Energy transition yes, but a wind turbine nearby? No! The expansion of wind energy is urgently needed, but resistance in the neighborhood and from nature conservation associations delays or stops many construction projects. Using artificial intelligence (AI), the interdisciplinary WindGISKI joint project aims to accelerate the expansion of wind energy. Eight companies, associations and research institutions are developing a geo-information system that will predict the prospects of success for wind energy construction projects.
artificial intelligence, AI, energy transition, wind energy, land evaluation, geoinformation system
Supply chain resilience is massively gaining importance for manufacturing companies in times of severe disruption due to crises. Supplier selection is a key aspect of building a resilient supply chain. Currently, however, there is no holistic method for supplier selection that takes resilience into account. This paper therefore presents a research project that aims to develop an assessment measure for resilience in the context of supplier selection. The aim is to consider the existing resilience from the supplier company’s perspective and the required resilience from the selecting company's perspective.
Logistics, Supplier Selection, Resilience, Supply Chain, Supply Chain Management
Volatile markets and increasing product variance lead to more complex internal material flows. In order to cope with this, a significant increase in the flexibility and adaptability of prevailing intralogistics systems is necessary. (Small-scale) modular conveyor systems can be used to make intralogistics more flexible. Obstacles for the practical use are the low distribution as well as the high investment costs. In order to reduce reservations as well as risks, an evaluation and optimization method as well as an applicationoriented planning tool for modular conveyor system layouts were developed in a research project. It enables both planning service providers and users to evaluate modular conveyor systems and to exploit their potential.
Conveyor Technology, Layout Planning, Optimization, Genetic Algorithm, Software
Work-related illnesses and the resulting employee absences can have a major impact on productivity and competitiveness, especially in small and medium-sized enterprises. Particularly in the forging industry, the manual handling of forged parts leads to high physical stress and thus to frequent illnesses of the musculoskeletal system, especially of the hand-arm system. One possibility to counteract this circumstance is the use of ergonomic forging tongs. In the study presented here, the influence of ergonomic forging tongs on the physical stress of forging employees was investigated by simulation and experiment and compared to conventional forging tongs. Within the simulation and the experimental investigation, forging parts and forging tongs were varied. In the simulation, an ergonomics assessment of the forging situation could be evaluated using the Ergonomic Assessment Worksheet. In the experimental study, gripping force measurements and calorie measurements were used to determine the impact of handling the forging tongs on the forging employees. The results show that the use of the new ergonomically optimized forging tongs can lead to a significant physical relief for the forging employees. The knowledge gained from the ergonomically developed concepts can also be transferred in other industries.
forming technology, ergonomics
Limited visibility during the operation of forklifts is one of the most significant sources of danger in in-plant material handling. Existing systems record concealed areas via cameras and display them directly on monitors in the operator's cab. The operator has to temporarily turn his attention to a screen and is unable to perceive the real information necessary for the driving task. We developed the first augmented reality based driver assistance system for safety improvement in intralogistics. The results show the capability to eliminate view restrictions directly in the operator's field of view and create the illusion of transparent vehicle components.
augmented reality, assistance system, intralogistics
Machine learning is already used in many areas of everyday life and offers far-reaching potential in production. At the same time, the efficient use of resources is becoming increasingly important due to the growing relevance of ESG. By implementing machine learning in production to increase resource efficiency, companies can become more effective and efficient while implementing ESG strategies. SMEs, in particular, face a major challenge when it comes to implementation. In addition to the high complexity of Machine Learning applications, there is often a lack of knowledge about suitable application possibilities as well as a lack of conviction about the benefits that can be derived from them. In the following article, applications of Machine Learning to increase resource efficiency along the internal supply chain as well as their potentials are discussed.
Machine Learning, production, resource efficiency
The realization of a planned layout concept represents a complex subtask within factory planning. In particular, the temporal arrangement of the necessary relocation steps, taking into account existing restrictions, is usually carried out manually according to the current state of the art. Therefore, an easy-to-use method for planning a factory move for reorganization projects was developed in a research project, which can be applied by companies in a practical context.
factory planning, removal planning, project scheduling, optimization, operations research
The use of machine learning has already become es-tablished and is applied in many areas of everyday life. Machine Learning is also becoming increasingly important in the field of production and logistics. However, the complex implementation poses major challenges, especially for small and medium-sized enterprises (SMEs). This leads to the fact that many SMEs refrain from using Machine Learning applications. For this reason, IPH – Institut für Integrierte Produktion and IPRI – International Performance Research Institute are working together on the research project „MLready“ to develop an implementation strategy that will enable SMEs to im-plement and use machine learning easily and efficiently.
machine learning, SMEs, production, ML implementation strategy
Although factory planning is widely recognized as a way to significantly enhance manufacturing productivity, the associated costs in terms of time and money can be prohibitive. In this paper, we present a solution to this challenge through the development of a Software-in-the-loop (SITL) framework that leverages an Unmanned Aircraft System (UAS) in an autonomous capacity. The framework incorporates simulated sensors, a UAS, and a virtual factory environment. Moreover, we propose a Deep Reinforcement Learning (DRL) agent that is capable of collision avoidance and exploration using the Dueling Double Deep Q-Network (3DQN) with prioritized experience replay.
Artificial Intelligence, reinforcement learning, Unmanned Aircraft Systems
Forgings are produced in several process steps, the so-called forging sequence. The design of efficient forging sequences is a very complex and iterative development process. In order to automate this process and to reduce the development time, a method is presented here, which automatically generates multi-stage forging sequences for different forging geometries on the basis of the component geometry (STL file). The method was developed for closed die forging. The individual modules of this forging sequence design method (FSD method) as well as the functioning of the algorithm for the generation of the intermediate forms are presented. The method is applied to different forgings with different geometrical characteristics. The generated forging sequences are checked with FE simulations for the quality criteria form filling and freedom from folds. The simulation results show that the developed FSD method provides good approximate solutions for an initial design of forging sequences for closed die forging in a short time.
forging sequence, forging sequence planning, automation
The realization of reorganization projects represents a complex and independent planning task within the framework of factory layout planning. Only little methodical knowledge exists, which considers the temporal, spatial and organizational restrictions in the creation of a schedule. This paper aims to present the interdependencies in the planning and execution of realization projects and thus to provide a basis for discussion for further investigations in the field of scheduling factory relocations for the reorganization of factory objects.
factory planning, relocation planning, project planning, effect modeling
Process Optimization through Thin Flash Prevention. Due to the good flow properties of aluminum, the material tends to flow into tool gaps during flashless precision forging and produce the so-called thin flash. For the industrial implementation of flashless precision forging processes, an innovative prediction method for thin flash as well as sealing concepts are to be developed in cooperation with an industrial partner. Simulative studies show that local form filling does not correlate with high pressure or an increased potential for thin flash.
thin flash, FEM-simulation, sealing concepts, precision forging, forming technology
Progressive digitalization and new technologies have had a major impact on the development of artificial intelligence (AI) in recent years. Particularly for companies in the skilled trades sector, the time factor is taking on an increasingly changing customer behavior, more complex and demanding tasks, and other challenges, the time factor is playing an increasingly decisive role.
artificial intelligence, craft, guideline
A new process chain for the manufacturing of load-adapted hybrid components is presented. The "Tailored Forming” process chain consists of a deposition welding process, hot forming, machining and an optional heat treatment. This paper focuses on the combination of laser hot-wire cladding with subsequent hot forming to produce hybrid components. The applicability is investigated for different material combinations and component geometries, e.g. a shaft with a bearing seat or a bevel gear. Austenitic stainless steel AISI 316L and martensitic valve steel AISI HNV3 are used as cladding materials, mild steel AISI 1022M and case hardening steel AISI 5120 are used as base materials. The resulting component properties after laser hot-wire cladding and hot forming such as hardness, microstructure and residual stress state are presented. In the cladding and the heat-affected zone, the hot forming process causes a transformation from a welding microstructure to a fine-grained forming microstructure. Hot forming significantly affects the residual stress state in the cladding the resulting residual stress state depends on the material combination.
laser hot-wire cladding, cladding, hot forming, residual stress, tailored forming
Geometry, design, and processing in addition to the thermoelectric material properties have a significant influence on the economic efficiency and performance of thermoelectric generators (TEGs). While conventional BULK TEGs are elaborate to manufacture and allow only limited variations in geometry, printed TEGs are often restricted in their application and processing temperature due to the use of organic materials. In this work, a proof-of-concept for fabricating modular, customizable, and temperature-stable TEGs is demonstrated by applying an alternative laser process. For this purpose, low temperature cofired ceramics substrates were coated over a large area, freely structured and cut without masks by a laser and sintered to a solid structure in a single optimized thermal post-processing. A scalable design with complex geometry and large cooling surface for application on a hot shaft was realized to prove feasibility.
thermoelectric, printed electronic, laser structuring, printed ceramics, spray coating
The digital development of spaces within the city of Hannover by means of a digital image makes it possible to cover the usage needs of spaces more efficiently and in line with the requirements. The crea-tion of a digital image, which develops new possibilities for access to public space, requires the use of different sensors such as LiDAR sensors and tracking cameras. In order to select suitable sensors that can be used with UAS, the requirements for the overall system are first defined, which are derived in functional requirements for the sensor technology. Subsequently, the degree of fulfilment of the functional requirements by the different sensors
5G, UAS, digital image, digital twin
In the non-circular rolling, the feasibility of rolling several mutually offset, locally non-round shaped elements into a cylindrical semi-finished product are investigated. One sub-area of the investigations is the rolling of two elliptical sections.
From three different calculation concepts for the determination of the tool engraving, one was chosen for a simulative parameter study. The main influencing variables, including the length and width of the engraving and a process window, were identified.
forming technology, manufacturing technology, FEM
In order to use laser transmission welding (LTW) for additively manufactured parts such as prototypes, small series, or one-off products, an enhanced process knowledge is needed to overcome the difficulties in the part composition resulting from the additive manufacturing process itself. In comparison to an injection molding process for thermoplastic parts, the additive manufacturing process fused deposition modeling leads to an inhomogeneous structure with trapped air inside the volume.
In this paper, a neural network-based expert system is presented that provides the user with process knowledge in order to improve the weld seam quality of laser welded additively manufactured parts. Both additive manufacturing and LTW process are assisted by the expert system. First, the designed expert system supports the user in setting up the additive manufacturing process to increase the transmissivity. During welding, the additive manufacturing and LTW process parameters are used to predict the weld seam strength. To create the database for the expert system, specimens of transparent and black polylactide are additively manufactured. In order to change the transmissivity at an emission wavelength of 940?nm of the diode laser used, the manufacturing parameters for the transparent parts are varied. The transmissivity of the parts is measured with a spectroscope. The transparent samples are welded to the black samples with laser powers between 8 and 14?W in the overlap configuration and shear tensile tests are performed. In this work, the predictions of the transmissivity and the shear tensile force are demonstrated with an accuracy of more than 88.1% of the neural networks used for the expert system.
Additive manufacturing, laser transmission welding, neural networks, expert system
In order to make the production of complex geometries as efficient as possible, several forming stages are generally used. In these, the billet is first heated homogeneously and then forged via several preliminary and intermediate stages as well as final forming. Previous investigations have shown that significant material savings can be achieved by using inhomogeneous, rather than homogeneous, billet heating. A limiting factor in the practical implementation of inhomogeneous heating is the temperature gradient between the hot and warm regions of the billet.
This study therefore investigates the influence of the length of the temperature gradient on the blank size required to achieve form filling for a given finished part geometry. For this purpose, a simulative parameter study was carried out with three temperature transitions of different lengths and two different finished part sizes.
It was shown that, depending on the finished part size and the length of the temperature gradient, between 3.31% and 17.49% material can be saved compared to a homogeneously heated billet. The length of the temperature gradient thus has a significant influence on the material savings potential.
bulk forming, inhomogeneous heating, resource efficiency, FEA
The temporally and spatially accurate display of information in augmented reality (AR) systems is essential for immersion and operational reliability when using the technology. We developed an assistant system using a head-mounted display (HMD) to hide visual restrictions on forklifts. We propose a method to evaluate the accuracy and latency of AR systems using HMD. For measuring accuracy, we compare the deviation between real and virtual markers. For latency measurement, we count the frame difference between real and virtual events. We present the influence of different system parameters and dynamics on latency and overlay accuracy.
augmented reality, image processing, driver assistance system, forklift trucks
