Digitalized automated welding systems for weld quality predictions and reliability

Gyasi, Emmanuel Afrane; Kah, Paul; Penttilä, Sakari; Ratava, Juho; Handroos, Heikki; Lin, Sanbao

doi:10.1016/j.promfg.2020.01.018

Cited by 9 publications

(7 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We believe that the breadth of the welding fault prediction problem can stimulate the development of new techniques in Machine Learning (ML). Recently, data-driven solutions for the welding domain have made considerable progress ranging from the weld nugget quality prediction 3 , welds diameter prediction 4 , process optimization 5 and process control 6 . However, there is little existing research that focuses on the fault prediction of RSW guns, mostly because it is very expensive and time-consuming to collect defective welding data on the production line.…”

Section: Background and Summarymentioning

confidence: 99%

Benchmark for welding gun fault prediction with multivariate time series data

Wang,

Zhang,

Wang

2024

Sci Data

View full text Add to dashboard Cite

In the automotive industry, machinery failures of the resistance spot welding (RSW) guns would interrupt the manufacturing lines and cause unplanned downtime, potentially resulting in a significant loss of production and reliability. Predicting the machinery failures of the RSW gun can provide more scientific strategies for predictive maintenance and decision-making. However, fault prediction of RSW guns has become increasingly challenging due to their complex behavior and data variability. In this paper, we created a benchmark dataset and proposed welding gun fault prediction benchmarks to aid in the development of machine learning approaches toward welding gun fault prediction. The dataset was collected at the Body-Shop (BS) of BMW Brilliance Automotive Ltd. from different components of hundreds of RSW guns to capture the patterns and trends before welding errors with historical data. Then we provide state-of-the-art machine learning (ML) benchmarks on time series forecasting methods in a welding gun fault prediction use case. This study will provide insights for time series forecasting while enabling ML researchers to contribute towards the fault prediction of the RSW guns.

show abstract

Section: Background and Summarymentioning

confidence: 99%

Benchmark for welding gun fault prediction with multivariate time series data

Wang,

Zhang,

Wang

2024

Sci Data

View full text Add to dashboard Cite

show abstract

“…The weld bead geometry is characterized by convexity index, depth of penetration (bead penetration), bead height, bead width, and reinforcement area [20,36,38]. To obtain the desired quality characteristics, process parameters, such as welding speeds, current, wire feed speed, contact tip to workpiece distance, and voltage, are set on the welding equipment.…”

Section: Weld Bead Geometrymentioning

confidence: 99%

“…The combination of artificial neural network (ANN) decision-making software and machine vision system leads to the development of an adaptive (AI)-based GMAW parameter control system [37]. Gyasi et al [38] developed an adaptive intelligent system using infrared thermography (IRT)-based device and AI system.…”

Section: Integral Sliding Mode Controller (Smc)mentioning

confidence: 99%

Influence of Process Parameters in Gas-Metal Arc Welding (GMAW) of Carbon Steels

Tukahirwa,

Wandera

2023

Welding - Materials, Fabrication Processes, and Industry 5.0

View full text Add to dashboard Cite

Gas-metal arc welding (GMAW) is a widely used fusion joining process in industry known for its ability to create high-quality welds. However, the complex and nonlinear nature of GMAW process variables often leads to weld defects in certain situations. Various dynamic factors affect the GMAW process, including power source dynamics, metal transfer dynamics, arc and droplet dynamics, and weld pool dynamics, making precise control challenging. While achieving completely defect-free welds can be difficult, some welds may still meet industry standards for acceptable performance in specific applications. Properly controlling process parameters plays a crucial role in reducing defects and enhancing overall weld quality. Advanced sensor technologies have emerged as valuable tools for monitoring and adjusting process parameters to achieve desired weld characteristics. This chapter provides a review of research on how GMAW process parameters influence the welding of carbon steels, emphasizing the importance of process control and the role of sensor technologies in improving weld quality.

show abstract

“…Teknologi kedua yang dipresentasikan kepada direktur perusahaan adalah solusi pengelasan otomatis. Karena pekerjaan produksi utama perusahaan adalah pengelasan, maka penting untuk mempertimbangkan mengotomatisasi proses pengelasan untuk memastikan kualitas, produktivitas, integritas las dan untuk mengurangi biaya dalam manufaktur (Gyasi, 2019). Selain itu, terbukti dengan adanya pandemic, sangat mengandalkan tenaga kerja adalah langkah yang berisiko bagi bisnis.…”

Section: Pemilihan Kriteriaunclassified

Pemilihan Teknologi Baru Menuju Industri 4.0 Pada Perusahaan Manufaktur Menggunakan Analytical Hierarchy Process (AHP)

Solihin

Belmoro²,

Redi³

2022

JAH

View full text Add to dashboard Cite

Adopsi teknologi baru sebagai bagian dari Industri 4.0 memberikan peluang bagi bisnis terlepas dari sekala dan ukurannya. UKM menghadapi tantangan dalam mengadopsi I4.0 meskipun tidak mengurangi manfaat yang akan dapat oleh perusahaan-perusahaan ini, yaitu lambatnya proses pengambilan keputusan untuk memperkenalkan teknologi canggih ke bisnis. Untuk membantu bisnis dalam menghasilkan keputusan tentang teknologi mana yang harus diinvestasikan, AHP akan digunakan dalam penelitian ini. Kriteria yang berbeda berdasarkan data yang dikumpulkan dari UKM akan dipertimbangkan dan 3 teknologi akan disajikan kepada pembuat keputusan utama perusahaan. Melalui perangkat lunak Super Decisions, setiap kriteria ditugaskan dengan bobot yang berbeda dengan cara melakukan wawancara dengan pembuat keputusan. Melalui hal ini, kesimpulan dari penelitian ini adalah keputusan yang tidak memihak dan objektif yang dapat membantu perusahaan dalam adopsi Industri 4.0.

show abstract

Digitalized automated welding systems for weld quality predictions and reliability

Cited by 9 publications

References 2 publications

Benchmark for welding gun fault prediction with multivariate time series data

Benchmark for welding gun fault prediction with multivariate time series data

Influence of Process Parameters in Gas-Metal Arc Welding (GMAW) of Carbon Steels

Pemilihan Teknologi Baru Menuju Industri 4.0 Pada Perusahaan Manufaktur Menggunakan Analytical Hierarchy Process (AHP)

Contact Info

Product

Resources

About