Instrumentation & Measurement Magazine 25-8 - 5

IMS Technical Committee TC-3:
Condition Monitoring and Fault
Diagnosis Instrument
Weihua Li and Xuefeng Chen
T
his article provides an overview of the IEEE Instrumentation
and Measurement Society (IMS) Technical
Committee TC-3 on Condition Monitoring and Fault
Diagnosis Instrument. TC-3 aims at serving as a platform for
scientists and engineers involved in the field of condition
monitoring and fault diagnosis, with a focus on potential applications
in the industry. Particularly, the main goals of TC-3
are to:
◗ Encourage theoretical and technical research related to
condition monitoring and fault diagnosis.
◗ Promote research for diagnosing major technical equipment
in the fields of industrial robots, new energy, rail
transit, aeronautics, astronautics, etc.
◗ Integrate data processing methods of compressed sensing,
big data, and deep learning with mechanical system
mechanisms to develop intelligent diagnosis and
prediction.
◗ Develop software and hardware systems to facilitate
condition monitoring and fault diagnosis.
◗ Stimulate knowledge exchange between scientists,
provide professional consultative opinions for the industry
of condition monitoring and fault diagnosis, and
promote new standards and guidelines.
TC-3 is a young technical committee as it was established in
2019, but many efforts and preparations were done for its establishment,
and more progress had been achieved since then,
including conducting research projects, organizing academic
conferences, designing teaching activities, and offering public
service.
Research Projects
Within the scope of IMS and Instrumentation & Measurement
Magazine, TC-3 establishes several research projects with experts
and scholars domestically and internationally, such as
Intelligent Fault Diagnosis (IFD) and Blade Tip Timing (BTT).
Intelligent Fault Diagnosis (IFD)
Modern industrial equipment systems have experienced rapid
development in recent years with higher complexity, faster
November 2022
running speeds, and higher intelligence levels. To avoid potential
economic losses, environmental pollution, or casualties
caused by equipment failures (mostly because of the inevitable
fatigue failure of the key working components), the IFD technique
has become crucial for maintenance. Led by TC-3 chairs
and members, the research group has developed Deep Transfer
Learning (DTL)-based methods in the field of IFD.
As a promising paradigm of machine learning, DTL integrates
the advantage of Deep Learning (DL) in feature
representation with the superiority of Transfer Learning (TL)
in knowledge transfer, which is more robust and reliable in actual
applications. The research group led by TC-3 members
has carried out comprehensive studies on DTL-based IFD
methods, and several techniques have been proposed for four
main application scenarios, including generalization performance
improvement of diagnosis models, partial domain fault
diagnosis, emerging fault detection, and compound fault decoupling
[1]. Test rigs based on common rotating machinery
(wind power gearbox, automobile transmission, computerized
numerical control (CNC) machine, industrial robot, etc.)
have been set up, and multiple experiments and validations
have been carried out (Fig. 1a and Fig. 1b). Furthermore, some
of the proposed DTL techniques have been successfully applied
to equipment condition monitoring in real industry.
Blade Tip Timing (BTT)
Blade Tip Timing (BTT) is a non-intrusive technique for measuring
the vibration condition of all blades simultaneously
based on the analysis of time differences between blade tip
passages. Approaches used for the measurement of BTT are
capacitive, eddy current, and optical sensors. Capacitive
sensors are simple and inexpensive, but they have a poor
frequency response and require iron blades. Eddy current sensors
may be affected by magnetic disturbance and need to be
calibrated in advance. Optical fiber sensors are considered
the most powerful probes for online fan/compressor blades
health monitoring as they provide small size and simple measurements,
high sensitivity, resolution and bandwidth, and
insensitivity to electromagnetic interference [2].
IEEE Instrumentation & Measurement Magazine
1094-6969/22/$25.00©2022IEEE
5
Instrumentation & Measurement Magazine 25-8

Table of Contents for the Digital Edition of Instrumentation & Measurement Magazine 25-8
