8 results about "MRAS" patented technology

The invention provides an MRAS permanent magnet synchronous motor parameter online identification method based on BP neural network optimization, and the method comprises the steps: constructing two BP neural network models, carrying out the offline training optimization of the two models, and obtaining an optimal neural network model which can accurately predict the flux linkage of a rotor and the inductance of a stator; based on an MRAS step-by-step identification strategy, two-stage motor parameter step-by-step identification units are built, the two optimal neural network models are embedded into the corresponding motor parameter step-by-step identification units, and based on the problem that the stator resistance identification effect of the BP neural network is poor, the two optimal neural network models are embedded into the corresponding motor parameter step-by-step identification units; according to the invention, the BP neural network and the adaptive rate unit are established in the second MRAS parameter identification unit, and the online dynamic identification of the stator resistance and the stator inductance is realized through the combination of the BP neural network and the adaptive rate unit. According to the method, an off-line training-on-line identification mode is adopted, the complex parameter setting process in a traditional method is avoided, the identification efficiency is remarkably improved, and the identification result is accurate.

The invention relates to the field of molecular diagnosis and tumor risk assessment, in particular to a marker combination and a kit for assessing the lymphatic metastasis risk of cervical cancer and application of the marker combination and the kit. The marker comprises a group of gene markers and a group of microbial markers, the gene markers comprise CARD9, MNX1AS2, MRAS, OLFML2A and RPS28, preferably, the gene markers further comprise at least one of CFL1P1 and GRASLND, and the microbial markers comprise microorganisms of the genus Dialister, the genus Catonella and the genus Campylobacter. The marker provided by the invention can be used for constructing an accurate risk assessment model, and can be used for developing a corresponding PCR (Polymerase Chain Reaction) kit, a mass spectrum or a chromatographic analysis system to realize metastasis risk prediction, curative effect assessment and new drug screening of cervical cancer patients.

The present invention provides a method and a model based on transcriptome and intratumoral microorganisms, specifically relating to a computational model for evaluating the risk of lymph node metastasis in cervical cancer and related methods, programs, systems and devices. This model integrates the abundance information of multiple gene markers (including CARD9, MNX1_AS2, MRAS, OLFML2A and RPS28) and multiple microbial genera (including Dialister, Catonella and Campylobacter) as input features, and constructs a risk prediction model through machine learning algorithms, so as to realize the quantitative evaluation of the risk of lymph node metastasis in cervical cancer patients. The present invention improves the prediction accuracy of lymph node metastasis in cervical cancer, provides a basis for clinical auxiliary diagnosis and decision-making, and has important medical application value and industrial transformation potential.

The invention relates to the field of tumor biomarkers, and relates to a cervical cancer lymph node metastasis marker and application thereof, in particular to a marker for evaluating the risk of cervical cancer lymph node metastasis and a combination, a detection reagent, a kit and application thereof. According to the invention, seven key molecules related to cervical cancer lymphatic metastasis, including RCARD9, CFL1P1, GRASLND, MNX1AS2, MRAS, OLFML2A and RPS28, are screened and verified for the first time, can be used as a single marker or a combination of a plurality of molecules, and are suitable for constructing a molecular diagnosis tool for evaluating the risk of cervical cancer lymphatic metastasis. The marker can also be used for evaluating the effect of drugs on inhibiting cervical cancer lymph node metastasis or screening drugs. The invention provides a molecular means with high sensitivity and high specificity, which is helpful for assisting clinical individualized treatment decision.

The invention discloses a sensorless model prediction speed control method for a synchronous reluctance motor. The method comprises the following steps: firstly, establishing a mathematical model of the synchronous reluctance motor; then constructing a model reference adaptive system; an improved adaptive law combining mechanical and electromagnetic models is constructed; and deducing a linearization model, and performing linearization approximation on the IAL-MRAS error system containing a nonlinear feedback link near a working point to obtain the linearization model and a transfer function of the IAL-MRAS error system. And finally, establishing a prediction model to obtain a stator current prediction value and a flux linkage prediction value, and performing switching vector optimization through a cost function. By systematically improving the speed / position estimator, the dynamic performance of sensorless driving of the synchronous reluctance motor is improved.

The invention discloses a variable step size model reference adaptive (MRAS) multi-parameter identification algorithm, and relates to the field of parameter identification of motor control. According to the method, the problem of under-rank of a traditional MRAS method during multi-parameter identification is solved, the defect that precision errors exist in the traditional method under the complex working condition that motor inductance and permanent magnet flux linkage change at the same time is overcome, and a variable-step-size MRAS multi-parameter identification algorithm is provided. In order to solve the problem that a traditional MRAS parameter identification algorithm is under-rank when identifying three parameters, the invention designs a variable step size MRAS multi-parameter identification algorithm capable of identifying d-axis inductance Ld, q-axis inductance Lq and flux linkage psi f of a motor at the same time, the algorithm combines two sections of MRAS structures in a cascade form, adopts a frequency-division variable step size design, and can identify the three parameters of the motor at the same time. According to the method, convergence is ensured by reasonably distributing the identification frequency of two sections of algorithms, a periodic variable step size strategy is provided to stabilize the identification process, and on the basis of simultaneously identifying three parameters of d-q axis inductance and flux linkage, the calculation efficiency is improved, and the identification error is reduced. Compared with a traditional method, the variable-step MRAS multi-parameter identification method has the advantages that the control precision, efficiency and robustness of the algorithm are improved to the greatest extent, more reliable parameter support is provided for motor control, and the anti-interference capability of the motor in special scenes such as parameter fluctuation is improved.

SENSORLESS MOTOR SPEED ESTIMATION DEVICE USING Δ-MRAS WITH IMPEDANCE ANGLE REFERENCE

The application discloses a kind of winding segmentation linear permanent magnet synchronous motor's position sensorless control method, first according to the coupling relationship of two adjacent stator and rotor, establish double-section composite equivalent model;Then MRAS reference model and adjustable model are constructed based on composite equivalent model;Third, the LESO observer of the dq axis lumped disturbance formed by parameter drift, inverter nonlinear error and load disturbance is established;Further, the disturbance estimation value output by LESO is fed forward to the adjustable model of MRAS, and a composite equivalent model LESO-MRAS observer is formed;Finally, the speed and position estimation value output by the observer is used to realize closed-loop position sensorless control.The application can significantly weaken the influence of position-sensitive parameters on position sensorless control, improve the speed, position estimation accuracy and system disturbance robustness in the full stroke range, especially in the transition area between sections.