05 Maintenance & Reliability Engineering

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.    

3D printing has important advantages over traditional manufacturing processes. However, as it is a relatively new class of manufacturing technologies, problems of reliability and parameter optimization remain largely unresolved. Our work focuses on addressing some of these issues through in-situ monitoring and closed-loop control, using machine learning as a tool for the endeavour. The idea is to analyze the condition of the process by predicting key characteristics of the final product, and then to use this analysis for adjusting process parameters on the fly. We imagine that this framework of predictive analysis leading to closed-loop control can be extended to a variety of applications outside of 3D printing. In a more general maintenance scenario, sensor readings can be used to assess the condition of equipment and to predict the condition at a future time. This information can then be used to determine appropriate maintenance activities, such as triggering preventive maintenance, scaling back on the intensity of use, and ordering replacement parts, as well as the timing of these events. For our case study in 3D printing, we have implemented in-situ monitoring hardware for a fused deposition modelling (FDM) printer and have constructed a dataset for modelling the process. The dataset consists of in-situ observations (photographs) and select mechanical property measurements for 359 fabricated parts. With this data, we demonstrate the ability of machine learning methods to capture the complex dynamics of a 3D printing process. Specifically, we train a neural network-based model which is able to predict mechanical properties of the final product based on in-situ photographs as well as parameter information. Predictions made by these models can then be used to assess the quality of products as they are being fabricated, thereby making it possible to correct errors or to improve the expected outcome through online parameter adjustments.

The Irving Pulp & Paper maintenance team was the recipient of the PEMAC Maintenance Team of the Year Award for 2021. The team was honored to be nominated based upon long term sustained performance improvements, professional development, controlling reactive maintenance and continuous improvement.

Reliability and Maintenance (R&M) teams at manufacturing facilities employ different maintenance strategies on their physical assets to achieve the desired reliability and maximize the availability of the assets. Most of the production downtime in manufacturing facilities is because of unexpected (or) random failures of equipment and the associated reactive maintenance work. One of the factors that affects the total time to fix failed equipment is spare parts availability. The increasing complexity to minimize production downtime with aging assets demands problem-specific decision models. In this study, a multi-criteria decision model is proposed to assist the R&M stakeholders at manufacturing facilities in making decisions on stocking the right parts. The proposed model will help facilities to stock the spare parts required to maintain the system with-in acceptable and manageable risk. Two case studies from a pulp mill will be presented to demonstrate the use of the proposed decision model. The first case study deals with “Pulp Machine Process Area” with historical data on equipment failures and spare parts usage while the second one focuses on a newly commissioned plant without failure information. The proposed decision model helped to identify the right parts to stock and minimized the risk and inventory costs in both cases.

This paper introduces a Reliability Engineering process also known as Barringer Process Reliability (or BPR). It is a simple yet powerful method for senior managers to assess and quantify the performance of their production plant with simple graphics and a few key performance numbers.  It is “my factory on an A4 page” appropriate for busy managers in an organization.  The underlying mathematical concept for BPR is the Weibull statistical distribution assuming that daily outputs in production plants all follow a Weibull statistical distribution. BPR is not intended to go into the weeds of the losses or low production root causes but rather remains at a high level. However, it is still able to benchmark, quantify production losses as well as opportunities and measure quite precisely, the variability in production outputs. The presenter who is well versed in this technique, will briefly introduce the concept followed by a variety of applications in industrial environments.

This presentation is a holistic approach to precision machinery installation. We all know very well that the installation has direct impact on the performance and the operating life of the rotating equipment. In my presentation first I speak about the importance of standardization of the installation procedures based on existing standards such as API, ISO, NORSOK, ASME and ANSI. Second I speak about the importance of trainings in Installation procedures and the culture of teaching and sharing the knowledge among the team members including the suppliers. And finally the importance of documentation. The collection and transfer of data during the installation phase, though Commissioning and Site testing and then handing over the equipment to the Operations. I also provide a suggestion how to improve and optimize the installation work.

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.

We’ve all heard time and time again the value that Planning and Scheduling brings to a Maintenance organization. But, is your organization fully realizing this value? If Planning and Scheduling is intended to be a “wrench time multiplier” of you Maintenance Technicians, have you looked at the “wrench time” of your Planners and Schedulers? What are the potential barriers preventing them from achieving the ultimate goals of their roles? Can one Maintenance Planner really bring the same effective value as 15-17 tradespersons in your organization? Likely not, and it isn’t the fault of your Planners and Schedulers. In this presentation we’ll review the planning and scheduling function, define what it really is, and more importantly what it is NOT. We’ll also take a close look at many of the “value vampires” common in Planning and Scheduling that detract from the intended value generation. We’ll compare what an ideal Day-in-the-life of a Maintenance Planner should be against the realities they so commonly face. The intent of this presentation is to help you understand Why Planning and Scheduling is likely less effective than it could be in your organization. More importantly, this will hopefully trigger changes that help the Planners and Schedulers in your teams do more of what they do best.

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.

We know that reliability has value to your business, but many of us with technical backgrounds struggle to present a good business case to decision-makers. We are very often held back by budget constraints and we are not in a position to make decisions involving financial risk-taking. Most of us don't have a business background, nor do we speak "finance". It is a whole different language than maintenance and reliability, yet we all want the same things for our business. This presentation will give you some ideas on what you will need to determine in order to show what reliability is worth, and how to present that to decision-makers.