This chapter addresses the paradigm shift in modern maintenance systems from the traditional “fail and fix” practices to a “predict and prevent” methodology. A re- configurable and scalable Watchdog Agent®-based intelligent maintenance system
has been developed, which serves as a baseline system for researchers and companies to develop next-generation e-maintenance systems. It enables machine makers and users to predict machine health degradation conditions, diagnose fault sources, and suggest maintenance decisions before a fault actually occurs. The Watchdog Agent®-based R2M-PHM platform expands the OSA-CBM architecture topology by including real-time remote machinery diagnosis and prognosis systems and embedded Watchdog Agent® technology. The Watchdog Agent® is an embedded algorithm toolbox which converts multi-sensory data to machine health information. Innovative sensory processing and autonomous feature extraction methods are developed to facilitate the plug-and-play approach in which the Watchdog Agent® can be setup and run without any need for expert knowledge or intervention.
Future work will be the further development of the Watchdog Agent®-based IMS platform. Smart software and NetWare will be further developed for proactive maintenance capabilities such as performance degradation measurement, fault recovery, self-maintenance and remote diagnostics. For the embedded Watchdog Agent® application, we need to harvest the developed technologies and tools and to accelerate their deployment in real-world applications through close collaboration between industrial and academic researchers. Specifically, future work will include the following aspects: (i) evaluate the existing Watchdog Agent® tools and identify the application needs from the smart machine testbed; (ii) develop a configurable prognostics tools platform for rotary machinery elements such as bearings, motors, and gears, etc., so that several of most frequently used prognostics tools can be pre- tested and deposited into a ready-to-use tool library; (iii) develop a user interface system for tool selection, which allows users to use the right tools effectively for the right applications and achieve “the first tool correct” accuracy; (iv) validate the reconfiguration of these tools to a variety of similar applications (to be defined by the company participants); and (v) explore research in a ‘‘peer-to-peer’’ (P2P) paradigm in which Watchdog Agent®s embedded on identical products operating under similar conditions could exchange information and thus assist each other in machine health diagnosis and prognosis.
To predict, prioritize, and plan precision maintenance actions to achieve an
“every action correct” objective, the IMS Center is creating advanced maintenance simulation software for maintenance schedule planning and service logistics cost optimization for transparent decision making. At the same time, the Center is exploring the integration of decision support tool and optimization techniques for proactive maintenance; this integration will facilitate the functionalities of the Watchdog Agent®-based R2M-PHM in which an intelligent maintenance systems can operate as a near-zero down-time, self-sustainable and self-aware artificially intelligent system that learns from its own operation and experience.
Embedding is crucial for creating an enabling technology that can facilitate proactive maintenance and life cycle assessment for mobile systems, transportation devices and other products for which cost-effective realization of predictive perform- ance assessment capabilities cannot be implemented on general purpose personal computers. The main research challenge will be to accomplish sophisticated perform- ance evaluation and prediction capabilities under the severe power consumption, processing power and data storage limitations imposed by embedding. The Center
will develop a wireless sensor network made of self-powered wireless motes for machine health monitoring and embedded prognostics. These networked smart motes can be easily installed in products and machines with ad hoc communications. In addition, the Center is investigating the feasibility of harvesting energy by using vibration in an environment equipped with wireless motes for remote monitoring of equipment and machinery. In conjunction with that investigation, the Center is looking at ways of developing communication protocols that require less energy for communication. Power converter circuitry has been designed by using vibration signals in order to convert vibration energy into useful electric energy. These tech- nologies are very critical for monitoring equipment or systems in a complex environ- ment where the availability of power is the major constraint.
In the area of collaborative product life cycle design and management, the Watchdog Agent® can serve as an infotronics agent to store product usage and end- of-life (EOL) service data and to send feedback to designers and life cycle management systems. Currently, an international intelligent manufacturing systems consortium on product embedded information systems for service and EOL has been proposed. The goal is to integrate Watchdog Agent® capabilities into products and systems for closed-loop design and life cycle management, as illustrated in Figure 3.19.
Figure 3.19. Embedded and tether-free product life cycle monitoring
The Center will continue advancing its research to develop technologies and tools for closed-loop life cycle design for product reliability and serviceability, as well as explore research in new frontier areas such as embedded and networked agents for self-maintenance and self-healing, and self-recovery of products and systems. These new frontier efforts will lead to a fundamental understanding of reconfigurability and allow the closed-loop design of autonomously reconfigurable engineered systems that integrate physical, information, and knowledge domains. These autonomously reconfigurable engineered systems will be able to sense, perform self-prognosis, self-
diagnose, and reconfigure the system to function uninterruptedly when subject to unplanned failure events, as illustrated in Figure 3.20.
Enhanced Six-Sigma Design Product
Center
Product Redesign Design for Reliability and
Serviceability
Self-Maintenance
•Redundancy
•Active
•Passive
Health Monitoring
Communications
•Tether -Free (Bluetooth)
• Internet
•TCP/IP Sensors & Embedded
Intelligence Product or
System In Use
Service
Smart Design
Watchdog Agent and Device-to-Business (D2B) are Trademarks of IMS Center Condition-based
Maintenance (CBM)
•Web-enabled Monitoring &
Prognostics
•Decision Support Tools for Optimized Maintenance
•Business and Service Synchronization
•Asset Optimization Degradation Watchdog
Agent®
Web-enabled D2B™Platform (XML-based)
Near “0”
Near “0”
Downtime Life Cycle
Design Closed-Loop
Life Cycle Design
Figure 3.20. Intelligent maintenance systems and its key elements