Low-Power, Neuromorphic, Acoustic Anomaly Detection for Persistent Machine Monitoring
Authors: Steven C. Nesbit, Victor M. Vergara, Michael A. Felix, Evan T. Kain, Luis R. García Carrillo, Gerd J. Kunde, Andrew T. Sornborger
Organizations: Information Sciences, CAI-3, Los Alamos National Laboratory, Los Alamos, USA · Information Sciences (CAI-3), Los Alamos National Laboratory, Los Alamos, NM, USA · AeroVironment Inc., Albuquerque, USA · AeroVironment, Inc, Albuquerque, NM, USA · University of New Mexico COSMIAC Research Center, Albuquerque, USA · University of New Mexico COSMIAC Research Center, Albuquerque, NM, USA · Air Force Research Laboratory, Kirtland AFB, USA · Air Force Research Laboratory, Kirtland AFB, NM, USA · Nuclear and Particle Physics and Applications, P-3, Los Alamos National Laboratory, Los Alamos, USA · Nuclear & Particle Physics & Applications (P-3), Los Alamos National Laboratory, Los Alamos, NM, USA
Persistent acoustic monitoring can detect machine faults without physical contact, but always-on inference is constrained by power, latency, and deployment complexity. We demonstrate autoencoder-based acoustic anomaly detection on an Intel Loihi 2 neuromorphic processor under clean and noisy conditions. Log-mel features are computed off chip; normalization, autoencoder inference, L1 reconstruction scoring, and thresholding run on chip. In a clean, microphone-position-invariant ToyADMOS ToyCar benchmark, the on-chip model achieves 0.9959 AUC and 0.9785 standardized pAUC at maximum false-positive rate 0.1. In the DCASE 2026 Task 2 ToyCar noisy benchmark, the model achieves source AUC 0.7990, target AUC 0.6466, and pAUC 0.6426, exceeding reported baseline metrics. Power profiling on a 16-chip Loihi 2 VPX system shows real-time throughput with 0.0406\unicodex20130.0426 mJ dynamic energy per sample, two orders of magnitude lower than both a CPU and GPU. These results support neuromorphic acoustic anomaly detection as a practical candidate for low-power, persistent machine monitoring.
Figures & tables
Figure 1: Persistent-monitoring pipeline. Log-mel extraction is off chip; normalization, autoencoder inference, L1 scoring, and thresholding run on Loihi 2.
Condition
Source/Pooled AUC
Target AUC
pAUC
ToyADMOS ToyCar, Loihi 2
0.9959
–
0.9785
DCASE 2026 ToyCar, Loihi 2
0.7990
0.6466
0.6426
DCASE 2026 ToyCar, baseline
0.7728
0.5317
0.5825
Table 1: Anomaly-detection performance. pAUC is standardized pAUC at maximum FPR 0.1.
Hardware
Latency
Total power
Total energy
Dynamic energy
( μ s/sample)
(W)
(mJ/sample)
(mJ/sample)
Loihi 2 VPX, Ethernet I/O
281.0
16.20
4.554
0.0426
Loihi 2 VPX, Preloaded Input
48.3
16.89
0.816
0.0406
Xeon E5-2660 v3 CPU
420.3
77.96
32.769
20.156
Tesla V100S GPU
163.5
58.35
9.540
5.350
Table 2: Inference latency and energy profiling.
Figure 2: Total and dynamic energy per sample; dynamic energy excludes static platform power.
Reliable fault detection is crucial for industrial machinery in large-scale facilities, where unexpected failures can cause costly downtime and production interruptions. Although acoustic monitoring provides a scalable solution for machine condition monitoring, its deployment is often constrained by high false-positive rates. We propose a two-step approach to automatic anomalous sound detection: first, when only normal operating audio samples are available, a regularized unsupervised model is deployed; then, after the first machine fault, a few-shot adaptation strategy exploits the anomalous samples acquired during the fault to improve the system. This adaptation increases the area under the precision-recall curve (AUPR) from 23.0 to 64.0 and improves detection in the low false-positive-rate region, with the partial area under the receiver operating characteristic curve (pAUROC) increasing from 39.6 to 72.8. We also show that covariance regularization improves both prediction accuracy and training stability in the unsupervised model. These results provide a practical strategy for acoustic anomaly detection systems, enabling improved accuracy and reduced false alarms.
Simone Lugani, Christof Pichler, Hannes Wegleiter +3
DITEN, University of Genoa, Genoa, Italy · Christian Doppler Laboratory for Measurement Systems for Harsh Operating Conditions, EMS, TU Graz, Graz, Austria · voestalpine Stahl GmbH, Linz, Austria
Autoencoder-based anomalous sound detection is attractive for machine condition monitoring because it can be trained using only normal recordings and yields an interpretable anomaly score from reconstruction error. Most prior work uses spectrogram autoencoders, but reconstructing detailed time--frequency patterns is sensitive to noise and transients, and models can reconstruct some anomalous inputs well, weakening normal--anomaly separation. We propose MemNMF, a constrained reconstruction method that operates on the Linear Predictive Coding spectrum, a compact estimate of the spectral envelope. MemNMF initializes a memory module from an NMF dictionary learned on normal LPC spectra and reconstructs each input as an attention-weighted combination of prototypical normal spectral patterns. Experiments on MIMII and DCASE 2020 Task 2 across multiple machine types and operating conditions show that LPC-spectrum inputs improve a standard autoencoder baseline and that MemNMF yields further gains, with especially strong robustness under noisy, non-stationary settings.
Tiny Machine Learning enables real-time, energy-efficient data processing directly on microcontrollers, making it ideal for Internet of Things sensor networks. This paper presents a compact TinyML pipeline for detecting anomalies in environmental sound within IoT sensor networks. Acoustic monitoring in IoT systems can enhance safety and context awareness, yet cloud-based processing introduces challenges related to latency, power usage, and privacy. Our pipeline addresses these issues by extracting Mel Frequency Cepstral Coefficients from sound signals and training a lightweight neural network classifier optimized for deployment on edge devices. The model was trained and evaluated using the UrbanSound8K dataset, achieving a test accuracy of 91% and balanced F1-scores of 0.91 across both normal and anomalous sound classes. These results demonstrate the feasibility and reliability of embedded acoustic anomaly detection for scalable and responsive IoT deployments.
Amar Almaini, Jakob Folz, Ghadeer Ashour
computer science, Deggendorf Institute of Technology, Deggendorf, Germany · Computer Science and Engineering, University of West Bohemia, Pilsen, Czech Republic · The Applied College, King Abdulaziz University, Jeddah, Saudi Arabia