Low-Power Detection and Classification for In-Sensor Predictive Maintenance Based on Vibration Monitoring

Abstract

In this work, a new custom design of an anomaly detection and classification system is proposed. It is composed of a convolutional Auto-Encoder (AE) hardware design to perform anomaly detection which cooperates with a mixed HW/SW Convolutional Neural Network (CNN) to perform the classification of detected anomalies. The AE features a partial binarization, so that the weights are binarized while the activations, associated to some selected layers, are non-binarized. This has been necessary to meet the severe area and energy constraints that allow it to be integrated on the same die as the MEMS sensors for which it serves as a neural accelerator. The CNN shares the feature extraction module with the AE, whereas a SW classifier is triggered by the AE when a fault is detected, working asynchronously to it. The AE has been mapped on a Xilinx Artix-7 FPGA, featuring an Output Data Rate (ODR) of 365 kHz and achieving a power dissipation of 333 W/MHz. Logic synthesis has targeted TSMC CMOS 65 nm, 90 nm, and 130 nm standard cells. Best results achieved highlight a power consumption of 138 μW/MHz with an area occupation of 0.49 mm 2 when real-time operations are set. These results enable the integration of the complete neural accelerator in the CMOS circuitry that typically sits with the inertial MEMS on the same silicon die. Comparisons with the related works suggest that the proposed system is capable of state-of-the-art performances and accuracy.

Few-Shot Learning for Prescriptive Maintenance

“…In our experiment, we randomly select three classes to construct the classification tasks. To evaluate the necessity of using few-shot learning, we evaluate the MAML algorithm together with Vitolo et al's solution [11] which is based on Convolutional Neural Networks (CNN) and Ren's solution [12] that is based on neighbor nearest algorithm. Following Vinyals et al's [7][8] design of the experiment, we use N-way classification with 1 or 5 shots.…”

Automatic Audio Feature Extraction for Keyword Spotting

“…However, these methods still rely on computationally complex FT processes. The aim of this work is to demonstrate the advantages of using Auto-Encoders (AE) [9]- [11] in implementing an automated data-driven approach for audio feature extraction. The main advantages of the proposed approach are as follows:…”

Energy Balance of Wireless Sensor Nodes Based on Bluetooth Low Energy and Thermoelectric Energy Harvesting

“…With the development of IoT technology, today this goal is within reach. Devices designed for this purpose must include an energy harvesting unit, specific sensors, and a communication module to acquire the key physical variables and send this information wirelessly to the cloud to be analyzed in real time to apply predictive maintenance approaches [ 7 ]. The required energy and communication capabilities are critical factors, which are highly influenced by factors such as data transfer rate and distances to be covered [ 8 ].…”