Use of Machine Learning-Based Health Index With K-Nearest Neighbors Method to Maintain Desalination Plant Performance Gas and Steam Power Plants Applications

Udi Harmoko; Marcelinus  Christwardana; Muhammad  Rizkan

doi:10.59888/ajosh.v3i7.549

Authors

Udi Harmoko Faculty of Science and Mathematics, Universitas Diponegoro
Marcelinus Christwardana Faculty of Science and Mathematics, Universitas Diponegoro
Muhammad Rizkan School of Postgraduate Studies, Universitas Diponegoro

DOI:

https://doi.org/10.59888/ajosh.v3i7.549

Keywords:

Machine learning, K-Nearest Neighbors (K-NN), desalination plant, predictive maintenance, power plant efficiency

Abstract

This study presents the implementation of a Machine Learning-Based Health Index utilizing the K-Nearest Neighbors (K-NN) algorithm for predictive maintenance in desalination plants within gas and steam power plants. The research focuses on optimizing the maintenance schedule of the Block 3 Priok Desalination Plant, which is critical for providing high-quality distilled water for power generation. This study aims to develop and integrate a predictive maintenance framework into PLN’s digitization system, allowing for automated monitoring and optimized servicing schedules. Unlike the previous application of K-NN in Block 4, which utilized five health indices for performance classification, Block 3 requires an expanded model incorporating at least seven input parameters due to its multi-effect desalination process. By refining the predictive model and increasing data parameterization, this study seeks to enhance maintenance accuracy, minimize operational downtime, and improve overall desalination efficiency. By leveraging historical operational data and real-time monitoring, the K-NN model predicts the health index of desalination components with 98% accuracy. Implementing this approach minimizes downtime, optimizes maintenance schedules, and enhances energy efficiency. The results demonstrate that AI-driven predictive maintenance significantly improves reliability, reduces costs, and supports energy sustainability goals.

References

Afzal S, Ziapour MB, Shokri A, Shakibi H, Sobhani B (2023) 'Building Energy Consumption Prediction Using Multilayer Perceptron Neural Network-Assisted Models; Comparison of Different Optimization Algorithms', Energy, doi:10.1016/j.energy.2023.128446

Ahmadi G, Jahangiri A, Toghraei D (2023) 'Design Of Heat Recovery Steam Generator (HRSG) and Selection Of Gas Turbine Based on Energy, Exergy, Exergoeconomic, and Exergo-Environmental Prospects', Process Safety and Environmental Protection, 172(4)353-368

Amjad Z (1996) 'Scale Inhibition in Desalination Applications: An Overview', in The NACE International Annual Conference and Expositionhttps://www.lubrizol.com/-/media/Lubrizol/Water-Treatment/Documents/TEC-RO/NACE-96-230-Scale-Inhibition.pdf

Amonkar Y, Farnham DJ and Lall U (2022) 'A K-Nearest Neighbor Space-Time Simulator with Applications to Large-Scale Wind and Solar Power Modeling', Patterns, 3(3):100454–100454, doi:10.1016/j.patter.2022.100454

Anshori L, Regasari R and Putri M (2018) 'Implementation of the K-Nearest Neighbor Method for Study Interest Recommendations', Journal of Information Technology and Computer Science Development (J-PTIIK) Universitas Brawijaya, 2(7):2745–2753

Blanquero R, Carrizosa E, Cobo RP, Denamiel SRM (2021) ' Variable Selection for Naïve Bayes Classification', Computers & Operations Research, doi:10.1016/j.cor.2021.105456

Bwapwa JK, Mkhize N and Seyam M (2024) 'Evaluation of Operational Efficiency and Performance for a Water Treatment Plant', South African Journal of Chemical Engineering, (49)11-34, doi:10.1016/j.sajce.2024.04.003

Chahboun S and Maaroufi M (2021) 'Performance Comparison of K-Nearest Neighbor, Random Forest, and Multiple Linear Regression to Predict Photovoltaic Panels Power Output', in Advances on Smart and Soft Computing, 301–311, Springer Singapore, doi:10.1007/978-981-16-5559-3_25

Chen S, Webb IG, Liu L, Ma X (2020) ' A novel selective naïve Bayes algorithm', Knowledge-Based Systems, doi:10.1016/j.knosys.2019.105361

Cholil RS, Handayani T, Prathivi R, Ardianita T (2021) ' Implementation of the K-Nearest Neighbor (KNN) Classification Algorithm for Scholarship Recipient Selection Classification', Indonesian Journal on Computer and Information Technology, https://ejournal.bsi.ac.id/ejurnal/index.php/ijcit

Doninelli M, Morosini E, Gentile G, Putelli L, Marcoberardino DG, Binooti M, Manzolini G (2023) ' Thermal Desalination from Rejected Heat of Power Cycles Working With CO2-Based Working Fluids in CSP Application: A Focus on The MED technology', Sustainable Energy Technologies and Assessments, doi:10.1016/j.seta.2023.103481

Egorova AA and Kandyba KS (2022) 'Comparative Analysis of Anomaly Detection Algorithms for Development of the Unmanned Aerial Vehicle Power Plant Digital Twin', in The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Conference Proceedings, 6-9, Piscataway, doi:10.1109/TSCZh55469.2022.9802480

Eisenberg D, Soller J, Sakaji R and Olivieri A (2001) 'A Methodology to Evaluate Water and Wastewater Treatment Plant Reliability', In Water science and technology, 43(10):91–99, doi:10.2166/wst.2001.0589

Gufron H, Rusirawan D and Widyawati L (2022) 'Forecasting Energy Production of 1 kWp Solar Power Plant Using Machine Learning with Support Vector Machine Algorithm', Journal of Incentive Technology, 16(2):79-91, doi: https://doi.org/10.36787/jti.v16i2.843

Khordagui HK (1999) 'Desalination', in Environmental Geology, Encyclopedia of Earth Science, doi:10.1007/1-4020-4494-1_78

Levebvre HA and Ballal RD (2010) 'Gas Turbine Combustion Alternative Fouls and Emmision', International Standard Book, Number-13: 978-1-4200-8605-8

Li T, Tang JC, Yu JM, Cui D and Jiang D (2022) 'Reliability Analysis of Real Time Operation State of Power System Based on K-Nearest Neighbor', in IoT and Big Data Technologies for Health Care, (414):344–360 Springer International Publishing AG, Switzerland, https://link.springer.com/content/pdf/10.1007/978-3-030-94185-7_23?pdf=chapter%20toc

Liu Y (2009) 'On Equality of Ordinary Least Squares Estimator, Best Linear Unbiased Estimator and Best Linear Unbiased Predictor in the General Linear Model', Journal of Statistical Planning and Inference, 139(4):1522–1529, doi:10.1016/j.jspi.2008.08.015

Lopes AL, Machado PV, Rabelo LAR, Fernando SAR, Lima AVB, (2016) ' Automatic Labelling of Clusters of Discrete and Continuous Data with Supervised Machine Learning', Knowledge-Based Systems, 106: 231-241, doi:10.1016/j.knosys.2016.05.044

Manassaldi IJ, Mussati CM, Scenna JN, Morosuk T, Mussati S (2021) ' Process Optimization and Revamping of Combined-Cycle Heat and Power Plants Integrated With Thermal Desalination Processes', Energy 233, doi:10.1016/j.energy.2021.121131

Nguyen P and Tenno R (2017) ' Stochastic Evolution of Regulation Errors in a Boundary-Actuated Desalination Plant', Journal of Process Control, 54: 101-117, doi:10.1016/j.jprocont.2017.03.007

Pan H, Dou Z, Cai Y, Li W, Lei X and Han D (2020) 'Digital Twin and Its Application in Power System', in The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Conference Proceedings, 21-26, Piscataway, doi:10.1109/ICPRE51194.2020.9233278

Paryanto P, Indrawan H, Cahyo N, Simaremare A and Aisyah S (2020) 'Challenges Toward Industry 4.0: A Case Study of Power Plants in Indonesia', International Conference on Technology and Policy in Energy and Electric Power (ICT-PEP), 272-276, doi: 10.1109/ICT-PEP50916.2020.9249918

Polyzakis AL, Koroneos C and Xydis G (2008) 'Optimum Gas Turbine Cycle for Combined Cycle Power Plant', Energy Conversion and Management, 49(4):551–563, doi:10.1016/j.enconman.2007.08.002

Poulikas A (2004) 'Overview And Future Suistanable Gas Turbine Technologoies, in Renew Sustain Energy, 2004(9):409-43

Putri M, Widiarti, Nuryaman A and Warsono (2023) 'Application of the Vector Error Correction Model (VECM) in the Forecasting of Export Value Data and Import Value of All Commodities in Lampung Province in 2022', Journal of Siger Mathematics 04(02):67-75, doi:10.23960%2Fjsm.v4i2.12583

Rendalop PRO POMU (2012) 'Operation Work Instructions of Desalination Plant', PT. Indonesia Power PRO POMU

Sabry W (2018) 'From Distributed Generation to Virtual Power Plants: The Future of Electric Power Systems', in The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Conference Proceedings, 157-161, Piscataway, doi: 10.1109/MEPCON.2018.8635185

Saravanamutto HIH, Rogers GFC, Cohen H (2001) 'Gas Turbine Theory Fifth Edition', in Pearson Education in South Asia,

Sasakura (2012) 'Manual Book Desalination Plant Block 4 PRO POMU', Mitsubishi Heavy Industry, 201

Senter HF (2008) 'Applied Linear Statistical Models', Journal of the American Statistical Association, 103(482):880–880, doi:10.1198/016214508000000300

Shah A, Shah M, Pandya A, Sushra R, Ratnam S, Mehta M, Patel K and Patel K (2023) 'A Comprehensive Study on Skin Cancer Detection Using Artificial Neural Network (ANN) and Convolutional Neural Network (CNN)', Clinical Ehealth, 6:76–84, doi:10.1016/j.ceh.2023.08.002

Smith and Hinchcliffe RG (2004) 'RCM--Gateway to World Class Maintenance', Elsevier Science & Technology, ebookcentral.proquest.com/lib/monash/detail.action?docID=289011

Suwirmayanti NLGP (2017) 'Application of K-Nearest Neighbor Method for Car Selection Recommendation System', Techno. Com, 16(2), 120–131.

Tang Y, Jing L, Li H, & Atkinson PM (2016) 'A multiple-point spatially weighted k-NN method for object-based classification', International Journal of Applied Earth Observation and Geoinformation, 263–274, doi: 10.1016/j.jag.2016.06.01

PT Indonesia Power Big Data Team (2022) 'Handbook REOC – PI Vision', PT. Indonesia Power

Wang P, Fan E, Wang P (2021) 'Comparative Analysis of Image Classification Algorithms Based on Traditional Machine Learning and Deep Learning', Pattern Recognition Letters, 141: 61-67, doi:10.1016/j.patrec.2020.07.042

Wang Y, Wang Y, Ding Y, Zhou Y and Zhang Z (2019) 'A Fast Load-Shedding Algorithm for Power System based on Artificial Neural Network', International Conference on IC Design and Technology (ICICDT), 1-4, doi: 10.1109/ICICDT.2019.8790851

Widiastuti IN and Susanto R (2014) 'A Study of the Monitoring System of Unikom Informatics Engineering Accreditation Documents', Unikom Scientific Journal, 12(1):195-202

Vico FJ and Sandoval F (1992) 'Neural Networks Definition Algorithm', Microprocessing and microprogramming, 34(1):251–254, doi:10.1016/0165-6074(92)90145-W

Yu J, Zhang G, Yang Q, Zhang H, Liu M, Xu G (2024) ' Analytical Solution and its Application for The Dynamic Characteristics of A Heat Recovery Steam Generator in Gas–Steam Combined Cycle, Applied Thermal Engineering, doi:10.1016/j.applthermaleng.2023.122170

Zhao Z, Alzubaidi L, Zhang J, Duan Y, Gu Y (2024) ' A Comparison Review of Transfer Learning and Self-supervised Learning: Definitions, Applications, Advantages and Limitations', Expert Systems with Applications, doi:10.1016/j.eswa.2023.122807