Search results
1 – 2 of 2Rommel Stiward Prieto, Diego Alberto Bravo Montenegro and Carlos Rengifo
The purpose of this paper is to approach predictive maintenance (PdM) of brushless direct current (BLDC) motors using audio signal processing and extracting statistical and…
Abstract
Purpose
The purpose of this paper is to approach predictive maintenance (PdM) of brushless direct current (BLDC) motors using audio signal processing and extracting statistical and spectral features to train classical machine learning (ML) models.
Design/methodology/approach
The proposed methodology relies on classification predictive model that shows the motors prone to failure. To verify this, the model was implemented and tested with audio data. The trained models are then deployed to an Industrial Internet of Things (IIoT) application built using Django.
Findings
The implementation of the methodology allows for achieving performance as high as 92% accuracy, proving that spectral features should be considered when training ML models for PdM.
Originality/value
The proposed model is an effective decision-making tool that provides an ideal solution for preventive maintenance scheduling problems for BLDC motors.
Details
Keywords
Yogesh Patil, Ashik Kumar Patel, Gopal Dnyanba Gote, Yash G. Mittal, Avinash Kumar Mehta, Sahil Devendra Singh, K.P. Karunakaran and Milind Akarte
This study aims to improve the acceleration in the additive manufacturing (AM) process. AM tools, such as extrusion heads, jets, electric arcs, lasers and electron beams (EB)…
Abstract
Purpose
This study aims to improve the acceleration in the additive manufacturing (AM) process. AM tools, such as extrusion heads, jets, electric arcs, lasers and electron beams (EB), experience negligible forces. However, their speeds are limited by the positioning systems. In addition, a thin tool must travel several kilometers in tiny motions with several turns while realizing the AM part. Hence, acceleration is a more significant limiting factor than the velocity or precision for all except EB.
Design/methodology/approach
The sawtooth (ST) scanning strategy presented in this paper minimizes the time by combining three motion features: zigzag scan, 45º or 135º rotation for successive layers in G00 to avoid the CNC interpolation, and modifying these movements along 45º or 135º into sawtooth to halve the turns.
Findings
Sawtooth effectiveness is tested using an in-house developed Sand AM (SaAM) apparatus based on the laser–powder bed fusion AM technique. For a simple rectangle layer, the sawtooth achieved a path length reduction of 0.19%–1.49% and reduced the overall time by 3.508–4.889 times, proving that sawtooth uses increased acceleration more effectively than the other three scans. The complex layer study reduced calculated time by 69.80%–139.96% and manufacturing time by 47.35%–86.85%. Sawtooth samples also exhibited less dimensional variation (0.88%) than zigzag 45° (12.94%) along the build direction.
Research limitations/implications
Sawtooth is limited to flying optics AM process.
Originality/value
Development of scanning strategy for flying optics AM process to reduce the warpage by improving the acceleration.
Details