Demonstrates enhanced leak detection accuracy in legacy systems, suggesting superior integration methods.
This paper presents a software-based dynamic digital signal processing (DSP) pipeline reengineering method enabling seamless integration of legacy acoustic leak detectors (SebaKMT, Kaskad-3) operating at 6554 Hz into the RIVIXI AI v1.3 platform originally designed for 44100 Hz sensors. The adaptive DSP module resolves Nyquist frequency collisions by dynamically scaling Butterworth filter bandpass boundaries to 0.99 of the Nyquist limit, implements a dynamic speed-of-sound equation for fluid-filled metallic pipes (reducing localization error to centimeter precision), and applies Z-Score peak detection. Validated on 60 field recordings (steel pipelines, 400–1000 mm diameter), the method achieves complete linear class separation with Z-Score 6.35–6.47 for normal pipes and 14.19–16.48 for verified leaks (Welch's t-test: t(29.1) = −75.2, p < 0.0001). Comparative benchmarking against linear resampling (11.7% FPR) and sinc-interpolation (3.3% FPR, 4.2× CPU overhead) demonstrates that native-rate DSP reengineering achieves 0.0% FPR at only 1.05× computational overhead.
No takes yet. Share an insight, caveat, or question.
Ivanaiskii et al. (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: