Forecasting of Energy Consumption for Anomaly Detection in Automated Guided Vehicles: Models and Feature Selection

Automated guided vehicles (AGV) provide a cost-efficient transportation method in smart industrial plants. Their continuous operation is crucial for production flow. However, while detection of typical failures, e.g., those related to battery voltage, can be performed in an automated manner, more complex scenarios require expert knowledge and human monitoring. In this paper, we evaluate recurrent neural network-based (RNN) energy consumption forecasting using other telemetry features. We aim to find models well suited for anomaly detection methods working on the analysis of error between forecasted and actual values. We compare the results of RNN architectures on our data and public vehicle energy datasets. We demonstrate that RNN-based forecasting, together with a proper selection of telemetry features used in prediction, can be effectively utilized on AGV telemetry data as a first step in anomaly detection schemes.