Maintenance Methods Research Articles

Digitalization of Adjustment and Maintenance Processes for Optimizing Energy Consumption in the Oil and Gas Sector

This article examines the impact of digitalization on adjustment and maintenance processes in the oil and gas sector aimed at optimizing energy consumption. Modern technologies such as big data analysis, the Internet of Things (IoT), and Machine Learning (ML) algorithms are discussed, highlighting how they assist companies in reducing energy consumption and enhancing operational efficiency. Examples of the implementation of these solutions in major companies are provided, demonstrating significant reductions in energy costs and equipment downtime. The advantages of contemporary approaches over traditional adjustment and maintenance methods are emphasized.

Maintenance Methods and Strategies for Existing Bridges in China

Abstract. In China, bridges constructed in the past century have deteriorated due to environmental exposure and increasing loads, necessitating attention from researchers on assessment, maintenance, and reinforcement to ensure safety. Appropriate design and construction techniques are key to improving load-bearing capacity and extending service life. This paper summarizes China's bridge challenges, introduces the development of bridges in China since the 20th century and visual inspection methods, and outlines strengthening techniques for bridge superstructures and substructures. Furthermore, the paper concludes with a discussion of future research directions, highlighting the importance of continued efforts to ensure the safety, reliability, and longevity of these vital transportation structures.

A Magnetic Climbing Robot for Steel Bridge Inspection

Abstract. The maintenance of traditional steel bridges presents many significant challenges due to the fact that bridges of different ages and standards vary in design, structural complexity and technical difficulty. In light of these considerations, it is clear that maintenance personnel must possess a wealth of professional expertise and experience in order to effectively address the diverse and intricate maintenance challenges that arise. Moreover, the maintenance process entails high-risk operations such as high-altitude work and welding, which pose a threat to the safety of construction personnel. Therefore, this study introduces a magnetic adsorption robot designed to address the low efficiency and high costs of traditional maintenance methods. This robot features a dual robotic arm mechanism and modeled using the Denavit Hartenberg (D-H) parameter method. Electromagnetic adsorption is utilized to achieve wall adhesion, and direct power supply is provided through DC power to control weight. The robot can perform flexible remote control operations through the HC-05 Bluetooth module. The experimental results show that the robot exhibits robust adhesion and obstacle crossing ability on steel surfaces, thereby enabling unimpeded movement within the steel structure. In addition, the robot is now capable of performing overhaul procedures via remote control.

Advanced Machine Learning Algorithms for Predictive Maintenance in Industrial Manufacturing Systems

In industrial manufacturing systems, predictive maintenance is the process of increasing the rate of productivity and minimizing the time that equipment takes to be out of order through early identification of the equipment that is likely to fail. The main focus of this research is to analyze the possibility of using modern approaches in machine learning to enhance the methods of predictive maintenance. We compare multiple current approaches of deep learning, ensemble methods, and anomaly detection to determine their effectiveness in predicting the maintenance requirements utilizing the sensor and operational data. With the help of a large amount of data, we consider the results of the work of each algorithm for the assessment of the predictive accuracy, the ranking of features, and the detection of anomalies. The findings highlight disparities in the effectiveness of the algorithms in terms of accuracy, precision, and recall, and the deep learning models’ ability to grasp intricate and anomalous patterns. The performance of the maintenance predictions is depicted by the use of visualizations of the performance metrics and feature importance. It also describes the drawbacks of the existing models, such as the problem of data quality and generalization. The study draws attention to the possibility of applying sophisticated machine-learning methods to improve the effectiveness of PM in industrial environments. Possible directions of future research are to enhance the generalization ability of the developed models and to expand the usage of modern trends in the machine learning field to enhance maintenance strategies.

Best IDEAS: Special Issue of the International Database Engineered Applications Symposium

Database engineered applications cover a broad range of topics including various design and maintenance methods, as well as data analytics and data mining algorithms and learning strategies for enterprise, distributed, or federated data stores [...]

Improved machine learning models with a similarity-based approach for remaining useful life prediction

Abstract Cost efficiency is a critical factor in the competitive aviation sector. These efficiency factors force airline operators to develop new approaches in their organizations. Predictive maintenance helps to build scheduling maintenance programs for airline operators or MROs. Scheduled maintenance programs benefit cost efficiency in the aviation sector. Predictive maintenance methods predict the failure time of any equipment. Predictions can be made by analyzing the sensor values from equipment. In this paper, we predicted the remaining useful life (RUL) of turbofan engines using machine learning models and a similarity-based approach. Sensor datasets from the Prognostics Data Repository of NASA, called CMAPPS, were utilized. Using the FD0002 sub-dataset, a health index (HI) was created, and models were trained. Once the models were trained, train and test HIs were estimated. The predicted test HI was matched with the predicted train HI based on a similarity-based approach, and then a RUL prediction was made. The results obtained were compared with the actual results to calculate the accuracy, and the algorithm that resulted in the maximum accuracy was identified. We selected six machine learning algorithms and also created an ensemble model by averaging the predictions of six machine learning algorithms for comparing prediction accuracy. The different algorithms were compared to obtain the prediction model with the closest prediction of remaining useful lifecycle in terms of the number of life cycles. This experiment showed us the effect of the similarity-based approach on the basic version of machine learning models for RUL prediction.

Reliability analysis of the vehicle door system EDCU based on Weibull distribution

The paper established a two-parameter Weibull distribution model to analyze the failure law of key components of metro vehicles and employed the least squares method to fit the parameters of the Weibull function. The paper provided a detailed introduction of the model's parameter fitting method based on actual historical failure data. Taking the EDCU (Electrical Door Control Unit) as an example, the failure rate, cumulative failure rate, and reliability of EDCU for 3 different vehicle models were calculated, and the calculation results were verified to conform to the Weibull distribution through Q-Q diagrams. The results show that although the designed service life of EDCU of vehicle door system is 15 years, the reliability of the EDCU decreases significantly around 10 years. The EDCU reliability of the three vehicle models declines by 22%, 4.2%, 10.6% and the failure rates are 2.7%, 0.57%, 1.13%. Based on the reliability of EDCU mentioned above, while ensuring the reliability of components, the maintenance methods of components can be optimized to reduce maintenance costs.

Innovative technology for microalgal cell preservation through immobilization in polylactic acid nanofibers

Microalgae are of great biotechnological importance. Thus, it is essential to apply maintenance methods for the utilization of microalgae at any time. Facilitating microalgae adsorption processes on nanofibers may be a promising approach for microalgae preservation. Thus, the objective of this study was to apply poly (lactic acid) nanofibers in the preservation of microalgae Chlorella fusca LEB 111 cells. The nanofibers were characterized regarding their morphology, thermal properties, structural characteristics and wettability. The microalgae cells were immobilized on the nanofibers and stored for 30 days at room temperature, refrigeration and thermostated chamber. Free microalgae cells were also maintained for the same period under the same conditions of the traditional method of microalgae preservation, continuous replication. The cell viability of the free and immobilized cells on the nanofibers was analyzed by Neutral Red (NR) and Trypan Blue (TB). At the end of the experiment, the immobilized cells showed greater viability (94 and 100 %) compared to the free cells (84 %). The cultivation of immobilized cells showed significant cell growth on the 25th day of cultivation for the evaluated storage conditions (3.6, 3.6 and 2.8 g L−1 for refrigeration, room temperature and thermostatted chamber, respectively). Therefore, poly (lactic acid) nanofibers (PLA) are characterized as an innovative technology for microalgae maintenance.

PATOLOGIAS EM PAVIMENTOS FLEXÍVEIS: TRECHO AVENIDA TORQUATO TAPAJÓS COM AVENIDA CONSTANTINO NERY NA CIDADE DE MANAUS - AM

This study aimed to conduct a case analysis through the evaluation and assessment of pathologies in flexible pavements at a stretch of Avenida Torquato Tapajós with Avenida Constantino Nery, in the city of Manaus - AM. The research sought to identify the causes and origins of these pathologies, relating solutions to each diagnosed situation based on theses, articles, and consulted literature. The main objective of this article is to analyze the most common pathologies in flexible pavements. The research is justified by the need to assess the maintenance of damages and pathologies in pavements, a constant factor in the infrastructure sector that incurs high costs and requires thorough analysis to determine the procedures to be adopted. The method used was a descriptive qualitative exploratory study, grounded in existing literature and field documentation. Based on the analysis of the pathologies, the necessary maintenance methods were defined in accordance with federal regulations and current standards in Brazil. The results revealed different classifications of pathological manifestations in flexible pavements. It was found that the traffic anticipated for the road project does not align with its actual usage, contributing to the noticeable occurrence of cracks in the analyzed roadway. Implementing best practices can mitigate the negative impacts of these pathologies, ensuring the longevity of pavements and the safety of users. Adherence to established guidelines is crucial to ensure that flexible pavements meet required standards, avoiding future problems arising from inadequate interventions. With the increasing digitization in the construction sector, the integration of new technologies becomes increasingly viable for managing pathologies in flexible pavements in heavily trafficked highway segments.

Evaluation of Load-Bearing Capacity in Japanese Arch Steel Aqueduct Bridge through Structural Redundancy Assessment

Structural redundancy assessment of steel aqueduct bridges is made by the analysis of a case study using the Musota Aqueduct bridge structure: a simply supported steel arch bridge erected in 1973 and a seven- span continuous steel aqueduct bridge. In this paper, as a case study, after the validation of the model, the structural redundancy of the Musota aqueduct bridge in Wakayama City with respect to its load-carrying capacity after the failure of hanging components due to corrosion was investigated. The conventional procedure for the assessment of redundancy makes use of static nonlinear structural analysis. A three-dimensional finite-element model of this bridge was developed to simulate its behavior. The results from the linear analysis are compared with those from the nonlinear analysis to investigate the appropriateness of the former in the evaluation of redundancy. A detailed nonlinear static finite element study is carried out into the hangers' components of the arch bridge in order to clarify the implications involved in the failure of redundancy. Finally, recommendations for prudent bridge maintenance methods are presented based on findings from the investigation.

Innovative housing models to support shared use of space: the case study of Sonnwendviertel Ost in Vienna

Amidst the persistent urban expansion in European cities, the need for high-quality housing for growing populations remains a challenge. Integrating newly developed housing areas into the urban fabric and fostering a distinct local identity pose additional challenges. Despite extensive research in this realm, there exists a gap in the examination of the extent of shared space utilization in new housing developments. This study fills that gap by analyzing the quantity, quality, and diversity of space utilization in new housing projects, focusing on the development processes and maintenance methods. The research, conducted through site and case study analyses of Sonnwendviertel Ost development area in Vienna, underscores that the shared utilization of spaces is closely tied to distinct housing models with varied levels of financing and involvement of diverse actors. Consequently, it provides insights into the housing models and their configurations that best facilitate the development of shared use of spaces in housing construction. This, in turn, is perceived as instrumental in cultivating a more robust neighborhood identity and enhancing the livability of communities, thereby contributing to sustainable urban development.

Perawatan Preventive Maintenance Mobil Satlantas Model Sedan Mazda dengan Metode Reliability Centered Maintenance pada Polres Kota X

The aim of this research is to find out the preventive maintenance of Mazda Sedan Model Traffic Cars using the reliability centered maintenance method at the City functional block diagram, determining system function and functional failure, failure mode and effect analysis, logic tree analysis, and task selection. The results of this research are that the maintenance system for traffic vehicle units carries out routine check-ups every 5,000 kilometers or every 3 months and for brake and tire components every 10,000 kilometers or 6 months, the damage that appears with the current maintenance system is the break caliper (right front), hose (water pump), and ball joint, factors that arise with current maintenance problems are safety problems, proposed improvements that need to be made to resolve the problem are preventive maintenance for the break caliper (right front), hose (water pump), and ball joint every 11000 hours or 458 days.

Evaluation and maintenance method for general speed railway turnouts based on multi-source data

In recent years, with the increasing passengers' requirements for safety and comfort, as well as the measures of increasing revenue and reducing the expenditure of railway company, more efficient, more scientific and more comprehensive requirements have been put forward for the maintenance of railway turnouts. This paper develops a maintenance strategy based on the Turnout Service State Indicator (TSSI), derived from an analysis of multi-source data concerning turnout conditions. The weights of critical indicators affecting turnout conditions are determined using Analytical Target Cascading (ATC) and Analytic Hierarchy Process (AHP). Subsequently, turnouts are classified into four categories—great, good, general, and poor—based on their TSSI values, guiding specific maintenance strategies. The proposed assessment method was validated using data from four sets of turnouts collected on actual tracks, showing consistency between the assessment results and field technicians' evaluations. A comparative analysis of the ATC and AHP suggests that the latter provides a more scientific and objective assessment of turnout conditions. The established methods for evaluating the service state and deciding on turnout maintenance actions have been proven feasible and practical through field validation. These methods can be broadly applied to maintain general speed railway turnouts to enhance repair efficiency and reduce maintenance costs.

Research on a Photovoltaic Panel Dust Detection Algorithm Based on 3D Data Generation

With the rapid advancements in AI technology, UAV-based inspection has become a mainstream method for intelligent maintenance of PV power stations. To address limitations in accuracy and data acquisition, this paper presents a defect detection algorithm for PV panels based on an enhanced YOLOv8 model. The PV panel dust dataset is manually extended using 3D modeling technology, which significantly improves the model’s ability to generalize and detect fine dust particles in complex environments. SENetV2 is introduced to improve the model’s perception of dust features in cluttered backgrounds. AKConv replaces traditional convolution in the neck network, allowing for more flexible and accurate feature extraction through arbitrary kernel parameters and sampling shapes. Additionally, a DySample dynamic upsampler accelerates processing by 8.73%, improving the frame rate from 87.58 FPS to 95.23 FPS while maintaining efficiency. Experimental results show that the 3D image expansion method contributes to a 4.6% increase in detection accuracy, an 8.4% improvement in recall, a 5.7% increase in mAP@50, and a 15.1% improvement in mAP@50-95 compared to the original YOLOv8. The expanded dataset and enhanced model demonstrate the effectiveness and practicality of the proposed approach.

Generation of maintenance and troubleshooting strategies for complex equipment based on Bayesian network reinforcement learning

To solve the problem of long decision-making time and high total cost of generated strategies in traditional heuristic maintenance and troubleshooting decision-making methods, a method for complex equipment maintenance and troubleshooting strategy generation based on Bayesian network combined with reinforcement learning is proposed . In order to better utilize the knowledge of complex equipment models, Bayesian network is used to express maintenance and troubleshooting knowledge, and in order to be closer to the actual situation of complex equipment, the failure probability analyzed according to the failure mode, impact and criticality is used as the prior probability of the Bayesian network after reasonable transformation; in order to generate maintenance and troubleshooting strategies using the decision-making process of reinforcement learning, a method for converting the maintenance and troubleshooting decision problem into a reinforcement learning problem is proposed ; in order to better solve the transformed reinforcement learning problem, the observation-repair action pair is introduced to reduce the problem scale, and the action mask is set to process the dynamic action space. The simulation verification results show that under the unified performance index , the proposed method obtains higher index values than the traditional method, which proves the effectiveness and superiority of the method.

PELATIHAN PERAWATAN TRANSMISI MOTOR MATIC UNTUK MENINGKATKAN PERFORMA MOTOR DI DESA SUKAMUKTI

This service activity aims to train the community so that people can be more aware or given awareness about the maintenance of their personal vehicles, so that they are more independent in maintaining their motorbikes. Because many people only use their vehicles and don't think about maintenance, this will become a complex problem because over time, the vehicle's performance will decrease, and at any time this can have fatal consequences for the driver himself. From this problem, a solution was found by creating a motorbike maintenance training program to educate and introduce the procedures for maintaining motorbikes, especially in the automatic motorbike transmission section. The result of this activity is that residents understand more about the parts in automatic motorbike transmissions, how to maintain them, can practice the correct maintenance methods, and the dangers that arise if spare parts in automatic motorbike transmissions are not properly maintained.

Enhanced fault detection in energy systems using individual contextual forgetting factors in recursive principal component analysis

Improving maintenance strategies is an important component in reducing wastes of energy in industrial systems and especially energy systems, as they represent a large proportion of our total energy use. The use of fault detection methods can help transition to proactive maintenance methods and automate the detection of faults using data from the systems themselves. However, the presence of normal operational changes must be accounted for to avoid false alarms, as static fault detection methods cannot handle them. A recursive fault detection method, specifically recursive principal component analysis (RPCA), is applied to real building data in this paper to aid in addressing this challenge. Additionally, improvements to the aspect of updating forgetting factors, which are integral to RPCA's functionality, is also proposed which allows for enhanced adaptability. The results show that the improvement increases adaptability when setpoints are changed and provides similar performance otherwise. Lastly, the application of this was shown to significantly reduce false alarms in the building application, while still detecting the known faults.

Maintenance of RZA equipment according to technical condition

Subject of research: methods of maintenance and adjustment of relay protection and automation devices (RPA) in electrical power systems. Purpose of research: analysis of existing maintenance and adjustment methods, development of proposals for their optimization to increase the efficiency and reliability of electrical power systems. Methods of research: the research used methods of analysis of regulatory documents, survey of specialists and analysis of publications. Main results of research: identification of a lack of standardization of procedures, problems with personnel qualifications and the discrepancy of some devices with the declared characteristics. The findings highlight the need to develop unified approaches to maintenance and commissioning, as well as improve the professional training of specialists. The results of the study can be used to improve the practices of maintenance and adjustment of relay protection and automation systems, which helps to increase the reliability of electric power systems.

Development of decision support methods for efficient maintenance of urban wastewater systems

The sanitation network is a vital urban infrastructure that requires systematic and co-ordinated activities and practices to realize lowest life cycle cost. The sustainable management of this asset is based on the efficient acquisition of diagnostic data from the sanitation network in order to analyze the defects of each section, then to assess their condition to prioritize and consider the effective mode of maintenance of sections deemed failing. In this perspective, knowledge of the sanitation networks is essential for reliable classification of defects and effective maintenance. A numerical model based on weighted criticality is developed to evaluate and prioritize the defects in an urban sanitation network. It is based on the combination of two methods: Fuzzy Analytic Hierarchy Process (F-AHP) and Weighted Product Model (WPM). A case study of a real sanitation network in Bejaia city (Algeria), consisting mainly of non-visitable pipes evaluated from television inspections, is used to illustrate and validate the proposed model. The results show that the weighting of criticality parameters has a considerable influence on the classification of defects in a sanitation network. The weighted criticality results obtained in the present case are significantly better than those obtained using a method based on the notion of classical criticality. This clearly indicates the relevance of the proposed numerical model.

A Machine Learning-Based Algorithm for the Prediction of Eigenfrequencies of Railway Bridges

As part of the development of advanced, data-driven methods for predictive maintenance of railway infrastructure, this paper analyzes and evaluates more realistic predictions of eigenfrequencies of railway bridges, also referred to as natural frequencies, based on a population of already assessed, measured existing bridges using regression techniques. For this purpose, Machine Learning (ML) techniques such as Polynomial Regression (PR), ANN and XGBoost are consistently evaluated and the application of the XGBoost algorithm is identified as the most suitable prediction model for these eigenfrequencies, usable for dynamic train-bridge interactions. The results of the post-processing are incorporated into the safety architecture for bridge verification (risk management). The presented data-based techniques are a steppingstone towards digitalization of structural health monitoring and offer safety and longevity of the railway bridges. Furthermore, the use of these methods can save costs that would be incurred by physical in-situ measurements. The types of bridges analyzed with ML are Filler Beam Bridges (FBE), which outnumber other construction types of bridges in Germany (DB InfraGO AG). This methodology is applicable to any bridge type as long as sufficient data are gathered for training, validation and testing.