ReCoN: A Reconfigurable CNN Acceleration Framework for Hybrid Semantic Segmentation on Hybrid SoCs for Space Applications

Reconfigurable Framework for Resilient Semantic Segmentation for Space Applications

ACM Transactions on Reconfigurable Technology and Systems ◽

10.1145/3472770 ◽

2021 ◽

Vol 14 (4) ◽

pp. 1-32

Author(s):

Sebastian Sabogal ◽

Alan George ◽

Gary Crum

Keyword(s):

High Performance ◽

Fault Injection ◽

Semantic Segmentation ◽

Control Flow ◽

Radiation Environment ◽

Space Applications ◽

Selective Approach ◽

Availability Constraints ◽

Computationally Intensive ◽

Commercial Off The Shelf

Deep learning (DL) presents new opportunities for enabling spacecraft autonomy, onboard analysis, and intelligent applications for space missions. However, DL applications are computationally intensive and often infeasible to deploy on radiation-hardened (rad-hard) processors, which traditionally harness a fraction of the computational capability of their commercial-off-the-shelf counterparts. Commercial FPGAs and system-on-chips present numerous architectural advantages and provide the computation capabilities to enable onboard DL applications; however, these devices are highly susceptible to radiation-induced single-event effects (SEEs) that can degrade the dependability of DL applications. In this article, we propose Reconfigurable ConvNet (RECON), a reconfigurable acceleration framework for dependable, high-performance semantic segmentation for space applications. In RECON, we propose both selective and adaptive approaches to enable efficient SEE mitigation. In our selective approach, control-flow parts are selectively protected by triple-modular redundancy to minimize SEE-induced hangs, and in our adaptive approach, partial reconfiguration is used to adapt the mitigation of dataflow parts in response to a dynamic radiation environment. Combined, both approaches enable RECON to maximize system performability subject to mission availability constraints. We perform fault injection and neutron irradiation to observe the susceptibility of RECON and use dependability modeling to evaluate RECON in various orbital case studies to demonstrate a 1.5–3.0× performability improvement in both performance and energy efficiency compared to static approaches.

Download Full-text

4D printing technology, modern era: A short review

International Journal of Energy Technology ◽

10.32438//ijet.203015 ◽

2020 ◽

pp. 92-111

Author(s):

Khodadad Mostakim ◽

Nahid Imtiaz Masuk ◽

Md. Rakib Hasan ◽

Md. Shafikul Islam

Keyword(s):

Smart Materials ◽

Computer Aided Design ◽

Short Review ◽

Stimuli Responsive ◽

4D Printing ◽

Space Applications ◽

Printing Technology ◽

Practical Applications ◽

Biomedical Technologies ◽

Novel Material

The advancement in 3D printing has led to the rapid growth of 4D printing technology. Adding time, as the fourth dimension, this technology ushered the potential of a massive evolution in fields of biomedical technologies, space applications, deployable structures, manufacturing industries, and so forth. This technology performs ingenious design, using smart materials to create advanced forms of the 3-D printed specimen. Improvements in Computer-aided design, additive manufacturing process, and material science engineering have ultimately favored the growth of 4-D printing innovation and revealed an effective method to gather complex 3-D structures. Contrast to all these developments, novel material is still a challenging sector. However, this short review illustrates the basic of 4D printing, summarizes the stimuli responsive materials properties, which have prominent role in the field of 4D technology. In addition, the practical applications are depicted and the potential prospect of this technology is put forward.

Download Full-text