Parallelization is All System Identification Needs: End-to-End Vibration Diagnostics on a Multicore RISC-V Edge Device

The early detection of structural malfunctions requires the installation of real-time monitoring systems ensuring continuous access to the damage-sensitive information; nevertheless, it can generate bottlenecks in terms of bandwidth and storage. Deploying data reduction techniques at the edge is recognized as a proficient solution to reduce the system’s network traffic. However, the most effective solutions currently employed for the purpose are typically based on memory and power-hungry algorithms, making their embedding on resource-constrained devices very challenging; this is the case of vibration data reduction based on System Identification (SysId) models. This article presents PARSY-VDD, a fully optimized PArallel end-to-end software framework based on SysId for vibration-based damage detection, as a suitable solution to perform damage detection at the edge in a time and energy-efficient manner, avoiding streaming raw data to the cloud. First, we evaluate the damage detection capabilities of PARSY-VDD with two benchmarks: 1) a bridge and 2) a wind turbine blade, showcasing the robustness of the end-to-end approach. Then, we deploy PARSY-VDD on both commercial single-core (STM32 family) and a specific multicore (GAP9) edge device. We introduce an architecture-agnostic algorithmic optimization for SysId, improving the execution by ${90}{\times }$ and reducing the consumption by ${85}{\times }$ compared with the state-of-the-art SysId implementation on GAP9. Results show that by utilizing the unique parallel computing capabilities of GAP9, the execution time is $\mathrm {751~ {\mu }\text {s}}$ with the high-performance multicore solution operating at 370 MHz and 0.8 V, while the energy consumption is $\mathrm {37~ {\mu }J}$ with the low-power solution operating at 240 MHz and 0.65 V. Compared with other single-core implementations based on STM32 microcontrollers, the GAP9 high-performance configuration is ${76}{\times }$ faster, while the low-power configuration is ${360}{\times }$ more energy efficient.