Support Vector Fuzzy Adaptive Network in the Modeling of Material Removal Rate in Rotary Ultrasonic Machining

Shen, Judong; Pei, Zhi; Lee, E. S.

doi:10.1115/1.2951935

Cited by 9 publications

(5 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The accuracy of the model was demonstrated for magnesia stabilized zirconia. Shen et al [70] developed the model for material removal rate using support vector fuzzy adaptive network (SVFAN) in RUM. Results also compared with that obtained by using fuzzy adaptive network and it had also been showed that the combined approach is a more effective algorithm for the modeling.…”

Section: Rotary Ultrasonic Machiningmentioning

confidence: 99%

Ultrasonic Machining: A Review

Kataria¹,

Kumar²

2016

AMR

View full text Add to dashboard Cite

Ultrasonic machining is a contemporary manufacturing method usually employed for processing materials with higher hardness/brittleness such as quartz, semiconductor materials, ceramics etc. The machined surface produced by ultrasonic machining is found to be free from any surface defects (heat affected zone, cracks, recast layer, etc.) in contrast to the thermal based machining processes like; electric discharge machining, laser beam machining etc. In this article, a review has been reported on the fundamental principle of ultrasonic machining, effect of operating parameters on material removal rate, tool wear rate, surface roughness and hole quality. It also presents a brief review on micro-USM, rotary USM and hybrid methods with other processes.

show abstract

Section: Rotary Ultrasonic Machiningmentioning

confidence: 99%

Ultrasonic Machining: A Review

Kataria¹,

Kumar²

2016

AMR

View full text Add to dashboard Cite

show abstract

“…This is the first successful example to use fuzzy control to replace the expert operator. Some of the fuzzy aspects in manufacturing were studied using the proposed adaptive system shen, Pei & Lee, 2004;, Shen, Pei & Lee, 2008Jiao Pei et al, 2005Pai & Lee 1999;shen, et al, 2006;. Industrial welding operation is more art than science.…”

Section: Examples Of Application To Humanistic Systemsmentioning

confidence: 99%

Soft Computing and Learning Techniques in the Modeling of Humanistic Systems

Lee

2012

International Journal of Artificial Life Research

View full text Add to dashboard Cite

Although modern computer is the most revolutionary and most powerful tool developed in the twenty’s century, it is almost useless for the application of this tool to the not well defined humanistic systems such as politics, law, or even the many hour-to-hour small decisions people make routinely and daily. This is in spite of the fact that the human action of the cognitive band, which is of the order of seconds, is much slower than the speed of the modern computer. In this paper, the author shall first examine the basic differences between the scientific systems and the humanistic systems. Then based on these resulting differences, the author shall propose a neural-soft-computing combined approach, which is naturally suited for the vague and difficult to define humanistic systems. These combined systems are developed during the last approximately twenty years. Yet, it has not applied to the humanistic systems in a systematic and extensive manner. Some of the neural-soft-computing systems, also known as neural-evolutionary operational systems are the combined use of neural network, or support vector machine, with fuzzy system or fuzzy logic and evolutionary operational techniques such as genetic algorithm. Several of these systems are summarized and discussed as to why these systems seem more promising for the handling of humanistic systems. To illustrate the effectiveness of the proposed approaches, several initial applications in the literature are summarized.

show abstract

“…Shen et al applied Support Vector Fuzzy Adaptive Network as a parameter-free nonlinear regression technique to model material removal rate. The algorithm retains the advantages of fuzzy adaptive network and support vector machine, and it is a more effective modeling algorithm for complex manufacturing processes [14]. A material removal model for Inconel 718 robotic belt grinding based on acoustic sensing and machine learning is proposed [15].…”

Section: Introductionmentioning

confidence: 99%

A Material Removal State Prediction Method Based on Multi-Scale Attention Mechanism

Tang

Liu

et al. 2022

Volume 2: 42nd Computers and Information in Engineering Conference (CIE)

View full text Add to dashboard Cite

The exact removal of material in abrasive belt grinding determines the final machining quality of the workpiece. However, it is difficult to determine the removal state of materials in actual processing, which is affected by factors such as abrasive belt wear and processing errors. Therefore, a multi-scale attention convolutional neural network for material removal state prediction method is proposed based on the analysis of displacement data. First, the first-order difference and sliding-window expansion methods for displacement data are adopted, making it possible to use displacement data for deep learning, which is the premise of material removal state prediction. Then, the multi-scale convolutional neural network is Employed to extract important features of the displacement data. Due to the different importance of different features, Squeeze-and-Excitation Networks are used to independently assign the importance of features based on the loss function, so that the model pays more attention to those main features and ignores the secondary features, which can improve the convergence speed and prediction accuracy of the model. The K6 cross-validation of experiment results shows that this method can accurately predict the material removal state with an average prediction accuracy of 87.9%, which can be practically applied to the online prediction of the material removal state in industrial processing to further control the processing quality.

show abstract

Support Vector Fuzzy Adaptive Network in the Modeling of Material Removal Rate in Rotary Ultrasonic Machining

Cited by 9 publications

References 24 publications

Ultrasonic Machining: A Review

Ultrasonic Machining: A Review

Soft Computing and Learning Techniques in the Modeling of Humanistic Systems

A Material Removal State Prediction Method Based on Multi-Scale Attention Mechanism

Contact Info

Product

Resources

About