7 results about "Genetic algorithm" patented technology

The invention discloses an optimization design method of a radial-flow-type hydraulic turbine. In the design method, a unitary thermal optimization design, a three-dimensional modeling method of a through-flow part and a complete machine optimization platform are utilized, wherein the optimization platform comprises four modules, namely nozzle blade and impeller blade parameterization, a coevolution genetic algorithm, a self-adaption approximation model, and autocall of CFD (computational fluid dynamics). Through the parameterization, characteristic variables describing impeller blades, nozzle blade patterns and installation angle variation are extracted. The optimization target is to enhance the overall efficiency and expansion ratio of the hydraulic turbine simultaneously under a complete machine environment. The optimization platform can be used for reducing the calculated amount and accelerating the convergence by virtue of the following measures: the approximation model is built and updated by a dynamic sampling strategy, and enough prediction accuracy is obtained by virtue of less CFD calculation; and a complicated multivariable optimization problem is decomposed into a plurality of relatively independent and interactive subproblems by virtue of the coevolution genetic algorithm, so that not only can the characteristics of the original problem be maintained, but also the calculated amount is reduced effectively.

The invention relates to a method for using man-made feature sparse shape points to automatically generate a feature contour. The method has the advantages that a feature contour method based on a genetic algorithm is applied to a construction feature region description system, and the feature contour is generated automatically through the feature sparse shape points; a good sealing line connection scheme is searched accurately through the successive generation optimization operation of the genetic algorithm so as to form the feature contour region; the method is applicable to description of optional sealed regions, so that area equal-quantity statistic can be performed on one region; in addition, the time defects using a violence method for searching and the precision defects of a greedy algorithm are overcome, and time-precision balance can be achieved; due to the fact that the genetic algorithm is high in robustness, the genetic algorithm is quite applicable to sketching of real world complex regions.

The invention discloses a new energy vehicle energy storage optimization control method based on a multi-objective genetic algorithm, which comprises the following steps: establishing a control strategy database of the vehicle-mounted energy storage system; establishing characteristic data module of vehicle energy storage system; establishing the evaluation module of multi-factor coupled energy storage system to evaluate the advantages and disadvantages of the current control strategy in the whole life cycle; a multi-objective genetic algorithm is used to optimize the energy-saving control strategies. By comparing and analyzing the effect of each control strategy, the optimal control strategy of new energy vehicle energy storage is obtained under the coupling of multiple factors. Under thecondition that the passenger comfort degree is ensured, the speed command designed by the invention can realize traction energy saving. The speed command obtained from the final design meets the requirements of non-dominated standards, which is very beneficial to the decision-making based on the time uniform distribution standard and the energy consumption sensitivity standard. Aiming at the energy-saving optimization of speed commands under various control strategies of energy storage system, the optimal control strategy of vehicle-mounted energy storage system can be obtained through the comparative analysis of its effects.

The invention belongs to the technical field of data analysis, and discloses a computer system for economic management data analysis. The computer system comprises an input module, a genetic algorithmmodule, an output module, a linearization transformation module, a calling module, an economic management database and a modeling prediction module, wherein the input module is connected with the genetic algorithm module and the linearization transformation module; the genetic algorithm module is connected with the output module; the linearization transformation module is connected with the calling module and the modeling prediction module; the calling module is connected with the economic management database. The invention provides a systematic and logical analysis method, by which several factors such as demand, production, cost and market are comprehensively considered and an optimal solution of a multivariate problem is calculated according to a genetic algorithm; logratio transformation and modeling can be also performed according to data in the database, to predict economic management data.