One way to solve the challenge of small and medium-sized enterprise (SME) manufacturers of acquiring sufficient orders is by joining digital Manufacturing-as-a-Service (MaaS) platforms for on-demand manufacturing. However, joining such platforms brings about new challenges such as efficient quoting handling in the face of potentially low success rates and the need for high production quality for low lot sizes. Automating the complete interaction between manufacturers and MaaS platforms, from registering the manufacturer and its capabilities to handling incoming requests and managing offers, orders, and production quality reporting, helps to overcome these challenges. Thus, the increased number of requests can be handled efficiently, and the production quality can be maintained at a high level even for low lot sizes. This paper presents an architecture for automating the interaction and functional building blocks between manufacturers and MaaS platforms, along with a prototype implementation and evaluation of its effectiveness in addressing the challenges SME manufacturers are faced with.

The implementation of closed-loop production systems in manufacturing is a promising approach to mitigate environmental impacts and supply chain disruptions, while increasing the value and lifespan of products and materials. These systems integrate forward and reverse material flow activities such as repair, remanufacturing, and recycling within a single facility. However, a major challenge in planning and operating closed-loop production systems is the high uncertainty surrounding material availability and condition. Different process chains may be required depending on the extent and type of wear present in the used products. During the tactical planning phase, factory planners play a crucial role in evaluating and economically assessing various system and process chain configurations. Multiple technology chain and manufacturing equipment options provide different solutions for managing forward and reverse material flows. To address this, this paper introduces a metaheuristic framework based on discrete event simulation and genetic algorithms to evaluate these system configurations. The framework serves as decision-support for factory planners, whether they are planning a greenfield production system or undertaking a brownfield project aimed at transforming linear into circular production systems with both forward and reverse flows.The presented framework is built on data models that incorporate different technology and process chain options for manufacturing and repair, considering the condition of the cores. A manufacturing equipment database contains predefined data models describing machine skills and load profiles, which are utilized to generate various simulation models using different production system configurations. These models are then used to execute predefined scenarios. The main objective is to identify configurations that achieve a beneficial fitness value balancing technical, economic, and environmental key performance indicators for closed-loop production systems.

Manufacturing as a Service (MaaS) enables a paradigm shift in the current manufacturing landscape, from integrated production and inflexible, fragile supply chains to open production and flexible, robust supply chains. As part of this evolution, new scaling effects for production capacities and customer segments are possible. This article describes how to accomplish this paradigm shift for the automotive industry by building a digital MaaS ecosystem for the large-scale automotive innovation project Catena-X, which aims at a standardized global data exchange based on European values. A digital MaaS ecosystem can not only achieve scaling effects, but also realize new business models and overcome current and future challenges in the areas of legislation, sustainability, and standardization. This article analyzes the state-of-the-art of MaaS ecosystems and describes the development of a digital MaaS ecosystem based on an updated and advanced version of the reference architecture for smart connected factories, called the Smart Factory Web. Furthermore, this article describes a demonstrator for a federated MaaS marketplace for Catena-X which leverages the full technological potential of this digital ecosystem. In conclusion, the evaluation of the implemented digital ecosystem enables the advancement of the reference architecture Smart Factory Web, which can now be used as a blueprint for open, sustainable, and resilient digital manufacturing ecosystems.

We introduce a novel hybrid methodology that combines classical finite element methods (FEM) with neural networks to create a well-performing and generalizable surrogate model for forward and inverse problems. The residual from finite element methods and custom loss functions from neural networks are merged to form the algorithm. The Finite Element Method-enhanced Neural Network hybrid model (FEM-NN hybrid) is data-efficient and physics-conforming. The proposed methodology can be used for surrogate models in real-time simulation, uncertainty quantification, and optimization in the case of forward problems. It can be used to update models for inverse problems. The method is demonstrated with examples and the accuracy of the results and performance is compared to the conventional way of network training and the classical finite element method. An application of the forward-solving algorithm is demonstrated for the uncertainty quantification of wind effects on a high-rise buildings. The inverse algorithm is demonstrated in the speed-dependent bearing coefficient identification of fluid bearings. Hybrid methodology of this kind will serve as a paradigm shift in the simulation methods currently used.

Traditional computational methods face significant challenges with ever-increasing complexity in the problems of engineering interest. One category of problems that suffer from this phenomenon is those where Fluid-Structure Interaction (FSI) is present. One set of problems that suffer from this phenomenon is those where Fluid-Structure Interaction (FSI) is present. FSI simulations are traditionally time-consuming and computationally extremely expensive. Potential alternatives rely on using a surrogate model to substitute one or more systems involved. A promising approach employs artificial neural networks as the basis for such a surrogate model combined with strong physics simulations based on finite element methods (FEM). This approach requires the seamless integration of AI algorithms and packages into the simulation workflow. Such an example is the NeuralNetworkApplication developed in KratosMultiphysics. The routines related to the neural networks are executed through an interface with the Keras API. Mok's benchmark is chosen as the study case to test the capacity of the previous method applied to FSI problems. Two cases in which one of the systems is substituted by a neural network-based surrogate model are analyzed. Strong and weak coupling scenarios are considered. The results present improvements in simulation time without sacrificing accuracy, especially when compared with the original benchmark. This contribution discusses the influence of the original data and network architecture on the simulation outcome and different considerations for generating surrogate models for FSI.

We introduce a generalized physics-informed machine learning workflow to accurately predict the behavior of a transient physical system with enhanced physics conformity. A physics-guided machine learning (PGML) model is developed to achieve this goal. Our model consists of two main parts for a given transient system: (1) a physics-based numerical model which solves the system using conventional numerical methods and returns the stiffness matrix and force vector at each time step; (2) a neural network (NN) based machine learning (ML) surrogate model which predicts the solution of the system using a custom physics-guided loss function constructed from system matrix and force vector. The proposed workflow results in a physics-aware Machine Learning (ML) model. Such a trained model can be used to avoid the prohibitively expensive step of running a transient system simulation at the desired resolutions in space and time. We demonstrate and test the model on single-degree-of-freedom (SDOF) and multiple-degree-of-freedom (MDOF) system’s examples from structural dynamics. Our results show that the method predicts the simulation results accurately. The proposed workflow can be directly adapted to any other physics and numerical method as it is not tailored towards a specific physics or a numerical method.

The simulation of subtractive manufacturing processes has a long history in engineering. Corresponding predictions are utilized for planning, validation and optimization, e.g., of CNC-machining processes. With the up-rise of flexible robotic machining and the advancements of computational and algorithmic capability, the simulation of the coupled machine-process behaviour for complex machining processes and large workpieces is within reach. These simulations require fast material removal predictions and analysis with high spatial resolution for multi-axis operations. Within this contribution, we propose to leverage voxel-based concepts introduced in the computer graphics industry to accelerate material removal simulations. Corresponding schemes are well suited for massive parallelization. By leveraging the computational power offered by modern graphics hardware, the computational performance of high spatial accuracy volumetric voxel-based algorithms is further improved. They now allow for very fast and accurate volume removal simulation and analysis of machining processes. Within this paper, a detailed description of the data structures and algorithms is provided along a detailed benchmark for common machining operations.

Sampling approaches for uncertainty quantification for real-world engineering problems are associated with large computational time and cost. This cost comes from the expensive deterministic simulation. Usage of surrogate models is a common way to overcome this issue in engineering applications. A conventional Neural Network (NN) can be used for building such surrogates. However, these neural networks are built based on input-output pairs. It is not possible to verify that the predicted output satisfies underlying physics. In this contribution, a physics-informed neural network based on a hybrid model of machine learning and classical Finite Element Method (FEM) is presented for forward propagation of uncertainty. The method uses FEM during both training and prediction stages. A surrogate model based on neural network for high dimensional problem is constructed by constraining the predictions of the neural network with the discretized partial differential equation of the system. During the training stage, the predicted solution from the FEM informed Neural Network(FEM-NN) is used to compute the residual using stiffness matrices and force vectors. This residual is used as a custom loss function from NN. This makes the whole training unsupervised as it does not require any output values. Hence, the need for expensive FEM solves is circumvented. The FEM-NN hybrid also gives an estimate of the accuracy of prediction by means of the calculated residual along with the prediction. The framework does not require mandatory expensive linear solves of the discretized equation instead substitutes the prediction from the neural network for computing the residual. This reduces the expensive training phase of the problem and can be applicable to real-world FEM simulations. The trained neural network is then sampled in a Monte Carlo (MC) manner to evaluate the statistics of the Quantities of Interest (QoI). The resulting FEM-NN hybrid is physics confirming and data-efficient. The efficacy of the framework is presented by a series of test case examples. The results are compared with classical MC results. The suitability of the method for the uncertainty quantification is studied and presented.

Conventional industrial robots are increasingly used for milling applications of large workpieces due to their workspace and their low investment costs in comparison to conventional machine tools. However, static deflections and dynamic instabilities during the milling process limit the efficiency and productivity of such robot-based milling systems. Since the pose-dependent dynamic properties of the industrial robot structures are notoriously difficult to model analytically, machine learning methods are recently gaining more and more popularity to derive system models from experimental data. In this publication, a modeling concept based on a modern information fusion scheme, fusing simulation and experimental data, is proposed. This approach provides a precise model of the robot’s pose-dependent structural dynamics and is validated for a one-dimensional variation of the robot pose. The results of two information fusion algorithms are compared with a conventional, data-driven approach and indicate a superior model accuracy regarding interpolation and extrapolation of the pose-dependent dynamics. The proposed approach enables decreasing the necessary amount of experimental data needed to assess the vibrational properties of the robot for a desired pose. Additionally, the concept is able to predict the robot dynamics at poses where experimental data is very costly to gather.

The paper discusses a new method for the propagation of risk levels. This discretization takes place by considering the phase space of the state and its subdivision into boxes. In each time step, the method computes the probability of the state being in one box. We start with a variety of technical and physical problems by showing how discrete modeling under uncertainties is technically meaningful and often even problem inherent. Then we select the technical problem of contaminant spread in water grids, to which we apply the method of risk-level propagation in depth. Extensions of the method such as modeling of contaminant mixing at junctions in the discretized phase space and the applicability of conservation laws arise naturally along these lines and are discussed in the context of the general theory.

In this paper a generic simulation environment is introduced that allows the integration of commercial and research-based simulation tools in a service-oriented manufacturing environment, such as in Industrie 4.0 factories, to support in flexible reconfiguration and scheduling decisions. For this purpose, the simulation environment is connected to a generic middleware and processes parameterized simulation requests via automated model generation and execution, based on current shop floor conditions. Those simulation requests are formulated in a standardized description language for production systems, in this case a derivative of AutomationML (AML) that was extended by simulation specific data sets. Therefore, the Simulation Environment comprises different tool- and non-tool-specific functionalities and components that allow the integration of simulation tools into industrial IT platform environments.

Cities can be seen as complex systems of heterogeneous processes with a high variety of different influences (e.g. social, infrastructural, economic, and political impacts). This especially applies for tasks concerning urban development of existing assets. The optimization of traffic flows, reduction of emissions, improvement of energy efficiency, but also urban climate and landscape planning issues require the involvement of many different actors, balancing different perspectives, and divergent claims. The increasing complexities of planning and decision processes make high demands on professionals of various disciplines, government departments, and municipal decision-makers. In the long term, topics like urban resilience, energy management, risk and resource management have to be taken into account and reflected in future projects, but always related to socio-spatial and governmental aspects. Accordingly, it is important to develop models to be able to understand and analyze the outcomes and effects of governmental measures and planning to the urban environment. Thus, a more systematic approach is needed – going away from welldefined city models to city system models. The purpose is to describe urban processes not only quantitatively, but to grasp their qualitative complexity and interdependencies, by modeling and simulating existing urban systems. This contribution will present the City System Model (CSM) concept closely related to an Urban Energy Planning use case, will highlight the methodology, and focus on first results and findings from an ongoing interdisciplinary research project and use case to improve the basis of information for decision-makers and politicians about urban planning decisions.