4 results about "Optimal criterion" patented technology

This invention relates to the fields of civil engineering structural safety inspection and machine learning technology, and discloses a machine learning-based collaborative evaluation method and system for the mechanical properties of concrete components. The method constructs a coupled graph of mechanical indices with confidence levels, trains a missing-node-aware joint evaluation model, and suppresses the propagation of noise from missing nodes through joint attenuation of observability masks and edge confidence weights. Then, it performs weighted SHAP interaction effect analysis and hierarchical verification, and generates a supplementary detection scheme with comprehensive information gain ranking based on the D-optimal criterion. Through iterative closed-loop optimization, it outputs the collaborative evaluation results and evaluation confidence levels of the concrete component's compressive strength, splitting tensile strength, and elastic modulus.

The application discloses a phase transition super-elastic material topology optimization method based on a nonlinear constitutive model and belongs to the technical field of intelligent material structure design and multi-physical field optimization. The method comprises the following steps: establishing a super-elastic constitutive model containing a martensitic volume fraction to describe the coupling relationship between material phase transition behavior and mechanical properties; constructing a topology optimization model with the minimum structural flexibility as an objective and the volume fraction and a balance equation as constraints; adopting an additional super-elastic technology of dynamic reconstruction to solve the numerical instability problem in the optimization process; performing sensitivity analysis through an adjoint vector method; and obtaining an optimal topology configuration through iterative solution by using an optimal criteria method. The application can efficiently and stably realize the structure optimization of the phase transition super-elastic material, significantly improves the calculation efficiency and numerical stability of the optimization process, and is suitable for the structure design of intelligent materials such as shape memory alloys in the fields of aerospace, medical devices and the like.

The invention discloses a servo controller accelerated degradation test method based on multi-parameter optimization. The method comprises the following steps: constructing a servo controller multi-parameter accelerated degradation model: constructing the servo controller multi-parameter accelerated degradation model through a Wiener process model, an Arrhenius model and a Gaussian Copula function; constructing a multi-parameter comprehensive optimal criterion; deducing a service life distribution function of the servo controller at a normal working temperature; on the basis of a V-optimal criterion, a multi-parameter comprehensive optimal criterion is constructed by taking minimization of the quantile life asymptotic variance of the servo controller as an optimization target so as to form an optimization target function; and constructing and solving an accelerated degradation test optimization model: constructing the accelerated degradation test optimization model by taking the optimization target function as a target, and solving the accelerated degradation test optimization model by adopting a genetic algorithm to obtain a servo controller accelerated degradation test scheme. The evaluation precision of predicting the service life and reliability of the servo controller based on the test data is remarkably improved.

The invention discloses a gradient method-based two-dimensional photonic crystal multi-target topological optimization method, which comprises the following steps of: constructing a finite element analysis model of a photonic crystal, taking the relative density of a unit as a design variable, and parameterizing material attributes by adopting a material interpolation model; discrete characteristic frequency data are acquired and smoothed; constructing a multi-objective optimization problem with the objective of simultaneously maximizing the band gap width and minimizing the structural flexibility, or simultaneously maximizing the band gap width and minimizing the thermal flexibility; respectively calculating the sensitivity of each target function to the design variable, and carrying out normalization processing; carrying out weighted fusion on the normalized sensitivity; filtering and historically averaging the sensitivity field to smooth the update process; a clear topological structure is obtained by using Heaviside projection; updating design variables based on an optimal criterion method; and iteratively optimizing until a preset convergence criterion is met, and outputting an optimal topological configuration. The design efficiency of the comprehensive performance of the photonic crystal is remarkably improved.