Intelligent fault diagnosis of cooling radiator based on deep learning analysis of infrared thermal images. (25th December 2019)

• Record Type: Journal Article
• Authors: Nasiri, Amin; Taheri-Garavand, Amin; Omid, Mahmoud; Carlomagno, Giovanni Maria
• Is Part Of: Applied thermal engineering. Volume 163(2019)
• Publication Date: 2019-12-25
• Subjects: Cooling radiator -- Fault detection -- Thermal image analysis -- Deep learning -- Convolutional neural network; Heat engineering -- Periodicals; Heating -- Equipment and supplies -- Periodicals; Periodicals; 621.40205
• DOI: 10.1016/j.applthermaleng.2019.114410
• Languages: English
• ISSNs: 1359-4311

Abstract

Highlights: A deep learning model for intelligent fault diagnosis of radiator is proposed. Convolutional neural network is utilized for constructing the suggested model. Infrared thermal images are directly used as input to the modified CNN model. Classification accuracy of fault detection is 96.67%. Abstract: Detection of faults and intelligent monitoring of equipment operations are essential for modern industries. Cooling radiator condition is one of the factors that affects engine performance. This paper proposes a novel and accurate radiator condition monitoring and intelligent fault detection based on thermal images and using a deep convolutional neural network (CNN) which has a specific configuration to combine the feature extraction and classification steps. The CNN model is constructed from VGG-16 structure that is followed by batch normalization layer, dropout layer, and dense layer. The suggested CNN model directly uses infrared thermal images as input to classify six conditions of the radiator: normal, tubes blockage, coolant leakage, cap failure, loose connections between fins & tubes and fins blockage. Evaluation of the model demonstrates that leads to results better than traditional computational intelligence methods, such as an artificial neural network, and can be employed with high performance and accuracy for fault diagnosis and condition monitoring of the cooling radiator under various working circumstances.