The design and feasibility test of a mobile semi-auto scraping system

Yang, Lin; Yeh, Chun-Yaun; Shiu, Shiau-Cheng; Lan, Pei-Shiuang; Lin, Shih-Chieh

doi:10.1007/s00170-018-3030-6

Cited by 4 publications

(4 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hence, the quality of the scraping workpieces is crucial to the machine tool that directly affects the machining accuracy and the service life of the machine tool [ 3 ]. Two main parameters for evaluating scraping surfaces, which are the percentage of points (POP) and peak point per square inch (PPI), are used in this research and in [ 4 , 5 ]. The primary evaluation method of these POP and PPI parameters involves visually checking the areas and the distribution of HOP, as shown in Figure 1 c. However, the quality evaluation of the scraping workpiece is performed manually by the scraping worker’s subjective judgment.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Cascaded Segmentation U-Net for Quality Evaluation of Scraping Workpiece

Yin

Lien

2023

Sensors

View full text Add to dashboard Cite

In the terms of industry, the hand-scraping method is a key technology for achieving high precision in machine tools, and the quality of scraping workpieces directly affects the accuracy and service life of the machine tool. However, most of the quality evaluation of the scraping workpieces is carried out by the scraping worker’s subjective judgment, which results in differences in the quality of the scraping workpieces and is time-consuming. Hence, in this research, an edge-cloud computing system was developed to obtain the relevant parameters, which are the percentage of point (POP) and the peak point per square inch (PPI), for evaluating the quality of scraping workpieces. On the cloud computing server-side, a novel network called cascaded segmentation U-Net is proposed to high-quality segment the height of points (HOP) (around 40 μm height) in favor of small datasets training and then carries out a post-processing algorithm that automatically calculates POP and PPI. This research emphasizes the architecture of the network itself instead. The design of the components of our network is based on the basic idea of identity function, which not only solves the problem of the misjudgment of the oil ditch and the residual pigment but also allows the network to be end-to-end trained effectively. At the head of the network, a cascaded multi-stage pixel-wise classification is designed for obtaining more accurate HOP borders. Furthermore, the “Cross-dimension Compression” stage is used to fuse high-dimensional semantic feature maps across the depth of the feature maps into low-dimensional feature maps, producing decipherable content for final pixel-wise classification. Our system can achieve an error rate of 3.7% and 0.9 points for POP and PPI. The novel network achieves an Intersection over Union (IoU) of 90.2%.

show abstract

Section: Introductionmentioning

confidence: 99%

“…In previous experiments, according to the method proposed by [ 4 , 5 ], the HSV color domain and Otsu algorithm [ 6 ] were attempted to segment the HOP. However, the previous methods are not appropriate for this research.…”

Section: Introductionmentioning

confidence: 99%

Cascaded Segmentation U-Net for Quality Evaluation of Scraping Workpiece

Yin

Lien

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…This method unveils areas of high points of the workpiece and thus areas that have to be further worked. This concept was implemented for automation by several research groups and transferred into a task of an automated camera-based system [10,11]. An alternative approach was taken by Hsieh et al [12] who used a scanning triangulation sensor to obtain a model of the workpiece surface.…”

Section: Introductionmentioning

confidence: 99%

“…Other important components of automated scraping are the positioning and the actuation of the tool. Lin et al [11] developed a gantry positioning system that also serves for actuating the tool. Two scraping approaches ("chess board pattern" and "dense pattern") were imitated by the system and the results were characterized.…”

Section: Introductionmentioning

confidence: 99%

Macroanalysis of Hand Scraping

Oßwald

Gissel

Lochmahr³

2020

JMMP

View full text Add to dashboard Cite

Hand scraping is a manual metalworking method that is still used in many industries to obtain good planarity, low friction and good gliding properties of metal and plastic surfaces. However, it is characterized by low productivity and requires skilled and well-trained workers. This macroanalysis focuses on the strategy and procedure of the workers during the scraping operation. Forces and tool positions were acquired simultaneously and the resulting surfaces were measured after each scraping pass. Results show that in most instances differences between individual workers’ scraping styles are more significant than between consecutive scraping passes. This research was conducted in order to gather sufficient insight into the hand scraping method to take steps towards its automation.

show abstract