Design framework for model-based self-optimizing manufacturing systems

Thombansen, Ulrich; Buchholz, Guido; Frank, Daniel; Heinisch, Julian; Kemper, Maximilian; Pullen, Thomas; Reimer, Viktor; Rotshteyn, Grigory; Schwenzer, Max; Stemmler, Sebastian; Abel, Dirk; Gries, Thomas; Hopmann, Christian; Klocke, Fritz; Poprawe, R.; Reisgen, Uwe; Schmitt, Robert

doi:10.1007/s00170-018-1951-8

Cited by 21 publications

(5 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another work with a similar contribution is that of [14], as it aims to intelligently and autonomously control the main characteristics of product and process quality. This fact was identified as a necessity in the case study of this work.…”

Section: Literature Review and Classificationmentioning

confidence: 99%

Intelligent Product Quality Failure Prediction System in Smart Factories Based on Machine Learning Techniques

Rocha

Szejka

Canciglieri

2021

Advances in Transdisciplinary Engineering

View full text Add to dashboard Cite

Industry 4.0 has brought innovative principles to the entire world, especially for the manufacturing industry. The adaptation to a technological era showed limitations in the current processes, of which we can highlight the divergence between software and machinery technologies, cloud data processing, difficulty for the information to circulate within a manufacturing environment, so that it flows clearly and objectively, without ambiguity. These limitations end up generating errors between operations in the manufacturing process resulting in costs, customer dissatisfaction, low product quality, and reduced competitiveness. Thus, problems related to the semantic web, semantic interoperability, horizontal and vertical integration are responsible for such limitations in manufacturing processes. To resolve such restrictions and improve the final quality of the product, it is possible to apply Machine Learning techniques. Through the use of ensemble models of machine learning algorithm techniques, techniques with specific characteristics can be grouped, complementing each other, thus providing better prediction results during the manufacture of products, reducing costs, increasing the reliability and quality of the final product. In this way, it is expected to improve the final quality of the product and minimize the impacts that detract from the performance indicators, such as scrap, cost, rework, labor. This research will contribute scientifically to the creation of a system, which can be applied in different manufacturing production processes.

show abstract

Section: Literature Review and Classificationmentioning

confidence: 99%

Intelligent Product Quality Failure Prediction System in Smart Factories Based on Machine Learning Techniques

Rocha

Szejka

Canciglieri

2021

Advances in Transdisciplinary Engineering

View full text Add to dashboard Cite

show abstract

“…The new population is combined with old population and the combined population of size 2N is achieved. Further the non-dominated sorting is performed [22], which clubs the solutions of combined population using some ranking method (Fi where i=1, 2,…, n). In the next iteration the population is acquired using this ranking method (e.g.…”

Section: Regression Analysismentioning

confidence: 99%

NSGA III for CNC End Milling Process Optimization

Ghosh

Martinsen

2020

Communications in Computer and Information Science

View full text Add to dashboard Cite

Computer Numerical Controlled (CNC) end milling processes require very complex and expensive experimentations or simulations to measure the overall performance due to the involvement of many process parameters. Such problems are computationally expensive, which could be efficiently solved using surrogate driven evolutionary optimization algorithms. An attempt is made in this paper to use such technique for the end milling process optimization of aluminium block and solved using Non-dominated Sorting Genetic Algorithm (NSGA III). The material removal rate, and surface roughness are considered as the crucial performance criteria. It is shown that the regression driven NSGA III is efficient and effective while obtaining improved process responses for the end milling.

show abstract

“…Surrogate-based optimization tries to search for the optimal process parameters based on an established surrogate model, and it requires an appropriate mechanism to do so. Genetic algorithms [11] and model-based self-optimizations [12] have been used to iteratively improve candidate process parameters.…”

Section: Introductionmentioning

confidence: 99%

The Steelmaking Process Parameter Optimization with a Surrogate Model Based on Convolutional Neural Networks and the Firefly Algorithm

et al. 2021

View full text Add to dashboard Cite

High-strength low-alloy steels (HSLAs) are widely used in the structural body components of many domestic motor vehicles owing to their better mechanical properties and greater resistance. The real production process of HSLA steelmaking can be regarded as a model that builds on the relationship between process parameters and product quality attributes. A surrogate modeling method is used, and the resulting production process model can be applied to predict the optimal manufacturing process parameters. We used different methods in this paper, including linear regression, random forests, support vector regression, multilayer perception, and a simplified VGG model to build such a surrogate model. We then applied three bio-inspired search algorithms, namely particle swarm optimization, the artificial bee colony algorithm, and the firefly algorithm, to search for the optimal controllable manufacturing process parameters. Through experiments on 9000 test samples used for building the surrogate model and 299 test samples for making the optimal process parameter selection, we found that the combination of a simplified VGG model and the firefly algorithm was the most successful at reaching a success rate of 100%—in other words, when the product quality attributes of all test samples satisfy the mechanical requirements of the end products.

show abstract

Design framework for model-based self-optimizing manufacturing systems

Cited by 21 publications

References 45 publications

Intelligent Product Quality Failure Prediction System in Smart Factories Based on Machine Learning Techniques

Intelligent Product Quality Failure Prediction System in Smart Factories Based on Machine Learning Techniques

NSGA III for CNC End Milling Process Optimization

The Steelmaking Process Parameter Optimization with a Surrogate Model Based on Convolutional Neural Networks and the Firefly Algorithm

Contact Info

Product

Resources

About