Robust Design of UOE Forming Process Based on Support Vector Machine

2015 ◽  
Vol 817 ◽  
pp. 523-530
Author(s):  
Tian Xia Zou ◽  
Guang Han Wu ◽  
Da Yong Li ◽  
Qiang Ren ◽  
Ying Hong Peng
Keyword(s):  
Support Vector Machine ◽  
Robust Optimization ◽  
Robust Design ◽  
Pipeline Steel ◽  
Optimization Methods ◽  
Material Behavior ◽  
Support Vector ◽  
Optimization Approach ◽  
Forming Process ◽  
Noise Factors

Fluctuations in material properties of the incoming steel for UOE forming process are widespread. According to the statistics, the fluctuation range of the yield strength of the same grade pipeline steel is around 80MPa. Robust optimization methods have been widely applied in sheet metal forming area. In this paper, experiments were conducted to investigate how a stochastic material behavior of noise factors affected UOE forming quality. Robust design models integrated with response surface method for UOE forming process were established to minimize impact of the variations and improve the qualified rate of UOE pipe ovality. Support vector machine in both classification and regression was adopted to map the relation between input process parameters and forming qualities. The deterministic and robust optimization results are presented and compared, demonstrating increased process robustness and decreased number of product rejects by application of the robust optimization approach.

Advanced Multi-Objective Robust Optimization Under Interval Uncertainty Using Kriging Model and Support Vector Machine

2018 ◽  
Vol 18 (4) ◽  
Author(s):  
Tingli Xie ◽  
Ping Jiang ◽  
Qi Zhou ◽  
Leshi Shu ◽  
Yahui Zhang ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Robust Optimization ◽  
Engineering Design ◽  
Kriging Model ◽  
Support Vector ◽  
Svm Classifier ◽  
Optimization Approach ◽  
Design Problems ◽  
Multi Objective ◽  
Engineering Design Problems

There are a large number of real-world engineering design problems that are multi-objective and multiconstrained, having uncertainty in their inputs. Robust optimization is developed to obtain solutions that are optimal and less sensitive to uncertainty. Since most of complex engineering design problems rely on time-consuming simulations, the robust optimization approaches may become computationally intractable. To address this issue, an advanced multi-objective robust optimization approach based on Kriging model and support vector machine (MORO-KS) is proposed in this work. First, the main problem in MORO-KS is iteratively restricted by constraint cuts formed in the subproblem. Second, each objective function is approximated by a Kriging model to predict the response value. Third, a support vector machine (SVM) classifier is constructed to replace all constraint functions classifying design alternatives into two categories: feasible and infeasible. The proposed MORO-KS approach is tested on two numerical examples and the design optimization of a micro-aerial vehicle (MAV) fuselage. Compared with the results obtained from other MORO approaches, the effectiveness and efficiency of the proposed MORO-KS approach are illustrated.

A Multi-Objective Robust Optimization Approach Under Interval Uncertainty Based on Kriging and Support Vector Machine

2018 ◽  
Author(s):  
Tingli Xie ◽  
Ping Jiang ◽  
Qi Zhou ◽  
Leshi Shu ◽  
Yang Yang
Keyword(s):  
Support Vector Machine ◽  
Robust Optimization ◽  
Kriging Model ◽  
Interval Uncertainty ◽  
Support Vector ◽  
Optimization Approach ◽  
Multi Objective ◽  
Large Numbers ◽  
Design Alternatives ◽  
Engineering Design Problems

Interval uncertainty can cause uncontrollable variations in the objective and constraint values, which could seriously deteriorate the performance or even change the feasibility of the optimal solutions. Robust optimization is to obtain solutions that are optimal and minimally sensitive to uncertainty. Because large numbers of complex engineering design problems depend on time-consuming simulations, the robust optimization approaches might become computationally intractable. To address this issue, a multi-objective robust optimization approach based on Kriging and support vector machine (MORO-KS) is proposed in this paper. Firstly, the feasible domain of main problem in MORO-KS is iteratively restricted by constraint cuts formed in the subproblem. Secondly, each objective function is approximated by a Kriging model to predict the response value. Thirdly, a Support Vector Machine (SVM) model is constructed to replace all constraint functions classifying design alternatives into two categories: feasible and infeasible. A numerical example and the design optimization of a microaerial vehicle fuselage are adopted to test the proposed MORO-KS approach. Compared with the results obtained from the MORO approach based on Constraint Cuts (MORO-CC), the effectiveness and efficiency of the proposed MORO-KS approach are illustrated.

The Effect of Different Optimization Methods on Robustness for Robust Optimization Design

2014 ◽  
Vol 721 ◽  
pp. 464-467
Author(s):  
Tao Fu ◽  
Qin Zhong Gong ◽  
Da Zhen Wang
Keyword(s):  
Robust Optimization ◽  
Objective Function ◽  
Robust Design ◽  
Optimization Design ◽  
Optimization Methods ◽  
Optimization Method ◽  
Design Parameters ◽  
Hybrid Particle Swarm Optimization ◽  
Design Variables ◽  
Robust Optimization Design

In view of robustness of objective function and constraints in robust design, the method of maximum variation analysis is adopted to improve the robust design. In this method, firstly, we analyses the effect of uncertain factors in design variables and design parameters on the objective function and constraints, then calculate maximum variations of objective function and constraints. A two-level optimum mathematical model is constructed by adding the maximum variations to the original constraints. Different solving methods are used to solve the model to study the influence to robustness. As a demonstration, we apply our robust optimization method to an engineering example, the design of a machine tool spindle. The results show that, compared with other methods, this method of HPSO(hybrid particle swarm optimization) algorithm is superior on solving efficiency and solving results, and the constraint robustness and the objective robustness completely satisfy the requirement, revealing that excellent solving method can improve robustness.

scholarly journals Short-Term Wind Speed Forecasting Using the Data Processing Approach and the Support Vector Machine Model Optimized by the Improved Cuckoo Search Parameter Estimation Algorithm

2016 ◽  
Vol 2016 ◽  
pp. 1-17 ◽  
Author(s):  
Chen Wang ◽  
Jie Wu ◽  
Jianzhou Wang ◽  
Zhongjin Hu
Keyword(s):  
Support Vector Machine ◽  
Wind Speed ◽  
Wind Power ◽  
Parameter Optimization ◽  
Cuckoo Search ◽  
Support Vector ◽  
Optimization Approach ◽  
Short Term ◽  
Wind Speed Forecasting ◽  
Comparison Results

Power systems could be at risk when the power-grid collapse accident occurs. As a clean and renewable resource, wind energy plays an increasingly vital role in reducing air pollution and wind power generation becomes an important way to produce electrical power. Therefore, accurate wind power and wind speed forecasting are in need. In this research, a novel short-term wind speed forecasting portfolio has been proposed using the following three procedures: (I) data preprocessing: apart from the regular normalization preprocessing, the data are preprocessed through empirical model decomposition (EMD), which reduces the effect of noise on the wind speed data; (II) artificially intelligent parameter optimization introduction: the unknown parameters in the support vector machine (SVM) model are optimized by the cuckoo search (CS) algorithm; (III) parameter optimization approach modification: an improved parameter optimization approach, called the SDCS model, based on the CS algorithm and the steepest descent (SD) method is proposed. The comparison results show that the simple and effective portfolio EMD-SDCS-SVM produces promising predictions and has better performance than the individual forecasting components, with very small root mean squared errors and mean absolute percentage errors.

scholarly journals A Hybrid Least Square Support Vector Machine Model with Parameters Optimization for Stock Forecasting

2015 ◽  
Vol 2015 ◽  
pp. 1-7 ◽  
Author(s):  
Jian Chai ◽  
Jiangze Du ◽  
Kin Keung Lai ◽  
Yan Pui Lee
Keyword(s):  
Support Vector Machine ◽  
Least Squares ◽  
Support Vector Machine Model ◽  
Optimization Methods ◽  
Parameters Optimization ◽  
Least Square ◽  
Movement Direction ◽  
Support Vector ◽  
Machine Model ◽  
Mode Decomposition

This paper proposes an EMD-LSSVM (empirical mode decomposition least squares support vector machine) model to analyze the CSI 300 index. A WD-LSSVM (wavelet denoising least squares support machine) is also proposed as a benchmark to compare with the performance of EMD-LSSVM. Since parameters selection is vital to the performance of the model, different optimization methods are used, including simplex, GS (grid search), PSO (particle swarm optimization), and GA (genetic algorithm). Experimental results show that the EMD-LSSVM model with GS algorithm outperforms other methods in predicting stock market movement direction.

Response surface approach to robust design of assembly cells through simulation

2018 ◽  
Vol 38 (4) ◽  
pp. 450-464 ◽  
Author(s):  
Cem Savas Aydin ◽  
Senim Ozgurler ◽  
Mehmet Bulent Durmusoglu ◽  
Mesut Ozgurler
Keyword(s):  
Response Surface ◽  
Robust Design ◽  
Performance Measures ◽  
Performance Optimization ◽  
Design Approach ◽  
Shop Floor ◽  
Optimization Approach ◽  
Content Type ◽  
Performance Variability ◽  
Noise Factors

Purpose This paper aims to present a multi-response robust design (RD) optimization approach for U-shaped assembly cells (ACs) with multi-functional walking-workers by using operational design (OD) factors in a simulation setting. The proposed methodology incorporated the design factors related to the operation of ACs into an RD framework. Utilization of OD factors provided a practical design approach for ACs addressing system robustness without modifying the cell structure. Design/methodology/approach Taguchi’s design philosophy and response surface meta-models have been combined for robust simulation optimization (SO). Multiple performance measures have been considered for the study and concurrently optimized by using a multi-response optimization (MRO) approach. Simulation setting provided flexibility in experimental design selection and facilitated experiments by avoiding cost and time constraints in real-world experiments. Findings The present approach is illustrated through RD of an AC for performance measures: average throughput time, average WIP inventory and cycle time. Findings are in line with expectations that a significant reduction in performance variability is attainable by trading-off optimality for robustness. Reductions in expected performance (optimality) values are negligible in comparison to reductions in performance variability (robustness). Practical implications ACs designed for robustness are more likely to meet design objectives once they are implemented, preventing changes or roll-backs. Successful implementations serve as examples to shop-floor personnel alleviating issues such as operator/supervisor resistance and scepticism, encouraging participation and facilitating teamwork. Originality/value ACs include many activities related to cell operation which can be used for performance optimization. The proposed framework is a realistic design approach using OD factors and considering system stochasticity in terms of noise factors for RD optimization through simulation. To the best of the authors’ knowledge, it is the first time a multi-response RD optimization approach for U-shaped manual ACs with multi-functional walking-workers using factors related to AC operation is proposed.

A Unified Classification Model Based on Robust Optimization

2013 ◽  
Vol 25 (3) ◽  
pp. 759-804 ◽  
Author(s):  
Akiko Takeda ◽  
Hiroyuki Mitsugi ◽  
Takafumi Kanamori
Keyword(s):  
Robust Optimization ◽  
Unified Model ◽  
Machine Learning Algorithms ◽  
Classification Model ◽  
Support Vector ◽  
Optimization Approach ◽  
Statistical Interpretation ◽  
Fisher Discriminant Analysis ◽  
Learning Methods ◽  
Worst Case

A wide variety of machine learning algorithms such as the support vector machine (SVM), minimax probability machine (MPM), and Fisher discriminant analysis (FDA) exist for binary classification. The purpose of this letter is to provide a unified classification model that includes these models through a robust optimization approach. This unified model has several benefits. One is that the extensions and improvements intended for SVMs become applicable to MPM and FDA, and vice versa. For example, we can obtain nonconvex variants of MPM and FDA by mimicking Perez-Cruz, Weston, Hermann, and Schölkopf's ( 2003 ) extension from convex ν-SVM to nonconvex Eν-SVM. Another benefit is to provide theoretical results concerning these learning methods at once by dealing with the unified model. We give a statistical interpretation of the unified classification model and prove that the model is a good approximation for the worst-case minimization of an expected loss with respect to the uncertain probability distribution. We also propose a nonconvex optimization algorithm that can be applied to nonconvex variants of existing learning methods and show promising numerical results.

Sign in / Sign up

Export Citation Format

Share Document