electronics Article An Explainable DL-Based Condition Monitoring Framework for Water-Emulsified Diesel CR Systems Ugochukwu Ejike Akpudo and Jang-Wook Hur *   Citation: Akpudo, U.E.; Hur, J.-W. An Explainable DL-Based Condition Monitoring Framework for Water-Emulsified Diesel CR Systems. Electronics 2021, 10, 2522. https:// doi.org/10.3390/electronics10202522 Academic Editors: Paolo Castaldi and Silvio Simani Received: 23 August 2021 Accepted: 12 October 2021 Published: 15 October 2021 Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affil- iations. Copyright: © 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https:// creativecommons.org/licenses/by/ 4.0/). Department of Mechanical Engineering (Department of Aeronautics, Mechanical and Electronic Convergence Engineering), Kumoh National Institute of Technology, 61 Daehak-ro (yangho-dong), Gumi 39177, Korea; akpudougo@gmail.com * Correspondence: hhjw88@kumoh.ac.kr Abstract: Despite global patronage, diesel engines still contribute significantly to urban air pol- lution, and with the ongoing campaign for green automobiles, there is an increasing demand for controlling/monitoring the pollution severity of diesel engines especially in heavy-duty industries. Emulsified diesel fuels provide a readily available solution to engine pollution; however, the inher- ent reduction in engine power, component corrosion, and/or damage poses a major concern for global adoption. Notwithstanding, on-going investigations suggest the need for reliable condition monitoring frameworks to accurately monitor/control the water-diesel emulsion compositions for inevitable cases. This study proposes the use of common rail (CR) pressure differentials and a deep one-dimensional convolutional neural network (1D-CNN) with the local interpretable model- agnostic explanations (LIME) for empirical diagnostic evaluations (and validations) using a KIA Sorento 2004 four-cylinder line engine as a case study. CR pressure signals were digitally extracted at various water-in-diesel emulsion compositions at various engine RPMs, pre-processed, and used for necessary transient and spectral analysis, and empirical validations. Results reveal high model trustworthiness with an average validation accuracy of 95.9%. Keywords: common rail; fault detection and isolation; water-emulsified diesel fuel; condition monitoring; convolutional neural network 1. Introduction For several decades, diesel engines have served profitably for high-power energy/power generation across industries, and with several innovations, their cost efficiency, output optimization, and process design/control have significantly improved [1–3]. On the down- side, the emissions from these engines contain high amounts of harmful compounds— nitrogen oxides (NOx), particulate matter (PM), and carbon monoxide (CO). These pollu- tants contribute nearly 30% of greenhouse effects and several health and environmental problems. Although an aggressive campaign is ongoing for renewable non-combustible energy sources; particularly for transportation, the necessary resources required for such a transition are yet to be fully harnessed on a global scale while the increasing energy demand still remain [2,4]. Studies on the Asia–Pacific and European regions suggest there will be a 75% increase in energy demand for transportation by 2040. This also suggests there would be an 85% increase in demand for heavy-duty diesel fuels and a 10% decrease in demand for gasoline fuels [5]. The impact of fuel quality on combustion engine efficiency, power, and durability can- not be overemphasized; however, there is a need to minimize the amount of pollution while maintaining engine efficiency [6,7]. A common, cost-efficient, and reliable emission control method for diesel engines is the use of water-in-diesel emulsified fuels. This is because the physio-chemical properties of emulsion fuels disfavours NOx, CO, and PM production— the major pollution-causing compounds. Nonetheless, the composition percentage of water by volume of diesel should be kept in check to avoid engine power losses, component Electronics 2021, 10, 2522. https://doi.org/10.3390/electronics10202522 https://www.mdpi.com/journal/electronics