63results about How to "Increase population diversity" patented technology

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 a mixed flow assembly production scheduling control method based on a bee society self-organization model. The method comprises the following steps of: 1, setting algorithm parameters according to scale of mixed flow assembly production scheduling problems; 2, selecting a random +NEH method for an initialization function aiming at characteristics of the mixed flow assembly production scheduling problems; 3, dynamically adjusting a searching scale in neighboring areas; 4, performing an employment bee algorithm on each employment bee, and triggering a scout bee algorithm to replace the employment bee when the employment bee meets a limit parameter; 5, performing an observation bee algorithm on each observation bee, and triggering the scout bee algorithm to replace the observation bee when the observation bee meets the limit parameter; 6, performing an optimal control algorithm on the employment bee population and observation bee population; and 7, stopping the operation when iteration conditions are met, otherwise repeating the steps from 3 to 7. The method has high speed, high neighboring searching precision, high solution efficiency and good control effect, and local optimum is effectively avoided.

The invention discloses a flower pollination algorithm optimization method based on adaptive Gaussian mutation. Firstly, the population is firstly ranked according to adaptability values and is grouped, and then the position of the worst individual in each group is updated, thereby enhancing the local depth search ability of the algorithm and enhancing the population diversity; and secondly, whether the algorithm falls into the local optimization is dynamically monitored through a bulletin board, and if yes, a Gaussian mutation operation operator is automatically introduced, mutation operation is executed on the global optimal individual, thereby not only improving the ability of the individual jumping out of the local optimization but also enhancing the population diversity and quickening the convergence rate. The method of the invention has better stability, better reliability, quicker convergence rate and higher optimization precision.

The invention discloses an intelligent optimization method and system for ecological operation of cascade hydropower stations, belonging to the technical field of efficient utilization of water resources and optimal operation of hydropower systems. The method comprises the following steps: establishing a cascade hydropower station reservoir operation model which takes the minimum ecological watershortage as an objective function and considers a complex constraint set; Knowledge rules are used to dynamically generate the initial scheduling process, and the initial population is generated by random disturbance in its neighborhood. All individuals are modified to feasible search space in turn, individual fitness value is calculated by penalty function method, individual position and velocityare updated dynamically, and neighborhood search is carried out by adaptive mutation strategy. The search process described above is repeated until the termination condition is met. The invention hasthe advantages of clear and simple principle, fast convergence speed and the like, and the obtained result is reasonable and feasible, and can provide strong technical support for rational allocationof hydropower resources.

The invention discloses a central air conditioner parallel refrigerator load optimal distribution method based on a swarm intelligent framework. A controller is arranged in each refrigerator in a parallel refrigerator system, and all controllers in the parallel refrigerator system are connected according to an actual physical topology connection relationship of the refrigerators to form a swarm intelligent network system; when one certain controller initiates an adjustment task, the remaining controllers cooperate with the controller initiating the adjustment task to perform information interaction with the respective neighbor controllers, response system operation is completed in allusion to the adjustment task, and autonomous coordination adjusting operation of the parallel refrigerator system is achieved; and a distributed chaos distribution estimation method is used for conducting optimized calculation on an objective function to complete an optimal assignment task. The central air conditioner parallel refrigerator load optimal distribution method improves the working efficiency, reduces system energy consumption and saves energy.

The invention discloses a calculation unloading distribution method of an edge server. The method comprises the following steps of: constructing a to-be-optimized vector according to the proportion oftasks executed by each user terminal on an edge server in the tasks of the user terminal; utilizing a first target sub-function, a second target sub-function and a third target sub-function to construct a target optimization function, wherein the first target sub-function is the sum of the calculation time of locally executing tasks on all user terminals and the calculation time of executing tasks on the edge server, the second target sub-function is the sum of the energy consumption of locally executing the tasks on all the user terminals and the energy consumption of executing the tasks onthe edge server, and the third target sub-function is the sum of the charges generated by executing the tasks on the edge server; and solving the optimization value of the to-be-optimized vector by utilizing the target optimization function, and correspondingly configuring the proportion of the tasks executed by each user terminal on the edge server in the tasks of the user terminal according to the optimization value of the to-be-optimized vector.

A tunnel tunneling feasibility prediction method and system based on a TBM rock-machine parameter dynamic interaction mechanism includes: creating device information and rock mass information sample databases; analyzing and calculating a rock mass information sample database of a rising section of TBM tunneling parameters to obtain rock mass information weights under a condition of different device states; determining convergence conditions in different device information states through the rock-machine parameter dynamic interaction mechanism, and obtaining an optimal solution of tunneling parameters of a stable section of the TBM tunneling parameters under a condition of different rock mass information; and creating an optimal tunneling formula applicable to TBM tunneling through the obtained weight information and the optimal solution of the tunneling parameters of the stable section, performing TBM tunneling feasibility classification, and predicting TBM tunneling efficiency. Indexes of device parameters and rock parameters are selected based on TMB construction features.

The invention discloses an ecological regulation and control method and system for a cascade hydropower station group, and belongs to the field of cascade hydropower station group optimization and ecological dispatching, and the method comprises the steps: taking the water level of each power station in the cascade hydropower station group as an individual in a group, setting the maximum number ofiterations, and randomly initializing the group; updating the global optimal position of the current population in the iteration process; updating the position of each individual in the current population by utilizing the speed of each individual in the current population; zooming the globally optimal position of the current population by using the Levy random number, subtracting the zoomed position of each individual in the current population from the globally optimal position of the current population, and superposing the zoomed position with the random individual in the current populationto obtain the mutated position of each individual in the current population; and taking the global optimal position when the maximum number of iterations is reached as the optimal scheduling scheme ofthe cascade hydropower station group. The invention is high in convergence speed, and can effectively avoid falling into local optimum.

The invention discloses a global optimization method for multi-thread operation of AGVs used for scheduling of cigarette ingredients. The method comprises the following steps: constructing a time sequence constraint matrix and a resource constraint matrix; initializing particle swarm by adopting a random generation task priority and an execution method; encoding particle individuals according to arandom rule and a random execution method; decoding the particle individuals; calculating a local optimal solution of the particle individuals and a global optimal solution of initial particle swarm;and updating the particle individuals based on the local optimal solution and the global optimal solution, and randomly changing the value of a certain coding position to generate new particle individuals. According to the global optimization method for multi-thread operation of AGVs used for scheduling of cigarette ingredients, updating iteration is conducted on all the particles by means of local solutions and global optimal solutions of the individuals in all the stages, and mutation operators are added to increase population diversity, so the advantages that a particle swarm algorithm iseasy to achieve and fast in convergence are reserved, proneness to falling into the local optimal solutions is avoided, and a solution can be provided for task scheduling of multiple AGVs in distribution operation.

The invention discloses a virtual reality based crowd simulation method and system. The method includes: step (1), establishing a building and obstacle model library; step (2), respectively establishing a real person database, a model database of people with physique differences and a character attribute library; step (3), establishing a character library according to results of the step (2); step(4), establishing a virtual reality scene according to results of the step (1) and the step (3); step (5), testing the virtual reality scene; evaluating a test result, and outputting an evaluating result. By combination of person models and character attributes, various characters can be created; in addition, the real person database enables direct use of real person mapping which includes various attributes of real persons; moreover, due to real person control of the system, crowd diversity in crowd simulation is further improved.

Provided is a logistics distribution path planning method based on regional multi-strategy. The method includes: firstly, encoding an optimization problem of a vehicle distribution path according to adistribution place and a vehicle, and converting the optimization problem to a variable with an algorithm capable of being optimized; then designing a differential evolutionary algorithm based on theregional multi-strategy for a distribution path optimization model, classifying similar individuals as one category through partitioning, selecting the individuals from different categories in a variation process to guide variation, generating test individuals of each individual by employing two different variation strategies, and selecting the superior test individual for update to improve the algorithm searching efficiency, increase the population diversity and avoid premature convergence; and finally decoding an optimal solution obtained through optimization according to an encoding rule to obtain an optimal distribution path scheme. According to the logistics distribution path planning method based on regional multi-strategy, the searching speed is fast, and results are reliable.

The invention discloses a DG grid connection optimization configuration method based on the improved genetic algorithm. The method comprises the following steps: Step 1, establishing an objective function based on system losses, voltage deviations and economical performances; Step 2, establishing equality constraints according to the objective function; Step 3, establishing inequality constraints;and Step 4, using the reciprocal of the objective function as a fitness function, and calculating the optimal solutions through the genetic algorithm to obtain an installation position and an installed capacity of a DG. The method disclosed by the invention has the advantages that the problem in the prior art that voltages of nodes in a power distribution system cannot be effectively improved after adoption of an installation position and an installed capacity of the DG because the installation position and the installed capacity of the DG are determined mostly based on empirical equations and human judgments is solved, the system losses are reduced, and the system operation stability and the power supply safety are improved.

The invention discloses a grey wolf algorithm-based economic back pressure optimization method for a wet cooling unit of a thermal power plant. The method aims to maximize the net economic benefit obtained by power generation of a cold end system of the unit, and the net economic benefit is mainly composed of the economic benefit brought by the increase of the power generation power of the steam turbine, the economic cost required for circulating water flow regulation and the economic cost required for circulating water temperature regulation. The method is based on a wet cooling unit back pressure model, takes unit operation conditions, circulating water flow and condenser inlet circulating water temperature as input variables, takes unit back pressure as an output variable, adopts a greywolf algorithm after position updating strategy improvement and population evolution mechanism improvement, and the optimal back pressure can be found more quickly and accurately through the random and rapid traversal of the input variables. According to the method, the problem that the economic back pressure of the thermal power plant is difficult to determine due to equipment parameters and operation condition changes is solved, the time required for determining the economic back pressure of the unit is effectively shortened, and the optimization precision of the economic back pressure is improved.

The invention discloses an unmanned aerial vehicle cluster collaborative ground strike method based on an improved wolf pack optimization algorithm, and the method comprises the steps: firstly, building a task distribution model which comprehensively considers the performances of unmanned aerial vehicles, carrying reconnaissance resources, target information, time sequence constraints, balanced strike and other conditions; secondly, considering the problem that a traditional wolf pack algorithm is not suitable for task allocation, and redesigning a discrete wolf pack algorithm in order to improve the global optimization efficiency of the algorithm; and then, combining with a 2-opt reverse mutation algorithm and a new encoding and decoding mode, and providing an improved wolf pack optimization algorithm. The multi-constraint multi-task distribution model established by the invention and the improved wolf pack optimization algorithm successfully meet the effectiveness and superiority of the distribution scheme on the ground strike problem, and meanwhile, the task time sequence constraint is met after the decoding is completed.

The invention provides a pressure vessel structure optimization method based on an improved Harris eagle optimization algorithm. The method comprises the following steps: firstly, determining all variables and change ranges affecting the structural performance of a pressure vessel through the mathematical modeling of the pressure vessel, and building a target function for the structural optimization of the pressure vessel; and then, optimizing the target function by utilizing an improved Harris eagle optimization algorithm to obtain an optimal value of each variable of the pressure vessel structure. According to the method, the adaptive cooperative foraging strategy is embedded into the one-dimensional position updating framework, and the one-dimensional updating operation and the traditional full-dimensional updating operation are adaptively selected according to the conversion factor, so that the population diversity of the algorithm is effectively improved; through a decentralized foraging strategy, part of Hamilk individuals are randomly decentralized to other areas for foraging, and the algorithm is prevented from falling into local optimum; according to the method, the consumption process of prey energy is better simulated by adopting a random exponential decay function, and the defect that the exploration stage and the development stage are unbalanced is overcome.

The invention discloses a crowd generation and simulation method and system based on an image segmentation algorithm. The crowd generation and simulation method comprises the following steps of constructing a crowd simulation three-dimensional person model or selecting an existing three-dimensional person model from a crowd simulation person model library; carrying out texture map drawing on the appearance of the three-dimensional person model and storing the texture map; unfolding an original texture map, storing the unfolded original texture map in a person model texture map library, and extracting the texture map from the person model texture map library; carrying out segmentation treatment on the texture map by using the image segmentation algorithm, and canceling superfluous edge andpoint in the texture map, so as to obtain a new texture map; mapping the new texture map on the three-dimensional person model; canceling superfluous edge and point of the three-dimensional person model, so as to generate a new person model; storing the new person model in a person reduced model library; giving the new person model to the original texture map, storing the new person model with thetexture map, and storing in a complete person library. The simulation calculation efficiency of a crowd is improved.

The invention discloses a feature selection method based on an improved suburb wolf optimization algorithm. The method comprises the following steps: obtaining features to be selected from a data set;initializing a suburb wolf population to obtain social conditions of suburb wolves; converting social conditions of the suburb wolves into binary data; calculating a fitness function value; determining a first wolf in each subgroup; calculating the cultural tendency of each subgroup; updating all suburb wolves in each subgroup; enabling each subgroup to generate a binary newborn suburb wolf; enabling each subgroup to execute a birth-death mechanism; migrating a part of suburb wolves among the subgroups; updating ages of all suburb wolves; judging whether the current number of iterations reaches a preset maximum number of iterations or not; and selecting a feature corresponding to the suburb wolf with the best social condition in the population as an optimal feature subset. The method is few in algorithm adjustment parameters, high in search efficiency, accurate in feature selection and high in self-adaptive capacity, and the optimal feature combination can still be quickly searched under the condition that excessive human parameter adjustment intervention is not needed.

The invention discloses a ring topology Gaussian dynamic particle swarm optimization algorithm-based ship power grid reconstruction method and belongs to the field of swarm intelligent computation. Essentially, the ship power grid reconstruction problem belongs to a multi-target multivariable discrete optimization problem, and in the prior art, the defects of being long in computation time and easy to search non-satisfactory solutions during the processing of ship power grid reconstruction problems and the special requirements of the ships for the safety and instantaneity are difficult to satisfy. According to the ring topology Gaussian dynamic particle swarm optimization algorithm-based ship power grid reconstruction method, a ring topology is introduced in a discrete GDPS optimization algorithm to ensure that the information exchange among particles is relatively slow; when several particles get into local extremum, the influence on the other particles is small so that the search of globally optimal solution is more facilitated. Meanwhile, the ring topology is relatively simple so that the computation time can be remarkably shortened. The method provided by the invention can be used for keeping the swarm diversity in the whole search process so as to obtain quicker and better global optimization effect.

The invention discloses a microbial sewage treatment system and a sewage treatment method. The system includes a microbial combination tank, an aeration system, a sludge collection system, a sludge transportation system and a recovery system. The recovery system includes a regeneration recovery tank, which is divided into an upper part and a lower part by an electromagnetic disk, a filter materialis installed at the upper part for phosphorus recovery, and an aeration device and a magnetic powder recovery mechanism are installed at the lower part to recover magnetic powder. The sludge collection system realizes the collection of magnetic activated sludge, and the sludge transportation system realizes reflux transportation of magnetic activated sludge outside the tank. The system adopts themagnetic field induced HAP crystallization method to enhance phosphorus removal, and utilizes the dual purposes of the magnetic field to realize simultaneous recovery of phosphorus and magnetic powder. While an original sewage treatment system is reconstructed, the system can achieve production and construction simultaneously. With the system and method provided by the invention, after sewage treatment the water quality is obviously improved.

The invention discloses a generator excitation system parameter identification algorithm based on an improved grey wolf algorithm. The generator excitation system parameter identification algorithm comprises: establishing an original model and an actual system model of an excitation system in a no-load state; identifying the actual system model entering the linear region through an improved grey wolf algorithm to obtain linear part parameters; inputting the linear part parameters into an actual system model; and identifying the actual system model which enters the non-linear region and is substituted with the linear part parameters through an improved grey wolf algorithm to obtain the non-linear part parameters. On the basis of the grey wolf algorithm, a convergence factor nonlinear decreasing strategy and a grey wolf grouping alternate chasing strategy are provided, population diversity of wolf groups is enhanced, and the defect that the algorithm is prone to falling into local optimum is overcome. The grey wolf algorithm is applied to identification of excitation system parameters, identification of the excitation system parameters is effectively achieved by improving the grey wolf algorithm, and an identification result proves that the identification precision and stability of the improved grey wolf algorithm are superior to those of a traditional grey wolf algorithm.