Unsupervised Deep Learning for Advanced Forming Limit Analysis in Sheet Metal: A Tensile Test-Based Approach.

An accurate description of the formability and failure behavior of sheet metal materials is essential for an optimal forming process design. In this respect, the forming limit curve (FLC) based on the Nakajima test, which is determined in accordance with DIN EN ISO 12004-2, is a wide-spread procedure for evaluating the formability of sheet metal materials. Thereby the FLC is affected by influences originating from intrinsic factors of the Nakajima test-setup, such as friction, which leads to deviations from the linear strain path, biaxial prestress and bending superposition. These disadvantages can be circumvented by an alternative test combination of uniaxial tensile test and hydraulic bulge test. In addition, the forming limit capacity of many lightweight materials is underestimated using the cross-section method according to DIN EN ISO 12004-2, due to the material-dependent occurrence of multiple strain maxima during forming or sudden cracking without prior necking. In this regard, machine learning approaches have a high potential for a more accurate determination of the forming limit curve due to the inclusion of other parameters influencing formability. This work presents a machine learning approach focused on uniaxial tensile tests to define the forming limit of lightweight materials and high-strength steels. The transferability of an existing weakly supervised convolutional neural network (CNN) approach was examined, originally designed for Nakajima tests, to uniaxial tensile tests. Additionally, a stereo camera-based method for this purpose was developed. In our evaluation, we train and test materials, including AA6016, DX54D, and DP800, through iterative data composition, using cross-validation. In the context of our stereo camera-based approach, strains for different materials and thicknesses were predicted. In this cases, our method successfully predicted the major strains with close agreement to ISO standards. For DX54D, with a thickness of 0.8 mm, the prediction was 0.659 (compared to ISO's 0.664). Similarly, for DX54D, 2.0 mm thickness, the predicted major strain was 0.780 (compared to ISO 0.705), and for AA6016, at 1.0 mm thickness, a major strain of 0.314 (in line with ISO 0.309) was estimated. However, for DP800 with a thickness of 1.0 mm, the prediction yielded a major strain of 0.478 (as compared to ISO 0.289), indicating a divergence from the ISO standard in this particular case. These results in general, generated with the CNN stereo camera-based approach, underline the quantitative alignment of the approach with the cross-section method.

Warmforming Flow Pressing Characteristics of Continuous Fibre Reinforced Thermoplastic Composites.

The paper presents research regarding a thermally supported multi-material clinching process (hotclinching) for metal and thermoplastic composite (TPC) sheets: an experimental approach to investigate the flow pressing phenomena during joining. Therefore, an experimental setup is developed to compress the TPC-specimens in out-of-plane direction with different initial TPC thicknesses and varying temperature levels. The deformed specimens are analyzed with computed tomography to investigate the resultant inner material structure at different compaction levels. The results are compared in terms of force-compaction-curves and occurring phenomena during compaction. The change of the material structure is characterized by sliding phenomena and crack initiation and growth.

Analysis of the Influence of Surface Modifications on the Fatigue Behavior of Hot Work Tool Steel Components.

Hot work tool steels (HWS) are widely used for high performance components as dies and molds in hot forging processes, where extreme process-related mechanical and thermal loads limit tool life. With the functionalizing and modification of tool surfaces with tailored surfaces, a promising approach is given to provide material flow control resulting in the efficient die filling of cavities while reducing the process forces. In terms of fatigue properties, the influence of surface modifications on surface integrity is insufficiently studied. Therefore, the potential of the machining processes of high-feed milling, micromilling and grinding with regard to the implications on the fatigue strength of components made of HWS (AISI H11) hardened to 50 ± 1 HRC was investigated. For this purpose, the machined surfaces were characterized in terms of surface topography and residual stress state to determine the surface integrity. In order to analyze the resulting fatigue behavior as a result of the machining processes, a rotating bending test was performed. The fracture surfaces were investigated using fractographic analysis to define the initiation area and to identify the source of failure. The investigations showed a significant influence of the machining-induced surface integrity and, in particular, the induced residual stress state on the fatigue properties of components made of HWS.

Forming of Components with Microgearings from Coil Material-Numerical Modeling of the Process Chain and Experimental Validation.

Compared to alternative production methods, cold forming offers technological, economic and ecological potential for the mass production of microgears. Within the current boundaries of the technology, the cold forming of modules m < 0.2 mm is not possible due to size effects, high tool stresses and handling problems. The investigations of this contribution present a novel process chain for the multi-step forming of microgears with a module of m = 0.1 mm. For this purpose, a numerical model of the first two steps of the process chain is set up and confirmed based on experimental forming tests. The results have proven the feasibility of the process chain by a complete forming of the gear teeth.

Investigation of Size Effects in Multi-Stage Cold Forming of Metallic Micro Parts from Sheet Metal.

Product miniaturisation and functional integration are currently global trends to save weight, space, materials and costs. This leads to an increasing demand for metallic micro components. Thus, the development of appropriate production technologies is in the focus of current research activities. Due to its efficiency, accuracy and short cycle times, microforming at room temperature offers the potential to meet the steadily increasing demand. During microforming, size effects occur which negatively affect the part quality, process stability, tool life and handling. Within this contribution, a multi-stage bulk microforming process from sheet metal is investigated for the materials Cu-OFE and AA6014 with regard to the basic feasibility and the occurrence of size effects. The results reveal that the process chain is basically suitable to produce metallic micro parts with a high repeatability. Size effects are identified during the process. Since several studies postulate that size effects can be minimised by scaling down the metallic grain structure, the grain size of the aluminium material AA6014-W is scaled down to less than one micrometre by using an accumulative roll bonding process (ARB). Subsequently, the effects of the ultrafine grain (UFG) structure on the forming process are analysed. It could be shown that a strengthened material state increases the material utilization. Furthermore, too soft materials can cause damage on the part during ejection. The occurring size effects cannot be eliminated by reducing the grain size.

Fringe Projection Profilometry in Production Metrology: A Multi-Scale Comparison in Sheet-Bulk Metal Forming.

Fringe projection profilometry in combination with other optical measuring technologies has established itself over the last decades as an essential complement to conventional, tactile measuring devices. The non-contact, holistic reconstruction of complex geometries within fractions of a second in conjunction with the lightweight and transportable sensor design open up many fields of application in production metrology. Furthermore, triangulation-based measuring principles feature good scalability, which has led to 3D scanners for various scale ranges. Innovative and modern production processes, such as sheet-bulk metal forming, thus, utilize fringe projection profilometry in many respects to monitor the process, quantify possible wear and improve production technology. Therefore, it is essential to identify the appropriate 3D scanner for each application and to properly evaluate the acquired data. Through precise knowledge of the measurement volume and the relative uncertainty with respect to the specimen and scanner position, adapted measurement strategies and integrated production concepts can be realized. Although there are extensive industrial standards and guidelines for the quantification of sensor performance, evaluation and tolerancing is mainly global and can, therefore, neither provide assistance in the correct, application-specific positioning and alignment of the sensor nor reflect the local characteristics within the measuring volume. Therefore, this article compares fringe projection systems across various scale ranges by positioning and scanning a calibrated sphere in a high resolution grid.

Investigation of the Microstructural Evolution during Hot Stamping of a Carburized Complex Phase Steel by Laser-Ultrasonics.

Prior carburization of semi-finished steel sheets is a new process variant in hot stamping to manufacture parts with tailored properties. Compared to conventional hot stamping processes, a complex phase typed steel alloy is used instead of 22MnB5. Yet recent investigations focused on final mechanical properties rather than microstructural mechanisms cause an increase in strength. Thus, the influence of additional carburization on the microstructural evolution during hot stamping of a complex phase steel CP-W®800 is investigated within this work. The phase transformation behavior, as well as the grain growth during austenitization, is evaluated by in-situ measurements employing a laser-ultrasound sensor. The results are correlated with additional hardness measurements in as-quenched condition and supplementary micrographs. The experiments reveal that the carburization process significantly improves the hardenability of the CP-W®800. However, even at quenching rates of 70 K/s no fully martensitic microstructure was achievable. Still, the resulting hardness of the carburized samples might exceed the fully martensitic hardness of 22MnB5 derived from literature. Furthermore, the carburization process has no adverse effect on the fine grain stability of the complex phase steel. This makes it more robust in terms of grain size than the conventional hot stamping steel 22MnB5.

Temporal and Spatial Detection of the Onset of Local Necking and Assessment of its Growth Behavior.

This study proposes a method for the temporal and spatial determination of the onset of local necking determined by means of a Nakajima test set-up for a DC04 deep drawing and a DP800 dual-phase steel, as well as an AA6014 aluminum alloy. Furthermore, the focus lies on the observation of the progress of the necking area and its transformation throughout the remainder of the forming process. The strain behavior is learned by a machine learning approach on the basis of the images when the process is close to material failure. These learned failure characteristics are transferred to new forming sequences, so that critical areas indicating material failure can be identified at an early stage, and consequently enable the determination of the beginning of necking and the analysis of the necking area. This improves understanding of the necking behavior and facilitates the determination of the evaluation area for strain paths. The growth behavior and traceability of the necking area is objectified by the proposed weakly supervised machine learning approach, thereby rendering a heuristic-based determination unnecessary. Furthermore, a simultaneous evaluation on image and pixel scale is provided that enables a distinct selection of the failure quantile of the probabilistic forming limit curve.

Determination of Forming Limits in Sheet Metal Forming Using Deep Learning.

The forming limit curve (FLC) is used to model the onset of sheet metal instability during forming processes e.g., in the area of finite element analysis, and is usually determined by evaluation of strain distributions, derived with optical measurement systems during Nakajima tests. Current methods comprise of the standardized DIN EN ISO 12004-2 or time-dependent approaches that heuristically limit the evaluation area to a fraction of the available information and show weaknesses in the context of brittle materials without a pronounced necking phase. To address these limitations, supervised and unsupervised pattern recognition methods were introduced recently. However, these approaches are still dependent on prior knowledge, time, and localization information. This study overcomes these limitations by adopting a Siamese convolutional neural network (CNN), as a feature extractor. Suitable features are automatically learned using the extreme cases of the homogeneous and inhomogeneous forming phase in a supervised setup. Using robust Student's t mixture models, the learned features are clustered into three distributions in an unsupervised manner that cover the complete forming process. Due to the location and time independency of the method, the knowledge learned from formed specimen up until fracture can be transferred on to other forming processes that were prematurely stopped and assessed using metallographic examinations, enabling probabilistic cluster membership assignments for each frame of the forming sequence. The generalization of the method to unseen materials is evaluated in multiple experiments, and additionally tested on an aluminum alloy AA5182, which is characterized by Portevin-LE Chatlier effects.

Analysis of Forming Limits in Sheet Metal Forming with Pattern Recognition Methods. Part 2: Unsupervised Methodology and Application.

The forming limit curve (FLC) is used in finite element analysis (FEA) for the modeling of onset of sheet metal instability during forming. The FLC is usually evaluated by achieving forming measurements with optical measurement system during Nakajima tests. Current evaluation methods such as the standard method according to DIN EN ISO 12004-2 and time-dependent methods limit the evaluation range to a fraction of the available information and show weaknesses in the context of brittle materials that do not have a pronounced constriction phase. In order to meet these challenges, a supervised pattern recognition method was proposed, whose results depend on the quality of the expert annotations. In order to alleviate this dependence on experts, this study proposes an unsupervised classification approach that does not require expert annotations and allows a probabilistic evaluation of the onset of localized necking. For this purpose, the results of the Nakajima tests are examined with an optical measuring system and evaluated using an unsupervised classification method. In order to assess the quality of the results, a comparison is made with the time-dependent method proposed by Volk and Hora, as well as expert annotations, while validated with metallographic investigations. Two evaluation methods are presented, the deterministic FLC, which provides a lower and upper limit for the onset of necking, and a probabilistic FLC, which allows definition of failure quantiles. Both methods provide a necking range that shows good correlation with the expert opinion as well as the results of the time-dependent method and metallographic examinations.

Analysis of Forming Limits in Sheet Metal Forming with Pattern Recognition Methods. Part 1: Characterization of Onset of Necking and Expert Evaluation.

In automotive manufacturing, high strength materials, and aluminum alloys are widely used to address the requirement of ensuring a lightweight car body and correspondingly, reducing pollution. In this context of complexity of materials and structures, an optimized process design with finite element analyses (FEA) is mandatory, as well as a correct definition of the material forming limits. For this purpose, in sheet metal forming, the forming limit curve (FLC) is used. The FLC is defined by the onset of necking. The standard evaluation method according to DIN EN ISO 12004-2 is based on the cross-section method and assumes that the failure occurs due to a clear localized necking. However, this approach has its limitations, specifically in the case of brittle materials that do not exhibit a distinct necking phase. To overcome this challenge, a pattern recognition-based evaluation is proposed. Although pattern recognition and machine learning techniques have been widely employed in the medical field, few studies have investigated them in the context of analyzing metal sheet forming limits. The application of pattern recognition in metal forming is subject to the exact definition of the forming behaviors. Thereby, it is challenging to relate patterns on the strain distribution during Nakajima tests with the onset of necking for the FLC determination. Thus, the first approach was based on the crack evaluation, since this class is well-defined. However, of substantial interest is the evaluation of the general material instabilities that precede failure. Therefore, in the present study, the analysis of the material behavior during stretching is conducted in order to characterize instability classes. The results of Nakajima tests are investigated using an optical measurement system. A conventional pattern recognition approach based on texture features, considering the outcomes of expert interviews for the definition of classes is used for the FLC determination. Moreover, an analysis of the validity of the supervised learning is conducted. The results show a good prediction of the onset of necking, even for high strength materials with a recall of up to 92%. Some deviations are observed in the determination of the diffuse necking. The discrepancies of the different experts' prognoses highlight the user-dependency of the FLC, suggesting further investigations with an data-driven approach, could be beneficial.

Investigation of Production Limits in Manufacturing Microstructured Surfaces Using Micro Coining.

The application of microstructured surfaces is one possible method to reduce friction in lubricated contacts between components with relative movement. Due to this, the energy efficiency and the occurring wear during the operating time of the final products could be decreased. To manufacture structured surfaces economically, a micro coining process was analyzed within this study. This process offers the potential for integration into the established manufacturing processes of different final products, such as tappets used in a valve train. Thus, large-scale production is enabled. To detect the manufacturing limits of the micro coining process, the manufacturing of the coining tools as well as the coining process needs to be investigated. Within this study, the achievable accuracy and the failure of cuboid and cylindrical microstructure elements with selected dimensions were analyzed. For both types of microstructures, the minimal lateral dimensions were detected. Besides the achievable accuracy, correlations between different geometrical dimensions of the micro elements are presented. Additionally, the aspect ratio is detected as the main cause of failure for the micro coining process. In general, the suitability of a coining process for manufacturing microstructured surfaces is proven.

Process Design of Aluminum Tailor Heat Treated Blanks.

In many industrials field, especially in the automotive sector, there is a trend toward lightweight constructions in order to reduce the weight and thereby the CO2 and NOx emissions of the products. An auspicious approach within this context is the substitution of conventional deep drawing steel by precipitation hardenable aluminum alloys. However, based on the low formability, the application for complex stamping parts is challenging. Therefore, at the Institute of Manufacturing Technology, an innovative technology to enhance the forming limit of these lightweight materials was invented. The key idea of the so-called Tailor Heat Treated Blanks (THTB) is optimization of the mechanical properties by local heat treatment before the forming operation. An accurate description of material properties is crucial to predict the forming behavior of tailor heat treated blanks by simulation. Therefore, within in this research project, a holistic approach for the design of the THTB process in dependency of the main influencing parameters is presented and discussed in detail. The capability of the approach for the process development of complex forming operations is demonstrated by a comparison of local blank thickness of a tailgate with the corresponding results from simulation.