Maintenance Activities Research Articles

Modelling bridge deterioration using long short-term memory neural networks: a deep learning-based approach

PurposeBridge deterioration is a critical risk to public safety, which mandates regular inspection and maintenance to ensure sustainable transport services. Many models have been developed to aid in understanding deterioration patterns and in planning maintenance actions and fund allocation. This study aims at developing a deep-learning model to predict the deterioration of concrete bridge decks.Design/methodology/approachThree long short-term memory (LSTM) models are formulated to predict the condition rating of bridge decks, namely vanilla LSTM (vLSTM), stacked LSTM (sLSTM), and convolutional neural networks combined with LSTM (CNN-LSTM). The models are developed by utilising the National Bridge Inventory (NBI) datasets spanning from 2001 to 2019 to predict the deck condition ratings in 2021.FindingsResults reveal that all three models have accuracies of 90% and above, with mean squared errors (MSE) between 0.81 and 0.103. Moreover, CNN-LSTM has the best performance, achieving an accuracy of 93%, coefficient of correlation of 0.91, R2 value of 0.83, and MSE of 0.081.Research limitations/implicationsThe study used the NBI bridge inventory databases to develop the bridge deterioration models. Future studies can extend the model to other bridge databases and other applications in the construction industry.Originality/valueThis study provides a detailed and extensive data cleansing process to address the shortcomings in the NBI database. This research presents a framework for implementing artificial intelligence-based models to enhance maintenance planning and a guideline for utilising the NBI or other bridge inventory databases to develop accurate bridge deterioration models. Future studies can extend the model to other bridge databases and other applications in the construction industry.

Многофакторный анализ эффективности автономных транспортных средств на основе метода анализа среды функционирования

The design of robotic and unmanned vehicles includes a virtual commissioning stage that provides an analysis of the operation of objects using digital twins. Conducting a large number of experiments on models leads to the use of methods for evaluating the results obtained to choose the best design solution. A method of multifactorial anal-ysis of the efficiency of the complex of autonomous vehicles (AV) for agro-industrial purposes is proposed. Multivariate analysis is performed at the virtual commissioning stage in order to plan early maintenance and repair activities. The paper uses the method of analyzing the operating environment for a comparative assessment of various operating scenarios. The method is based on solving a complex of optimization problems of linear programming. A formal description of virtual test scenarios is proposed. The method of multifactorial analysis is implemented in the process of virtual tests using optimal purpose system models and AV simulation. A procedure for virtual AV tests has been developed, including step-by-step modeling and multivariate analysis. The sets of input and output key parameters of the AV and analyzed scenarios are determined. It is proposed to perform two consecutive efficiency assessment tasks. The first task is to compare the effectiveness of individual AV and determine the limits of their effectiveness. The solution of the second task makes it possible to evaluate the effectiveness of AV system operation scenarios. The target values of changes in the key parameters of the AV and operating scenarios are obtained, leading to an increase in the efficiency of operation and maintenance. Conducting a multifactorial analysis of the results of virtual tests allows you to formulate requirements and recommendations for the design of AV maintenance systems.

An efficient approach to expand equitable access to antiobesity medications: deprescribing after weight loss plateau.

The authors advocate for a consideration of 2 distinct phases of obesity management (ie, active weight loss and maintenance of weight loss) to allow substantially more people access to antiobesity medications.

Machine learning-based technology for asphalt concrete pavement performance decision-making in hot and humid climates

Highway state agencies incur significant budget savings through optimal allocation of pavement Maintenance, Rehabilitation, and Reconstruction (MR&R) activities. These activities require robust prediction models that can handle large-scale, real-world data and can forecast pavement performance in the long run. Unfortunately, the traditional performance prediction models have been questionable in terms of efficiency and accuracy, are based on a limited number of explanatory variables, and are designated to predict short-term (up to five years) pavement conditions. Therefore, the goal of this study was to propose a machine learning-based technology that can predict the field performance by up to 11 years of Asphalt Concrete (AC) overlays placed on asphalt pavements in Southern states in the US based on key project conditions. The proposed technology resulted from assessing the prediction accuracy of machine learning algorithms, including Decision-Tree (DT), eXtreme Gradient Boosting (XGBoost), Artificial Neural Network (ANN), and ensemble-learning method, in forecasting the Pavement Condition Index (PCI) as the pavement performance indicator. For each algorithm, six models were developed sequentially based on historical pavement condition data collected from the Louisiana Department of Transportation and Development (LaDOTD) Pavement Management System (PMS) database. The six models learned from 892 log miles of randomly placed AC overlay sections in Louisiana. The output of these models was the future PCI of AC overlays at a biannual rate from one to 11 years. The findings showed that XGBoost and ensemble learning showed similar performance during model training and were further evaluated using the testing dataset. During model testing, the ensemble learning method yielded higher prediction accuracy than other algorithms, with R2 values decreasing from 0.77 at age 1 to 0.67 at age 11, Root Mean Square Error (RMSE) values increasing from ±1.65 to ±4.74, and Mean Absolute Error (MAE) increasing from 1.24 to 4.59. The resulting models can be used by state agencies to replace traditional prediction techniques.

A Comprehensive Systematic Review Coupled with an Interacting Network Analysis Identified Candidate Genes and Biological Pathways Related to Bovine Temperament.

Comprehension of the genetic basis of temperament has been improved by recent advances in the identification of genes and genetic variants. However, due to the complexity of the temperament traits, the elucidation of the genetic architecture of temperament is incomplete. A systematic review was performed following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) statement to analyze candidate genes related to bovine temperament, using bovine as the population, SNPs and genes as the exposure, and temperament test as the outcome, as principal search terms for population, exposure, and outcome (PEO) categories to define the scope of the search. The search results allowed the selection of 36 articles after removing duplicates and filtering by relevance. One hundred-two candidate genes associated with temperament traits were identified. The genes were further analyzed to construct an interaction network using the STRING database, resulting in 113 nodes and 346 interactions and the identification of 31 new candidate genes for temperament. Notably, the main genes identified were SST and members of the Kelch family. The candidate genes displayed interactions with pathways associated with different functions such as AMPA receptors, hormones, neuronal maintenance, protein signaling, neuronal regulation, serotonin synthesis, splicing, and ubiquitination activities. These new findings demonstrate the complexity of interconnected biological processes that regulate behavior and stress response in mammals. This insight now enables our targeted analysis of these newly identified temperament candidate genes in bovines.

The trajectory of depression and anxiety among children and adolescents over two years of the COVID-19 pandemic

Longitudinal research examining children's mental health (MH) over the course of the COVID-19 pandemic is scarce. We examined trajectories of depression and anxiety over two pandemic years among children with and without MH disorders. Parents and children 2-18 years completed surveys at seven timepoints (April 2020 to June 2022). Parents completed validated measures of depression and anxiety for children 8-18 years, and validated measures of emotional/behavioural symptoms for children 2-7 years old; children ≥10 years completed validated measures of depression and anxiety. Latent growth curve analysis determined depression and anxiety trajectories, accounting for demographics, child and parent MH. Data were available on 1315 unique children (1259 parent-reports; 550 child-reports). Trajectories were stable across the study period, however individual variation in trajectories was statistically significant. Of included covariates, only initial symptom level predicted symptom trajectories. Among participants with pre-COVID data, a significant increase in depression symptoms relative to pre-pandemic levels was observed; children and adolescents experienced elevated and sustained levels of depression and anxiety during the two-year period. Findings have direct policy implications in the prioritization and of maintenance of educational, recreational, and social activities with added MH supports in the face of future events.

Process improvement in Zamak injection machines for automotive component fabrication

Die casting processes are nowadays widely used in the industry and differentiate from metal casting from the high-speed and pressure applied to inject the metal into the cavity. Due to this procedure, the produced parts manage to acquire better mechanical characteristics, dimensional precision, and smaller roughness. Due to the automation possibility, and mould coating possibilities, the process becomes cost competitive at significant production rates. However, to assure proper functioning and extended life of die casting equipment, it is necessary to continuously control the process variables, undertake maintenance, and implement process improvement actions to the production lines. The objective of the present work is to improve the efficiency of a Zamak die cast injection line for cable terminals used in Bowden or control cables for the automotive industry. By reducing wear and number of failures of standard components in this production line, and thus by diminishing the stoppage and replacement costs, it becomes possible to improve the current process. By applying specific improvements to the injection subset, heating element, and pump, including geometry modifications to the injection elements and respective interactions, heat treatments, higher power resistor, and groove/ring system in the pumps’ piston, a significant process improvement was accomplished by the proposed and tested modifications, leading to reduction of failures and operational costs, and consequently higher competitiveness of the process.

MicroRNAs role in telomere length maintenance and telomerase activity in tumor cells.

MiRNAs, a class of non-coding RNA molecules, have emerged as critical modulators of telomere length and telomerase activity by finely tuning the expression of target genes (and not gene targets) within signaling pathways involved in telomere homeostasis. The primary objective of this systematic review was to compile and synthesize the existing body of knowledge on the role, association, and involvement of miRNAs in telomere length. Additionally, the review explored the regulation, function, and activation mechanism of thehuman telomerase reverse transcriptase(hTERT) gene and telomerase activity in tumor cells. A comprehensive analysis of 47 selected articles revealed 40 distinct miRNAs involved in these processes. These miRNAs were shown to exert their function, in both clinical cases and cell line models, either directly or indirectly, regulating hTERT and telomerase activity through distinct molecular mechanisms. The regulatory roles of these miRNAs significantly affected major cancer phenotypes, with outcomes largely dependent on the tissue type and the cellular actions within the tumor cells, whereby they functioned as oncogenes or tumor suppressors. These findings strongly support the pivotal role of miRNAs in modulating telomere length and telomerase activity, thereby contributing to the intricate and complex regulation of telomere homeostasis in tumor cells.Moreover, they emphasize the potential of targeting miRNAs and key regulatory genes as therapeutic strategies to disrupt cancer cell growth and promote senescence, offering promising avenues for novel cancer treatments.

An optimization model for determining cost-efficient maintenance policies for multi-component systems with economic and structural dependencies

In most multi-component systems, the cost-efficiency of maintenance policies depends on technical structural dependencies. Motivated by the recognition that these dependencies must be accounted for in the development of optimal maintenance policies, we develop an optimization model to determine cost-efficient maintenance schedules for multi-component systems. Our main contribution is twofold. First, we introduce directed graphs as an expressive tool to represent the economic and structural dependencies of the system, including situations in which the maintenance of a given component may require other components to be disassembled or maintained. Second, we formulate a Markov Decision Process model, which is solved through the modified policy-iteration algorithm to determine the most cost-efficient policy. This policy indicates which maintenance actions consisting of disassembly and component replacement decisions are optimal when mandatory replacements must be made whenever the system fails, or the reliability of the system falls below a predefined reliability threshold. To our knowledge, this is the first model that provides optimal maintenance policies that comply with reliability requirements in the presence of constraints arising from technical structural dependencies. We illustrate the model with a realistic case study on the development of cost-efficient maintenance policies and show that its results compare favorably with heuristic maintenance policies.

Strategies to Optimize the Deployment of Roadway Maintenance Machines for Overnight Maintenance in Urban Rail Systems

This research investigates the effectiveness of several strategies to deploy roadway maintenance machines (RMMs) in preparation for overnight maintenance in rapid transit systems. Owing to the short windows of time available for maintenance activities in the overnight period (i.e., when revenue service is suspended), efficient deployment of RMMs is an important aspect of ensuring adequate productive time for crews at work locations. Four deployment strategies are investigated: optimizing the long-term yard storage locations of RMMs; optimizing the assignment of RMMs to work zones; optimizing the use of nonrevenue locations within the network to “preposition” RMMs closer to their work zones; and optimizing the routing and scheduling of RMMs through the network to reach the work zones. The strategies have been tested using data from the Washington Metropolitan Area Transit Authority. The results indicated that the proposed strategies reduced the time needed for RMM deployment. In the case of prepositioning, the median prepositioned RMM was deployed 23 min earlier than in the baseline (i.e., routing and scheduling alone) scenario, and the median RMM receiving a new yard storage location was deployed 16 min earlier. This was achieved without widespread negative impacts to RMMs that could not benefit from the proposed strategies for operational reasons. The results also demonstrated the potential of the routing and scheduling model as a tool to evaluate the deployment time impacts of distance-minimizing strategies, considering factors such as conflicts between RMMs and the availability of tracks to avoid disruptions to revenue service.

Characteristics of life-cycle carbon dioxide emissions of arterial highway maintenance and the influencing factors

With the focus of highway development transitioning from construction to maintenance, a comprehensive understanding of the characteristics and influencing factors of carbon dioxide (CO2) emissions from highway maintenance activities is crucial for formulating effective strategies to promote the low-carbon development of road infrastructure. However, the quantitative relationships between CO2 emissions from highway maintenance schemes and factors such as pavement deterioration, traffic volume, and road grade remain unclear owing to a lack of comprehensive, multi-category, and real data. Using real maintenance data from 340 arterial highway segments in China, this study conducts the life cycle assessment (LCA) to estimate CO2 emissions from maintenance activities and examines the primary emission sources among various structural layers and materials. Furthermore, multiple linear regression (MLR) analysis is conducted to investigate the impact of traffic volume, road grade, and pavement deterioration on CO2 emissions from maintenance projects, and factors influencing the early-stage degradation of pavement performance. The results demonstrate that average CO2 emissions from heavy rehabilitation projects are 6.97 times higher than those from medium rehabilitation projects. Emissions from heavy rehabilitation projects exhibit a significantly negative linear relationship with the riding quality index (RQI) before maintenance (p < 0.05), and emissions from medium rehabilitation projects show a significant negative linear relationship with the pavement condition index (PCI) before maintenance (p < 0.05). Emissions from heavy and medium rehabilitation projects are significantly positively correlated with heavy vehicle traffic volume before maintenance (p < 0.05). Moreover, the early-stage degradation of PCI after heavy rehabilitation and RQI after medium rehabilitation exhibit significantly negative linear relationships with their respective indicators before maintenance (p < 0.05). The early-stage degradation of RQI after heavy rehabilitation is significantly positively correlated with CO2 emissions from the base course and cushion layers (p < 0.05). The findings emphasize that timely maintenance and reduction of CO2 emissions from asphalt mixing equipment are essential for mitigating emissions from road maintenance. This study offers valuable insights for advancing the low-carbon development of highways in temperate regions.

Fuzzy FMEA-Resilience Approach for Maintenance Planning in a Plastics Industry ‎

The productivity and efficiency of industrial systems are highly affected by failures and machine breakdowns. Further, in asset-intensive industries, unexpected failures are considered the primary source of operational risk. In response, the maintenance department strives to calculate reliable estimates of the risk levels associated with such failures and develop resilient maintenance strategies that enable it to respond effectively to equipment failures. The research developed a framework for integrating fuzzy failure mode and effects analysis (FFMEA) with resilience engineering (RE) concepts for maintenance planning. The framework consists of four main stages: FFMEA, Risk iso-surface (RI), resilience assessment, and maintenance planning. In FFMEA, multiple sub-factors were considered for each main risk factor and evaluated using fuzzy logic. Then, in the RI stage, the risk priority number (RPN) was calculated through a fuzzy approach that considered the order of the importance of the main three risk factors. The fuzzy resilience assessment was applied through a survey of fifty-one questions related to the main four RE potentials to determine the need for resilient maintenance strategies. Finally, the RPN-Resilience diagram was employed to classify maintenance activities into six main maintenance strategies. A case study from a production line of plastic bags was used for illustration. The main advantage of the proposed FFMEA is that it divides the main risk criteria into sub-criteria to increase the accuracy of risk assessment and evaluate resilience potentials under fuzziness. In conclusion, the integration of the risk-resilience evaluation is a valuable tool for effectively planning maintenance activities.

Diagnosis, treatment and burden in advanced ovarian cancer: a UK real-world survey of healthcare professionals and patients.

Aim: Little is known regarding uptake of epithelial ovarian cancer (EOC) treatments or patient burden in UK real-world practice.Methods: Cross-sectional surveys of patients with advanced EOC and healthcare professionals (HCPs).Results: 101 HCPs and 142 patients participated. Time from initial primary care consultation to diagnosis was ∼7weeks. 83% patients were offered hereditary genetic testing, with 89% uptake. 53% HCPs reported surgery was performed ≤1month in non-neoadjuvant setting. Surgery delay negatively impacted patient quality of life(61%), mental health (89%), and surgical outcomes (63%). 56% patients received active first-line maintenance treatment; patients on active surveillance had greater emotional/psychological distress.Conclusion: Treatment delays and low uptake of active first-line treatment should be addressed. Emotional support must be readily accessible throughout treatment.

Human reliability analysis in maintenance and repair operations of mining trucks: A Bayesian network approach

Failures in mining machinery can abruptly halt mineral production and operations, emphasizing the indispensable role of humans in maintenance and repair operations. Addressing human errors is crucial for ensuring a safe and reliable system, particularly during maintenance activities where accidents frequently occur. This paper focuses on evaluating Human Reliability (HR) to enhance activity implementation effectiveness. Given the challenge of limited and uncertain data on human errors, this study aims to estimate the probability of human errors using Bayesian networks (BN) under uncertain parameters. Applying this approach to assess HR in the maintenance and repair operations of mining trucks at Golgohar Iron Ore Mine in Iran, the study identifies critical factors influencing error occurrence in a fuzzy environment. The results highlight key factors impacting human error and offer insights into estimating HR with minimal human intervention.

FSBOA: feature selection using bat optimization algorithm for software fault detection

Feature selection (FS) plays a crucial role in software fault prediction (SFP), aiming to identify a subset of relevant and discriminative features from a large pool of software metrics. It serves as a critical preprocessing step in building accurate fault prediction models, enabling the identification of potential software faults early in the development life cycle and facilitating effective resource allocation for testing and maintenance activities. The study's objective is to determine how well the bat optimization algorithm (BOA) can extract the features that are most important for correctly predicting software flaws, improve the accuracy of fault prediction, reduce the dimensionality of the feature space, and mitigate the risk of overfitting, thereby enabling more effective resource utilization and better allocation of testing efforts. The forecasting models underwent testing and training utilizing a collection of software metrics, with the datasets undergoing evaluation using several different FS algorithms. An assessment was conducted by contrasting the effectiveness of multiple optimization algorithms, including evolutionary methods such as FS employing genetic algorithm (FSGA), FS employing differential evolution (FSDE), and swarm-based techniques such as FS employing ant colony optimization (FSACO), FS employing particle swarm optimization (FSPSO), FS employing firefly algorithm (FSFA), and FS employing binary grey wolf optimization algorithm (FSBGWO) in relation to FS employing bat optimization algorithm (FSBAO). The results obtained from FSBAO approach demonstrate the effectiveness in solving FS optimization problems with at most accuracy of 98.92%. Furthermore, the experimental results have been statistically validated for the greater efficiency of the proposed FSBAO algorithm. This study's findings have crucial implications for developing a software failure prediction models that is more accurate and efficient.

Maintainability Assessment during the Design Phase: Integrating MTA and UNE 151001

The focus on maintenance actions in the early design phases has been a trend in recent years. The main sources of information during the design of the maintainability process include operator reports, maintainer experience, failure history, and manufacturer recommendations. During this process, an important aspect is related to the configuration of maintenance tasks and interventions, such as their main phases, activities, and durations. The allocation or estimation of maintainability involves identifying and/or estimating the mean time to repair (MTTR) for each component or system. The time of the maintenance tasks or the repair time are fundamental for companies, as the availability of equipment directly depends on this parameter. In this study, a new method for evaluating maintainability during the design phases is proposed. The method is based on the integration of the maintenance task analysis (MTA) principles and the UNE 151001 maintainability evaluation standard. A data structure is proposed that serves the application of the UNE151001 procedures, obtaining a data-based maintainability evaluation. As a validation procedure, an application of the proposed approach is presented using two overhead cranes. Comparisons and recommendations are made regarding the maintainability of both pieces of equipment. Finally, some managerial and engineering insights are presented.

Development of Stabilizing Solution for Long-Term Storage of Bacteriophages at Room Temperature and Application to Control Foodborne Pathogens.

Bacteriophages (phages) have gained considerable attention as effective antimicrobial agents that infect and kill pathogenic bacteria. Based on this feature, phages have been increasingly used to achieve food safety. They are stored in a medium or buffer to ensure stability; however, they cannot be directly applied to food under these conditions due to reasons such as regulatory considerations and concerns about marketability. This study developed a stabilizing solution that allowed the maintenance of phage activity for extended periods at room temperature while being directly applicable to food. The stability of phages stored in distilled water was relatively low. However, adding a stabilizer composed of sugars and salts improved the survival rates of phages significantly, resulting in stability for up to 48 weeks at room temperature. When Escherichia coli O157:H7-contaminated vegetables were washed with tap water containing phages, the phages reduced the pathogenic E. coli count by over 90% compared with washing with tap water alone. Additionally, when pathogenic E. coli-contaminated vegetables were placed in a phage-coated container and exposed to water, the coating of the container dissolved, releasing phages and lysing the pathogenic E. coli. This led to a significant 90% reduction in pathogenic E. coli contamination compared to that after water rinsing. These results suggest an effective and economical method for maintaining phage activity and establishing the potential for commercialization through application in the food industry.

A generic logic model for physical activity interventions for the cardiac population using intervention mapping

Abstract Introduction Regular physical activity is important in the secondary prevention of cardiovascular disease. But many cardiac patients have difficulty establishing lifelong physical activity habits, even after completion of an exercise-based cardiac rehabilitation programme. There is a need for effective interventions to support cardiac patients' physical activity. Such interventions are often complex behaviour change interventions whose design should be grounded in programme theory, i.e., a description of how the intervention is expected to lead to its effects and under what conditions. A logic model is often used to communicate programme theory [1]. Purpose The purpose of this work was to describe a generic logic model for behaviour change interventions to increase and maintain physical activity among patients who have had an acute cardiac event. Methods We applied the Intervention Mapping approach [2] to develop a generic logic model that is both data- and theory-driven, i.e. informed by research evidence and behaviour change theory. The at-risk behaviour for the individual cardiac patient was defined as "insufficient independent long-term maintenance of heart-healthy physical activity", compounded by the environmental factor "lack of support provision for long-term independent physical activity" from the healthcare providers and people in the patient’s interpersonal environment. We defined performance objectives by asking the questions: "What do people who had an acute cardiac event need to do to increase and maintain their heart-healthy physical activity?" and "What do the healthcare providers and people in the patient’s interpersonal environment need to do to encourage and support the patient in being physically active?" The performance objectives specify what actions are required of the individuals targeted in the intervention. We selected determinants corresponding to performance objectives based on empirical evidence from systematic reviews and based on behaviour change theory such as the Reasoned Action Approach (RAA) and the Health Action Process Approach (HAPA). Results Central elements of the logic model are presented in table 1. The logic model includes 18 performance objectives and 13 determinants, supported by empirical evidence from 40 scientific publications. Conclusion The generic logic model serves as a collection of current knowledge regarding increasing and maintaining physical activity among the cardiac population and can be used for a number of purposes: as a foundation for developing new interventions; as a blueprint against which to compare and/or solidify the programme theory of existing interventions; as a conceptual framework for designing evaluations of interventions; as a current evidence map from which to identify research gaps; and as a point of reference for reflecting on one’s own health behaviour.Table 1.Elements of the logic model.

Performability analysis for the SPVC line system of leaf spring production plant using probabilistic approach

PurposeThis work ensures the higher performability of this complex system, which consists of five different subsystems, i.e. shearing machine, V-cutting machine, center hole punch, edge cutting burr and drilling machine. These subsystems are placed in combinations of both series and parallel arrangement. The concerned plant management must be aware of the failures that have the greatest/least impact on the system’s performance.Design/methodology/approachPerformability analysis has been done for the Shearing, Punch and V- Cutting (SPVC) line system by using a probabilistic approach (i.e. Markov method). This system was further divided into five subsystems, and single-order differential equations are derived using the transition diagram. MATLAB software was used to determine the performability of the system for various combinations of repair and failure rates.FindingsIn this research work, performability analysis was done using different combinations of repair and failure rates for these subsystems. Further, a decision matrix (DM) has been developed that indicates that edge cutting burr is the most critical subsystem, which requires the top level of maintenance priorities among the various subsystems. This matrix will facilitate policymaking related to various maintenance activities for the respective system.Originality/valueIn this research work, a mathematical modeling based on a single differential equation using a transition diagram has been developed for the SPVC line system. The novelty of this work is to consider interaction among different subsystem, which generates more realistic situation during modeling. The purposed DM helps make future maintenance planning, which reduces maintenance costs and enhances system's performability.

Research on the application of renewable energy in power system based on adaptive hierarchical fuzzy logic maintenance

Condition-based maintenance is very desirable for minimizing the maintenance and failure costs of power systems without sacrificing reliability. A systematic approach including an adaptive maintenance advisor and a system maintenance optimizer is proposed here for effectively handling the operational variations and uncertainties for condition-based maintenance. First, the maintenance advisor receives and implements the maintenance plans for its key components from the system maintenance optimizer, which optimizes the maintenance schedules with multi-objective evolutionary algorithm, considering only major system variables and the overall system performance. During operation, the offshore substation will experience continuing ageing and shifts in control, weather and load factors, measurement and human judgment detected from the connected grid and all other equipments with uncertainties. Then, the advisor estimates the changes of reliability indices due to operational variations and uncertainties of its key components by hierarchical fuzzy logic and sends the changes back to the maintenance optimizer. The maintenance optimizer will upgrade the load-point reliability and report any drastic deterioration of reliability within each substation, which may lead to re-optimization of the substation's maintenance activities for meeting its desired reliability. The offshore substation connected to a medium-sized onshore grid will be studied here to demonstrate the ability of this proposed approach in dealing with uncertainties in the implementation of maintenance with significant reduction of computational complexity and rule base.