320results about How to "Improve convergence speed" patented technology

The invention discloses a cascaded residual error neural network-based image denoising method. The method comprises the following steps of building a cascaded residual error neural network model, wherein the cascaded residual error neural network model is formed by connecting a plurality of residual error units in series, and each residual error unit comprises a plurality of convolutional layers, active layers after the convolutional layers and unit jump connection units; selecting a training set, and setting training parameters of the cascaded residual error neural network model; training the cascaded residual error neural network model by taking a minimized loss function as a target according to the cascaded residual error neural network model and the training parameters of the cascaded residual error neural network model to form an image denoising neural network model; and inputting a to-be-processed image to the image denoising neural network model, and outputting a denoised image. According to the cascaded residual error neural network-based image denoising method disclosed by the invention, the learning ability of the neural network is greatly enhanced, accurate mapping from noisy images to clean images is established, and real-time denoising can be realized.

The method comprises: creating a air-way planning model of a unmanned combat air vehicle (UCAV); using a shortest air-way and minimum detectable air-way weighted method to compute the cost function used as the performance index of describing the air-way; after using ant swarm intelligence to find the current candidate path node for the UCAV, using the satisficing-decision making principle to evaluate the satisficing degree of each candidate path node so as to select the satisfied candidate node; meanwhile, using a 'wheel of fortune' modified policy to improve the global search capacity of the algorithm; after each ant completes the selection of its own candidate air-way, making a overall correction for the biological information elements at each side.

The invention discloses a BP neutral network heavy machine tool thermal error modeling method optimized through a genetic algorithm. Through the establishment of the structure of a BP neutral network, global optimization is conducted on the initial weight and threshold of each layer of the BP neutral network through a training sample. After the error objective is set, global optimization is conducted on the initial weight and threshold of the BP neutral network structure through the genetic algorithm, and the optimal weight and threshold found by the genetic algorithm is substituted into the BP neutral network to be conducted with sample training. Based on the decline principle of the error gradient, quick search is conducted near the extreme point until the training is end and thermal error prediction model is obtained. Finally, robustness testing is conducted on the obtained thermal error prediction model. The global optimization is conducted on the initial weight and threshold of the BP neutral network structure through the utilization of the genetic algorithm, the self-characteristics of the BP neutral network is overcome, and the quickness, the accuracy and the robustness of convergence when the optimal weight and threshold is trained can be improved.

The invention relates to a default performance formation controller structure for multi-mobile robots and a design method. N double-mobile robots containing unknown dynamic states are regarded as followers, the networked system formed by connecting the followers with a leader through a one-way topological graph is regarded as a controlled object, and a time-varying formation controller with default performance is designed by using the active-disturbance-rejection and inverse techniques, so that the following robots track the reference trajectory of the leader and build and keep a desired time-varying rank, and the tracking error is within a preset range. The default performance formation controller structure has the advantages that according to the characteristic that an extended state observer is independent of a precise mobile robot model, the unknown dynamic states are compensated through estimation of the extended state amount in real time, so that the designed time-varying formation controller has a disturbance rejection capacity; the derivative of a complicated nonlinear function is effectively estimated by means of a tracking differentiator; the convergence precision and rate of a formation error are improved by using a default performance function; the problems about the unknown dynamic states, complicated derivation reduction and precision control in a system can be effectively solved.

The invention provides a transmission and distribution coordinated distribution type reactive voltage optimizing method, and belongs to the technical field of electrical power system operation and control. The method comprises the following steps: constructing a transmission and distribution combined reactive optimal model formed by a target function and a constraint condition by comprehensively taking the coupling relationship among a transmission network model, a distribution network model and transmission-and-distribution into consideration; then, performing second-order cone relaxation on a non-convex constraint of a distribution network, and converting the non-convex constraint into convex constraint; solving the model by applying an improved generalized Benders decomposition method. The method only needs to interact a small amount of information between the transmission network and the distribution network, has an excellent convergence speed, ensures the scheduling and controlling independence of transmission and distribution, can be used for solving the problems of overvoltage, power dismatching and the like caused by a traditional transmission and distribution independent reactive optimizing method, and can achieve optimal loss of the whole local network.

The invention provides an indoor evacuation simulating optimization method based on a potential energy driving cellular ant colony algorithm. The method is a personnel evacuation behavior simulating optimization method based on colony intelligence, a two-dimensional cellular automaton mathematic model in accordance with an actual scene is mainly built, personnel evacuation behaviors are simulated by using the cellular ant colony algorithm, and personnel paths are judged and selected according to a potential energy evaluation criterion of an artificial potential energy field, so that the method is more consistent to a true scene evacuation rule, the evacuation efficiency is improved, and a reasonable evacuation scheme is provided.

A conventional hill climbing method is not capable of tracking a maximum power when a shadow covers a part of a solar cell panel and a plurality of maximal values is thereby developed. The invention provides a photovoltaic power generation system control method that controls a photovoltaic output setting value to be an appropriate value by following up a variation in the solar irradiation, including a genetic algorithm process of employing the photovoltaic output setting value as a gene and the output power as an evaluation value thereof; randomly extracting a plurality of genes and repeating storage, selection and crossover/mutation of the output powers which are the evaluation values of the genes, so as to converge a difference between a maximum and minimum values of the output voltages into a predetermined range; and a hill climbing process of setting the photovoltaic output setting value corresponding to the greatest value of the converged output voltages, and a greater and a lower value than the photovoltaic output setting value by a predetermined amount, so as to select the greatest output power among these values; and repeating such steps to track the maximum output power.

The invention discloses a nonlinear modeling method and a linear trimming method for a composite rotor aircraft, and belongs to the technical field of control of composite rotor aircrafts. According to the method, the aerodynamic characteristics of all parts are analyzed, and a split modeling method is adopted to carry out dynamic modeling; on the basis of the model, combined with a quasi-Newton iteration method and a sequence quadratic programming method, a quasi-Newton-sequence quadratic programming method is proposed to dynamically balance the dynamic model of the composite rotor aircraft and make small disturbance linearity at the equilibrium point, so that an approximate linearized kinetic equation for the equilibrium point can be obtained. The dynamic model established by using the modeling method disclosed by the invention is high in confidence coefficient and simple in calculation, in addition, the new trimming method provided by the invention can avoid solving the inverse matrix of the objective function Hessian matrix, the calculation is simplified, the relatively high convergence speed is ensured, and the method can be used for researching the control method of the composite rotor aircraft.

The invention discloses a pedestrian re-recognition method based on migration learning. The pedestrian re-recognition method includes the steps of 1) preprocessing pictures in a data set by using a multi-scale Retinex color image enhancement algorithm to remove the influence caused by illumination; 2) concentrically extracting relevant features of pedestrians from the preprocessed data set; 3) establishing an asymmetric multi-task discriminant model; 4) refining the model by using a flow-shaped structure without label data; 5 ) optimizing the objective function by using a conjugation gradientmethod to obtain a final classifier; and 6 ) testing the pedestrian re-recognition rate on the classifier based on the pedestrian re-recognition standard database. Few label data and the label-free data are reasonably applied, and the model obtained through training can well improve the pedestrian re-recognition rate.

The invention relates to a power transmission network and power distribution network coordinated dynamic economy scheduling method based on multi-parameter planning, which belongs to the technical field of electric power system operations. With the comprehensive considerations of the dynamic economy scheduling models of the power transmission network and the power distribution network as well as the coupling relationship between the power transmission network and the power distribution network, the power transmission and distribution coordinated dynamic economy scheduling model is established. For the proposed power transmission and distribution coordinated dynamic economy scheduling model, a multi-parameter planning theory is utilized and an iterative solving algorithm for the power transmission and distribution coordinated dynamic economy scheduling model is provided. The proposed algorithm possesses a good converging speed, suitable for the problem of power mismatching between the power transmission network and the power distribution network caused when renewable energy is accessed and can obtain the optimal solution to the global power transmission and distribution.

The invention discloses a particle swarm optimization based orthogonal wavelet blind equalization method. The method comprises the following steps of: allowing a transmitted signal a(k) to pass through a pulse response channel h(k) to acquire a channel output signal x(k); acquiring an orthogonal wavelet transformation (WT) input signal y(k) through channel noise n(k) and x(k); performing WT on the input signal y(k) to acquire an output signal R(k); taking the input signal y(k) as input of a particle swarm optimization (PSO) algorithm and randomly initializing a group of weight vectors, wherein each particle corresponds to each group of weight vectors one to one; determining a fitness function of PSO through a cost function of an orthogonal wavelet transformation-constant module algorithm (WT-CMA) blind equalization method; when a fitness value is the maximum, finding out an optimal position vector in the group and taking the optimal position vector as an initialization weight vector W(k) of the WT-CMA; and acquiring an equalizer output signal z(k) from the output signal R(k) and initialization weight vector W(k). In the method, the optimal equalizer initialization weight vector is sought through PSO, and the autocorrelation of the signal is reduced by WT. Compared with WT-CMA, the method has higher convergence rate and lower steady-state error.

The invention relates to a multi-energy complementary energy internet optimized dispatching method. A multi-energy complementary energy internet comprises a cold/heat storage unit, a power storage unit, an electric output device, a cold output device, a heat output device and a load demand side. The method comprises the steps that under a set control strategy, minimal system operation and maintenance cost, environment-friendly cost and comprehensive benefit cost are taken as a multi-objective function, and the constraint conditions comprise power balance constraints, power generation output power limit constraint and energy storage battery operation constraint, solving is carried out through a genetic algorithm based on self-adaptive crossover variation operation, and load optimization distribution of all equipment is obtained. Compared with the prior art, the method has the advantages that the peak shaving valley filling of an external power grid is promoted, and the load pressure ofthe power grid is relieved, so that the local consumption capacity of new energy in the area is improved, and the cleaning and high efficiency is truly achieved.

A robust adaptive filter for use in a network echo canceller or other digital signal processing application utilizes a coefficient vector update device that, through the application of fast converging algorithms to a fast impulse response filter yields fast convergence of the adaptive filter's characteristics with the avoidance of divergence due to the onset of double talk. Robustness is also provided, via an adaptive scale non-linearity device which applies an adaptive scale non-linearity to the filter algorithms fed to the fast impulse response filter by the coefficient vector update device, so that the samples of an echo signal to be cancelled which are taken during the onset of double talk can be handled in such a manner that after the double talk detector causes adaptation to cease, the initial, potentially disturbing samples do not cause significant divergence in the filter system.

The invention relates to a micro-grid economic and optimal operation and scheduling method based on an improved quantum genetic algorithm. The micro-grid is in a grid-connected mode operation state and comprises multiple micro sources and loads, wherein the loads comprise electric loads and thermal loads; and the micro sources comprise a micro turbine, a wind turbine, a photovoltaic cell, a fuel cell, a storage battery and an electric vehicle. The method comprises the following steps: S1, state information of each load and each micro source in the micro-grid is acquired; S2, with minimum of operation cost and pollutant treatment cost as a target, a multi-target economic scheduling model is built; S3, the improved quantum genetic algorithm is adopted for carrying out optimal solution on the multi-target economic scheduling model, and the optimal active power of each micro source is acquired; and S4, according to the optimal active power of each micro source, active power output by each micro source is controlled. Compared with the prior art, the micro-grid formed by distributed power sources operates in a more economic, flexible and environment-friendly mode, and power generation advantages of the distributed power sources can be taken.

The invention provides an electric power equipment infrared image real-time detection and identification method based on artificial intelligence. The method comprises the following steps of S1, acquiring infrared images of various types of electric power equipment through an infrared thermal imager; S2, preprocessing an acquired image to form an effective power equipment infrared image data set; S3, performing target label processing on the obtained data set; dividing the data set into a training set and a test set; S4, constructing an improved YOLOv4 real-time detection model for detecting and identifying an infrared image target of the power equipment; S5, training and parameter adjustment of the model are carried out by using a training set in the data set; and S6, performing target detection and identification on the trained model by using a test set in the data set to prove the effectiveness of the model; through the above steps, automatic detection and identification of infraredimages of various types of power equipment are realized; the accuracy degree of identification can be greatly improved, detection and identification efficiency is improved, and operation resources areeffectively utilized.

The invention discloses an intelligent steel cord conveyer belt defect identification method and an intelligent steel cord conveyer belt defect identification system. The identification method includes the following steps: (1) electromagnetic loading; (2) defect signal acquisition; (3) feature extraction; (4) training sample obtainment; (5) class priority determination; (6) multi-class model establishment; (7) multi-class model training; (8) real-time signal acquisition and synchronous class: electromagnetic detection units are adopted for real-time detection, detected signals are synchronously inputted into a data processor, features are extracted and then sent into established multi-class models, and the defect class of a detected conveyer belt is automatically outputted. The identification system comprises an electromagnetic loader, a plurality of electromagnetic detection units, the data processor and an upper computer, the data processor can automatically output the defect class of the detected conveyer belt, and the upper computer bidirectionally communicates with the data processor. The design of the invention is reasonable, the invention is easy to operate and convenient to put into practice, moreover, the using effect is good, the practical value is high, the reliability of conveyer belt defect detection is enhanced, and the efficiency of defect identification is increased.

A set of input images are acquired sequentially as image tensors. A low-tubal rank tensor and a sparse tensor are initialized using the image tensor, wherein the low-tubal rank tensor is a tensor product of a low-rank spanning tensor basis and corresponding tensor coefficients, and for each image, updating iteratively the image tensor, the tensor coefficients, and the sparse tensor using the image tensor and the low-rank spanning basis from a previous iteration. The spanning tensor basis is updated using the tensor coefficients, the sparse tensor, and the low rank tubal tensor, wherein the low rank tubal tensor represents a set of output images and the sparse tensor representing a set of sparse images.

The invention provides a sparse planar array optimizing method for energy transducers of a phased array sonar system. The method comprises the steps of 1) initialization, 2) simulated annealing optimization, 3) teaching and learning optimization and 4) termination. According to the method, the minimal number of energy transducers, which need to be exited to satisfy the spatial response performance, of the sparse planar array is solved by utilizing spatial response performances including the main-lobe width and the side-lobe peak value of the array. The feasible solution obtained by the simulated annealing optimization can be further optimized via teaching and learning optimization, so that higher convergence speed and precision are provided, the optimal solution of the whole situation can be obtained, as few as energy transducers work, the required spatial response performance of the planar array of the energy transducers is obtained, and the required hardware cost of the phased array imaging sonar system can be effectively reduced.

An apparatus for allocating resources to nodes in a communication system comprises an iteration controller (10) for performing an iterative processing, the iteration controller being configured for using (11) iteration resource weights to obtain a resources allocation result for an iteration step, and for updating (12) the iteration resource weights to obtain updated iteration resource weights for a further iteration step using a weighted combination of the resources allocation results for the iteration step and for at least one earlier iteration step.

The invention relates to an antenna array spare construction method based on a quantum glowworm search mechanism. The antenna array spare construction method comprises the following steps: establishing an antenna spare array model, and determining a key parameter, which corresponds to the quantum glowworm search mechanism, of the antenna spare array model; substituting a quantum glowworm position into a fitness function to obtain a fitness value of the quantum glowworm position, and confirming a local optimal position and a global optimal position in a glowworm group; updating the fluorescein value and the learning neighborhood of each quantum glowworm; updating a quantum glowworm quantum position and the quantum glowworm position; updating the dynamic decision domain radius of the quantum glowworm; calculating the fitness value under a new quantum glowworm position, and confirming the local optimal position and the global optimal position in a quantum glowworm group again; and if a maximum iteration is achieved, outputting the global optimal position, and mapping to obtain a spare antenna array form.

The invention relates to a decomposition-coordination scheduling method of pyroelectric combination system, and belongs to the power system operation technology field. By comprehensively considering a scheduling model of a power system and a scheduling model of a heat supply system, a pyroelectric combination optimization scheduling model is established. By aiming at the pyroelectric combination optimization scheduling model, and based on a Benders decomposition algorithm, the decomposition-coordination scheduling solution algorithm of the pyroelectric combination system is provided. According to the pyroelectric combination optimization scheduling decomposition-coordination algorithm, the scheduling mechanism of the power system and the scheduling mechanism of the heat supply system are only required to optimize internal systems under the control of the above mentioned two systems, and the global optimal solution of the pyroelectric combination optimization scheduling is acquired by interaction iteration of boundary conditions between heat and electricity. The decomposition-coordination scheduling method of the pyroelectric combination system has good convergence speed, and is capable of obviously improving the operation flexibility of the heat supply system.

The invention discloses an improved quantum genetic algorithm-based micro-grid energy storage locating and sizing optimization method. The method comprises the following steps: establishing an energy storage locating and sizing optimization model, wherein the energy storage locating and sizing optimization model comprises a target function formula and a constraint formula; improving a quantum genetic algorithm; and solving the energy storage locating and sizing optimization model by using the improved quantum genetic algorithm. According to the method, the energy storage locating and sizing optimization model is established, energy storage whole life cycle period cost, peak clipping-valley filling earning and grid loss earning are taken as targets, and the trend, energy storage charge-discharge and energy storage charge-discharge energy balance are constrained and considered; the quantum genetic algorithm is corrected, the dynamic adjustment strategy of a quantum revolving door revolving angle is used for improving the search efficiency, and a selection operation implemented by a simulated annealing method and a good point set cross operation can avoid local optimum; a 34-node micro grid is adopted to carry out verification so as to indicate that the disclosed algorithm is feasible, and the convergence efficiency of the quantum genetic algorithm and the ability of jumping out of local optimum are effectively improved.

The invention belongs to the technical field of inertial navigation and provides an initial alignment method of a static base of a rotary type strap-down inertial navigation system to overcome the problems of the existing initial alignment method that the calculation amount is great, the convergence rate and the convergence precision are not ideal. The method adopts a low-order Kalman filtering state equation model and a corresponding self-alignment appearance observation obtaining method to effectively reduce the calculation amount in an alignment calculation process; and furthermore, the Kalman filtering performance is optimized through rotating an IMU (Initial Measurement Unit), so that the initial alignment performance of the static base of the inertial navigation system is improved.

The invention relates to a multi-target operation scheduling method for a micro-grid with an electric vehicle hybrid energy storage system. The micro-grid runs in a grid-connection mode and comprises a plurality of micro-sources and loads, wherein the loads include an electric load and a heat load; and the micro-sources include a micro-gas turbine, a fan, a photovoltaic cell, a fuel cell, a storage battery and an electric vehicle. The method comprises the following steps of S1: obtaining state information of each load and each micro-source in the micro-grid; S2: establishing a multi-target economic scheduling model with minimum running and pollutant control costs; S3: performing optimization solving on the multi-target economic scheduling model by adopting an NSGA-II multi-target optimization algorithm to obtain optimal active power of each micro-source; and S4: according to the optimal active power of each micro-source, controlling active power output of each micro-source. Compared with the prior art, the method has the advantages that the micro-grid consisting of a distributed power supply can run more economically, flexibly and environmentally, and the power generation advantage of the distributed power supply can be brought into full play.

The invention discloses a fault diagnosis method for a PWM inverter of a motor drive system. The fault diagnosis method is characterized in that an inverter fault diagnosis model based on both wavelet packet decomposition and an RBF neural network is designed, wavelet packet transformation is utilized to extract a feature vector of a fault signal of the inverter, and the feature vector is taken as the input quantity of the RBF neutral network; a wolf pack-simulated annealing algorithm is adopted to optimize structural parameters of the RBF neutral network; and 22 groups of learning samples and 6 groups of test samples are utilized to train and examine the RBF neutral network. Simulation experiment analysis shows that when the fault diagnosis method is used for an open-circuit fault of the PWM inverter of a three-phase motor drive system, the fault position of an inverter TGBT power tube can be accurately positioned, fault diagnosis is quick, accurate and efficient, and the fault diagnosis method contributes to improving the running reliability of the motor drive system.