Minimal-Configuration Anomaly Detection for IIoT Sensors

TL;DR

This paper compares deep learning models like autoencoders, LSTMs, DNNs, and CNNs for anomaly detection in IIoT sensor data, demonstrating that a single model can detect anomalies across different operating conditions with minimal configuration.

Contribution

It introduces a preliminary approach towards a generic, minimal-configuration anomaly detection method applicable to diverse industrial equipment using deep learning.

Findings

Autoencoders and LSTMs effectively detect anomalies without feature engineering.

A single model can handle multiple operating conditions.

Initial results show promise for transferability across equipment types.

Abstract

The increasing deployment of low-cost IoT sensor platforms in industry boosts the demand for anomaly detection solutions that fulfill two key requirements: minimal configuration effort and easy transferability across equipment. Recent advances in deep learning, especially long-short-term memory (LSTM) and autoencoders, offer promising methods for detecting anomalies in sensor data recordings. We compared autoencoders with various architectures such as deep neural networks (DNN), LSTMs and convolutional neural networks (CNN) using a simple benchmark dataset, which we generated by operating a peristaltic pump under various operating conditions and inducing anomalies manually. Our preliminary results indicate that a single model can detect anomalies under various operating conditions on a four-dimensional data set without any specific feature engineering for each operating condition. We consider this work as being the first step towards a generic anomaly detection method, which is applicable for a wide range of industrial equipment.