Planning Of Maintenance Activities Research Articles

HBIM tools for knowledge, maintenance and conservation of concrete built heritage

In the 20th century, reinforced concrete was one of the most popular building materials. It was formerly regarded as a material of outstanding durability and resilience, but over the past 50 years, it has revealed severe fundamental flaws. Main weaknesses of concrete include susceptibility to chemical agents and degradation brought on by poor design and construction. As a result, restoration interventions, recovery efforts, and re-functionalization of these artifacts have progressively grown in recent decades. Only when these improvements are combined with ongoing maintenance are they effective in extending the life of the structure. The most accurate knowledge of the building and all of its components can improve the efficiency of maintenance and recovery actions.
 Recently, the use of BIM tools for reinforced concrete buildings is spreading more and more, going beyond new construction to include built heritage. A BIM model of an existing asset may be used to assess the building's condition of conservation, pinpoint any issues, and assess the alternatives available for repair and conservation while projecting the impact of the adjustments on the structure. This data may be used to plan maintenance and restoration activities, track the building's condition of conservation through time, and assess the effects of any alterations on the structure.
 In this work, a workflow for "reverse engineering", enabling the creation of an HBIM model of an existing building, is proposed and then applied to a case study building.
 This technique may be regarded as a watershed moment in the management of reinforced concrete structures since it simplifies and organizes all of the information needed to preserve the existing architectural heritage while utilizing available resources.

Computational study of the dose-rate field of an ITER heat exchanger due to activated corrosion products

In ITER (Nuclear Facility INB-174), ACPs (Activated Corrosion Products) deposited in the cooling channels will represent a major contribution to the radiation field during machine shutdown. The primary cooling circuit includes eight Heat Exchangers (HXs) which host thousands of small pipes in the so-called bundles, where the heat is transferred from the primary to the secondary circuit and where ACPs accumulate. The accurate calculation of the radiation associated with these hot spots is needed, to ensure that the radiological zoning is respected during the planned maintenance activities in the ITER Equipment Vault. To characterize the impact of one HX on the radiation levels, three computational models were produced and simulated. The first one, called no-bundle model, was an unrealistically conservative model that omitted the steel of the bundle pipes, which resulted in extremely high dose rates surrounding this component. In the second one, called simplified-bundle model, the mass of the bundle pipes was considered by defining a bundle cell with a homogeneous material. To ensure the validity of this computational representation, a third model, called detailed-bundle model, was produced with the most realistic up-to-date model of the HX. The detailed-bundle model included an explicit representation of the complete bundle realized with automated modelling techniques. The radiation source deposited onto the thousands of surfaces of the bundle pipes was simulated explicitly using dedicated developments in D1SUNED. The dose field surrounding one HX was calculated with the detailed model and compared with the simplified, second model, showing good agreement. The simulation of the detailed-bundle model allowed us to reliably lower the dose rates estimates, by a factor of 8-10, compared to the first, unrealistic model. The validation of the simplified-bundle model will be used to practically evaluate the Occupational Radiation Exposure and to assess dose reduction measures for this component.

Automated machine learning recognition to diagnose flood resilience of railway switches and crossings

The increase in demand for railway transportation results in a significant need for higher train axle load and faster speed. Weak and sensitive trackforms such as railway switches and crossings (or called ‘turnout’) can suffer from such an increase in either axle loads or speeds. Moreover, railway turnout supports can deteriorate from other incidences due to extreme weather such as floods which undermine cohesion between ballast leading to ballast washaway or loss of support under turnout structures. In this study, new intelligent automation based on machine learning pattern recognition has been built to detect and predict the deterioration of railway turnouts exposed to flooding conditions which is the scope of this study. Since the turnout system is very complex by nature, different features and smart filtering are explored to find the potential features for deep learning. Nonlinear finite element models validated by actual field measurements are used to mimic the dynamic behaviors of turnout supports under flooding conditions. The study exhibits that the novel recognition model can achieve more than 98% accuracy, yielding the potential capability to recognize and classify turnout support deteriorations facing extreme weather conditions which will be beneficial for responsible parties to schedule and plan maintenance activities.

Main Bearing Fault Prognosis in Wind Turbines based on Gated Recurrent Unit Neural Networks

The transition from onshore to offshore wind farms is an imminent fact in the future. It supposes to face hard challenges like difficulties to carry out offshore maintenance operations due to increased downtime (because of several causes like continuously bad environmental conditions) on wind farms. That is why, there is a need to improve maintenance and monitoring practices like those involved in condition-based area. This work proposes a methodology based on three key points: (i) a semi-supervised model built from a gated recurrent unit (GRU) neural network and by using only healthy real SCADA data, (ii) propose a fault prognosis indicator (FPI) to trigger warnings or fault alarms as such, and (iii) detect the main bearing fault several months in advance on a faulty wind turbine. The reported results show the excellent performance of the GRU trained model to predict the main bearing temperature as output by exploiting the capabilities of GRUs (recurrent-based neural networks) to decide what information to forget or preserve through time. In the FPI construction, the use of exponentially weighted moving average (EWMA) helps at the results to avoid the presence of false alarms that is very useful in any detection strategy. Finally, the stated methodology lets to detect the main bearing fault on a WT two months in advance at least, which contributes to plan maintenance actions ahead of time. Furthermore, in this way, the lifespan of this large component may be extended and wind turbine’s uptime may increase in a significant percentage.

Evaluation of the residual carrying capacity of a large-scale model bridge through frequency shifts

Structural systems are often subjected to degradation processes due to different kinds of phenomena like unexpected loadings, ageing of the materials, and fatigue cycles. This is true, especially for bridges, in which their safety evaluation is crucial for planning maintenance activities. This paper discusses the experimental evaluation of the residual carrying capacity from frequency changes due to distributed damage scenarios. For this purpose, in the laboratory of the University of Bologna, an experimental reinforced concrete model bridge was built and loaded. The applied forces produced bending moments causing up to three increasing levels of damage severity, namely early and diffused concrete cracking, and finally rebar yielding. By processing the acceleration signals recorded during the dynamic tests on the model bridge, the main natural frequencies of the bridge were obtained and the remaining bearing capacity was estimated based on the damage state. The opening and closure of cracks during a dynamic excitation produced a biased estimation of natural frequencies related to each damaged condition. The frequency decay predicted by the theory of breathing cracks applied to the performed experiments properly estimated the losses in the carrying capacity.

A hierarchical Bayesian regression framework for enabling online reliability estimation and condition-based maintenance through accelerated testing

Thanks to the advances in the Internet of Things (IoT), Condition-based Maintenance (CBM) has progressively become one of the most renowned strategies to mitigate the risk arising from failures. Within any CBM framework, non-linear correlation among data and variability of condition monitoring data sources are among the main reasons that lead to a complex estimation of Reliability Indicators (RIs). Indeed, most classic approaches fail to fully consider these aspects. This work presents a novel methodology that employs Accelerated Life Testing (ALT) as multiple sources of data to define the impact of relevant PVs on RIs, and subsequently, plan maintenance actions through an online reliability estimation. For this purpose, a Generalized Linear Model (GLM) is exploited to model the relationship between PVs and an RI, while a Hierarchical Bayesian Regression (HBR) is implemented to estimate the parameters of the GLM. The HBR can deal with the aforementioned uncertainties, allowing to get a better explanation of the correlation of PVs. We considered a numerical example that exploits five distinct operating conditions for ALT as a case study. The developed methodology provides asset managers a solid tool to estimate online reliability and plan maintenance actions as soon as a given condition is reached.

Evaluating Short-Wave Effects in Railway Track Using the Rail Surface Signal

Condition assessment and maintenance planning of railway infrastructure is a prerequisite for safe and reliable train operation. As the loads are constantly increasing, condition assessment of the track must also be further developed. Existing methods can describe the condition of the track well in many cases, but they will reach their limits with faster deterioration processes and shorter time windows for inspection and maintenance, both associated with higher loads. This development can only be countered with an increased understanding of the system and the associated better planning of component specific measures. Among others, short-wave effects of the track need to be considered. The aim of this paper is to demonstrate the possibility of describing short-wave effects with an already existing data source. Insulated rail joints, welding joints, switch components, but also rail corrugation of different wavelengths and squat can be detected, evaluated and monitored by a measuring system based on optical distance meters. These assets and wear phenomena form essential parts of track asset management, but still are not described sufficiently by established methods. Although the so-called rail surface measurement system has been installed on the main Austrian measuring car for years, its full potential could not be exploited due to insufficient positioning accuracy. The method presented in this paper intends to change that. This allows for a holistic assessment of track condition when planning maintenance activities.

The Application of Homogeneous Markov Chains in the Analysis of the Technical State of Tractors

Planning maintenance activities on tractors can be improved and become more effective when using a mathematical apparatus for modelling the processes of the operation and maintenance of machines and tractors using homogeneous Markov chains. For this purpose, it is necessary to switch from the traditional methods for determining the indicators of their technical state to dynamic methods based on the theory of random processes. The most promising method is the use of homogeneous Markov chains. Based on the accumulated statistical data, it is possible to determine the probabilities of transition from one technical state to another. The values of the transition probabilities are used to construct a probability matrix describing a simple Markov chain. For tractors, taking into account the approaching of their limit state, which is characterized by the full depletion of resources, an absorbing Markov chain is best suited. The algorithms for the decomposition and study of the properties of reducible absorbing Markov chains, which allow obtaining useful information for an efficient operation, maintenance and repair of tractors and complex agricultural machinery, are presented.

Life Cycle Assessment for Adaptive Remanufacturing: incorporating ecological considerations into the planning of maintenance activities – a case study in the German heavy machinery industry

Driven by the awareness of the global depletion of irrecoverable materials, cradle-to-cradle approaches like remanufacturing are enablers for increasing sustainability and resource efficiency in the manufacturing sector. In this context, the research project Adaptive Remanufacturing for Life Cycle Optimization of Capital Goods (ReLIFE) offers a holistic approach for a proactive, intelligent maintenance strategy with a focus on the life cycle extension of capital goods. As quantitative input to a decision-making model, Life Cycle Assessment (LCA) has been used to present comparative results between a traditional maintenance strategy and an Adaptive Remanufacturing (AdR) strategy. In contrast to conventional LCA, the contribution of this paper is on the impacts incurred by specific maintenance measures. Therefore, the scope of assessment encompasses a life cycle on measure level to model and assess long-term ecological effects. For a decision-making model created in the project, the LCA results enable plant operators to select maintenance strategies that factor in long-term ecological implications.

Multi-objective maintenance planning under preventive maintenance

PurposeThis research developed and examined a mathematical model for concurrent corrective and preventive maintenance policy of a system of series configuration.Design/methodology/approachA mathematical model was developed to maximize availability, and maximal net revenues, and minimal cost. Different probability distributions for time to failure and time to repair were considered. The model was then implemented on a real case study, which was studied under corrective maintenance policy and concurrent corrective and preventive policy.FindingsA comparison between results at current policy (90 days) and optimal period of corrective and preventive policy was conducted. It was found that availability, profit was increased from 94.4% and $20.091 – 96.5% and $24.803, respectively. Further, the cost was reduced from $1104.8 to $797.22.Research limitations/implicationsThe proposed optimization model can be adopted in planning maintenance activities for a single machine as well as for a system of series configuration machines under various probability distributions.Practical implicationsThe proposed model can significantly enhance performance of the production as well as maintenance systems. In addition, the developed model may support maintenance engineering in effective management of maintenance resources and the performance of its activities.Originality/valueThis research considers a mathematical model with multi-objective functions and distinct probability distributions for time-to-failure for a system of series machines. Moreover, appropriate approximation solution was deployed to find integral of some functions. Finally, it provides maintenance planning for a single machine or a series of machines.

Operating Environment effect on Remaining Useful Life Case study: Sungun Copper Mine

The Remaining Useful Life (RUL) valuation of mining machinery is a principal to ensure the production/output and customer satisfaction in the mining zone. In many cases, it may be of attention to know the expected value of the remaining life of the item before it fails from an arbitrary time that known RUL. The system's failure is also evaluated with the reliability index, which describes up-times. An individual unit's reliability during field use is essential in many mining equipment applications. This index, especially in industrial systems, and being affected by the internal condition also affects operating environmental conditions. For example, the loader performance in cold weather will be different from that of warm, which will affect the machine's reliability and thus the RUL. In reliability engineering, operating environmental conditions are considered Risk factors or Covariates. Therefore, in this paper, an approach is proposed first to analyze the system's reliability considering covariates' effect and then estimate the RUL for different scenarios. The proportional hazard model was used in reliability analysis to be realistic and take the operational influencing factors in calculation. Methods are presented for calculating the reliability function and computing the RUL as a function of the current conditions to guarantee the desired output. The remaining useful life estimation of a Komatsu PC-1250 from the Sungun copper mine was evaluated as a case study of this approach. Systems operating environmental factors such as shift, dump-truck kind, rock kind, … (known as covariates) are assumed to influence covariate in this context. As a result, the Weibull proportional hazard model was fitted to describe the failure behavior, and the RUL of four selected scenarios was evaluated. Presented results can be used, e.g., for developing operational performance, planning of maintenance activities, spare parts provision, and the profitability of the owner of an asset.

Analysis of the Training Needs Identification of the Beneficiary Group (KPP) of the PNPM Pisew Program in Bengkulu Province

The objective of this research is to Acquire Preview Performance Recovery Group and maintainer, Knowing gaps/ inadequacies Recovery Working Group and maintainer, Identify training needed by administrators and custodians Recovery Group. This research is a descriptive study with a qualitative approach. Data were collected through questionnaire to 30 respondents and conducted interviews to 4 people and 4 Sub Working Group Facilitator District. Based on the results of the study found that the respondents (administrators group users and custodians) gives value - average overall element to the performance of groups of users and custodians are 2, 36 which means Not Good. Of the five elements / variables under study is related to availability of performance planning and budgeting infrastructure maintenance activities, the controlled utilization and maintenance of infrastructure, contributions of users as well as from the others is manageable, the availability of physical progress reports on a regular basis, the availability of technical skills of construction. For elements - elements that need to be improved, then the required training in order to cover a gap between the ideal performance/ standards organization with actual performance.

Automated and Controlled Data Collection Using Industrial IoT System for Smart Maintenance

Maintenance 4.0 is a concept that involves the use of IIoT (Industrial Internet of Things) technology to connect maintenance objects, which enables remote data collection, information exchange, analysis and potential improvement in productivity and efficiency, as well as planning maintenance activities. The purpose of this paper is to present the development of the Industrial Internet of Things data collection system, which relies on Tinkerforge IoT modules, that enables automated data collection alongside control of sensor and data collection parameters. To evaluate the ability of the system, an experiment was conducted where two equipment states were simulated using a rotational equipment failure simulator. The experiment determined that the presented IIoT system had successfully gathered information and that there is a clear distinction in acceleration patterns when simulating two different equipment states.

Predictive maintenance integrated production scheduling by applying deep generative prognostics models: approach, formulation and solution

To harness the full potential of predictive maintenance (PdM), PdM information has to be used to optimally plan production and maintenance actions. Hence, operation-specific modelling of degradation, i.e. predictions of the health condition under time-varying operational conditions, has to be realized. By utilizing operation-specific degradation information, maintenance and production can be planned with regard to each other and thus, predictive maintenance integrated production scheduling (PdM-IPS) is enabled. This publication proposes a novel PdM-IPS approach consisting of two interacting modules: an operation-specific Prognostics and Health Management (PHM) module and an integrated production scheduling and maintenance planning (IPSMP) module. Specifically, the mathematical problem of the IPSMP module based on an extended version of the maintenance integrated flexible job shop problem is formulated. A two-stage genetic algorithm to efficiently solve this problem is designed and subsequently applied to simulated condition monitoring, as well as real industrial data. Results indicate that the approach is able to find feasible high quality PdM integrated production schedules.

Mathematical Approach for System Repair Rate Analysis Used in Maintenance Decision Making

Reliability, the number of spare parts and repair time have a great impact on system availability. In this paper, we observed a repairable system comprised of several components. The aim was to determine the repair rate by emphasizing its stochastic nature. A model for the statistical analysis of the component repair rate in function of the desired level of availability is presented. Furthermore, based on the presented model, the approach for the calculation of probability density functions of maximal and minimal repair times for a system comprised of observed components was developed as an important measure that unambiguously defines the total annual repair time. The obtained generalized analytical expressions that can be used to predict the total repair time for an observed entity are the main contributions of the manuscript. The outputs of the model can be useful for making decisions in which time interval repair or replacement should be done to maintain the system and component availability. In addition to planning maintenance activities, the presented models could be used for service capacity planning and the dynamic forecasting of system characteristics.

Degradation stage classification via interpretable feature learning

Predictive maintenance (PdM) advocates for the usage of machine learning technologies to monitor asset's health conditions and plan maintenance activities accordingly. However, according to the specific degradation process, some health-related measures (e.g. temperature) may be not informative enough to reliably assess the health stage. Moreover, each measure needs to be properly treated to extract the information linked to the health stage. Those issues are usually addressed by performing a manual feature engineering, which results in high management cost and poor generalization capability of those approaches. In this work, we address this issue by coupling a health stage classifier with a feature learning mechanism. With feature learning, minimally processed data are automatically transformed into informative features. Many effective feature learning approaches are based on deep learning. With those, the features are obtained as a non-linear combination of the inputs, thus it is difficult to understand the input's contribution to the classification outcome and so the reasoning behind the model. Still, these insights are increasingly required to interpret the results and assess the reliability of the model. In this regard, we propose a feature learning approach able to (i) effectively extract high-quality features by processing different input signals, and (ii) provide useful insights about the most informative domain transformations (e.g. Fourier transform or probability density function) of the input signals (e.g. vibration or temperature). The effectiveness of the proposed approach is tested with publicly available real-world datasets about bearings' progressive deterioration and compared with the traditional feature engineering approach.

Building condition assessment supported by Building Information Modelling

The buildings natural ageing along with the absence of planned maintenance actions and the effects of climate changes accelerate the building materials degradation. So, to extend the materials’ service life, the application of appropriate maintenance actions is imperative. This work aims to assess the building performance and to prioritize the maintenance actions employing Key Performance Indicators using Building Information Modelling-(BIM) as a supporting tool for Building Condition Assessment-(BCA) and maintenance management. To achieve these goals a methodology was proposed and applied to a case study involving 1) Building data collection; 2) Building Life Cycle Cost estimation, and 3) Automated calculation of Building Performance Indicator. This research application highlights the importance of BIM role in buildings' Facility Management, allowing the model's permanent update of information, in this case for BCA purposes. It also has high potential to prioritize the building maintenance actions, extending its materials service life, which contribute to attain a sustainable built environment.

A multimodal solution approach for mitigating the impact of planned maintenance on metro rail attractiveness

The possible unavailability of urban rail-based transport services due to planned maintenance activities may have significant consequences on the perceived quality of service, thus affecting railway attractiveness. To cope with the mitigation of planned service interruptions and to guarantee a seamless journey and a good travel experience for passengers, it is possible to exploit the existing services differently and/or provide additional on-demand services, such as temporary supplemental bus lines. In this context, this paper aims to develop a mathematical programming model for planning service interruptions due to maintenance considering passenger transport demand dynamics. In particular, the proposed approach deals with service interruptions characterized by a long duration for which timetable adaption strategies are not applicable, suggesting mitigation actions that exploit the already existing services and/or the activation of additional ones, with the aim of minimizing users' inconvenience. In doing so, the planned infrastructure status (i.e., available or under maintenance), as well as the forecasted transport demand, are taken into account to adapt the service accordingly by offering a multimodal transport solution to passengers. To find the best solution, a decomposition solution approach is proposed in combination with a multistage cooperative framework with feedback that models the negotiation process between the involved actors. Finally, the applicability of the proposed approach to real case studies is discussed based on some performance indicators.

Adaptive prognostics in a controlled energy conversion process based on long- and short-term predictors

The pulp and paper industry is a fundamental sector of the economy of many countries. However, this sector requires real collaboration and initiatives from stakeholders to reduce its significant consumption of energy and emission of greenhouse gases. Heat exchangers are examples of equipment in pulp mills that are subjected to undesirable and complex phenomena such as evolution of fouling over time, which leads to inefficiency in terms of energy consumption and unplanned shutdowns, resulting in ineffective maintenance strategies and production costs. Therefore, there is a clear need to develop an accurate predictive maintenance tool that helps mill operators avoid such situations. It is necessary for that tool to effectively track the fouling evolution level and, based on it, deploy a reliable prognostics approach to estimate more accurately the time-to-clean of this equipment. This study presents a new hybrid prognostics approach for fouling prediction in heat exchangers. The proposed approach relies on the fusion of information of different prediction horizons to estimate the time-to-clean. Employing long short-term memory, it allows adaptation of long-term predictions by accurate short-term predictions using multiple non-linear auto-regressive exogenous models. This fusion not only captures the changes in degradation trend over time, but also ensures a good accuracy of prognostics results in both the short- and long-term horizons for planning maintenance actions. The effectiveness of the proposed approach was successfully proven on real industrial data collected from a pulp mill heat exchanger located in Canada.

Managing infrastructure asset: Bayesian networks for inspection and maintenance decisions reasoning and planning

Models of maintenance problems must handle complex assumptions, allowing, for example, the condition of some assets to be rated directly using multiple states while in others the condition rating is inferred from that of the components from which they are assembled. The overall condition inferred, which informs the maintenance decisions, requires evidential reasoning under uncertainty. This paper uses Bayesian networks to address these challenges with real case studies. We apply the binary factorisation technique to allow inference of multi-state condition prediction, and further extend it to predict the condition of an asset with multiple components. These models are used to recommend inspection decisions such as which assets to inspect and when to inspect them. Models are also developed to evaluate the effectiveness of repair interventions and to use this to suggest repair actions. We show how to model multiple interventions within the asset life cycle considering both repair effectiveness and further deterioration. This modelling allows us to plan maintenance activities for an asset over its whole life cycle.