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

Abstract

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.

Numerical Modelling of Bond Strength in Overmoulded Thermoplastic Composites

“…Due to the overmoulding process in closed moulds and the difficult use of sensors in the interface, this can only be determined with the help of simulations. Hence, a process simulation is a suitable tool to determine the local process parameters, allowing a precise temporally and spatially resolved analysis of the conditions at the interface [31].…”

Application of machine learning methods in the analysis of interface bonding strength for overmolded hybrid thermoset‐thermoplastic composites

“…24 However, extensive datasets are often needed for machine learning models, making experimental methods impractical due to high costs. Hürkamp et al 19,25 generated training data for machine learning methods using FEM and developed an surrogate model capable of predicting interface bonding strength quality based on process settings. Hürkamp et al 26 introduced a digital twin framework that combines simulation, Proper Orthogonal Decomposition (POD), and machine learning to predict the temperature field in the overmolding process.…”

Development of surrogate models of clamp configuration for optical glass lens centering through finite element analysis and machine learning

“…Simulating and analyzing a complex finite element model are usually tasks that require substantial time and computational resources [11,12]. Surrogate models are often applied as substitutes of complex computational models in engineering design; they are established by using simple computational models…”

“…Therefore, effective methods for evaluating and analyzing clamping stress are required for the centering process.The finite element method (FEM) is widely used to solve engineering problems, including the evaluation of stress distribution [4] and simulation of mechanical behavior [5,6]. FEM-derived results can also be used to conduct pre-machining assessments [7,8] and support parameter optimization [9,10].However, to obtain accurate simulation results, precise engineering modeling and meshing are required.Simulating and analyzing a complex finite element model are usually tasks that require substantial time and computational resources [11,12]. Surrogate models are often applied as substitutes of complex computational models in engineering design; they are established by using simple computational models…”