70results about How to "Few adjustable parameters" patented technology

The invention relates to a cement decomposing furnace temperature control method based on constraint smith GPC, which includes variable selection, model recognition, optimizing computation, constraint processing and feedforward compensation; the variable selection includes that: coal powder flow is selected as a control variable, raw flow is selected as the feedforward variable and the decomposing furnace temperature is selected as the controlled variable; the model recognition includes that: the model recognizer based on least square method and retardation time estimation time is adopted to obtain a pulse transfer function model; the optimizing computation includes that: the future output state is predicated and the reference track w of the output value is also set; a secondary performance index controller is adopted for the rolling optimization, the control increment Delta u of the current time is computed to obtain control action value u through addition; the constraint processing includes that: the control variable and controlled variable are respectively performed with constraint amplitude limiting processing; the feedforward compensation includes that: the dynamic compensation principle is utilized to compute the current time t added to the feedforward control action value ud. The invention has simple recognition process, less adjustable parameters, good tracking performance, strong robustness, effectively refrains the disturbance influence caused by raw material flow and prevents saltus step of the system variable.

The invention discloses a combustion optimization control method for a boiler. The combustion optimization control method is characterized by comprising the following steps: sampling a combustion nonlinear system of the boiler to obtain input/output data at the current moment; training the real-time sampled input/output data by an online incremental learning fuzzy neural network, building an online incremental learning predicting model of the combustion nonlinear system of the boiler; performing a nonlinear prediction control algorithm on the online incremental learning predicting model for realizing the optimization and the control of the combustion process of the boiler. According to the combustion optimization control method for the power station boiler of the online incremental learning fuzzy neural network, the nonlinear optimization problem in the predication control algorithm is solved by utilizing a particle swarm optimization algorithm through the online identification of the boiler combustion optimization model; the real-time optimization and control of the boiler combustion process are realized.

The invention particularly relates to a design and setting method for an active disturbance rejection control system of a time delay system. According to the method, based on the active disturbance rejection technology, firstly, complex controlled objects are fit into a one-order inertial element plus dead time delay mathematic model, meanwhile, time delay comes down to the disturbance quantity, a time delay reduction linear extended state observer is applied to estimation of unknown total disturbance including the time delay, active compensation for the influences of the total disturbance on the system is achieved, the time delay system is restored into a system in an integrator tandem type in an ADRC standard, and then compensation for the time delay system is achieved; finally, a closed-loop transfer function of the system is deduced, a dead time delay link in a characteristic equation is eliminated, and the numerical relationship between an ADRC single-parameter setting formula with universality and adjustable parameters is correspondingly provided. The simulation result verifies that designed practical ADRC has good stability, rapidity, accuracy and disturbance rejection.

The invention relates to a human face expression identification method, in particular to a convolutional neural network-based human face expression identification method. The method comprises the steps of firstly obtaining human face images from a video, performing scale normalization operation processing on the obtained human face images to obtain human face images same in size, and performing alignment preprocessing operation on the human face images same in size to obtain preprocessed human face images; and performing feature extraction operation on the preprocessed human face images by using a convolutional neural network to obtain features of the human face images, and performing classified identification operation on the features of the human face images by utilizing a Softmax classifier. A human face expression identification algorithm realized by utilizing the convolutional neural network is an end-to-end process. According to the method, the human face images only need to be simply preprocessed and then fed into the convolutional neural network, the feature extraction is automatically performed, and a classification result is given, so that the accuracy is greatly improved, adjustable parameters are reduced, and intermediate processing steps are simplified to a great extent.

The invention discloses a weighted least square support vector machine-based soft measurement method for magnetic flux linkage of a bearingless permanent magnet synchronous motor. The method comprises the following steps of: selecting a rotor position angle, torque winding current, levitation force winding current and rotor eccentric displacement of the bearingless permanent magnet synchronous motor as four input variables of a bearingless permanent magnet synchronous motor magnetic flux linkage soft measurement model, wherein the magnetic flux linkage y is taken as an input variable; acquiring representative input variable sample data and output variable sample data, performing normalization preprocessing on both the output variable and the input variables, and forming a modeling sample set for corresponding normalized values; performing residual analysis on the modeling sample set to acquire each sample weight; training the modeling sample set and establishing a bearingless permanent magnet synchronous motor magnetic flux linkage correlation model by using a weighted least square support vector machine; and finally abnormalizing an sy value to acquire the magnetic flux linkage y. Thus, the magnetic flux linkage value of the bearingless permanent magnet synchronous motor is predicted and controlled on line in real time.

The invention discloses a nonlinear model predictive control method based on support vector machine for groove type reactor, which consists of support vector machine open loop identification circuit and closed-loop control circuit, the vector machine comprises support vector machine and its black box identifier, a controlled member groove type reactor, an internal prediction model, a feedback calibration and closed-loop output, a non-linear controller design, and a reference track, wherein the support vector machine identifies the non-parameter internal forecast model of the groove type reactor, obtains the closed-loop output through model output error for feedback calibration, and calculates the single step and multi step forecasting and analyzing control rule exerted to the system.

The invention provides a traffic simulation software parameter calibration method and system based on a learning algorithm, and a medium, and the method comprises the steps: A, carrying out the preliminary screening of parameters, carrying out the sensitivity analysis of the screened parameters, obtaining a first to-be-calibrated parameter meeting a preset requirement, and collecting a training data set; b, according to the obtained first to-be-calibrated parameters and the training data set, carrying out neural network model training, and obtaining a trained neural network model; and C, performing particle swarm optimization according to the obtained trained neural network model. The method provided by the invention can efficiently find the optimal parameter suitable for the current roadnetwork, and is suitable for practical application.

The invention discloses an extreme value optimization self-adjusting digital PID control method used for a megawatt inverter system. According to the method, a model input signal and a system error signal of the megawatt inverter system and an adjustable parameter initial value serve as digital PID controller input. The control parameter Kp, the control parameter Ki and the control parameter Kd of a PID controller are encoded into a binary sequence, iterative optimization is carried out on the binary sequence through a binary encoding extreme value optimization solver until an end condition preset by a project planner is met, so that an optimal binary sequence is automatically adjusted, converted into a PID controller optimum control parameter through the binary encoding and then transmitted to the megawatt inverter system, and real-time on-time optimal control is achieved. Compared with an engineering adjusting method based on an empirical rule, the extreme value optimization self-adjusting digital PID control method has the advantages that the PID controller parameter can be adjusted on line and optimized in real time. Compared with a genetic algorithm and other intelligent optimizing methods, the extreme value optimization self-adjusting digital PID control method is less in number of adjustable parameters, simpler in implementation, and higher in optimizing efficiency.

The invention discloses a heuristic gain adaptive PID control method for a complex nonlinear pumped storage power unit speed regulating system. First, a heuristic gain adaptive PID controller is set up based on a simple and practical parallel PID control structure; then, a fine model of a nonlinear pumped storage power unit speed regulating system is constructed; next, a multi-objective function of nonlinear pumped storage power unit speed regulating system HGS-NPID control parameter optimization is built; and finally, nonlinear pumped storage power unit speed regulating system HGS-NPID control parameters are optimized using a multi-objective artificial sheep flock algorithm. The heuristic gain adaptive PID control method for a nonlinear pumped storage power unit speed regulating system presented by the invention is simple to implement, and has strong real-time performance. The control gain can be adjusted online and adaptively according to the change of the operating point. The method fully adapts to the hydraulic shock and nonlinearity of the pumped storage power unit speed regulating system, and can improve the dynamic quality of the conventional control method under different working conditions of a water head.

The invention discloses a double-assistance circular spherical steering system and a control method thereof. The system comprises a steering wheel, a steering tubular column, a torque sensor, a segment gear, a bidirectional gear and worm reducing mechanism, a steering rocker arm, a steering transverse pull rod, wheels, a vehicle speed sensor, a yaw velocity sensor, an electronic control unit and a left-right assistance motor. In a running process, the electronic control unit acquires signals of the torque sensor, the yaw velocity and the vehicle speed, difference between the perfect yaw velocity and the actual yaw velocity is calculated, the compensation torque of the double-assistance motor is recalculated by a designed adaptive fault-tolerant controller, and a ECU transmits pulse to control running of the adaptive fault-tolerant controller to finish control on stability of an automobile under the normal condition and under the condition that an actuator fails partially. Adaptive fault-tolerant control on the double-assistance circular spherical steering system can be realized, and reliability of the steering system and stability and safety of the automobile during running are improved.

The invention provides an intelligent detection and yield optimization method for an HDPE (high density polyethylene) cascade polymerization reaction course, which solves the problems that the HDPE cascade polymerization reaction course is complicated in technology, on-line measurement of a key quality variable is difficult, and the operating cost of a production course is high. The method comprises the steps of preprocessing by adopting data correction and data excavation techniques, searching a rule from production and analysis data, adopting an artificial neural network technique to establish an intelligent soft measuring instrument and a polyethylene product unit consumption model, and adopting an extension engineering technique to optimize an artificial neural network structure and improve the neural network modeling accuracy. The method has the characteristics of high response time, high modeling accuracy, high inferential capability and convenience in management, and assists in ensuring safe production of HDPE, improving the quality of a polymer product, and saving the production cost.

The invention discloses a power transformer fault diagnosis method and device. The method comprises the steps that: after dissolved gas analysis (DGA) data in power transformer oil is obtained, faulttype identification on a fault sample is carried out through a support vector regression-variable prediction model (SVR-VPMCD); firstly, ratios of all kinds of gas in the total gas content are selected as various characteristic values, so that corresponding characteristic vectors are formed; then, polynomial response surface regression in VPMCD is replaced by SVR; variable prediction models (VPMs)corresponding to various fault types are constructed by utilization of a training sample; finally, each test sample is predicted by sequential utilization of the constructed VPMs of all kinds of faults; and the fault type corresponding to the VPM having the minimum prediction error is the fault type of the test sample. The SVR-VPMCD method sufficiently considers mutual correlation among various characteristic values, and overcomes the disadvantage that the VPMCD method has poor processing capability to high-dimensional data; therefore, the identification precision of the mode identification method on the sample type is increased; and the method has good small sample data identification capability.

The invention belongs to the radar technology field and particularly relates to a target feature extraction method used for a synthetic aperture radar. The target feature extraction method combines peak value area segmentation of an image domain and sparse Bayes learning of a signal domain to perform feature extraction, segments a strong scattering area through an PRS algorithm in order to avoid an effect on an SBL algorithm by strong scattering points, uses the SBL algorithm to autonomously study to extract weak scattering featurepoints to compensate insufficient segmentation on an weak target by the PRS algorithm based on the image domain. The target feature extraction method uses the advantages of the PRS algorithm and the SBL algorithm to show a good effect in weak object feature extraction and is less in adjustable parameters and strong in robustness. After the PRS algorithm segments the strong scattering area, the number of dimensions of a measurement matrix is reduced, which reduces computation burden and improves calculation efficiency. As a result, the target feature extraction method can be widely applied to the SAR object feature extraction field and provides a basis for a follow-up automatic target recognition.

The invention discloses a complete time delay compensation control method for a chemical engineering multi-variable process. According to the control method, a control module which is used for controlling the multi-variable process to make the same meet the requirements of control indexes, a decoupling module which is used for decoupling the multi-variable processes into a plurality of independent individual variable objects, and a feedback control module which is used for rendering estimated feedback information and increasing the robustness of a system are adopted. With the complete time delay compensation control method of the invention adopted, the deficiency of incapability of a traditional control method to realize complete time delay compensation can be eliminated; (2) reverse decoupling is adopted, and the realization form of a decoupler is simple; and a filter is additionally installed in the feedback control module, so that the robustness of the system can be improved. As for the multi-variable process, the complete time delay compensation control method can realize effective control and can be popularized.

The invention relates to the technical field of infrared spectrum wavelength, and concretely relates to a convex optimization theory-based novel infrared spectrum wavelength selection method. The method is a self-adaptive wavelength selection method adopting a Group Lasso technology without knowing spectrum partitioning priori knowledge. An infrared spectrum wavelength screening problem is converted into a Group Lasso sparse optimization problem, the sparse structure priori knowledge of the infrared spectrum is fully used to self-adaptively determine the partitioning size, a Shooting rapid algorithm is adopted to calculate the sparse solution, and Belsley colinearity examination of the sparse solution is carried out on the sparse solution to reject wavelength points with small contribution. The method has the advantages of small calculation capacity, few adjustable parameters and strong robustness, can effectively reduce the complexity of a model and improve the generalization performance of the model, and can be widely used in the field of infrared spectrum wavelength selection of a solid phase, a liquid phase and a gas phase.

The invention belongs to the field of damper performance testing devices and specifically discloses a parameter adjustable squeeze oil film damper performance testing device which comprises a false shaft, an oil film assembly and a supporting base. The oil film assembly includes an oil film inner ring and an oil film outer ring. The oil film inner ring is sleeved on an outside of the false shaft,and is matched with the false shaft through a tapered surface. The oil film outer ring is sleeved on one end, positioned near the false shaft, of the oil film inner ring; the oil film outer ring cooperates with the oil film inner ring to form an oil film gap, the oil film outer ring is connected to the supporting base through an oil film outer ring support member, and the oil film outer ring support member is provided with an oil inlet hole; a rigidity adjustable elastic rod is disposed between the oil film outer ring support member and one end, positioned away from the false shaft, of the oilfilm inner ring. The elastic rod is provided with a left adjusting check ring and a right adjusting check ring that are adjustable in position, an oil outlet hole is formed on the supporting base andis sleeved outside the oil film inner ring. The testing device disclosed in the invention can provide different test rigidity variables and different oil film thickness and width variables; the testing device is advantaged by adjustable test conditions, a large quantity of test conditions, rich test measurement parameters and the like.

The invention relates to the technical field of infrared spectra, in particular to an infrared spectrum wavelength selection method based on integrated L1 regularization, and the infrared spectrum wavelength selection method uses the integrated learning thought; the infrared spectrum wavelength selection method based on integrated L1 regularization comprises the steps that firstly, a plurality of sub data sets are generated with a Bootstrap sampling method, then each sub data set is subjected to feature selection with an L1 regularization method, a feature selection problem is converted into a sparse optimization problem and then calculation is performed, and finally, wavelength selection results of each sub data set are integrated with a voting method, so that an optimal feature wavelength combination is screened; the infrared spectrum wavelength selection method based on integrated L1 regularization is mainly applied in the infrared spectrum aspect.

The present invention provides a continuous sterilization and repetition learning self-adaptive controller on the basis of characteristic model including a characteristic model identifying module, an overall coefficient control law module, a repetition learning feed-forward module, and an overhead control quantity calculating module. The characteristic model identifying module acquires the temperature of the culture medium at the current steam ejector outlet and the steam valve opening so as to obtain identifying parameters, and the overall coefficient control law module receives the identifying parameters and the error of the temperature of the culture medium and the reference temperature so as to obtain the feedback control quality. The repetition learning feed-forward module constructs and updates a feedback lookup table. The overhead controlled quantity calculating module obtains the current steam valve opening according to the feedback control quality and the feed-forward control quality. The continuous sterilization and repetition learning self-adaptive controller on the basis of characteristic model constantly optimizes the lookup table by repetition learning so that the turbulence of measurable fast variables, such as material inlet temperature and material flow, can be eliminated, and the influence of the measurable fast variables during the continuous sterilization process can be reduced. The continuous sterilization and repetition learning self-adaptive controller on the basis of characteristic model is strong in robustness and is simple in realization.

The invention discloses a built-in permanent magnet synchronous motor anti-interference controller and a design method thereof. The controller comprises a controller unit, a nonlinear observation unitand an execution unit. The designed anti-interference controller does not depend on an accurate mathematical model, and the overshoot problem is solved. It can be known from the simulation tracking effect that no overshoot phenomenon occurs. The designed nonlinear observation unit has the characteristic of higher response speed. The number of adjustable parameters is reduced to two, and the complexity of parameter adjustment is greatly reduced through the design of the nonlinear observation unit by adjusting the parameters beta and delta. According to the nonlinear observation unit, externalload disturbance and internal uncertain parts of the built-in permanent magnet synchronous motor are used as total disturbance. The built-in permanent magnet synchronous motor can accurately observe and estimate the total disturbance, speed and position, the simulation result shows that good tracking performance can be realized. The dynamic performance and anti-interference capability of the built-in permanent magnet synchronous motor are improved. The built-in permanent magnet synchronous motor is beneficial to the application in a control servo system.

A vehicle variable-speed cruise control method under wireless communication channel attenuation includes the following steps: 1) establishing a third-order dynamic mathematical model of vehicle variable-speed cruise control; 2) defining x1=[beta1, beta1<.>, alpha1]<T> to obtain a vehicle variable-speed cruise control system state space model; 3) defining the vehicle distance, the speed and the acceleration control function of the variable-speed cruise system at the time t under the wireless communication channel attenuation; 4), giving real numbers rho1 and lambda, solving a real matrix P=P<-><T>>= 0, Q<->=Q<-><T>>= 0 and V to satisfy a linear matrix inequality; and 5) obtaining a distance difference and a speed difference between a host vehicle and a vehicle ahead, and the acceleration ofthe vehicle ahead, calculating the acceleration, the speed and the distance control amount of the host vehicle in real time, driving the host vehicle to follow the motion state of the vehicle ahead,and repeating the process to achieve vehicle variable-speed cruise control with high real-time performance and high accuracy under the wireless communication channel attenuation. The method considersthe channel attenuation characteristics of the vehicle during driving, thereby well achieving a vehicle variable-speed cruise control target.

The invention discloses a phase lead linear active disturbance rejection controller of a permanent magnet synchronous linear motor platform, and belongs to the technical field of control engineering.The purpose of the invention is to provide the phase lead linear active disturbance rejection controller of the permanent magnet synchronous linear motor platform, so by adopting a mode of improving feedback control rate by using a lead compensation loop, the system bandwidth is expanded, the problem of phase lag of an extended state observer in traditional linear active disturbance rejection control is solved and tracking precision and the anti-interference capacity of the system is improved. According to the invention, a conventional three-order linear extended state observer is designed fora mathematical model of the second-order permanent magnet synchronous linear motor; a phase lead feedback controller is designed for the second-order integral model of the controlled object after disturbance estimation and compensation; and the parameters of the phase lead linear active disturbance rejection controller are adjusted by utilizing the accurate estimation of the linear extended stateobserver on the total disturbance and the real-time compensation characteristic of the phase lead PI feedback controller on the total disturbance until an expected control effect is achieved. According to the invention, the estimation speed and precision of total disturbance are improved, and an expected control effect is obtained.

The invention relates to a universal station scheduling method and device for an adaptive disturbance quantum particle swarm. The method comprises the following steps: establishing an energy efficiency model, setting algorithm parameters, and initializing particle positions; constructing a target function, calculating fitness Fitness of each particle according to the target function under an initial condition, and determining and recording an individual optimal position Pbest of each particle, a global optimal position gpbest of a group and an optimal median position S (t) according to a particle swarm optimization algorithm; updating the particle speed, recalculating the fitness Fitness of the particles, and updating the individual optimal position pbest of the particles, the global optimal position gpbest of the population and the average optimal position S(k); judging whether the algorithm meets a termination condition or not, if so, outputting an optimal scheduling result, otherwise, calculating an average fitness deviation delta of the group, judging whether delta is smaller than a threshold value or not, and if not, repeating the process; otherwise, executing disturbance operation on the group and then repeating the process. The method effectively reduces the engineering application cost.