A deep-learning approach for predicting water absorption in composite pipes by extracting the material's dielectric features. (May 2023)

• Record Type: Journal Article
• Authors: Altabey, Wael A.; Noori, Mohammad; Wu, Zhishen; Al-Moghazy, Mohamed A.; Kouritem, Sallam A.
• Is Part Of: Engineering applications of artificial intelligence. Volume 121(2023)
• Publication Date: 2023-05
• Subjects: Artificial intelligence (AI) -- Deep learning (DL) -- Electrical capacitance sensor (ECS) -- Mass of liquid absorption (M% ) -- Laminated composite pipe -- Glass fiber reinforced epoxy (GFRE); Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2023.105963
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: Monitoring the mass of liquid absorption in laminated composite structures, that have a direct contact surface with working liquid-like pipes, is very important in order to prevent the sudden collapse of the structures because of the degradations in strength and mechanical properties over time. An electrical capacitance sensor technique has been applied for monitoring the mass of liquid absorption, over the time, in laminated composite pipelines by measuring the change of dielectric characteristics of composite pipelines subjected to an internal hydrostatic pressure load of water and thermal effect. Results show the technique is very effective. However, a major difficulty in utilizing this technique is that it is highly time consuming to be used for monitoring, in addition to the detection efforts that it requires to calculate the mass of liquid absorption that exerts high cost and loss of additional time in monitoring. In this paper, a deep neural network model is used to estimate the mass of liquid absorption in glass fiber reinforced epoxy laminated composite pipelines by extracting the features from datasets from experimental and numerical measurements of the electrical capacitance sensor. The experimental and numerical data used in this paper to train and test the new deep neural network model are collected from the literature and the finite element model of the electrical capacitance sensor system respectively. The results show an excellent agreement between the finite element model data, available experimental data, and those predicted by a deep neural network with an average error of 0.067%, and show that the proposed method achieves satisfactory performance with 86.34% accuracy, 82.83% regression rate and 83.74% F-score. The proposed approach overcomes the difficult problem of saving time and effort to accurately detect the mass of liquid absorption over the time, and provides a promising approach for a wider application of this intelligent model. Highlights: A FEM is established for monitoring the mass of water absorption over time (M%) of the composite pipeline. The M% of the composite pipeline is analyzed using the electrical capacitance sensor (ECS) technique. The ECS results are verified using a dataset of experimental work adapted from literature. Trained and tested the Convolutional Neural Network (CNN) by the electrical potential difference between ECS electrodes. The M% over time of composite pipeline is predicted and compared with the FEM outputs and available experimental results.