19results about How to "Realize online identification" patented technology

The invention discloses a vibration component decomposition and resonance area identification method based on blade tip timing original data, and relates to the field of blade vibration state monitoring. In order to solve the defects that an existing blade tip timing test method cannot realize online analysis and cannot automatically identify a resonance area, the method comprises the following steps: acquiring blade tip timing data by adopting a blade tip timing probe; the vibration displacement of the tip position of the rotating blade is obtained by subtracting the actual arrival time of the rotating blade from the theoretical time and combining the rotating speed of the tip of the rotating blade: constructing a blade tip vibration signal model, selecting a blade tip timing signal of the blade to carry out sparse auxiliary decomposition, setting optimization parameters and the maximum number of iterations, and calculating the vibration displacement of the tip position of the rotating blade. Obtaining decomposition results of the synchronous vibration signal component and the asynchronous vibration signal component; and carrying out automatic identification on a resonance region, and respectively obtaining region identification results of synchronous resonance and asynchronous resonance. The method is mainly used for online analysis of blade tip timing original data and automatic resonance area identification.

The application discloses a kind of for tantalum niobium tailings in tin metal recovery's synergistic treatment system, specifically related to metallurgical solid waste resource utilization technical field, acoustic-electricity perception pre-agglomeration module exports pre-agglomeration probability index according to pre-agglomeration threshold value;Heat resistance chromatography module exports the temperature field and fluidized void fraction distribution of suspected agglomeration area;Inhibiting ingredient self-adapting module calculates inhibitor addition rate according to distribution;Wind material decoupling adjustment module exports decoupled wind speed and feed rate set value according to addition rate and bed pressure drop;Chain negative feedback blocking module detects pressure drop deviation to generate feedback correction, superimposed to wind speed set value and reversely adjust feed rate set value, while used to update pre-agglomeration threshold value;The application realizes the online identification of agglomeration precursor, accurate danger area precision inhibiting and the closed-loop cooperation of wind material decoupling, inhibits the nonlinear deterioration of coking loss flow, makes tin recovery rate keep stable when tailings fluctuation, and reduces inhibitor consumption and manual intervention.

This application relates to the field of copper wire drawing technology, and particularly to a method for compensating for the implicit resistance of guide wheels in copper wire drawing machines, and the copper wire drawing machine itself. The method includes: acquiring a tension signal and a set of rotational speed signals; calculating the dynamic friction coefficient of each first-type guide wheel using Fourier transform based on the tension signal, the set of rotational speed signals, and the wrap angle of each first-type guide wheel, obtaining a set of dynamic friction coefficients; determining the smooth friction coefficient of each first-type guide wheel based on the set of dynamic friction coefficients, obtaining a set of smooth friction coefficients; determining that compensation conditions are met, and determining tension compensation based on the set of smooth friction coefficients; determining feedforward compensation based on the tension compensation, and generating a compensation command based on the feedforward compensation; and controlling the output torque of the traction device based on the compensation command. This method achieves online identification and quantification of the friction state of key guide wheels, reduces tension control lag, and improves the real-time performance of tension control.

The invention relates to the technical field of adsorption detection, and discloses an imidazolium resin adsorption kinetic parameter online identification method and system.The method comprises the steps that 1, flow, inlet and outlet water concentration, conductivity, temperature and pH value are synchronously collected, and apparent ion strength is obtained through the conductivity; step 2, performing mass balance based on the flow, the inlet and outlet water concentration and the resin dry basis mass to obtain a real-time track of the average adsorption capacity of the resin; step 3, constructing counter-ion coupling isothermal driving force and screening a quasi-balance section; 4, solving isothermal coupling parameters by combining a quasi-balance relational expression; 5, calculating an overall mass transfer coefficient point by point; step 6, simultaneously solving an outer membrane mass transfer proportionality coefficient and an in-hole mass transfer coefficient under two levels of flow; and step 7, constructing a core parameter group and outputting a consistency judgment result identifier. According to the method, online identification and consistency judgment of the adsorption thermodynamic parameters and the mass transfer kinetic parameters of the imidazolium resin are realized.

The present invention relates to a composite non-Gaussian filtering method for inertial / polarization combined attitude determination. For an inertial / polarization combined attitude determination system that is simultaneously affected by inertial device drift, unknown incident light intensity coefficient, inertial navigation and polarization measurement noise, firstly, a tightly coupled model of an inertial / polarization combined attitude determination system containing an unknown incident light intensity coefficient is established; secondly, for a situation where the incident light intensity coefficient is known, a composite non-Gaussian filter containing inertial device drift compensation is designed to achieve real-time estimation of attitude posterior distribution; finally, an expectation-maximization iterative algorithm with an embedded composite non-Gaussian filter is designed to achieve online identification of the incident light intensity coefficient. The present invention can improve the attitude solution accuracy of an inertial / polarization combined attitude determination system under multi-source error conditions, improve the adaptability of an inertial / polarization combined attitude determination system to unknown environments and meteorological conditions, and can be applied to autonomous navigation tasks of various unmanned systems such as drones / vehicles / ships in complex environments.

The application belongs to the technical field of power distribution network state estimation, and discloses a power distribution network operation mode identification method based on measurement big data analysis, which comprises the following steps: step 1, pre-processing measurement data; step 2, taking the measurement data of each sampling time as a sample, and using an improved t-distributed stochastic neighbor embedding algorithm to reduce the dimension of each sample; step 3, selecting a small number of samples from all samples, manually marking the corresponding power distribution network operation mode of the samples, and then automatically establishing the corresponding relationship between the remaining samples and the power distribution network operation mode through semi-supervised learning; and step 4, pre-processing and reducing the dimension of real-time measurement data, and identifying the real-time operation mode of the power distribution network according to the corresponding relationship obtained through semi-supervised learning. The online identification method provided by the application can quickly and accurately identify the operation mode of the power distribution network according to real-time measurement data, and provides guarantee for real-time observation of the operation mode of an active power distribution network containing a large number of distributed renewable energy sources.

The invention relates to a permanent magnet synchronous motor control method based on a mechanical parameter self-identification technology, and the method comprises the following steps: 1, building a motor observation model under the condition of considering disturbance, and designing a linear expansion state observer and a linear active disturbance rejection controller according to the motor observation model; 2, according to a total disturbance observation formula obtained by the linear expansion state observer, calculating an identification algorithm of the viscous friction coefficient and the rotational inertia of the motor; step 3, suppressing medium-high frequency disturbance by adopting a quasi-resonance controller; and 4, substituting the parameters obtained by the identification algorithm into the linear active disturbance rejection controller. According to the method, on-line identification of the viscous friction coefficient and the rotational inertia of the motor is realized on the premise that the permanent magnet synchronous motor maintains constant-speed operation by using the disturbance observation characteristic of the linear expansion state observer; error values caused by periodic torque pulsation in an identification result are eliminated through the quasi-resonance controller and the linear active disturbance rejection controller, and the identification accuracy is improved.

The present invention provides a method for online recognition of slab numbers based on an autonomous evolutionary neural network, and relates to the technical field of automatic control of hot rolling production processes in steel enterprises. The method first extracts video data of the slab traveling process, and performs data processing to obtain a slab image data set with slab numbers; then, based on the idea of ​​transfer learning, the specific position of the slab number on the slab image is located to produce a data set required for slab number recognition; based on the idea of ​​multi-objective genetic programming, an autonomous evolutionary neural network algorithm is designed to construct an integrated model for slab number recognition, and online recognition of slab numbers is realized; finally, the recognized single slab number characters are reorganized to obtain a predicted slab number. The method can realize end-to-end online recognition of slab numbers, effectively reduce labor costs, and improve the intelligent manufacturing level of hot rolling production lines.

The application discloses a lithium battery operation state evaluation system and method based on data analysis, relates to the technical field of lithium battery operation state evaluation, collects electric excitation response data of a battery under different measurement parameters, generates an impedance spectrum tensor, carries out normalization processing on the impedance spectrum tensor along a temperature dimension, outputs a temperature decoupling impedance tensor, decomposes the temperature decoupling impedance tensor along a rate dimension, outputs a rate separation impedance matrix, extracts static contact impedance from the rate separation impedance matrix, carries out trend deduction along a state of charge dimension, outputs a charge decoupling impedance sequence, decomposes the charge decoupling impedance sequence, outputs a contact impedance fluctuation sequence, carries out filtering processing on the rate separation impedance matrix according to the contact impedance fluctuation sequence, outputs a corrected internal resistance spectrum, calculates a real health state of the battery based on the corrected internal resistance spectrum and carries out determination, and outputs a battery health state signal.

The invention discloses an autonomous identification method and system for an error degradation form of direct current measurement equipment, and the method comprises the steps: building an evaluation standard quantity based on the normal operation state after operation and historical data measured by the direct current measurement equipment in different error degradation forms; based on the measured historical data, establishing a mathematical model of a metering error degradation form of the direct current measurement equipment; extracting feature sample sets of different error forms based on the evaluation standard quantity; based on the feature sample set, establishing a direct-current measurement equipment error form identification model and training the direct-current measurement equipment error form identification model; and when the evaluation standard quantity detects that the metering error state of the direct current measurement equipment is abnormal, performing online detection on the metering error of the direct current measurement equipment by utilizing the established mathematical model of the metering error degradation form of the direct current measurement equipment, and performing online identification by applying the trained error form identification model of the direct current measurement equipment. According to the invention, workers can be helped to detect the abnormal state of the direct current measurement equipment in time.

The invention discloses a fractional order sliding mode controller optimization design method for improving the transient voltage stability of a power grid, and the method comprises the steps: firstly designing an additional voltage controller based on a fractional order sliding mode theory, and then carrying out the recognition of a discrete z function expression of a system through combining with a least square criterion; and finally, based on the designed transfer function of the additional voltage controller and the discrete z function, establishing a parameter optimization model of the additional voltage controller. On the basis, iterative optimization is carried out in combination with a reinforcement learning algorithm, so that a parameter self-adjustment strategy of the fractional order sliding mode controller is obtained, adaptive updating of controller parameters under different working conditions is realized, and the fractional order sliding mode controller can play a good voltage control effect under different working conditions; and the system voltage stability under variable working conditions is enhanced.

The present invention discloses a train operation control optimization method based on time-varying parameter identification, comprising the following steps: step S1, determining input and output data through the records of on-board equipment during train operation, analyzing the time-varying parameters that the train needs to identify, and establishing a basic train model; step S2, obtaining a train operation model based on the auxiliary model through auxiliary model processing for actual collected data; step S3, using the train operation model obtained in step S2, applying it to the train control system, and optimizing the train operation. The present invention is based on data-driven parameter identification, starting from actual input and output data, taking into account the variability of the actual train operation environment, by continuously iteratively updating information, and accelerating the decay of historical data with a forgetting factor, it can track environmental changes well, realize the identification of time-varying parameters, have lower prediction errors, and can achieve optimization of train control.

The invention discloses an on-line identification and adaptive filtering method and system for an inductance parameter of an over-modulation field weakening area of a permanent magnet synchronous motor, and relates to the field of over-modulation field weakening control of the permanent magnet synchronous motor. The problem of inductance parameter perturbation of an overmodulation flux-weakening area caused by reduction of inductance saturation current loop decoupling precision of the flux-weakening area of the permanent magnet synchronous motor during high-speed operation and a large amount of harmonic waves introduced by overmodulation is solved. The method comprises the following steps: S1, constructing a steady-state voltage equation of the permanent magnet synchronous motor; s2, deducing an actual inductance expression according to a voltage equation and a decoupling item; s3, constructing an inductance identification closed loop and designing an inductance identification controller; and S4, carrying out adaptive filtering on an over-modulation weak magnetic region parameter identification result. The method is applied to the fields of electric automobiles, aerospace and the like.

The present application relates to a kind of self-adapting filter mutual inductor error dynamic compensation method and system, it is related to mutual inductor technical field, including the following steps, to the current, voltage sampling of mutual inductor secondary side and temperature measurement, construct working condition parameter matrix;In combination with pre-calibrated iron core hysteresis curve, mapping obtains prior excitation sequence;Through residual feedback and gain update generation posteriori excitation sequence;Accordingly, the error of secondary electric quantity is converted, obtains dynamic compensation sequence, and inverse superposition obtains correction secondary sequence;Finally, according to the ratio conversion, restore primary electric quantity sequence, the problem that the prior art cannot track the dynamic change of iron core hysteresis nonlinearity and operating condition in real time is solved, leading to excitation error is difficult to accurately separate from secondary side signal, and then influence primary side electric quantity restoration precision problem.

The invention relates to a motor cross coupling effect identification and compensation method for a multi-degree-of-freedom forming robot. The method comprises the following steps: S1, establishing a kinematics model, a mechanical dynamics model, a permanent magnet synchronous motor dynamics model considering the cross coupling effect and an electromechanical coupling dynamics model of the multi-degree-of-freedom forming robot; s2, establishing a motor cross coupling angle identification model of the multi-degree-of-freedom forming robot in combination with an electromechanical coupling dynamic model; and S3, combining the electromechanical coupling dynamics model and the motor cross coupling angle identification model to establish a multi-degree-of-freedom forming robot dynamics feedback control model, wherein the multi-degree-of-freedom forming robot dynamics feedback control model comprises coupling field orientation control, load feedback control and dynamics feedback control. High-precision and high-efficiency forming of the thin-wall high-rib component is achieved, and the forming precision can be guaranteed on the premise that the forming speed is increased.

A vibration component decomposition and resonance region identification method based on blade tip timing raw data relates to the field of blade vibration state monitoring. In order to solve the defects of existing blade tip timing test methods that cannot realize online analysis and cannot automatically identify resonance regions, the present invention adopts a blade tip timing probe to obtain blade tip timing data; by subtracting the actual arrival time of the rotating blade from the theoretical time, and combining the rotation speed of the rotating blade tip to obtain the vibration displacement of the rotating blade tip position: construct a blade tip vibration signal model, select the blade tip timing signal for sparse auxiliary decomposition, set optimization parameters and the maximum number of iterations, and obtain the decomposition results of synchronous vibration signal components and asynchronous vibration signal components; perform automatic identification of resonance regions, and obtain the regional identification results of synchronous resonance and asynchronous resonance respectively. The present invention is mainly used for online analysis of blade tip timing raw data and automatic resonance region identification.

The application relates to a power grid application layer instruction level detection method fusing control service logic. For power grid application layer instruction level detection, a rule matching-based method is used to detect abnormal messages and attack messages; abnormal message rules are designed according to protocol specifications, and a mature snort network attack rule library is used as an attack message feature library; for the discrete characteristics of service feature values, an abnormal detection technology based on clustering learning is proposed to realize abnormal identification of service instruction frequencies and service feature codes.

The invention discloses an online identification method of dq impedance of an MMC type direct current ice melting device. The method comprises the following steps: connecting the MMC type direct current ice melting device to a power grid via a multi-frequency voltage disturbance source, setting the disturbance source frequency, phase and amplitude parameters, and collecting voltage and current data of a grid-connected point of the direct current ice melting device after the disturbance source is connected; establishing a dual-input and dual-output dq impedance identification model, giving the initial order and parameters of the model, and adopting a recursive least squares algorithm to perform impedance identification; calculating the error between the output voltage of the model and the actual collected voltage under the current order and parameters, and if the error is greater than a given threshold, updating the model order, repeating step 2 to form an iteration until the error is less than the given threshold, and outputting the impedance identification result; the method can meet the demand for fast and accurate impedance identification at an actual engineering site; effectively carrying out stability analysis of the connection of the MMC type direct current ice melting device to a power grid, and also providing basic data support for actual engineering scenarios such as setting value calculation of a relay protection device and device operating condition evaluation.

The application discloses a heavy mass and equivalent offset state joint identification method based on q-axis current steady-state and dynamic characteristics, belongs to the technical field of gravity energy storage system state perception and motor control, and comprises the following steps: collecting three-phase currents of a permanent magnet synchronous motor and obtaining q-axis currents through coordinate transformation, simultaneously acquiring a reel mechanical angle, a motor angular velocity and a heavy mass running speed; extracting q-axis current steady-state components in a uniform speed steady-state window, combining a motor torque model to estimate the heavy mass and equivalent friction; calling a baseline model to obtain offset related residuals after inertia compensation of the q-axis current, extracting mechanical synchronous order amplitude after conversion to the reel mechanical angle domain, constructing a normalized offset feature, and outputting an equivalent offset or an unbalanced load risk index; and using the identification result for power correction, heavy mass scheduling, unbalanced load early warning or maintenance decision making. The application simultaneously realizes online identification of the heavy mass, equivalent friction and equivalent offset state by using motor current signals, has less dependence on hardware, and has low modification cost.