Ensemble transfer learning for refining stability predictions in milling using experimental stability states

Postel, Martin; Bugdayci, Bircan; Wegener, Konrad

doi:10.1007/s00170-020-05322-w

Cited by 49 publications

(18 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The main limit of this application was the availability of data when the system changed the conditions. For this reason, Postel et al [19] proposed a new approach based on Deep Neural Networks and transfer learning, since DNN models are pretrained with simulated data from analytical stability models. The aim was to reduce the differences between the real measurements and the model output due to the cutting forces and the tooltip dynamics.…”

Section: Chattermentioning

confidence: 99%

“…Typical choices in machining are the measurements of the process forces [12,13], accelerations [14,15], vibrations or acoustic emission sensors [16,17] (2-3). Furthermore, the availability of the inner sensors or process parameters allow simple and reliable applications [18,19], including all the data available during the production. The use of new external sensors may be evaluated in the details, since it may increase the time and cost of the study and not imply better results in terms of accuracy for the ML application.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Recent Advances on Machine Learning Applications in Machining Processes

2021

View full text Add to dashboard Cite

This study aims to present an overall review of the recent research status regarding Machine Learning (ML) applications in machining processes. In the current industrial systems, processes require the capacity to adapt to manufacturing conditions continuously, guaranteeing high performance- in terms of production quality and equipment availability. Artificial Intelligence (AI) offers new opportunities to develop and integrate innovative solutions in conventional machine tools to reduce undesirable effects during operational activities. In particular, the significant increase of the computational capacity may permit the application of complex algorithms to big data volumes in a short time, expanding the potentialities of ML techniques. ML applications are present in several contexts of machining processes, from roughness quality prediction to tool condition monitoring. This review focuses on recent applications and implications, classifying the main problems that may be solved using ML related to the machining quality, energy consumption and conditional monitoring. Finally, a discussion on the advantages and limits of ML algorithms is summarized for future investigations.

show abstract

Section: Chattermentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Recent Advances on Machine Learning Applications in Machining Processes

2021

View full text Add to dashboard Cite

show abstract

“…In the third example, a new hybrid approach for the refinement of stability limits in milling operations is presented [45]. While Deep Neural Networks (DNN) have been used in previous approaches for chatter prediction in milling and turning [42,46], the methods required a very large amount of data samples for training.…”

Section: Ensemble Deep Transfer Learningmentioning

confidence: 99%

“…Table 2. Cutting cases and number of cuts (training samples) that were included in the fine-tuning [45] 5. THERMALLY SELF-EQUILIBRATING MACHINES…”

Section: Ensemble Deep Transfer Learningmentioning

confidence: 99%

Operator Integrated – Concept for Manufacturing Intelligence

Wegener¹,

Weikert²,

Mayr³

et al. 2021

Journal of Machine Engineering

View full text Add to dashboard Cite

Increasing autonomy and sustainability are major goals in manufacturing. Main technological trends provide enablers for achieving these goals and need to be implemented and combined in manufacturing machinery in a suitable manner. The paper exposes a vision of modern manufacturing machines, where the complexity of manufacturing processes is handled within the manufacturing machine and a simplistic front end is presented to the operator, which means that major elements of operators' tasks are fulfilled by the intelligence of the machine. Research vectors paving the ground for this concept from different points of view are then discussed. Research is presented on intelligent grinding, intelligent recognition and suppression of chatter, adaptive thermal and motion error compensation exploting also self-learning abilities. It is necessary to point out, that not only intelligent mastering of process and machine becomes more and more important but communications among machine tools enabling process chain overarching intelligent approaches and creating intelligent factories.

show abstract

“…All these approaches model a setup with a single combination of one machine and one tool. Postel et al propose a hybrid approach for stability prediction relying on ensemble transfer learning, showing potential for deployment to a broader range of machines and tools [15]. Denkena et al propose a process planning approach that relies on machine learning models to predict surface roughness in turning operations [16].…”

Section: Experimental Identification and Data-driven Approachesmentioning

confidence: 99%

Concept for Predicting Vibrations in Machine Tools Using Machine Learning

Barton

Fleischer²

2020

Lecture Notes in Production Engineering

View full text Add to dashboard Cite

Vibrations have a significant influence on quality and costs in metal cutting processes. Existing methods for predicting vibrations in machine tools enable an informed choice of process settings, however they rely on costly equipment and specialised staff. Therefore, this contribution proposes to reduce the modelling effort required by using machine learning based on data gathered during production. The approach relies on two sub-models, representing the machine structure and machining process respectively. A method is proposed for initialising and updating the models in production.

show abstract

Ensemble transfer learning for refining stability predictions in milling using experimental stability states

Cited by 49 publications

References 31 publications

Recent Advances on Machine Learning Applications in Machining Processes

Recent Advances on Machine Learning Applications in Machining Processes

Operator Integrated – Concept for Manufacturing Intelligence

Concept for Predicting Vibrations in Machine Tools Using Machine Learning

Contact Info

Product

Resources

About