32 results about "Niche genetic algorithm" patented technology

The invention discloses a bearing fault diagnosis method for NGAs synchronously optimizing wavelet filters and MCKD. First, use the sensor to collect the original vibration signal and input it, set the initial conditions of the Niche Genetic Algorithm (NGAs), and use the NGAs to carry out the Morlet wavelet filter center frequency and bandwidth, maximum correlation kurtosis deconvolution (MCKD) filter length and period Synchronous joint optimization, taking the correlation kurtosis (CK) of the occurrence characteristics of the bearing fault shock cycle as the optimization index, realizes the parameter adaptive synchronization optimization of the two processing steps before and after, adopts Morlet band-pass filter preprocessing, and MCKD performs in-band filtering on the filtered signal Noise reduction processing, and finally use the envelope spectrum of the MCKD in-band noise reduction signal to determine whether there is a fault and the type of fault. The analysis of simulation signal, laboratory signal and experimental data of Dongfang Institute shows that the method proposed in this paper can effectively eliminate the influence of external occasional interference impact and reduce the influence of signal transmission path and noise, ensuring the effectiveness of bearing fault diagnosis.

A single agent mobile path optimization method based on a multi-niche genetic algorithm and a storage medium are disclosed. Aimint at the path optimization problem, the multi-niche genetic algorithm and the Dijkstra algorithm are used to raise problems and analyze problems; the multi-niche genetic algorithm is used to perform population initialization, multi-niche genetic algorithm computation, decoding and fitness calculation; the usage of Dijkstra algorithm is improved, In a small number of path groups, searching whether there are connected paths to achieve the single agent shortest path optimization problem in combat simulation, which significantly improves the effectiveness and efficiency of single agent path optimization under constrained conditions in the process of combat simulation, reduces the overall computational load, and efficiently obtains the optimal solution of the problem.

The invention relates to a transmission network planning method based on a deterministic two-layer planning model. The planning model takes the investment cost of the power grid as an economical target, and takes the sum of load shedding of the system under normal and single-fault operation conditions as a reliability target. The lower-level goal is the reliability goal, and the lower-level constraints are the normal operation constraints of the system and the operation constraints under single-fault conditions; the upper-level objectives are mainly economical objectives, and the lower-level reliability objectives are added in the form of penalty functions, and the upper-level constraints are the lines to be erected Quantity constraints. The hybrid algorithm combining the improved niche genetic algorithm and the primal-dual interior point method is used to solve the model, and the niche genetic algorithm is used to process the integer variables of the upper-level planning for global optimization; the lower-level planning is carried out using the primal-dual interior point algorithm. Fast solution, improve algorithm speed and convergence. The invention adds the reliability problem into the economical planning with constraints, and realizes the optimal economical efficiency of the planning scheme under the condition of high reliability.

A method for optimizing the consumption of a micro-satellite group formation, which mainly includes the following steps: determining the factors related to the satellite orbit transfer time and fuel consumption as the transfer time and the terminal position; determining the inter-satellite coding structure in the satellite group; forming the satellite orbit transfer energy consumption calculation method; the niche genetic algorithm analysis is carried out on the energy consumption of the formed satellite orbit change transfer, and the optimal orbit change energy consumption data is formed, which is converted into the corresponding dual-pulse engine energy consumption control parameters. The invention combines niche technology and genetic algorithm, takes energy consumption as the optimization target, and is applicable to the situations of a single orbiting satellite, synchronous establishment of multi-satellite formation, and formation of multi-satellite asynchronous formation, and the algorithm has no requirement for the release location of the satellite group, and can Enhanced flexibility for release of microsatellite constellations. It not only retains the advantages of strong robustness, global search and parallelism of genetic algorithm, but also overcomes the disadvantage of poor local search ability of genetic algorithm.

The invention discloses a production operation scheduling method based on a clustering ecological niche genetic algorithm, and the method comprises the following steps: S1, building a multi-objectivefunction, proposing a multi-constraint condition, and building a production operation scheduling optimization mathematic model; S2, performing weighting processing on the multi-objective function based on a particle swarm weight optimization method, and converting the multi-objective model into a problem of a single-objective function; S3, dividing the population into K clusters according to a K-means mean clustering algorithm, and determining a clustering center; S4, performing selection, self-adaptive crossover, self-adaptive variation and niche elimination operation; and S5, judging whethera termination condition is met or not to obtain a final production scheduling scheme. The method aims at solving the problems that existing multiple targets in scheduling are difficult to solve and prone to falling into a local optimal solution. According to the scheduling method based on the clustering niche genetic algorithm, the three processes of determining the weight of the multi-objectivefunction, the radius of the niche and crossover and mutation operators are improved, the production scheduling capacity is effectively and remarkably improved, and the production cost is effectively saved.

The invention discloses a multi-objective flexible job shop scheduling method based on an improved niche genetic algorithm. The production scheduling sequence is constructed from the process data of all workpieces in the multi-objective flexible job shop, and the production scheduling sequence is used as an individual to generate the first generation population; calculate the total objective function value of the individual, and use the improved niche method to calculate the individual fitness value; The degree value uses the roulette method to select the individual set; implement the crossover operation and mutation operation of the genetic algorithm; form a new population between the obtained individual and the individual with the highest fitness value in the current generation population; repeat the steps until the termination condition, and output the last generation The optimal individual in the population uses the optimal individual's production scheduling sequence to arrange processing to achieve multi-objective flexible job shop scheduling. The invention adopts the improved niche genetic algorithm to deal with the scheduling problem in the production process, can stably obtain high-quality scheduling results, optimize the allocation of workshop resources, and thereby improve the production efficiency of the workshop.

The invention discloses an optimal design method for a high-low pressure compressor transition flow channel, which is used to solve the technical problem of large flow loss in the compressor transition flow channel designed by the existing compressor transition flow channel design method. The technical solution is to preliminarily determine the geometric shape of the transition flow channel of the compressor through the existing design method, and then use the Bezier curve to construct the end wall profile line equation that meets the initial design results, and further superimpose the constructed support plate on this basis . Then the geometric parameters of the casing and the hub are randomly generated, and a new profile is generated. Then the through-flow is used to solve the performance parameters of the flow field. Finally, taking the total pressure loss coefficient at the outlet of the support plate as the optimization objective function, and taking the gradient of the static pressure recovery coefficient along the hub as the constraint condition to be smaller than the gradient of the pressure recovery coefficient before optimization, the niche genetic algorithm is used to optimize until it evolves to a given generation until. Since the Bezier curve is used to construct the profile equation of the transition channel of the compressor, the flow loss of the designed transition channel of the compressor is reduced.