Condition-based Maintenance Approach Research Articles

A rolling horizon approach for production planning and condition-based maintenance under uncertain demand

In reality, the forecast of uncertainties often becomes more accurate with the approaching of the forecasted period. This article proposes a rolling horizon approach to dynamically determine the production plan and the maintenance plan for a degradation system under uncertain environment. In each rolling horizon, demand forecasts are updated with new information from customers, and the degradation level of system is confirmed by inspection. By taking advantage of the updated uncertainties, at each decision point, the maintenance plan is determined by an advance-postpone balancing approach and the production plan is optimized by a heuristic algorithm in a two-stage stochastic model. Numerical results validate that the rolling horizon approach has great superiority over traditional stochastic programming approach in terms of real total cost and service level.

Maintenance Decision-Making Support for Textile Machines: A Knowledge-Based Approach Using Fuzzy Logic and Vibration Monitoring

A condition-based maintenance approach may be used for planning the maintenance activities of textile machines with a satisfactory performance by developing maintenance decision-making support based on fuzzy logic and vibration monitoring. Since textile machines are systems with moving parts operating at relatively high-speed, vibration monitoring was used to indicate their failure development. At the same time, the characterization of the degradation phenomenon of textile machines involves some degree of uncertainty and vagueness. Within this context, a knowledge-based approach that employed fuzzy logic and vibration monitoring was developed. Deterioration symptoms do announce future failures of industrial machines, therefore building a maintenance decision-making support for scheduling maintenance actions of textile machines based on the estimation of their condition becomes a resourceful way to prevent their further deterioration.

Model-based Life Cycle Management Using Deterioration Simulation

An essential mission of life cycle management (LCM) is to manage the life time of a target system by understanding its states. Since LCM is becoming digitalized and various data throughout a product life cycle can be collected, a data-driven approach such as machine learning has been used. However, a data-driven approach has some drawbacks: a large volume of required data and so called “black box” problem of reasoning results. This paper proposes a model-based approach for condition-based maintenance, where deterioration simulation is executed. The deterioration simulation enables to examine all possible state changes when each part is deteriorated.

A decision support approach for condition-based maintenance of rails based on big data analysis

In this paper, a decision support approach is proposed for condition-based maintenance of rails relying on expert-based systems. The methodology takes into account both the actual conditions of the rails (using axle box acceleration measurements and rail video images) and the prior knowledge of the railway track. The approach provides an integrated estimation of the rail health conditions to support the maintenance decisions for a given time period. An expert-based system is defined to analyse interdependency between the prior knowledge of the track (defined by influential factors) and the surface defect measurements over the rail. When the rail health conditions is computed, the different track segments are prioritized, in order to facilitate grinding planning of those segments of rail that are prone to critical conditions. In this paper, real-life rail conditions measurements from the track Amersfoort-Weert in the Dutch railway network are used to show the benefits of the proposed methodology. The results support infrastructure managers to analyse the problems in their rail infrastructure and to efficiently perform a condition-based maintenance decision making.

Enabling condition-based maintenance decisions with proactive event-driven computing

Condition Based Maintenance (CBM) can take advantage of the emergence of Internet of Things (IoT) and the proactive event-driven computing paradigm for fully exploiting its capabilities by enabling proactive maintenance decisions ahead of time. In this paper, proactive event-driven computing is used as a lever in order to provide a holistic CBM approach along with an information system for generating proactive maintenance recommendations. Since the Detect and the Predict phases of the “Detect-Predict-Decide-Act” proactivity principle as applied to the CBM framework are well-studied fields in literature, the focus of the current research is on the Decide phase that is still an unexplored area. Therefore, in the context of this paper, the approach, contributing decision methods and technical specifications of an associated information system are defined and developed for this phase. The proposed approach is implemented in an information system, which is deployed and evaluated in the context of two real industrial scenarios in the area of oil and gas and automotive lighting equipment industries. The results of a comparative and a sensitivity evaluation analysis show that the proposed approach can enable industrial business transformation from a reactive to a proactive mode of operation, in order to eliminate maintenance-related losses and optimize business performance.

Prognostics of gas turbine: A condition-based maintenance approach based on multi-environmental time similarity

Abstract The maintenance cost of a gas turbine is significantly higher than its original purchase cost. This study presents a novel prognostic condition-based maintenance (CBM) approach based on the theory of multi-environmental time similarity (METS). In this approach, gas turbine of the same type is regarded as the reference system, and two influential factors - the running hours and number of start-ups are selected as the main degradation indicators. The similarities are calculated based on the values of the degradation indicators under service environment and benchmark environment. Equivalent life (EL) of the object system under the benchmark environment is calculated on the basis of the similarities and historical data of the object system under the service environment. Remaining life (RL) of the object system is obtained by comparing EL and theoretical life. Real-time RL, historical RL and their calculating algorithms are proposed for acquiring more accurate historical degradation data that can be employed for decision making. Factored service factor is proposed as a key indicator in decision making of CBM, and four optional CBM scenarios are constructed based on different values of the factored service factor. This approach is applied in a thermal power plant in Hangzhou, China, and its effectiveness is proved as an extra power generation of 302,640 MW·h can be achieved due to re-scheduled maintenance.

Predictive Maintenance of Machine Tool Linear Axes: A Case from Manufacturing Industry

In sustainable manufacturing, the proper maintenance is crucial to minimise the negative environmental impact. In the context of Cloud Manufacturing, Internet of Things and Big Data, amount of available information is not an issue, the problem is to obtain the relevant information and process them in a useful way. In this paper a maintenance decision support system is presented that utilises information from multiple sources and of a different kind. The key elements of the proposed approach are processing and machine learning method evaluation and selection, as well as estimation of long-term key performance indicators (KPIs) such as a ratio of unplanned breakdowns or a cost of maintenance approach. Presented framework is applied to machine tool linear axes. Statistical models of failures and Condition Based Maintenance (CBM) are built based on data from a population of 29 similar machines from the period of over 4 years and with use of proposed processing approach. Those models are used in simulation to estimate the long-term effect on selected KPIs for different strategies. Simple CBM approach allows, in the considered case, a cost reduction of 40% with the number of breakdowns reduced 6 times in respect to an optimal time-based approach.

Economic Assessment of Condition-based Maintenance with Statistical Process Monitoring

Fault detection and identification methods have received extensive study in the literature, but very rarely demonstrate the economic impact of these interventions. In this paper, a simulation of a two-tank system with economic performance functions is presented as a test-bed for process monitoring methods. The simulation includes sensor noise and process variation, control loops, and safety interlocks, as well as sensor failures. Simple process monitoring, by principal component analysis and contribution methods, is applied to single- and successive-sensor failure simulations, and the economic benefit of the proposed condition-based maintenance approach demonstrated, even for cases in which the faulty sensor was not correctly identified. Challenges with fault identification, root cause analysis and fault prognosis are discussed. Proposals are made for further development of the simulation, which has been made available for future research.

Differential evolution-based multi-objective optimization for the definition of a health indicator for fault diagnostics and prognostics

Abstract The identification of the current degradation state of an industrial component and the prediction of its future evolution is a fundamental step for the development of condition-based and predictive maintenance approaches. The objective of the present work is to propose a general method for extracting a health indicator to measure the amount of component degradation from a set of signals measured during operation. The proposed method is based on the combined use of feature extraction techniques, such as Empirical Mode Decomposition and Auto-Associative Kernel Regression, and a multi-objective Binary Differential Evolution (BDE) algorithm for selecting the subset of features optimal for the definition of the health indicator. The objectives of the optimization are desired characteristics of the health indicator, such as monotonicity, trendability and prognosability. A case study is considered, concerning the prediction of the remaining useful life of turbofan engines. The obtained results confirm that the method is capable of extracting health indicators suitable for accurate prognostics.

Developing Simulation Based Optimization Mechanism for Novel Stochastic Reliability Centered Maintenance Problem

This research investigates joint scheduling of maintenance and production planning. This novel integrated problem takes benefit of reliability-centered maintenance (RCM) for monitoring and managing maintenance function of a stochastic complex production-planning problem namely flexible job shop scheduling problem (FJSP). The developed RCM works based on stochastic shocking of machines during their process time. In fact, it implements condition based maintenance approach regulated according to stochastic reliability concept. Comparison of the system reliability with critical levels determines the failure statues of the machines. It activates two main types of reaction called preventive and corrective maintenance. Considering breakdown of the system between inspection intervals makes the proposed model more realistic. Moreover, maintenance activity times and their duration are considered stochastically. Because of the high complexity level for this joint system, simulation-based optimization (SBO) approach is proposed for solving the problem. This SBO searches the feasible area through genetic algorithm (GA) and biogeography based optimization (BBO) algorithm. Different test problems, statistical methods, novel visualizations are used to discuss the problem and the algorithm explicitly.

Analysis of the Results of Accelerated Aging Tests in Insulated Gate Bipolar Transistors

The introduction of fully electric vehicles (FEVs) into the mainstream has raised concerns about the reliability of their electronic components such as IGBT. The great variability in IGBT failure times caused by the very different operating conditions experienced and the stochasticity of their degradation processes suggests the adoption of condition-based maintenance approaches. Thus, the development of methods for assessing their healthy state and predicting their remaining useful life (RUL) is of key importance. In this paper, we investigate the results of performing accelerated aging tests. Our objective is to discuss the design and the results of accelerated aging tests performed on three different IGBT types within the electrical powertrain health monitoring for increased safety (HEMIS) of FEVs European Community project. During the tests, several electric signals were measured in different operating conditions. The results show that the case temperature $(T_{C})$ , the collector current $(I_{C})$ , and the collector–emitter voltage $(V_{{\rm CE}})$ are the failure precursor parameters that can be used for the development of a prognostic and health monitoring (PHM) system for FEV IGBTs and other medium-power switching supplies.

Evaluating Company's Maintenance Strategy Effectiveness by Maintenance Improvement Index - A Case Study

The purpose of this paper is to present development of a methodology for identifying improvement areas and supporting decision making process in the field of maintenance; an index for measuring the performance level of different maintenance approaches is proposed. Empirical data for this case study was drawn from a Slovenian textile company. The results of this study indicate that from respondents' points of view, maintenance practices related to condition-based maintenance approach represent the highest opportunity for improvements in this company. Further, this study provides key insights for managers to evaluate maintenance approaches, and to identify potential areas for improvements. In this regard, companies can gain a better understanding of how to measure and diagnose the effectiveness of the selected (implemented) maintenance strategy. As such, the presented work provides an intuitive and simple approach to identify the areas where a company effectively deploys its resources, and those areas that need more attention. Presented approach therefore represents an effective way of selecting areas for improvements for companies searching an approach how to improve effectiveness of maintenance strategy, and therefore company's competitiveness.

Efficiency Improvement of Nonuniformly Aged PV Arrays

The utilization of solar energy by photovoltaic (PV) systems has received much research and development attention across the globe. In the past decades, a large number of PV array have been installed. Since the installed PV arrays often operate in harsh environments, nonuniform aging can occur and impact adversely on the performance of PV systems, especially in the middle and late periods of their service life. Due to the high cost of replacing aged PV modules by new modules, it is appealing to improve energy efficiency of aged PV systems. For this purpose, this paper presents a PV module reconfiguration strategy to achieve the maximum power generation from nonuniformly aged PV arrays without significant investment. The proposed reconfiguration strategy is based on the cell-unit structure of PV modules, the operating voltage limit of grid-connected converter, and the resulted bucket effect of the maximum short-circuit current. The objectives are to analyze all the potential reorganization options of the PV modules, find the maximum power point, and express it in a proposition. This proposition is further developed into a novel implementable algorithm to calculate the maximum power generation and the corresponding reconfiguration of the PV modules. The immediate benefits from this reconfiguration are the increased total power output and maximum power point voltage information for global maximum power point tracking. A PV array simulation model is used to illustrate the proposed method under three different cases. Furthermore, an experimental rig is built to verify the effectiveness of the proposed method. The proposed method will open an effective approach for condition-based maintenance of emerging aging PV arrays.

Investigation on the use of energy efficiency for condition-based maintenance decision-making

Abstract: Condition-based maintenance (CBM) has been introduced in industrial systems to maintain preventively the correct equipment at the right time with regards to its current health “condition” represented mainly the conventional indicators such as oil temperature, harmonics data, vibration, etc. The monitoring of these indicators is done through sensors or inspection tasks leading to incorporate in the maintenance optimization models, additional costs related to CBM. Nevertheless, while this practice is quite mastered in terms of benefits and costs, it is not well adapted to face now the new challenge encountered by the “industry of the future” such as the sustainable one. Indeed CBM indicators and maintenance cost model are not really taken into account today emergent indicators (and their impacts) related to energy consumption, energy efficiency or footprint tracking. In that way, this paper is investigating the interest to use energy efficiency (EE) for CBM decision-making. Investigation is consisting first to propose a new EE-based CBM model by using energy efficiency indicator (EEI) which is defined as the amount of energy consumption to produce one useful output unit. The proposed model leads to consider energy directly in the maintenance optimization. An extension of an existing CBM by integrating energy consumption in optimization model is also investigated in the way to compare the new CBM approach with conventional (extended) one. The comparison step is developed on the case study of the TELMA platform allowing to assess the impact of EE on existing CBM strategies and to conclude on the interest of a new EE-based CBM practice both in terms of cost and efficiency.

A Cloud-based Approach for Maintenance of Machine Tools and Equipment Based on Shop-floor Monitoring

Maintenance and its cost continue, over the years, to draw the attention of production management since the unplanned failures decrease the reliability of the system and also the return of investments. Advanced maintenance techniques that capture and process shop-floor information can reduce costs and increase the sustainability of an enterprise. This paper presents a condition-based preventive maintenance approach integrated into a machine monitoring framework. The latter acquires data from shop-floor machine tools and analyses them through an information fusion technique to support the condition-based preventive maintenance operations. The proposed approach is developed into a software service, deployed on a Cloud environment. The service gathers and processes data, such as their actual processing time and machining time per tool, related to the operation of machine tools and equipment and calculates the expected remaining useful life of components. Moreover, it provides notifications to machine tool operators and maintenance departments, as well as it enables the communication among them using mobile technology. The framework is applied to a case study with data obtained from a machining SME.

Application Potentials for an Ontology-based Integration of Intelligent Maintenance Systems and Spare Parts Supply Chain Planning

In today's evermore complex manufacturing systems, effective and efficient maintenance has become crucial for achieving operational competitive advantages. Breakdowns and system failures caused by insufficient maintenance can lead to significant economic impact such as higher costs, diminishing profits and declined customer satisfaction. In order to avoid unforeseen systems’ unavailability, it is necessary to accurately and precisely forecast maintenance demand in advance – including the provision of maintenance services and spare parts. Moreover, the management and planning of spare parts supply chains has become more important in order to ensure the availability of spare parts and maintenance personnel at the required location and time while operating at reasonable costs. Both issues are recently targeted by the research domains of intelligent maintenance systems (IMS) – forecasting machine failures using a condition-based maintenance (CBM) approach – and spare parts supply chains (SPSC) – planning and providing related maintenance services and spare parts. A proper integration of these two domains enables the exchange of relevant information that could be applied for advanced failure forecasting, machine control and SPSC planning. However, the challenge of integrating both domains is to deal with the different meanings and knowledge, e.g., the concepts being applied in both domains vary in their level of granularity and importance. This paper addresses the integration problem of IMS devices and SPSC planning systems by presenting a refined ontology including concepts that semantically connect the different systems and thus provides the basis for a conceptual integration architecture and a deduced service-oriented architecture facilitating dynamic communication services to support the information exchange. Furthermore, the applied design of the ontology is described for an industrial case and the application potentials to be achieved by the integration of both system types are highlighted.

Remaining useful life prediction of rotating equipment using covariate-based hazard models – Industry applications

The ability to estimate the expected remaining useful life (RUL) is critical to reduce maintenance costs, operational downtime and safety hazards. In most industries, reliability analysis is based on the reliability-centred maintenance and lifetime distribution models. In these models, the lifetime of an asset is estimated using failure time data; however, statistically sufficient failure time data are often difficult to attain in practice due to the fixed time-based replacement and the small population of identical assets. When condition indicator data are available in addition to failure time data, one of the alternate approaches to the traditional reliability models is the condition-based maintenance (CBM). The covariate-based hazard modelling is one of CBM approaches. There are a number of covariate-based hazard models; however, little study has been conducted to evaluate the performance of these models in asset life prediction using various condition indicators and data availability. This paper reviews two covariate-based hazard models, proportional hazard model (PHM) and proportional covariate model (PCM). To assess these models’ performance, the expected RUL is compared to the actual RUL. Outcomes demonstrate that both models achieve convincingly good results in RUL prediction; however, PCM has smaller absolute prediction error. In addition, PHM shows over-smoothing tendency compared to PCM in sudden changes of condition data. Moreover, the case studies show PCM is not being biased in the case of small sample size.

On condition based maintenance policy

Abstract In the case of a high-valuable asset, the Operation and Maintenance (O&M) phase requires heavy charges and more efforts than the installation (construction) phase, because it has long usage life and any accident of an asset during this period causes catastrophic damage to an industry. Recently, with the advent of emerging Information Communication Technologies (ICTs), we can get the visibility of asset status information during its usage period. It gives us new challenging issues for improving the efficiency of asset operations. One issue is to implement the Condition-Based Maintenance (CBM) approach that makes a diagnosis of the asset status based on wire or wireless monitored data, predicts the assets abnormality, and executes suitable maintenance actions such as repair and replacement before serious problems happen. In this study, we have addressed several aspects of CBM approach: definition, related international standards, procedure, and techniques with the introduction of some relevant case studies that we have carried out.

Computerised Decision-Making Support System Based on Data Fusion for Machinery System’s Management and Maintenance

In the present fast-paced world of business in a highly competitive marketplace, the focus on increasing the efficiency of business processes seems to be a reasonable challenge. For this reason in order to optimize production costs, there is an increasing trend toward maximising the use of the operational capabilities of the equipment – technological line components – with the prevention of failure events and their consequences in the form of costly repairs or replacements. A condition-based maintenance (CBM) approach allows to globally monitor, maintain and control operation of the whole complex of equipment and/or processes. The CBM effectively supports decision-making process concerning their further use or determination of the optimum repair/replacement schedule. The presented decision support system is dedicated for an underground copper mine, where the network of belt conveyors is a critical part of the production process. Due to complexity of mechanical system, harsh mining environment and presence of many degradation factors, development of the effective CBM system seems to be justified. It requires the integration of data from different sources, adaptation of advanced data mining techniques, procedures or various diagnostic methods. Because of the multidimensional nature of diagnostic data and diversified technical configurations of the facilities, it was necessary to develop and implement multivariate analytical models based on artificial intelligence techniques. Consequently, it allows to achieve improvement of efficiency of transportation network and reduction of repairs costs and unplanned breakdowns. In this paper we will briefly refer to all these issues.

Machine learning approaches for improving condition-based maintenance of naval propulsion plants

Availability, reliability and economic sustainability of naval propulsion plants are key elements to cope with because maintenance costs represent a large slice of total operational expenses. Depending on the adopted strategy, impact of maintenance on overall expenses can remarkably vary; for example, letting an asset running up until breakdown can lead to unaffordable costs. As a matter of fact, a desideratum is to progress maintenance technology of ship propulsion systems from breakdown or preventive maintenance up to more effective condition-based maintenance approaches. The central idea in condition-based maintenance is to monitor the propulsion equipment by exploiting heterogeneous sensors, enabling diagnosis and, most of all, prognosis of the propulsion system’s components and of their potential future failures. The success of condition-based maintenance clearly hinges on the capability of developing effective predictive models; for this purpose, effective use of machine learning methods is proposed in this article. In particular, authors take into consideration an application of condition-based maintenance to gas turbines used for vessel propulsion, where the performance and advantages of exploiting machine learning methods in modeling the degradation of the propulsion plant over time are tested. Experiments, conducted on data generated from a sophisticated simulator of a gas turbine, mounted on a Frigate characterized by a COmbined Diesel eLectric And Gas propulsion plant type, will allow to show the effectiveness of the proposed machine learning approaches and to benchmark them in a realistic maritime application.