Instrumentation & Measurement Magazine 25-5 - 26

ZU7EV which has a multi-core ARM and a Field-Programmable
Gate Array (FPGA). The ARM can deal with IO-intensive
tasks, while the FPGA pays attention to customizable computing,
which can realize parallel and pipelined computing.
Though the frequency of the FPGA is lower than that of the
CPU and GPU, a heterogeneous SoC can obtain lower processing
latency, better throughput, and higher computing
efficiency by customizing data structures and computing
structures in the FPGA. This makes the heterogeneous SoCbased
platform more suitable for developing an embedded
OCM instrument that needs to process the condition monitoring
data stream. However, this kind of platform requires
longer development cycles to design a customizable computing
architecture for an intelligent algorithm.
According to the above analysis, when developing the
embedded OCM instrument, it is necessary to select an appropriate
edge computing platform according to the specific data
characteristics and the time complexity of the intelligent assessment
model.
Case Study: Embedded Online
Condition Monitoring Instrument for
UAV
In this case study, fault detection is the main function of the
embedded OCM instrument. With this instrument, the UAV
can detect its faults and take fault mitigation measures in time
to avoid crashes. Airborne sensors in the flight control system
of a UAV are utilized to generate data that reflects the condition
of the UAV. These data can be input into the embedded
OCM instrument as perceived data for the intelligent assessment
of UAV conditions. This section focuses on the intelligent
assessment model in the UAV OCM and the construction of the
embedded OCM instrument.
Intelligent Assessment Model for Fault Detection
Generally, UAV fault detection methods can be divided into
three categories: knowledge-based methods, model-based
methods, and data-driven methods. The fault detection performance
of the knowledge-based method depends on the
richness of the expert knowledge base. It is suitable for detecting
known faults and has the advantage of high efficiency. The
model-based method uses the aerodynamics of the UAV to
establish the fault detection model. Its detection performance
depends on the accuracy of the aerodynamic model, but it is
usually difficult to obtain an accurate model in practical application.
The data-driven method uses machine learning
algorithms to recognize fault patterns in the perceived data.
Historical data are usually used for modelling, and fault detection
is conducted on the online data stream. Because the
data-driven method can automatically learn and model from
historical data, it does not need too much expert knowledge or
an accurate aerodynamic model. Its ease of use makes it the focus
of fault detection researchers.
The data generated by the UAV airborne sensors are time
series. Therefore, the essence of UAV condition monitoring
is time series analysis. In this case study, the time series
26
Fig. 3. Structure of the LSTM memory cell.
prediction method based on deep learning is used to realize
UAV fault detection. At present, the most commonly used and
effective time series prediction method is the Long Short-Term
Memory network (LSTM), which has evolved from RNN [6]. It
is constructed with the LSTM memory cell (Fig. 3), where each
has an input gate, a forget gate, and an output gate. The reasoning
process of the LSTM can be described as follows: When a
d dimensional condition monitoring data
x  R 1d
t
and the hidden state ht
is input to
the cell at time t. Considering the LSTM layer has k cells. The
cell state ct
moment t+1, which are defined as c  and h  , and
the hidden state ht will also be the output of LSTM. The three
t
t
R 1k
gates can be calculated with these formulas:
The input gate:
i  
t
it t
1
ct  tanh( [ , ]
ct t
 1
The forget gate:
ft   f
sigmoid(wh x b
ft t
1
The output gate:
ot   o
wh x b
ot t
1
c   
t tt tt 1fc i c
tt tanh( )t
h  oc
gate, and the output gate; t
c
i

o
are the bias. Furthermore, sigmoid and tanh refer
to sigmoid activation function and hyperbolic tangent activation
function. The symbol '*' denotes the Hadamard product.
To obtain better prediction results from the condition monitoring
data, LSTM can be stacked (Fig. 4). In this model,
the first LSTM layer is working in sequential mode, and the

o
August 2022
sigmoid( [ ,] )
(4)
(5)
(6)
where it, ft, and ot are the outputs of the input gate, the forget
is the intermediate variable to up
, w  R ()k dk , w  R ()k dk

c

f

i
c
f

,
, and
[ ,] )
(3)
sigmoid( [ ,] )
wh x bi
wh x b )
c
(1)
(2)
will be delivered to the next
R 1k
date the cell state ct; and w  R ()k dk
and w  R ()k dk
state. Similarly, b  R ()k dk
b  R ()k dk
are representing the weight matrices of each
 , b  R ()k dk , b  R ()k dk
IEEE Instrumentation & Measurement Magazine

Instrumentation & Measurement Magazine 25-5

Table of Contents for the Digital Edition of Instrumentation & Measurement Magazine 25-5

Instrumentation & Measurement Magazine 25-5 - Cover1
Instrumentation & Measurement Magazine 25-5 - Cover2
Instrumentation & Measurement Magazine 25-5 - 1
Instrumentation & Measurement Magazine 25-5 - 2
Instrumentation & Measurement Magazine 25-5 - 3
Instrumentation & Measurement Magazine 25-5 - 4
Instrumentation & Measurement Magazine 25-5 - 5
Instrumentation & Measurement Magazine 25-5 - 6
Instrumentation & Measurement Magazine 25-5 - 7
Instrumentation & Measurement Magazine 25-5 - 8
Instrumentation & Measurement Magazine 25-5 - 9
Instrumentation & Measurement Magazine 25-5 - 10
Instrumentation & Measurement Magazine 25-5 - 11
Instrumentation & Measurement Magazine 25-5 - 12
Instrumentation & Measurement Magazine 25-5 - 13
Instrumentation & Measurement Magazine 25-5 - 14
Instrumentation & Measurement Magazine 25-5 - 15
Instrumentation & Measurement Magazine 25-5 - 16
Instrumentation & Measurement Magazine 25-5 - 17
Instrumentation & Measurement Magazine 25-5 - 18
Instrumentation & Measurement Magazine 25-5 - 19
Instrumentation & Measurement Magazine 25-5 - 20
Instrumentation & Measurement Magazine 25-5 - 21
Instrumentation & Measurement Magazine 25-5 - 22
Instrumentation & Measurement Magazine 25-5 - 23
Instrumentation & Measurement Magazine 25-5 - 24
Instrumentation & Measurement Magazine 25-5 - 25
Instrumentation & Measurement Magazine 25-5 - 26
Instrumentation & Measurement Magazine 25-5 - 27
Instrumentation & Measurement Magazine 25-5 - 28
Instrumentation & Measurement Magazine 25-5 - 29
Instrumentation & Measurement Magazine 25-5 - 30
Instrumentation & Measurement Magazine 25-5 - 31
Instrumentation & Measurement Magazine 25-5 - 32
Instrumentation & Measurement Magazine 25-5 - 33
Instrumentation & Measurement Magazine 25-5 - 34
Instrumentation & Measurement Magazine 25-5 - 35
Instrumentation & Measurement Magazine 25-5 - 36
Instrumentation & Measurement Magazine 25-5 - 37
Instrumentation & Measurement Magazine 25-5 - 38
Instrumentation & Measurement Magazine 25-5 - 39
Instrumentation & Measurement Magazine 25-5 - 40
Instrumentation & Measurement Magazine 25-5 - 41
Instrumentation & Measurement Magazine 25-5 - 42
Instrumentation & Measurement Magazine 25-5 - 43
Instrumentation & Measurement Magazine 25-5 - 44
Instrumentation & Measurement Magazine 25-5 - 45
Instrumentation & Measurement Magazine 25-5 - 46
Instrumentation & Measurement Magazine 25-5 - 47
Instrumentation & Measurement Magazine 25-5 - 48
Instrumentation & Measurement Magazine 25-5 - 49
Instrumentation & Measurement Magazine 25-5 - 50
Instrumentation & Measurement Magazine 25-5 - 51
Instrumentation & Measurement Magazine 25-5 - 52
Instrumentation & Measurement Magazine 25-5 - 53
Instrumentation & Measurement Magazine 25-5 - 54
Instrumentation & Measurement Magazine 25-5 - 55
Instrumentation & Measurement Magazine 25-5 - 56
Instrumentation & Measurement Magazine 25-5 - 57
Instrumentation & Measurement Magazine 25-5 - 58
Instrumentation & Measurement Magazine 25-5 - 59
Instrumentation & Measurement Magazine 25-5 - 60
Instrumentation & Measurement Magazine 25-5 - 61
Instrumentation & Measurement Magazine 25-5 - 62
Instrumentation & Measurement Magazine 25-5 - 63
Instrumentation & Measurement Magazine 25-5 - 64
Instrumentation & Measurement Magazine 25-5 - 65
Instrumentation & Measurement Magazine 25-5 - 66
Instrumentation & Measurement Magazine 25-5 - 67
Instrumentation & Measurement Magazine 25-5 - Cover3
Instrumentation & Measurement Magazine 25-5 - Cover4
https://www.nxtbook.com/allen/iamm/26-6
https://www.nxtbook.com/allen/iamm/26-5
https://www.nxtbook.com/allen/iamm/26-4
https://www.nxtbook.com/allen/iamm/26-3
https://www.nxtbook.com/allen/iamm/26-2
https://www.nxtbook.com/allen/iamm/26-1
https://www.nxtbook.com/allen/iamm/25-9
https://www.nxtbook.com/allen/iamm/25-8
https://www.nxtbook.com/allen/iamm/25-7
https://www.nxtbook.com/allen/iamm/25-6
https://www.nxtbook.com/allen/iamm/25-5
https://www.nxtbook.com/allen/iamm/25-4
https://www.nxtbook.com/allen/iamm/25-3
https://www.nxtbook.com/allen/iamm/instrumentation-measurement-magazine-25-2
https://www.nxtbook.com/allen/iamm/25-1
https://www.nxtbook.com/allen/iamm/24-9
https://www.nxtbook.com/allen/iamm/24-7
https://www.nxtbook.com/allen/iamm/24-8
https://www.nxtbook.com/allen/iamm/24-6
https://www.nxtbook.com/allen/iamm/24-5
https://www.nxtbook.com/allen/iamm/24-4
https://www.nxtbook.com/allen/iamm/24-3
https://www.nxtbook.com/allen/iamm/24-2
https://www.nxtbook.com/allen/iamm/24-1
https://www.nxtbook.com/allen/iamm/23-9
https://www.nxtbook.com/allen/iamm/23-8
https://www.nxtbook.com/allen/iamm/23-6
https://www.nxtbook.com/allen/iamm/23-5
https://www.nxtbook.com/allen/iamm/23-2
https://www.nxtbook.com/allen/iamm/23-3
https://www.nxtbook.com/allen/iamm/23-4
https://www.nxtbookmedia.com