Towards Data Driven Process Control in Manufacturing Car Body Parts

Stein, Bas van; Leeuwen, Matthijs van; Wang, Hao; Purr, S.; Kreissl, Sebastian; Meinhardt, Josef; Bäck, Thomas

doi:10.1109/csci.2016.0093

Cited by 11 publications

(12 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On one hand, data-driven approaches benefit by requiring a minimal understanding of the inherent process mechanisms [8] while, on the other hand, suffer from dimensionality issues, which often requires a huge amount of data for reliable performance and do not contain features for full fault diagnosis and isolability [7]. On the other hand, model-based approaches, albeit capture, provide a clear cause-effect relationship between product/process parameters [11].…”

Section: Discussionmentioning

confidence: 99%

“…On the other hand, model-based approaches, albeit capture, provide a clear cause-effect relationship between product/process parameters [11]. They fail to take into account the external disturbances and noises prevalent in real production processes [8] while also require rigorous experimentation/effort to derive the process models [6]. It is believed that the combination of operation data that capture fluctuations present in reality with model-based approaches that comprise of extensive knowledge regarding product/process behaviour could benefit the monitoring and control approaches in the context of complex manufacturing processes.…”

Section: Discussionmentioning

confidence: 99%

“…More recently, with concepts like zero-defect manufacturing gaining importance, the focus has shifted toward fault diagnosis and troubleshooting activities that consume a considerably larger portion of the process downtime [1,7] compared to fault detection activities. In this context, several data-driven [7][8][9][10][11], model-based [12][13][14], and statistical [15] approaches have been proposed to support Processes 2020, 8, 89 2 of 11 the identification of the underlying root cause of a fault. However, most of these approaches lack features necessary to completely diagnose and isolate a fault [16].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Hybrid Data-Based and Model-Based Approach to Process Monitoring and Control in Sheet Metal Forming

et al. 2020

View full text Add to dashboard Cite

The ability to predict and control the outcome of the sheet metal forming process demands holistic knowledge of the product/process parameter influences and their contribution in shaping the output product quality. Recent improvements in the ability to harvest in-line production data and the increased capability to understand complex process behaviour through computer simulations open up the possibility for new approaches to monitor and control production process performance and output product quality. This research presents an overview of the common process monitoring and control approaches while highlighting their limitations in handling the dynamics of the sheet metal forming process. The current paper envisions the need for a collaborative monitoring and control system for enhancing production process performance. Such a system must incorporate comprehensive knowledge regarding process behaviour and parameter influences in addition to the current-system-state derived using in-line production data to function effectively. Accordingly, a framework for monitoring and control within automotive sheet metal forming is proposed. The framework addresses the current limitations through the use of real-time production data and reduced process models. Lastly, the significance of the presented framework in transitioning to the digital manufacturing paradigm is reflected upon.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Hybrid Data-Based and Model-Based Approach to Process Monitoring and Control in Sheet Metal Forming

et al. 2020

View full text Add to dashboard Cite

show abstract

“…According to these publications, the amount of lubricant affects the friction and thus plays an important role in the deep drawing process of sheet metals. 8,9 Using scanning mirrors in combination with laser induced fluorescence allows for the first time to monitor the spatial distribution of lubricant on 100% of the metal sheets surface with strip speeds of several meters per second. 7 For typical lab applications of fluorescence spectroscopy, well-defined smooth surfaces, such as microscope slides or glass cuvettes, are used as substrate material under the fluorescent layer.…”

Section: Introductionmentioning

confidence: 99%

Quantitative Measurement of Fluorescent Layers with Respect to Spatial Thickness Variations and Substrate Properties

2020

View full text Add to dashboard Cite

Imaging fluorescence spectroscopy proves to be a fast and sensitive method for measuring the thickness of thin coatings in the manufacturing industry. This encouraged us to systematically study, theoretically and experimentally, parameters that influence the fluorescence of thin layers. We analyzed the fluorescence signal as a function of the scattering and reflectance properties of the sample substrate. In addition, we investigated effects of the layer properties on fluorescence emission. A ray-tracing software is used to describe the influence of these parameters on the fluorescence emission of thin layers. Experiments using a custom-made system for imaging fluorescence analysis verify the simulations. This work shows a factor five variation of fluorescence intensity as a function of the reflectance of the sample substrate. Simulations show variations by a factor of up to eight for samples with different surface roughness. Results on tilted samples indicate a significant increase of the detected fluorescence signal, for fluorescent droplets on reflective substrates, if illuminated and coaxially observed at angles greater than 25°. These findings are of utmost relevance for all applications which utilize the fluorescence emission to quantify thin layers. These applications range from in-line lubricant monitoring in press plants to monitoring of functional coatings in medical technology and the detection of filmic contaminations.

show abstract

“…More recently, with concepts like zeroဨdefect manufacturing gaining importance, the focus has shifted towards fault diagnosis and troubleshooting activities that consume a considerably larger portion of the process downtime [1,2] compared to fault detection activities. In this context, several dataဨdriven [1,[3][4][5][6], modelဨbased [7][8][9] and statistical [10] approaches have been proposed to support the identification of the underlying root cause of a fault. However, most of these approaches lack features necessary to completely diagnose and isolate a fault [11].…”

Section: Introductionmentioning

confidence: 99%

Towards Improving Process Control in Sheet Metal Forming: A Hybrid Data- and Model-Based Approach

Tatipala

Wall

Larsson

et al. 2020

Advances in Transdisciplinary Engineering

View full text Add to dashboard Cite

Ability to predict and control involved parameters and hence the outcome of sheet metal forming processes demand holistic knowledge of the product/-process parameter influences and their contribution in shaping the output product quality. Recent improvements in the ability to harvest inline production data and the capability to understand complex process behaviour through computer simulations opens up the possibility for new monitoring and control approaches for improving production process performance and output product quality. Current work presents a framework for monitoring and control of sheet metal forming processes which incorporates a hybrid dataï£¡and modelï£¡based approach. An initial attempt to evaluate the proposed frameworks’ ability to support output product quality and process performance enhancements is made by implementing the proposed approach via an in-house built wire-bending machine prototype. Initial experiments conducted using the built prototype indicate that the proposed framework has the potential to support such enhancements and further work is needed to validate the overall framework.

show abstract

Towards Data Driven Process Control in Manufacturing Car Body Parts

Cited by 11 publications

References 18 publications

A Hybrid Data-Based and Model-Based Approach to Process Monitoring and Control in Sheet Metal Forming

A Hybrid Data-Based and Model-Based Approach to Process Monitoring and Control in Sheet Metal Forming

Quantitative Measurement of Fluorescent Layers with Respect to Spatial Thickness Variations and Substrate Properties

Towards Improving Process Control in Sheet Metal Forming: A Hybrid Data- and Model-Based Approach

Contact Info

Product

Resources

About