This paper discusses the expected benefits of using linked data for the tasks of gathering, managing and understanding the data of smart factories. It has the further specific focus of using this data to maintaining a Digital Twin for the purposes of analysis and optimisation of such factories. The proposals are motivated by the use of an industrial example looking at the types of information required, the variation in data which is available and the requirements of an analysis platform to provide parameters for seamless, automated simulation and optimisation. 

Metamodeling plays an important role in simulation-based optimization by providing computationally inexpensive approximations for the objective and constraint functions. Additionally metamodeling can also serve to filter noise, which is inherent in many simulation problems causing optimization algorithms to be mislead. In this paper, we conduct a thorough statistical comparison of four popular metamodeling methods with respect to their approximation accuracy at various levels of noise. We use six scalable benchmark problems from the optimization literature as our test suite. The problems have been chosen to represent different types of fitness landscapes, namely, bowl-shaped, valley-shaped, steep ridges and multi-modal, all of which can significantly influence the impact of noise. Each metamodeling technique is used in combination with four different noise handling techniques that are commonly employed by practitioners in the field of simulation-based optimization. The goal is to identify the metamodeling strategy, i.e. a combination of metamodeling and noise handling, that performs significantly better than others on the fitness landscapes under consideration. We also demonstrate how these results carry over to a simulation-based optimization problem concerning a scalable discrete event model of a simple but realistic production line.

Old machine reconditioning projects extend the life length of machines with reduced investments, however they frequently involve complex challenges. Due to the lack of technical documentation and the fact that the machines are running in production, they can require a reverse engineering phase and extremely short commissioning times. Recently, emulation software has become a key tool to create Digital Twins and carry out virtual commissioning of new manufacturing systems, reducing the commissioning time and increasing its final quality. This paper presents an industrial application study in which an emulation model is used to support a reconditioning project and where the benefits gained in the working process are highlighted.

Saving and managing virtual models’ provenance information (models’ history) can increase the level of reusability of those models. This paper describes a provenance management system (PMS) that has been developed based on an industrial case study.

The product lifecycle management (PLM) system, as a main data management system, is responsible for receiving virtual models and their related data from Computer-Aided technologies (CAx) and providing this information for the PMS. In this paper, the management of discrete event simulation data with the PLM system will be demonstrated as the first link of provenance data management chain (CAx-PLM-PMS).

Radial basis functions are augmented with a posteriori bias in order to perform robustly when used as metamodels. Recently, it has been proposed that the bias can simply be set a priori by using the normal equation, i.e., the bias becomes the corresponding regression model. In this study, we demonstrate the performance of the suggested approach (RBFpri) with four other well-known metamodeling methods; Kriging, support vector regression, neural network and multivariate adaptive regression. The performance of the five methods is investigated by a comparative study, using 19 mathematical test functions, with five different degrees of dimensionality and sampling size for each function. The performance is evaluated by root mean squared error representing the accuracy, rank error representing the suitability of metamodels when coupled with evolutionary optimization algorithms, training time representing the efficiency and variation of root mean squared error representing the robustness. Furthermore, a rigorous statistical analysis of performance metrics is performed. The results show that the proposed radial basis function with a priori bias achieved the best performance in most of the experiments in terms of all three metrics. When considering the statistical analysis results, the proposed approach again behaved the best, while Kriging was relatively as accurate and support vector regression was almost as fast as RBFpri. The proposed RBF is proven to be the most suitable method in predicting the ranking among pairs of solutions utilized in evolutionary algorithms. Finally, the comparison study is carried out on a real-world engineering optimization problem. © 2018 Elsevier Ltd

Identifying sustainable strategies to develop maintenance performance within the short-termism framework is indeed challenging. It requires reinforcing long-term capabilities while managing short-term requirements. This study explores differently applied time horizons when optimizing the tradeoff between conflicting objectives, in maintenance performance, which are: maximize availability, minimize maintenance costs, and minimize maintenance consequence costs. The study has applied multi-objective optimization on a maintenance performance system dynamics model that contains feedback structures that explains reactive and proactive maintenance behavior on a general level. The quantified results provide insights on how different time frames are conditional to enable more or less proactive maintenance behavior in servicing production.

The new industrial revolution brings important changes to organizations that will need to adapt their machines, systems and employees’ competences to sustain their business in a highly competitive market. Management philosophies such as lean will also need to adapt to the improvement possibilities that Industry 4.0 brings. This paper presents a review on the role of lean and simulation in the context of Industry 4.0. Additionally, the paper presents a conceptual framework where simulation and optimization will make the lean approach more efficient, speeding up system improvements and reconfiguration, by means of an enhanced decision-making process and supported organizational learning.