Waterjet machining is a particularly flexible and powerful tool for processing of high-performance materials which are difficult to machine conventionally. Waterjet cutting is a non-conventional and time efficient cut...
详细信息
Waterjet machining is a particularly flexible and powerful tool for processing of high-performance materials which are difficult to machine conventionally. Waterjet cutting is a non-conventional and time efficient cutting technique without any significant thermal influence. However, it is difficult to handle as contour damages such as striations and taper angle arise in the component for 3D cutting applications. Consequently, it is mainly used in industry just for simple cutting tasks. Therefore, the main goal of this study is to compensate the contour damages of 3D cutting applications by employing an optimized model for 3D waterjet cutting. By using the optimized model with a particular dynamic process control, the necessary required inputs of the currently prevailing 3D waterjet processing are decreased. Moreover, these processes have been optimized in terms of reducing the striation and taper angle formation. By overcoming the contour damages during 3D waterjet cutting, the utilization potential of the waterjet machining for modern productions has been increased.
In this work we investigate the effect of using synthetic data, generated in a simulation, in order to pre-train an AI-based image classification for industrial components. After pre-training we use real camera-captur...
In this work we investigate the effect of using synthetic data, generated in a simulation, in order to pre-train an AI-based image classification for industrial components. After pre-training we use real camera-captured training images to fine-tune the AI with the aim to close the Sim2Real domain gap. We compare our approach to purely using real training images of a single candidate object instance. In an exemplary case study for screw recognition, we found that a given AI classification algorithm dropped its recognition rate from 99.8% to 88.5% when testing the algorithm with known and unknown screw instances of the learned object classes, respectively. Employing our pre-training method on the basis of synthetic data, the drop in recognition rate is decreased from 99% to 96.95%. Thus, our proposed method has only a relative drop of 2.05% when shifting towards a generalized domain (including unknown part instances), while a compared approach on the basis of real camera-captured data showed a drop of 11.3%.
In recent years various cases of damage analysis have shown an increasing number of overload scenarios resulting in failures of entire press structures. This happens in spite of manufacture-compliant utilization and a...
详细信息
In recent years various cases of damage analysis have shown an increasing number of overload scenarios resulting in failures of entire press structures. This happens in spite of manufacture-compliant utilization and a correct press design process based on state-of-the-art methods such as FEM simulation. This paper proves the hypothesis that geometrical tolerances, defined clearances and geometrical signs of wear have a significant impact on residual stress of a press, by conducting an empirical sensitivity analysis. The focus is on mechanical presses with four-point leverage actuation as an example for highly over-determined press structures. As proven by FEM simulation, the identified geometrical deviations result in a preload of the press structure, amounting up to 10% of its theoretical sustainable stress. The significant impact of geometrical deviations on the residual stress has been proven successfully for the empirically determined assumption.
The technique joining by forming allows the structural integration of piezoceramic fibers into locally microstructured metal sheets without any elastic interlayers.A high-volume production of the joining partners caus...
详细信息
The technique joining by forming allows the structural integration of piezoceramic fibers into locally microstructured metal sheets without any elastic interlayers.A high-volume production of the joining partners causes in statistical deviations from the nominal dimensions.A numerical simulation on geometric process sensitivity shows that the deviations have a high significant influence on the resulting fiber stresses after the joining by forming operation and demonstrate the necessity of a monitoring *** this basis,the electromechanical behavior of piezoceramic array transducers is investigated experimentally before,during and after the joining *** piezoceramic array transducer consists of an arrangement of five electrical interconnected piezoceramic *** findings show that the impedance spectrum depends on the fiber stresses and can be used for in-process monitoring during the joining *** on the impedance values the preload state of the interconnected piezoceramic fibers can be specifically controlled and a fiber overload.
Wet grinding is a process with a complex interaction of individual sub-processes such as fluid mechanics, continuum mechanics and thermodynamics and branched coupling of corresponding properties. In order to be able t...
Wet grinding is a process with a complex interaction of individual sub-processes such as fluid mechanics, continuum mechanics and thermodynamics and branched coupling of corresponding properties. In order to be able to represent these properties in a model, this paper develops a description of the hydrodynamic properties in the grinding gap as a building block for a simple but accurate model to describe the process of wet grinding. To this end, it is shown that the Reynolds equation, which is well-established in the lubrication theory, is also suitable for describing an exemplary grinding wheel with abrasive grains or pores. This is done by demonstrating the feasibility of a calculation and by comparing the results with Computational Fluid Dynamics (CFD) simulations.
The production phase has a major influence on the embodied energy of many products and, thus, their overall environmental performance. As a result, manufacturing enterprises are prompted to raise their energy efficien...
详细信息
The production phase has a major influence on the embodied energy of many products and, thus, their overall environmental performance. As a result, manufacturing enterprises are prompted to raise their energy efficiency and flexibility to improve their products’ sustainability. The simultaneous integration of renewable energy sources and decentral storages is a feasible option in this but also require consistent solutions for appropriately planning and controlling the operation of the entire factory system. This paper proposes an iterative multi-stage heuristic optimization for intelligent load and energy management. A load profile of the production plan, based on the minimized overall makespan, is checked against the available energy supply to identify demands and opportunities to shift single jobs based on calculated buffer times. Whenever infeasibility is determined, the process returns to the previous production planning stage for further alterations. This cycle is initiated regularly (e.g. weekly) or following certain events (e.g. long-lasting machine failure) and terminates once all restrictions are observed or if a termination threshold (e.g. calculation time) is reached. The experimental setup used for developing and validating this approach to energy-aware factory operation makes use of a probabilistic material flow simulation model. It provides information on tasks to be scheduled and executes production plans to evaluate the performance of the proposed solution. This new approach to energy-aware factory operation also provides opportunity to integrate additional ecologic criteria to improve the sustainability of manufactured products.
In rear axle drive assembly, drive bevel gear and crown gear are aligned within a narrow tolerance range and installed in the gearbox. Due to limited adaptability after installation, the ideal dimension is estimated a...
详细信息
In rear axle drive assembly, drive bevel gear and crown gear are aligned within a narrow tolerance range and installed in the gearbox. Due to limited adaptability after installation, the ideal dimension is estimated a priori based on physical correlations and empirical correction terms. This paper follows a data-driven approach to predict the installation dimension with sufficient accuracy within a comprehensive optimization strategy in industrial application. An initial evaluation with production data logged in day-to-day operations suggests a significant improvement in accuracy compared to status quo and contributes to the dissemination of predictive analytics in industrial practice.
Highly developed production technologies facilitate unique component characteristics depending on the respective manufacturing objective. However, often several technologies are required in a sequential manner to achi...
详细信息
Highly developed production technologies facilitate unique component characteristics depending on the respective manufacturing objective. However, often several technologies are required in a sequential manner to achieve either the geometrical or the mechanical component properties. Innovative stainless steel alloys show an outstanding work hardening capability. Therefore, they are of great interest for the development of an enhanced burnishing process. The incremental cold formingtechnology of profile cross rolling can be applied to burnish machined preforms. This paper examines an approach for the geometrical preform design. Starting from the geometrical surface of revolution, the procedure is further developed to helical component surfaces. Both numerical and experimental results indicate that the preform design allows attaining a hardness increase in highly loaded component subsurface regions. This hardness increase goes along with low geometrical deviations and high surface integrity. Hence the results allow the conclusion that this technological development enables the achievement of several component characteristics with one fast burnishing operation. This might lead to an increased acceptance of forming technologies in industries that are usually characterized by pure machining processes. Such an industry could be plastics compounding.
Tool condition monitoring is a key component of predictive maintenance in smart manufacturing. Predicting excessive tool wear in machining processes becomes increasingly difficult if different materials need to be pro...
详细信息
Tool condition monitoring is a key component of predictive maintenance in smart manufacturing. Predicting excessive tool wear in machining processes becomes increasingly difficult if different materials need to be processed. We propose a novel computer vision-based system for saw blade condition monitoring that is independent of the processed materials and combines deep learning with classic computer vision. Our approach allows for accurate condition monitoring of blade wear which can further be used for predictive maintenance. Additionally, the system can classify different defect types such as missing blade teeth, thus preventing the production of scrap parts.
At present, the process selection, the selection of tools and tool materials are key functions for the economic efficiency of manufacturing lines. The continuous improvements in production technology, including the re...
详细信息
At present, the process selection, the selection of tools and tool materials are key functions for the economic efficiency of manufacturing lines. The continuous improvements in production technology, including the related machine and tooling technology, have made it possible to increase both economic efficiency and resource efficiency in production. As a result of the market demand for a high variety of products and the constant change in the demand structure, the requested volume of individual product types is reduced – the trend towards small-series production is constantly increasing. In hot bulk forming processes, it is usually not possible to produce the workpiece in just one forming step. As an alternative to the well-known machining processes for optimized preforms, the axial feed cross rolling process was developed from wedge cross rolling. Due to the all-purpose tools, the use of this process is already economical for very small batch sizes. In order to achieve optimum results with regard to optimized mass pre-distribution, the process parameters during rolling must be kept within close limits. If this is the case, axial feed cross rolling allows additional material savings of between 12% and 15% compared to other preforming processes. In order to achieve best results, the preform operation is designed by using FE simulation axial feed cross rolling.
暂无评论