State identification of a 5-axis ultra-precision CNC machine tool using energy consumption data assisted by multi-output densely connected 1D-CNN model

Zhicheng Xu (), Vignesh Selvaraj () and Sangkee Min ()
Additional contact information
Zhicheng Xu: University of Wisconsin Madison
Vignesh Selvaraj: University of Wisconsin Madison
Sangkee Min: University of Wisconsin Madison

Journal of Intelligent Manufacturing, 2024, vol. 35, issue 1, No 9, 147-160

Abstract: Abstract Ultra-precision machine tools are the foundation for ultra-precision manufacturing. In the era of Industry 4.0, monitoring the machine tool’s working condition is critical to control the machining quality. In a conventional setting, numerous sensors are retrofitted to the machine to monitor its condition effectively. This process could potentially increase the cost of the widespread application of Industry 4.0 technologies. In contrast to the method of retrofitting the machine tool, in this work, we propose an intelligent monitoring system that utilizes the equipment’s power consumption data to assess and determine the equipment states. The work also discusses the development of a G-code interpreter application used to develop an equipment working status matrix. The G-code interpreter application can generate the training data and extract features for the Deep Learning/Machine learning models. The feature extraction process can also be customized by providing template functions to the application. A densely connected convolutional neural network with multiple outputs was then developed to identify the machine state and predict the feedrate simultaneously. The model was able to identify the working component of the machine with an accuracy of $$\sim $$ ∼ 94% and was able to predict the feed rate with a standard deviation ( $$\sigma $$ σ ) of 21.900 from the energy consumption data. The overarching goal of the research work is to predict energy consumed, and augment anomaly detection for an ultra-precision CNC machine tool. The work presented here involves the identification of the equipment state and prediction of the equipment feedrate, and it will serve as a precursor.

Keywords: Ultra-precision CNC machine tool; Densely connected convolutional neural network; Axis detection; Smart manufacturing (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://link.springer.com/10.1007/s10845-022-02030-y Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:joinma:v:35:y:2024:i:1:d:10.1007_s10845-022-02030-y

Ordering information: This journal article can be ordered from
http://www.springer.com/journal/10845

DOI: 10.1007/s10845-022-02030-y

Access Statistics for this article

Journal of Intelligent Manufacturing is currently edited by Andrew Kusiak

More articles in Journal of Intelligent Manufacturing from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().