AI-based predictive maintenance solution
16/09/2021
QuickLogic Corporation, a developer of ultra-low-power multi-core voice-enabled systems on chips (SoCs), embedded FPGA IP and end-point artificial intelligence (AI) solutions, has announced that its customer, aiSensing, has developed an AI-enabled Industrial Internet of Things (IIoT) solution that can determine multiple fault modes for predictive maintenance applications.This vibration sensor employs AI/machine learning (ML) techniques to intelligently monitor the equipment status and identify and signal when different fault modes occur. The aiSensing solution is based on QuickLogic’s QuickAI platform, including the ultra-low-power EOS™ S3 multi-core sensor processing SoC, QuickFeather development kit and SensiML Analytics Toolkit for end-point AI applications.
aiSensing’s predictive maintenance (PdM) solution integrates AI/ML technology to monitor the status of manufacturing equipment locally without the need for an internet-based cloud connection. This approach results in a robust, high-performance, real-time and high-security PdM solution for end-customers. The total solution is also extremely low-power and low-cost, making it practical to implement for a wide range of manufacturing applications. In addition, the AI models used by the sensor can be easily and quickly customised for each piece of manufacturing equipment to achieve a high degree of accuracy.
Accurate predictive maintenance is one of the key hallmarks of the AI-enabled Industry 4.0 (fourth-generation) wave of intelligent manufacturing. In this case, the aiSensing solution integrates a vibration sensor, using AI to differentiate between normal and abnormal operation for a particular piece of manufacturing equipment, and sends an alarm message to engineers and managers as soon as an abnormal state is detected. By identifying pending failures before they happen, the intelligent sensor allows operators to shut down equipment for maintenance in an orderly way and thus manage their production lines more efficiently and cost-effectively. It can also help save costs by avoiding unnecessary preventative maintenance.
“With QuickLogic’s multi-core ultra-low-power EOS S3 SoC plus Open Source QuickFeather development kit and SensiML’s Analytics Toolkit, aiSensing has developed three generations of our AI vibration detector in less than six months to support different customer requirements,” said Dennis Chu, Chief Technology Officer, aiSensing. “Our resulting end-point AI-based IoT solution helps us enable predictive maintenance applications with better performance and cost than cloud-based AI solutions and positions us well for future growth.”
