Intelligent Machine Health Monitoring and Maintenance System
Project Duration: October 2001 – March 2003
Sponsor: Ohio Aerospace Institute
Collaborator: Allison Advanced Development Company, B. F. Goodrich Aerospace, and Aircraft Braking Systems
Subcontractor: VerTech LLC
The goal of this project is to develop a preliminary intelligent machine health monitoring and maintenance system and demonstrate its applicability and effectiveness via an industrial case study. Some aircraft component failures can lead to consequences ranging from flight delay or cancellation to personal injury, a significant and increasingly visible problem for the traveling public. Technologies to anticipate maintenance and repair requirements will provide the opportunity to schedule maintenance in ways to minimize cost and flight scheduling disruption. Machine health models that can drill down to subassembly or component levels in failure prediction offer the additional opportunity of enabling maintenance to be targeted to specific components, rather than requiring replacement of complex and expensive assemblies.
Quarter I (10/1/01 – 12/31/01) Activity Summary
Quarter III (4/1/02 – 6/31/02) Activity Summary
1. Feature Extraction from Time-Series Data. In machine
health monitoring and maintenance, a large number of data samples are collected
over time. It is essential to extract
features, such as trends and peaks, from time-series data to identify patterns
associated with the status of a machine.
We have reviewed a number of general feature extraction techniques. We have also realized that customized
feature extraction techniques are needed to deal with specific problems.
2. Engine Condition Monitoring Follow-up Study. In the
initial study, our model achieved an 89.5% accuracy. In an attempt to improve model accuracy, a follow-up study was
conducted. We used more sophisticated
feature extraction techniques and used subtractive clustering for rule
extraction. The model is better than
the initial model, yet we are still unable to achieve 100% diagnosis
accuracy. A closer examination of the
data showed that in some cases, AADC engineers were not absolutely sure about
engine statuses. There is no doubt that
our model can still be improved.
Nonetheless, we believe that our model is very competitive. We are looking forward to a controlled case
study to benchmark our technology with human experts or existing computer
systems. A
detailed report of our follow-up study is available upon request, subject to
AADC approval.
3. Condition-based Maintenance Survey. We started a survey on existing machine health
monitoring and maintenance research. A
list of researchers in the area has been identified.
Quarter IV
(7/1/02 – 9/30/02) Activity Summary
1. Rule extraction. Our initial rule extraction
method requires parameter discretization followed by neural network
training. It is well known that neural
network training is more of an art than science, and there is a potential
danger of overfitting the training data because of the large number of connections
(free parameters). Therefore, we have
developed two other rule extraction methods, one based on decision tree
induction and the other based on clustering analysis.
2. AMFM modeling. There were a few bugs with
our original AMFM (Adaptive Mamdani Fuzzy Model) model implementation in
Microsoft Visual C ++, because of the difficulty (mainly visualization) in
debugging. We have revisited the design
of AMFM and implemented the model in MATLAB, because of the build-in graphical
display capability that facilitates debugging.
Currently, our AMFM model only considers Gaussion type (closed) fuzzy
membership function. We are currently
working on implementing Sigmoid type (open left or open right) membership
functions.
Quarter V (10/1/02 – 12/31/02) Activity Summary
Quarter VI (1/1/03 – 3/31/03) Activity Summary
Summary
This project was carried out in conjunction with a
parallel SBIR (small business innovation research) Phase I project entitled “Development
of an Intelligent Condition-Based Maintenance System,” which was awarded to
VerTech LLC by the National Institute of Standards and Technology (NIST). The SBIR project was from August 2001 to
February 2002 with a total value of $70K.
By pulling the resources together, we were able to successfully complete
two case studies (engine condition monitoring and hard turning) in early
February 2002 and submit a Phase II proposal to NIST. Since we clearly
demonstrated the feasibility of intelligent condition-based maintenance, NIST
awarded the Phase II proposal from August 2002 to February 2004 with a total
value of $300K. Because this OAI CCRP
project was leveraged by the NIST funding, we were able to conduct both
theoretical modeling research and practical case studies. Results of this project are summarized as
follows:
·
Modeling Technology: We adopted a knowledge-based modeling approach
where IF-THEN rules are used as model elements. Two techniques for rule extraction from data are developed,
namely, decision-tree induction and clustering-based rule extraction. A proprietary AMFM model is developed for
rule tuning and optimization.
·
Application: A hard turning case study (tool wear prediction
and identification of bearing wear and fixture misalignment) using simulated
dataset has demonstrated the accuracy and noise immunity of our modeling technology;
while its practical utility is demonstrated via a real-world aircraft engine fault
diagnosis application. Details of both applications are available upon request.
·
Commercialization
Assessment: We have conducted literature-based
business survey and competitive analysis.
We also visited a number of companies to assess the commercial viability
of machine health monitoring and maintenance service. In addition to RRC/AADC, GEAE provided power generator engine
data and Kennametal provided cutting tool wear data. Both datasets are been analyzed under the NIST support. The following companies also provided data:
Parker Hannifin, Timken, Cincinnati Machine, Swagelok, and Everady. However, these data are not suitable for
this particular project either because the way data is collected or the
application focus. A number of
companies also expressed their interest in machine health monitoring but have
no data ready available: Goodrich, Aircraft Braking Systems, and Caterpillar.
·
Future Development: A number of research issues have been identified
for future development, including dimensionality reduction, treatment of data
with missing elements, and model adaptation to a changing environment. A couple of proposals have been submitted to
federal funding agencies.