Semantic understanding of the environment is crucial for indoor navigation. To train the machine learning algorithm, a large dataset is necessary, which can be generated synthetically to reduce manual work to label the data. A synthetic data generation pipeline is developed using Nvidia Isaac Sim to randomly generate various datasets for industrial environments. These environments contain machine tools, distractor objects and different lighting conditions. Six different randomization strategies are evaluated by training two different YOLO models with the synthetic data. The trained models are evaluated with synthetic and real data. The best Sim2Real transfer strategy in this scenario involves using background images of real industrial environments.

Exploiting data and information is known to be essential for tapping into unrealized (business) potential. In the context of the Industrial Internet of Things (IIoT), concerns related to the sensitivity of data frequently hinder its sharing (across organizations). Despite this situation, universal approaches that account for and appropriately model the confidentiality needs of stakeholders are still missing. In this paper, we address this research gap by proposing ConfMod, a middleware that simplifies the fine-granular modeling of confidentiality requirements while striving for interoperability with other tools and standardization in the area. We evaluate ConfMod in a diverse set of twelve real-world use cases from industry and show its general feasibility. Hence, we are confident that the functionality and simplicity of ConfMod facilitate an important building block for the IIoT, which will fuel inter-organizational data sharing in the future.

Fast paced industry requirements call for fast and easy robot programming, especially for Small and Medium sized Enterprises (SME) that often lack robot programming experience. Even with the advancement of graphical activity representation languages such as Behaviour Trees (BTs), it can still be time consuming to program robots for new behaviors due to the shifting product specifications and the dynamic production environments. This paper presents an extension of BTs that offers more flexibility as well as higher reactivity and robustness by introducing Mixed Initiative Planning (MIP) to BTs using Dynamic Sequence Nodes (DSNs). DSNs reduce the human effort needed to design a BT as well as the number of nodes to achieve a certain task while maintaining robustness, readability, and modularity of the tree. Additionally, it introduces run-time optimization to BTs, as opposed to tree synthesis approaches that guarantee convergence but overlook performance.

This paper reports on a strategy to model a fully automated planning system for a production platform, exemplified by the iCellFactory, an automated cell production platform. First, we analyze the prerequisites, based on a PDDL-based planning system. Then we describe the structure and development of the data model in the web ontology language and the implementation of our data server to store the model. Finally, we evaluate the data model based on the requirements, draw conclusions about the effectiveness of our approach and give an outlook on further development.

Continual learning (CL) is a machine learning (ML) paradigm for learning continually from non-stationary data streams while simultaneously transferring and protecting past knowledge. Therefore, CL avoids catastrophic forgetting, a common problem that arises when training ML-models on new data. This paper presents a CL framework for data-driven learning of the dynamics model of a 6-degree-of-freedom serial industrial robot. This model can be used for model-based control algorithms, without the need for extensive identification of robot specific parameters such as mass inertia, and can additionally model complex effects such as friction. Furthermore, using CL, it can adapt to changes of the robot e.g., due to wear or new tasks. With the help of CL, the ML-based dynamics model is continually fed new data and improves over the operating period of the robot.

With the advent of collaborative robots, the demand for manipulators is constantly increasing, especially in SMEs. Hence, the risk of collisions and resulting damage due to programs written by inexperienced users is also simultaneously increasing. Due to the lack of 3D maps of the environment, there are no comprehensive support systems available to check programmed sequences for collision-free execution or to optimize them subsequently. This leads to longer process times and complicates commissioning, especially for inexperienced users. In this paper, a method is presented in which a collaborative robot can autonomously create a 3D map of its environment. Subsequently, the created environment map can be used to optimize existing processes, guarantee collision-free motions and support the operator during commissioning.

Standardized and reliable interfaces for production machines are essential requirements for realizing fully automated manufacturing throughout the value chain. Especially the lightweight industry with its heterogeneous and interdependent process landscape will profit from such a standardized, semantic process and material description. This paper presents an approach for semantic modeling of the automated laser-assisted tape placement process with in-situ consolidation using the OPC UA information-modeling framework and realizes an exemplary implementation for an existing machine prototype.

Nowadays, collaborations between industrial companies always go hand in hand with trust issues, i.e., exchanging valuable production data entails the risk of improper use of potentially sensitive information. Therefore, companies hesitate to offer their production data, e.g., process parameters that would allow other companies to establish new production lines faster, against a quid pro quo. Nevertheless, the expected benefits of industrial collaboration, data exchanges, and the utilization of external knowledge are significant.

More and more industrial robots are being used in SMEs. Due to the lack of CAD models, they are rarely programmed using offline programming methods. With the methods presented in this paper, missing 3D maps of the environment can be flexibly created and even inexperienced operators can be enabled to program complex, collision-free motion sequences. In addition, already programmed sequences can be optimized by the downstream motion planning. The presented method also allows the omitting of intermediate points in complex sequences, which significantly reduces commissioning time and complexity.

In many sectors of the economy, modularization and linkage of distributed structures has significantly increased flexibility. Thereby, individual customer demands and changing conditions can be adressed. While this concept is often applied to closed systems whose control is coordinated by central components or can follow defined processes, concepts for the implementation in decentralized and open systems are missing. Such processes can be found in different domains of application, such as logistics, the construction industry or forestry. The use of active asset administration shells for modularized objects enables elements of a system or products to take over parts of the control and coordination. Production systems are enabled to act autonomously. A service infrastructure provides the necessary directory services to provide the asset administration shells with an entry point and to offer suitable routing services. The overall structure is demonstrated and evaluated using a representative example from forestry.

In the production industry, the volume, variety, and velocity of data as well as the number of deployed protocols increase exponentially due to the influences of the Internet-of-Things (IoT) advances. While hundreds of isolated solutions exist to utilize these data, e.g., optimizing processes or monitoring machine conditions, the lack of a unified data handling and exchange mechanism hinders the implementation of approaches to improve the quality of decisions and processes in such an interconnected environment. The vision of anInternet of Productionpromises the establishment of aWorldwide Lab, where data from every process in the network can be utilized, even interorganizational and across domains. While numerous existing approaches consider interoperability from an interface and communication system perspective, fundamental questions of data and information interoperability remain insufficiently addressed. In this article, we identifytenkey issues, derived from three distinctive real-world use cases that hinder large-scale data interoperability for industrial processes. Based on these issues, we derive a set offivekey requirements for future (IoT) data layers, building upon the FAIR data principles. We propose to address them by creatingFactDAG, a conceptual data layer model for maintaining a provenance-based, directed acyclic graph of facts, inspired by successful distributed version-control and collaboration systems. Eventually, such a standardization should greatly shape the future of interoperability in an interconnected production industry.

The manual cultivation of biological cells is very time- and cost-intensive. The automation of these processes promises significant cost savings as well as the required transparency and quality of the results. Biological cell cultivation protocols are constantly being researched and modified, which enormously increases the flexibility requirements for the plant technology. An important aspect is the early consideration of different laboratory equipment and the possibility of step-by-step partial automation of biological processes. In the course of process development and automation, it helps that manually executed process parts can be transparently integrated into the higher-level process control before they are automated using suitable laboratory equipment. Furthermore, device failures can be replaced by manual process execution. This paper presents a method for mapping biological skills using OPC UA models and integrating them into automated plants.

In the context of the Industrial Internet of Things safety and robustness play a crucial role as autonomous and emergent behavior increase the complexity of Cyber-Physical Production Systems. Given the intractability of exhaustively verifying distributed production systems, testing and runtime monitoring seem to be two promising methods used to verify correctness in the digitally networked factory. External runtime monitoring is an efficient and lightweight technique that bridges the gap between testing and verification.This paper describes a framework for on-the-fly monitor generation using a state-of-the-art monitoring algorithm for proving properties of a distributed production system relying on the Amazon Web Services Internet of Things architecture and the use of the digital shadow. The feasibility of the proposed architecture is evaluated using an industrial case study.

Due to agile product development, production systems have to be flexible and adaptable to meet high quality standards and a high productivity. As a result, set-up processes has to be shorter and more resilient because of the increasing number of variants. To meet future requirements, the processes need to be self-adaptive and reconfigurable at any time. Nowadays, a shift of the automation pyramid to interconnected cyber physical systems can be observed as well as emerging technologies as cloud and edge computing are introduced to production systems. These technologies in combination with the Digital Shadow, which provides information about all production assets, open up potential for an adaptive process control and an overall life cycle data management. For this, the Digital Shadow has to be used not only for the aggregation of data, but also for pushing data back into the system and to control the process. As a result, services in regard to an architecture based on edge computing as an enabling technology for an adaptive production together with the Digital Shadow are presented, implemented and discussed on the basis of an industrial use case.

Todays engineering processes utilize purchased parts from different manufacturers to set up a product model within engineering tools. As manufacturers provide product data using different catalog services, multiple interfaces have to be implemented to integrate data of purchased parts into engineering tools. By downloading the data into the engineering tool at a certain time, data consistency is interrupted. A holistic solution is still missing. This paper depicts an integrative concept to utilize Industry 4.0 components in the engineering process, allowing an extension of data consistency from manufacturers product descriptions over engineering tools to the product life cycle.

Feed drive systems of machine tools have to fulfil sophisticated requirements concerning speed and contouring accuracy. Due to this, disturbance force compensation of the feed drive systems is an important technology to enhance the accuracy. Since a relative delay of the feed drives behavior causes contouring errors in high-speed motion, model-based compensation of disturbance force is essential. Disturbance forces have complex characteristics that are affected by several state values such as the position of the mechanic and velocity of the tool or work piece. Therefore, systematic analysis and modeling are necessary. In addition, parameters of disturbance force change according to the conditions such as temperature and table load. Hence, identification of model parameters during operation is also an important topic. In this article, a method for model identification of disturbances is presented. From the result of measurement a combined disturbance force model is suggested. In addition an automatic identification algorithm for updating model parameters is implemented and tested.

Due to the rising share of renewable energy sources in the energy market (e.g. 40 % in Germany 2018) the power grid has to be stabilized by other sources of balancing power than conventional power plants and the volatility of the energy price is expected to increase. Production machines in the industry have unused energy flexibilities in their production processes. Those flexibilities like the differences in energy consumption between various machining processes or even between single processing steps could be used for demand-side management. This paper presents an approach on how to model and control the energy consumption of CNC (Computerized Numerical Control) machines. While in previous studies on energy flexibilities, mainly high energy-consuming auxiliary units are investigated, the focus of this publication is to use explicitly the flexibilities inside the process. The main idea is to optimize automatically the production process to a certain volatile energy price without significantly delaying the process, increasing the workload on the shop floor with additional tasks or jeopardizing (much) the workpiece quality. The proposed method uses a material removal simulation in combination with an energy model of the flexibilized machine tool, to be able to model the energy consumption of each processing step, and its dependencies to other steps. The energy costs can be reduced by scheduling the various processing steps. The precondition for the “look ahead” is a workpiece model, a model of the machine and a tool model which are described in this publication. Therefore, it is not only suitable for series production but also for small batch production. The approach is especially interesting for long production processes (>>1 h) or a market with highly volatile energy prices.

The machine tool industry faces global competition today in terms of price and quality. Feed drives have a strong influence on the positioning accuracy of the machines. The aim of this paper is to study the capability of synchronous reluctance machines (SynRM) for feed drive systems in machine tools, which are more affordable than the most used permanent magnet synchronous motors. The main disadvantage of SynRM is the presence of higher torque ripples. To simulate the influences of the torque ripple, a SynRM is investigated with finite element method and an analytical model considering saturation and slotting effects is established. A vector control based on the maximum torque per ampere (MTPA) strategy is implemented and a valid axis model of a machine tool including position control loop is used to simulate the performance of the SynRM. For comparison, the performance of a comparable permanent magnet synchronous motor (PMSM) is also investigated under the same conditions. Evaluations in time domain and frequency domain concerning dynamic behavior and positioning accuracy such as bandwidth, Kv-factor and settling time are presented. The simulation results show that SynRM could be a potential alternative in feed drive applications for machine tools with lower accuracy requirements.

The fourth industrial revolution, also referred to as Industrie 4.0, has triggered a number of research projects to improve communication systems for industrial environments. Wireless technologies for mission-critical machine-to-machine communication are expected to enable very efficient and highly flexible production processes. It is especially challenging for wireless interfaces to fulfill the required end-to-end latency and the reliability constraints of the automation industry. In order to design novel PHY and MAC schemes for ultra low delay, ultra reliable and deterministic transmission of data, e.g., through optimized pulse shaping, we study the indoor radio propagation in a representative factory automation cell where industrial robots are to be controlled. We performed channel measurements using a broadband channel sounder at 5.85 GHz carrier frequency. During the measurements, the robots were in motion and executed a typical pick-and-place process. From the recorded data we evaluate the channel characteristics and calculate relevant delay statistics. We distinguish two measurement series that differ in the scattering environment and present the derived parameters. Finally, we discuss the impact of our results on the design of new 5G waveforms for industrial radio systems.

Active damping systems are able to suppress chatter in cutting processes by counteracting occurring vibrations. Main part of such an active system is the actuator, which provides the necessary energy for the counteracting. For the use in an active damping system for large scale machine tools, a highly dynamic electrohydraulic actuator with steel membranes instead of gliding gaskets has been developed. In this paper a controller, which increases positioning accuracy and bandwidth of this actuator is presented.

For a long time self-optimizing production systems have been proposed as a contribution to make production processes more adaptive while keeping them synchronized towards a global goal. As today's industrial automation is identified as a bottle-neck, a control framework which is built around the cognitive platform SOAR is introduced in this paper. The main idea is the provision of a model-based approach to explicitly describe the application task and a control architecture which is able to generate adequate (or even optimal) action-flows to achieve the task. As an illustrative scenario a robot based handling cell is presented.