40results about How to "Improve optimization design efficiency" patented technology

The invention discloses a material breakage constraint-based continuum structure topology design modeling and optimization design method, which is used for solving (a) problems of stress concentration and singularity, and (b) a problem of maximum stress fluctuation and a problem of high analyzed and calculated quantity in different degrees in the prior art. In the method, effective stress constraint relaxation is adopted to treat the phenomenon of stress singularity. In the process of optimizing problem approximation modeling, a q1 norm metrical function of the structural stress serves as a penalty function, all unit stress constraints are replaced by q2 norm metrical function constraint of the structural stress, the most potential active unit stress constraints and the introduced volume constraints, and the local stress level is controlled by combining variable constraint limit. The optimization process of the method is divided into two optimization stages and a conversion stage, and the design space is automatically expanded and reduced. A quadratic programming method is utilized to solve each stage, a pure optimized structural topology in black/white distribution can be obtained, and the method has high optimization design efficiency.

The invention relates to an optimum design method for an aircraft system based on a sequence radial basis function surrogate model and belongs to the technical field of optimum design of the aircraft system. According to the optimum design method, the thought of searching step range of trust domain solving high-dimensional optimization problem is applied to a supervisory sequence surrogate model, the sample space is gradually updated and the approximate precision of the surrogate model is promoted, so that the optimizing strategy convergence is guided to the globally optimal solution and the optimum design method provided by the invention has better global optimization capacity and optimization efficiency. The method is strong in universality. According to the method, the program development is conveniently realized, the optimum design means for the aircraft system is improved, the design cost is lowered and the requirement for multidisciplinary optimum design of the present aircraft system is met.

The invention discloses a roll groove design method for a seamless steel pipe stretch reducing machine set, which can reduce difficulty in optimal design and satisfy needs for product pipe profile and wall thickness control, and comprises the following steps: 1, collecting equipment parameters and variety specification ranges of a seamless steel pipe stretch reducing machine set; 2, selecting products of steel pipe representative specifications and determining the weighting coefficient of every specification; 3, setting a groove curve equation(Y=a0+a1*2+a2*4+,..., +an*2n) by using a0, a1, a2,..., and an as the groove curve parameters of the machine frames of the seamless steel pipe stretch reducing machine set; 4, setting a target function for optimizing groove curves, and determining the optimal values of the groove curve parameters by using an optimal design method; and 5, substituting the optimal values of the groove curve parameters into the groove curve function to obtain the required groove curves of every machine frame of the seamless steel pipe stretch reducing machine set. When the method of the invention is used, the optimization process of the groove design can be simplified, and the designed groove can meet the pipe profile requirements of products and has uniform wall thickness.

The invention provides a design method of a baffle for controlling distribution of film thickness of a planar optical element in a film coating planetary system. In a vacuum film coating process, the film material is delivered in a vacuum environment through an evaporating mode or a splashing mode, and forms a film with non-uniform thickness distribution on the surface of a planar optical element. Models are respectively established for really reflecting the distribution of the thickness of film deposited on the planar optical element in a planetary system of a vacuum film coating machine under the condition that a baffle is not used and the baffle is not used for correcting. The evaporating or splashing property of the film material in the vacuum film coating process is determined according to the film thickness distribution model under the condition that the baffle is not used, and then the distribution of the thickness of the film on the planar optical element in the planetary system of the vacuum film coating machine is simulated based on a film thickness distribution model theory in the presence of the correcting of the baffle. And finally the baffle design is optimized through a computer until the distribution of the thickness of the film on the planar optical element subject to the baffle correcting in the planetary system of the vacuum film coating machine meets the design requirement, so that the optimal baffle design is obtained. The design method can be applied to precisely controlling the distribution of the thickness of the film on the planar optical element.

The invention discloses a transfer learning-based satellite part temperature field determination method. The method comprises the steps of establishing a simplified structure model of electronic partlayout; acquiring a plurality of electronic part layout schemes under a first grid scale and a first boundary condition, calculating corresponding temperature field distribution, and processing the schemes and the temperature field distribution into standardized data; constructing a deep learning model, and determining model parameters of the deep learning model by utilizing the standardized data;acquiring a plurality of electronic part layout schemes under different grid scales and different boundary conditions, calculating corresponding temperature field distribution, and processing the schemes and the temperature field distribution into standardized data; updating model parameters of the deep learning model by utilizing the standardized data; and inputting the electronic part layout scheme of the temperature field distribution to be calculated into the deep learning model to obtain the temperature field distribution. The method can achieve the quick obtaining of the temperature field distribution corresponding to the electronic assembly layout under different grid scales and different boundary conditions.

The invention provides a design method for a baffle plate used for controlling film thickness distribution on a conical optical element in a film plating planetary system. According to the invention, in the process of vacuum plating, a film material is transmitted in a vacuum environment in a manner of evaporation or sputtering and forms a film with nonuniformly distributed thickness on the surface of the conical optical element, a film thickness distribution model capable of reflecting actual thickness distribution of the film deposited on the conical optical element in a vacuum plating machine planetary system when the baffle plate is not used and a film thickness distribution model capable of reflecting actual thickness distribution of the film on the conical optical element when baffle plate correction is used are respectively established; evaporation or sputtering characteristics of the film material during vacuum plating are determined based on the film thickness distribution model when the baffle plate is not used, then film thickness distribution on the conical optical element is simulated by using theories for the film thickness distribution model when baffle plate correction is used, designing of the baffle plate is optimized by using a computer until film thickness distribution on the conical optical element in the vacuum plating machine planetary system meets design demands after utilization of baffle plate correction, and therefore, an optimal baffle plate design is obtained. The method provided by the invention can realize accurate control of film thickness distribution on the conical optical element.

The invention discloses a reduced-order model-based aerodynamic-heat-structure optimization method and belongs to the field of aerospace. The method comprises the steps of building an aircraft analysis model; building an initial aerodynamic heat reduced-order model; verifying an overall average relative error of the built aerodynamic heat reduced-order model; building an aerodynamic heat reduced-order model meeting a design precision requirement; obtaining a change condition of a structural internal temperature field of an aircraft in a whole ballistic flight process; performing aeroelasticityanalysis considering temperature influence in a whole ballistic trajectory for the aircraft; and by taking aircraft aeroelasticity characteristics obtained by analysis as constraints, optimizing design variables in the aircraft by adopting an optimization algorithm with a global optimization capability, thereby improving comprehensive performance of the hypersonic aircraft. The aerodynamic-heat-structure multidisciplinary optimization design efficiency of the hypersonic aircraft can be improved; the design cost can be reduced; the engineering practicality of the multidisciplinary design optimization method in hypersonic aircraft design can be improved; and the method has the advantage of high universality.

The invention relates to a method and system for predicting the hydrodynamic load of a drag parachute, and the method comprises the following steps: screening influence factors affecting the load of a drag parachute to obtain a design variable; establishing a drag parachute simulation model in virtual simulation software according to the geometric parameters of the drag parachute; calibrating simulation parameters of the simulation model by means of a physical test; adjusting the design variables, carrying out virtual simulation to obtain different load variables, and and forming a database by the multiple sets of design variables and the corresponding load variables; obtaining an agent model of the design variable and the corresponding load variable through machine learning by utilizing data in the database; and inputting any design variable in a set range into the agent model to obtain a corresponding load variable prediction value.

The embodiment of the invention discloses a lightweight implementation method and a device of a battery box. The method comprises the following steps: determining a response surface approximation model of the battery box; According to the response surface approximation model, the quality of the battery box is optimized, and the calculation results which accord with the preset quality lightening verification standard are obtained as the quality of the battery box. As that response surface approximation model is adopted for quality optimization calculation, the optimization design period of thebattery box is shortened, and the optimization design efficiency is improve.

The invention discloses an optimization design method for a microwave circuit, and the method comprises the following steps: obtaining a sample model design parameter through LHS, and obtaining a corresponding sample response through a Matlab-HFSS joint simulation technology; calculating correlation coefficients of all sample responses and target responses, selecting the sample with the maximum correlation coefficient as an optimization sample, and other samples serving as training samples; training the ELM by using the training sample, predicting design parameters responding to the optimized sample, and optimizing an input weight and a threshold value of the ELM by using BSO; and establishing a mapping relationship between the microwave circuit model design parameters and the response by using the ELM after optimizing the input weight and the threshold, training by using all the training samples in the training process, and predicting the model design parameters corresponding to the target response in the prediction process. According to the method, the training and prediction quality of the neural network is improved, the number of required training samples is reduced, the time required for optimization design of the microwave circuit is shortened, the automation of the optimization design of the microwave circuit is realized, and the optimization design efficiency is improved.