10 results
Now showing1 - 10 of 10
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , Feeling machines: Prediction of thin-walled workpiece deflection by monitoring variations in tool bending moment pattern during circumferential milling(Elsevier, 2026-06-30); ; ; In circumferential milling, the in-process deflection of thin-walled workpieces induced by feed normal forces results in reduced material removal, leading to geometric errors after machining. With the increasing use of additive manufacturing technologies and the production of near-net-shape structures, this problem is gaining increasing importance. Various strategies attempt to compensate for this geometric errors, for example by modeling the occurring cutting forces and workpiece deflection and then applying countermeasures during machining. However, this requires a high level of process understanding, and multiple parameters need to be considered, including material properties, cutting edge geometry as well as wear state of the tool. This paper examines a novel approach to predict workpiece deflection state by analyzing the bending moment pattern measured by an in-process sensor system located in the tool holder. It could be demonstrated that features extracted and evaluated from the bending moment signal can represent the current deflection state of the workpiece in an offline approach, enabling future in-situ toolpath adaptation to reduce geometric errors without relying on time-consuming simulation of the workpiece stiffness and with minimal signal processing effort.Publicationtype: Journal Article38 16 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Resonant surface acoustic wave sensors for in-situ monitoring of cutting forces in turning processes(IEEE, 2026-01); ; ; ; Effective monitoring of machining processes requires robust and cost-effective sensors capable of capturing dynamic forces. This study investigates a turning tool holder with an integrated 2.4 GHz resonant surface acoustic wave (SAW) sensor for measuring cutting forces under varying feed rate conditions. Reference measurements were performed using a calibrated dynamometer. The comparison between the SAW sensor and the dynamometer data revealed strong agreement, confirming that the integrated sensor captures the progression of the cutting force. These results demonstrate the potential of SAW-based sensor technology for real-time monitoring of forces in machining processes.Publicationtype: Conference Paper73 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Prozesskette zum Oberflächenschleifen von nachgiebigen Luftfahrtstrukturbauteilen aus kohlenstofffaserverstärkten Kunststoffen(Deutsche Gesellschaft für Luft- und Raumfahrt - Lilienthal-Oberth e.V. (DGLR), 2025-11-07); ; In the production of structural components made of carbon fiber-reinforced plastics (CFRP) in aircraft manufacturing, manufacturing-related dimensional deviations can occur. These lead to gaps during assembly, which have so far been compensated by so-called shimming. For this purpose, manual filler materials are applied at the affected areas. However, this process is time-consuming and costly. A promising alternative is the automated sanding of the component surfaces, provided that designated sacrificial layers are available. The goal is to avoid shimmering by selectively removing the surface irregularities that cause the gaps. However, implementation presents particular challenges. On the one hand, process forces act during grinding, which can lead to undesired component displacement. This is especially true for thin-walled, locally supported, and thus flexible structures. On the other hand, grinding forces continuously increase with increasing tool wear. As part of the SHILA project (Shim-free assembly of thin-walled aircraft structures), the Institute for Production Management and Technology (IPMT) at the Technical University of Hamburg (TUHH), together with the project partners (Boeing Germany GmbH, Broetje-Automation GmbH, KEBA Industrial Automation Germany GmbH, 3D.aero GmbH, WZL RWTH Aachen), is investigating, among other things, a grinding process chain that addresses these challenges by compensating for component deflection. The focus is on the application case of fuselage section assembly, where the individual fuselage segments exhibit deviations from the nominal contour. For this purpose, test rigs have been set up at IPMT to examine individual elements of the process chain in both analogy experiments and under conditions close to practical application. The focus is on selecting suitable tools and processing strategies, predicting the resulting process forces while taking tool wear into account, and integrating them into a FEM model to simulate component-specific displacement. Based on the simulated deformations, the tool path can then be adjusted to minimize component displacement.Publicationtype: Conference Paper34 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Enhancing Tool Replacement Decisions in Milling of Ti-6Al-4V Using Convolutional Neural Networks and Time-series-to-image Encoding(2023-12-11); ; ; ; In manufacturing of structural components for the aerospace industry, the application of milling tools with fixed service life time is a common practice. A tool replacement is often based on predetermined schedules rather than the actual wear. Consequently, tools may be replaced too soon or too late with respect to a defined final state of wear. To address this issue, different evaluation methods based on sensor data from the machining process have been proposed in the literature as a means of predicting tool wear and automating tool change decisions. However, decision models often do not take into account the variability of the data due to a change in the cutting parameters and tool load, thereby limiting their applicability to specific situations. In this paper, a convolutional neural network (CNN) is trained based on the pretrained GoogLeNet architecture to detect different states of tool wear in circumferential milling of Ti-6Al-4V with varying cutting parameters. Experiments have been carried out to capture sensor data, such as structure-borne noise, machine drive data, and cutting forces, in comparable states of tool wear under varying cutting parameters, for the purpose of model training and assessment. Different types of sensor data and time-series-to-image encoding techniques have been investigated in terms of model performance. The conducted experiments successfully applied gramian angular fields (GAF), markov transition fields (MTF), recurrence plots (RP), wavelet transform (WT) and short time fourier transform (STFT) to different signal regions (entry, full cut and exit). Using a trained CNN for classification, accurate states of tool wear can be predicted based on the created images. WT performed best in the investigations. Furthermore, an investigation was conducted to determine the level of deviation in actual tool wear on a sample of 10 tools that were removed from an active production line after being used for a fixed duration of 60 minutes. The level of deviation on tool wear across the 10 tools was found to be significantly high, indicating that the tools were not wearing out uniformly and that there may be a need for better tool monitoring and maintenance practices. This ML-based approach enhanced the tool replacement decisions by predicting similar states closer to the actual wear of the tools. Thus, the use of a CNN is found to be a helpful method to predict tool wear even under variable process conditions. They are able to provide more accurate and timely tool replacement decisions, reducing the risk of premature or delayed replacement, and improving overall manufacturing efficiency.Publicationtype: Conference Paper55 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Improving Efficiency and Sustainability Through Predictive Tool Wear Monitoring During Manual Drilling of CFRP(2023-11-18); ; ; ; Aircraft assembly involves many high-precision rivet holes, with around one-third drilled manually by experienced workers. Wireless electrical machines are increasingly replacing pneumatic drilling machines to reduce energy consumption. Nevertheless, the lifespan of the cutting tools varies between 20 and 70 drill holes in carbon fiber reinforced polymer (CFRP) depending on the individual experience and constitution of the worker, resulting in a large waste in cemented carbide. This article proposes a method that uses the internal sensors of the drilling machine to predict tool wear during manual drilling. The main challenge is the rapid wear of the tools and the unknown feed rate, which depends on the individual workers’ constitution and experience. By predicting tool wear, this method can help reduce waste and improve the efficiency, sustainability, and precision of manual drilling operations in aircraft structural assembly.Publicationtype: Conference Paper70 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Characterization of the surface error during peripheral milling of thin-walled, near-net-shaped structures(Springer, 2023-11-18); ; ; ; Lightweight aerospace structural components are usually milled out of plate-material, converting up to 95% of the material into difficult to recycle chips. Therefore, additive-manufacturing holds great resource saving potential through the near-net-shape production of thin-walled parts. However, these parts pose new challenges. For example, previous methods such as the “waterline”-path approach, which uses the residual stiffness of the solid-block to reduce the deformation of the thin-walls due to process forces, can only be applied to a very limited extent. This results in a greater deflection of the near-net-shape, additively-manufactured structure. In this paper the surface error is investigated using milling experiments. An analytical approach to qualitatively predict the surface characteristics is provided. The results get used to discuss whether an adjustment to the tool path is suitable to compensate for the dimensional error. Such a compensation method has the potential to efficiently machine near-net-shape semi-finished parts within the required tolerances.Publicationtype: Conference Paper60 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Nutzung von Methoden des Maschinellen Lernens für die Werkstückqualität- und Werkzeugverschleißüberwachung bei semi-automatischen Bohrprozessen(Deutsche Gesellschaft für Luft- und Raumfahrt - Lilienthal-Oberth e.V. (DGLR), 2023-11-10); ; Riveting structural components in aircraft construction requires the production of a large number of rivet holes. Quality standards must be maintained for each well to avoid rework and waste. This results in high demands on process stability and quality monitoring during drilling. The production of rivet holes is increasingly being carried out with electric, semi-automatic drill feed units (BVE), replacing pneumatically operated machines. The electrical BVEs enable them to be equipped with internal sensors that enable recording of drive currents and vibrations of the machine structure. In this work, the process data is examined with regard to its potential for determining the currently prevailing tool wear condition and the resulting workpiece quality using machine learning (ML) methods. For this purpose, process data from drilling TiAl6V4 and CFRP were recorded in an experimental environment and examined with the help of data processing scripts in Matlab. The suitability of selected methods for dimension reduction for model training with regard to predicting tool wear and workpiece quality was determined. Relevant features could be identified primarily in the time domain and in the time-frequency domain of the wavelet transformation of the feed motor current. Prediction models could be successfully trained for both wear and quality based on the highlighted characteristics. The evaluation of the classification and regression showed good prediction of tool wear using classification trees as well as irregularized and regularized linear regression. Good quality predictions could be achieved for the exit burr height when drilling in TiAl6V4 and for the delamination on the exit side when drilling in CFRP. The results achieved form a basis for further development of methods using machine learning in quality control during drilling.Publicationtype: Conference Paper25 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , ML Models for Intelligent Tool Replacement(2023-11); ; The wear limits of milling tools should not be exceeded with regard to the workpiece quality. Current approaches of relying on fixed service lifetimes for tool replacement overlook the crucial factor of varying wear rates and fail to determine the optimal times for replacement. This article presents an approach that uses ML algorithms in the decision-making process, which enables a tool replacement while considering varying wear rates within a defined range of cutting parameters. © 2023 Walter de Gruyter GmbH, Berlin/Boston, GermanyPublicationtype: Journal Article38 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Adaptive Präzisionsbearbeitung additiv gefertigter Leichtbaustrukturen in der digitalisierten Prozesskette(Machining Innovations Network e.V., 2021); ; ; Publicationtype: Journal Article116 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , Finish machining of Ti6Al4V SLM components under consideration of thin walls and support structure removalUsing additive manufacturing (AM) technologies such as powder bed based selective laser melting, it is possible to realize new bionic designs for Ti6Al4V aerospace components, thus significantly reducing weight. With these technologies, the goals of reducing emissions in the aviation industry can be achieved while passenger numbers are growing at the same time. In order to fulfill the quality requirements of the components, the AM process chain includes many further process steps in addition to melting, such as heat treatment. Furthermore, the functional surfaces must be machined and the support structures removed. These are essential for selective laser melting. The paper shows how the deflection of the workpiece can be minimized by milling thin-walled functional surfaces using a clamping device with support points. This increases the geometric accuracy considerably. Finally, the paper shows the results for milling support structures. The design of the support structure has a high effect on the machining behavior. Finally, results are presented that show the influence of different milling strategies on the surface quality of AM components, considering the support structures.Publicationtype: Journal ArticleScopus© Citations 23 328 383