Plant Maintenance Research Articles

Hazard Identification and Risk Assessment During Simultaneous Operations in Industrial Plant Maintenance Based on Job Safety Analysis

The risk of accidents during simultaneous operations (SIMOPS) in plant maintenance has been increasing. However, research on methods to prevent such accidents has been limited. This study aims to develop a novel framework, hazard identification and risk assessment of simultaneous operations (HIRAS), for identifying and evaluating potential hazards during concurrent tasks. The framework developed herein is expected to be an effective safety management tool that can help prevent accidents during these operations. To this end, the job location and hazard information in job safety analysis (JSA) were standardized into four attributes. The standardized information was then synchronized spatially and temporally to develop a HIRAS model that identifies and assesses the impact of hazards between operations. The model was tested using 40 JSA documents corresponding to maintenance operations at Company P, a South Korean steel-making company. The model was tested in two scenarios: one with planned operations and the other with unplanned operations in addition to planned operations. The performance evaluation results of the first scenario showed an F1-score of 98.33%. In this case, a recall of 97.52% means that the model identified 97.52% of the hazard-inducing factors. The second scenario was compared with the results of a review by six subject matter experts (SMEs). The comparison of the results identified by the SMEs and the model showed an accuracy of 89.3%. This study demonstrates the potential of JSA, which incorporates the domain knowledge of workers and can be used not only for individual tasks but also as a safety management tool for surrounding operations. Furthermore, by improving the plant maintenance work environment, it is expected to prevent accidents, protect workers’ lives and health, and contribute to the long-term sustainable management of companies.

Advancing photovoltaic panel temperature forecasting: A comparative study of numerical simulation and machine learning in two types of PV power plant

Photovoltaic (PV) panel temperature dynamic monitoring and forecasting is important for managing and maintaining of PV power plant. However, it is uncommon to use a variety of methods to predict and evaluate the panel temperature of different types of PV power plants. Therefore, this study aims to advance PV panel temperature forecasting through a comparative analysis of numerical simulation and machine learning models in two types of PV power plants: land- and water-mounted. The results indicate that PV panel temperature condition for two types of PV power plants can be well captured by the numerical simulation (NS) and machine learning, except for the NS in water-mounted PV power plant (R2 with 0.66). Models perform better in land-mounted PV power plants, with Random Forest Regression (RFR) and ResNet models demonstrating superior accuracy across both environments. While all models exhibit some degree of deviation from normal distribution in residuals, RFR and ResNet show the least deviation and lowest prediction errors, highlighting their robustness in forecasting PV panel temperatures. This study can provide valuable insights for predicting PV panel temperatures and for the management and maintenance of PV power plants.

A Novel Ultrasonic Leak Detection System in Nuclear Power Plants Using Rigid Guide Tubes with FCOG and SNR.

Leak detection in nuclear reactor coolant systems is crucial for maintaining the safety and operational integrity of nuclear power plants. Traditional leak detection methods, such as acoustic emission sensors and spectroscopy, face challenges in sensitivity, response time, and accurate leak localization, particularly in complex piping systems. In this study, we propose a novel leak detection approach that incorporates a rigid guide tube into the insulation layer surrounding reactor coolant pipes and combines this with an advanced detection criterion based on Frequency Center of Gravity shifts and Signal-to-Noise Ratio analysis. This dual-method strategy significantly improves the sensitivity and accuracy of leak detection by providing a stable transmission path for ultrasonic signals and enabling robust signal analysis. The rigid guide tube-based system, along with the integrated criteria, addresses several limitations of existing technologies, including the detection of minor leaks and the complexity of installation and maintenance. By enhancing the early detection of leaks and enabling precise localization, this approach contributes to increased reactor safety, reduced downtime, and lower operational costs. Experimental evaluations demonstrate the system's effectiveness, focusing on its potential as a valuable addition to the current array of nuclear power plant maintenance technologies. Future research will focus on optimizing key parameters, such as the threshold frequency shift (Δf) and the number of randomly selected frequencies (N), using machine learning techniques to further enhance the system's accuracy and reliability in various reactor environments.

Economic Overhaul Mode of Steam Engine Professional Equipment in Thermal Power Plant

To ensure that the daily production activities of thermal power plants can produce their due effect in the production and business activities, it is necessary to carry out efficient and orderly maintenance work on the professional equipment of steam engines. However, the maintenance work of steam engine professional equipment in thermal power plants usually uses high-cost expenditures. Therefore, how to take effective measures to reduce the cost of professional equipment maintenance in thermal power plants has become a problem that needs to be solved before such maintenance can proceed. Among them, through the application of economic maintenance equipment in thermal power plants, the actual production and operation costs can be effectively reduced. Based on this, the author will analyze the application of the model of economic maintenance of steam engine professional equipment in thermal power plants.

Foliar solution hydrophobicity influenced by plant species, product, and concentration

AbstractFoliar application of nutrients and pesticides is a popular practice for plant maintenance and weed control. Understanding how different products and adjuvants interact with the intended plant leaf surface will improve uptake and decrease losses. Various fertilizer, adjuvant, and pesticide solutions were tested to determine solution hydrophobicity on St. Augustinegrass, tall fescue, and white clover. A 1 µL droplet of each solution was placed on the adaxial leaf surface and imaged with a stereomicroscope to determine average solution contact angle. For all solutions groups, plant species had the most consistent effect, with white clover having the highest average contact angle followed by St. Augustinegrass and tall fescue, respectively. All product solutions significantly reduced the average contact angle compared to water. The urea solution resulted in the largest decrease for the fertilizer group at 7.6%. The largest decrease was found with the siloxane nonionic surfactant, which resulted in a decrease of 87.5% compared to water alone. Significant interactions were found between plant species and product solutions, indicating product solutions interact differently dependent upon the leaf surface characteristics. The results suggest that plant leaf surface, product solution and concentration, and their combination should be accounted for to increase wettability of a foliar application and improve product absorption.

Daya Saing Kacang Mete Indonesia Di Pasar Negara Tujuan Ekspor

Cashew nuts (Anacardium occidentale) are a leading plantation commodity with high economic value, essential for the development of the agricultural industry. Despite their significant potential as an export commodity, the export value of Indonesian cashew nuts has tended to decline during the period from 2013 to 2022. The aim of this study is to measure the competitiveness and development position of Indonesian cashew nuts from 2013 to 2022 in export destination countries. The data used in this research are secondary data in the form of time series data. The time series data includes annual data over 10 years (2013-2022) with export destination countries being Vietnam, India, Malaysia, Singapore, Sri Lanka, Japan, and China. The methods used in this study are the Revealed Comparative Advantage (RCA), Export Product Dynamics (EPD), and X-Model Potential Export Product methods. The results of the study show the Revealed Comparative Advantage (RCA) and Export Product Dynamics (EPD) values of Indonesian cashew nuts for the period 2013-2022 in the Vietnamese market with an RCA of 4.47 and a Lost Opportunity market position, India at 0.88 with a Retreat status, Singapore at 0.019 with a Falling Star status, Malaysia at 0.43 with a Lost Opportunity status, Sri Lanka at 21.55 with a Falling Star status, Japan at 7.36 with a Falling Star status, and China at 0.21 with a Rising Star market position. Meanwhile, the X-Model analysis shows that the market potential in Vietnam, Singapore, Sri Lanka, Japan, and Malaysia is classified as potential markets, the market potential in China is classified as an optimistic market, and the market potential in India is classified as a less potential market. As an export commodity, cashew nuts require proper handling and special attention. To ensure the quality, selling value, and strong competitiveness of cashew nuts, the government must continuously strive to enhance the selling value of cashew nuts through plantation development, garden and plant maintenance, and processing improvements.

Smartphone Usage Behavior And Technology Acceptance In Oil Palm Replanting

Replanting activities need support using information technology so that plantation business actors can access information related to plantations independently and accurately. This research analyzes smartphone usage behavior using a technology acceptance model approach among oil palm users. This research was conducted at the Karya Dharma III Village Unit Cooperative, Keranji Guguh Village, Koto Gasib District, Siak Regency. The sample taken in this research was 30 planters. The sampling technique in this research uses a snowball sampling technique, which is obtained through a rolling process based on the relationship between one respondent and another. Snowball sampling is a sampling method that uses initial illustration data to identify other illustrations that meet the criteria. Data analysis was carried out using a descriptive study based on a Likert scale. The final results of this research show that using smartphones among oil palm planters in Keranji Guguh Village as a medium to help search for and receive information for oil palm planters is classified as moderate, with an average score of 2.84. Smartphone use has become an alternative media planters use to search for information on supporting oil palm rejuvenation activities, land clearing, planting spacing patterns, using superior seeds, and plant maintenance replanting.

Short-Term Growth Dynamics of Spontaneous and Planted Vegetation on Subtropical Extensive Green Roof as Renaturalized Biotope

Spontaneous vegetation within a managed green space is often regarded as unwelcoming and insignificant weeds. This perception is still deep-rooted among green-space managers and the general public worldwide; they are generally uncertain about the management needs after allowing these groups of flora to take root. The short-term growth dynamics of both spontaneous and planted vegetation should be analyzed, and a widely acceptable, feasible management plan to balance aesthetic and ecological functions should be formulated with the backing of data and analysis for such fast-growing flora in tropical and subtropical regions. A manicured, extensive green roof with only seven (two native, five exotic) plant species was transformed into a renaturalized biotope by replacing 15 native ferns and forb species over 15 months. After planting, a baseline plant survey was conducted, with 54 plant species representing spontaneous growth and 14 planted species alive (7 planted native species survived, plus 7 species planted prior to renaturalization revived). Three quarterly plant surveys recorded the cover-abundance of each species, and the growth dynamics of the planted and spontaneous plant species were evaluated over the first year of study. During each quarterly survey, the number of planted and spontaneous plant species remained stable (ranging from 14 to 16 species and 51 to 54 species, respectively), with a constant turnover of 11 to 12 die-out species and 11 to 12 newly colonized or revived species. Plant coverage of different plant forms fluctuated slightly (within 7%) in the quarterly surveys according to seasonal changes, except for ferns, which outperformed (12% increase in coverage in a year) all the other plant forms. The height of the planted vegetation fluctuated in a year, being shorter during the summer, while the height of spontaneous vegetation remained stable throughout the year, exhibiting resilience to scouring heat. The seasonal growth tendencies of both planted and spontaneous plants were illustrated in relation to their species ranks, and further hierarchical cluster analysis was conducted for the clustering of spontaneous species. Their differential growth patterns provided comprehensive information or supported decisions regarding plant selection and maintenance, which is a scientific novelty within this unexplored topic. Management recommendations based on the findings were suggested to fulfill both aesthetic and ecological needs. Species with stable and less stable growth patterns could be useful to meet maintenance efficiency and biodiversity enhancement needs, respectively. These findings provide insights to form guiding principles for choosing plant species for renaturalization projects.

Explainable, Deep Reinforcement Learning–Based Decision Making for Operations and Maintenance

This paper presents research that integrates condition monitoring and prognostics with decision making for nuclear power plant operations and maintenance aimed at reducing lifetime maintenance and repair costs. Additionally, a focal point of this research is to make the decisions explainable to operators, improving the trustworthiness of the decisions from what can be considered a black box model. In this work, we develop and evaluate an explainable, online asset management methodology to help reduce lifetime maintenance and repair costs. Using the latest advancements in condition monitoring, inventory management, deep reinforcement learning, and explainable artificial intelligence methods, we create a predictive maintenance methodology that can optimize the maintenance and spare part management of a repairable nuclear power plant system. To demonstrate these methods, preliminary studies were conducted on a representative maintenance system undergoing a stochastic degradation process that requires repairs or replacement to continue operation. Using deep reinforcement learning, we were able to reduce maintenance spending by approximately 50% compared to optimized, time-based maintenance strategies for the chosen system. A key component of our methodology is the integration of Shapley values to quantify the contribution of various factors to the decision-making process. This addition enhances the explainability and trustworthiness of our decisions, providing operators with transparent and understandable insights into the rationale behind maintenance strategies. The robustness and resiliency of our decision policy against observation noise were also thoroughly evaluated, demonstrating its effectiveness in uncertain operational environments.

Robots for the Energy Transition: A Review

The energy transition relies on an increasingly massive and pervasive use of renewable energy sources, mainly photovoltaic and wind, characterized by an intrinsic degree of production uncertainty, mostly due to meteorological conditions variability that, even if accurately estimated, can hardly be kept under control. Because of this limit, continuously monitoring the operative status of each renewable energy-based power plant becomes relevant in order to timely face any other uncertainty source such as those related to the plant operation and maintenance (O&M), whose effect may become relevant in terms of the levelized cost of energy. In this frame, the use of robots, which incorporate fully automatic platforms capable of monitoring each plant and also allow effective and efficient process operation, can be considered a feasible solution. This paper carries out a review on the use of robots for the O&M of photovoltaic, wind, hydroelectric, and concentrated solar power, including robot applications for controlling power lines, whose role can in fact be considered a key complementary issue within the energy transition. It is shown that various robotic solutions have so far been proposed both by the academy and by industries and that implementing their use should be considered mandatory for the energy transition scenario.

Offshore Wind Power: Progress of the Edge Tool, Which Can Promote Sustainable Energy Development

Offshore wind is renewable, clean, and widely distributed. Therefore, the utilization of offshore wind power can potentially satisfy the increasing energy demand and circumvent the dependence on fossil energy. Thus, offshore wind power is an edge tool for achieving sustainable energy development because of its potential in large-scale energy supply and its important role in reducing environmental pollution as well as carbon emission brought by fossil energy. The worldwide development of offshore wind power has entered the era of large-scale research and commercial application. It displays a trend of rapid development, continuous technological breakthroughs, and high-speed market growth. This article systematically introduces the structural components and technical characteristics of offshore wind power. Moreover, the current developmental status of offshore wind power is summarized. By reviewing the current development and application status of offshore wind power technology worldwide, large wind turbines and fixed and floating offshore wind power technologies are analyzed. Additionally, the development of the offshore wind energy market is overviewed. The policy condition and key aspects such as the construction, operation, and maintenance of offshore wind power plants are also summarized. Finally, the prospective challenges and development trends of offshore wind power and its significance in achieving sustainable society development are proposed. We consider that the article can provide reference and inspiration for researchers and developers dedicated to offshore wind power.

An approach for modern gardening through monitoring and maintenance of plant health

The study explores the use of internet of things (IoT) devices in agriculture to improve sustainable practices and environmental concerns. It uses the ESP8266 microcontroller and the Blynk platform to create a revolutionary plant health monitoring and automated care system. The system is designed to handle continuous monitoring and plant maintenance in various environmental conditions. Sensors measuring light, temperature, humidity, and soil moisture are strategically placed to receive real-time data. The ESP8266 microcontroller analyzes this information and links it to the Blynk cloud for accessibility via mobile or web applications. The system is effective in monitoring ideal growing conditions, such as soil moisture and weather conditions. Automated care elements like irrigation and supplemental lighting have been shown to improve plant growth and health. The study contributes to smart farming by offering an affordable and easy way to automate and monitor plant health, demonstrating how IoT technologies can enhance agricultural practices, conserve resources, and enable remote management of plant ecosystems.

A lightweight joint metric detection approach on YOLO for hot spots in photovoltaic modules

The hot spot effect is one of the primary causes of damage to photovoltaic (PV) modules and a significant factor contributing to the decline in their power generation capacity. Thermal imaging inspection of PV modules is an indispensable aspect of PV plant operation and maintenance. This article introduces a lightweight detection algorithm for hot spots in PV modules based on an enhanced version of YOLOv8. The algorithm incorporates a lightweight convolution operator, Volumetric Grid Spatial Cross Stage Partial, as a replacement for the original C2f operator, resulting in effective reduction of the model's parameter size and improved detection speed. Additionally, the Content-Aware ReAssembly of FEatures upsampling operator is utilized instead of the nearest-neighbor algorithm during the upsampling process, thereby minimizing the loss of hot spot feature information. Furthermore, a joint metric approach combining the Complete Intersection over Union metric and the normalized Wasserstein distance metric is proposed to calculate the localization loss of the target bounding boxes, thereby enhancing the regression accuracy of small hot spot prediction boxes. Experimental results demonstrate that the improved YOLOv8 network enables fast and accurate detection of hot spots. This method achieves an impressive average precision of 98.8% and a high detection speed of 218.3 fps.

A giant gardener of the Floodplains: The Amazonian manatee

During an unusual event of extreme drought and rainfall scarcity in the Amazon in October 2023, we found 96 feces of the Amazonian manatee on the beaches of Lake Amanã (Central Amazon, Brazil). All feces contained seeds and some of them seedlings of aquatic herbaceous species, offering the opportunity to study the role of the manatee as an endozoochoric dispersal agent in the Amazonian floodplains. The feces were collected, analyzed, and the intact seeds were separated, identifying 9 morphotypes of aquatic herbaceous plants. Whole seeds were sectioned and immersed in a tetrazolium solution to assess viability of the embryos. The seeds of the species Luziola spruceana were present in all fecal samples. In 17 feces, 79 seedlings of L. sprucena, Eleocharis subarticulata, Bacopa egensis, Cyperus blepharoleptos, and Cyperus sp. were observed. The Amazon manatee migrates annually between different types of floodable environments due to the rise and fall of water levels. In these two phases of the hydrological cycle there is the availability of fruiting aquatic herbaceous plants on which it feeds. In this way, the Amazonian manatee can be considered a gardener of the Amazon floodplains, as it fertilizes the waters with nutrients that favor plant productivity and acts in the dispersal, colonization and plant succession in these environments. This fact opens a range of research opportunities and considerably elevates the importance of the manatee in the maintenance and diversity of aquatic plants, as well as in maintaining the balance of trophic chains in its living areas.

Assessing PV inverter efficiency degradation under semi-arid conditions: A case study in Morocco

The worldwide shift towards renewable energy sources, including solar and wind, is progressing rapidly. This change is driven by decreasing prices and technical advancements that are becoming more centralized. The objective is to develop a cutting-edge approach and technology that seamlessly incorporates photovoltaic (PV) energy sources into a power network while ensuring grid stability. This research evaluates the lifetime and degradation of PV inverters under real operating conditions, focusing on semi-arid climate scenarios. Current papers demonstrate a yearly failure rate of 1–15% for PV inverters, highlighting the need for a thorough reliability evaluation. This investigation research applied a unique technique that included continuous monitoring of PV inverter performance parameters by comparing the measured with the predicted normal operating output. The results show that Sandia's inverter performance model is highly suitable for accurately modeling normal PV inverter behavior. Furthermore, weighted efficiency dropped by 3.96%, 0.63% and 1.29% respectively for 7kW, 15kW and 20kW photovoltaic systems over the five years. These findings have implications for comprehensive maintenance strategies, including regular inspections, safety protocols, and remote monitoring solutions. Ultimately, this research paper sheds light on the causes of declining solar inverter performance and provides suggestions for enhancing PV plant maintenance and reliability. It also represents an outstanding reference given the literature shortage.

An estimation method for bias error of measurements by utilizing process data, an incidence matrix and a reference instrument for data validation and reconciliation: Part 2 Extension to the energy balance relation

Abstract Ensuring data reliability is becoming increasingly important for further applications of AI, IoT, and digital twins. One promising technology for ensuring data reliability is data validation and reconciliation (DVR), which minimizes the uncertainty of measurements based on statistics. DVR has been widely used for the operation and maintenance of nuclear power plants in Europe and the United States in recent years. The most important input for DVR analysis is measurement uncertainty. The catalog value provided by sensor manufacturers includes the measurement uncertainty, but in reality, the actual measurement uncertainty is often smaller. Previous studies have proposed several methods for evaluating the actual measurement uncertainty based on process data, which have been confirmed to be effective for evaluating random errors. It is important to note that bias errors also contribute significantly to the measurement uncertainty. In our previous paper, we proposed a method for estimating bias error using process data, an incidence matrix, and a reference instrument. The proposed method was limited to a mass balance relation, i.e., flow rate measurements. In this paper, we extend the method to include an energy balance relation by considering energy conservation in addition to mass conservation. This extension enables the evaluation of measurement uncertainty for flow rate and temperature. The proposed method was validated with two benchmark problems. It was found to be applicable to various flow conditions, including physically fluctuating flow, such as that observed in the feedwater flow in nuclear power plants.

Optimizing Asset Management: Comprehensive Analysis and Innovative Strategy Design to Increase the Effectiveness of Life Cycle Delivery at PT Pembangkitan Jawa-Bali Services

Asset management is the art and science of making the right decisions and optimizing the delivery of value from organizational assets. ( Institute of Asset Management , 2010). PT PLN Pembangkitan Jawa Bali Services, which is often abbreviated as PT PJB Services, is a subsidiary of PT Pembangkitan Jawa-Bali (PT PJB) . This company operates in the field of power plant operation and maintenance services, as well as supporting services related to power plants. The company has a strong focus on asset management, given its role in managing and maintaining critical power generation assets. This research examines the implementation of multidimensional strategies in optimizing asset management at PT Pembangkitan Jawa-Bali Services (PJB Services). The main focus of the analysis is to test the variables that influence the success of asset performance at PT Pembangkitan Jawa Bali Services based on group 3 ( Life Cycle Delivery ) consist of 11 key dimensions of asset management: Technical Standards & Legislation , Asset Creation & Acquisition , Systems Engineering , Configuration Management , Maintenance Delivery. Reliability Engineering, Asset Operation, Resource Management, Shutdown & Outage Management, Fault & Incident Response, Asset Decommissioning & Disposal. The main aim of the research is to design an integrated approach to improve the effectiveness of corporate asset management. The method used in this research is the Structural Equation Model with the Partial Least Square approach. The research results revealed that the accepted hypothesis is H1, H2, H3, H4, H9, H10, H12, H16, H17, H18, and H19 are acceptable because they have t-statistic values > 1.96 and p-values < 0.05. Meanwhile, the hypotheses H5, H6, H7, H8, H11, H13, H14, and H15 were rejected because they had t-statistic values > 1.96 and p-values > 0.05.

Role of Indian power markets in energy transition

India's power sector is transforming rapidly, marked by rising demand and a growing share of renewables. The short-term power market provides option for power distribution utilities to meet demand exigency. The paper presents trends and perspectives of short-term electricity trading of select states of India. Market transactions reflect seasonal demand variations, higher during summer-monsoon months, dipping in winters. Analysis of data highlights substantial share of short-term power in the total procurement. Quantum of power traded correlates inversely with operational performance of thermal plants as well as grid share of renewable energy. Suggested policy measures include honing of demand forecasting skills using advanced metering infrastructure, deploying energy storage technologies, including decentralized solar, ensuring sustained supply of coal and preventive maintenance of thermal power plants, initiating seasonal procurement contracts with merchant power plants, encouraging power banking arrangements and including storage component in solar and wind tenders. Power markets, if employed appropriately, can help minimize the demand-supply gap, facilitate energy access, and accommodate higher quantum of green power, thus fulfilling SDG-7 targets.

The Mechanism of the Development and Maintenance of Sexual Dimorphism in the Dioecious Mulberry Plant (Morus alba).

Intersexual differentiation is crucial for the speciation and maintenance of dioecious plants, but the underlying mechanisms, including the genes involved, are still poorly understood. Here, we focused on a typical dioicous plant Morus alba, to explore the molecular footprints relevant to sex evolution by revealing the differentially expressed genes (DEGs) between two sexes and the testing signals of selection for these DEGs. From the results, we found a total of 1543 DEGs. Interestingly, 333 and 66 genes expression were detected only in male and female inflorescences, respectively. Using comparative transcriptomics, the expression of 841 genes were found to be significantly higher in male than in female inflorescences and were mainly enriched in defense-related pathways including the biosynthesis of phenylpropanoids, cutin, suberine and waxes. Meanwhile, the expression of 702 genes was female-biased and largely enriched in pathways related to growth and development, such as carbohydrate metabolism, auxin signaling and cellular responses. In addition, 16.7% and 17.6% signals of selection were significantly detected in female- and male-biased genes, respectively, suggesting their non-negligible role in evolution. Our findings expanded the understanding of the molecular basis of intersexual differentiation and contribute to further research on sex evolution in dioecious plants.

Predictive modeling of combined cycle power plant performance using a digital twin-based neural ODE approach

This study presents a novel digital twin-based predictive modeling approach to enhance the operation, maintenance, and management of combined cycle power plants. The research aimed to accurately forecast the combined cycle power (CCP) output, a critical performance indicator, to support intelligent decision-making for plant operators and engineers. The proposed framework leverages a neural ordinary differential equation (NODE) model integrated within a digital twin architecture to capture the complex, nonlinear dynamics of combined cycle gas turbine unit (CCGU) system. The predictive model was trained and validated using multivariate time-series data collected from a CCGU, achieving high accuracy with an R2_score of 0.993, a mean absolute percentage error of 0.325 %, and a root mean squared error of 1.518. Importantly, the NODE model demonstrated superior forecasting capabilities compared to traditional machine learning techniques. The digital twin (DT) concept enables seamless real-time data integration, physics-based models, and advanced data analytics to facilitate comprehensive CCGU lifecycle management. This novel approach provides operators with reliable, real-time insights to optimize plant performance, reduce maintenance costs, and improve overall sustainability. The generalization of the NODE model to an independent CCGU unit validated its applicability across diverse power plant configurations, highlighting the originality and practical value of the research. The key contribution of this work is the development of a digital twin-based predictive modeling framework centered on the innovative use of neural ordinary differential equations to enhance the operation and maintenance of critical energy infrastructure. This research advances the state-of-the-art in intelligent asset management for the built environment.