Product
Patsnap Eureka
For R&D, Patsnap Eureka makes reading and utilizing patents & technical documents easy.
Patsnap Eureka AIR
Designed for self-driven R&D workflows. Generate viable solutions, solve complex R&D challenges, empower your innovation with AI.
Patsnap Eureka Materials
Designed for material experts only. Revolutionize your material R&D, from search, analyze, to developing new materials.
Feature
TechResearch
Generate reliable direction feasibility study reports for your R&D in just a few steps.
TechSeek
Discover and master advanced knowledge NOW. Basics, ideas, possibilities, all at once.
TechMind
As an expert in R&D Theories, TechMind can generates customized viable solutions instantly.
TechRisk
Analyze your overall solution with one click, know your potential R&D risks in advance.
TechMonitor
Get weekly tech updates, stay abreast of the latest tech innovations and key insights.
Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
42results about How to "Guaranteed identification accuracy" patented technology
Efficacy Topic
Property
Owner
Technical Advancement
Application Domain
Technology Topic
Technology Field Word
Patent Country/Region
Patent Type
Patent Status
Application Year
Inventor
Neural-network self-correcting control method of permanent magnet synchronous motor speed loop
ActiveCN102497156AAdaptableSimple structureElectronic commutation motor controlVector control systemsPower flowLoad torque
The invention discloses a neural-network self-correcting control method of a permanent magnet synchronous motor speed loop. The method is characterized by: taking a current loop and a motor as generalized objects; firstly, collecting information, such as a rotating speed, a current and the like; using an adaptive linear time-delay neural network to carry out off-line parameter identification to the motor; then, taking a weight obtained through off-line learning as an initial value of on-line learning; finally, carrying out on-line parameter identification to the system, calculating a load torque of the motor according to the identified parameter; designing a neural-network self-correcting control law according to the obtained parameter value and a load disturbance value, adjusting the network weight on line according to an error between a controlled object and an identification model, and then setting the parameter of the neural-network self-correcting controller on line so as to realize online adjustment of the controller parameter. Uncertainty of the system and influence brought by the external disturbance can be eliminated. Dynamic performance and an anti-disturbance ability of a servo system can be improved.
Owner:SOUTHEAST UNIV +1
Industrial robot dynamics model parameter identification method
InactiveCN106125548AHigh precisionLower estimated impactAdaptive controlPeriodic excitationDynamic models
The present invention proposes a parameter identification method for the dynamic model of an industrial robot, comprising: establishing a dynamic model of an industrial robot with six joints connected in series; setting a periodic excitation signal, and using the periodic excitation signal to optimize the identification track of the dynamic model of the industrial robot ;Measure the data of the dynamic model of the industrial robot at multiple time points, and average the data; estimate the parameters of the dynamic model of the industrial robot according to the data average processing results, and obtain the estimator of the unknown parameter vector; The industrial robot dynamics model and estimated parameters are verified, including: calculating the prediction error of the estimated parameters and the measured parameters of the industrial robot dynamics model, and using the residual root mean square of the prediction error to verify and evaluate the industrial robot dynamics model. The invention reduces the influence of measurement noise on parameter estimation and improves the precision of dynamic parameter identification.
Owner:珞石(北京)科技有限公司
On-line identification method for unbalance of magnetic suspension rotor based on current test mass
ActiveCN103604563AImprove work efficiencyStability is not affectedStatic/dynamic balance measurementRotary gyroscopesMagnetic bearingDynamic balance
Provided is an on-line identification method for unbalance of a magnetic suspension rotor based on current test mass. First, a mathematical model of static and dynamic unbalance of the rotor is established, then at rated rotating speed, a current transformer measures a current of a magnetic bearing coil, and a displacement sensor measures the displacement of a radial channel of the magnetic suspension rotor; secondly, the rotating speed is kept unchanged, a test mass current is added for the first time, the current of the magnetic bearing coil is measured, and the displacement of the radial channel of the rotor is measured; at the same rotating speed, the test mass current is added for the second time, the current of the magnetic bearing coil is measured, and the displacement of the rotor on the radial channel is measured; finally, the static and dynamic unbalance of the rotor is identified according to the currents and displacements measured at three times. The on-line identification method is simple and easy to implement by starting a car at one time and is applied to identification of the static and dynamic unbalance of the magnetic suspension rotor in the on-line dynamic balance process.
Owner:BEIHANG UNIV
An industrial robot dynamic parameter identification method considering joint elasticity
ActiveCN109583093AHigh precisionDoes not affect independenceDesign optimisation/simulationSpecial data processing applicationsControl theoryEncoder
The invention discloses an industrial robot dynamic parameter identification method considering joint elasticity. The problem that in the prior art, each joint needs to be provided with double encoders to achieve identification is solved. the beneficial effect of accurately identifying the dynamic parameters is achieved; According to the scheme, the industrial robot dynamic parameter identification method considering the joint elasticity comprises the steps of analyzing and classifying unknown parameters, establishing a linear identification model considering the friction coefficient of a motor, combining a static test to realize respective identification of the unknown parameters, and utilizing a separation identification strategy and an approximate processing method to accurately identify the dynamic parameters.
Owner:SHANDONG UNIV
Unbalanced compensation algorithm of polygonal iterative search with variable step size for rotor imbalance coefficient
ActiveCN107133387AFix stability issuesGuaranteed identification accuracyDesign optimisation/simulationSpecial data processing applicationsIterative searchFundamental frequency
The invention discloses an unbalanced compensation algorithm of polygonal iterative search with variable step size for rotor imbalance coefficients. The algorithm comprises the steps that in the step of signal processing, identification and compensation output of unbalanced coefficients, the signal processing is based on the rotor vibration signal and the rotor speed obtained by a displacement sensor and the rotor speed and phase signals obtained by a phase detection device, the amplitude values of the fundamental frequency of rotor vibration signals are obtained by calculation; the amplitude values of the fundamental frequency of rotor vibration signals are used as the judgment criterion for the identification of unbalanced coefficients, unbalance coefficients are obtained through the identifications by the polygon iterative search method with variable step size; unbalanced compensation electric currents are generated by the compensation output based on the unbalanced coefficients, and inputted in electromagnetic coils, then suppression is conducted on the rotor imbalance vibrations. The unbalanced compensation algorithm of polygonal iterative search with variable step size for rotor imbalance coefficients can be applied to active rotor systems with active control units, online compensation of the imbalance of the active rotor system is achieved, so that suppression is conducted on unbalanced vibration of the rotor system of the entire rotor speed range in the acceleration and deceleration operation process.
Owner:ZHEJIANG UNIV
Rotary shaft and position-independent geometric error identification method based on ball-bar measurement
InactiveCN108723893AQuick checkEasy to analyzeMeasurement/indication equipmentsGeometric errorPosition error
The invention discloses a rotary shaft and position-independent geometric error identification method based on ball-bar measurement. The method comprises the following steps of determining the measurement position of a ball-bar according to the structure of a machine tool and the type of rotary shafts, mounting a spindle tool cup and a base tool cup and conducting correction; mounting the ball-bar, detecting the shaft A and the shaft C without a lengthening bar to obtain ball-bar readings, and conducting compensation calculation on position errors of the shaft A and the shaft C; changing the length of the ball-bar by additionally arranging the lengthening bar, changing the position of the spindle tool cup, rotating the shaft A and the shaft C correspondingly to obtain the ball-bar readingsand obtaining eight position-independent geometric errors of the rotary shafts of the machine tool through calculation. Through the method, the position-independent geometric errors of the rotary shafts can be identified quickly and effectively, the identification precision is high, and the practicality is good.
Owner:TIANJIN POLYTECHNIC UNIV
Novel electromagnetic signal identification method and device for graph convolution network and transfer learning
ActiveCN110427835AGuaranteed identification accuracyGuaranteed robustnessCharacter and pattern recognitionNeural architecturesFeature vectorPattern perception
The invention provides a novel electromagnetic signal identification method and device based on a graph convolution network and transfer learning, and the method comprises the steps: constructing a graph structure based on the implicit knowledge of an electromagnetic signal; constructing a graph convolutional neural network, obtaining a category weight vector to which the novel electromagnetic signal belongs, and constructing an updated electromagnetic signal classification weight matrix; extracting a deep feature vector of the novel electromagnetic signal to be identified; and according to the updated electromagnetic signal classification weight matrix and the deep feature vector, completing transfer learning of the novel electromagnetic signal, and generating a perception identificationresult of the novel electromagnetic signal. The method can recognize the novel electromagnetic signal based on the graph convolution network and transfer learning, and effectively guarantees the recognition precision of the novel electromagnetic signal for a target, the robustness for the conversion of a scene and sensing equipment, the recognition response speed, and the adaptive capability whena new target appears.
Owner:TSINGHUA UNIV
Flux linkage full-rank identification method for permanent magnet of PMSM
ActiveCN106602952ARealize full rank identificationEliminate the influence of identification accuracyElectronic commutation motor controlVector control systemsOperandLinearization error
The invention discloses a flux linkage full-rank identification method for a permanent magnet of a PMSM. According to the method, an unscented-Kalman-filter-algorithm-based parameter sensitivity analysis for the flux linkage identification precision of a permanent magnet of a PMSM is carried out; a permanent magnet flux linkage full-rank identification method of different rotating speed zones of a PMSM drive system is determined. With the unscented-Kalman-filter-algorithm-based permanent-magnet flux linkage full-rank identification method of different rotating speed zones of a PMSM drive system, influences on the permanent magnet flux linkage identification precision by the system measurement noises, PMSM parameter changing, and a degenerate-rank phenomenon of an identification model can be eliminated; linear error occurrence and complicated Jacobian matrix calculation during the state identification process of the traditional extended Kalman filter algorithm can be avoided; and the algorithm implementation difficulty can be reduce. Meanwhile, the number of to-be-identified parameters can be reduced at a high-speed operating zone in a PMSM drive system; the operand of the identification algorithm can be reduced; and reasonable consideration of the identification precision and the identification speed can be realized.
Owner:HENAN INST OF ENG
Machine tool rotating shaft geometric error identification method based on ballbar measurement
InactiveCN108972154AEasy to analyzeQuick checkMeasurement/indication equipmentsGeometric errorSoftware engineering
The invention discloses a machine tool rotating shaft geometric error identification method based on ballbar measurement. The machine tool rotating shaft geometric error identification method based onballbar measurement comprises the following steps of according to the positions of a machine tool structure and a rotating shaft, installing a ballbar, and calibrating a main shaft tool cup and a base tool cup; utilizing a corresponding machine tool code for controlling only one rotating shaft of the machine tool to rotate; utilizing the ballbar for preliminarily identifying geometric errors, irrelevant to the position, of the rotating shaft; and changing the installation position of a ballbar base, utilizing the ballbar for accurately identifying the geometric errors, irrelevant to the position, of the rotating shaft, and obtaining eight geometric errors, irrelevant to the position, of the rotating shaft of the machine tool. The method provided by the invention can be used for quickly and effectively identifying the geometric errors of the rotating shaft of the machine tool, and is high in identification accuracy and good in practicability.
Owner:TIANJIN POLYTECHNIC UNIV
Unbalance compensation method for rotor unbalance coefficient variable-angle iterative search
ActiveCN111177943ASimple structureStability impactGeometric CADDesign optimisation/simulationVibration amplitudeIterative search
The invention discloses an unbalance compensation method for rotor unbalance coefficient variable-angle iterative search. The method comprises the steps of vibration signal processing, variable anglecompensation algorithm recognition coefficient searching and compensation current calculation, wherein a vibration signal processing module calculates a rotor unbalance vibration signal amplitude according to rotor vibration information, rotor rotation angle information and rotation speed information; the variable-angle compensation algorithm is used for searching for recognition coefficients, the rotor unbalance vibration signal amplitude serves as the judgment basis, the unbalance coefficients are repeatedly identified and optimized through a variable-angle iterative search method, and a set of unbalance coefficients enabling the unbalance vibration amplitude to be reduced to the minimum are obtained through iteration. Corresponding compensation current is calculated according to the unbalance coefficient and input into the electromagnetic coil to restrain unbalance vibration of the rotor. The method can be used for an active rotor system with an active control unit, unbalance on-line compensation of the active rotor system is achieved, and unbalance vibration in the acceleration and deceleration operation process within the whole rotating speed range is restrained.
Owner:ZHEJIANG UNIV
Motion controller and system identifying method
InactiveCN101044673AEasy to identifyReduce the impact of interferenceElectric motor controlMotor parameters estimation/adaptationDifferentiatorViscous friction
A motion controller accurately identifies system constants, such as inertia, viscous friction coefficient, and constant disturbance, without requiring operation, even in cases where viscous friction and / or constant disturbance are present. An identifier includes a time-differentiator for calculating an acceleration detection value afb by time-differentiating a speed detection value Vfb, a first filter for calculating Fafb by filtering the acceleration detection value afb, a second filter for calculating Fvfb by filtering the speed detection value Vfb, a third filter for calculating Ftref by filtering a torque command value Tref, and a JDC estimator for calculating an inertia identification value J_hat, a viscous friction coefficient identification value D_hat, and a constant disturbance identification value C_hat of a control object by performing time-differentiation and four arithmetic operations based on Ftref, Fvfb and Fafb.
Owner:YASKAWA DENKI KK
Plant identification method based on cloud model and TOPSIS (Technique for Order Preference by Similarity to Ideal Solution) method
InactiveCN102156710AExpand your searchImprove retrieval accuracyCharacter and pattern recognitionSpecial data processing applicationsPattern recognitionTOPSIS
The invention relates to a plant identification method based on a cloud model and a TOPSIS (Technique for Order Preference by Similarity to Ideal Solution) method. The method comprises the following steps: constructing a plant shape feature specimen database; utilizing a trapezium-cloud model to compare the shape features of a plant to be identified with the plant shape feature specimen database to acquire a comparative membership between the plant to be identified and the shape feature specimen database, thus completing the primary identification of the plant to be identified; when a plurality of identification results exist, utilizing a normal cloud model to carry out accurate matching calculation on the retrieval results so as to acquire a comparative accurate membership between the plant to be identified and the shape feature specimen database; and comprehensively evaluating the membership by utilizing the TOPSIS method to identify the plant. The method can comprehensively evaluate the final identification result by adopting the TOPSIS method, and can completely, reasonably and accurately carry out advantage and disadvantage sequencing according to certain evaluation indexes, so that the evaluation process is clear, and the evaluation result is objective.
Owner:SHANGHAI UNIV
Adaptive active damping control method for three-phase current-type PWM rectifier
InactiveCN109831106AImprove reliabilityRealize real-time monitoringAc-dc conversionPWM rectifierThree-phase
An adaptive active damping control method for a three-phase current-type PWM rectifier includes the following steps of 1, establishing a parameter adjustable model based on a model reference adaptiveidentification principle; 2, sampling and reconstructing a critical voltage and current signal; 3, establishing a value optimization function; 4, obtaining an adjustable model adaptive adjustment lawaccording to the value optimization function and an optimization purpose; 5, designing the optimal virtual resistance of an LC filter based on parameter online identification; and 6, performing adaptive active damping control based on the parameter online identification.
Owner:INST OF ELECTRICAL ENG CHINESE ACAD OF SCI
Battery thermal parameter identification method based on dimensionless model
ActiveCN110750912AGuaranteed identification accuracyPrevent safety accidents such as thermal runawayDesign optimisation/simulationEngineeringMechanical engineering
The invention provides a battery thermal parameter identification method based on a dimensionless model, and belongs to the technical field of batteries. The method comprises the following steps of bonding two same battery samples by using a heating sheet; establishing a dimensionalized heat transfer model for the battery sample and carrying out non-dimensionalization; respectively arranging a plurality of thermocouples on the non-contact surfaces of the two battery samples and the heating sheet; and after the heating time is determined, heating the heating sheet to obtain a battery temperature curve corresponding to the position point of each thermocouple on the two battery samples, and optimizing the dimensionless heat transfer model to finally obtain a thermal parameter identification result of the battery samples. According to the method, the thermal parameters of the battery are rapidly identified while the identification precision is ensured, and the identification efficiency isimproved.
Owner:TSINGHUA UNIV
Composite material layered damage identification method based on contour and depth sequence identification
ActiveCN113720907AGuaranteed accuracyGuaranteed practicalityAnalysing solids using sonic/ultrasonic/infrasonic wavesUltrasonic/sonic/infrasonic wave generationMathematical modelStructural engineering
The invention discloses a composite material layered damage identification method based on contour and depth sequence identification. The method comprises the steps of firstly, defining the layout of active piezoelectric sensors and passive strain sensors; secondly, carrying out active excitation and signal receiving on each piezoelectric sensor in sequence, and obtaining scattered waves of the damage through signal subtraction before and after the damage; then estimating the central position of the damage by using an alternating time reversal phase synthesis method, estimating boundary points of the layered damage by using the flight time of the direct wave in sequence, and performing damage boundary fitting based on the obtained multiple groups of boundary points; and thirdly, establishing a mathematical model for identifying the layering depth based on Bayesian posterior probability, updating a posterior probability model through strain measurement on the basis of the estimated damage boundary, and finally determining the layering depth. According to the method, a framework of active and passive information cooperative utilization is provided, reliable identification of the area and depth of the layered damage is achieved, the precision is high, and the practicability is high.
Owner:BEIHANG UNIV
Virtual load dominant parameter identification method based on incremental learning
ActiveCN112241836AGuaranteed identification accuracyImprove training efficiencyArtificial lifeResourcesSystems analysisData platform
The invention discloses a virtual load dominant parameter identification method based on incremental learning. The virtual load dominant parameter identification method comprises the steps that (1) enabling virtual load model dominant parameters to be subjected to random value simulation; (2) establishing a deep learning neural network; (3) carrying out deep neural network incremental learning; and (4) carrying out online rapid identification and cyclic training. The feasibility of incremental learning applied to power system analysis is mainly introduced and is combined with load parameter identification, the training efficiency is improved while the identification precision is ensured, the storage overhead is maintained while catastrophic forgetting is prevented, a new thought is provided for processing training samples in parameter identification, and a technical support is provided for online identification of dominant parameters of the virtual load model; by means of the thought of continuous training online rapid identification, the convolutional neural network is applied to parameter identification of the load model, and online identification, continuous circulation and continuous training of dominant parameters of the virtual load model are achieved on a power grid big data platform.
Owner:TIANJIN UNIV
Airplane icing on-line detection method based on statistical test and filtering
ActiveCN112046761AStrong icing online detection capabilityMore icing related informationDe-icing equipmentsAerodynamic derivativesClassical mechanics
The invention discloses an airplane icing on-line detection method based on statistical test and filtering. The airplane icing on-line detection method at least comprises the following steps that S1,flight state measurement data, engine thrust data and rudder deviation input data in the flight process are collected; S2, an icing starting moment is detected by utilizing a generalized likelihood ratio test method; S3, a disturbance signal is generated to be superposed on the rudder deviation input data, and joint state estimation and aerodynamic derivative identification influenced by icing areconducted on the flight state measurement data by utilizing an H-infinity filtering method; S4, an icing end moment is detected by utilizing the generalized likelihood ratio test method; and S5, generating and superposing of the rudder deflection disturbance signal are stopped, and joint state estimation and aerodynamic derivative identification influenced by icing continue to be conducted on themeasurement data by utilizing H-infinity filtering until the flight is finished. By combining quick icing detection and a parameter estimation method, an airplane icing detection algorithm with stronger functions is obtained.
Owner:CALCULATION AERODYNAMICS INST CHINA AERODYNAMICS RES & DEV CENT
An improved MIT-MRAI four-rotor unmanned aerial vehicle parameter identification method
ActiveCN109933869AHigh precisionLower requirementSustainable transportationSpecial data processing applicationsModel selectionUncrewed vehicle
The invention discloses an improved MIT-MRAI four-rotor unmanned aerial vehicle parameter identification method which comprises the following steps: step 1, establishing a spatial motion equation of aquadrotor unmanned aerial vehicle based on a mechanism modeling method; 2, selecting related parameters needing to be identified according to the established model; 3, solving the rotational inertiaof the unmanned aerial vehicle around three axes by using a suspension line method; 4, utilizing the improved MIT-MRAI parameter identification method to identify the lift coefficient and the resistance coefficient of the rotor. The improved suspension line method is adopted to solve the rotational inertia of the unmanned aerial vehicle around the three axes, so that the suspension line method period measurement mode is more accurate.
Owner:ROCKET FORCE UNIV OF ENG
Linear variable parameter vibration system global identification method
PendingCN113486523AImprove identification efficiencyGuaranteed identification accuracyDesign optimisation/simulationSpecial data processing applicationsParametric vibrationIndustrial engineering
A linear variable parameter vibration system global identification method is characterized by comprising the following steps: continuously applying excitation to an LPV vibration system with continuously changed scheduling variables, constructing an over-complete dictionary function library, and obtaining a vibration system model in an LPV-ARX form from excitation-response data with continuously changed scheduling variables through sparse regression; and calculating the impact excitation response or random excitation response of the scheduling variables as different values, and carrying out modal identification to obtain the distribution of modal parameters about the scheduling variables. Compared with a traditional local identification method of the LPV vibration system, the global identification method disclosed by the invention can obtain a vibration system model in an LPV form only through one-time identification, and the identification efficiency of the LPV vibration system is remarkably improved on the premise of ensuring the identification precision.
Owner:NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
Neural-network self-correcting control method of permanent magnet synchronous motor speed loop
ActiveCN102497156BAdaptableSimple structureElectronic commutation motor controlVector control systemsPower flowLoad torque
The invention discloses a neural-network self-correcting control method of a permanent magnet synchronous motor speed loop. The method is characterized by: taking a current loop and a motor as generalized objects; firstly, collecting information, such as a rotating speed, a current and the like; using an adaptive linear time-delay neural network to carry out off-line parameter identification to the motor; then, taking a weight obtained through off-line learning as an initial value of on-line learning; finally, carrying out on-line parameter identification to the system, calculating a load torque of the motor according to the identified parameter; designing a neural-network self-correcting control law according to the obtained parameter value and a load disturbance value, adjusting the network weight on line according to an error between a controlled object and an identification model, and then setting the parameter of the neural-network self-correcting controller on line so as to realize online adjustment of the controller parameter. Uncertainty of the system and influence brought by the external disturbance can be eliminated. Dynamic performance and an anti-disturbance ability of a servo system can be improved.
Owner:SOUTHEAST UNIV +1
Power battery parameter identification method suitable for sparse data
ActiveCN108519557AGuaranteed identification accuracyImprove reliabilityElectrical testingPower managementPower battery
The present invention provides a power battery parameter identification method suitable for sparse data. Based on a set membership identification algorithm, when it is difficult to determine statistical distribution features of actual system noise, it is not needed to perform assumption of the statistical distribution features of the system noise, the boundary of the system noise is only needed, asensor is configured to measure introduced errors, and round-off errors and model errors of the machine number can be taken as a form of boundary errors. The algorithm has a capacity of identification of redundant data and can ensure identification precision when the battery management system sample interval is increased, is specially suitable for a condition of sparse data, can observably improve the reliability of the power battery management system, etc.
Owner:BEIJING INSTITUTE OF TECHNOLOGYGY
Unbalance Compensation Method for Rotor Unbalance Coefficient Variable Step Polygon Iterative Search
ActiveCN107133387BFix stability issuesGuaranteed identification accuracyDesign optimisation/simulationSpecial data processing applicationsFundamental frequencyPhysics
The invention discloses an unbalanced compensation algorithm of polygonal iterative search with variable step size for rotor imbalance coefficients. The algorithm comprises the steps that in the step of signal processing, identification and compensation output of unbalanced coefficients, the signal processing is based on the rotor vibration signal and the rotor speed obtained by a displacement sensor and the rotor speed and phase signals obtained by a phase detection device, the amplitude values of the fundamental frequency of rotor vibration signals are obtained by calculation; the amplitude values of the fundamental frequency of rotor vibration signals are used as the judgment criterion for the identification of unbalanced coefficients, unbalance coefficients are obtained through the identifications by the polygon iterative search method with variable step size; unbalanced compensation electric currents are generated by the compensation output based on the unbalanced coefficients, and inputted in electromagnetic coils, then suppression is conducted on the rotor imbalance vibrations. The unbalanced compensation algorithm of polygonal iterative search with variable step size for rotor imbalance coefficients can be applied to active rotor systems with active control units, online compensation of the imbalance of the active rotor system is achieved, so that suppression is conducted on unbalanced vibration of the rotor system of the entire rotor speed range in the acceleration and deceleration operation process.
Owner:ZHEJIANG UNIV
Machine learning sample generation method for aircraft thrust fault on-line identification
ActiveCN111240304AThe data is authentic and credibleImprove the accuracy of fault identificationProgramme controlSustainable transportationControl systemTest sample
The invention relates to a machine learning sample generation method for aircraft thrust fault on-line identification, and the method is suitable for the field of typical power system fault on-line identification in the aircraft flight process. Data fusion generation is carried out on flight motion information (such as flight position, speed, acceleration, attitude angle and angular speed) of a control system, and corresponding data is intercepted as a machine learning training and testing sample according to the design method provided by the invention. Factors such as mass center motion, disturbance center motion, structural disturbance, aerodynamic force and moment of force of the aircraft are considered, deviation combination circulation is introduced into the simulation model to generate data, the data is more real and credible, and improvement of actual fault identification precision is facilitated. According to the method, the fault mode is refined, related data with relatively fine granularity of the fault mode is generated, and the identification precision is improved.
Owner:BEIJING AEROSPACE AUTOMATIC CONTROL RES INST
Resonant frequency identification method and device for grid-connected converter equipment, equipment and medium
ActiveCN111521870AAccurate identificationGuaranteed identification accuracyMultiple-port networksSingle network parallel feeding arrangementsCapacitor voltageControl engineering
The invention discloses a resonant frequency identification method and device for grid-connected converter equipment, an electronic device and a computer readable storage medium. The method comprisesthe following steps: acquiring a capacitor voltage signal of an LCL filter; extracting a fluctuation component signal of the capacitor voltage signal; sending the fluctuation component signals to twopreset identification controllers with the same structure and different center frequencies to obtain two output identification variable values; performing PI control based on the difference value of the two identification variable values so as to adjust the center frequency of the two preset identification controllers in real time until a closed-loop steady state is entered; and determining the average value of the center frequencies of the two preset identification controllers in the closed-loop steady state as the resonant frequency of the grid-connected converter equipment. By utilizing thefrequency characteristics of the identification results of the two preset identification controllers with different center frequencies relative to the resonant frequency and combining PI closed-loopcontrol, the resonant frequency of the grid-connected converter equipment can be effectively tracked and identified, and the identification rate, accuracy and real-time performance are effectively improved.
Owner:SHENZHEN INVT ELECTRIC
Control-oriented permanent magnet synchronous linear motor system identification method
ActiveCN112737451AImprove design efficiencyGuaranteed identification accuracyElectronic commutation motor controlAC motor controlMotor speedIndustrial engineering
The invention belongs to the technical field of servo system model identification and motion control, and discloses a control-oriented permanent magnet synchronous linear motor system identification method, which comprises the steps of: S1, establishing a motor dynamic model; S2, considering an interference environment to obtain model comprehensive description; S3, identifying a positioning force; S4, identifying a friction force; S5, taking a chaotic signal as a driver input signal, and collecting motor speed and position signals; S6, after the influence of nonlinear factors is counteracted by the input signal, acquiring effective excitation, and identifying a linear link transfer function; and S7, completing servo control parameter setting in combination with an identification result. By analyzing the system working principle and the environmental influence, typical nonlinear factors are identified under a servo full-closed-loop condition, and on the basis of separating the typical nonlinear factors, linearized identification of remaining modules is achieved; the problems that a traditional linear identification method is low in identification precision, and a nonlinear identification method is unclear in control strategy and parameter design are solved.
Owner:HUAZHONG UNIV OF SCI & TECH
A full rank identification method of pmsm permanent magnet flux linkage
ActiveCN106602952BRealize full rank identificationEliminate the influence of identification accuracyElectronic commutation motor controlVector control systemsOperandLinearization error
The invention discloses a flux linkage full-rank identification method for a permanent magnet of a PMSM. According to the method, an unscented-Kalman-filter-algorithm-based parameter sensitivity analysis for the flux linkage identification precision of a permanent magnet of a PMSM is carried out; a permanent magnet flux linkage full-rank identification method of different rotating speed zones of a PMSM drive system is determined. With the unscented-Kalman-filter-algorithm-based permanent-magnet flux linkage full-rank identification method of different rotating speed zones of a PMSM drive system, influences on the permanent magnet flux linkage identification precision by the system measurement noises, PMSM parameter changing, and a degenerate-rank phenomenon of an identification model can be eliminated; linear error occurrence and complicated Jacobian matrix calculation during the state identification process of the traditional extended Kalman filter algorithm can be avoided; and the algorithm implementation difficulty can be reduce. Meanwhile, the number of to-be-identified parameters can be reduced at a high-speed operating zone in a PMSM drive system; the operand of the identification algorithm can be reduced; and reasonable consideration of the identification precision and the identification speed can be realized.
Owner:HENAN INST OF ENG
A Control-Oriented System Identification Method for Permanent Magnet Synchronous Linear Motor
ActiveCN112737451BImprove design efficiencyGuaranteed identification accuracyElectronic commutation motor controlAC motor controlMotor speedClosed loop
Owner:HUAZHONG UNIV OF SCI & TECH
Multivariable system two-stage online identification method and system
PendingCN114859724AGuaranteed identification accuracyReduce computationInternal combustion piston enginesAdaptive controlMultivariable system identificationControl engineering
The invention discloses a two-stage online identification method and system for a multivariable system. The method comprises the following steps: acquiring continuous historical data of each controlled variable and each controlled variable in the multivariable system; constructing a data sample by adopting a CARMA model; obtaining the optimal pure lag time from each controlled variable to each controlled variable in the multivariable system, and establishing an optimal pure lag CARMA model; obtaining a step response curve of each controlled variable when each controlled variable is subjected to step change on the basis of an optimal pure lag CARMA model; acquiring continuous change data of the step response curve as an identification sample, acquiring the optimal pure lag time from each controlled variable to any controlled variable in the single-variable system based on a second-order pure lag CARMA model, and establishing a second-order optimal pure lag CARMA model; and performing matrix combination on the second-order optimal pure lag CARMA model to obtain a multivariable system identification model. According to the method, the multivariable model is decoupled and simplified while the model precision is ensured, and prediction control can be realized.
Owner:NR ELECTRIC CO LTD +1
Energy storage power station operation condition classification method and system, storage medium and server
PendingCN114462549AAccurate classificationSimple structureCharacter and pattern recognitionResourcesData setPower station
The invention discloses an energy storage power station operation condition classification method and system, a storage medium and a server. The method comprises the steps of collecting grid-connected operation condition data of an energy storage power station; preprocessing the grid-connected operation condition data of the energy storage power station to obtain a to-be-classified data set; judging whether a working condition classification model based on the random forest algorithm exists, if yes, inputting the to-be-classified data set into the working condition classification model based on the random forest algorithm for classification, and if not, training the working condition classification model based on the random forest algorithm; when the working condition classification model based on the random forest algorithm is trained, whether the working condition characteristic parameter system needs to be optimized or not is judged, if not, the working condition classification model based on the random forest algorithm is directly obtained, and if yes, the working condition characteristic parameter system is optimized based on the VIM of the working condition characteristic parameter importance measurement; and obtaining a working condition classification model based on a random forest algorithm. The working condition classification model based on the random forest algorithm has high tolerance to abnormal values and noise of working condition operation data.
Owner:CHINA ELECTRIC POWER RES INST +2
An Online Aircraft Icing Detection Method Based on Statistical Test and Filtering
ActiveCN112046761BStrong icing online detection capabilityMore icing related informationDe-icing equipmentsAerodynamic derivativesSimulation
The invention discloses an online detection method for aircraft icing based on statistical inspection and filtering. The online detection method for aircraft icing at least includes the following steps: S1: collecting flight state measurement data, engine thrust data and rudder deviation during flight Input data; S2: Use the generalized likelihood ratio test method to detect the beginning of icing; S3: Generate a disturbance signal and superimpose it on the rudder deviation input data, and use H ∞ The filtering method performs joint state estimation and icing-affected aerodynamic derivative identification on the flight state measurement data; S4: uses the generalized likelihood ratio test method to detect the end time of icing; S5: stops generating and superimposing the rudder deviation disturbance signal, and continues to use the H ∞ Filtering performs joint state estimation and identification of aerodynamic derivatives affected by icing on the measured data until the end of the flight. By combining the rapid detection of icing with the parameter estimation method, a more powerful aircraft icing detection algorithm is obtained.
Owner:CALCULATION AERODYNAMICS INST CHINA AERODYNAMICS RES & DEV CENT
Who we serve
- R&D Engineer
- R&D Manager
- IP Professional
Why Patsnap Eureka
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com