A hybrid artificial neural network method with uniform design for structural optimization

Cheng, Jin; Li, Qiusheng

doi:10.1007/s00466-008-0355-2

Cited by 21 publications

(8 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared to other DOE methods, the uniform design (UD) method is more suitable for multi-factor DOE with a large number of levels. It not only decreases the required number of experiments, but also ensures that the experimental points cover the entire design space uniformly (Wang and Fang, 1981;Cheng and Li, 2009). In UD, each level is estimated for each factor with just only one experimental run, that is, the number of experiments and levels would be equal (Fang, 1994).…”

Section: Uniform Designmentioning

confidence: 99%

Multi-objective structural optimization of hub unit bearing using response surface methodology and genetic algorithm

Lü

Xie

2014

JAMDSM

View full text Add to dashboard Cite

Hub unit bearings are key components in automobiles for carrying load and accurate piloting. The hub unit bearing must be of a smaller size and lighter weight to meet the requirements of automobile for higher fuel efficiency, improved ease of movement and freedom in sizing of peripheral components. Reduction of such basic performance as strength, stiffness or the like due to reduced weight must be avoided. In this study, an efficient lightweight of hub unit bearing is investigated by integrating finite element (FE) analysis, uniform design (UD), response surface methodology (RSM), and genetic algorithm (GA). The FE analysis of the hub unit bearing is conducted, its validity is verified by the test of moment rigidity. A multi-objective optimization model with constraint functions is established by RSM according to FE analysis results from the samples of UD. The exterior point penalty function method is used to convert the constrained optimization problem into an unconstrained optimization problem. The normalized weighting method is used to transform the multi-objective optimization problem into a single-objective problem. By ensuring that the maximum equivalent stress is below the yield limit stress and that the rigidity hardly changes, the optimization model is interfaced with an effective GA to match the lightweight target.

show abstract

Section: Uniform Designmentioning

confidence: 99%

Multi-objective structural optimization of hub unit bearing using response surface methodology and genetic algorithm

Lü

Xie

2014

JAMDSM

View full text Add to dashboard Cite

show abstract

“…It could produce efficient experiment sampling with proper estimation. In structural optimization analysis, the UDM has been used together with NNs successfully …”

Section: Introductionmentioning

confidence: 99%

“…In structural optimization analysis, the UDM has been used together with NNs successfully. [19,20] Because of a good prediction performance, the SVM was employed herein. Moreover, the SVM was optimized by genetic algorithm (GA) and PSO, respectively.…”

Section: Introductionmentioning

confidence: 99%

An optimum metamodel for safety control of operational subway tunnel during underpass shield tunneling

Zhang

Huang

Gou

2018

Struct Control Health Monit

View full text Add to dashboard Cite

Summary The settlement is regarded as an important index in underground engineering. When tunneling under across the operational subway tunnel, settlement of the operational tunnel should be monitored. To control the tunneling‐induced movement of the operational subway tunnel, the operation parameters of mechanized‐tunneling, namely, face and grout pressures, should be kept in a specific range. A hybrid approach is proposed utilizing uniform design method, and radial basis function neural network to develop the relation of settlement and related influential factors. Such connection is used as a tuning module for tunneling boring machine (TBM). Furthermore, implementing total station robot and soft computing method of support vector machine (SVM), a forecast model for settlement of the rail is established. The prediction tool SVM is improved by using the particle swarm optimization. Parameters c and g from the SVM and γ in the kernel function of the SVM are optimized using the particle swarm optimization. An illustrative case in Changsha Metro Line 3 constructing under the Metro Line 1 tunnel validates the prediction model. The feasibility of the metamodel is demonstrated by means of the example.

show abstract

“…In order to solve this problem some experimental designs such as BoxBehnken Design (De Leon et al, 2010;Ferreira et al, 2007), Central Composite Design (Mehri, 2012;Mehri et al, 2012;Montgomery, 2008), and Uniform Design (Fang, 1980) were suggested. Uniform design was initially proposed by Fang (1980) and it is becoming increasingly popular both in the industry and the academia (Cheng & Li, 2009;Fang & Lin, 2003). Uniform design has the distinct features: 1) it allows for multiple optimization with moderate number of experiments, reducing costs; 2) since there is no assumption about the underlying function, the more uniform points which are spread within the domain result in a good representation of the underlying function by the model; 3) it can A Hybrid Model of Uniform Design and Artificial Neural Network for The Optimization of Dietary Metabolizable Energy, Digestible Lysine, and Methionine in Quail Chicks be used for more possible numbers of levels of each factor among all experimental designs (Zhang et al, 1998).…”

Section: Introductionmentioning

confidence: 99%

A hybrid model of uniform design and artificial neural network for the optimization of dietary metabolizable energy, digestible lysine, and methionine in quail chicks

Mehri

Ghazaghi

2014

Rev. Bras. Cienc. Avic.

View full text Add to dashboard Cite

KeywordsQuail chick, nutritional requirement, uniform design, neural network.Submitted: September/2013 Approved: June/2014 ABSTRACT A uniform design (UD) was used to construct models to explain the growth response of Japanese quails to dietary metabolizable energy (ME), and digestible methionine (dMet) and lysine (dLys) under tropical condition. In total, 100 floor pens with seven birds each were fed 25 UD different diets containing 25 ME (2808-3092 kcal/kg), dMet (0.31-0.49% of diet), and dLys (0.91-1.39% of diet) levels from 7 to 14 d of age. A platform of artificial neural network based on UD (ANN-UD) was generated to describe the growth response of the birds to dietary inputs using random search. Artificial neural networks of body weight gain (BWG) and feed conversion ratio (FCR) were optimized using random search algorithm. The optimization the ANN-UD results showed that maximum BWG may be achieved with 2995 kcal ME/kg, 0.45% dMet, and 1.18% dLys of diet; and minimum FCR may be obtained with 3000 kcal ME/kg, 0.45% dMet, and 1.17% dLys of diet. The result of this study showed that a ANN and UD hybrid model can be used successfully to optimize the nutritional requirements of quail chicks.

show abstract

A hybrid artificial neural network method with uniform design for structural optimization

Cited by 21 publications

References 21 publications

Multi-objective structural optimization of hub unit bearing using response surface methodology and genetic algorithm

Multi-objective structural optimization of hub unit bearing using response surface methodology and genetic algorithm

An optimum metamodel for safety control of operational subway tunnel during underpass shield tunneling

A hybrid model of uniform design and artificial neural network for the optimization of dietary metabolizable energy, digestible lysine, and methionine in quail chicks

Contact Info

Product

Resources

About