Real-Time Diagnostics, Prognostics and Health Management for Large-Scale Manufacturing Maintenance Systems

Abstract

Traditional technologies emphasize either experience or model-based approaches to the Diagnostics, Prognostics & Health Management (DPHM) problem. However, most of these methodologies often apply only to the narrow type of machines that they were developed for, and only support strategic level assessments as opposed to real-time tactical decisions. By enabling widespread integration of diagnostics and prognostics into our manufacturing business processes, we have reduced spacio-temporal uncertainties associated with future states and system performance and therefore enabled more informed and effective decisions on manufacturing activities. For large-scale systems, the usual approach is to aggregate multidimensional data into a single-dimensional stream. These methods are generally adequate to extract key performance indicators. However, they only point to observable effects of a failure and not to their root causes. An integrated framework for DPHM requires the availability of bidirectional cause-effect relationships that enable system-wide health management rather than just predicting what its future state would be. This paper summarizes best practices, benchmarks, and lessons learned from the design, development, deployment, and execution of DPHM systems into real-life applications in the automotive industry.

Hierarchical Decomposition of a Manufacturing Work Cell to Promote Monitoring, Diagnostics, and Prognostics

“…PHM may ultimately enable a machine or system to self-diagnose and self-heal with enough intelligence to be both aware of its current health and make an appropriate decision given both its state and goals. This is known as the proactive/intelligent maintenance strategy and is the topic of substantial research [27][28][29]. Current PHM technologies are enabling the three afore-mentioned maintenance strategies (reactive, preventative, and predictive) within a range of manufacturing environments [30][31][32][33][34] .…”

Application of Statistical Techniques and Neural Networks in Condition‐Based Maintenance

“…It may not be the optimal use of resource. The military, manufacturing, food processing, aero‐space, automotive, and various other industries have been considering the use of CBM to ‘lean'out their maintenance processes and practices. In many cases, this approach is more useful and efficient than the existing maintenance policies.…”

Harmonizing Prognostics and Health Management with Risk Analysis for Smart Manufacturing Systems

“…In fact, the first major design component titled PHM Design labels the first step as to "identify high value critical systems." Unfortunately, a smart manufacturing system of systems may involve multiple subsystems or processes that present reasonable targets for the development of PHM systems (Barajas & Srinivasa, 2008). This selection problem is made even more difficult because the potential costs and benefits of those potential PHM systems are subject to uncertainties (Feldman, Jazouli, & Sandborn, 2009 variables, inputs, outputs, and objectives) in order to recognize the interconnectedness and interdependencies between subsystems and components.…”

“…The term "prognostics" refers to the prediction of the future status, health, or performance of components and systems. The term "health management" on the other hand refers to the process of making maintenance and logistics decisions from the prognostics information, available resources, and operational demand (Barajas & Srinivasa, 2008). The focus of health management is to minimize operational loss and to maximize the objectives established by the facility (Lee, Wu, Zhao, Ghaffari, Liao, & Siegel, 2014).…”

“…A commonly used metric within engineering prognostics is the remaining usable life (RUL) of a machine or system (National Institute of Standards and Technology, 2014). The term "health management" on the other hand refers to the process of making maintenance and logistics decisions from the prognostics information, available resources, and operational demand (Barajas & Srinivasa, 2008). The focus of health management is to minimize operational loss and to maximize the objectives established by the facility (Lee, Wu, Zhao, Ghaffari, Liao, & Siegel, 2014 The first part of the risk analysis roadmap is called "The Evolving Base", and it refers to a number of shifting rules and realities that risk analysts and decision makers must always keep in mind.…”