33 results about "Gaussian mutation" patented technology

The invention discloses a dynamic production scheduling method and system of a flexible machining production line and application of a G-series high-speed train part group flexible-machining production line, belongs to the fields of complicated production, information technologies and advanced manufacturing and aims to solve the scheduling problem of initial production scheduling plan deviations caused by random production of interference events in a machining environment of the flexible machining production line. The technical characteristic is that a mixed particle swarm optimization algorithm including multi-layer neighborhood search structures of a Gaussian mutation operator and / or randomized policy is used in the dynamic production scheduling process of the flexible machining production line to obtain a re-scheduling scheme. The dynamic production scheduling method and system have the advantages that an initial scheduling plan is dynamically corrected according to random disturbance information to respond to random disturbance.

The invention discloses a multi-unmanned surface vehicle (USV) group coordinated collision avoidance planning method based on a genetic algorithm, and belongs to the technical field of USV control. The method provided by the invention comprises the steps of firstly performing initialization coding on a speed adjustment and a heading adjustment of a USV and setting other control parameters by usinga float-point coding mode; then building an evaluation function, computing the evaluation function value of each individual of a group so as to perform roulette selection, discrete crossing and Gaussian mutation genetic operations on the individual of the group, and building an iteration process to acquire an optimal solution; and at last building a USV collision avoidance plan simulation software platform by using QT software, adding a radar detection module and the genetic algorithm, and designing a typical simulation case to verify the effectiveness of the algorithm. According to the method provided by the invention, the problems that the genetic algorithm is poor in timeliness, trapping in local optimum and premature to converge, and in the genetic algorithm, the offspring optimalityis inferior to the parent optimality, and the bad navigation problems of large angle steering and large-range acceleration and deceleration during a sailing process are solved.

The invention relates to a method for accurately extracting an unknown phase shift amount based on an optimized quantum particle swarm algorithm. First, the statistical average value of the Fresnel diffraction field of each phase shift amount in the four-step phase shift is approximately calculated based on the statistical properties of the diffraction field; , obtain the intermediate value according to the phase random condition, and use it to represent the approximate phase shift; finally, set the average error function as the fitness function, and improve the quantum particle swarm algorithm to further approximate the true value of the phase shift, among which, the quantum particle swarm The Gaussian mutation operation is added to the algorithm to make the algorithm conform to the initial distribution law of particles. The invention has reasonable conception and perfect theory, can not only realize the approximate pre-estimation of the unknown phase shift amount in the four-step phase shift, improve the accuracy of the calculation direction, but also improve the accuracy and speed of calculating the real value of the unknown phase shift amount, effectively It overcomes the "sawtooth solution phenomenon" that appears near the true value in traditional iterative methods, and has the advantages of extremely fast speed and excellent solution quality.

A multi-target optimization method for a main bearing of an RV speed reducer comprises the steps of analyzing an external loading condition of the main bearing, building a quasi-static model of the main bearing of the RV speed reducer, and outputting target functions to be angular rigidity, a friction moment and an axial rated dynamic load of the main bearing of the RV speed reducer; randomly generating an initial population, calculating three optimization target function values of each individual by the model, performing non-dominated sorting, calculating a congestion distance, performing selection, heuristic crossover and Gaussian mutation to generate a new population based on a binary system tournament, and calculating a target function of each individual; and combining a parent population and the new population to form a big population, extracting the best individual to be used as a population entering next iteration, removing a repeated individual of the population after combination, detecting whether a current algebra reaches a set algebra or not, and outputting an optimization result. By the multi-target optimization method, a group of pareto-optimal design parameters which can be reference data for a designer can be acquired, whether the current design is a theoretical non-dominated solution can also be determined, and meanwhile, the algorithm efficiency is improved.

The invention discloses a soft measurement method for total nitrogen concentration in underground water in rare earth mining areas optimized by artificial bee colony. The present invention adopts the support vector machine as the soft sensor model of the total nitrogen concentration in the groundwater of the rare earth mining area, and utilizes the adaptive artificial bee colony algorithm to optimize and design the penalty factor C, the radial basis kernel parameter g and the parameter ε in the insensitive loss function of the support vector machine . In the adaptive artificial bee colony algorithm, the feedback information of the fitness value is used to adaptively adjust the search scaling factor, and the information of the neighborhood optimal individual and the global optimal individual is fused into the Gaussian mutation strategy to adaptively generate new individuals . The invention can improve the soft measurement accuracy of the total nitrogen concentration in the underground water of the rare earth mining area.

The invention discloses an image cutting method based on a multi-target intelligent body evolution clustering algorithm. The problems that the image cutting technology is prone to local optimum and an algorithm is not high in robustness are mainly solved. The image cutting problem is converted into a global optimization clustering problem. The process includes the steps of extracting gray information of pixel points of an image to be cut, initiating parameters and establishing an image intelligent body network, calculating the energy of an image intelligent body, conducting non-domination sequencing, conducting neighborhood competition operation, conducting Gaussian mutation operation, calculating the energy of the image intelligent body, conducting non-domination sequencing, conducting self-learning operation, selecting the optimal clustering result according to the crowding distance, outputting a clustering label, and achieving image cutting. Multiple targeting is achieved for the image processing process, the convergence effect is good, the robustness of the method is enhanced, the image cutting quality can be improved, the cutting effect stability can be enhanced, and the extraction, recognition and other subsequent processing of the image targets are facilitated.

The invention relates to an optimal control algorithm for a chilled water system, which adopts a PID controller to control the chilled water system, and adopts an improved sparrow search algorithm to obtain three parameters K of the PID controller. p , K i and K d The method for improving the sparrow search algorithm at least includes: using a random walk strategy to improve the sparrow search algorithm, and using Gaussian mutation to improve the sparrow search algorithm. The invention uses the random walk strategy to randomly perturb the sparrow group, enhances the search ability of the sparrow group, and reduces the limit value of the decision variable with the increase of the number of iterations; in addition, Gaussian mutation is added to conduct sufficient search, compare the fitness function, and update the position of the sparrow individual in the group. The control algorithm proposed by the invention solves the problem that the algorithm is easy to fall into the local minimum value, and has small overshoot, fast response speed and corresponding improvement in stability.

The invention discloses a multi-unmanned aerial vehicle cooperative search method based on improved pigeon group optimization, which includes: first establishing a search map model, and using a Markov model to establish a target information map, and then establishing a movement model of the unmanned aerial vehicle and digital Pheromone map; apply the pigeon swarm optimization algorithm for multi-UAV collaborative search, and use chaos and reverse strategies to realize the initialization of the population position to ensure the randomness of the initial position; the first stage is to iterate the map and compass operator When using Cauchy mutation to prevent falling into local optimum, in the second stage of iteration of landmark operator, simulated annealing is used to retain some individuals with poor performance and Gaussian mutation to avoid premature falling into local optimum. The present invention combines the use of chaos and reverse strategies to initialize the population position, the mutation introduced in order to avoid falling into local optimum and the simulated annealing algorithm, which solves the dynamic target and repeated search problems in the search process, and effectively improves the search efficiency. efficiency.

The invention provides a robot welding path planning method based on a firework particle swarm optimization algorithm, belonging to the technical field of robot welding control. The method comprises the following steps of: using a greedy algorithm to initialize all path solutions and parameters of the population; updating the speed and position of all population individuals according to the particle swarm operator; taking the individual of the particle swarm as a firework of the firework algorithm; generating sparks by modifying a blast operator and a Gaussian mutation operator; selecting firework populations by using an elite-roulette strategy; rebuilding the population by using a dual population strategy; and updating the individual historical optimal solution and the global optimal solution to obtain an optimal welding path. According to the robot welding path planning method based on the firework particle swarm optimization algorithm, the population diversity of the particle swarmis enhanced, information interaction among the firework algorithm individuals is achieved, and the optimal welding path is obtained by combining the particle swarm optimization algorithm with the firework algorithm, and the effectiveness and feasibility are high.

The invention discloses an ore rock strength soft sensing method based on adaptive artificial bee colony optimization. The method of the invention adopts a three-layer perception neural network as a soft sensing model for ore rock strength, and utilizes the adaptive artificial bee colony algorithm to optimize a connection weight and an offset value of the designed neural network. In the adaptive artificial bee colony algorithm, search scaling factors are generated adaptively according to the feedback information of adaptive values, and a Gaussian mutation strategy based on neighbor optimal individuals and global optimal individuals is designed to adaptively generate new individuals. The method of the invention can raise the precision of soft sensing of the strength of ore rocks, and raises the efficiency of measuring the strength of the ore rocks.

The invention discloses a transformer optimal design method based on adaptive teaching-learning-based optimization. According to the transformer optimal design method, a transformer is designed optimally by an adaptive teaching-learning-based optimization algorithm. In the adaptive teaching-learning-based optimization algorithm, a teaching-learning searching operator based on an adaptive inertia weight and a searching step length is designed, and an individual with an optimal adaptive value is fused into the teaching-learning searching operator. On the other hand, in a self-learning searching operator, information of the optimal individual and a random individual is introduced into a Gaussian mutation strategy at the same time in order to coordinate the balance between a convergence rate and the population diversity. Through adoption of the transformer optimal design method, the optimal design accuracy of the transformer can be increased, and the optimal design efficiency of the transformer is increased.

A multi-USV group collaborative collision avoidance planning method based on genetic algorithm belongs to the technical field of USV control. The present invention firstly uses the floating-point coding method to initialize the speed adjustment and heading adjustment of the USV and set other control parameters; and then constructs an evaluation function, and calculates the evaluation function value of each generation of individuals of the population, so as to conduct rounds of individual populations. The genetic operations of betting selection, discrete crossover and Gaussian mutation are used to establish an iterative process to obtain the optimal solution; finally, QT software is used to build a simulation software platform for USV collision avoidance planning, adding radar detection module and genetic algorithm, and designing a typical simulation case verification algorithm effectiveness. The invention solves the problems of poor timeliness of the genetic algorithm, falling into local optimum, premature convergence, and the optimal child generation being inferior to the parent generation optimum, as well as the problem of bad navigation such as large-angle steering and wide-scale acceleration and deceleration in the navigation process.

The invention relates to an intelligent micro-grid optimization scheduling method based on an improved particle swarm algorithm. Aiming at the problem of system energy uncertainty caused by renewable energy in the microgrid, the present invention introduces the idea of ​​annealing and mutation into the PSO algorithm, and uses the probabilistic jump characteristics of the simulated annealing algorithm to improve the global search ability of the particle swarm algorithm. At the same time, Using Gaussian mutation algorithm to focus on the local area near the individual area to search the characteristics of the particle swarm algorithm to improve the fine search ability. The invention can effectively improve the economy and reliability of microgrid operation.

The invention discloses a boiler four-pipe leakage acoustic detection precision positioning system for a power station and belongs to the technical field of boiler pipeline leakage detection positioning for a thermal generator set. A planar four-element boiler pressure-bearing pipe leakage precision positioning microphone array and the arrangement in a hearth thereof are designed according to thestructural characteristics of power station boilers. The time delay estimation is obtained through the maximized generalized likelihood cross-correlation, and by adopting a decimal floating-point coding self-adaptive Gaussian mutation algorithm, the determination of a precise position of the boiler pressure-bearing pipe leakage is realized. The boiler four-pipe leakage sound detection precision positioning system has the advantages of high precision and robustness.