Exploitation of force displacement curves in blanking—feature engineering beyond defect detection

Abstract

With the current tendency of mass production towards customer-oriented serial production, blanking processes are facing new challenges. They require an increase in knowledge about faulty process conditions and their influence on the quality of a component as well as an instruction for a target-oriented adaptation of the process. The aim of this study is therefore to identify property deviations based on force-displacement curves and to establish correlations between the quality of the component and features of force-displacement curves. For this purpose, parameter variations are carried out on a high-speed press and features are extracted from these measured time series. Afterwards, the correlation between varying process parameters and features is carried out to obtain a conclusion about the condition of the component. The results of these studies for a regression analysis form the basis for a decision support system to identify deviations of the component as well as faulty process conditions. The paper shows that a reliable correlation between the quality of the component and force-displacement curves is possibly based on the feature engineering approach even under industrial boundary conditions. This also applies to the simultaneous modification and variations within a limited range of several process parameters.

Smart sheet metal forming: importance of data acquisition, preprocessing and transformation on the performance of a multiclass support vector machine for predicting wear states during blanking

“…In this work we focus on the rounding of the cutting edge radii by abrasive wear. Hambli, Klingenberg and Singh as well as Kubik et al showed in their work that exactly this abrasive wear is the most common cause of wear in blanking and has a significant influence on the quality of the component (Hambli, 2001;Klingenberg & Singh, 2004;Kubik et al 2021).…”

“…According to Li, features can be extracted either from the time domain, the frequency domain or the time-frequency domain (Wang & Gao, 2006 show in their studies that engineering feature from the time domain represent effective parameters for describing process conditions during blanking (see Fig. 8) (Hoppe et al 2019;Kubik et al 2021). Therefore, the force signal is initially divided into three phases and characteristic points which define the start and end points as well as extrema during each phase are identified.…”

Comparative Life Cycle Assessment of Safety Shoes Toe Caps Manufacturing Processes

“…Considering the maximum force, the most suitable deep drawing process was chosen on the Ecoinvent database (650 kN deep drawing process). Blanking maximum force was calculated as follows [39]:…”

Optical inline monitoring of the burnish surface in the punching process

“…acceleration [18], force [19], acoustic emission [20]). In addition, different approaches for expert systems [21], feature engineering approaches [5,11,12,22] or by artificial neural networks [23,24] were made to predict the process quality. To our best knowledge, the current state-of-the-art of inline measurement systems for quality monitoring of the cutting surface parameters is only established via the correlation with indirect measured parameters or engineered features.…”

“…Fig.2Selection of process parameters that are most likely to influence the cutting surface parameters[22,25] …”