79results about How to "Strong local search ability" patented technology

The invention discloses a robust controller of a permanent magnet synchronous motor based on a fuzzy-neural network generalized inverse and a construction method thereof. The construction method of the invention comprises the following steps of: combining an internal model controller and a fuzzy-neural network generalized inverse to form a compound controlled object; serially connecting two linear transfer functions and one integrator with the fuzzy-neural network with determined parameters and weight coefficients to form the fuzzy-neural network generalized inverse, serially connecting the fuzzy-neural network generalized inverse and the compound controlled object to form a generalized pseudo-linear system, linearizing a PMSM (permanent magnet synchronous motor), and decoupling and equalizing the linearized PMSM into a second-order speed pseudo-linear subsystem and a first-order current pseudo-linear subsystem; and respectively introducing an internal-model control method in the two pseudo-linear subsystems to construct the internal model controller. The robust controller of the invention has the advantages of overcoming the dependence and local convergence of the optimal gradient method on initial values and solving the problems of randomness and probability caused by using the simple genetic algorithm, obtaining the high performance control, anti-disturbance performance and adaptability of the motor and simplifying the control difficulty, along with simple structure and high system robustness.

The invention discloses a goods location distributing method of a mobile shelf warehousing system for a refrigeration house. The goods location distributing method includes the steps: distributing items with strong correlation to the same sorting roadway, thus reducing the possibility of repeatedly opening the sorting roadway; taking the similarity coefficient of the order item as the basis of thecorrelation; establishing a multi-target goods allocation optimization model by comprehensively considering item sorting frequency and goods shelf gravity center; solving by adopting an improved invasive weed algorithm to obtain an optimal storage position of goods; generating a part of initial population by adopting a greedy algorithm; setting a reasonable spatial diffusion operator; and finallyintroducing an evolutionary reversal operation of a genetic algorithm. According to the goods location distributing method, the global search capacity and the local search capacity are high, and theoptimization effect is remarkable, and the warehouse sorting efficiency and the shelf stability are effectively improved.

The invention relates to a microgrid multi-energy economic method based on a positive and negative feedback particle swarm optimization algorithm. The method comprises: step one, an optimization objective function for optimizing the system generator output and minimum power generation cost is established under the circumstance of satisfying the system operation constraint condition; step two, setting a constraint condition of the optimization objective function from the step one; and step three, carrying out optimization calculation by using a positive and negative feedback particle swarm algorithm, setting various parameters of the algorithm, and then starting iterative calculation to obtain an optimal solution of the optimization objective function from the step one. According to the invention, with a dynamic double-population particle swarm structure and linear decreasing inertia weight calculation, multi-energy scheduling of the micro grid is optimized effectively.

The invention discloses a forward kinematics solving method of a parallel robot. When the method is applied to solve the forward kinematics problem of the parallel robot, the characteristic of easily solving inverse kinematics of the method is utilized, the forward kinematics solving problem of the parallel robot is converted into the equivalent minimal optimization problem, and the numerical optimization method is used for solving the problem. The method is integrated with the advantage of differential evolution having excellent global exploration performance on the solution space and the characteristic of pattern search having good local development capability on the solution space; and the mutual mechanisms of the two optimization algorithms are merged so that the search performance of the algorithms is improved. Compared with the traditional method, the method provided by the invention has high optimal solution searching accuracy and high rate of convergence while solving the forward kinematics problem of a 6-SPS type parallel robot; and simultaneously, the method also can be popularized to solve the forward kinematics problems of the parallel robots of other types.

The invention relates to a wind farm multi-model draught fan optimized arrangement method based on a genetic algorithm. The method includes the following steps that (1) a wind farm region is divided into square meshes which are the same in size according to the diameter of a draught fan, and an integer matrix which is the same in line and row is generated randomly to be used as the initial solution of the algorithm; (2) the individual fitness value of a current generation is calculated; (3) parent individuals participating in crossover are selected through even random selection operators, and then filial generation individuals are generated by the adoption of improved crossover and mutation operators; (4) repairing operators are introduced to the individuals in a population; (5) a Tabu operator is introduced to an optimal solution of the current generation of the population, the optimal solution is used as the initial solution of a Tabu algorithm, and the neighborhood solution of the optimal solution is searched for; (6) whether the biggest number of iterations is reached or not is judged, if yes, the multi-model draught fan optimized arrangement is completed, and if not, the step (2) is executed again. Compared with the prior art, the wind farm multi-model draught fan optimized arrangement method based on the genetic algorithm has the advantages of being visual in coding mode, good in performance index, high in local search capacity, high in expansibility, high in practicability and the like.

The invention relates to an array antenna beam forming method and belongs to the technical field of wireless communication and signal processing. The invention relates to an array antenna phase-only conversion beam forming method, beam forming of different radiation requirements can be achieved through phase weighting under a condition that power is maintained unchanged. The method comprises the following steps of using a quantification particle swarm algorithm to obtain an element amplitude value corresponding to each ideal directional diagram as an initial value of iterative Fourier transform; applying inverse discrete Fourier transform (IDFT) to obtain an array directional diagram; comparing the array directional diagram with an expected directional diagram to obtain a new directional diagram; and applying fast Fourier transform (FFT) to obtain new element excitation through inverse computation. According to the method provided by the invention, the directional diagram forming rapidity and effectiveness of a quantification particle swarm algorithm and the final convergence ability and high convergence speed of an iteration Fourier transform algorithm are combined, and the capability of beam coverage in a spatial domain of each directional diagram with only phase change is improved, so that the method provided by the invention has better engineering practicality.

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.

The invention discloses a heterogeneous multi-core embedded system energy consumption optimization scheduling method based on a reinforcement learning algorithm. In the hardware aspect, a DVFS regulator is loaded on each processor, and the hardware platform matching the software characteristics is dynamically constructed by adjusting the working voltage of each processor and changing the hardwarecharacteristics of each processor. In the aspect of software, aiming at the shortcomings of traditional heuristic algorithm (genetic algorithm, annealing algorithm, etc.), such as insufficient local searching ability or weak global searching ability, this paper makes an exploratory application of Q-Learning algorithm to find the optimal scheduling solution of energy consumption. The Q-Learning algorithm can give consideration to the performance of global search and local search by trial-and-error and interactive feedback with the environment, so as to achieve better search results than the traditional heuristic algorithm. Thousands of experiments show that compared with the traditional GA algorithm, the energy consumption reduction rate of the Q-learning algorithm can reach 6%-32%.

The invention provides a routing method of a small-scale wireless sensor network, belongs to the field of routing of a wireless sensor network, and solves the problem that a Harmony search algorithm in the prior art cannot be directly used for solving the routing of the wireless sensor network. The routing method comprises a step of transmitting global information, a step of sending data packet, a step of transmitting the data packet and a step of updating rest energy information. Through improving the encoding manner and the candidate Harmony generation method of the existing Harmony search algorithm, with the consideration of both path energy consumption and path length, the energy consumption of the whole network can be balanced effectively, and the service life of the whole network is prolonged significantly.

The invention relates to a cold load prediction method based on support vector machine parameters optimized with the cat swarm algorithm. The method includes the following steps: (1) selecting prediction features of a cold load, (2) pre-processing historical data of the cold load, (3) analyzing the historical data of the cold load, (4) automatically optimizing the support vector machine parameters with the cat swarm algorithm, and (5) performing cold load prediction with an optimized support vector machine. The parameters of the support vector machine are optimized through the local searching capability and the global searching capability possessed by the cat swarm algorithm, so that the prediction capability of the support vector machine is promoted, and the effect of promoting prediction accuracy is achieved. Due to the cat swarm algorithm is applied to the optimization process of the support vector machine parameters, automatic optimization of the support vector machine parameters is achieved, and finally the prediction accuracy of the cold load prediction is promoted. The cold load prediction method based on the support vector machine parameters optimized with the cat swarm algorithm is high in practicality and strong in popularization capacity.

The invention relates to an array antenna phase-only transform beamforming method based on a QIWO_IFT combined algorithm, and belongs to the technical field of wireless communication and signal processing. The invention relates to the array antenna phase-only transform beamforming method, i.e. different radiation requirements of beams are realized by phase weighting only under the condition of unchanged power. The method comprises the following parts that the unit amplitude and phase value corresponding to each ideal directional graph is obtained by using a quantitative invasion weed method to act as an initial value of iterative Fourier transform, an array directional graph is obtained by applying inverse discrete Fourier transform (IFFT) and then compared with an expected directional graph so as to obtain a new directional graph, and new unit excitation is reversely calculated by applying fast Fourier transform (FFT). Beam coverage capacity of the airspace of each directional graph of phase-only transform is enhanced through combination of rapidity and effectiveness of quantitative invasion weed method directional graph forming and the characteristics of final convergence and high convergence speed of the iterative Fourier algorithm so that the method has great engineering practicality.

The invention discloses an error compensation method for a photoelectric encoder. Based on improved particle swarm optimization and a Fourier neural network principle, the method is used for improving the measurement accuracy of the photoelectric encoder, and is particularly suitable for an angle measuring system requiring low cost and high accuracy. According to the method, a compass error is modeled by a Fourier neural network, and the weight of the neural network is optimized by the improved particle swarm optimization, so that an accurate error model is obtained to compensate a measured value of the photoelectric encoder. The error model established by the method can realize accurate mapping of a sample space and has high nonlinear approximation capability; and by the method, local minimum is avoided, a defect that the neural network has ultralow convergence rate, oscillates and the like is overcome, measurement errors of the photoelectric encoder are effectively reduced, and the measurement accuracy of the photoelectric encoder is greatly improved.

The invention relates to a self-adaptive spinal CT image segmentation method based on particle swarm optimization. The method comprises the following steps that (1) an original image is inputted; (2) the first generation of population is initialized; (3) an individual optimum and a global optimum are calculated; (4) new individuals are generated; (5) a new individual optimum and a global optimum are calculated; (6) whether the maximum number of iterations is met is judged, and the process goes to step (7) if the judgment result is yes, or the process returns to the step (4); (7) initial image segmentation is performed to act as an initial segmentation result; and (8) topology operation is adopted to perform further accurate spinal segmentation so that the image is outputted. Search granularity is optimized, and speed of algorithm convergence is controlled in a coarse-to-fine way so that speed of algorithm convergence is greatly enhanced, segmentation precision is enhanced, further accurate spinal segmentation is performed by adopting the topology through the prior knowledge of areas to be segmented, and thus image segmentation efficiency and quality are greatly enhanced.

The invention relates to an optimal torque distribution method based on a distributed electric drive vehicle. The torques of four drive wheels are reasonably distributed, and meanwhile the drive system efficiency and driving safety of the distributed electric drive vehicle are improved. The torque distribution method comprises the following steps of (1) adopting a response surface analysis methodfor conducting regression analysis on test data of a hub motor to obtain a drive motor efficiency function; (2) based on a demand torque value of a distributed electric drive system, establishing objective functions which characterize the efficiency optimization of the drive system and the driving safety optimization of the vehicle respectively; adopting a linear weighting method of a self-adaptive weight coefficient for converting solutions of the two objective functions into a multi-objective optimization problem under constraint conditions; (3) integrating the respective advantages of a genetic algorithm and a taboo search algorithm to put forward a hybrid genetic taboo search algorithm (HGTSA) for solving the multi-objective optimization problem, and obtaining the optimal torque distribution of the distributed electric drive system accordingly.

The invention discloses an optimization model method based on a generative adversarial network and an application, called GAN-O, the method comprises the following steps: expressing the application (such as logistics distribution optimization) as a function optimization problem; establishing a function optimization model based on the generative adversarial network according to the test function and the test dimension of the function optimization problem, including constructing a generator and a discriminator based on the generative adversarial network; training a function optimization model; carrying out iterative computation by utilizing the trained function optimization model to obtain an optimal solution; therefore, the optimization solution based on the generative adversarial network is realized. According to the method, a better local optimal solution can be obtained in a shorter time, so that the training of the deep neural network is stable, and the method has more excellent local search capability. The method can be used for many application scenarios such as logistics distribution problems which can be converted into function optimization problems in reality, the application field is wide, a large number of actual problems can be solved, and the popularization and application value is high.

The invention discloses a fast point cloud boundary extraction method combined with an improved particle swarm algorithm. The method comprises the following steps: obtaining point cloud data, establishing a topological relation and carrying out smoothing processing; selecting optimal feature points of all local structures through the improved particle swarm algorithm; through random sample consensus RANSAC, keeping N optimal feature points, and returning an optimal model; and according to uniformity of point distribution in point cloud data point k-neighborhood, finding all boundary feature points in the optimal model and finishing boundary extraction. Compared with a conventional point cloud boundary extraction method, the extraction method in the invention reduces point cloud boundary extraction calculation amount and is high in efficiency; since inertia weight is introduced, influence of the previous speed on the current speed can be controlled; by adjusting the magnitude of the inertia weight, the group can be prevented from falling into the local optimal point, and calculation precision is improved; and the method is close to a real object and is better in boundary effect.

The invention provides a vehicle ride-sharing path optimization method and system. The method comprises the steps of acquiring real-time riding data of vehicles, roads and passengers; screening and eliminating the data outside the area range; temporarily storing the data in the area range; the highest driver income, the shortest vehicle driving distance, the minimum vehicle idle time and the highest passenger satisfaction are taken as optimization objectives; establishing a multi-vehicle ride-sharing matching and path optimization model with constraint conditions; according to the vehicle, road and passenger riding real-time data temporarily stored in the server module, solving the multi-vehicle ride-sharing matching and path optimization model by utilizing an improved genetic algorithm and a simulated annealing algorithm; the optimal target function value is obtained, the relation between passengers, the relation between passengers and vehicles and the relation between vehicles are established, ride-sharing matching between passengers and passengers and vehicles is effectively achieved, path planning is efficiently achieved, the contradiction between passengers and drivers is balanced, vehicle resources are saved, and energy waste is reduced.

The invention discloses a high-efficiency scheduling optimization method. According to the invention, a swarm intelligence optimization method based on a variable neighborhood search algorithm is employed for solving a multi-processing-task mixed flow work shop scheduling problem, and the variable neighborhood search algorithm which comprises five neighborhood structures is introduced to a fireflyalgorithm, thereby improving the diversity of populations, improving the local search capability of the algorithm, and improving the search precision of the algorithm. Moreover, a work adjustment rule is proposed, thereby increasing the convergence rate of the algorithm, and enabling the method to achieve the optimal scheduling at high efficiency. The method can effectively shorten the idle timeof a processing machine, improves the production efficiency, and improves the economic benefits after scheduling.

The invention discloses an identification method for photovoltaic inverter control parameters based on a self-adaptive differential evolution algorithm. The method is characterized by comprising the steps of 1, setting a disturbance point in an outgoing line of a photovoltaic inverter to collect disturbance data required for parameter identification; 2, carrying out outlier rejection and correction on input and output sampling sequences of the photovoltaic inverter; and 3, identifying a d-axis control parameter and a q-axis control parameter of the photovoltaic inverter through the self-adaptive differential evolution algorithm. According to the method, photovoltaic inverter control parameter values can be obtained rapidly and accurately, and thus the purpose of improving the precision of a photovoltaic model is achieved.

The invention discloses an electric capacitance tomography method based on improved particle swarm optimization. The method comprises applying voltage so that the electrostatic field in the measured field satisfies the Laplace equation, carrying out taylor expansion on the capacitance value between the electrodes and the relative dielectric constant relationship, ignoring the high order phase, carrying out normalization processing to obtain a normalized capacitance vector, reconstructing the electric capacitance tomography images to optimize a target, acquiring an objective function of the Landweber algorithm according to the vector norm function definition, rebuilding an iterative formula of the electric capacitance tomography according to the steepest descent principle, improving the rebuilding quality through a particle swarm optimized fitness function, acquiring a modified particle velocity update formula through an exponential decay weight mechanism, and optimizing the data. The electric capacitance tomography method utilizes the inertia weight exponential decay particle swarm optimization algorithm to optimize the rebuilding result obtained by the Landweber algorithm, solvesthe problem in the Landweber imaging process and reduces the influence caused by a soft field on the image reconstruction.

The invention relates to a vector quantization codebook designing method based on a genetic algorithm, which comprises the following steps coding chromosomes; generating an initial population; calculating the adaptability of each chromosome; selecting an individual which enters a next generation; making the chromosomes intersect; making the chromosomes vary; and generating a new population. The vector quantization codebook designing method aims at the population. A selection operator is used for performing targeted optimum operation on the populations. Furthermore diversity of the populations is increased through an improved crossover algorithm. Finally the average adaptive value of the population is improved through a mutation operator, so that the average adaptive value gets rid of a partial least point. The vector quantization codebook designing method has a good partial searching capability through reserving an LBG optimization selection strategy.

A contact state recognition method for robot assembly based on GWA-SVM comprises the following steps: 1, using an industrial robot to assemble parts, and collecting force data in the assembly process;2, setting initial parameters; 3, standardizing the data set; 4, initializing a population of SVM parameters by using a chaotic logic mapping strategy; 5, optimizing the population of SVM parametersby using an improved reverse learning strategy; 6, updating the population by using a GWA operator; 7, calculating the fitness of population individuals, and updating the optimal individual; 8, if thecurrent iteration reaches the maximum allowable iteration frequency, executing the step 9, otherwise, t=t+1 and returning to the step 6; 9, ending the SVM parameter optimization process, substitutingthe optimal SVM parameters C and gamma and the training data set into the SVM, and establishing a GWA-SVM based contact state identification model; and 10, identifying the test data set by using thecontact state model, and drawing a classification result graph. The method is high in classification precision.

The invention discloses a wire and cable defect detection system. The system comprises an image acquisition module, an image processing module, a defect detection module, a defect early warning moduleand an image display module, the image acquisition module is used for acquiring surface images of a to-be-detected wire and cable in an omnibearing manner. The image processing module is used for processing the acquired wire and cable images, segmenting the processed wire and cable image and obtaining wire and cable region images, the defect detection module is used for calculating a variance ofa pixel gray value in the electric wire and cable area image, and when the variance is higher than a given defect threshold, judging that defects exist on the surface of the to-be-detected electric wire and cable, enabling a defect early warning module to carry out early warning, and displaying the electric wire and cable region images obtained by segmentation on the image display module. The system has the advantages that the image processing technology is applied to detection of the surface defects of the wires and the cables, and the detection precision and the automation level of the surface defects of the wires and the cables are improved.

The invention discloses an energy storage system-distributed power supply-capacitor integrated control reactive power optimization method. Establishing an objective function, performing constant volume and location calculation according to a preset algorithm; obtaining a candidate solution of a preset function, optimizing the first optimal solution, mining a second optimal solution, determining atarget ideal point of the current optimization problem and an Euclidean distance square from each second optimal solution to the ideal point according to an optimal Pareto leading edge obtained by a multi-strategy fusion particle swarm optimization algorithm, and obtaining a decision compromise solution. According to the invention, multiple elements are combined to optimize the power quality, theabsorption capability of the power distribution network for the distributed power supply is improved, the reactive power distribution and voltage level of the system are improved, and the network lossis reduced; according to the method, a multi-strategy fusion particle swarm optimization algorithm is introduced to execute thorough search on individuals falling into local optimum, the global search capability and the local search capability are high, the local particle jumping-out capability is high, and the probability that the population falls into premature convergence is greatly reduced.