Operational Failures Research Articles

Qualitative evaluation and corrective planning for centrifugal pump maintenance at Soekarno-Hatta airport

This study focuses on enhancing the maintenance processes of centrifugal pumps at Soekarno-Hatta Airport’s Water Treatment Unit in Indonesia, crucial for meeting the clean water needs of the airport, which served around 19.8 million passengers in 2022. Using a qualitative methodology, the research involved focus group discussions with the unit’s operators, technicians, and engineers to pinpoint maintenance challenges and devise solutions. Key findings reveal issues such as insufficient routine maintenance, unplanned repairs, and inadequate staffing, leading to operational disruptions and pump failures. The study highlights the role of Total Productive Maintenance (TPM) in reducing machine breakdowns and improving efficiency. It emphasizes the critical role of centrifugal pumps in the airport’s water supply system. The research proposes several corrective measures, adhering to the 5W + 1H framework, including regular lubrication, bearing replacements, hiring more staff, and advanced training on PLC systems. These actions aim to rectify immediate maintenance problems and establish a foundation for the long-term effectiveness of the pump systems. Conclusively, the study underscores the need for a comprehensive maintenance strategy that aligns with standard operating procedures and preventive maintenance. This approach is essential for boosting the operational performance and reliability of the Water Treatment Unit. It has broader implications for similar infrastructure facilities, underscoring the importance of efficient maintenance management.

An Innovative Honeypot Architecture for Detecting and Mitigating Hardware Trojans in IoT Devices

The exponential growth and widespread adoption of Internet of Things (IoT) devices have introduced many vulnerabilities. Attackers frequently exploit these flaws, necessitating advanced technological approaches to protect against emerging cyber threats. This paper introduces a novel approach utilizing hardware honeypots as an additional defensive layer against hardware vulnerabilities, particularly hardware Trojans (HTs). HTs pose significant risks to the security of modern integrated circuits (ICs), potentially causing operational failures, denial of service, or data leakage through intentional modifications. The proposed system was implemented on a Raspberry Pi and tested on an emulated HT circuit using a Field-Programmable Gate Array (FPGA). This approach leverages hardware honeypots to detect and mitigate HTs in the IoT devices. The results demonstrate that the system effectively detects and mitigates HTs without imposing additional complexity on the IoT devices. The Trojan-agnostic solution offers full customization to meet specific security needs, providing a flexible and robust layer of security. These findings provide valuable insights into enhancing the security of IoT devices against hardware-based cyber threats, thereby contributing to the overall resilience of IoT networks. This innovative approach offers a promising solution to address the growing security challenges in IoT environments.

Beyond the Ire of Flames: Work Experiences of Bureau of Fire Protection (BFP) Station Chiefs

Fire occurrences have significantly risen in recent years. These fires endanger lives, cause economic damage, and harm the environment. Uncontrolled fires are a major reason for building collapses and injuries. Building fires cause trauma due to the loss of belongings and the building itself. Existing fire safety systems are failing due to unaddressed factors causing building fires (Rathnayake et al., 2020). This study explored the experiences of the station chiefs of the Bureau of Fire Protection in Iloilo Province, Philippines, through a qualitative research method. The participants of this study were the selected ten (10) BFP station chiefs. All participants were subjected to an individual in-depth interview. The findings of this study are described in emergent themes. Six (6) emergent themes described the positive and negative experiences of the informants in the performance of their duties. For the positive experiences, two (2) emergent themes were developed, namely Personal Satisfaction Through Job Fulfillment and Workplace Camaraderie and Support. For the negative experiences, four (4) emergent themes were also developed, namely: Inadequate Resources and Financial Challenges, Complexity of Leadership and Personnel Management, Bombarded with Public Dissatisfaction, and Operational Delays and Equipment Failures. Meanwhile, three (3) emergent themes were formulated to explain how the participants address the challenges encountered in the performance of their duties, namely: Empowering Collaboration and Support Networks, Bolstering Preventive Measures and Education, and Embodying Resilience and Adaptability. Finally, three (3) emergent themes were created to express the aspirations of participants to improve the quality of their services, namely Continuous Training and Professional Development, Adequate Fiscal Allocation and Service Facilities, and Improvement of Personnel and Staffing Issues. Based on the emergent themes identified, it is recommended that the fire station chiefs be enhanced by providing them with specialized training and career development programs. This can be accomplished by the successful integration of the latest firefighting technologies in the specialized training to enhance the response effectiveness of their station.

Nanoparticle integration in adhesive and hybrid single lap joints: effect on strength and fatigue life under environmental aging

Examining the mechanical performance of CFRP and aluminum samples subjected to environmental aging is crucial. Additionally, it is essential to develop methods to enhance their mechanical properties. This research investigates the impact of fullerene and single-walled carbon nanotubes (SWCNT) on the fatigue life and static strength of bonded and bonded/bolted joints. The study focuses on composite-to-composite (CTC) and composite-to-aluminum (CTA) substrates under three-point bending, both before and after hygrothermal aging. The samples were divided into four categories: (1) neat specimens, (2) specimens with added fullerene, (3) specimens with added SWCNT, and (4) specimens with a combination of 50% SWCNT and 50% fullerene. The experimental results indicated that the optimal nanoparticle ratio for bonded joints differs from that for bonded/bolted joints. Adding nanoparticles to the adhesive increased the fatigue life of SLJs, particularly in samples containing mixed particles and SWCNT. In some cases, nanoparticles amplified the effect of hygrothermal conditions, enhancing fatigue life further. The integration of nanoparticles into the adhesive and the use of bonded/bolted joints significantly improved joint strength, with the combination of both techniques yielding the best results. These modified joints offer a promising alternative to traditional joints in terms of strength and fatigue life. The study enhances understanding of the aging of adhesive and hybrid joints, especially dissimilar joints (composite to metal), and provides insights into their behavior under various environmental aging conditions. These methods show potential for optimizing joints and composite structures, improving durability, and reducing the likelihood of operational failures.

Ultra-Small Copper-Based Multienzyme-Like Nanoparticles Protect Against Hepatic Ischemia-Reperfusion Injury Through Scavenging Reactive Oxygen Species in Mice.

Hepatic ischemia-reperfusion injury (IRI) is a severe complication that occurs in the process of liver transplantation, hepatectomy, and other end-stage liver disease surgery, often resulting in the failure of surgery operation and even patient death. Currently, there is no effective way to prevent hepatic IRI clinically. Here, it is reported that the ultra-small copper-based multienzyme-like nanoparticles with catalase-like (CAT-like) and superoxide dismutase-like (SOD-like) catalytic activities significantly scavenge the surge-generated endogenous reactive oxygen species (ROS) and effectively protects hepatic IRI. Density functional theory calculations confirm that the nanoparticles efficiently scavenge ROS through their synergistic effects of the ultra-small copper SOD-like activity and manganese dioxides CAT-like activity. Furthermore, the results show that the biocompatible CMP NPs significantly protected hepatocytes from IRI in vitro and in vivo. Importantly, their therapeutic effect is much stronger than that of N-acetylcysteamine acid (NAC), an FDA-approved antioxidative drug. Finally, it is demonstrated that the protective effects of CMP NPs on hepatic IRI are related to suppressing inflammation and hepatocytic apoptosis and maintaining endothelial functions through scavenging ROS in liver tissues. The study can provide insight into the development of next-generation nanomedicines for scavenging ROS.

Reliability Analysis of Steam Turbine Instrumentation Using the Failure Mode and Effect Analysis (FMEA) Method at PT. PLN Nusantara Power UP Tenayan

PT. PLN Nusantara Power Unit Generation Tenayan is a company operating in the Steam Power Plant sector in Pekanbaru, Indonesia. One of the main components of a steam power plant (PLTU) is a steam turbine. A steam turbine is a machine that functions to convert kinetic energy into electrical current. Operational failures are often caused by less than optimal instrumentation in the steam turbine. This research uses the failure mode and effect analysis (FMEA) method with the aim of identifying the type of failure, the cause of the failure, the effect of the failure, and determining the RPN value. The analysis results from this research show that the turbine instrumentation components still meet performance standards because the risk priority number (RPN) value is less than 200. The conclusion from this research is that errors in steam turbine instrumentation are inaccurate sensor readings, switches cannot deactivate the equipment, and readings control room does not match local readings, the instrumentation component with the highest risk priority number (RPN) is the solenoid valve with a value of 140, and the instrumentation component with the lowest risk priority number (RPN) is the pressure indicator with a value of 30. The component given top priority in action The recommendation is for the solenoid valve component, namely to carry out maintenance every 6 months and add an overspeed protection system

Artificial intelligence‐driven sustainability: Enhancing carbon capture for sustainable development goals– A review

AbstractArtificial intelligence (AI) and environmental points are equally important components within the response to local weather change. Therefore, based on the efforts of reducing carbon emissions more efficiently and effectively, this study tries to focus on AI integration with carbon capture technology. The urgency of tackling climate change means we need more advanced carbon capture, and this is an area where AI can make a huge impact in how these technologies are operated and managed. It will minimize manufacturing emissions and improve both resource efficiency as well as our planet's environmental footprint by turning waste into something of value again. Artificial intelligence could be leveraged to analyze huge data sets from carbon capture plants, searching for optimal system settings and more efficient ways of identifying patterns in the available information at a larger scale than currently possible. In addition, AI incorporated sensors and monitoring mechanisms in the supply chain can identify any operational failure at reception itself allowing for timely action to protect those areas. Artificial intelligence also helps generative design for carbon capture materials, which allows researchers to explore new types of carbon‐absorbing material, including metal–organic frameworks and polymeric materials that are important in industrial CO2, such as moisture. In addition, it increases the accuracy of reservoir simulations and controls CO2 injection systems for storage or enhanced oil recovery. Through applying AI algorithms on reservoir geology, production performance and real‐time data this study would like to facilitate the optimization of injection processes as well as minimize CO2 emissions while assuring a maximum efficiency. Artificial intelligence integrates with renewable‐based carbon capture efforts that can be employed by AI‐driven smart grid systems to improve carbon capture methods.

A systematic review and meta-analysis of randomized controlled trials for the management of ventral hernia: biologic versus synthetic mesh.

An abdominal wall hernia near the location of a prior surgical incision is referred to as an incisional hernia. A midline incisional hernia is the most prevalent form. The management of incisional hernia includes many options, from conservative to surgical. The surgeon might consider using a synthetic or biological mesh when discussing surgical options with patients. Our aim through this study is to comprehensively compare synthetic and biological mesh in terms of complication and infection rates for managing elective incisional hernia. This systematic review was designed and conducted using PRISMA guidelines. The literature was systematically searched in January 2023 using the following databases: MEDLINE, Cochrane, and EMBASE. Among the terms used to aid the search were the following: incisional hernia, ventral hernia, ventral herniorrhaphy, biologic mesh, polypropylene mesh, absorbable mesh, permanent mesh, biomaterial mesh, biological mesh, and synthetic mesh. The review of the literature resulted in a total of 3115 publications. By applying our criteria, six articles were included in this study, with 949 participants. Our meta-analysis showed the overall complication incidence displaying a significant difference favouring the synthetic mesh group (IV = 1.25, 95% CI 1.11-1.42, P = 0.0002). The operation failure rate, defined as hernia recurrence, also significantly favoured synthetic mesh (IV = 2.42, 95% CI 1.66-3.52, P < 0.00001). In conclusion, the present study found that the synthetic mesh proved superior in overall complication rate and operation failure compared to biologic mesh. However, it had no significant differences in other complications.

Characterization of Hydraulic Spool Clamping Triggered by Solid Particles Based on Mechanical Model and Experiment Research

Hydraulic spool valves may clamp under the action of sensitive particles when working in hydraulic oils that contain solid particles, which will then bring about a devastating detriment to the machines. According to the failure statistics of hydraulic systems organized by ISO, more than 80% of the operational failures of hydraulic systems are caused by fluid contamination, and particulate contamination is the most important factor causing spool valve stagnation. In this paper, we considered various factors, including the material, size, and concentration of particles and the spool postures, and built a systematic spool clamping mechanical model. A device was designed to measure the spool valve friction under the action of particles. The influence of particle material, concentration, and size on the friction force of spool valves was investigated. By experiments, we measured the spool clamping force under the action of each single factor and then fitted the datum quantity of spool clamping force and the empirical equation of pulsating quantity. The study results demonstrate three types of non-ideal postures of spools in a valve hole, which are off-center, tilting, and off-center with tilting. Those three postures can engender clamping risk zones with different ranges inside the clearance between spool valves, increasing the risk of spool clamping. The kind of particles is found to have a certain but limited impact on the spool clamping force. Usually, particles with a higher elastic modulus can trigger a larger spool clamping force, which is in line with the theoretical equation. Within a certain range, the probability density distribution of particle size tallies with the normal distribution function, where the “sensitive particles” take up 0.7–1 of the clearance between spool valves. A higher particle volume fraction in oils means a greater number of sensitive particles and a larger spool clamping force. For the particles of a similar size with the clearance between spool valves, when their volume concentration tops over the “sensitive concentration”, namely 5%, the risk of spool clamping rises in a drastic manner. This study provides a theoretical reference and an empirical equation for the mechanism of spool clamping under the action of particles, as well as a definite quantitative indicator for the prediction and estimation of spool clamping which is of positive significance for the study of the predictive maintenance of hydraulic equipment.

Design and first tests of the trapped electrons experiment T-REX.

Gyrotrons are essential for electron cyclotron resonance heating in fusion reactors, making efficient operation crucial for advancing fusion energy. Past experiments revealed instability issues due to trapped electrons in the magnetron injection gun (MIG) region, causing undesired currents and operational failures. To address this, tight manufacturing tolerances are required for the MIG geometry [Pagonakis etal., Phys. Plasmas 23, 023105 (2016)]. We present the initial findings of the trapped electrons experiment developed at the Swiss Plasma Center, designed to understand the physics of electron clouds in gyrotron MIGs. T-REX replicates MIG geometries, as well as their typical electric and magnetic fields, and it is supported by 2D particle-in-cell simulations with the FENNECS code [Le Bars etal., Phys. Plasmas 29, 082105 (2022); Le Bars, Ph.D. thesis, EPFL, Lausanne, 2023]. The setup includes two coaxial electrodes in a vacuum chamber atop a superconducting magnet, with a central electrode biased to negative DC voltages and an outer one at the ground, creating a radial electric field (1-2MV/m) and an axial magnetic field (B < 0.4T). This setup mimics Penning-Malmberg traps. We present the experimental device and first findings on current distribution and also a qualitative comparison with FENNECS simulations [Le Bars etal., Comput. Phys. Commun. 303, 109268 (2024)]. Planned diagnostics include optical emission spectroscopy, phosphor screen imaging, streak camera imaging, and potentially electric field distribution via the Stark effect. This research aims to enhance gyrotron performance and reliability in fusion energy systems.

Adhering to Patient Safety Standards: A Healthcare Imperative for the 21st Century

The ethics of healthcare processes aim to protect patient safety by emphasizing the importance of adhering to rules and avoiding harmful practices. They also suggest practical solutions to prevent such failures. Non-compliance, whether due to human error or technical failure, can result in operational failures and pose severe hazards to patients, healthcare workers, and hospital facilities. This paper discusses intentional non-compliance with healthcare standards and guidelines, referred to as deviation, and demonstrates how adhering to these rules can reduce the risk of harm. Noncompliance can have severe consequences, as it may reveal an organization's fail-safe mechanisms, defenses, or safety nets, potentially resulting in catastrophic events and causing significant harm. These errors typically occur when active errors combine with latent errors, such as flaws or vulnerabilities in a system's defenses. This habit allows the latter to overcome the defenses, gain patient access, and cause harm. There is no such thing as a completely safe environment, even the most advanced ones. Additionally, all humans, regardless of their intelligence, have weaknesses. In healthcare processes, every signal has the potential to cause harm, leading to tragic outcomes or even death. The factors contributing to non-compliance fall under individual, collective, organizational, or sociocultural categories. Reducing non-compliance in healthcare processes and ensuring patient safety requires all stakeholders to commit to patient safety ethics.

Legal Responsibility For Operational Failures Through Robotic Telesurgery

Technological developments, especially in the health sector, are currently growing very rapidly. Robotic Telesurgery or remote surgical robots are expected to become a technology that can realize health equality in Indonesia, but it is a shame that technological progress is not comparable to the relevant regulations that regulate it, it is feared that this will not guarantee legal certainty which could lead to malpractice. The method used in this research is a normative legal research method because the focus of the study departs from the vagueness of norms using the approach: statute approach, conceptual approach, as well as analytical approach. The legal material search technique uses document study techniques, and study analysis uses qualitative analysis. The results of this research are that there is a void in norms in Law Number 17 of 2023 concerning Health which does not regulate legal responsibility for failed operations through Robotic Telesurgery So it is necessary to create a law that specifically regulates the responsibilities of doctors.

DESIGN OF IMAGE PROCESSING APPLICATION FOR FOREIGN OBJECT INSPECTION USING DRONE ON AIRCRAFT RUNWAYS

Flight safety is a crucial aspect of the aviation industry, heavily reliant on optimal runway conditions for successful takeoffs and landings. Foreign Object Debris (FOD) such as stones and potholes on the runway pose significant threats, necessitating preventive measures to avoid operational failures and aircraft damage. This research focuses on designing an image processing application for drone usage to enhance runway inspections. The Research and Development (R&amp;D) method is employed from application design to field testing. Image processing utilizes the You Only Look Once (YOLO) method for swift and accurate FOD detection, maximizing drone effectiveness in identifying risks. Findings indicate that object size and image capture distance significantly affect detection performance. This analysis provides a basis for model optimization through improved data augmentation techniques and parameter adjustments to address challenges in detecting objects of various sizes.

Reliability Analysis of Coal Feeder Instrumentation Using Failure Mode and Effect Analysis (FMEA) at PT. PLN Nusantara Power UP Tenayan

PLN Nusantara Power UP Tenayan is a coal-fired power plant supplying electricity to the Riau region with a capacity of 2 x 110 MW. Operating 24/7, the plant faces frequent failures, particularly in the instrumentation components of the coal feeder. This research employs the Failure Mode and Effect Analysis (FMEA) method to identify and analyze these failures. The Risk Priority Number (RPN), calculated by multiplying severity, occurrence, and detection ratings, helps determine the failure level. Research stages include a preliminary study, problem identification, observations and interviews, data collection and processing, FMEA analysis, and conclusion drawing. The results indicate that the instrumentation components are generally reliable, with RPN values below the critical threshold of 200. The speed sensor, with the highest RPN value of 160, is still categorized as reliable. Failures in these components can lead to operational failures, suboptimal coal feeder performance, and monitoring difficulties. The study recommends preventive maintenance every six months to enhance reliability and minimize disruptions.

The Role of ICG-Guided Fluorescent Mode in Boosting the Learning Curve of Laparoscopic Cholecystectomy.

Background: The most common therapy for gallstones is laparoscopic cholecystectomy (LC). How to help young residents avoid bile duct injuries (BDI) during surgery and grasp LC seems to be a paradox. Methods: We retrospectively reviewed 145 cases of LC operated by two residents under indocyanine green (ICG)-guided mode or normal LC procedures to illustrate the role of ICG mode in boosting the LC learning curve. The clinic data were analyzed by logistic regression, receiver operator curve tests, Cumulative Sum (CUSUM), and Risk-Adjusted Cumulative Sum (RA-CUSUM) analysis. Results: The operation failure rate is similar. However, operation time under ICG mode is shorter than that under normal mode. The peak at the 49th case represented the normal resident's complete mastery of the surgery, while the peak point of ICG mode appeared at the 36th case in the fitting curve. The most significant cumulative risk (peak point) of operation failure of LC was at the 35th case in ICG LC mode, while it appeared in the 49th in normal LC mode. Conclusions: Owing to the advantage of real-time imaging and the stable success rate of cholangiography, ICG-guided LC helps residents shorten the operation time, boost the learning curve, and manage to control the operation failure rate.

How environmental accidents influence consumer “green” behavior: An econometric analysis

AbstractEnvironmental accidents (EAs) are firm operational failures that harm human health, the natural environment, and offending firms. We propose they also initiate a subtle form of activism among consumers living near the accident by stimulating increased “green” behavior. Using annual county‐level data in California from 2000 to 2015, we show that following an EA, consumers reduce the trash/garbage they generate and the energy they consume. The impact is long‐lasting and stronger when EAs are more severe and when consumers have pro‐environmental beliefs, ready access to information, and convenient access to “green” options, such as recycling. Since affected consumers may also refuse to buy from, invest in, or work for offending companies, the results suggest that firms should develop environmental strategies, which include engaging and collaborating with local communities. The study results also provide input for the development of initiatives, which maximize consumer “green” behavior after, or in the absence of, an EA.

An Integrated Approach: A Hybrid Machine Learning Model for the Classification of Unscheduled Stoppages in a Mining Crushing Line Employing Principal Component Analysis and Artificial Neural Networks.

This article implements a hybrid Machine Learning (ML) model to classify stoppage events in a copper-crushing equipment, more specifically, a conveyor belt. The model combines Artificial Neural Networks (ANNs) and Support Vector Machines (SVMs) with Principal Component Analysis (PCA) to identify the type of stoppage event when they occur in an industrial sector that is significant for the Chilean economy. This research addresses the critical need to optimise maintenance management in the mining industry, highlighting the technological relevance and motivation for using advanced ML techniques. This study focusses on combining and implementing three ML models trained with historical data composed of information from various sensors, real and virtual, as well from maintenance reports that report operational conditions and equipment failure characteristics. The main objective of this study is to improve the efficiency when identifying the nature of a stoppage serving as a basis for the subsequent development of a reliable failure prediction system. The results indicate that this approach significantly increases information reliability, addressing the persistent challenges in data management within the maintenance area. With a classification accuracy of 96.2% and a recall of 96.3%, the model validates and automates the classification of stoppage events, significantly reducing dependency on interdepartmental interactions. This advancement eliminates the need for reliance on external databases, which have previously been prone to errors, missing critical data, or containing outdated information. By implementing this methodology, a robust and reliable foundation is established for developing a failure prediction model, fostering both efficiency and reliability in the maintenance process. The application of ML in this context produces demonstrably positive outcomes in the classification of stoppage events, underscoring its significant impact on industry operations.

Research on Risk Management of Equity Pledge in Listed Companies: A Case Study of Guirenniao

In the present financial market, the financial needs of listed companies are expanding rapidly. Equity pledge, as a commonly used means of financing for listed companies, is becoming increasingly significant. As an emerging form of guarantee, equity pledge allows listed companies to pledge their own equity as collateral to obtain financing from external financial institutions. Equity pledge has many advantages, such as universality, fast financing speed, strong security, and effective risk diversification. However, equity pledge not only meets the financing needs of listed companies, but also brings corresponding risks to them. this paper selects the classic case of Guirenniao Co., Ltd. as the research object and adopts the literature analysis method to review relevant research on equity pledge both domestically and internationally. Based on the leverage cycle theory, PBC (Private Benefits of Control) theory, and asymmetric information theory, the article analyzes the risks associated with equity pledge and identifies excessive pledge by Guirenniao as an important factor contributing to the failure of company operation. Finally, based on the research findings, risk response measures are proposed from the main aspects of external information disclosure, internal supervision and control, enhancement of enterprise value, and dynamic monitoring of business operations. It aims to raise awareness among other listed companies and their stakeholders, prevent risks, effectively supervise the equity pledge behavior of listed companies, and ensure the sustainable development of equity pledge.

CFD-DEM analysis of internal flow characteristics in multistage deep-sea mining pumps

ABSTRACT The potential profits associated with deep-sea mineral deposits have encouraged the development of new mining techniques. In particular, the effectiveness of lift pumps is crucial to the success or failure of these mining operations. In this study, the interior pressure field, turbulence characteristics, and turbulent kinetic energy of deep-sea mining pumps were numerically simulated using the computational fluid dynamics/discrete element method (CFD-DEM). Turbulence in the solid–liquid two-phase flow in deep-sea mining lift pumps was also investigated using CFD-DEM, and the key factors affecting lift and efficiency were obtained. Data exchange among particles and between particles and fluids was fully considered to obtain reliable calculation results. The results show that lift pump operation improves when the speed increases. A real-world hydraulic test was conducted to verify the simulation result. That is, increasing the speed of the lift pump stabilises the flow of particles and fluids and gradually increases the lift and efficiency. The simulation method provides a reliable starting point for developing and optimising subsea lift pumps.

Prediction of Glass Transition Temperature of Polymers Using Simple Machine Learning.

Polymer materials have garnered significant attention due to their exceptional mechanical properties and diverse industrial applications. Understanding the glass transition temperature (Tg) of polymers is critical to prevent operational failures at specific temperatures. Traditional methods for measuring Tg, such as differential scanning calorimetry (DSC) and dynamic mechanical analysis, while accurate, are often time-consuming, costly, and susceptible to inaccuracies due to random and uncertain factors. To address these limitations, the aim of the present study is to investigate the potential of Simplified Molecular Input Line Entry System (SMILES) as descriptors in simple machine learning models to predict Tg efficiently and reliably. Five models were utilized: k-nearest neighbors (KNNs), support vector regression (SVR), extreme gradient boosting (XGBoost), artificial neural network (ANN), and recurrent neural network (RNN). SMILES descriptors were converted into numerical data using either One Hot Encoding (OHE) or Natural Language Processing (NLP). The study found that SMILES inputs with fewer than 200 characters were inadequate for accurately describing compound structures, while inputs exceeding 200 characters diminished model performance due to the curse of dimensionality. The ANN model achieved the highest R2 value of 0.79; however, the XGB model, with an R2 value of 0.774, exhibited the highest stability and shorter training times compared to other models, making it the preferred choice for Tg prediction. The efficiency of the OHE method over NLP was demonstrated by faster training times across the KNN, SVR, XGB, and ANN models. Validation of new polymer data showed the XGB model's robustness, with an average prediction deviation of 9.76 from actual Tg values. These findings underscore the importance of optimizing SMILES conversion methods and model parameters to enhance prediction reliability. Future research should focus on improving model accuracy and generalizability by incorporating additional features and advanced techniques. This study contributes to the development of efficient and reliable predictive models for polymer properties, facilitating the design and application of new polymer materials.