15th WCEAM Proceedings

Asset management has become an active field of research with the consolidation of the international ISO 55000 series. It coordinates activities to realize value from assets in organizations. Maintenance is one of the main stages to deliver business outcomes from physical assets over its life cycle. In the fourth industrial revolution scenario, it could not be different. Establishing activities to address unwanted incidents, nonconformities, and opportunities for improvement is an important and required element in the maintenance management of an asset management system. The standards, however, are not specific and only determine what needs to be done, not how to do it. Accordingly, this paper proposes a framework for maintenance management improvement (MMI) based on the international standard ISO 55000 series for asset management. To this end, a four-step methodology was applied. First, an ISO 55000 series review focused on a broad understanding of the concepts and requirements for the improvements in an asset management system is presented. Then, a framework was developed for MMI and demonstrated through a maintenance case study application in a Brazilian hydroelectric plant. Finally, the framework processes were correlated and discussed with the improvement requirements of ISO 55001. As the main result, an MMI framework for addressing improvements has been demonstrated to maintenance management for asset management. It encompasses activities for elaborating control and corrective actions, dealing with consequences, addressing opportunities for improvement, critically assessing events, and analyzing root causes. It was evidenced the framework is able to address nonconformities, incidents, and opportunities systematically. Therefore, these findings are expected to contribute to the researchers and practitioners in the field of asset management as the proposed framework based on the ISO 55000 series is an approach to the achievement of continuous improvement in maintenance management and, consequently, in asset management.

The main proposition of the ISO 550xx series of standards is that any organization that intensively deploys engineered assets should implement a ‘management system for asset management’. As human impact on earth’s geology and ecosystems transcend the era of Society 5.0 powered by fourth industrial revolution technologies, curiously, the composite ISO 550xx series of standards are tantalizingly applied for auditing and certification in engineering asset management. What does it really mean to audit and certify on the basis of the ISO 550xx series of standards? The discourse in this paper uses empirical evidence from two case studies to examine the conundrum of auditing and certification according to the ISO 550xx series of asset management standards.

This study examines the mediating effects of physical/engineering asset management on the relationship between continuous quality improvement and business performance. Using empirical data based on survey data from six European countries (i.e. Greece, Poland, Slovakia, Slovenia, Sweden and Turkey), this study used mediation analysis to address the research problem. A macro for SPSS was used to estimate the size of an indirect effect of continuous quality improvement on business performance by a proposed mediator. The results of this study show that physical asset management mediates the effect of continuous quality improvement on business performance. This study provides valuable insights into mechanisms that have the potential to improve business performance. The results contribute to a better understanding of how companies could achieve higher performance outcomes through the introduction of continuous quality improvement and through physical asset management practices.

In today’s society, infrastructure asset management is a priority for multiple policymakers as it is key to guarantee high-quality transport infrastructure. While the relative quality of transport infrastructure in a number of Western European countries is deteriorating, the volumes of freight and passengers, as well as the expected service levels of all modes of transport for citizens and businesses, are increasing sharply. In response, infrastructure asset managers have developed and integrated technical and management system innovations. While short-term cost and damage control is taken better care of, a long-term asset vision and strategic principles supporting a strong future transport infrastructure network are still largely missing in many EU countries. In this paper, we analyze the strategic infrastructure asset management (SIAM) for Belgian road transport, rail and inland waterways through a cross-case analysis. Our literature study identifies strategic asset management principles, potential barriers and solutions for transport infrastructure assets in general, as well as for the different transport modes in particular. Through in-depth interviews with Belgian top administrators, the principles and SIAM frameworks for different types of mainland infrastructure are analyzed. We find, based on the studied Belgian cases, that ‘one SIAM-model does not fit all’, and that a variety of models, adapted to transport modes and the regional context, could better suit the strategic goals of different policies.

Using daylight to offset renewable power generation and energy consumption in buildings has attracted significant attention in recent years. More specifically, daylight harvesting (DH) systems have attributes that reduce energy consumption, but there has been limited uptake because compliant DH designs are rarely explored during design phases. A contributing factor is that the cost of equipment, and the installation of such, rarely achieves satisfactory investment returns. To demonstrate an economic benefit, this paper presents a predictive energy saving simulation that can be applied to artificial lighting designs. The results show that when using a sensor-less daylight harvesting (SDH) algorithm to predict energy savings, satisfactory financial returns can be achieved by modifying existing lighting control systems (LCS). To support this finding, a simulation using a prototype LCS, and real-world case study on a high-rise building was carried-out to demonstrate the financial assessment methodology that is used to predict energy savings.

In recent decades, there has been an increase in the frequency and intensity of natural disasters. The worldwide growth of population, and consequently of infrastructure, increases the exposure to risks of this type. The expectation that the frequency of such disasters will increase amplifies the need to act today, to minimize the associated economic risks and costs in the future. The ability of buildings to maintain or restore their functionality after disruptive events, within a certain period, has increasingly attracted the attention of academics and professionals. This work intends to study and develop a method to measure the resilience of built assets. Therefore, a resilience classification system is proposed, which assesses resilience according to 5 dimensions (environmental, economic, organizational, social, and technical), which are subdivided into 16 indicators and 75 parameters. This proposal is based on various existent systems such as REDi or Building Scorecard, and its applicability is tested with 11 buildings with varied uses. The results are analysed via SPSS using a Pearson correlation coefficient matrix and clustering techniques. These empirical cases allowed improvements in the system initially proposed. The proposed resilience classification system allows classifying and comparing the performance of buildings, identifying their vulnerabilities, essential information to establish investment priorities. Multiple stakeholders are involved in the life cycle of buildings that may benefit from the developed proposal. The work carried out is in its early stages of development and includes the identification of improvements to be developed in future work.

In recent years, modern society has been facing more traffic jams, higher fuel prices and an increase in Carbon Dioxide emissions. According to NASA Global Climate Change, the current warming trend is extremely likely (greater than 95% probability) to be the result of human activity since the mid-20th century. Although general awareness in sustainability issues has improved in recent years through mass media coverage, this knowledge is not always translated into actual sustainable practice. The transportation sector consumes more petroleum than any other sector, and that share has increased over time from about 50% in 1950 to about 70% in 2018. In 2016, light-duty vehicles accounted for 58.5% of transportation energy use while medium/heavy-duty trucks and buses accounted for 23.9%. Vehicle miles travelled was seven times higher in 2017 than in 1950. In the transportation sector, the Fourth Industrial Revolution (Industry 4.0) emphasizes advances in communication and connectivity with breakthroughs in emerging technologies in fields such as fully autonomous vehicles sector. Small to mid-sized cities are not always wealthy enough to adopt these infrastructure changes so sustainable transportation falls on the decision of commuters. This paper shows how gamification can be linked to the components of Industry 4.0 to encourage drivers to drive less aggressively and, thus, more environmentally friendly. The gamification approach is illustrated using a sample of nine college-aged drivers but can be extended to fleet drivers.

Approximately 300,000 km of the Swedish road network consists of gravel roads. These roads contribute to accessibility and accessibility throughout Sweden, which is especially important in rural areas. An annual operation and maintenance grant is paid to these roads to be maintained and kept open to public transport, but the grant covers only part of the total maintenance costs. Some of the costliest maintenance activities are planing and gravelling. When gravelling, natural resources in the form of rock and gravel are used, which is an energy-intensive process that has a negative impact on the environment. A couple of methods exist for recycling of gravel from the roads, but the utilization is rather limited. In order to promote and motivate recycling of gravel, it is important to highlight the environmental benefits of using recycled gravel, but also to be able to assess the economic impact as additional costs may arise. The overall purpose of the paper is to gain deeper understanding of the environmental and economic effects of recycling of gravel during gravel road maintenance. To achieve this, a calculation model is developed to estimate the environmental impact and economic effects of gravel road maintenance. The purpose of the calculation model is to be able to compare alternative methods for gravelling. The calculation model is evaluated through a test scenario with three alternative methods for gravelling; two where gravel recycling is performed by the means of two different methods and one in which new gravel is used. The test scenario shows that it is economically and environmentally beneficial, in a life cycle perspective, to use recycled gravel for road gravelling.

Food security is becoming a growing problem worldwide. Much focus should therefore be placed on the agricultural sector with a view of equipping the sector for increased food production capabilities. The agricultural sector is changing rapidly globally due to the fourth industrial revolution (4IR) mega technologies, resulting in smarter ways to farm. These technologies allow farmers to maximise production remotely while controlling every aspect of crop farming such as pest control, soil conditions, crop monitoring, and soil moisture. These advances will allow farmers to be more profitable, efficient and environmentally friendly. However, evidence suggests that small-scale farmers are left behind in the use of 4IR mega technologies in South Africa.The purpose of this paper is to highlight the use of various 4IR technologies in the agricultural sector by using a desktop review of current literature. The paper recommends for a government-driven entity to be established that will focus on building capacity for small-scale farmers to build more sustainable and bigger businesses to assist in increased food production through the introduction of 4IR technologies.

In face of increasing pressure regarding climate change and greenhouse gases emissions, various countries and economic regions are setting ambitious action plans for a systematic transition towards a carbon-neutral economy. For example, the European Union aims at achieving this goal by 2050 through actions such as the investment and adoption of hydrogen technologies. Green Hydrogen – meaning hydrogen produced from renewable energies – is expected to play an important role towards a sustainable energy transition as an energy carrier with numerous use applications in transportation, industry, heating, and energy storage. Several experts see it as a viable solution to decarbonize different sectors over time. However, this technology is still in its early stages of development at various points of the supply chain. This paper discusses existing Green Hydrogen technologies and focuses on the diffusion of innovations through the extended Green Hydrogen Supply Chain. It uses a dependency model based on available Case Studies and semi-structured interviews to assess how these innovations will diffuse in the current market conditions until market saturation.

One of the main interests for today’s companies is to reduce the life cycle cost of those assets included in their productive processes. With that purpose, new business models are considering the acquisition of services provided by an asset, instead of the direct ownership of such asset. In other words, the focus is that the asset’s ownership remains in the service supplier, since the company just purchases the results obtained using the asset during a specific period. This asset utilization is at the end of the day the value added by the asset to the productive process. With that idea, this contribution is intended to summarize an overview of factors in order to decide between “lease or buy” an industrial asset. The choice between buying or leasing an asset must take into account different aspects, all of them with advantages and disadvantages, that must provide finally a positive influence in the profit and loss statement. Together with this discussion, one of the factor to take into account is nowadays the new digital tools that come from the so-called Fourth Industrial Revolution (4ID). These new tools (i.e. the IoT) support the asset management in a servitization context, contributing with big data analytics to facilitate the decision making in terms of criticality and reliability assessments as well as other decisions involved in the industrial asset management. In fact, the Digital Transformation may simplify the connection among system, process, asset and service, dealing with massive information interconnected among different assets, as well as different organizations like the asset user and the service supplier.

In capital intensive industries, the purchasing of IoT, predictive maintenance or other digital solutions is very complex as there already exists several separate legacy systems. Also for a single solution provider, the customer needs and expectations can be huge, and they might not have all resources or competences needed for the delivery. In our research, we examined various aspects related to joint offering development and value creation. We define the joint offering as a concept or solution that is co-created in collaboration with two or more actors that usually have complementary technological skills or value creation logics. Based on our study, there is still relatively little joint offerings deployed supporting asset performance management and execution of asset management operations. To discover the interaction between the actors able to provide a joint-solution, we further sketched value network models from the anonymised industrial challenges. Finally, the developed conceptual framework clarifies the scene of both the business opportunities and value assessment. The first part of the framework, business opportunities, considers the business models, value networks and analysis of business opportunities and risks. The later part, business value assessment, is built on capital and operating expenditure and revenues summarising the business value.

The paper discusses the role of maintenance in the digital era and propose directions for supporting the technology and business transformation towards Maintenance 4.0 and Service Management 4.0. For achieving this, the paper summaries previous research in the area and conceptualizes the transformation of maintenance towards Maintenance 4.0 and Service Management 4.0. The concept applies a systems approach on digitalization and recognizes the need for combining several working areas (production and maintenance management, information systems management, improvement processes and business management) for successful digital transformation within maintenance. Service Management 4.0 describes how maintenance becomes a business opportunity and modular maintenance offerings a way to approach the new opportunities. The concepts proposed in the paper provide support for industries in the digital transformation process towards Maintenance 4.0 and Service management 4.0.

This article outlines the methodology developed by Hydro-Québec Distribution (HQD) for optimizing the maintenance policy related to equipment on an electrical distribution network based on the estimated useful life, reliability and replacement costs. This methodology relies on the failure modes analysis as well as on the statistical analysis of operational data and safety risk. Its application will be demonstrated using MV three-phase gang operated overhead switches, but the methodology is applicable to assets on a distribution network with a preventive maintenance program, including equipment refurbishment. The application of the optimal preventive maintenance policy obtained with the proposed methodology on approximately 5000 equipment generated labour gains of more than 2,000 h per year, a useful life considerably higher than the design life and economic gains of more than $400k per year. The proposed application case contributes to the literature relating MV three-phase overhead switches, which is currently absent, and to the optimization of its maintenance strategy.

To manage the realization of value, the core concept of asset management, it is vital to have a good understanding of what that value is, how it is produced and how it can be measured. In this paper, we first make a connection between the concept of value, its production in a value chain and the asset lifecycle and conclude that these concepts are not necessarily aligned. Next we address issues in performance management. Common practice is to use Key Performance Indicators (KPIs) to keep track of results, with multiple KPI’s often compiled into a business dashboard or balanced scorecard. To be effective, KPIs need to be valid, functional and legitimate. Unfortunately, a focus on pursuing targets can provoke strategic behavior resulting in destruction of value. Furthermore, targets may be aimed at the wrong lifecycle, be part of an optimization or be blind for optimization across portfolios. To address these challenges, we propose a pragmatic approach based on the cost to benefit ratio of interventions, embedded in a social setting. This model has been applied for an organization with 3 separate but comparable portfolios. The concept still has to be tested in a more diverse setting.

As assets deteriorate and/or new technology becomes available, asset-intensive industries across the world struggle with planning and justifying the necessary reinvestment to renew and modernize their equipment. This paper presents a methodology for rapidly creating an optimized long-term asset renewal plan that targets the maximization of value to the organization. It ensures alignment with top-level strategic objectives, while at the same time is built from the bottom up, based on the assets’ condition, system functions and criticalities. It also involves broad participation and buy-in from technical staff, so there is widespread consensus on the emerging priorities.The methodology is based upon the 6-step SALVO Process for Strategic Asset Lifecycle Value Optimization, the product of a 5-year multi-sector R&D collaboration programme. Benefits of the method include the ability to calculate and demonstrate the monetized value, risks and other business impacts generated by each proposed intervention at different potential timings, and the optimization of combined effects within any overriding constraints (such as budgets, resources or timing commitments). This involves quantifying and modelling the trade-offs between Capex, Opex, risks, performance and sustainability, with mixed quality data and expert/tacit knowledge, using state-of-the-art decision support tools. It also achieves, usually for the first time, true alignment between technical and financial departments, providing a transparent and auditable basis for the interventions and funding requirements. A case study is demonstrated and discussed, with lessons learnt, from the successful creation of a 10-year renewal and modernization plan at a large electricity transmission company (ISA CTEEP) in Brasil. This work formed part of a wider 3-year asset management innovation project under the R&D programme supported by the Brazilian electrical sector regulator, ANEEL.

This work presents the development of a system for detection of early damage to insulation of electrical machines. This system is composed by a hardware implemented in a FPGA board in conjunction with a software written in C#. The frequency response analysis (FRA) technique is used to infer about the machine insulation condition. The application of FRA consists of obtaining, periodically, the impedance spectra of the device under test (DUT). The obtained spectra are compared with a base spectrum, called baseline. Differences between the baseline and the acquired spectra can indicates a damage or the forming of a failure mechanism in machine insulation. The software implements a sweep frequency algorithm to control the hardware and obtain the machine impedance spectra. This algorithm communicates with the hardware, sending commands for generation and acquisition of signals in a predefined frequency range. With the acquired signals, the software is able to calculates the impedance for each signal and, in the end of the process, the impedance spectrum is obtained. Since the early damage diagnosis is based in comparison between spectra, and a visual analysis requires a well-trained and expert maintenance team, it is proposed in the literature the use of some statistical indexes to compare the data. Those indexes have the advantage of obtaining a more objective diagnosis of the DUT, since visual analysis is subject to subjective interpretations. The software also implements some of the indexes proposed in the literature for a better analysis of the machine insulation. To evaluate the developed system, experimental results are presented using a machine with taps on its windings in order to emulate insulation faults. Since insulation faults represents a considerable percentage of electrical machines failure, the proposed system has great potential in industrial applications, preventing unscheduled stops of the machinery.

Turnaround maintenances (TAMs) are huge projects in terms of manpower and expenditure and therefore they have a direct effect to company’s profitability. TAMs include several challenges, such as prioritizing the maintenance tasks, scheduling the project, sharing information among all stakeholders on site and keeping focal company’s maintenance data in the IT systems updated. Due to the significance of TAM in economic and safety perspective, solutions for the challenges are needed, and advanced technologies could play a major role in solving these challenges. For example, sensor technology and software could help in evaluating asset condition and prioritizing maintenance tasks. In addition, mobile technology and apps could enable smoother information sharing on site. Moreover, external expertise could be brought into the TAM project by utilizing virtual- and augmented reality.

Determining appropriate maintenance programmes for technical inventory is recognized as important for quality reliability and safety management in the oil and gas industry. The programme could be achieved through reliability-centred maintenance (RCM) analysis, where safety-critical equipment with potential for hidden failures is given particular attention. Output of the analysis is seen in combination with relevant requirements to perform functional testing of the equipment. The testing involves collecting and analysing data for verification of acceptable reliability and safety levels during the operational phase. This testing is often required in periodic intervals, where shorter intervals might be required initially or after failures for more control. Despite the intention of such activity, it could however influence equipment conditions in a negative way and over time contribute to a reduced reliability performance, i.e., lead to maintenance-induced failures. In this paper, focus is on periodic testing of the component ‘downhole safety valve’ (DHSV), and mechanisms leading to its failure. We consider the use of an age-adjusting imperfect repair model for analysing the effect of maintenance-induced DHSV failures and discuss the influence of recommended industry guidance. We particularly discuss the benefits of a test strategy having initially one to three months intervals, compared with an alternative strategy with constant six-month or one-year intervals. Based on the analysis, the 12-month interval gives the highest overall probability of failure on demand despite reducing the probability for maintenance-induced failures. There is a marginal difference between the other two alternatives, where then the selected distributions and uncertainties play a larger role. Barrier data collected by the Petroleum Safety Authority Norway (RNNP project data) is used for the analysis.

Predictive maintenance is the promise of the future in infrastructure asset management. Predictive maintenance more and more uses sensor data. Sensors are relatively cheap, and their data mostly comes in huge quantities. Trends or flags may be observed in the data, sometimes with traditional statistical analyses and more often with advanced analyses such as machine learning techniques. These trends and flags may indicate a developing problem, allowing maintenance professionals to act before a failure occurs. However, as of today predictive maintenance is far from being common practice in infrastructure asset management. Failure mechanisms are often extremely complex. Besides knowing how to search for flags and trends, one should first know what to search for. Also, on the organisational side barriers are found. Often, big data is available in infrastructure organisations but underutilised for various reasons such as inaccessibility of data, client unfriendly user interfaces and a lack of tools to analyse data effectively by maintenance engineers. The current research investigates the potential for more predictive maintenance in current professional practices, not by adding new sensors but through exploitation of existing data (data mining) and removal of barriers which professionals experience in using such data.

This contribution is intended to provide a view on the standards ISO 55001 (requirements for an asset management system) and the ISO 30401 (requirements for a knowledge management system), in order to consider knowledge and human asset management, as a relevant dimension for all engineering and industrial sectors. An intangible asset management framework is proposed in this paper, considering the principles and requirements of the above-mentioned standards, together with methodologies already developed for physical asset management, in order to coordinate and realize value (in this case) from the industrial knowledge. This proposal is intended to be a helpful decision support tool in order to align the different knowledge areas to the industry strategy and, in particular, to the business drivers of the company. Such a proposal will require first the identification of the key company knowledge areas, which are needed to sustain and grow the business, supporting strategic decision-making. After that priorization, a gap analysis shall be performed in order to reckon if the core knowledge and the key industrial capabilities match with the current company resources and where they lie (people expertise, document repositories, etc.). This analysis will help not only to detect core capabilities to be developed and/or acquired by the organization, but also to reassign efficiently the current company resources to more critical activities with more added value. Finally, connections to risk and uncertainty references, the digitalization industry process, as well as to possible future research lines are commented as a conclusion.

The potential of digital twin technology has become apparent in recent literature, occurring evermore frequently in literature as the world moves on to the fourth industrial revolution. The use of digital twins in industries such as manufacturing, aerospace and aviation, and healthcare, have illustrated its value in lifecycle data management, control, monitoring, and more. This paper presents a review of digital twin applications in railway infrastructure. Considering digital twin adoption for public infrastructure, the rail industry is still at an early stage with few recorded implementations. However, digital twins present the possibility of addressing the emerging needs of infrastructure data management in the rail sector. Identified needs include the integration of data from various sources, validation of management paradigms, and the processing of large volumes of data.

Asset management is data-intensive and new tools and processes are often necessary to collect, manage, analyse, and use asset data. The use of these tools can improve organisational knowledge and decision-making. Industry 4.0 tools are prompting the digital transformation of organisations and emerging innovation opportunities. Among these tools are those supporting the concept of Digital Twin (DT). The concept started being mentioned a few decades ago, but the discussion around its definition and potential applications still continues. This paper explores some of the interpretations of the concept of DT and its interrelation with some Industry 4.0 tools. Besides presenting some of the known benefits and opportunities related to DT applications in specific industries such as aerospace and manufacturing, namely in the early stage of asset lifecycle, the paper seeks to emphasise the vast exploratory potential of DT use in infrastructure asset management, especially in the operation and maintenance (O&M) phases. This presentation includes the description of an exploratory project for DT implementation in rail and road networks by the largest infrastructure management body in Portugal.

The digitalization of the economy in the past decades has made data availability grow and become more important. From the maintenance point of view, clients are more demanding, wanting systems that will not have breakdowns while reducing exploitation costs. This challenging scenario has pushed companies in the direction of more intelligent maintenance solutions that involve choosing the best course of action in terms of system availability. Nowadays, these solutions are usually called prescriptive maintenance. This term is vaguely defined and its use is often unjustified. In this article we will discuss what really characterizes prescriptive maintenance, review some of the work published with this term and propose a generic framework to guide the development of such solutions. In the end, we will illustrate the use of the generic framework in a practical case.

As the Electricity Sector has a strategic role in the socioeconomic development of a country, shortages have a damaging effect for all consumers and for the company itself. Therefore, companies in the Electricity Sector is considered asset-intensive, as their performance depends on the performance of their assets. This work has as objective to evaluate the critical success factors, promoting good performance on the Asset Information Management Systems in the Brazilian Electricity Sector. To achieve this objective, we defined a model that analyzes the impact of implementing Asset Information Management Systems into organizational performance indicators of companies in the Electric Sector. To validate this model, we simulate connections that were performed through structural equation modeling, based on data obtained directly from professionals from different sectors of Generation, Transmission and Distribution companies in Brazil, in a previously defined form for this research. The relevance of the research is the analysis of the relation between impact and correlation in the Asset Information Management Systems, so that companies in the Electric Sector can prioritize efforts in factors of greater impact. The research is limited to evaluating only the Information within the Management Systems of Assets, with suggestions for future research to evaluate the other elements.

Context: While asset information management and asset information monitoring play an important role in asset management, low levels of asset information quality can have consequences, such as missed business opportunities, inadequate decisions and flawed risk analysis. Objective: To perform a gap analysis on the perception of employees of a Utility Company in Brazil, about the asset information quality in their respective areas, roles, segments and hierarchical levels. Method: We applied a questionnaire based on the AIMQ model [20], using five-point Likert items. We collected 70 answered questionnaires. The AIMQ model assesses asset information quality on the following dimensions: Accessibility, Appropriate, Amount, Believability, Completeness, Conciseness, Representation, Consistency, Representation, Ease of Operation, Free-of-Error, Interpretability, Objectivity, Relevance, Reputation, Security, Timeliness, and Understandability. Results: The results present a small satisfaction rate, considering hierarchical levels and professional work experience. Only the “Relevance” dimension reached an average higher than 3, which illustrates the low perception of respondents about the quality of information. The analysis of the results (using quality standards, verification metrics, and the created rules) shows that only two samples reached a percentage above 60% accuracy, reaching an overall average of only 25.95%. Regarding completeness, the global average was slightly higher, reaching 35.23%. Some resulting correlations from this study are: Free-of-Error x Objectivity; Accessibility x Ease of Operation; Understandability x Interpretability; Believability x Free-of-Error. Conclusions: Benchmarks developed from the AIMQ model help comparing asset information quality across organizations, and provide a baseline for assessing IQ improvements. This study presents important correlations, choosing further automatic techniques for evaluating data quality (DQ) on asset management databases.

Asset Management (AM) processes play a significant role in organisations’ profitability. Clearly documented and managed AM processes improve the delivery potential of assets and minimise the costs and risks involved. Business Process Management (BPM) is a discipline that uses various methods, tools, and techniques to discover, model, analyse, measure, improve, optimise, and automate business processes. Despite the prevalence and proven effectiveness of BPM in a wide variety of domains, there has been little research investigating its potential for describing AM processes. This paper presents a case study that explores the application of BPM to power transmission assets. BPM principles were applied for decision modelling and to capture the lifecycle of power transmission assets. The case study demonstrates how BPM application to AM processes can result in greater clarity of processes, increased collaboration, a better understanding of data, external rules, and regulations, and serve as an internal point of audit.

Evidence-based asset management aims at making right decisions and optimizing asset management processes with best available information. Asset information systems are widely applied in industrial companies to collect and store asset related data. However, competence and experience of people, - i.e. tacit knowledge - has a crucial role in the decision-making. In this paper, we discuss information transfer, usability of current IT-systems and data utilization in daily tasks of different user groups. In addition, we outline a solution that supports the way towards evidence-based approach in process industry.

This paper presents a novel approach for planning replacement projects using prognostic developed for turbines and generators to try to defer unit replacements by maximizing economic gains while minimizing risk. In the same analysis in which we optimize replacement dates, we would like to also optimize operation and maintenance plans since each turbine design is affected differently by these plans. The current maintenance plans scheduled at fixed intervals and the unit commitment strategy solely based on hydraulic efficiency are therefore also questioned. The goal of this analysis is to demonstrate that maintenance and operating plans need to be adjusted to minimize the probability of regret when optimizing NPV (Net Present Value) by changing replacement dates while considering equipment prognostic. For this study, the impact of inspections, frequency of unit start-up and deferred equipment replacement have been evaluated by comparing them to a reference scenario where the equipment would have been operated under traditional frameworks. The analysis demonstrated the following points: It is possible to observe the impacts of the improvements (frequency of inspection, start-up, replacement date, etc.) separately in the technico-economic analyses; Unexpected breakdowns can be taken into account for informed risk management; Investment deferrals can be analyzed by taking into account the risk; Maintenance and repair can be rigorously taken into account by the model. In fact, the proposed model allows to define the required maintenance and operation plans according to the replacement strategy that will be chosen in a global optimization of the unit fleet. The sensitivity analysis presented shows the importance of adjusting operation and maintenance according to the specific design of each runner and the importance of the chosen deferral date. With this kind of analysis, the decision-maker could possibly (while controlling the risk): Distribute the number of start-ups or other damaging conditions differently in order to protect some units while maximizing the use and wear of others; Postpone as much as possible the replacement of those equipments that show very little risk of failure. The paper will be structured as follows. First, an overview of the modelling strategy will be presented. Then, the parameters of the case study and the methodology will be detailed. A sensitivity analysis will show the impacts of the different assumptions on the mean net present value and the probability of regret. Finally, we will discuss the results for several units in terms of applicability for decision making and asset management.

In the era of Society 5.0 powered by fourth industrial revolution technologies, the pervading cliché of “information about everything” is aggressively transforming how we monitor and assess the reliability, resilience and vulnerability of engineered assets such as personal gadgets, equipment, machinery, interconnected and interdependent facilities and infrastructure that constitute modern day cyber physical systems. Two case studies of conventional approaches to condition assessments are briefly discussed in the paper. Given that the era of Society 5.0 proffers huge technology-driven paradigm shifts, the contention is that the sustainability imperative demands a wider and more holistic approach to condition and performance assessments of engineered discrete assets and asset systems.

Internal combustion engines are intermittently operating in Thermoelectric Power Plants (TPP) and consequently suffer a lot of detriction. Due to this, these engines are subject to ostentatious controls of temperatures, pressures and physical properties of the working fluids at critical points on the machine to monitor the behavior and abnormal events of this machine. However, often these controls only indicate abnormalities after a failure, not providing an early study of the operational state of the engine. A trend analysis of failures in auxiliary systems of the internal combustion engine, based on the matrix structure, is proposed in this article in order to verify the operational conditions of the auxiliary engine lubrication system and the influence that this system is producing on electrical generation based on operating data from the lubrication system of an internal combustion engine model similar to a Wärtsilä 18V46-C2. The proposed math model is validated through comparison with the standard behavior of the internal combustion engine lubrication system. It is demonstrated that the results obtained with the proposed methodology correspond to the high compatibility of the simulated results with the real data of failure of the lubrication system of the analyzed engine model, which makes this math model a favorable mechanism to direct predictive maintenance and, consequently, reduce operating costs of electricity generation.

In order to improve the efficiency and accuracy of diesel engine combustion chamber fault isolation, a method of combining the feature dimension reduction of AutoEncoder network and the fault isolation of BP neural network was proposed based on acoustic emission signals. Taking a Z6170 diesel engine of China ZICHAI company as an example, fault simulation tests of exhaust valve and piston rings under experimental environments were carried out, and the acoustic emission signals of the cylinder head were collected, then the time-domain, frequency-domain and other characteristic parameters of different signal sections in the whole cycle were extracted. The dimension of characteristic parameters was reduced by using AutoEncoder network, BP neural network was used to fault diagnosis and fault isolation, so that a fault diagnosis and fault isolation model of combustion chamber components was established. After training and verification of the model, it shows that the proposed diagnosis and isolation method is effective with capability of identifying the faults of exhaust valve and piston ring for the combustion chamber parts of diesel engines, therefore, it is promising to detect and isolate the condition of combustion components automatically.

This paper addresses the asset management and energy efficiency of a critical environment - the Bioterium of the Faculty of Health Sciences (FCS) of the University of Beira Interior, Portugal – a facility where the environmental conditions are required to be uninterruptedly maintained at a temperature of 21 ºC and with an air-humidity of 50%. Such requirements demand a constant utilization of the Heating, Ventilation, and Air Conditioning (HVAC) system, in particular the use of chillers and propane boilers for cooling and heating purposes, respectively. Indeed, due to the significative local weather variation over the year, a system failure breakdown may result in drastic consequences for the facility assets and its critical activities. Hence, a large amount of energy is constantly required, thereby increasing the facility operating costs.In order to improve the energy efficiency, reduce the operating costs, and guarantee good asset management, this work aims to assess opportunities for improvements that may enable a more profitable and reliable asset management of the bioterium facilities, mainly with the advent and evolution of new technologies, which besides being more efficient, provide more useful information as well.

The measurement of relative permittivity of fluids is a convenient way to identify the amount of each element in a two-component mixture. This approach applies especially to cases in which the permittivities of the two components are far apart from each other, such as determining the water content in heavy fuel oil (HFO). The latter is a high-viscosity and high-density fuel, obtained from residual portions in the distillation process of crude oil. The presence of water in HFO is generally unwanted, and can be a major concern due to equipment degrading, decrease in heat transfer capabilities and loss of burning efficiency. This work addresses the determination of water content in HFO samples, benefiting from the great difference between the relative permittivities of both fluids. A relative permittivity meter designed specifically for this purpose was employed. The meter uses capacitance as its working principle, and comprises a capacitive sensor that is in direct contact with the oil, and a capacitance meter circuit that connects to the sensor. This paper describes both components, as well as the calibration procedures involved in their usage. HFO samples with different amounts of water were prepared and probed in order to obtain a relationship between water content and relative permittivity. The collected data provides enough information to determine the amount of water present in other HFO samples, by measuring its relative permittivity and using adequate interpolation methods.

Air pollution is directly related to the increased risk of acute respiratory infections, and it was estimated by the World Health Organization that 6.5 million deaths in 2012 were caused by air pollution-related illnesses. In Brazil, there are few cities that have air quality data collection, although legislation has been recently updated and quality standards have been planned with promising targets, according to CONAMA Resolution 491/2018. This research presents an alternative air quality monitoring station, focused on the use of Internet of Things (IoT) resources, low-cost equipment and real-time acquisition via the internet. The purpose of the research is to use the SDS011 sensor for particulate matter (PM10 and PM2.5) concentration monitoring in Joinville, Santa Catarina, Brazil, connected to the Raspberry Pi computer. The code for data acquisition of the sensor was developed in Python and the data cloud storage was done through the use of Dropbox API. The system aims to reduce the costs of equipment and monitoring stations along with their energy consumption, in addition to enabling real-time monitoring, with availability of data for the scientific community and the city population, also representing an easy-to-install and cheap maintenance. The results show the time series of particulate matter as well as the daily profile and the data completeness calculated for the period of monitoring. It is intended as future work to relate the measurements of PM10 and PM2.5 with other methodologies and compare data with other equipment. Joinville is a highly industrialized city and has no official monitoring, so the continuity of this work with the expansion of monitoring stations is vital to make the data available to the population and to understand the relationship between local atmospheric stability and air quality.

Failure diagnosis on some system is often preferred even the data of the system is not designed for the condition monitoring and does not contain any or contains little example cases of failures. For this kind of system, it is unrealistic to directly observe condition from single feature or neither to build a machine learning system that has been trained to detect known failures. Still if any data describing the system exists, it is possible to provide some level of diagnosis on the system. Here we present an LSTM (Long Short Term Memory) autoencoder approach for detecting and isolating system failures with insufficient data conditions. Here we also illustrate how the failure isolation capability is effected by the choice of input feature space. The approach is tested with the flight data of F-18 aircraft and the applicability is validated against several leading edge flap (LEF) control surface seizure failures. The method shows a potential for not only detecting a potential failure in advance but also to isolate the failure by allocating the anomaly on the data to the features that are related to the operation of LEFs. The approach presented here provides diagnostic value from the data than is not designed for condition monitoring neither contain any example case failures.

Boiler heat exchanger tubes lose thickness over time, resulting in costly ruptures and losses in capacity as thin tubes are taken out of operation. To mitigate the costs associated with thickness loss, boiler tubes are inspected and can be preventively taken out of service (i.e. “plugged”) to avoid in-service ruptures. Moreover, there is an economic dependence among thousands of tubes of heat exchangers in inspection and maintenance activities where a large setup cost may be induced when inspection is conducted for any tube. This paper extends the authors’ previous study on boiler tube inspections to include a dynamic inspection and preventive maintenance grouping policy to pursue additional savings on setup costs. The inspection policy is said to be condition-based since the time for next inspection is based on the current inspected state. A heuristic thickness loss threshold for plugging is computed for each tube by balancing the risk of an in-service rupture with the lost revenue due to capacity loss and an optimal inspection grouping strategy is developed using the Markov Decision Process paradigm. The policy is applied to a case study of a boiler operating in an Australian sugar factory and benchmarked with policies that represent current practices and do not consider grouping. The results show that the proposed condition-based grouping inspection policy yields significant savings compared to tube individual inspection policies.

In this study, lubrication oil age is predicted based on selected monitoring indicators. The information that was extracted from the oil analysis report are the TBN, oxidation, kinematic viscosity (100 ℃), contaminants and elemental analysis. Correlation analysis was applied to the data to assess the relationship between the lubrication parameters and oil age. Based on the analysis, oxidation was identified to have high correlation with oil age. Mahalanobis-Taguchi Gram Schmidt (MTGS) method was applied to identify the critical variable to predict oil age. Based on the MTGS analysis, TBN, oxidation, Pb and Mo have a positive SN ratio gain and were selected to be included in the lubrication oil age prediction model. The study demonstrates the lubrication oil age prediction model based on Artificial neural network (ANN) with TBN, oxidation, Pb and Mo as predictor variables with an R squared of 0.8176, mean square error (MSE) and mean absolute deviation (MAD) of 1191 and 26 respectively. Based on the available sample data and threshold value, it can also be observed that readings of the lubrication oil parameters are still within limits after the recommended duration for lubrication oil to be in service. These findings are beneficial for future works to predict the remaining useful life of lubrication oil.

This paper describes methods for predicting track geometry degradation to provide support for maintenance planning. The track geometry data recorded by the Track Recording Car (TRC) and the maintenance work orders were used for degradation modelling. The degradation indicator considered in this study was the deviation of the longitudinal level from the design value sampled every 100 m-long track segment. A Wiener process model was built to model the time-evolution of the geometry condition indicator for a track segment and the parameters were estimated via standard maximum likelihood estimation techniques. It was found that the proposed degradation model provided good fit to the data, except in some extreme cases where the TRC data exhibits large changes in the degradation indicator between two runs. Nevertheless, even in these cases the Wiener process model “responds” to this lack of confidence about the slope in an intuitively appealing manner: the variance on the slope is increased to reflect a lack of confidence in the degradation rate. Finally, the utility of the model in maintenance decision making is demonstrated by predicting the expected number of different maintenance interventions and policies.

The reliability of many industrial processes depends on the sensor system. However, these sensors can be affected by noise, perturbations and failures. Hence, sensor monitoring and diagnosis are fundamental to guarantee the quality of an industrial process. Nowadays, artificial neural networks (ANN) are widely used in sensor signal processing and diagnosis. However, those ANNs usually require many artificial neurons, being difficult to implement in software and hardware due to their high computational costs. This paper presents an optimized implementation of artificial neurons in ANNs for sensor data analysis using a Genetic Algorithm (GA). The objective of GA is to find an adequate segmentation to reduce the activation function approximation error. One of the advantages of the proposed approach is that the cost function used in GA considers the effect of factors such as the ANN architecture or the number of bits used in arithmetic operations. The proposed ANN implementation technique aims to get the best possible approximation for a specific ANN architecture, making easier its implementation in software and hardware. Simulation and experimental results using FPGA (Field Programmable Gate Array) prove the advantages of the proposed approach for implementing sensor data analysis systems based on ANNs.

Fast, precise and robust sensing of currents and motor shaft angle is essential for the excellent performance of electric and hybrid vehicles (EV/HEV). Multiplexing techniques are commonly applied in data acquisition systems (DAQs) to digitize the signals sensed in EV/HEV drives. Frequency-division multiplexing (FDM) applied to get the signals from current sensors and resolver angular position sensor has advantages over conventional multiplexing approaches. However, problems such as aging and mechanical imperfections distort the outputs of those sensors, producing measurement errors of the angular position and currents. Conventional techniques designed to compensate for those errors cannot be applied in signals multiplexed in frequency. This paper proposes online techniques to detect and compensate for the distortions in the resolver sensor and current sensors. The demultiplexing process was adjusted to allow distortion detection and compensation. An auto-associative neural network (ANN) compensates for the current measurement error, while an energy-based technique is applied to compensate for the distortions in the resolver outputs. The obtained results show that the distortions were compensated, allowing a more accurate estimation of stator currents and angular position when FDM is applied in EV/HEV DAQs.

In this paper we present a study that tackles the health monitoring problem of rolling contact fatigue between train wheels and railway rails. This study is focused on model exploration, and explainable Machine Learning, with the objective of predicting defect apparition.

PMSMs are widely used in high-performance industry applications. This popularity is due to their high torque-to-inertia ratio, high efficiency, low maintenance, fast dynamic response, among others features. However, the construction of such machines includes some components that are highly sensitive to the temperature, hence, requiring control strategies that mitigate failures and loss management, taking the machine temperatures into account. Sensor-based temperature measurements of such parts are difficult to be implemented, and are not always well-accurate. Therefore, this paper proposes an approach based on artificial neural network model to estimate the temperature at the most critical points of a PMSM, namely, the permanent magnet, stator teeth, windings, and stator yoke. In this study, the variables, ambient and coolant temperatures, motor speed, and the stator voltages and currents in the direct and quadrature axes are taken as inputs to a Non-linear Autoregressive Neural Networks with Exogenous Input (NARX). To develop and test the proposed temperature estimator, a 140-h multivariate database from a torque-controlled 52 kW PMSM was used. The obtained results have shown that the proposed method successfully estimates the temperature at the selected points.