End-to-End Deep Learning by MCU Implementation: An Intelligent Gripper for Shape Identification

Hung, Chung-Wen; Zeng, Shi-Xuan; Lee, Ching‐Hung; Li, Wei-Ting

doi:10.3390/s21030891

Cited by 16 publications

(13 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Convolutional neural net is a popular algorithm for classification due to its ability to learn and extract the features, and less parameter memory and calculation requirement is suitable for modularization [10,12,13]. 1-D CNN is adopted in this paper due to the resource limitation in a low-cost MCU, no matter memory or calculation speed.…”

Section: Identification Algorithmmentioning

confidence: 99%

“…In [9], a chamfering tool diagnostic AI algorithm was developed and installed into a SOC. A smart grape with object shape classification function was proposed and implemented into an MCU in Hung et al [10]. The experimental results of both researches showed that the end-point machine learning equipment could provide a complete AI function in real time.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

End-to-End Deep Learning by MCU Implementation: Indoor Localization by Sound Spectrum of Light Fingerprints

Hung¹,

Kobayashi²,

Wu³

et al. 2021

JRNAL

Self Cite

View full text Add to dashboard Cite

This paper introduces a low-cost indoor localization system using sound spectrum of light fingerprint. An Artificial Intelligence (AI), algorithm will be implemented in a low-cost Micro-Control Unit (MCU), to perform the localization function. The unique light fingerprints with complex and tiny differences are caused by the different characteristics of the discrete components used in lighting devices. Only sound spectrum of light fingerprint is adopted for the identification of the lighting device to reduce the memory size requirement for implementation in a low-cost MCU. So, the grid search is used to optimize the hyperparameters for the smallest AI model. The system architecture and algorithm development are discussed in this paper, and the experimental results will be present to show the performance of the proposed system.

show abstract

Section: Identification Algorithmmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

End-to-End Deep Learning by MCU Implementation: Indoor Localization by Sound Spectrum of Light Fingerprints

Hung¹,

Kobayashi²,

Wu³

et al. 2021

JRNAL

Self Cite

View full text Add to dashboard Cite

show abstract

“…With the development of artificial intelligence technology, deep learning is a branch of machine learning that can automatically extract features to represent the characteristics of the data [ 28 , 29 , 30 , 31 , 32 , 33 ]. In this study, we estimate the tool wear and surface roughness using a one-dimensional (1D) convolutional neural network (1D-CNN) with sensor fusion.…”

Section: Introductionmentioning

confidence: 99%

Estimation of Tool Wear and Surface Roughness Development Using Deep Learning and Sensors Fusion

Huang

Lee

2021

Sensors

Self Cite

View full text Add to dashboard Cite

This paper proposes an estimation approach for tool wear and surface roughness using deep learning and sensor fusion. The one-dimensional convolutional neural network (1D-CNN) is utilized as the estimation model with X- and Y-coordinate vibration signals and sound signal fusion using sensor influence analysis. First, machining experiments with computer numerical control (CNC) parameters are designed using a uniform experimental design (UED) method to guarantee the variety of collected data. The vibration, sound, and spindle current signals are collected and labeled according to the machining parameters. To speed up the degree of tool wear, an accelerated experiment is designed, and the corresponding tool wear and surface roughness are measured. An influential sensor selection analysis is proposed to preserve the estimation accuracy and to minimize the number of sensors. After sensor selection analysis, the sensor signals with better estimation capability are selected and combined using the sensor fusion method. The proposed estimation system combined with sensor selection analysis performs well in terms of accuracy and computational effort. Finally, the proposed approach is applied for on-line monitoring of tool wear with an alarm, which demonstrates the effectiveness of our approach.

show abstract

“…Applications of a CNN in vibration signals are discussed in lots of research, including bearing faults diagnosis, tool wear classification and machining roughness estimation. By employing convolutional operation, the features can be extracted automatically [ 44 , 45 , 46 , 47 , 48 ]. One-dimensional CNNs (1DCNN) and two-dimensional CNNs (2DCNN) are used in the domain of REB signals prediction.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Approach for Vibration Signals Applications

Chen

Lee

2021

Sensors

Self Cite

View full text Add to dashboard Cite

This study discusses convolutional neural networks (CNNs) for vibration signals analysis, including applications in machining surface roughness estimation, bearing faults diagnosis, and tool wear detection. The one-dimensional CNNs (1DCNN) and two-dimensional CNNs (2DCNN) are applied for regression and classification applications using different types of inputs, e.g., raw signals, and time-frequency spectra images by short time Fourier transform. In the application of regression and the estimation of machining surface roughness, the 1DCNN is utilized and the corresponding CNN structure (hyper parameters) optimization is proposed by using uniform experimental design (UED), neural network, multiple regression, and particle swarm optimization. It demonstrates the effectiveness of the proposed approach to obtain a structure with better performance. In applications of classification, bearing faults and tool wear classification are carried out by vibration signals analysis and CNN. Finally, the experimental results are shown to demonstrate the effectiveness and performance of our approach.

show abstract

End-to-End Deep Learning by MCU Implementation: An Intelligent Gripper for Shape Identification

Cited by 16 publications

References 34 publications

End-to-End Deep Learning by MCU Implementation: Indoor Localization by Sound Spectrum of Light Fingerprints

End-to-End Deep Learning by MCU Implementation: Indoor Localization by Sound Spectrum of Light Fingerprints

Estimation of Tool Wear and Surface Roughness Development Using Deep Learning and Sensors Fusion

Deep Learning Approach for Vibration Signals Applications

Contact Info

Product

Resources

About