4.5 Detective Maintenance

Cameco Corp. has recently deployed approximately 1,500 wireless asset condition monitoring sensors across four of its operations. This presentation will explore all aspects of this project, from initial identification of business pain, all the way through to deployment and management of the system. Condition-based monitoring of rotating assets typically involves a route that is executed at a fixed interval to collect asset condition data. This data can include vibration, temperature, acoustic emissions, and others. This data is then downloaded into software and analyzed for faults and trends. This method has many shortcomings that can be solved with remote sensing technology. This presentation will take you through Cameco’s journey of identifying the limitations of traditional data collection and why an alternative was investigated. Some of the key topics will include problems and inefficiencies with the current system, methodology used to determine which sensor company to partner with, potential cost savings and benefits, deployment strategy and execution, and some screen captures of actual asset detections. Finally, we will conclude with lessons learned and benefits realized from deploying a sensor solution.

As maintainers, we know there is a lot of value in what we do. Without our work, plant, and equipment will soon stop and our companies will then go out of business. What we do impacts safety, health, revenues, costs, and company reputation. A dirty little truth about maintenance is that it is only we who work in it, that really know the value of what we do – or do we? We do know our value in qualitative terms, but can we quantify it? Most maintenance can be improved and we know it. We can do things more efficiently, and we can keep things running more reliably. We often know how to do that, but when we want to make those improvements there is no money for them. Why? Most business people know very little about what we do and how it impacts their business. They see maintenance as a repair shop. We fix what breaks. And they know little, or nothing, more. They may know that maintenance represents a significant cost, and they may even know that they can’t get away with cutting it too much. But they do not know the full value of what maintenance can deliver, nor what it takes to deliver it. If you want to make improvements you need a decision-maker, someone with executive-level authority, to back you up. To get that, you will need to explain what value you can deliver, and in terms they can understand. You will need to show them the savings that are possible from doing things more efficiently, and the added revenues that can arise from investment in defining the right work. You will also need to show them how their support is needed to bring operators and the supply chain into the team with you to make those changes happen so that benefits are fully realized. Quantifying value and being simple in how you say it matters.

We are in unprecedented times. Covid-19 wreaked havoc on supply chains; decreased production during times of increased demand. Labor shortages, chip shortages, long lead items turning into “maybe next year, if you’re lucky” items. The Russia Ukraine war added further stress to supply chains through sanctions, port closures, fuel shortages and much more. What once was reliable is now unreliable. So how can companies overcome an unreliable supply chain to maintain their reliability? There are several ways to mitigate unreliability; scenario planning, supplier management, and technology. There is no one size fits all and what may work for one company will not necessarily work for another. Scenario planning involves reviewing every potential situation that could occur, then working through to see how the company would be impacted. Ultimately this results in mitigation plans for each scenario. These can then be reviewed and implemented. Proper Supplier Management includes ensuring all suppliers have their scorecards reviewed on a regular basis. Their information updated and kept current. It can also include reviewing which suppliers can become substitutes for others in the event one is not able to provide the required product in time. Technology is important as it links all the information together. Algorithms can be created to let management know that certain parts are low, equipment is wearing out sooner, it also collects information on suppliers for the scorecards. Overall technology is the glue that binds and provides real time information updates. This presentation will review how to best use technology to help mitigate reliability and supply chain issues.

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.

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.

With many people at home either due to the closure of their operations, self-isolation protocols, or as a proactive measure to reduce non-essential staff on site, some might question how these individuals can be productive, particularly when assets are not operating. However, if employees have access to their CMMS/EAM/ERP data systems from home, here are some value-added activities that employees and employers should consider undertaking given the time they now have. Note these are in no particular order as priorities would be context-specific, and specific procedures are omitted for this same reason. 

This article is to address the difference in conditional probability of failure patterns, and the impact on how best to maintain assets based upon those differences.

While a host of factors influence profitability, maximizing your plant’s production output potential is arguably one of the facility’s greatest opportunities. An Asset Management, Reliability and Maintenance Strategic Plan can guide continuous improvement that’s aligned with bottom-line performance expectations for managing assets and people. This presentation will provide a framework approach for establishing your strategic asset management & reliability plan and the associated business case. Delegates will gain a fundamental understanding of how to establish a baseline: "know where you are," define where you’re going, who needs to be involved, how to measure the program’s progress and results, and what elements are essential for success.

With all the talk about big data and the IIoT, many are asking how can we use this in maintenance? The IIoT enables us to put sensors in any location where we might want to collect and analyze equipment condition and performance data. There are companies that offer predictive maintenance services, and some companies do this for themselves, in-house. Typically, it’s the larger companies that can afford this, but democratization has meant this has become available to a much broader market. But there are hurdles to taking advantage of this sort of continuous monitoring program, even for your most critical equipment. One, it’s expensive, whether you do it in-house or outsource. And two, there are data bottlenecks. Condition monitoring data comes is huge volumes and it’s all time-sensitive. Even if you can afford it, you need a data handling network with a lot of capacity. In this workshop, we’ll present a viable technical solution to the data bottleneck problem — based on a solution already proven in financial securities markets — that opens up these possibilities in the realm of plant continuous condition monitoring.

Electrical maintenance surveillance device (EMSD) technologies refer to condition-based monitoring technologies and equipment used every day to inspect electrical distribution assets. These surveillance and inspection systems determine the condition of the individual asset or system being inspected and include, but are not limited to, infrared thermography, airborne ultrasound, motor current analysis, partial discharge testing, corona cameras, and visual inspections. The implementation challenge is that the inspection and surveillance equipment used yield their most valuable results when inspecting electrical distribution equipment that’s operating under full load conditions. Doing so while working within the confines of CSA Z462 guidelines can be challenging when the equipment is both of danger to maintenance personnel and of value to the process they’re powering. The surveillance equipment implemented normally requires direct access or direct line of sight to the energized components inside the electrical system. This requires panels to be open, which is extremely dangerous. In this workshop, we’ll show you how EMSD technologies maintain the energized compartment’s closed and guarded condition, ensuring that personnel are not endangered. You’ll learn how the design allows the required test equipment to be used safely at any time, especially when equipment is under full load conditions. We’ll also present a case study from an Ontario beverage bottling facility, demonstrating how these devices can be easily retrofitted on existing electrical distribution equipment to become the nexus for an electrical infrastructure reliability program.