Estimating Optimum Process Parameters in Textile Draping of Variable Part Geometries - A Reinforcement Learning Approach

Zimmerling, Clemens; Poppe, Christian; Kärger, Luise

doi:10.1016/j.promfg.2020.04.263

Cited by 25 publications

(17 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The multi-agent reinforcement learning (MARL) system proposed performed dominated the baseline methods of MOPSO and NSGA-II in our case study to optimize the ozonation process solution and achieve the objective color on treated fabrics. The difference from these comparative results could be explained as that the meta-heuristic algorithms of MOPSO and NSGA-2 have been reported that may fail to work with smaller datasets [6] and take an impracticably long time in iteration [63]. But more importantly, though they are effective to deal with low dimension multi-objective optimization problems, the increased stress of selection due to the growing dimension in the problem would decline the effects dramatically when the objectives are more than three.…”

Section: Resultsmentioning

confidence: 89%

Multi-objective optimization of the textile manufacturing process using deep-Q-network based multi-agent reinforcement learning

Tran

Thomassey

et al. 2022

Journal of Manufacturing Systems

View full text Add to dashboard Cite

Multi-objective optimization of the textile manufacturing process is an increasing challenge because of the growing complexity involved in the development of the textile industry. The use of intelligent techniques has been often discussed in this domain, although a significant improvement from certain successful applications has been reported, the traditional methods failed to work with high-as well as human intervention. Upon which, this paper proposed a multi-agent reinforcement learning (MARL) framework to transform the optimization process into a stochastic game and introduced the deep Q-networks algorithm to train the multiple agents. A utilitarian selection mechanism was employed in the stochastic game, which ( -greedy policy) in each state to avoid the interruption of multiple equilibria and achieve the correlated equilibrium optimal solutions of the optimizing process. The case study result reflects that the proposed MARL system is possible to achieve the optimal solutions for the textile ozonation process and it performs better than the traditional approaches.

show abstract

Section: Resultsmentioning

confidence: 89%

Multi-objective optimization of the textile manufacturing process using deep-Q-network based multi-agent reinforcement learning

Tran

Thomassey

et al. 2022

Journal of Manufacturing Systems

View full text Add to dashboard Cite

show abstract

“…First results for textile draping appear promising: [20] and [21] hint that CNNs can learn to assess formability of new components from generic draping examples. [22] further shows that -in principle -CNNs can additionally be used to estimate optimal process parameters for new components. Thus, DL-techniques appear a promising and efficient tool for process design at early stages of product development.…”

Section: /8mentioning

confidence: 95%

Deep neural networks as surrogate models for time-efficient manufacturing process optimisation

Zimmerling¹,

Schindler²,

Seuffert³

et al. 2021

Esaform 2021

Self Cite

View full text Add to dashboard Cite

Manufacturing process optimisation usually amounts to searching optima in high-dimensional parameter spaces. In industrial practice, this search is most often directed by human-subjective expert judgment and trial-and-error experiments. In contrast, high-fidelity simulation models in combination with general-purpose optimisation algorithms, e.g. finite element models and evolutionary algorithms, enable a methodological, virtual process exploration and optimisation. However, reliable process models generally entail significant computation times, which often renders classical, iterative optimisation impracticable. Thus, efficiency is a key factor in optimisation. One option to increase efficiency is surrogate-based optimisation (SBO): SBO seeks to reduce the overall computational load by constructing a numerically inexpensive, data-driven approximation („surrogate“) of the expensive simulation. Traditionally, classical regression techniques are applied for surrogate construction. However, they typically predict a predefined, scalar performance metric only, which limits the amount of usable information gained from simulations. The advent of machine learning (ML) techniques introduces additional options for surrogates: in this work, a deep neural network (DNN) is trained to predict the full strain field instead of a single scalar during textile forming („draping“). Results reveal an improved predictive accuracy as more process-relevant information from the supplied simulations can be extracted. Application of the DNN in an SBO- framework for blank holder optimisation shows improved convergence compared to classical evolutionary algorithms. Thus, DNNs are a promising option for future surrogates in SBO.

show abstract

“…Furthermore, detailed simulations allow the prediction of internal temperature distributions that can hardly be measured to ensure the required temperature conditions during manufacturing [16,17]. Since these simulations are usually time consuming and expensive to evaluate [18], a real-time suitable surrogate model is needed for virtual quality control to stay computational feasible.…”

Section: Introductionmentioning

confidence: 99%

“…in the field of biomechanics [20] or composite manufacturing [21]. An open issue in datadriven modeling of FEM data is its inevitable problem specificity, which is addressed by an approach of Zimmerling et al [18]. In the context of this work, the surrogate predicts the resulting part properties based on the process parameters.…”

Section: Introductionmentioning

confidence: 99%

Machine learning and simulation-based surrogate modeling for improved process chain operation

Hürkamp

Gellrich

Dér

et al. 2021

Int J Adv Manuf Technol

View full text Add to dashboard Cite

In this contribution, a concept is presented that combines different simulation paradigms during the engineering phase. These methods are transferred into the operation phase by the use of data-based surrogates. As an virtual production scenario, the process combination of thermoforming continuous fiber-reinforced thermoplastic sheets and injection overmolding of thermoplastic polymers is investigated. Since this process is very sensitive regarding the temperature, the volatile transfer time is considered in a dynamic process chain control. Based on numerical analyses of the injection molding process, a surrogate model is developed. It enables a fast prediction of the product quality based on the temperature history. The physical model is transferred to an agent-based process chain simulation identifying lead time, bottle necks and quality rates taking into account the whole process chain. In the second step of surrogate modeling, a feasible soft sensor model is derived for quality control over the process chain during the operation stage. For this specific uses case, the production rejection can be reduced by 12% compared to conventional static approaches.

show abstract

Estimating Optimum Process Parameters in Textile Draping of Variable Part Geometries - A Reinforcement Learning Approach

Cited by 25 publications

References 14 publications

Multi-objective optimization of the textile manufacturing process using deep-Q-network based multi-agent reinforcement learning

Multi-objective optimization of the textile manufacturing process using deep-Q-network based multi-agent reinforcement learning

Deep neural networks as surrogate models for time-efficient manufacturing process optimisation

Machine learning and simulation-based surrogate modeling for improved process chain operation

Contact Info

Product

Resources

About