6.05 Assets Performance & Health Monitoring

This presentation will provide a detailed look at how Manitoba Hydro builds and applies whole-life cost models for the purpose of projecting performance, cost, and risk for an asset class. The application of predictive analytics, through the use of these models, will be discussed as it relates to a single asset class, to mature Manitoba Hydro’s asset management strategy.

The City of Winnipeg faced challenges with the condition of their Return Activated Sludge (RAS) piping within the North End Sewage Treatment Plant. Non-destructive and destructive condition assessment techniques were used to determine that the critical process piping was life expired, and required replacement or rehabilitation to maintain process level of service until the plant is upgraded. Replacement of a RAS piping system is akin to major heart surgery on a sewage treatment plant. To manage the process risk, in situ structural renewal using an engineered Carbon Fibre Reinforced Polymer (CFRP) external wrap system to encapsulate the original carbon steel piping was chosen. Selection of the rehabilitation method reduced the schedule by two years compared to the replacement option and minimized operational risk, as process outages were reduced to a few short-term events. Offline testing of mock-ups and emphasis on environmental and quality control further managed the risks associated with CFRP installation. The project faced unique challenges due to the complex configuration of the RAS piping, which was located inside a congested plant gallery with surrounding equipment, piping, and electrical services in continuous operation. To effectively convey information during planning, design, tender, and construction, a digital 3D model was developed using laser scanning to capture the detailed configuration of the piping and surrounding physical constraints. The 3D model was embedded with data to define the rehabilitation scope, locations of existing pipe leaks requiring immediate repair, rework of pipe supports to accommodate the CFRP installation, and other aspects relevant to the work. This model was a highly effective tool used for collaborative review by all project team members throughout design and construction, leading to successful completion of the RAS piping rehabilitation.

If we were to do reliability analysis on certain assets, which assets are worth our effort and provide the greatest impact? To solve this, our team developed a focused methodology to help us identify which asset types need to be further analyzed in the coming years. Our goal is to identify the asset type that causes the highest generation of lost opportunity cost and the highest maintenance costs. Ideally, the generation of lost opportunity cost should be added to maintenance cost. Lost opportunity cost is calculated from existing operational performance data, which is collected and used for NERC GADS (North American Electric Reliability Corporation Generating Availability Data System) reporting. Maintenance cost is calculated from maintenance history in CMMS (Computerized Maintenance Management System). The operational performance and maintenance history data are illustrated using a Pareto chart. As a result, the asset type that causes the highest generation of lost opportunity cost can be identified from the chart. However, asset types with the highest maintenance costs may not indicate the asset type with the most issues. Besides, the NERC GADS codes may be related to one or more assets in CMMS and, therefore, need a relationship to be created if the costs are to be added.

We all love to solution and check off that win for the team, but moving too quickly may result in introducing new problems or even amplifying previously smaller issues. The latter is common particularly in technology implementation where the hope is for efficiency improvement, but the results sometimes don’t meet the desired outcome. Although root cause analysis was informally practiced at the SMCDSB, the implementation of a formal program using a process approach to problem solve, define requirements, and solution has strengthened troubleshooting and preventing future problems. By taking a very focused stance on identifying the problem or need clearly and leveraging the Kepner-Tregoe Analytical Troubleshooting method, there is improved clarity, definition, and logic in how the analysis completed. I wish to share the journey of RCA program implementation for the SMCDSB with examples and successes we've achieved.

Recent developments in AI, ML and related techniques see wide adoption in many industries. However, in the asset management area, such technical advances are still in their infancy, especially in the maintenance, repair, and operations (MRO) area. Part of the reason is that, contrary to production, MRO data has its unique characteristics (e.g. incompleteness, inconsistency and heterogeneous), and most organizations are still planning to introduce diagnostic sensors dedicated to maintenance and equipment reliability. We face both challenges and opportunities in advancing data-driven continuous improvements within the asset management world. This presentation shares the findings of our current research and development focus. Titled “How to use historical data to find opportunities to improve the effectiveness of equipment reliability programs, optimize MRO inventory operations, and enhance MRO workflow management processes”, we will first examine the characteristics of MRO data as their uniqueness to a specific company, plant or equipment and their commonality across all sectors. Then we evaluate the feasibility of applying AI/ML techniques with MRO history for better operational efficiencies. We need to understand what data is related to human knowledge, human interaction and process, and what data is associated with the actual condition of the asset, and if there are patterns and models that can be learned. Last, we will demonstrate that AI/ML can find equipment agnostic models and patterns which help continuously improve MRO operations across different industries. Based on the findings, we will also show how AI/ML models learned from historical MRO data can be translated into prescribed actions for improvements in equipment reliability, MRO inventory and workflow operations for individual organizations.

Organizations are observing the change in the maintenance landscape with the use of data-driven analytics for decision-making. Underpinning these analytics is Machine Learning. The algorithms form the model that ingests data to represent the system and predict its future state. While this method has found rapid applicability in other sectors, the field of Reliability & Maintenance Engineering is still exploring ways to adapt this idea to its conventional Asset Management programs. The objective of this paper is to explain the predictive power of machine learning by wrapping it around a prevalent reliability tool: the P-F Curve. Initially proposed in the Reliability-Centered Maintenance (RCM) framework, the P-F Curve is ubiquitous and the practitioners understand its simple and elegant description of the failure behavior. In spite of its understanding, the use of the P-F Curve has been minimal in everyday analysis to estimate when and how soon the failure will occur. Predictive Maintenance (PdM) Tools such as Vibration Analysis, Ultrasound, and Thermography have made the P-F Curve more accessible. Adding Machine Learning to these PdM tools, with a real-time data stream, will amplify the value of this analysis with better detection of Potential Failure (Pf) and forewarning of Functional Failure (Ff). Having real-time data and a real-time P-F Curve plot will enable the users to capture the changing conditions. We define this new curve as the Dynamic P-F Curve™. Dynamic P-F Curve™ Machine Learning models will estimate the time available (P- F Interval) for the maintenance team to respond to an asset before catastrophic failure. This interval will change if the asset experiences an external force causing it to wear out sooner. Thus, a dynamic curve makes the maintenance plan itself changeable and agile, improving the plan's efficiency. The final part of the presentation will showcase an example of how a Dynamic P-F Curve™ is calculated and represented by using an open-source data set. The resulting change in the maintenance plan actions is also prescribed to fully explain this idea, concluding with the list of use cases.    

An Asset Health Index or AHI refers to analysis performed using various asset data to determine the state or condition of the asset. AHI can be used to better assess asset condition, used and useful life, progression toward potential failure, and failure probability. Further, using AHI can also enable the development of optimized maintenance and replacement strategies for assets using a set of objective criteria to assess the true health of the asset. However, entities vary widely in whether they develop Asset Health Indexes (AHIs) for their key assets. For those that do, there are marked differences in the level of rigour and sophistication employed in developing and applying AHIs for effective asset management decision-making. AHI calculations involve identifying and collecting data which may include a review of core asset attributes such as manufacturer, inspection data including field observations, destructive and/or non-destructive test data, maintenance data including historical records, operational records, and asset failure/refurbishment data. In other words, some are core inventory data, some work records, and some inspections or tests. This presentation will go through how to make the best use of asset SMEs and how you can start to develop useful AHIs from what you already know/have. Technically, the process begins with identifying the most critical assets and determining which can best benefit from AHI formulation development. The next steps are used to develop proposed condition factors (CF) and weighting factors (WF) that provide insight into the condition of the assets. Finally, CFs and WFs are used to develop a mathematical algorithm or formulas for the Health Index. We will also discuss how AHI can be used to develop asset management and maintenance strategies – the whole point of the data and analysis in the first place.

Asset Criticality is an important input to production system design, maintenance strategy definition and short term work execution management processes. The value the supporting FEMA exercises provide in determining these categorizations is well understood in the Reliability Community. Less common is the extension of this analytical rigor to the spare parts required to maintain equipment. Establishing and maintaining robust part criticality values can be an invaluable link between operations and the supporting supply chain, helping to set stocking strategies, inform alternative material management approaches and quickly flag when expediting is required. Despite the value, part criticality values (or Risk Priority Numbers) are rarely objectively derived and even less frequently maintained. This presentation is intended to: 1. Establish the link between asset health and spare part availability 2. Illustrate common item criticality practices 3. Provide an overview of a robust item criticality assessment approach 4. Highlight the benefits to be gained from an enhanced approach to item criticality determination.

Business improvements require changes. In reliability and maintenance, some of the change factors are within our control, but many are not. If we stick with small changes, they can often happen but they often fail to achieve their full potential. Why? The short answer is that there are many factors we can’t control and usually we have limited influence. Some of those are related to people and are dealt with by “change management”, but others are related to how our businesses are structured and organized. If we want to make big changes we need to get past that! This presentation will give you something to think about and share with your senior management. If they want miracles from you, then they will need to make it possible!

MainTrain 2021 Panel DiscussionModerator: Susan LubellAuthor of "Root Cause Analysis Made Simple", Susan specializes in asset management and reliability strategy, cost effective lean maintenance programs and operational excellence. She brings over 25 years of practical experience to drive asset management, maintenance and operational business improvement opportunities. Susan currently serves as National President for PEMAC Asset Management Association of Canada, Chair of the World Partners in Asset Management (WPiAM), and teaches for both the Maintenance Management Professional (MMP) and Certified Asset Management Professional (CAMP) programs. Panelists:John Hardwick, Executive Director, Sydney, Roads and Martime Services NSWRepresenting: AMC - Asset Management Council, AustraliaWith extensive Executive Management and Board experience and a background over the past 30 years in asset management within the electricity and transport industries. A passionate leader of organisational improvement in asset and operational risk management, and has implemented world class asset management strategies implementing effective asset management strategies and systems to manage risk and provide value for customers and communities.John is co-author of Living Asset Management.John has a desire to make a difference and explore new ways of solving wicked problems. John is the past Chair of multiple not for profit organisations the World Partners in Asset Management, Global Forum on Maintenance and Asset Management and the Asset Management Council.João Lafraia, President, Fábrica Carioca de Catalisadores S.A.Representing:  ABRAMAN - Associação Brasileira de Manutenção e Gestão de Ativos, BrazilOÃO RICARDO B. LAFRAIA is MSc by the Cranfi eld Institute of Techonology, in England. MBA by the Pontificia Catholic University/State of Paraná. He taught in the graduation and post graduation about Quality Assurance, Reliability and Organization in the Federal University of Paraná and FGV Rio. He is author and co-author of the books of Reliability Handbook, Mantenability and Availability and Strategic Management and Reliability, Creating the Habit of the Excellence. Author of several articles and lectures about Excellence in Management of Reliability and Health, Environment and Security.Lafraia has acted as General-Manager in 5 Refineries around Brazil. He also headed the Operational Excellence Department for all refineries at Petrobras Headquarters in Rio de Janeiro. Executive Director for the FCCSA Chemical Company. He served as board member for 4 chemical companies. At present moment, he has the position of General-Manager in the Exploration and Production Santos Basin Business Unit and Chairman of the Deliberative Council of ABRAMAN.Johannes Coetzee, Managing Director, Machine Assessment & Reliability Technology (Martech)Representing:  SAAMA - The Southern African Asset Management Association, South AfricaJohannes Coetzee is the MD of Martec and Chairman of the Global Forum on Maintenance and Asset Management (GFMAM), the umbrella body for professional associations in the field of maintenance and assets management across the world. He is the past-president of the Southern African Asset Management Association (SAAMA) and also serves on the Advisory Board of the Industrial Engineering Department at the University of Pretoria, South Africa. Johannes is an Industrial Engineer, holds an MBA and has been in the field of asset management for more than two decades. Naoki Takesue, Mitsubishi Research Institute Inc.Representing:  JAAM - Japan Association of Asset Management, JapanMr. Naoki Takesue is a Professional Engineer and has more than 30 years experience in the field of construction management and asset management for public and private sectors.  In MRI, he is engaged in research and consulting works for developing government policies of infrastructure management.  Also, as a director of JAAM, he is  actively involved in the introduction of ISO55000s into Japan.