Runtime Tracking-Based Replication of On-Chip Embedded Software Using Transfer Function Learning for Dust Particle Sensing Systems

Abstract

A digital twin is a widely used method that uses digitized simulations of the real-world characteristics because it is effective in predicting results at a low cost. In digital twin analysis, the transfer function between the input and output data is an important research subject. In this study, we intend to investigate the application of the digital twin method to dust particle sensing. A high-performance multichannel reference dust particle sensor provides particle count as well as particulate matter information, whereas a lightweight embedded test device only provides a particle count. The particulate matter acquisition algorithm for a reference device is unknown and complex. Instead of that, we propose a simple method to calculate the transfer function using singular-value decomposition. In the experimental results, using singular-value decomposition, the predicted particulate matter of the test device was similar to that of the reference device. The obtained transfer function shows similar measurement results of the two dust particle sensor devices, confirming that particulate matter environmental information can be digitized even with low-power and lightweight sensor-embedded devices. In addition, the power consumption of the test device was approximately ten times lower than that of the reference device. INDEX TERMS Digital twin, Particle sensing, Particulate matter, Singular-value decomposition.

LSTM‐based post‐processing for noise reduction in SVD‐based particulate matter digital twinning on lightweight embedded devices

“…Calibration requires a transfer function, which can vary depending on the sampling frequency and the number of sensor, and the transfer function is often unknown. Lee [6] proposed obtaining the transfer function in the calculation of a transfer matrix using SVD.…”

“…Lee [6] introduced a methodology employing singular value decomposition (SVD) to replicate the transfer function between particle count (PC) acquired from a cost-effective single-sensor device (referred as the "test device") and the PM values obtained from a high-performance multi-sensor device (referred as the "reference device"). The primary objective was to derive particulate matter (PM) of the test device (denoted as TPM) that align with PM values of the reference device (denoted as RPM).…”