Multi-Response Parameter Interval Sensitivity and Optimization for the Composite Tape Winding Process

Deng, Bo; Shi, Yaoyao; Yu, Tao; Kang, Chang-Yong; Zhao, Pan

doi:10.3390/ma11020220

Cited by 14 publications

(5 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this work, MC-based method summarized in Algorithm 1 is used to estimate importance values of p inputs xj (j = 1,..., p) for each output yl (l = 1,..., L); this is a modified version of the method presented in [45,46]. First of all, after generating N uniform random vectors x (1) ,..., x (N) with p dimensions, these vectors are substituted into the lth regression function…”

Section: Monte Carlo (Mc)-based Methods For Estimating Importance Val...mentioning

confidence: 99%

A machine learning approach for ball milling of alumina ceramics

Raju

Jin

et al. 2022

Int J Adv Manuf Technol

View full text Add to dashboard Cite

In this work, machine learning (ML) approach based on polynomial regression was explored to analyze the optimal processing parameters and predict the target particle sizes for ball milling of alumina ceramics. Data points were experimentally obtained by measuring the particle sizes. Prediction interval (PI)-based optimization methods using polynomial regression analysis are proposed. As a first step, functional relations between the inputs and the responses are derived by applying the regression analysis. Later, based on these relations, objective functions to be maximized are defined by desirability approach. Finally, the proposed PI-based methods optimize both parameter points and intervals of the target mill for accomplishing userspecified target responses. The optimization results show that the PI-based point optimization methods can select and recommend statistically reliable optimized parameter points even though unique solutions for the objective functions do not exist. From the results of confirmation experiments, it is established that the optimized parameter points can produce desired particle sizes with quality responses quite similar to the target responses.

show abstract

Section: Monte Carlo (Mc)-based Methods For Estimating Importance Val...mentioning

confidence: 99%

A machine learning approach for ball milling of alumina ceramics

Raju

Jin

et al. 2022

Int J Adv Manuf Technol

View full text Add to dashboard Cite

show abstract

“…In this section, the second-order polynomial regression analysis and the MC-based method inspired from Ref. [10,19] are explained in detail. From now on, scalars and vectors are written in italics, and bold lowercase, respectively, and matrices are written in bold capitals.…”

Section: Process Modeling Using Second-order Polynomial Regressionmentioning

confidence: 99%

“…This subsection describes a MC-based method to estimate the variable importance of the p controllable factors; this is a modified version of the method presented in [10,19]. In general, when using second-order polynomial regression models, one can confirm how much each term contributes to the output by closely examining the magnitude of the corresponding estimated coefficient and its t-statistic.…”

Section: Importance Estimation Of Input Variablesmentioning

confidence: 99%

A Confidence Interval-Based Process Optimization Method Using Second-Order Polynomial Regression Analysis

Kim

Lee

et al. 2020

Processes

View full text Add to dashboard Cite

In the manufacturing processes, process optimization tasks, to optimize their product quality, can be performed through the following procedures. First, process models mimicking functional relationships between quality characteristics and controllable factors are constructed. Next, based on these models, objective functions formulating process optimization problems are defined. Finally, optimization algorithms are applied for finding solutions for these functions. It is important to note that different solutions can be found whenever these algorithms are independently executed if a unique solution does not exist; this may cause confusion for process operators and engineers. This paper proposes a confidence interval (CI)-based process optimization method using second-order polynomial regression analysis. This method evaluates the quality of the different solutions in terms of the lengths of their CIs; these CIs enclose the outputs of the regression models for these solutions. As the CIs become narrower, the uncertainty about the solutions decreases (i.e., they become statistically significant). In the proposed method, after sorting the different solutions in ascending order, according to the lengths, the first few solutions are selected and recommended for the users. To verify the performance, the method is applied to a process dataset, gathered from a ball mill, used to grind ceramic powders and mix these powders with solvents and some additives. Simulation results show that this method can provide good solutions from a statistical perspective; among the provided solutions, the users are able to flexibly choose and use proper solutions fulfilling key requirements for target processes.

show abstract

“…However, the high processing cost hinders composite materials being widely used [ 4 ]. Winding technology and automated placement technology are common technologies for fabricating composite products with low cost [ 5 , 6 , 7 , 8 ]. As a key branch of low-cost composite processing technologies, robotic fiber placement (RFP) technology provides several advantages for the fabrication of composite components with complex surfaces, including real-time process parameter control [ 9 ], low rejection rates and large layup angles [ 10 ].…”

Section: Introductionmentioning

confidence: 99%

Predicting and Improving Interlaminar Bonding Uniformity during the Robotic Fiber Steering Process

Zhao

Shirinzadeh

et al. 2022

Polymers

Self Cite

View full text Add to dashboard Cite

With their high specific stiffness, corrosion resistance and other characteristics, especially their outstanding performance in product weight loss, fiber-reinforced resin matrix composites are widely used in the aviation, shipbuilding and automotive fields. The difficulties in minimizing defects are an important factor in the high cost of composite material component fabrication. Fiber steering is one of the typical means of producing composite parts with increased strength or stiffness. However, fiber waviness is an important defect induced by fiber steering during the fiber placement process. Meanwhile, the laying speeds of the inner and outer tows along the path width direction are different during the fiber steering process, resulting in different interlaminar bond strengths. Therefore, the fiber waviness and uneven interlaminar bonding strength during fiber steering not only affect the dimensions of a composite product, but also influence the mechanical properties of the part. This study aims to reduce fiber waviness and improve interlaminar bonding uniformity along the path width direction using a multi-piece compaction roller. By analyzing the mechanism of the generation of fiber waviness, the interlaminar bonding strength for each tow during fiber steering is investigated. Through analyzing and optimizing the compaction force, laying temperature and laying velocity during fiber steering experiments, the optimization approach is verified.

show abstract

Multi-Response Parameter Interval Sensitivity and Optimization for the Composite Tape Winding Process

Cited by 14 publications

References 40 publications

A machine learning approach for ball milling of alumina ceramics

A machine learning approach for ball milling of alumina ceramics

A Confidence Interval-Based Process Optimization Method Using Second-Order Polynomial Regression Analysis

Predicting and Improving Interlaminar Bonding Uniformity during the Robotic Fiber Steering Process

Contact Info

Product

Resources

About