One of the unique features of the PHM conferences is a full day of free technical tutorials on various topics in health management taught by industry experts. As educational events tutorials provide a comprehensive introduction to the state-of-the-art in the tutorial’s topic. Proposed tutorials address the interests of a varied audience: beginners, developers, designers, researchers, practitioners, and decision makers who wish to learn a given aspect of prognostic health management. Tutorials will focus both on theoretical aspects as well as industrial applications of prognostics. These tutorials reach a good balance between the topic coverage and its relevance to the community.
Presented by Dr. Doug Brown, Sr. Systems Engineer, Analatom, Inc
- Bayesian Filtering for Failure Prognosis
Presented by Dr. Bruno Paes Leão, Lead Scientist, GE Global Research
- Making the (Business) Case for PHM
Presented by Joel Luna, Senior Operations Research Analyst , Frontier Technology, Inc.
- Data Mining
Presented by Dr. Nikunj Oza, Leader Data Sciences Group, NASA Ames Research Center
- Electronics PHM
Presented by Dr. Jose Celaya, Research Scientist, SGT Inc. at the Prognostics Center of Excellence, NASA Ames Research Center
PHM conference tutorials have been a popular event in the past and the PHM Society is proud to continue this service to the community. Tutorials from the past conferences can be freely accessed from respective conference pages.
Kai Goebel firstname.lastname@example.org
George Vachtsenavos. email@example.com
Tutorial Title: Diagnostics
Tutorial Presenter: Dr. Doug Brown, Sr. Systems Engineer, Analatom, Inc.
Diagnosis is the process of identifying the nature and cause of such adverse events. The challenge of diagnosis is to detect a fault in the operation of a system as early and accurately as possible. Researchers in diverse disciplines such as medicine, engineering, the sciences, business, and finance have been developing methodologies to detect fault or anomaly conditions, pinpoint or isolate a faulty component, and identify the impact of a failing or failed component on the overall health of a system. This tutorial will introduce the three elements of diagnosis (fault detection, isolation and identification) with a survey of available techniques, strategies, and applications for each.
Tutorial Title: Bayesian Filtering for Failure Prognosis
Tutorial Presenters: Dr. Bruno Paes Leão, Lead Scientist, GE Global Research
The evolution in computer processing power, sensor data availability and analytics methods is making possible the design and deployment of increasingly sophisticated and powerful health management solutions. Failure prognosis is in the forefront of such advanced solutions, since it enables the implementation of true condition based maintenance: performing maintenance at the most convenient time and eliminating costly surprises in equipment operation. This tutorial is in the context of data analytics for failure prognosis. The focus is in the so called Discrete Time Bayesian Estimation (a.k.a. Bayesian Filtering), which comprises the renowned Kalman Filter (KF) and its variants, and also the Particle Filter (PF), among others. Such methods have been successfully employed in academic and industrial solutions, and have even been claimed by some authors to be the de facto state of the art in failure prognosis. The goal of the tutorial is to provide an intuitive view of this class of methods, describing its most usual variants and how they can be employed for estimating Remaining Useful Life.
Tutorial Title: Making the (Business) Case for PHM
Tutorial Presenter: Joel Luna, Senior Operations Research Analyst , Frontier Technology, Inc.
This capability for advanced warning for the purpose of taking action is one of the key elements in areas such as Prognostics and Health Management (PHM) and initiatives such as Condition Based Maintenance plus (CBM+). Despite the promise of benefits from the application of PHM, it is frequently necessary to justify those benefits by quantifying them in a business case analysis. Although a key part of any business case is determination of the cost benefit of the action taken, usually expressed as a return on investment (ROI), the operational and logistics drivers of those costs are also important to understand and characterize. For this reason, a business case is dependent not only on cost modeling, but modeling of the operations and support of the system as well.
This tutorial covers the following topics:
- Approaches to cost-benefit analysis for PHM and current DoD guidance
- Metrics, PHM attributes, and System Engineering methods/processes
- Logistics and cost modeling in support of PHM BCA
- Requirements-driven approaches to PHM BCA
The tutorial will also provide insights into the relationships between key cost and PHM factors, as well as propose a standard process and tools.
Tutorial Presenter: Dr. Nikunj Oza, Leader Data Sciences Group, NASA Ames Research Center
This tutorial will give an overview of data mining and how it relates to machine learning, statistics, big data, and other related terms that people may have heard. We will then focus on aspects of data mining that are most relevant to prognostics and health management, including concrete examples. We will end with a discussion of some open-sourced data mining tools that NASA has made available and show how attendees can use these tools and join our community of users and developers.
Tutorial Title: Electronics PHM
Tutorial Presenter: Dr. Jose Celaya, Research Scientist, SGT Inc. at the Prognostics Center of Excellence, NASA Ames Research Center
The focus of this tutorial is on the area of prognostics of electronic systems. An overview of the state of the art and latest Intellectual Property will be presented. A review of the most common methods based on the data-driven prognostics approach will be presented. Special attention will be given to model-based prognostics methods for electronic components like power transistors and filter capacitors. This will include modeling of the degradation processes and how to make use of such models in order to assess the condition-based state of health and to predict remaining useful life. A discussion on how these model-based approaches relates to the electronics reliability tools will be presented making emphasis on difference and similarities but with the main objective of conveying how such approaches complement each other.