5 results about "Robust design" patented technology

The invention relates to an aerodynamic stability quantification method and system based on flow mechanism and deep learning coupling, and the method comprises the steps: compressing the high-dimensional point cloud data of a manufactured blade into a low-dimensional basic mode based on principal component analysis, and effectively relieving the variable dimension disaster problem caused by geometric uncertainty; and then, by taking the low-dimensional fundamental mode weight as input, directly embedding the key physical characteristic, namely the blade tip leakage flow rate ratio, into a deep neural network hidden layer and taking the gas compressor stability margin variable quantity as output, constructing a physical constraint and data driving collaborative optimization framework, and remarkably improving the prediction precision of the pneumatic stability of the gas compressor under the small sample condition. According to the method, a quantification tool with high precision and physical credibility is provided for solving the problem of performance degradation caused by geometric deviation of the CAES multi-stage axial flow compressor under the non-design working condition, and key technical support is provided for achieving robustness design of the CAES multi-stage axial flow compressor.

The invention discloses an uncertainty analysis method and system for turbine blade tip gas thermal performance. The method comprises the steps that firstly, key structure parameters of a turbine blade tip are determined to serve as uncertainty variables, and a multi-precision sample set is constructed; then, a multi-fidelity deep neural network model is constructed by adopting a prediction sub-network and a correction sub-network which are cascaded, and a mapping correction relation from low precision to high precision is established through staged training; carrying out gas-heat performance distribution analysis by utilizing the trained blade tip gas-heat performance prediction network model, and quantifying the influence degree of each uncertainty variable on performance fluctuation in combination with a Sobol global sensitivity analysis method; and finally, screening significant parameters according to the influence degree sequence, and determining an optimal value combination of the significant parameters to form a design scheme for enabling the turbine blade tip gas-heat performance to approach to global optimization. According to the method, the dimension limitation of high-dimensional uncertainty analysis is effectively broken through, the calculation efficiency and the prediction precision are remarkably improved, and reliable technical support is provided for robust design of the turbine blade top.

The application discloses a robust design method of surface-mounted permanent magnet synchronous motor considering manufacturing tolerance, and the method is as follows: step 1, a parameterized model and a data set of the surface-mounted permanent magnet synchronous motor are established; step 2, a multi-output proxy model based on integrated learning is constructed; step 3, a manufacturing tolerance model is constructed; step 4, a robust genetic algorithm considering manufacturing tolerance is executed; and step 5, evolution optimization and verification are performed. Through construction of a high-precision mapping model of structure parameters-performance indexes, and embedding tolerance analysis based on Monte Carlo sampling in the individual evaluation link of the genetic algorithm, the performance robustness optimization of the motor design scheme in the manufacturing error environment is realized. Compared with the method of optimization only under the nominal size, the application can significantly reduce the performance discreteness of batch products, improve the tolerance to manufacturing deviation and the qualified rate while maintaining the motor efficiency and output torque level, and is suitable for structural design and parameter optimization of various permanent magnet motors.

The invention provides a power battery liquid cooling plate robustness optimization method and system fused with uncertainty modeling. The method comprises the following steps: 1) constructing a high-precision numerical simulation model and planning a proxy model training sample set; 2) constructing a liquid cooling plate size-performance mapping agent model; 3) constructing a probability distribution model of the key geometric parameters; 4) in combination with Monte Carlo random sampling and an agent model, quantifying statistical characteristics of each performance index under manufacturing disturbance; 5) taking the standard deviation and mean value minimization of the performance response as an optimization target, and constructing a multi-target robust optimization model; and 6) solving the Pareto optimal solution set by adopting a multi-objective evolutionary algorithm, and outputting the optimal nominal design parameter meeting the engineering preference and the corresponding key performance fluctuation level.According to the method, a robust design scheme which is most insensitive to manufacturing disturbance is realized in a feasible design domain, and the performance consistency of liquid cooling plate batch production is remarkably improved.

This invention relates to the field of turbomachinery performance evaluation technology, and discloses a method for quantitatively evaluating the performance uncertainty of turbomachinery blade geometric deviations. The method includes parametrically modeling geometric deviation characteristics and sampling to construct a sample; generating a three-dimensional blade simulation model based on the sample by performing deviation modeling on the original design blade profile; performing aerodynamic simulation calculations on the simulation model; extracting aerodynamic indicators using a condition control strategy to construct a mapping database; training a surrogate model using the database to establish mapping relationships; and finally using the surrogate model to perform aerodynamic performance inference to complete the evaluation. Furthermore, interpretable machine learning methods are combined to calculate contribution to identify geometric features highly sensitive to aerodynamic performance. This invention overcomes the limitation of two-dimensional evaluation in failing to consider radial flow effects by reconstructing a three-dimensional simulation model, and eliminates flow deviation operating errors by employing a condition control strategy, providing a quantitative decision-making basis for robust design, machining tolerance setting, and cleaning and maintenance schemes for turbomachinery.