Convolutional neural network–based classification for improving the surface quality of metal additive manufactured components

Abhilash, P. M.; Ahmed, Afzaal

doi:10.1007/s00170-023-11388-z

Cited by 11 publications

(3 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ensemble method of programming techniques aided by AI procedures is a tool that works on many levels (Dawod and Hanna, 2019;Abhilash and Ahmed, 2023). In this research, GH helped with the interoperability of the process, connecting Microsoft Excel, ArchiCAD, and Rhinoceros, in a digital production script to optimize exhaustive design tasks that become complex when combined in real-life situations, mostly due to the quantity of data to process.…”

Section: Discussionmentioning

confidence: 99%

Evolutive Dataset for Social Housing Design Projects through Artificial Intelligence: From pixel to BIM through deep learning

Lacroix,

Güzelci,

Sousa

2023

eCAADe Proceedings

View full text Add to dashboard Cite

Establishing an evolutive dataset for architectural rationalization of social housing is technically achievable through artificial intelligence based on deep learning (DL).However, concerning the sensitive quality of social housing, the application of such technology needs to preserve the human factor and relate ethically to architectural design. A reference on this subject is historic Portuguese research from the 1960s and the 1970s. By then, pioneering research at the National Laboratory of Civil Engineering (LNEC), based in Lisbon, explored early computing methods to aid the design process by considering deontological concerns. The authors studied these works to refactor those goals and concerns of technological application and sociological interaction with current digital technologies. When digitizing their processes of creating architectural design instruments for social housing a problem emerged with parsing a dataset of floor plans and using it to generate building information models. Thus, a DL process was explored to achieve an evolutive dataset in the most automated way at the architectural level. The paper presents the implementation of a DL process that recognizes floor plans of social housing and consequently enables the development of an instrument for direct architectural rationalization.

show abstract

Section: Discussionmentioning

confidence: 99%

Evolutive Dataset for Social Housing Design Projects through Artificial Intelligence: From pixel to BIM through deep learning

Lacroix,

Güzelci,

Sousa

2023

eCAADe Proceedings

View full text Add to dashboard Cite

show abstract

“…The number of input layer neurons is seven, the number of neurons in the output layer is four corresponding to targets followed. To avoid overfitting issue 3 , 19 , the architecture of ANN to use has been simplified to one hidden layer in the goal to increase its ability for generalization 20 mainly because of the use of limited amount of data. The choice of the number of neurons in this layer is based on a practice rule that consists to retain a value less than twice the number of input variables 12 .…”

Section: Optimization Methods and Experimental Setupmentioning

confidence: 99%

A hybrid optimization approach for intelligent manufacturing in plastic injection molding by using artificial neural network and genetic algorithm

EL Ghadoui,

Mouchtachi,

Majdoul

2023

Sci Rep

View full text Add to dashboard Cite

This study presents a novel hybrid optimization approach for intelligent manufacturing in plastic injection molding (PIM). It focuses on globally optimizing process parameters to ensure high-quality products while reducing cycle time, material waste, and energy consumption. The method combines a backpropagation neural network (BPNN) with a genetic algorithm (GA) and employs a multi-objective optimization model based on design of experiments (DoE). A BP artificial neural network captures the relationship between optimization goals and process parameters. Leveraging the genetic algorithm, it effectively optimizes process parameters for achieving global optimization goals. The case study involves a polypropylene product, considering dimensional deviation, weight, cycle time, and energy consumption during the PIM cycle. Design variables include melt temperature, injection velocity, injection pressure, commutation position, holding pressure, holding time, and cooling time. The results demonstrate that this approach efficiently adjusts process parameters to meet quality standards, significantly reducing raw material consumption (2%), cycle time (12%), and energy consumption (16%). This offers substantial benefits for companies in highly competitive markets demanding swift adoption of smart production methods.

show abstract

“…In a recent study [ 153 ], a deep learning CNN model was utilized to predict the surface roughness of additively manufactured components. The study proposed a combined approach of CNN classification and electrical discharge-assisted post-processing to enhance the surface quality of these components.…”

Section: Ai-based Surface Roughness Prediction Methods For Additively...mentioning

confidence: 99%

Application of Artificial Intelligence for Surface Roughness Prediction of Additively Manufactured Components

Batu,

Lemu,

Shimels

2023

Materials

View full text Add to dashboard Cite

Additive manufacturing has gained significant popularity from a manufacturing perspective due to its potential for improving production efficiency. However, ensuring consistent product quality within predetermined equipment, cost, and time constraints remains a persistent challenge. Surface roughness, a crucial quality parameter, presents difficulties in meeting the required standards, posing significant challenges in industries such as automotive, aerospace, medical devices, energy, optics, and electronics manufacturing, where surface quality directly impacts performance and functionality. As a result, researchers have given great attention to improving the quality of manufactured parts, particularly by predicting surface roughness using different parameters related to the manufactured parts. Artificial intelligence (AI) is one of the methods used by researchers to predict the surface quality of additively fabricated parts. Numerous research studies have developed models utilizing AI methods, including recent deep learning and machine learning approaches, which are effective in cost reduction and saving time, and are emerging as a promising technique. This paper presents the recent advancements in machine learning and AI deep learning techniques employed by researchers. Additionally, the paper discusses the limitations, challenges, and future directions for applying AI in surface roughness prediction for additively manufactured components. Through this review paper, it becomes evident that integrating AI methodologies holds great potential to improve the productivity and competitiveness of the additive manufacturing process. This integration minimizes the need for re-processing machined components and ensures compliance with technical specifications. By leveraging AI, the industry can enhance efficiency and overcome the challenges associated with achieving consistent product quality in additive manufacturing.

show abstract

Convolutional neural network–based classification for improving the surface quality of metal additive manufactured components

Cited by 11 publications

References 44 publications

Evolutive Dataset for Social Housing Design Projects through Artificial Intelligence: From pixel to BIM through deep learning

Evolutive Dataset for Social Housing Design Projects through Artificial Intelligence: From pixel to BIM through deep learning

A hybrid optimization approach for intelligent manufacturing in plastic injection molding by using artificial neural network and genetic algorithm

Application of Artificial Intelligence for Surface Roughness Prediction of Additively Manufactured Components

Contact Info

Product

Resources

About