Boyang Song

Boyang Song

Auto-generated profile, based on publicly available information

Boyang Song

Department of Automatic Control and Systems Engineering, The University of Sheffield, Sheffield S1 3JD, U.K

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 July 2022 in IEEE Sensors Journal
Verified
Journal Article
Open access
ZZZe Zhang
Ze Zhang
Michael FarnsworthMichael Farnsworth
Michael Farnsworth
BSBoyang Song
Boyang Song
DTDIVYA Tiwari
DIVYA Tiwari
Ashutosh TiwariAshutosh Tiwari
Ashutosh Tiwari
Monitoring of complex industrial processes can be achieved by obtaining process data by utilising various sensing modalities. The recent emergence of deep learning provides a new routine for processing multi-sensor information. However, the learning ability of shallow neural networks is insufficient, and the data amount required by deep networks is often too large for industrial scenarios. This paper provides a novel deep transfer learning method as a possible solution that offers an advantage of better learning ability of the deep network without the requirement for a large amount of training data. This paper presents how Transformer with self-attention trained from natural language can be transferred to the sensor fusion task. Our proposed method is tested on 3 datasets: condition monitoring of a hydraulic system, bearing, and gearbox dataset. The results show that the Transformer trained from natural language can effectively reduce the required data amount for using deep learning in industrial sensor fusion with high prediction accuracy. The difficult and uncertain artificial feature engineering which requires a large workload can also be eliminated, as the deep networks are able to extract features automatically. In addition, the self-attention mechanism of Transformer aids in the identification of critical sensors, hence the interpretability of deep learning in industrial sensor fusion can be improved.

9 October 2015 in The International Journal of Advanced Manufacturing Technology
Verified
Journal Article
Open access
PDF file
VPVinayak Ashok Prabhu
Vinayak Ashok Prabhu
BSBoyang Song
Boyang Song
JTJohn Thrower
John Thrower
ATAshutosh Tiwari
Ashutosh Tiwari
PWPhil Webb
Phil Webb
Several manufacturing operations continue to be manual even in today’s highly automated industry because the complexity of such operations makes them heavily reliant on human skills, intellect and experience. This work aims to aid the automation of one such operation, the wheel loading operation on the trim and final moving assembly line in automotive production. It proposes a new method that uses multiple low-cost depth imaging sensors, commonly used in gaming, to acquire and digitise key shopfloor data associated with the operation, such as motion characteristics of the vehicle body on the moving conveyor line and the angular positions of alignment features of the parts to be assembled, in order to inform an intelligent automation solution. Experiments are conducted to test the performance of the proposed method across various assembly conditions, and the results are validated against an industry standard method using laser tracking. Some disadvantages of the method are discussed, and suggestions for improvements are suggested. The proposed method has the potential to be adopted to enable the automation of a wide range of moving assembly operations in multiple sectors of the manufacturing industry.

16 May 2016 in Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture
Verified
Journal Article
Closed access
PDF file
VPVinayak Ashok Prabhu
Vinayak Ashok Prabhu
NMNarendi Muhandri
Narendi Muhandri
BSBoyang Song
Boyang Song
ATAshutosh Tiwari
Ashutosh Tiwari
Automation, driven by informatics, enables manufacturing companies to increase productivity and meet market demands for cost-effective and high-quality products. However, many manufacturing operations across industry verticals continue to be manual even today. One such example is the manual assembly of the final trim and wheels in an automotive production line where there is heavy reliance on human decision-making pertaining to when, where and how to install components on and inside a constantly moving vehicle body. The main aim of this work is to develop a rule-based decision support system that will enable an automation solution to make human-like decisions in moving assembly operations. The wheel loading operation is chosen as a case study and a decision support framework and tool is developed and successfully tested using multiple assembly scenarios generated from experimental data provided by gaming interface sensors installed on the laboratory-based shopfloor. The resulting decision support system has the potential to enable the automation of moving assembly operations in various sectors of the manufacturing industry.