62results about How to "Good global search ability" patented technology

A flexible job shop order insertion dynamic scheduling optimization method is a solution method aiming at the delay problems caused by the order insertion in the job shop batch dynamic scheduling, andcomprises the steps of on the basis of establishing a mathematical model of the task sequence optimization and the order batch distribution, researching a batch selection strategy, adopting an example simulation mode to obtain the reasonable sub-batch number, at the same time, according to the simulation and calculation of the typical examples, giving a recommending value of the batch number; secondly, based on the three-layer gene chromosomes of the processes, the machines and the order distribution number, taking the minimum maximum time of completion and the delay period as the optimization targets; and finally, adopting a mixed algorithm of a particle swarm optimization algorithm and a genetic algorithm to improve the speed of evolution of the sub-batch number towards an optimal direction, thereby effectively reducing the tardiness quantity. The method is good at reducing the delay period in the job shop dynamic scheduling, and for the conventional genetic algorithm, enables the convergence speed and the stability to be improved substantially, at the same time, fully combines the actual production statuses of the intelligent job shops, greatly promotes the dynamic scheduling solution, and has the great application value in the engineering.

The invention discloses an unmanned vehicle speed control method based on PSO (Particle Swarm Optimization) and an RBF neutral network. The method comprises the following specific steps: 1, establishing an unmanned vehicle speed control system configuration; 2, building a vehicle speed tracking closed loop control mathematic dynamic model; 3, building an unmanned vehicle speed control driver model based on a fuzzy RBF neutral network structure; 4, fuzzifying an input variable of the driver model to obtain a fuzzy value, and utilizing the fuzzy value to establish an input and output variable membership function; 5, establishing a driver model fuzzy control rule list on the basis of the step 3, the step 4, the experience of a driver and measurement data; 6, calculating the fitness of each rule in the driver model, and completing fuzzification and normalization calculation; 7, establishing an improved PSO control flow on the basis of PSO; and 8, establishing a vehicle speed control flow on the basis of the improved PSO and a fuzzy RBF neutral network algorithm. According to the vehicle speed control method, the vehicle speed tracking error is low, and the anti-interference capability is high.

The invention discloses a wireless sensor network clustering routing method based on a harmony search algorithm. The method comprises the following steps: (1) global information transmission and convergence: acquiring the global information, and transmitting the global information to an aggregation node; (2) the aggregation node performs optimization calculation and configuration of network clustering routing of the entire sensor network through the global information; (3) a common sensor node monitors, collects and processes application information, processes the application information into a data packet, and forwards the data packet to a cluster head node, and the cluster head node performs data fusion and sends the data packet to a next hop cluster head node; and (4) the next hop cluster head node adds its own dump energy information to the data packet after receiving the data packet, and continues to forward the data packet to the next hop cluster head node according to the optical routing in the data packet. By adoption of the method disclosed by the invention, the problems of unreasonable member node allocation, uneven power consumption of the cluster head nodes of a wireless sensor network are solved, the energy efficiency of the network is improved, and the life cycle of the network is prolonged.

The invention provides an EWT-PDBN combination-based short-term wind power prediction method. The method comprises the following steps of A, collecting numerical weather forecast data and historical wind power data of a wind power plant; b, performing preprocessing and normalization processing of all the acquired data; c, decomposing the normalized historical average wind power data by using an empirical wavelet transform signal decomposition technology; d, performing correlation screening of the decomposed different intrinsic mode component function sub-sequences, respectively taking the screened group sub-sequences and other data subjected to normalization processing as input data, and inputting the input data into a particle swarm optimization deep belief network model for prediction toobtain group prediction data; and E, superposing a group of prediction data to reconstruct a group of data, and then performing reverse normalization processing of the group of data to obtain the result as the final wind power prediction result. The method is advantaged in that through EWT-PDBN combined prediction, the wind power prediction result with high precision and small error is obtained.

The invention discloses an optimization method of phase compensation link time constants of a power system stabilizer. The optimization method comprises the following steps of (1) measuring non-compensation phase-frequency characteristics of a unit excitation system by adopting a dynamic signal analyzer on the spot and reading a phase angle within a range of 0.1-2.0Hz; (2) converting the power system stabilizer into the PSS of a rotating speed deviation single-input mode according to structure characteristics of an electric power and rotating speed deviation double-input signal of a PSS4B-W; and (3) building a parameter optimization model of the PSS4B-W by employing third-order lead-lag phase compensation link time constants of the PSS4B-W as optimization variables and in-phase additional moment generated by the PSS and [delta]omega shaft as an optimization target and solving the time constants through an adaptive weight particle swarm optimization algorithm. According to the optimization method, optimized parameters, meeting the industry standard requirements, of the PSS4B-W can be quickly and efficiently found out.

The invention discloses a reliability optimization allocation method based on an improved Pareto artificial bee colony algorithm. The method comprises the following steps of: constructing a development cost-reliability function model, a maintenance cost-reliability function model and a total cost-reliability function model of an offshore wind turbine generator set; establishing a reliability optimal distribution model of the offshore wind turbine generator set by taking the reliability of the offshore wind turbine generator set as the target and the development cost, the maintenance cost and the total cost of the offshore wind turbine generator set as the target on the basis of analyzing the reliability constraint relationship of each subsystem through the maintenance cost-reliability function model and the total cost-reliability function model. Based on the idea of Pareto multi-objective optimization, an improved artificial bee colony algorithm is proposed to be applied to solving ofa reliability optimization allocation model; the improved artificial bee colony algorithm can effectively improve the solving efficiency and solving quality of the model. For the solved Pareto non-dominated solution set of the reliability allocation scheme, a PROMETHEE-II method is adopted to perform secondary optimization on the reliability allocation scheme, and the optimal reliability allocation index of each subsystem is determined.

The invention provides a quantum chemistry reaction optimization multi-relay selection method of a cognitive relay network. The method comprises steps of: 1, establishing a cognitive system relay selection model; 2, initializing a quantum molecule set and a system parameter; 3, evaluating the potential energy of all quantum molecules in the set and selecting the measurement state of the quantum molecule with the lowest potential energy as a global optimal solution; 4, arranging the kinetic energy of quantum molecules in a descending order, and performing decomposition reaction, invalid collision, and synthetic reaction; 5, evaluating the potential energy of newly generated quantum molecules, and if the minimum potential energy of the newly generated quantum molecules is less than the minimum potential energy of the previous generation, marking the newly generated quantum molecules as a new global optimal solution; and 6, if the number of iteration times is less than a preset maximum number of iteration times, returning to step 4, otherwise, outputting the global optimal solution. The method balances the primary user constraint condition and non-primary user constraint condition of the cognitive relay network, and chooses a relay selection scheme that maximizes the system throughput based on a quantum chemistry reaction mechanism.

The invention provides a bee colony optimization based network traffic scheduling method under multiple QoS (quality of service) constraints. According to the method, a multi-objective optimization problem is solved with a multi-objective artificial bee colony optimization algorithm, a fitness function is improved in combination of the algorithm with a Pareto sorting mechanism and a crowding distance, solution selection is performed with a Boltzmann strategy, a found Pareto solution is recorded with an external file, and neighborhood search of the colony is guided according to global information, so that the found Pareto optimal solutions are uniformly distributed at the real Pareto optimal front end. The degree of importance of each objective is analyzed according to actual conditions, an optimal traffic scheduling scheme is determined, so that after traffic scheduling, the network traffic is scheduled as required, the service level for users is improved, the utilization rate of network resources is increased, the load balancing purpose is achieved, and the traffic scheduling effect is optimal. With the application of the method, the high-utilization and low-consumption traffic scheduling of the network traffic under the multiple QoS constraints can be realized.

The invention discloses a multi-region dynamic economy scheduling method and system. The method comprises that a target function of a multi-region economic scheduling problem is established; an initial population is generated by initialization, the fitness of the initial population is calculated, and the initial population serves as a parent population; an NW small world network model is used to obtain an adjacent matrix; the parent population is updated according to the adjacent matrix to obtain a filial population, and the fitness of particles in the filial population is calculated by utilizing a fitness function; the particle fitness in neighborhoods divided by corresponding adjacent matrixes in parent and filial populations is compared by utilizing a competition operator, and particles of high fitness are reserves and serve as a parent population in next iteration; and when a preset maximal iteration frequency is reached, a result of the multi-region economic scheduling problem is output. The NW small world network improved differential crisscross algorithm is used to overcome the defect of population diversity loss in the optimization searching process of basic differential evolution algorithm and crisscross algorithm.

The invention discloses a resource optimization method for maximizing the total throughput of network function virtualization. A network function virtualization architecture comprises a logic layer, avirtual layer, a physical layer and a management arrangement system, the logic layer comprises logic nodes and controllers, and the physical layer comprises a physical node; the logic nodes and controllers send information signals to a base station via an orthogonal channel through the corresponding physical node; the base station calculates the number of effective load bits, the number of used channels, transmitting power, a receiving signal to noise ratio, throughput and total transmitting energy of each logic node and each controller; and when the third number, the number of effective loadbits, the receiving signal to noise ratio, the first total transmitting energy and the second total transmitting energy meet corresponding requirements, and the logic nodes and the controllers meet the ultra-reliability requirements, the management arrangement system adaptively allocates the transmitting power and the number of used channels based on a hybrid optimization algorithm to maximize the total throughput.

The invention discloses a protein conformational space optimization method based on fragment assembly. The protein conformational space optimization method includes the following steps that fragments are selected from a protein fragment library randomly to generate population individuals, the function value of each population can be calculated according to a scoring function, sorting is conducted, the optimal function value is obtained, crossover and variation operation is carried out on the individuals in each population, so that the populations are updated, and iterative operation is performed until a set terminal condition is met. The effective conformational space optimization method is provided.

The invention discloses a method for improving the precision of an output angle of a magnetic encoder based on a Hall effect. The method specifically comprises the following steps: constructing an LM-BP neural network structure; optimizing the initial weight and threshold of the LM-BP neural network through a PSO method: calculating the particle dimension of a PSO particle swarm, calculating the fitness value of particles, updating the positions and speeds of the particles, and obtaining the initial weight and threshold of the LM-BP neural network after PSO optimization; carrying out PSO-LM-BPneural network training: initializing an LM-BP neural network control vector, calculating a square error between output of an output layer and an ideal output signal, updating the control vector, andjudging the size of the square error; and predicting the output angle of the magnetic encoder by the PSO-LM-BP neural network. According to the method, the BP neural network is optimized in a PSO andLM matching manner, and the globally optimal initial weight and threshold are found for the BP neural network method, so that the precision of the original output angle of the magnetic encoder is improved, and the error of the magnetic encoder is reduced, and the precision of the output angle of the magnetic encoder is greatly improved.

The invention relates to the technology of wireless sensor network positioning, in particular to a positioning method for non-collinear unknown sensor nodes of a wireless sensor network, which is mainly used for acquiring accurate position information of the non-collinear unknown sensor nodes of the wireless sensor network, and solves the problem that the existing ranging-based positioning algorithm has low positioning accuracy and complicated algorithm. The method provided by the invention firstly converts the signal intensity value received between the nodes into the distance value between the nodes, obtains two possible coordinates (FORMULA referred as follows) of an unknown node by using the known position coordinates of any two beacon nodes A and B around the unknown node based on thelinear intersection principle when the unknown node and any two beacon nodes are not collinear, determines the two possible coordinates, and finally uses the artificial bee colony algorithm for optimization to determine the coordinates of the unknown node to complete the positioning. The method provided by the invention improves the accuracy of the algorithm, reduces the complexity of the algorithm, reduces the energy consumption of the nodes, and prolongs the life cycle of the nodes.

The invention provides a cooperative scheduling method for distributed manufacturing and multi-mode transportation of high-end equipment, and relates to the technical field of task scheduling. According to the invention, distributed manufacturing, learning effects, multiple transportation modes and production and transportation collaboration are combined together, and learning effects of factories distributed at different positions in the production process and multiple transportation modes of the transportation process are considered in the classical production and transportation collaboration problem, so the research content is closer to the actual production environment, and the adaptability of the obtained scheduling scheme is improved.

The invention discloses a cold-chain logistics temperature prediction method, and a temperature regulation and control method. The cold-chain logistics temperature prediction method comprises the following steps: performing normalization processing on collected data; inputting the data set into an ELM model, and calculating a model evaluation value; optimizing the input weight w and the hidden layer bias b of the ELM model by using a mayfly algorithm, continuously updating the positions of male mayflies and female mayflies, carrying out crossover operation so as to obtain new w and b, calculating a new model evaluation value based on the new w and b, and updating the minimum model evaluation value so achieve that the error of a prediction result is minimum; judging whether the mayfly algorithm reaches the maximum number of iterations, and if the condition is met, outputting an optimal solution, or otherwise, continuing iterative optimization until a stop condition is met; and outputting optimal parameters of the mayfly algorithm, substituting a result into the extreme learning machine model, outputting a predicted value and evaluating the performance of the model. According to the method, a more accurate temperature prediction result can be obtained, and temperature can be effectively regulated and controlled based on the result.

The invention relates to a DNA sequence optimization method based on a particle swarm chaotic intrusion weed algorithm. In the method, all DNA sequences are firstly constructed as an initial population; with the intrusion weed algorithm, the initial population is subjected to reproduction, spatial expansion and competitive exclusion (local optimal solution); then, the already-obtained local DNA coding sequence is used, the particle swarm optimization method is used for searching, a new DNA coding sequence is obtained, and the fitness of the sequence is calculated and sorted; and finally, the optimal DNA coding sequence is selected. The DNA sequence optimization method based on the particle swarm chaotic intrusion weed algorithm can search a DNA coding sequences with better quality.

The invention discloses a new workpiece rescheduling optimization method based on a self-adaptive genetic algorithm in a discrete manufacturing system containing a heat treatment process and taking energy conservation as a target. The new workpiece rescheduling optimization method comprises the following steps: establishing a mathematical model; performing initialization; determining initial values of the population size G, the crossover rate pc, the variation rate pm, the replacement rate pr, the upper limit t of the number of cycles and the number of local search times T; generating an initial population; whether rescheduling is optimal is judged, and if yes, the individual is the optimal rescheduling scheme; otherwise, executing sequential crossover, mutation operation and chromosome selection operation; finding a new rescheduling sequence which is superior to the current rescheduling solution through self-adaptive local area search; updating the population; stopping the criterion,if the total number of cycles reaches a specified upper limit value t, outputting an individual with a maximum right-worthiness function, and ending the calculation; otherwise, continuing to evolve the population. According to the method, three local area search operators of inversion, transfer and interchange are used for forming an adaptive local area search algorithm, and a better energy-savingrescheduling scheme can be obtained in a short time.

The invention discloses an unmanned aerial vehicle group target search method based on a chaos lost pigeon flock optimization mechanism. The method comprises the following steps of (1) environment map initialization: realizing search environment initialization by using rasterization, (2) performing cooperative path optimization on the unmanned aerial vehicle by adopting a chaos lost pigeon flock optimization mechanism, updating track point coordinates of the unmanned aerial vehicle at the next moment for a global optimal position, and guiding the unmanned aerial vehicle to fly to the most efficient search area, (3) broadcasting state information of the unmanned aerial vehicles: realizing information sharing among multiple unmanned aerial vehicles by adopting a communication mechanism to update the motion state of the unmanned aerial vehicles, and (4) target distribution: selecting the unmanned aerial vehicle with the highest matching degree to search the target to obtain an optimal target search scheme. The pigeon flock algorithm based on the chaos lost mechanism has obvious advantages in solving quality, and a chaos initialization strategy of the pigeon flock algorithm enables the algorithm to have high convergence speed and better convergence precision; the lost mechanism enables the algorithm to have a strong capability of jumping out of local optimum.

The present invention discloses a variable-stage gradual optimization based joint optimization scheduling method for cascaded hydropower stations. The method comprises: step 1, acquiring an initial scheduling process of each hydropower station, and performing water level regulation in a constraint search manner; step 2, fixing water levels of an ith node and an (i+VP)th node, and performing optimization calculation for problems in VP stages by adopting a differential evolution algorithm; step 3, selecting a population size NP, wherein initial individuals are adjustable points of the cascaded hydropower stations; step 4, obtaining a water level process line of each cascaded hydropower station; step 5, by using the water level process line of each hydropower station obtained in the step 4 as an initial trajectory, repeating the steps 2 to 5 until a variable-stage convergent condition is satisfied; step 6, setting VP to be equal to the sum of VP and 1; repeating the steps 2 to 5 until a final convergent condition is satisfied; and step 7, ending the calculation, and obtaining an optimal water level process line of each hydropower station. The method disclosed by the present invention has very good global search capability for solving the problem in joint optimization scheduling of the cascaded hydropower stations, and effectively solves the local convergence problem of a conventional algorithm.

The invention discloses an optimization method for design data of an integrated circuit, and the method comprises the steps: obtaining the design data of the integrated circuit, obtaining design parameters through the design data, and enabling the design parameters to comprise global design parameters and local design parameters; obtaining a performance index through the design data, and describing a mapping relation between the design data and the performance index through a neural network model; specifying an optimization criterion of the design data according to the performance index; obtaining basic data required by the optimization criterion according to the mapping relation; and iteratively optimizing integrated circuit design data by using a multi-level population optimization algorithm. According to the optimization method for the integrated circuit design data, the problems that an existing integrated circuit is complex in design, long in period and high in research and development cost can be solved.

The invention discloses a phase-change switch optimal configuration method and system based on a particle swarm optimization algorithm. The method comprises the steps of: constructing a phase-change switch configuration model according to user load power and power distribution network topology node impedance; solving the phase-change switch configuration model by using a particle swarm optimization algorithm by taking the minimized three-phase unbalance degree and the action times of the phase-change switch as target functions to obtain the optimal switch action of the phase-change switch; determining the load participating in commutation according to the change of the load before and after the optimal switching action of the commutation switch is executed; sorting the commutation times ofthe loads participating in commutation, wherein the position of the load with the maximum commutation times is the installation position of the commutation switch; and establishing a phase-change switch configuration model according to the topological structure of the power distribution network and the load power data, solving the model by using a particle swarm optimization algorithm by taking the three-phase unbalance degree and the phase-change frequency as targets, and determining the installation position of the phase-change switch according to the optimal solution, thereby realizing reasonable configuration of the phase-change switch.

The invention relates to an aircraft electromechanical system sealing structure long-life design method based on a particle swarm optimization algorithm. An RBF neural network agent model is adopted,modeling parameters and easy-to-fail point stress in an O-shaped sealing ring finite element model serve as samples to be input into an RBF neural network to be trained, and a cross validation methodis adopted to enable prediction errors to be reduced to 10% or below; the service life of the sealing ring is calculated by adopting a fatigue life empirical formula; the pre-compression amount of theO-shaped sealing ring is optimized by adopting an adaptive particle swarm optimization (APSO) algorithm by taking the service life of the O-shaped sealing ring as a target function, the pre-compression amount as a parameter to be optimized and no leakage of the sealing ring as a constraint condition. Compared with a traditional optimization algorithm, the method has good global search capabilityand high convergence rate for parameter optimization of a complex structure.

The invention discloses an analog circuit fault diagnosis method based on an SFO optimization depth extreme learning machine. The method comprises the following steps: inputting data; preprocessing the data; taking the training set sample as the input of a deep extreme learning machine (DELM), and training the training set sample; the method comprises the following steps: taking a test set classification error rate as a fitness function, finding a group of optimal initial weights of an extreme learning machine-based automatic encoder (ELM-AE) through a flag fish algorithm (SFO), optimizing the initial weights, and training a DELM model by using the optimized ELM-AE to enable the error rate of the DELM to be the lowest; an optimal initial weight parameter is returned through the fourth step, then the weight obtained through optimization is used for training the DELM model, and an optimal DELM model is constructed; and classifying the faults by using the optimal DELM model. Compared with the non-optimized DELM, the method has the advantages that the diagnosis accuracy of the SFO optimized DELM is improved, it is proved that the selection of hidden layer parameters affects the diagnosis precision, and the SFO algorithm has good global search capability.