SmartSV: Real-Time Solenoid Valve Diagnosis at Embedded Edge-Level

Abstract

In industrial process automation, sensors, controllers, and actuators are expected to be healthy throughout, so that production lines are working under pre-defined conditions. When these systems malfunction, alerts have to be generated in real-time to make sure production quality is not compromised and also the safety of humans and equipment is assured. In this work, we describe the construction of SmartSV, a smart real-time edge-based system, which monitors the health of a Solenoid Valve (SV). SmartSV is compact, low power, easy to install, and cost-effective. It has data fidelity and measurement accuracy comparable to signals captured using high-end equipment. SmartSV runs TinyML and is able to differentiate between the distinct types of faults. These faults include: (a) Spool stuck (b) Spring failure and (c) Under voltage.