Wyniki wyszukiwania - BazTech

1

Smart services for enhancing personal competence in Industrie 4.0 digital factory

Sun J., Gao M., Wang Q., Jiang M., Zhang X., Schmitt R.

LogForum

|

2018

|

Vol. 14, no. 1

51--57

EN

Background: Adaptive digitalization and networking of machines, working parts, employees and other entities on the plant floor are core of realizing industry 4.0, so that information and instruction will be available everywhere and all the time in the production process. Thus, smart devices, especially smart wearables, will play a very important role to help workers being integrated in the in the future manufacturing environment, as information need to be transferred faster and with the right level of detailing with respect to the individual need of workers, factory managers etc. Methods: The implementation of an indoor localization system using Bluetooth beacons in the shop floor as part of an enterprise IoT platform was introduced. This sensor network is aimed to implement tracing and tracking of workers and working parts in the future smart factory, as well as the to the networking of the smart wearables with existing manufacturing machines. The investigated problem was the inaccuracy and the instability of the sensor signals by such Bluetooth sensor networks. To solve the problem, various algorithms were investigated. Results and conclusions: The possible solution of given problem was solved by finding an algorithm improving the communication between devices. Together with the location information from Beacon network and orientation information from the compass sensor, it is able to determine the machine in the near, which the employee with the Smart Glasses is currently pointing to.

PL

Wstęp: Zastosowanie sieciowych rozwiązań dla urządzeń i ich części, jak również jako wspomożenie dla pracowników na poziomie hali produkcyjnej jest podstawowym elementem wdrożenia Industry 4.0., dzięki czemu w każdym momencie i w każdym miejsce zapewnia się dostępność do potrzebnej informacji. W związku z tym, urządzenia mobilne typu smart będą odgrywały ważną rolę w integrowaniu pracowników w środowisko produkcyjne w przyszłości, informacja będzie mogła być przekazywana szybciej i z większą szczegółowością w odniesieniu do poszczególnych pracowników czy kadry zarządzającej. Metody: Zastosowanie wewnętrznej lokalizacji przy użyciu Bluetooth beaconów na poziomie hali produkcyjnej jako fragmentu zakładowej platformy Internetu rzeczy zostało wdrożone. Sieć sensorów ma na celu śledzenie pracowników oraz urządzeń w przyszłościowym zakładzie produkcyjnym, jak również ma być połączeniem z istniejącym parkiem urządzeń produkcyjnych. Badany problem polegał na nietrafności i niestabilności sygnałów sensorów używanych w tej sieci. W celu rozwiązania problemu poddano analizie różne algorytmy możliwych rozwiązań. Wyniki i wnioski: Znaleziono możliwe rozwiązanie analizowanego problem poprzez określenie odpowiedniego algorytmu poprawiającego komunikację pomiędzy urządzeniami. W połączeniu z lokalizacją informacji przy zastosowania sieci beaconów oraz zorientowaniu informacji pochodzących z sensorów, można było zlokalizować urządzenie znajdujące się w pobliżu danego pracownika przy użyciu okularów Smart Glasses.

2

Cognitive failure cluster enhancing the efficiency and the precision of the self-optimizing process model for bevel gear contact patterns

Schmitt R., Niggemann C., Laass M.

Journal of Machine Engineering

|

2012

|

Vol. 12, No. 1

55--65

EN

The contact patterns of bevel gear sets are an important indicator for the acoustic quality of rear axle drives. The contact patterns are the result of complex interactions in the production process. This is due to many process steps, numerous influencing factors and interdependencies. In general, their effect on product variations is not fully comprehended. This impedes the design and control of the production process based on a holistic analytical model for new variants fulfilling the acoustic requirements. The approach with self-optimization is possible but can take a long time for the training of the artificial neural networks and the necessary iterations until a satisfying precision for the predicted process parameters is achieved. Also it can occur that the algorithm is not converging and therefore no satisfactory result is turned out at all. In this paper an approach is presented combining the flexibility of self-optimizing systems with the higher precision of delimited solution finders called the Cognitive Failure Cluster (CFC). The improvements provided by the clustering of the optimization program are evaluated regarding the training time and the precision of the result for a production lot of bevel gear sets.

3

Cognition-based self-optimisation of an automotive rear-axle-drive production process

Schmitt R., Niggemann C., Isermann M., Laass M., Matuschek N.

Journal of Machine Engineering

|

2010

|

Vol. 10, No. 3

68--77

EN

The production of automotive rear-axle drives is a complex process. This is due to many involved process steps, factors and interdependencies between processes, materials, means of production and individuals acting in this environment. In general their effect on product variations is not fully comprehended. Hence, a holistic analytical model is only possible in parts of the production. In this paper a modular approach is presented to make the production more flexible and enable it to react faster on product variations. This is achieved by a Cognitive Production System (CPS), which is based on accumulating, storing and processing of process knowledge so that it can be applied to similar cases. Through the combination and interaction of Cognitive Tolerance Matching (CTM) and Agent-based Systems the performance of the CPS is enhanced. The work discusses the set-up of such a CPS for the production of automotive rear-axle-drives with the focus on the failure state agent.

4

Production optimization by cognitive technologies

Schmitt R., Wagels C., Isermann M.

Journal of Machine Engineering

|

2009

|

Vol. 9, No. 1

78--90

EN

Today, value chains are considered fractionally and on the basis of simplified model assumptions. Interactions between processes, materials, means of production and individuals acting in this environment as well as the effect of changes on the product usually are not known exhaustively. In order to take corrective actions towards these deficits, self-optimizing production system technologies can be used. They provide systems that emulate the "human" ability of reaching a decision with technical architectures. The goal of these approaches is to steadily analyze and evaluate the actual status in technological as well as in organisational areas and conduct a system adaptation to alternating objectives. Central questioning in this field of research is how to survey production data in order to detect correlations of production parameters and their influence on product parameters, how to derive decisions from this knowledge and how to learn from the consequences. Application technologies capable of taking on these tasks of self-optimization to emulate intelligent behaviour are analysed. The aim is to identify the competencies of these technologies, in order to build a cognitive system architecture based on applications especially suited for each task that has to be fulfilled to emulate cognitive human decision making processes.

5

Cognitive optimization of an automotive rear-axle drive production process

Schmitt R., Isermann M., Wagels C., Matuschek N.

Journal of Machine Engineering

|

2009

|

Vol. 9, No. 4

71--80

EN

While optimizing tolerances in tolerance chains only single characteristics or objectives of single process steps are considered, there is no information exchange across all processes. Interdependencies between processes, materials, means of production and individuals acting in this environment as well as their effect on product variations are usually not fully understood. In order to face a dynamisation of process specification, interdependencies have to be identified and integrated in future production. The holistic consideration of the process chain focused on the allocation of tolerances allows detection of correlations and interdependencies in the production process itself. By this, process chain information is traced back to conduct the right optimizations at the right place in the process chain. But therefore intelligent controlling mechanisms are needed to analyze and optimize even complex production systems with multi-level interdependencies. Such a cognitive system is able to form the core of self-optimizing production system. Using this cognitive system, the production process of an automotive rear-axle drive is optimized in order to minimize disturbances created by structure-borne sound emissions. Therefore several cognitive technologies have been evaluated to fulfil specific tasks in process optimization.