Structural Reliability Optimization Design Based on Artificial Neural Network

2013 ◽  
Vol 834-836 ◽  
pp. 1877-1880
Author(s):  
Li Rong Sha ◽  
Yue Yang
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Economic Benefit ◽  
Optimization Design ◽  
Structural Reliability ◽  
Minimum Weight ◽  
Reliability Optimization ◽  
Fatigue Reliability ◽  
Surface Method ◽  
The Relationship

The ANN-based optimization design for considering fatigue reliability requirements on structure was proposed in this paper. The ANN-based response surface method was used to analysis fatigue reliability of the structure. The fatigue reliability requirements were taken as constraints while the structural weight as the objective function, the ANN model was performed to simulate the relationship between the fatigue reliability and geometry dimension of the structure, the optimization result of the structure with a minimum weight was obtained, thus can make economic benefit meanwhile ensure the safety of the structure.

ANN-Based Structure Optimization with Fatigue Reliability Constrains

2012 ◽  
Vol 204-208 ◽  
pp. 3128-3131
Author(s):  
Li Rong Sha ◽  
Yue Yang
Keyword(s):  
Structural Optimization ◽  
Objective Function ◽  
Reliability Analysis ◽  
Response Surface ◽  
Minimum Weight ◽  
Structure Optimization ◽  
Fatigue Reliability ◽  
Ann Model ◽  
Surface Method ◽  
The Relationship

The ANN-based optimization for considering fatigue reliability requirements in structural optimization was proposed. The ANN-based response surface method was employed for performing fatigue reliability analysis. The fatigue reliability requirements were considered as constraints while the weight as the objective function, the ANN model was adopted to establish the relationship between the fatigue reliability and geometry dimension of the structure, the optimal results of the structure with a minimum weight was reached.

Application of a new local effective constrained response surface method in structural reliability optimization design

2019 ◽  
Vol 36 (3) ◽  
pp. 1055-1078 ◽  
Author(s):  
Hailiang Su ◽  
Fengchong Lan ◽  
Yuyan He ◽  
Jiqing Chen
Keyword(s):  
Response Surface ◽  
Response Surface Method ◽  
Optimization Design ◽  
Structural Reliability ◽  
Reliability Optimization ◽  
Content Type ◽  
Meta Model ◽  
Proxy Model ◽  
Surface Method ◽  
Sampling Points

Purpose Meta-model method has been widely used in structural reliability optimization design. The main limitation of this method is that it is difficult to quantify the error caused by the meta-model approximation, which leads to the inaccuracy of the optimization results of the reliability evaluation. Taking the local high efficiency of the proxy model, this paper aims to propose a local effective constrained response surface method (LEC-RSM) based on a meta-model. Design/methodology/approach The operating mechanisms of LEC-RSM is to calculate the index of the local relative importance based on numerical theory and capture the most effective area in the entire design space, as well as selecting important analysis domains for sample changes. To improve the efficiency of the algorithm, the constrained efficient set algorithm (ESA) is introduced, in which the sample point validity is identified based on the reliability information obtained in the previous cycle and then the boundary sampling points that violate the constraint conditions are ignored or eliminated. Findings The computational power of the proposed method is demonstrated by solving two mathematical problems and the actual engineering optimization problem of a car collision. LEC-RSM makes it easier to achieve the optimal performance, less feature evaluation and fewer algorithm iterations. Originality/value This paper proposes a new RSM technology based on proxy model to complete the reliability design. The originality of this paper is to increase the sampling points by identifying the local importance of the analysis domain and introduce the constrained ESA to improve the efficiency of the algorithm.

Structural Reliability Optimization with Fourier Orthogonal Neural Network Method

2013 ◽  
Vol 834-836 ◽  
pp. 1907-1910
Author(s):  
Li Rong Sha ◽  
Yue Yang
Keyword(s):  
Neural Network ◽  
Optimization Design ◽  
Structural Reliability ◽  
Mathematical Optimization ◽  
Minimum Cost ◽  
Optimization Methods ◽  
Economic Benefits ◽  
Fatigue Reliability ◽  
Neural Network Method ◽  
Network Method

The structural optimization design considering reliability requirements was proposed based on Fourier orthogonal neural network method. The reliability-based optimization design of the structure is a combination of the structural reliability theory and mathematical optimization methods. The Fourier orthogonal neural network was used to analysis reliability of the structure and also to simulate the relationship between the fatigue reliability and geometry dimension of the structure. The structural reliability requirements were taken as constraints while the structural volume as the objective function, with Fourier orthogonal neural network method, the optimization results of the structure was obtained with a minimum cost, thus can make technical and economic benefits besides the structural reliability.

Optimization and Prediction of Machining Responses Using Response Surface Methodology and Adaptive Neural Network by Wire Electric Discharge Machining of Alloy-X

2021 ◽  
Vol 1026 ◽  
pp. 28-38
Author(s):  
I. Vishal Manoj ◽  
S. Narendranath ◽  
Alokesh Pramanik
Keyword(s):  
Neural Network ◽  
Surface Roughness ◽  
Artificial Neural Network ◽  
Response Surface ◽  
Electric Discharge ◽  
Cutting Speed ◽  
Electric Discharge Machining ◽  
Surface Method ◽  
Wire Electric Discharge Machining ◽  
Pulse On Time

Wire electric discharge machining non-contact machining process based on spark erosion technique. It can machine difficult-to-cut materials with excellent precision. In this paper Alloy-X, a nickel-based superalloy was machined at different machining parameters. Input parameters like pulse on time, pulse off time, servo voltage and wire feed were employed for the machining. Response parameters like cutting speed and surface roughness were analyzed from the L25 orthogonal experiments. It was noted that the pulse on time and servo voltage were the most influential parameters. Both cutting speed and surface roughness increased on increase in pulse on time and decrease in servo voltage. Grey relation analysis was performed to get the optimal parametric setting. Response surface method and artificial neural network predictors were used in the prediction of cutting speed and surface roughness. It was found that among the two predictors artificial neural network was accurate than response surface method.

scholarly journals Modelling of Rotary EDM Process Parameters of Inconel 718 Using Artificial Neural Networks

Mechanika ◽  
2020 ◽  
Vol 26 (6) ◽  
pp. 540-544
Author(s):  
Jayaraj JEEVAMALAR ◽  
Sundaresan RAMABALAN ◽  
Chinnamuthu SENTHILKUMAR
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Process Parameters ◽  
Inconel 718 ◽  
Machining Process ◽  
Artificial Neural ◽  
Pulse On Time ◽  
Pulse Off Time ◽  
Matlab Programming ◽  
The Relationship

Modelling is used for correlating the relationship between the input process parameters and the output responses during the machining process. To characterize real-world systems of considerable complexity, an Artificial Neural Network (ANN) model is regularly used to replace the mathematical approximation of the relationship. This paper explains the methodological procedure and the outcome of the ANN modeling process for Electrical Discharge Drilling of Inconel 718 superalloy and hollow tubular copper as tool electrode. The most important process parameters in this work are peak current, pulse on time and pulse off time with machining performances of material removal rate and surface roughness. The experiments were performed by L20 Orthogonal Array. In such conditions, an Artificial Neural Network model is developed using MATLAB programming on the Feed Forward Back Propagation technique was used to predict the responses. The experimental data were separated into three parts to train, test the network and validate the model. The developed model has been confirmed experimentally for training and testing in considering the number of iterations and mean square error convergence criteria. The developed model results are to approximate the responses fairly exactly. The model has the mean correlation coefficient of 0.96558. Results revealed that the proposed model can be used for the prediction of the complex EDM drilling process.

scholarly journals Solving multiple linear regression problem using artificial neural network

2022 ◽  
Vol 12 (1) ◽  
pp. 770
Author(s):  
Mohammad S. Khrisat ◽  
Ziad A. Alqadi
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Regression Problem ◽  
Simple Method ◽  
Scientific Experiments ◽  
Linear Regression Problem ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
The Relationship ◽  
Linear Regressions

<span>Multiple linear regressions are an important tool used to find the relationship between a set of variables used in various scientific experiments. In this article we are going to introduce a simple method of solving a multiple rectilinear regressions (MLR) problem that uses an artificial neural network to find the accurate and expected output from MLR problem. Different artificial neural network (ANN) types with different architecture will be tested, the error between the target outputs and the calculated ANN outputs will be investigated. A recommendation of using a certain type of ANN based on the experimental results will be raised.</span>

Aerodynamic Optimization Design of Compressor Cascade Based on Parallel Multi-Objective Genetic Algorithm and Artificial Neural Network

2011 ◽  
Vol 138-139 ◽  
pp. 534-539
Author(s):  
Li Hai Chen ◽  
Qing Zhen Yang ◽  
Jin Hui Cui
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Artificial Neural Network ◽  
Optimization Design ◽  
Compressor Cascade ◽  
Aerodynamic Optimization ◽  
Navier Stokes Equation ◽  
Multi Objective ◽  
Multi Objective Genetic Algorithm ◽  
Artificial Neural

Genetic algorithm (GA) is improved with fast non-dominated sort approach and crowded comparison operator. A new algorithm called parallel multi-objective genetic algorithm (PMGA) is developed with the support of Massage Passing Interface (MPI). Then, PMGA is combined with Artificial Neural Network (ANN) to improve the optimization efficiency. Training samples of the ANN are evaluated based on the two-dimensional Navier-Stokes equation solver of cascade. To demonstrate the feasibility of the hybrid algorithm, an optimization of a controllable diffusion cascade is performed. The optimization results show that the present method is efficient and trustiness.

Sign in / Sign up

Export Citation Format

Share Document