Low-Cost Embedded System for Acoustic Fault Detection

Research on Fault Feature Extraction and Intelligent Diagnosis Technology of Motor Drive in Embedded Systems

Motor drive systems operating in embedded environments are frequently affected by noise, dynamic loading conditions, and electromagnetic interference, making timely fault diagnosis difficult. To improve diagnostic accuracy and real-time performance, this study proposes an intelligent fault diagnosis framework based on embedded multi-source data acquisition and feature fusion. High-precision sensors are employed to synchronously collect vibration and current signals, while improved wavelet packet decomposition and principal component analysis are combined to extract discriminative multi-dimensional fault features and eliminate redundant information. A lightweight convolutional neural network optimized for embedded deployment is then developed to perform low-latency fault classification and edge inference. Experimental results show that the proposed method achieves an average F1-score exceeding 97% under complex mixed-fault conditions, while maintaining an average detection latency of approximately 45 ms. The proposed framework demonstrates strong robustness and computational efficiency, providing practical support for intelligent industrial maintenance and offering reference solutions for embedded sensing, signal processing, and electromagnetic compatibility environments.

Radar-based electrical machine fault diagnosis via time–frequency imaging and deep feature-based machine learning

Edge-Server Collaborative System for Real-Time and In-Depth Damage Detection of Wind Turbine Blades using Acoustic Signals

Efficient health monitoring is indispensable for the reliable operation of wind turbines. Damage to wind turbine blades, such as cracks and holes, typically generates whistle-like sounds during rotation. This study proposes a two-stage edge-server collaborative system for detecting blade damage using acoustic signals captured by arrays built from commodity microphones. The first stage employs a lightweight attention-based convolutional neural network to run on edge devices for the real-time binary classification to determine whether anomalous sounds are present. Suspicious time segments are stored for further analysis. The second stage uses a time-frequency sound event detection model that employs a detection transformer with an audio spectrogram transformer backbone to identify the time and frequency ranges of sound events via bounding boxes in the spectrograms. Owing to its high computational demand, this in-depth analysis is performed on a server. To validate the proposed system, acoustic signals were recorded intermittently for more than a year using micro-electromechanical system (MEMS) microphones externally attached to wind turbine towers. The models were trained and evaluated on a manually annotated dataset comprising 4,210 audio clips (15 s each) containing 14,420 sound events. The experimental results demonstrated that the binary classification model achieved an area under the receiver operating characteristic curve (AUC) of 0.920, whereas the sound event detection model attained an average precision at a 50% intersection-over-union threshold (AP50) of 0.510. Furthermore, evaluations on test data under unseen conditions, comprising 496 clips with 135 sound events recorded by handheld recorders at different locations, yielded an AUC of 0.867 and an AP50 of 0.440. The results highlight the robustness of the proposed system to variations in microphone types, recording locations, and environmental noise, demonstrating its strong potential for practical continuous automatic damage detection in wind power infrastructure.

Self-Supervised Anomaly Detection for Industrial Machines With Sensor Distance Classification

The rise of low-power, affordable sensing technologies and machine learning algorithms has sparked a growing interest in using data-driven approaches to monitor industrial assets. In particular, applying machine learning to analyze the sounds produced by manufacturing tools is becoming an effective method for quickly detecting deviations from standard operating conditions. However, the implementation of these systems encounters a major challenge due to the difficulty in obtaining suitable training data. Self-supervised learning offers a promising solution to this issue. It enables the training of anomaly detection models exclusively with signals representing normal conditions, which are more accessible than anomalous signals. Despite its potential, achieving robust and consistent performance across machines of varying models and types remains critical. Existing methods generally follow one of two approaches. The first, single-machine training, involves training a dedicated model using local data from each machine. Although straightforward, this approach often yields suboptimal performance. The second, multi-machine training, aims to enhance detection capability by aggregating data from multiple machines to train a shared model. This strategy requires transmitting data from geographically dispersed manufacturing sites—often belonging to different clients—to centralized facilities, raising concerns about data transmission costs and risks of exposing sensitive production information. We address these issues by introducing a novel self-supervised strategy for effective single-machine training based on classifying the distance between the monitored machine (i.e., the sound source) and each microphone sensor of a multi-channel recording system. Our method bypasses the need for data aggregation, providing a cost-efficient and privacy-preserving alternative while delivering competitive detection performance. Experiments on the MIMII dataset highlight the effectiveness of our approach, with performance improvements up to 14.53% over conventional single-machine training strategies and 18.58% over multi-machine training strategies.

Deep Learning-Based Real-Time Fault Detection in VLSI and Embedded Systems using Intelligent Signal Analysis

The escalating intricacy of very-large-scale integration (VLSI) circuits and embedded computer systems has rendered swift and dependable fault detection a crucial necessity for reliable electronic systems. Traditional testing and monitoring methodologies typically rely on manually crafted signal descriptors, established thresholds, or resource-intensive diagnostic techniques, which may prove inadequate when fault signatures are faint, noisy, non-stationary, or dispersed across various operational parameters. This manuscript introduces a real-time fault detection framework utilising deep learning, which integrates intelligent signal preprocessing, multi-domain feature representation, temporal deep learning, and efficient inference for monitoring VLSI and embedded systems. The suggested methodology acquires electrical and operational data including voltage, current, clock performance, temperature, power consumption metrics, timing discrepancies, and chosen telemetry from embedded systems. A signal-analysis layer executes normalisation, denoising, segmentation, and time-frequency transformation prior to a hybrid neural architecture acquiring distinguishing fault representations. The framework is intended to differentiate between standard operation and various fault circumstances relating to timing, power, thermal issues, signal integrity, transients, and hardware, while concurrently assessing fault confidence and severity. An interpretability component can be integrated to discern the signal periods and attributes that most significantly affect each diagnostic choice. The experimental protocol assesses accuracy, precision, recall, F1-score, ROCAUC, false-positive rate, inference latency, and throughput, alongside ablation and cross-condition evaluations. The suggested approach aims to establish a replicable connection between profound signal intelligence and instantaneous electronic system analysis. The document outlines the mathematical foundation, experimental methodology, comparative assessment structure, and implementation factors necessary for validation using benchmark, simulation-derived, or laboratoryacquired fault data.

An Internet of Things-based intelligent monitoring and fault detection method for the operation and maintenance of offshore wind turbines

The rapid expansion of offshore wind farms has introduced significant challenges to operation and maintenance (O&M), particularly under harsh marine environments where reliable electromagnetic information transmission and constrained wireless communication resources directly affect intelligent monitoring performance. Traditional Supervisory Control and Data Acquisition (SCADA) systems relying on cloud-centric architectures often encounter excessive latency and bandwidth bottlenecks when transmitting high-frequency vibration signals, limiting real-time fault diagnosis. To address these issues, this study proposes an Internet of Things (IoT)-based intelligent monitoring and fault detection method built upon an Edge-Cloud collaborative architecture. A lightweight Adaptive One-Dimensional Convolutional Neural Network (A-1D-CNN) is developed for deployment on edge gateway devices, enabling direct extraction of fault characteristics from raw vibration signals without manual feature engineering. Combined with an “ Edge-Training, Cloud-Update” strategy, the proposed framework continuously optimizes diagnostic performance while substantially reducing communication overhead across wireless sensing and electromagnetic transmission infrastructures. Experimental evaluation on a standard bearing fault dataset demonstrates that the proposed method achieves a fault diagnosis accuracy of 99.25% with a compact model size of only 0.45 MB, providing an effective balance between diagnostic precision and deployment efficiency. The results indicate that the proposed framework offers a practical solution for real-time intelligent monitoring in bandwidth-limited offshore environments and provides technical support for reliable electromagnetic-enabled sensing networks and distributed fault diagnosis in next-generation offshore energy systems.