On-Device IoT-Based Predictive Maintenance Analytics Model: Comparing TinyLSTM and TinyModel from Edge Impulse

Abstract

A precise prediction of the health status of industrial equipment is of significant importance to determine its reliability and lifespan. This prediction provides users information that is useful in determining when to service, repair, or replace the unhealthy equipment’s components. In the last decades, many works have been conducted on data-driven prognostic models to estimate the asset’s remaining useful life. These models require updates on the novel happenings from regular diagnostics, otherwise, failure may happen before the estimated time due to different facts that may oblige rapid maintenance actions, including unexpected replacement. Adding to offline prognostic models, the continuous monitoring and prediction of remaining useful life can prevent failures, increase the useful lifespan through on-time maintenance actions, and reduce the unnecessary preventive maintenance and associated costs. This paper presents the ability of the two real-time tiny predictive analytics models: tiny long short-term memory (TinyLSTM) and sequential dense neural network (DNN). The model (TinyModel) from Edge Impulse is used to predict the remaining useful life of the equipment by considering the status of its different components. The equipment degradation insights were assessed through the real-time data gathered from operating equipment. To label our dataset, fuzzy logic based on the maintainer’s expertise is used to generate maintenance priorities, which are later used to compute the actual remaining useful life. The predictive analytic models were developed and performed well, with an evaluation loss of 0.01 and 0.11, respectively, for the LSTM and model from Edge Impulse. Both models were converted into TinyModels for on-device deployment. Unseen data were used to simulate the deployment of both TinyModels. Conferring to the evaluation and deployment results, both TinyLSTM and TinyModel from Edge Impulse are powerful in real-time predictive maintenance, but the model from Edge Impulse is much easier in terms of development, conversion to Tiny version, and deployment.

A survey on AI Approaches for Internet of Things Devices Failure Prediction

“…Nevertheless, the context and dataset are unique, presenting a major challenge for these studies as each article employs its own system-specific dataset, such as an autoclave sterilizer [28], an MEP component [26], light bulbs [23], Smart Grid [15] . The dataset comprises samples of varying sizes collected at different time intervals.…”

Análise de Modelos de Aprendizado Profundo para Sistemas Embarcados aplicados à Classificação de Rachaduras em Construções

“…Nessa versão, é introduzido o uso de blocos residuais, nos quais cada bloco é composto por três camadas distintas: (1) camada de expansão, (2) camada de convoluc ¸ão em profundidade e (3) camada de projec ¸ão [26]. Essa estrutura pode ser vista na Figura 2. mente coletar dados, treinar modelos, avaliar o desempenho e implantar os modelos em dispositivos embarcados [27]. A Figura 3 apresenta um fluxo de trabalho de aprendizado de máquina que pode ser realizado na plataforma Edge Impulse.…”

Embedded Machine Learning System for Muscle Patterns Detection in a Patient with Shoulder Disarticulation

“…Additionally, Edge Impulse has developed applications in monitoring the operational condition of industrial equipment, enabling timely maintenance detection. In this context, the use of inertial sensors has resulted in an accuracy of 99.87% [ 31 ]. Another documented application involves the utilization of surveillance cameras to identify suspicious activities, triggering alarms in response to the detection of abnormal behavior [ 32 ].…”