Article

Lessons Learned for the I02 Project

Authors:
To read the full-text of this research, you can request a copy directly from the authors.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

... For brevity, the paper will only consider applications on commercial aircraft data. Wylie & al. [2] and Yang & Létourneau [3] generalize the concepts presented here and illustrate applications to other kinds of equipment such as mining and railway equipment. The paper is structured as follows. ...
Article
The need for higher aircraft availability and lower maintenance cost is driving the development of Prognostics and Health Management (PHM) technologies. The JSF's Autonomic Logistics (AL) system and the TATEM project are examples of major initiatives that directly rely on PHM for essential enabling technologies. Techniques from artificial intelligence and data mining are expected to provide part of the PHM solution. Research performed at the Institute for Information Technology of the National Research Council of Canada over the last decade demonstrates the usefulness of these techniques for the extraction of knowledge, implementation of PHM reasoning techniques required by decision support tools, and integration of data sources and modelling approaches. However, the process is highly challenging: a significant level of procedural knowledge (or know-how) needs to be developed, the original techniques often need to be extended to achieve an adequate level of accuracy, and the selection of the software development approach appears decisive. Focusing on the use of existing data from a fleet of commercial aircraft and two PHM applications, this paper illustrates the above difficulties in a very practical manner and introduces corresponding solutions. The first application shows innovative use of artificial intelligence techniques to enhance diagnostics and improve maintenance efficiency at the 1st line. The second application introduces a data mining methodology to build prognostic models from readily available data. For both applications, the usefulness of the proposed solutions in terms of increased availability is discussed. The paper also provides an overview of a generic and open PHM software infrastructure developed to support this research. This software facilitates gradual extensions and integration of PHM techniques.
... The applications within the cloud may use the collected data and other information generated by the process control systems and, the maintenance systems and the business and process modelling systems as well as information generated by data analysis tools executed in each of these systems. However, the cloud may use any other desired type of expert system including, for example, any type of data mining system, already proven successful in the creation of knowledge for maintenance as one can see in (Iserman 2006) (Wylie et al. 2002) (Yang and Létourneau 2005). It may also include other applications which integrate data from various functional systems for any other purpose, such as for user information purposes, for diagnostic purposes and for taking actions within the process plant, such as process control actions, equipment replacement or repair actions, altering the type or amount of product produced based on financial factors, process performance factors, etc. ...
Article
Full-text available
A process control system deals with disperse information sources mostly related with operation and maintenance issues. For integration purposes, a data collection and distribution system based on the concept of cloud computing is proposed to collect data or information pertaining to the assets of a process plant from various sources or functional areas of the plant inc1uding, for example, the process control functional areas, the maintenance functional areas and the process performance monitoring functional areas. This data and information is manipulated in a coordinated manner by the cloud using XML for data exchange and is redistributed to other applications where is used to perform overall better or more optimal control, maintenance and business activities. From maintenance point of view, the benefit is that information or data may be collected by maintenance functions pertaining to the health, variability, performance or utilization of an asset. The end user, i.e. operators and maintainers are also considered. A user interface becomes necessary in order to enable users to access and manipulate the data and optimize plant operation. Furthermore, applications, such as work order generation applications may automatically generate work orders, parts or supplies orders, etc. based on events occurring within the plant due to this integration of data and creation of new knowledge as a consequence of such process
Conference Paper
Full-text available
A process control system deals with disperse information sources mostly related with operation and maintenance issues. For integration purposes, a data collection and distribution system based on the concept of cloud computing is proposed to collect data or information pertaining to the assets of a process plant from various sources or functional areas of the plant including, for example, the process control functional areas, the maintenance functional areas and the process performance monitoring functional areas. This data and information is manipulated in a coordinated manner by the cloud using XML for data exchange, and is redistributed to other applications where is used to perform overall better or more optimal control, maintenance and business activities. From maintenance point of view, the benefit is that information or data may be collected by maintenance functions pertaining to the health, variability, performance or utilization of an asset. The end user, i.e. operators and maintainers are also considered. A user interface becomes necessary in order to enable users to access and manipulate the data and optimize plant operation. Furthermore, applications, such as work order generation applications may automatically generate work orders, parts or supplies orders, etc. based on events occurring within the plant due to this integration of data and creation of new knowledge as a consequence of such process.
ResearchGate has not been able to resolve any references for this publication.