Acoustic emission technique for online monitoring during cold forging of steel components: a promising approach for online crack detection in metal forming processes

Behrens, Bernd‐Arno; Santangelo, A.; Buse, Christian

doi:10.1007/s11740-013-0452-8

Cited by 19 publications

(8 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a result, efforts have been made to apply process monitoring to detect different conditions during the process. Behrens, Santangelo, and Buse (2013) determined AE (Acoustic Emission) signals could effectively indicate the formation of cracks during the cold forming of bevel gears. A study by Kim et al (2018) found that under-filling could be detected during forming by monitoring signals from piezo-bolt sensors.…”

Section: Introductionmentioning

confidence: 99%

Applications of deep learning for fault detection in industrial cold forging

Glaeser

Selvaraj

Lee

et al. 2021

International Journal of Production Research

View full text Add to dashboard Cite

The feasibility of using deep learning techniques in industrial cold forging for fault detection was investigated. In this work, vibration data were collected from an industrial setting to detect machine conditions resulting in defective products (faults). After collecting data from several commonly encountered faults, a Convolutional Neural Network classifier detected fault conditions with 99.02% accuracy and further classified each fault with 92.66% accuracy. A decision tree (DT) model was also used in an attempt to detect and classify faults using time domain features. The model was able to detect faults with 92.5% accuracy but was unable to classify them. In addition, DT feature importance analysis was performed to understand how various faults impacted the machine signal for future refinement of the proposed system. The results suggest that the proposed deep learning method has the potential to detect faults in cold forging, but future work is required to validate the method.

show abstract

Section: Introductionmentioning

confidence: 99%

Applications of deep learning for fault detection in industrial cold forging

Glaeser

Selvaraj

Lee

et al. 2021

International Journal of Production Research

View full text Add to dashboard Cite

show abstract

“…At low forming temperatures, excessive tensile stresses can lead to material failure in the form of transverse cracks close to the surface [11] or to early failure of the joining zone during forming [12].…”

Section: Intr Introduction and Moti Oduction And Motiv Vation Ationmentioning

confidence: 99%

Numerical investigations on the influence of the weld surface and die geometry on the resulting tensile stresses in the joining zone during an extrusion process

Behrens¹,

Duran²,

Uhe³

et al. 2021

Esaform 2021

View full text Add to dashboard Cite

Bulk metal components are often used in areas which are subjected to very high loads. For most technical components, a distinction between structural and functional areas can be made. These areas usually have very different loading profiles, sometimes with contradictory requirements. Nevertheless, nowadays almost only monomaterials are used for the production of bulk metal components. With increasing requirements towards more and more efficient products with lower weight, compact design and extended functionality, these materials are reaching their material-specific limits. A significant increase of product quality and economic efficiency can be expected exclusively with locally adapted properties by combining different materials within one component. In this regard, the focus of this contribution is the production of a hybrid pinion shaft made of the material combination steel (37CrS4) and aluminium (AW6082). The tool concept for extrusion of the hybrid preform, the simulation-based design of the forming process as well as the material characterisation are presented. With the help of the FE-simulation, different serially arranged semi-finished component geometries were investigated in order to minimise the occurring tensile stresses in the component during the extrusion process to prevent failure during forming.

show abstract

“…They also explored the effects of the machine noise and sensor position on the monitoring performance and analyzed the experimental results. Behrens et al (7) investigated the feasibility of employing the AE technique for the online monitoring of the cold forging of casehardening steel. The energy, impact, and amplitude distributions recorded through AE were assessed and compared with actual cracks and tool wear.…”

Section: Introductionmentioning

confidence: 99%

System for Real-time Measurement and Monitoring of Forging Force of Screw-forming Machine

Cheng¹

2021

Sensors and Materials

View full text Add to dashboard Cite

Screws are commonly used fasteners. In general, the term "fastener" refers to machine components comprising screws and bolts used to affix two or more components together. Screw production consists of three steps, namely, heading, threading, and coating. During the forming process, the mold used may be damaged as a result of defects in the metal wire or metal bar. In this study, we employed the CBF-43S screw-forming machine developed by Chun Zu Machinery Industry as the monitoring target and performed kinetic analysis on the slider-crank mechanism of the machine using the provided parameters. Subsequently, the forging force of the machine was measured by a force sensor and its real time changes were recorded. When an error value was identified, the machine was immediately shut down and the mold was inspected for damage. Through this method, the detrimental effect of damaged molds on the quality of screws and bolts can be prevented.

show abstract

Acoustic emission technique for online monitoring during cold forging of steel components: a promising approach for online crack detection in metal forming processes

Cited by 19 publications

References 4 publications

Applications of deep learning for fault detection in industrial cold forging

Applications of deep learning for fault detection in industrial cold forging

Numerical investigations on the influence of the weld surface and die geometry on the resulting tensile stresses in the joining zone during an extrusion process

System for Real-time Measurement and Monitoring of Forging Force of Screw-forming Machine

Contact Info

Product

Resources

About