Litcius/Paper detail

EdgeCog: A Real-Time Bearing Fault Diagnosis System Based on Lightweight Edge Computing

Lei Fu, Ke Yan, Yikun Zhang, Rupeng Chen, Zepeng Ma, Fang Xu, Tiantian Zhu

2023IEEE Transactions on Instrumentation and Measurement25 citationsDOI

Abstract

Deep learning has made important contributions to classification tasks applied to fault diagnosis. However, it is crucial to integrate the technologies into real industrial applications through cost-effective hardware. Edge computing, a new computing paradigm, has the potential to accelerate system response time, reduce bandwidth for transmission, and use fewer computing resources. In this article, the distillation quantization compression method based on energy entropy is applied to compress the convolutional neural network (CNN), which is deployed on a Cortex-M4 series microcontroller with only 192 kB of RAM and 512 kB of ROM. Additionally, based on the fault mechanism of rolling bearings, this article integrates the attention mechanism and envelope spectrum to verify the effectiveness of feature extraction by the CNN model, which effectively weakens invalid features in the distillation quantization process. The experimental results show that the proposed method has excellent performance in terms of memory overhead and inference speed, which has great potential in industrial applications.

Topics & Concepts

Computer scienceEdge computingQuantization (signal processing)Convolutional neural networkFeature extractionEmbedded systemMicrocontrollerField-programmable gate arrayDeep learningEdge deviceEntropy (arrow of time)Artificial neural networkComputer engineeringArtificial intelligenceReal-time computingEnhanced Data Rates for GSM EvolutionAlgorithmQuantum mechanicsOperating systemCloud computingPhysicsIndustrial Vision Systems and Defect DetectionAnomaly Detection Techniques and ApplicationsFault Detection and Control Systems
EdgeCog: A Real-Time Bearing Fault Diagnosis System Based on Lightweight Edge Computing | Litcius