5 results about "Central composite design" patented technology

The application provides a floor grinding machine gear box guide plate structure parameter optimization design method, which is used for determining the optimal values of three radial clearances between the guide plate and the gear tooth top. Firstly, a parameterized gear box model containing clearance as a variable is constructed, and a gear oil stirring loss theoretical model is established based on the boundary layer theory and the fluid resistance theory; taking the maximum lubrication efficiency as the target and the oil stirring power loss not exceeding the set threshold as the constraint condition, a central composite design method is used to select representative sample points in the design space; through computational fluid dynamics simulation, a moving particle semi-implicit method is used for splash lubrication transient analysis to obtain performance data of each point; based on the simulation data, a high-precision proxy model is constructed; finally, under the condition of meeting the oil stirring power loss constraint condition, the maximum lubrication efficiency is taken as the target for optimization solving to obtain the optimal clearance combination. The method realizes the quantitative design from parameters to performance, and effectively replaces the traditional trial and error method.

The present application relates to the technical field of laser cladding, and discloses a laser cladding layer forming quality regulation method and system based on a molten pool powder island, which comprises the following steps: constructing a plurality of different process parameter value combinations based on central composite design according to the value range of each process parameter in the laser cladding process; obtaining the molten pool image in the laser cladding process under each process parameter value combination, extracting the molten pool area and the powder island area to obtain the powder island area proportion, and constructing a relationship model between the powder island area proportion and each process parameter value; determining the optimal value range of the powder island area proportion according to the relationship between the laser cladding layer forming quality and the powder island area proportion; and in the laser cladding process, controlling the value of each process parameter in real time according to the relationship model so that the real-time powder island area proportion is within the optimal value range. The present application can optimize the process parameters in real time, improve the efficiency and the laser cladding layer forming quality in the laser cladding process.

This invention discloses a multi-objective optimization method for motors that integrates neural networks and NSGA-III, relating to the fields of motor body design optimization and neural learning technology. The method first clarifies the optimization objectives and design variable constraints of maximizing average torque, efficiency, and minimizing torque ripple. Samples are collected and preprocessed through central composite design and finite element simulation. An FNN-CNN hybrid mapping model is constructed, simultaneously extracting local and global features, and establishing a high-precision mapping relationship with a MAE less than 3% as the training termination condition. Based on NSGA-III, θ dominance relations, density indices, and FC functions are introduced to optimize Nadir point estimation and genetic operations, achieving multi-objective collaborative optimization. Finally, the optimization effect is verified through finite element simulation. This invention improves mapping accuracy and the uniformity of the optimized solution distribution, has a faster convergence speed, and strong robustness, making it applicable to various permanent magnet motors and effectively solving the problems of inaccurate modeling and inefficient convergence in traditional methods.

The application discloses a torque optimization method for an outer rotor permanent magnet synchronous motor, and comprises the following steps: 1) design parameter selection: selecting key characteristics of a motor stator slot as design parameters, including slot shoulder height H s1 , tooth length H s2 , chord length B s0 and slot shoulder width B s1 ; 2) finite element model construction: establishing a multi-objective finite element model with tooth slot torque, torque ripple and average torque as targets; 3) analytical model establishment: establishing an analytical model of motor torque by using an energy method and a repeating unit method, and comparing with the finite element model to verify the accuracy of the analytical model; 4) response surface model construction: based on simulation data of the finite element model, performing finite element analysis by using a central composite design (CCD), constructing a response surface model, and performing sensitivity analysis on design variables to determine the influence of each variable on optimization targets; and 5) optimization efficiency improvement: determining an optimal configuration in a design space by using an adaptive genetic aggregation algorithm (AGA), so as to achieve a multi-objective optimization effect.

The invention discloses an asphalt mixture mix proportion design method based on a response surface method, and aims to solve the problems of high subjectivity, insufficient optimization and low efficiency and precision of traditional asphalt mixture mix proportion design. The method comprises the following steps: determining key design variables and response indexes, arranging an experimental scheme by adopting a central composite design in a response surface method, and combining a three-control-point hyperbolic theory to generate complete mineral aggregate gradation; a test piece is prepared, performance indexes are tested, a quadratic polynomial prediction model is established, an optimal design variable combination is solved through multi-objective optimization, and finally the optimal mix proportion is determined through verification. According to the method, on the basis of a mathematical statistical method, human experience interference is reduced, multi-factor interaction can be accurately quantified, the global optimal mix proportion is obtained with fewer test times, the performance potential of the material is maximized, and scientific and efficient technical support is provided for asphalt mixture design.