Identifying catalyst layer compositions of proton exchange membrane fuel cells through machine-learning-based approach. (1st September 2022)

• Record Type: Journal Article
• Authors: Jienkulsawad, P.; Wiranarongkorn, K.; Chen, Y.S.; Arpornwichanop, A.
• Is Part Of: International journal of hydrogen energy. Volume 47:Number 75(2022)
• Page Start: 32303
• Page End: 32314
• Publication Date: 2022-09-01
• Subjects: Proton exchange membrane fuel cell -- Low humidity operation -- Machine learning -- Classification -- Prediction; Hydrogen as fuel -- Periodicals; Hydrogène (Combustible) -- Périodiques; Hydrogen as fuel; Periodicals; 665.81
• DOI: 10.1016/j.ijhydene.2022.07.126
• Languages: English
• ISSNs: 0360-3199

Abstract

Abstract: Membrane electrode assembly (MEA) is considered a key component of a proton exchange membrane fuel cell (PEMFC). However, developing a new MEA to meet desired properties, such as operation under low-humidity conditions without a humidifier, is a time- and cost-consuming process. This study employs a machine-learning-based approach using K-nearest neighbor (KNN) and neural networks (NN) in the MEA development process by identifying a suitable catalyst layer (CL) recipe in MEA. Minimum redundancy maximum relevance and principal component analysis were implemented to specify the most important predictor and reduce the data dimension. The number of predictors was found to play an essential role in the accuracy of the KNN and NN models although the predictors have self-correlations. The KNN model with a K of 7 was found to minimize the model loss with a loss of 11.9%. The NN model constructed by three corresponding hidden layers with nine, eight, and nine nodes can achieve the lowest error of 0.1293 for the Pt catalyst and 0.031 for PVA as a good additive blending in the CL of the MEA. However, even if the error is low, the prediction of PVA seems to be inaccurate, regardless of the model structure. Therefore, the KNN model is more appropriate for CL recipe prediction. Graphical abstract: Image 1 Highlights: A machine learning model was developed to identify catalyst layer compositions. Predictor numbers play a role in achieving high model accuracies. Existing predictors can be transformed into new predictors in classification. The classification model is more suitable for catalyst layer recipe identification.