according to reconstruction. According to the method, scanning time is saved, quick imaging is realized, high-quality reliable image information is provided to medical nuclear magnetic resonance imaging detection, and solid theoretical and practical foundation is established for further development and large-scale popularization and application of the medical imaging detection technology.

The invention relates to an electroencephalogram feature extracting method based on brain function network adjacent matrix decomposition. The current motion image electroencephalogram signal feature extraction algorithm mostly focuses on partially activating the qualitative and quantitative analysis of brain areas, and ignores the interrelation of the bran areas and the overall coordination. In light of a brain function network, and on the basis of complex brain network theory based on atlas analysis, the method comprises the steps of: firstly, establishing the brain function network through a multi-channel motion image electroencephalogram signal, secondly, carrying out singular value decomposition on the network adjacent matrix, thirdly, identifying a group of feature parameters based on the singular value obtained by the decomposition for showing the feature vector of the electroencephalogram signal, and fourthly, inputting the feature vector into a classifier of a supporting vector machine to complete the classification and identification of various motion image tasks. The method has a wide application prospect in the identification of a motion image task in the field of brain-machine interfaces.

The invention discloses a heavy-duty lorry driving barrier detection and tracking method based on a binocular fisheye camera, and belongs to the technical field of traffic vehicle active safety. The method mainly comprises the steps: starting two calibrated and corrected infrared fisheye cameras, disposed at two ends of the tail of a vehicle, to synchronously collect back-up environment image information when the back-up of a heavy-duty lorry is detected, outputting a back-up information after jointing, and displaying the back-up image on a display screen of a cab. A binocular fisheye visual system is used for obtaining the initial position and distance of a to-be-tracked barrier object, and then a video target tracking algorithm combined with the low-rank matrix theory based on particle filtering is used for achieving the tracking of a barrier, achieves the real-time updating of an image template in a tracking process, and detects whether there is a new barrier or not. When a vehicle is detected to turn around, a supersonic radar is started to detect that there is a barrier in a one-meter range beside the lorry, the position of the barrier is displayed and the early warning is sent. The method is mainly used for a large-size lorry.

The invention provides a fault early warning method of a wind generating set. The fault early warning method comprises the following steps of: 10) collecting the actual temperature value R and temperature related parameter data of a monitored point for N times in a sampling period; 20) inputting the collected actual temperature value R and the temperature related parameter data of the monitored point into a predetermined temperature mould, computing to obtain a temperature predicted value of the monitored point and taking the temperature predicted value as the theoretical temperature value P of the monitored point; 30) obtaining a temperature deviation DEV, a temperature mean-square deviation MSE and related coefficients SCC of the theoretical temperature value P and the actual temperature value; and 40) estimating the health condition of the wind generating set on the basis of the temperature deviation DEV, the temperature mean-square deviation MSE and related coefficients SCC. By means of the fault early warning method, the accuracy of estimating the health condition of the wind generating set can be improved.

The invention relates to a method for processing the information of float cars under the structure of a parallel road network, which is mainly applied to the service field of the intelligent dynamic traffic information. The method comprises the steps: step 1, an SVM (Support Vector Machine) sorter is adopted to judge the matching relationship between sampling points and roads, and map match is carried out; step 2, according to map match information, a heuristic route deduction algorithm is adopted to deduce possible running routes of a car, and according to the properties of road chains contained in the routes, whether the car runs in the structure of a parallel road network or not is judged; the shortest running route or a main running route and a subsidiary running route are selectively output in different circumstances, and the reliability of average running speed information provided by the car is estimated; step 3, the D-S (Dempster-Shafer) evidence reasoning theory based on classification is adopted to merge road condition information provided by all the float cars passing by a certain road chain in a current period and consider the reliability of the road condition information in a merging process so as to obtain the mathematical expectations of the average speed and the travel time of the float cars passing by the road chain in the current period. On the basis that the data quality of the prior float cars is kept unchanged, the invention realizes the acquisition of the real-time dynamic traffic information under the structure of a parallel road network.

The invention discloses a clamping method and a fixture of processing and locating of a turbine hollow blade tenon. In the selection of locating points, five optimum locating points are selected by adopting a fixture precision theory based on the differential geometry, a form closure rule of locating points with the help of a blade surface three-dimensional model and so when six points comprising a benchmark are used for location, the precision of blade location is the highest; in the selection of clamping points, weak links are avoided and auxiliary clamping points are chosen on a tenon top end and a blade mounting plate which are better in rigidity and bigger in size for reducing as much stress and deformation as possible to the hollow blade. On the basis, the invention designs a special fixture for processing the blade tenon, which consists of a fixture body, a location pin, auxiliary fixtures of the tenon top end and the blade mounting plate. The fixture can ensure the accurate location and effective clamping in the processing of the turbine hollow blade tenons, improve the efficiency in the manufacturing process of complex curved hollow blades, reduce the cost and eliminate the harm to human health.

The invention discloses a traffic-wave theory-based traffic influence area determining method of expressway accidents, which is used for determining space-time influence areas of traffic accidents after the traffic accidents happen on expressways without inlet and outlet ramps. The traffic influence area determining method comprises the following steps of: firstly determining traffic flow and traffic density of the expressways under different traffic conditions, drawing an expressway flow-density map, and then analyzing an accumulating and evanishing process of traffic waves in a process fromthe beginning of the accidents to the elimination of accident influence by using the traffic-wave theory, calculating a traffic wave speed of each stage, drawing a space-time evolution map of the traffic accidents, and finally determining influence time ranges and space ranges of the accidents in each stage. The traffic influence area determining method is simple and convenient and has good stability and high reliability; and according to the traffic influence area determining method, the influence area of the traffic accidents can be timely and accurately forecasted, and stable, timely and reliable traffic accident information can be supplied to the administrative department of the expressway, thereby the implementation efficiency of a rapid traffic accident disposing measure is improved.

The invention relates to a motor rotating-speed tracking control method based on a self-adaptive fuzzy neural network, wherein rotating-speed and current double closed-loop control is adopted, an outer ring is a rotating-speed ring, a sliding-mode control theory-based fuzzy neural-network controller (SMFNN) is designed, an inner ring is a current ring, and a PI (Proportional-Integral) controller is adopted; a fuzzy neural-network rotating-speed controller comprises two parts, wherein one part is a PID (Proportional-Integral-Derivative) controller, and the other part is the fuzzy neural network, online real-time learning is carried out through the fuzzy neural network by utilizing a parameter correcting method designed on the basis of the sliding-mode control theory, and the two parts jointly act to obtain the output ir of the rotating-speed controller, i.e. a difference obtained by subtracting the output iFNN of the fuzzy neural network from the output iPID of the PID controller is used as the output ir of the rotating-speed controller. The control precision and the anti-interference performance of a motor speed-adjusting system can be improved through the control strategy of the motor rotating-speed tracking control method.

The invention relates to a power grid wind damage early warning system based on micro-landform wind field distribution and typhoon superimposed effect, belonging to the field of prevention, reduction and control of natural disaster for a power grid. The power grid wind damage early warning system comprises a weather data acquisition sub-system, a wind damage and wind speed forecasting computer sub-system, a power grid early warning information processing computer sub-system, a power grid wind damage estimation processing computer sub-system and an information issuing sub-system, and each above sub-system is orderly in signal electrical connections. The power grid wind damage early warning system is capable of acquiring timed weather data of meteorological stations in a region covered by the power grid, performing standard pretreatment, then, establishing a gale statistical diagnosis model and a numerical model by means of theory modeling and numerical simulation, analyzing influence degree of the gale on main lines, iron towers and transformer substations, and issuing a related gale early warning information report based on related rules for gale early warning grades, wherein the related rules are specified by the Meteorological Office. And the power grid wind damage early warning system has the advantages of high precision, excellent accuracy, quick real-time response speed and the like, and can provide decision support for gale damage prevention and power grid planning.

The invention discloses a fault diagnosis-based rail transit vehicle bearing residual life prediction method. The method includes the following steps that: S100, multi-angle feature extraction and fusion are performed; S200, cyclostationary theory-based fault diagnosis is performed; S300, multi-variable model training is performed, so that multi-variable model-based fault isolation is realized; and S400, based on a semi-supervised algorithm, a BP neural network algorithm and a support vector regression algorithm are used in combination to perform fault diagnosis-based residual life prediction. With the fault diagnosis-based rail transit vehicle bearing residual life prediction method of the invention adopted, fault detection, fault isolation and residual life prediction at the early stage of the fault of a bearing are realized, and a basis is provided for the formulation of vehicle bearing maintenance decision making.

The invention relates to a method for recognizing lighting shielding failure and counterattack of an AC transmission line. The different theories generated by the electromagnetic transient component of the lighting shielding failure and the counterattack of the high-voltage DC transmission line and different paths of transmission of the thunderbolt electromagnetic transient component on the circuit cause that the energy distribution of different frequency bands of the generated current transient state signals are different greatly. Therefore, in a travelling wave analysis and high-speed acquisition system at the protective installation position, the small wave analysis is adopted to extract the energy of the zero modulus current in different frequency bands. The shielding failure and the counterattack are differentiated according to the property of the energy distribution. A large amount of emulations show that the method is reliable and effective and can recognize accurately the shielding failure and the counterattack of the AC transmission line. The method has intuitive theory base and clear physical concepts, thereby being easy to implement, being widely applied to an AC system protective device, providing important data for the lightening protection design of the AC transmission line and providing reference for the operation and maintenance of the transmission line.

The invention relates to a collaborative theory-based DDoS (Distributed Denial of Service Attack) defense system, which comprises a controller and cleaning equipment arranged on a switchboard, wherein the controller monitors a port of a full-network switchboard, and then pulls monitored network flow of an abnormal port of the switchboard to the cleaning equipment; the cleaning equipment is used for analyzing and cleaning the received network flow and supplying a security defense strategy to the controller based on an analysis result; and the controller configures the switchboard based on the security defense strategy, so as to relieve the attack.

The invention discloses a remote sensing image change detection method based on multi-feature proof integration and structure similarity, comprising the following steps: A. data preparation: selecting remote sensing images to be carried out with change detection in different time phase and in the same spatial scope; B. feature extraction: respectively extracting features of textures, grads and edges of images in two time phases; C. structure similarity calculation: calculating the texture structure similarity, grads structure similarity and edge structure similarity of the remote sensing images in two time phases in a working window; D. basic probability assignment function determination: building basic probability assignment function (BPAF) of evidence theory based on texture structure similarity, the grads structure similarity and edge structure similarity; and E. forming evidence and obtaining change areas to realize change detection. The method carries out change detection based on the area statistic features of edges, texture sand grads of images and can effectively avoid detection miss and false detection caused by the change detection using single feature; and the algorithm has robustness.

The invention discloses a Bayesian theory-based multi-sensor detecting and tracking combined processing method, mainly used for solving the problem that the traditional sensor fusion system has poor performance. The implementation process of the method comprises the following steps of: 1, setting a motion model of a target; 2, setting an observation model of the target; initializing all sensors for predicting probability distribution; 4, calculating posterior probability distribution of the target in a combined state by each sensor according to respective observation and transmitting the posterior probability distribution to a fusion center; 5, performing fusion by the fusion center to obtain a posterior probability of the existence of the target after fusion; 6, detecting whether the target exists according to a set detection threshold; 7, performing fusion by the fusion center to obtain a posterior probability of the motion state of the target after fusion; 8, forecasting the combined state of the target by every sensor; and 9, repeating the steps from the step 4 to the step 8 to detect and track the target continuously. The Bayesian theory-based multi-sensor detecting and tracking combined processing method has the advantage of good detection performance and can be used for detecting and tracking the target on the basis of observation data.

The invention provides deep inclined fractured reservoir earthquake amplitude prediction technology and belongs to the field of seismic prospecting. In the method, deep inclined fractured reservoir earthquake amplitude prediction is performed by using pre-stack seismic amplitude data and the method comprises the following steps of: performing theoretical model forward and inversion analysis of an inclined fracture medium on target area characteristics to acquire optimization and inversion parameters; optimizing date by the pre-processing of data, macro-surface element partial superposition and a residual gather leveling method so as to optimize parameters; and performing inclined fracture medium theory-based reservoir fracture inversion to obtain the parameters of the fracture. In the method, special processing means are adopted according to the characteristics of the deep reservoir, so that the signal-to-noise ratio is improved, and the real amplitude is guaranteed to the maximum extent. By using the method, the inclined fracture of the deep reservoir can be accurately predicted; accuracy and applicability are high; and the method is an effective method for predicting a deep fractured reservoir.

The invention provides a simulation training method for a special situation fault of an unmanned aerial vehicle and a system thereof, and belongs to the field of data processing of the unmanned aerial vehicle. A fault tree theory-based unmanned combat aerial vehicle system fault traversing analysis method is provided; a fault which affects the safety of flight is used as a top event of a fault tree to decompose the fault step by step to obtain all fault modes which affect the safety of the flight; meanwhile, a simulation snapshot technology-based unmanned combat aerial vehicle training process decoupling design technology is provided, current training state data is extracted in real time to establish a snapshot database, snapshot data of corresponding stages is only required to be called aiming at different training stages, and simulation initialization is performed, so the problem of extraction of initial training parameters of different task stages is solved; the method and the system have a random selection function at the specific training stage of the special situation fault of the unmanned aerial vehicle and a random fault selection function.

The invention discloses a compressive sensing theory-based satellite remote sensing image fusion method. The method comprises the following steps of: vectoring a full-color image with high spatial resolution and a multi-spectral image with low spatial resolution; constructing a sparsely represented over-complete atom library of an image block with high spatial resolution; establishing a model from the multi-spectral image with high spatial resolution to the full-color image with high spatial resolution and the multi-spectral image with low spatial resolution according to an imaging principle of each land observation satellite; solving a compressive sensing problem of sparse signal recovery by using a base tracking algorithm to obtain sparse representation of the multi-spectral color image with high spatial resolution in an over-complete dictionary; and multiplying the sparse representation by the preset over-complete dictionary to obtain the vector representation of the multi-spectral color image block with high spatial resolution and converting the vector representation into the image block to obtain a fusion result. By introducing the compressive sensing theory into the image fusion technology, the image quality after fusion can be obviously improved, and ideal fusion effect is achieved.

The invention discloses a method for inverting a near-surface velocity model by utilizing preliminary waveforms. The method comprises acoustic wave equation-based wave field forward modeling and steepest descent-based waveform inversion technologies, and comprises the following steps of 1, extracting time-domain preliminary waveform records and an initial model; 2, calculating a simulated wave field and a wave field residual by utilizing acoustic wave equation staggered grid finite-difference forward modeling simulation; 3, reversely propagating the wave field residual to obtain a retransmission wave field; 4, calculating a gradient of a target function by utilizing the retransmission wave field and a forward propagation wave field, and calculating an updating step length; 5, updating a speed model; 6, inspecting whether the speed model is consistent with an iteration stopping condition, outputting the speed model if the speed model is consistent with the iteration stopping condition, otherwise returning to the step 2, and continuing iterative updating. According to the method, a wave equation theory-based full-waveform inversion technology is used as reference, and preliminary waves with higher energy and more stable waveforms are used for inversion, so that the multiplicity of solutions of full-waveform inversion is reduced, and the inversion stability and the calculation efficiency are improved; the accuracy of static correction and shallow depth imaging is improved.

The invention discloses a compressive sensing theory-based Doppler ambiguity-resolution processing method, which comprises the following steps of: (1) performing non-uniform sampling on continuous echo pulses in a totally-coherent processing period by utilizing Q-fold pulse repetition frequency values; (2) designing the possible Doppler frequency range of a target, and ensuring the Q-fold pulse repetition frequency values do not have Doppler dead zones in the Doppler frequency range; (3) constructing a compressive sensing (CS) model by utilizing the time-domain under-sampling characteristics of sampled data in the totally-coherent processing period and the sparse characteristics of frequency spectrums of the target to be detected in the possible Doppler frequency range; and (4) resolving the CS model by utilizing an orthogonal matching pursuit (OMP) reconstruction algorithm to directly estimate the amplitude response of ambiguity-free Doppler spectrums. The method eliminates the restriction of the PRF multiplicity adopted by a radar system to the number of the targets to be detected, and simultaneously avoids the condition of false values caused by the influence of measurement errors in the conventional methods by taking the influence of noise on reconstruction results into account and performing de-noising operation when the CS model is resolved to estimate the amplitude response of the ambiguity-free Doppler spectrums by adopting the OMP reconstruction algorithm.

The invention discloses a D-S evidence theory based multi-sensor information fusion method, relates to an evidence theory based multi-sensor information fusion method and belongs to the field of information fusion. The D-S evidence theory based multi-sensor information fusion method aims at solving the problem that a traditional evidence fusion method is large in calculated quantity and is uncertain in combination result and has one-ballot-veto problem during evidence combination. The D-S evidence theory based multi-sensor information fusion method comprises the steps of obtaining an evidence set E={ei, i=1, 2, ..., 1}; disposing the evidence ei into evidence data mi(A) according to a set identification frame theta={theta1, theta2, ..., theta n}; performing sorting from small to large according to cardinal number of the A to form an order focal element set K={C1, C2, ..., CJ}, and conducting BPA determination on evidence data mi(Cj) to obtain m'i(Cj); obtaining a fusion weighting function wi(Cj) according to wi(Cj)=1- m'i(Cj) - mi(Cj); performing evidence combination (as shown in the description) to obtain a combination result of all evidence sets and using the combination result as an output decision of a sensor. The D-S evidence theory based multi-sensor information fusion method is suitable for multi-sensor information fusion.

The invention relates to the field of image enhancement and discloses a Retinex-theory-based nonlinear image enhancement method and system. According to the method and the system, a gradient-domain-transformation-based edge-preserving filter manner is used for replacing the conventional Gaussian filter manner to obtain illumination components. On the one hand, the phenomenon of halo artifact near a high-contrast edge is effectively overcome; on the other hand, the edge-preserving filter of color images can be carried out in real time. In addition, a nonlinear compression function is constructed on account of the illumination components, a highlight area is suppressed and a dark area is effectively improved; the phenomenon of overexposure of the images is avoided; the image luminance is mapped to an ideal dynamic range; a self-adaptive local nonlinear enhancement manner is used for enhancing image details, so that the local details of reflection components are enhanced, the quality of the images is well improved; the enhanced images are closer to real natural sites; the details are more clear.

Equipment extracts components of spatial frequency that need to be evaluated in manufacturing a device or in analyzing a material or process out of edge roughness on fine line patterns and displays them as indexes. The equipment acquires data of edge roughness over a sufficiently long area, integrates a components corresponding to a spatial frequency region being set on a power spectrum by the operator, and displays them on a length measuring SEM. Alternatively, the equipment divides the edge roughness data of the sufficiently long area, computes long-period roughness and short-period roughness that correspond to an arbitrary inspection area by performing statistical processing and fitting based on theoretical calculation, and displays them on the length measuring SEM.

The invention provides a mechanical fatigue damage monitoring device and method under a multi-axis random load, which belong to the field of mechanical fatigue damage monitoring. The device mainly comprises a data collecting system (1), a data processing system (2) and a data monitoring system (3). The data collecting system (1) comprises a mechanical key part A2, a strain sensor A1 and a data transmission line A3; the data processing system (2) comprises a data collecting card B1, an alternating current power supply B2, a USB transmission line B3, a power amplifier B4 and an A / D (Analog to Digital) converter B5; and the data monitoring system (3) comprises a computer C1. According to the invention, as a multi-axis fatigue damage estimating theory based on a critical plane method is applied to a monitoring system, common fatigue damage monitoring problems under the multi-axis load in the actual construction are solved; and as shown by a predication result, the fatigue damage under the multi-axis load can be preferably estimated by using the algorithm.

The invention discloses a finite element theory based direct current magnetic bias suppression method under the condition of multiple direct-current falling points, and belongs to the field of direct current electric fields. According to the method, direct current electric fields are calculated with a finite element analysis method, the resistance in the direction parallel to the axis is obtained by calculating the radial resistance of the assigned specified soil grid, the distribution tendency of voltages and currents in the assigned direction is obtained, the current fields in different current falling points are determined, and the CDEGS software is adopted as a verification means; the current distribution curves corresponding to a plurality of directions are obtained to serve as the technical base for adopting the corresponding direct current magnetic bias suppression scheme in the following steps. Magnetic bias current calculating sub-models oriented to different power transmission systems can be respectively formed, the coverage range of the direct current magnetic bias research and the direct current magnetic bias suppression scheme is widened, and the simulating calculating efficiency is greatly improved. The method can be widely applied to the field of design, running and management of extra-high-voltage direct current power transmission lines.

The invention discloses a big data based power load prediction method. The method comprises the steps of step one, providing data information of N periods, obtaining a first power load predictive value of the (N+1) periods through a reinforcement learning load prediction data model directed at same data information and obtaining a second power load predictive value of the (N+1) periods in a data driving mode; step two, performing information fusion on the first power load predictive value and the second power load predictive value through a D-S evidence theory to obtain a final predictive result of the (N+1) periods. By the aid of the method, directed at a power load prediction system containing multiple dimensions and multiple stages of space, time, attributes and the like, a data driving theory based non-model load prediction controller and wavelet neural network based accumulative learning prediction are combined, information fusion is performed on the predictive values through the information fusion technology to obtain an optimal predictive value, and accordingly, the accuracy and the timeliness of load prediction are improved greatly.

The invention relates to a method for simultaneously acquiring a plurality of voice signals by using a DCS (distributed compressed sensing) technology. According to the method, the requirements of low hardware cost and high transmission rate of a plurality of sensor acquisition nodes in the agricultural Internet of Things can be met, the power consumption of a plurality of sensors in a communication process is reduced, and the sensors cooperatively work to prevent damage to the whole network structure due to the fact that the energy of certain nodes is excessively fast consumed. A JSM-1-model-based joint sparsity model for the voice signals is established by using a DCS theory, a plurality of pieces of sensing data are simultaneously compressed at a coding end, and the signals are precisely recovered by using a DCS-theory-based joint reconstruction algorithm at a decoding end to implement a complete signal acquisition process.

The invention relates to an anisotropic reverse time migration method for a quasi-P wave equation in a transverse isotropy with a vertical axis of symmetry (VTI) medium. The method comprises the following steps of: (1) performing discrete differentiation on a first-order quasi-P wave equation in a two-dimensional VTI medium and a perfect matched layer (PML) absorption layer boundary equation by adopting staggered meshes to obtain high-order difference formats of forward continuation and reverse continuation of the two equations; (2) performing numeric calculation to obtain a forwards-continued wave field of a shot point and a reverse time continued wave field of a receiver point, and performing normalized correlation operation on the two wave fields to obtain a migration imaging result of each imaging point in a model; and (3) extracting common imaging point gathers from migration results to obtain a final migration profile. By the method, a problem about the migration imaging of intensive transverse speed variation and a high dip angle stratum can be solved; and the influence of anisotropy of the medium is also taken into account, and the good imaging effect of longitudinal wave data acquired from an anisotropic region can be achieved by an anisotropy-theory-based migration method.

This invention relates to one city traffic journey time intelligent analysis system, which comprises each road catch identification device in the city traffic internet and intelligent servo with each catch device connected with intelligent servo, wherein, the servo comprises city traffic network topological structure module, car catch identification module, road section even drive time computation module, break judgment module to establish road topological structure and OD matrix relationship; due to number information from catch device, it uses road list to store router topological structure.