Open Access

Artificial intelligence is considered to be a significant technology for driving the future evolution of smart manufacturing environments. At the same time, automated guided vehicles (AGVs) play an essential role in manufacturing systems due to their potential to improve internal logistics by increasing production flexibility. Thereby, the productivity of the entire system relies on the quality of the schedule, which can achieve production cost savings by minimizing delays and the total makespan. However, traditional scheduling algorithms often have difficulties in adapting to changing environment conditions, and the performance of a selected algorithm depends on the individual scheduling problem. Therefore, this paper aimed to analyze the scheduling problem classes of AGVs by applying design science research to develop an algorithm selection approach. The designed artifact addressed a catalogue of characteristics that used several machine learning algorithms to find the optimal solution strategy for the intended scheduling problem. The contribution of this paper is the creation of an algorithm selection method that automatically selects a scheduling algorithm, depending on the problem class and the algorithm space. In this way, production efficiency can be increased by dynamically adapting the AGV schedules. A computational study with benchmark literature instances unveiled the successful implementation of constraint programming solvers for solving JSSP and FJSSP scheduling problems and machine learning algorithms for predicting the most promising solver. The performance of the solvers strongly depended on the given problem class and the problem instance. Consequently, the overall production performance increased by selecting the algorithms per instance. A field experiment in the learning factory at Reutlingen University enabled the validation of the approach within a running production scenario.

Der Anteil mittelständischer Unternehmen, die Standorte im Ausland unterhalten, nimmt seit einigen Jahren zu. Oft finden Auslandsaktivitäten dieser Art in Niedriglohnländern statt. Dort ergeben sich u.a durch die infrastrukturellen Gegebenheiten und durch die verfügbaren Personalressourcen diverse Herausforderungen, insbesondere für die Produktivitätsermittlung und -bewertung innerhalb der Produktion. Dieser Beitrag soll für diese Herausforderungen geeignete Technologien und eine mögliche Vorgehensweise für deren Auswahl vor dem Hintergrund der ländertypischen Herausforderungen aufzeigen.

Aimed at the problem that the accuracy of face image classification in complex environment is not high, a network model F-Net suitable for aesthetic classification of face images is proposed. Based on LeNet-5, the model uses convolutional layers to extract facial image features in complex backgrounds, optimized parameters in the network model, and changes the number of convolutional layers and fully connected layer feature elements in the model. The experimental results show that the F-Net network model proposed in this paper has a face image classifation accuracy of 73% in complex environment background, which is better than other classical convolutional neural network classification models.

The present publication reports the purification effort of two natural bone blocks, that is, an allogeneic bone block (maxgraft®, botiss biomaterials GmbH, Zossen, Germany) and a xenogeneic block (SMARTBONE®, IBI S.A., Mezzovico Vira, Switzerland) in addition to previously published results based on histology. Furthermore, specialized scanning electron microscopy (SEM) and in vitro analyses (XTT, BrdU, LDH) for testing of the cytocompatibility based on ISO 10993-5/-12 have been conducted. The microscopic analyses showed that both bone blocks possess a trabecular structure with a lamellar subarrangement. In the case of the xenogeneic bone block, only minor remnants of collagenous structures were found, while in contrast high amounts of collagen were found associated with the allogeneic bone matrix. Furthermore, only island-like remnants of the polymer coating in case of the xenogeneic bone substitute seemed to be detectable. Finally, no remaining cells or cellular remnants were found in both bone blocks. The in vitro analyses showed that both bone blocks are biocompatible. Altogether, the purification level of both bone blocks seems to be favorable for bone tissue regeneration without the risk for inflammatory responses or graft rejection. Moreover, the analysis of the maxgraft® bone block showed that the underlying purification process allows for preserving not only the calcified bone matrix but also high amounts of the intertrabecular collagen matrix.

In recent years, the numer of hybrid work systems using human robot collaboration (HRC) increased in industrial production environments - enhancing productivity while reducing work-related burden. Despite growing availability of HRC-suitable manipulation and safety technology, tools and techniques facilitating the design, planning and implementation process are still lacking. System engineers who strive to implement technically feasible, ergonomically meaningful and economically beneficial HRC application need to make design and technology decisions in various subject areas, whereas the design alternatives per morphological analysis is applied to establish a description model that can serve as both a supporting design guideline for future HRC application of value-adding, industrial quality as well as a tool to characterize and compare existing applications. It focuses on HRC within assembly processes, and illustrates the complexity of HRC applications in a comprehensible manner through its multi-dimensional structure. The morphology has been validated through its application on various existing industrial HRC applications, research demonstrators and interviews of experts from academia.