Sascha Feldhorst

Integration of a legacy automation system into a SOA for devices

Although networked embedded devices (NED) and service-oriented architectures (SOA) are often proclaimed as next generation technologies in industrial automation, there are some steps to take before they can be widely adopted. At the moment, productive systems are not SOA-ready and that is why integration approaches are interesting for manufacturers and operators of industrial plants. We suggest a solution for the integration of a legacy system into a so-called SOA for devices. Therefore, we use a thin abstraction layer which provides the technical functions of an industrial plant as re-usable services which can be arranged in control hierarchies and used as well in higher-level workflows. This enables a SOA-based automation with new control and monitoring approaches to be built upon the device services. To evaluate our solution a legacy material flow facility is used.

Reduction of Energy Consumption by Proper Speed Selection in PMSM-Driven Roller Conveyors

This paper suggests using transport speed selection as a degree of freedom to reduce the energy demand of roller conveyors driven by permanent-magnet synchronous motors (PMSMs) in the field of materials handling. A dynamic model of energy consumption of PMSM-driven roller conveyors is provided. Within the proposed model, a vector control strategy is used for motor speed control in addition to hysteresis trigger selection for the inverter. The relation between motor energy consumption, its desired rotational speed, and required torque for packet movement is analyzed. An optimum transportation speed is defined according to the load on the conveyor, and the resulting optimization method is qualified on a series of simulations and offers a potential saving margin for a pilot system. Applications of the proposed method during the planing and system operation are also presented.

Event-based 3D-monitoring of material flow systems in real-time

The following article presents a framework to develop event-based monitoring systems that collect data from an automated transportation system and provide a Human Machine Interface (HMI) with 3D-support. These systems allow to correlate data with the places where it has been collected. Together with 3D models of the technical components, the monitoring systems visualize the system state and the material flow in real-time. Further, we report on a practical monitoring system implementation, on its evaluation and on its development and installation process demonstrating feasibility, benefits and costs of 3D-monitoring.

Motion Classification for Analyzing the Order Picking Process using Mobile Sensors

This contribution introduces a new concept to analyze the manual order picking process which is a key task in the field of logistics. The approach relies on a sensor-based motion classification already used in other domains like sports or medical science. Thereby, different sensor data, e. g. acceleration or rotation rate, are continuously recorded during the order picking process. With help of this data, the process can be analyzed to identify different motion classes, like walking or picking, and the time a subject spends in each class. Moreover, relevant motion classes within the order picking process are defined which were identified during field studies in two different companies. These classes are recognized by a classification system working with methods from the field of statistical pattern recognition. The classification is done with a supervised learning approach for which promising results can be shown.

Engineering von modularen Förderanlagen im Internet der Dinge

Zusammenfassung Dieser Artikel gibt einen Überblick über Engineeringmethoden für modulare Förderanlagen nach dem Grundgedanken des Internet der Dinge. Durch strikte Modularisierung der mechanischen Fördermittel und durch Verteilung der Steuerungsintelligenz werden anpassungsfähige und skalierbare Materialflusssysteme bereits heute möglich. Neben der Beschreibung des Konzepts werden die Vorteile von modularen Systemen diskutiert. Den Kern des Artikels bildet die Beschreibung neuer Ansätze für das Engineering. Abstract This contribution describes new engineering concepts for modular conveyor systems. Through modularisation of mechanical material flow systems and the decentralisation of material flow control, the realisation of flexible and scalable systems is facilitated. We describe the concept of the internet of things in logistics and discuss benefits of this approach towards the efficiency of a material flow system. Subsequently, the main part of the paper deals with new ways for engineering such systems.

Deep Neural Network based Human Activity Recognition for the Order Picking Process

Although the fourth industrial revolution is already in pro-gress and advances have been made in automating factories, completely automated facilities are still far in the future. Human work is still an important factor in many factories and warehouses, especially in the field of logistics. Manual processes are, therefore, often subject to optimization efforts. In order to aid these optimization efforts, methods like human activity recognition (HAR) became of increasing interest in industrial settings. In this work a novel deep neural network architecture for HAR is introduced. A convolutional neural network (CNN), which employs temporal convolutions, is applied to the sequential data of multiple intertial measurement units (IMUs). The network is designed to separately handle different sensor values and IMUs, joining the information step-by-step within the architecture. An evaluation is performed using data from the order picking process recorded in two different warehouses. The influence of different design choices in the network architecture, as well as pre- and post-processing, will be evaluated. Crucial steps for learning a good classification network for the task of HAR in a complex industrial setting will be shown. Ultimately, it can be shown that traditional approaches based on statistical features as well as recent CNN architectures are outperformed.

Convolutional Neural Networks for Human Activity Recognition Using Body-Worn Sensors

Human activity recognition (HAR) is a classification task for recognizing human movements. Methods of HAR are of great interest as they have become tools for measuring occurrences and durations of human actions, which are the basis of smart assistive technologies and manual processes analysis. Recently, deep neural networks have been deployed for HAR in the context of activities of daily living using multichannel time-series. These time-series are acquired from body-worn devices, which are composed of different types of sensors. The deep architectures process these measurements for finding basic and complex features in human corporal movements, and for classifying them into a set of human actions. As the devices are worn at different parts of the human body, we propose a novel deep neural network for HAR. This network handles sequence measurements from different body-worn devices separately. An evaluation of the architecture is performed on three datasets, the Oportunity, Pamap2, and an industrial dataset, outperforming the state-of-the-art. In addition, different network configurations will also be evaluated. We find that applying convolutions per sensor channel and per body-worn device improves the capabilities of convolutional neural network (CNNs).

Energy optimized speed regulation of permanent magnet synchronous motors for driving roller conveyors

This paper provides an analysis and optimization of the power consumption for permanent magnet synchronous motors (PMSM) in the field of material handling application. Particular attention is paid to define a relation between motor power consumption, its desired rotational speed and required torque for packet movement while the motor works with constant speed. A mathematical model of PMSM power consumption for driving roller conveyors during the constant speed is provided and an approach to determine the optimum desired speed according to the packet weight is presented. Within the proposed model vector control strategy is used for motor speed control in addition to hysteresis trigger selection for the inverter. The resulting optimization method is qualified on a series of simulations and offers a potential saving margin for a pilot system.

Software-Methoden für die Automatisierung

Die Verfugbarkeit von zusatzlichen Berechnungsressourcen in der Feldebene ermoglicht die Verlagerung von Steuerungsfunktionen in die raumliche Nahe der technischen Prozesse (vgl. Kap. 4). Dies macht den Bereich Software zu einem aktuellen und zukunftigen Schwerpunkt fur technologische Innovationen in Automatisierungssystemen. Deshalb wird in den nachsten Jahren die Bedeutung von intelligenter Software in der Automatisierungstechnik weiterhin zunehmen (vgl. Favre-Bulle 2005). Schlieslich verleiht die Software den Geraten ihre Intelligenz und sorgt fur ein sinnvolles Zusammenwirken der einzelnen Gerate.