Edge-Compatible Convolutional Autoencoder Implemented on FPGA for Anomaly Detection in Vibration Condition-Based Monitoring
- 16 March 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Letters
- Vol. 6 (4) , 1-4
Abstract
Estimating state of health of machines using vibration signals analyzed with complex deep-learning models poses memory and processing speed constraints for edge implementation, while cloud-based computing poses high latency, high cost of data transmission and storage and privacy threats. Moreover, in most practical settings, a large amount of data may be available or easily obtainable for machines in healthy/normal operating condition, and not in anomalous conditions. Thus, there exists a need to develop lightweight unsupervised learning based algorithms that can be implemented on an embedded platform for data processing and estimating state of health. In this work, we present a lightweight convolutional autoencoder (CAE) implemented on a low-cost FPGA platform (PYNQ-Z2, Xilinx Zynq 7020 SoC) to discern anomalies in vibration data sets. We present extensive performance analysis of various encoding methods to represent 1D time series as images, and feasibility analysis of FPGA-implementation of CAE. The optimized model has less than 10000 trainable parameters and shows highest accuracy (>88% on CPU, >85% with fixed point arithmetic on FPGA) using scalogram encoding when trained and tested on the Airbus SAS helicopter accelerometer data set.Keywords
This publication has 20 references indexed in Scilit:
- Rolling Bearing Fault Diagnosis Based on Convolutional Neural Network and Support Vector MachineIEEE Access, 2020
- Robust Sensor Suite Combined With Predictive Analytics Enabled Anomaly Detection Model for Smart Monitoring of Concrete Sewer Pipe Surface Moisture ConditionsIEEE Sensors Journal, 2020
- Challenges and Opportunities of Deep Learning Models for Machinery Fault Detection and Diagnosis: A ReviewIEEE Access, 2019
- Lightweight Deep Residual CNN for Fault Diagnosis of Rotating Machinery Based on Depthwise Separable ConvolutionsIEEE Access, 2019
- Accelerating CNN-RNN Based Machine Health Monitoring on FPGA2019
- An FPGA Implementation of a Convolutional Auto-EncoderApplied Sciences, 2018
- Early Fault Detection of Machine Tools Based on Deep Learning and Dynamic IdentificationIEEE Transactions on Industrial Electronics, 2018
- Multisensor Feature Fusion for Bearing Fault Diagnosis Using Sparse Autoencoder and Deep Belief NetworkIEEE Transactions on Instrumentation and Measurement, 2017
- Optimizing FPGA-based Accelerator Design for Deep Convolutional Neural Networks2015
- Vibration‐based Condition Monitoring2010