Systematic review on machine learning (ML) methods for manufacturing processes – Identifying artificial intelligence (AI) methods for field application

Fahle, Simon; Prinz, Christopher; Kuhlenkötter, Bernd

doi:10.1016/j.procir.2020.04.109

Cited by 139 publications

(47 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Salah satu teknologi yang popular saat ini yaitu artificial intelligence, di mana suatu peristiwa yang akan terjadi dapat di diagnosa atau diprediksi secara akurat (Agrawal et al, 2019). Menurut (Fahle et al, 2020), salah satu cabang dari artificial intelligence yang paling banyak digunakan adalah machine learning, yakni suatu metode yang dapat membuat komputer melakukan pembelajaran berdasarkan pengalamannya tanpa perlu melakukan suatu pemrograman secara eksplisit. Dalam penerapannya saat ini telah banyak digunakan tidak hanya dalam industri saja, namun kini sudah merambah dalam kehidupan sehari-hari seperti pencarian dalam internet, rekomendasi produk dalam market place, iklan di internet hingga diagnosis medis (Ramamurthy & Roy, 2018) (Alemdar et al, 2015).…”

Section: Pendahuluanunclassified

Implementation of machine learning to increase productivity in the manufacturing industry: a literature review.

Purmala¹

2021

View full text Add to dashboard Cite

Industry 4.0 is currently developing quite rapidly, one of the technologies that is currently very popular in the industry is artificial intelligence, where an event can be diagnosed and predicted more quickly and accurately. One of the branches of artificial intelligence that can do this is Machine Learning, and its application can now be found in daily activities. In the manufacturing industry, the application of Machine Learning is one of them is to increase productivity through the results of analysis and predictions given based on the experience gained. This study uses a systematic literature review method, in which several articles were collected from several journal databases such as Elsevier, IEE, Springer, Taylor & Francis and ACM, with the publication period of the articles from 2015 to 2020. A total of 100 articles were collected, then re-validated. suitability based on the main goals and objectives of the research. There were 36 articles that were validated and used as a reference for a more in-depth review and analysis of their boundaries, so that there was a gap for further research. In this literature review study, its application is very helpful in making decisions in improving the quality, efficiency, and performance of companies in the manufacturing industry. The most popular algorithms used in this study include random forest, support vector machine, neural network, linear regression, and k-nearest neighbor. Finally, in this study it was found that the application of Machine Learning in diagnosing or predicting an event is suggested by modeling more than one algorithm to find and determine which algorithm is the most accurate and suitable to be applied to the phenomenon that occurs.

show abstract

Section: Pendahuluanunclassified

Implementation of machine learning to increase productivity in the manufacturing industry: a literature review.

Purmala¹

2021

View full text Add to dashboard Cite

show abstract

“…The actual use of AI in smart factories is to solve problems that are difficult or not formulated in codes and can only be solved intuitively. As a subset of AI in production processes, ML methods are the topic of this paper [31].…”

Section: Artificial Intelligence In Manufacturingmentioning

confidence: 99%

Artificial Intelligence Application in Different Scenarios of the Networked Society 5.0 Environment

Peraković¹,

Periša²,

Cvitić³

et al. 2021

Zbornik Radova Trideset Devetog Simpozijuma O Novim Tehnologijama U Poštanskom I Telekomunikacionom Saobraćaju – Postel 2021

View full text Add to dashboard Cite

A technologically based society geared towards every human being represents a Society 5.0 environment whose goal is to upgrade society to improve daily human life. It can be achieved through the significant application of information and communication networks, technologies, services, and user equipment. Industry 4.0 is the basis for developing the Society 5.0 environment in which the harmonious coexistence of people and machines comes to the fore. Artificial intelligence is one of the critical technologies for the further growth and development of the Society 5.0 environment, whose ability is to convert collected networked stakeholder's data into values. The authors in this paper systematically review the literature to investigate the application of artificial intelligence technology within the Society 5.0 environment. This paper aims to present the possibilities and scenarios of using artificial intelligence in different areas of the Society 5.0 environment, such as the digital transport system, healthcare, and manufacturing.

show abstract

“…Abubakr et al [20] also highlighted the importance of artificial intelligence techniques to optimize the manufacturing process, improve components quality, and achieve more sustainable processes. In this trend, as reported by Fhale et al [21], many authors have implemented the backpropagation Artificial neural network (ANN) and other artificial intelligence methods to simulate many different manufacturing processes, including welding. Muthu Krishnan et al [22] used an ANN model to develop regression equations relating to response characteristics and process input parameters for friction stir welding.…”

Section: Introductionmentioning

confidence: 99%

Investigations on quality characteristics in gas tungsten arc welding process using artificial neural network integrated with genetic algorithm

Tomaz

Colaço

Sarfraz

et al. 2021

Int J Adv Manuf Technol

View full text Add to dashboard Cite

Gas tungsten arc welding (GTAW) technology is widely used in industry and has advantages, including high precision, excellent welding quality, and low equipment cost. However, the inclusion of a large number of process parameters hinders its application on a wider scale. Therefore, there is a need to implement the prediction and optimization models that effectively enhance the process performance of the GTAW process in different applications. In this study, a five-factor five-level central composite design (CCD) matrix was used to conduct GTAW experiments. AISI 1020 steel blank was used as a substrate; UTP AF Ledurit 60 and UTP AF Ledurit 68 were used as the materials of two tubular wires. Further, an artificial neural network (ANN) was used to simulate the GTAW process and then combined with a genetic algorithm (GA) to determine welding parameters that can provide an optimal weld. In welding experiments, five different welding current levels, welding speed, distance to the nozzle, angle of movement, and frequency of the wire feed pulses were used. Using GA, optimal welding parameters were determined: welding current = 222 A, welding speed = 25 cm/min, nozzle deflection distance = 8 mm, travel angle = 25°, wire feed pulse frequency = 8 Hz. The determination coefficient (R2) and RMSE value of all response parameters are satisfactory, and the R2 of all the data remained higher than 0.65.

show abstract

Systematic review on machine learning (ML) methods for manufacturing processes – Identifying artificial intelligence (AI) methods for field application

Cited by 139 publications

References 47 publications

Implementation of machine learning to increase productivity in the manufacturing industry: a literature review.

Implementation of machine learning to increase productivity in the manufacturing industry: a literature review.

Artificial Intelligence Application in Different Scenarios of the Networked Society 5.0 Environment

Investigations on quality characteristics in gas tungsten arc welding process using artificial neural network integrated with genetic algorithm

Contact Info

Product

Resources

About