Automatic detection of thermal anomalies in induction motors

The paper proposes a methodology based on Artificial Intelligence techniques for the automatic detection of abnormal thermal distributions in electric motors, to rapidly identify pre-faults or fault conditions. The proposed approach, applied to induction motors of different sizes, installed in waterworks plants, is based on the execution of Thermographic Non-Destructive Tests, which allow identifying abnormal operating conditions without interrupting the ordinary working conditions of the system. Thermographic images of induction motors are acquired at the installation site and with perspectives visible to the operator, which are sometimes partially obstructed. These thermographic images are automatically controlled using a Convolutional Neural Network, realized on an open-source framework. Thanks to the pre-processing techniques implemented by the authors, the system is capable to detect, rapidly and cost-effectively, specific patterns typical of an abnormal thermal distribution. The accuracy values achieved depend on the size of the overheating area and the method of image acquisition; they can be 100%.

Automated summary

The paper introduces a methodology based on Artificial Intelligence for automatically detecting abnormal thermal distributions in electric motors, allowing for rapid identification of pre-faults or fault conditions without interrupting the normal working conditions of the system. By using Thermographic Non-Destructive Tests and a Convolutional Neural Network, the system is able to detect specific patterns of abnormal thermal distribution. Accuracy values achieved can reach up to 100%, depending on the size of the overheating area and image acquisition method.