Mechatronics 31 (2015) 124131

Contents lists available at ScienceDirect

Mechatronics
journal homepage: www.elsevier.com/locate/mechatronics

Modeling of pneumatic articial muscle using a hybrid articial neural

network approach
Chunsheng Song a,, Shengquan Xie b, Zude Zhou a, Yefa Hu a
a
b

School of Mechanical and Electronic Engineering, Wuhan University of Technology, Wuhan 430070, China
Department of Mechanical Engineering, The University of Auckland, Auckland 1142, New Zealand

a r t i c l e

i n f o

Article history:
Received 15 September 2014
Revised 13 March 2015
Accepted 27 April 2015
Available online 29 June 2015
Keywords:
Pneumatic articial muscle
Dynamic modeling
Hybrid approach
Articial neural network
Genetic algorithm

a b s t r a c t
Pneumatic Articial Muscle (PAM) actuator has been widely used in medical and rehabilitation robots,
owing to its high power-to-weight ratio and inherent safety characteristics. However, the PAM exhibits
highly non-linear and time variant behavior, due to compressibility of air, use of elastic-viscous material
as core tube and pantographic motion of the PAM outer sheath. It is difcult to obtain a precise model
using analytical modeling methods. This paper proposes a new Articial Neural Network (ANN) based
modeling approach for modeling PAM actuator. To obtain higher precision ANN model, three different
approaches, namely, Back Propagation (BP) algorithm, Genetic Algorithm (GA) approach and hybrid
approach combing BP algorithm with Modied Genetic Algorithm (MGA) are developed to optimize
ANN parameters. Results show that the ANN model using the GA approach outperforms the BP algorithm,
and the hybrid approach shows the best performance among the three approaches.
2015 Elsevier Ltd. All rights reserved.

1. Introduction
Pneumatic Articial Muscle (PAM) is a biomimetic device that
mimics the behavior of skeletal muscles. It exhibits forcelength
characteristics similar to that of a human muscle. PAM has simple
construction and consists of a rubber tube connected to pneumatic
valves at one end. The rubber tube is housed in a sheath made-up
of non-elastic and high-strength bers. The bers are arranged in a
rhomboidal fashion, which allows a dened contraction motion in
a longitudinal direction when the inner tube is inated which
results in shortening of the PAM. Consequently, force is exerted
by the PAM on the environment, attached at the other end, in
the axial direction. Compared to conventional actuators such as
electric and hydraulic actuators, PAM draws certain advantages
such as high power-to-weight and high power-to-volume ratios,
low maintenance, low price, cleanliness, compliance, pliability,
inherent safety, and applicability in rough environments. Air compressibility and elasticity of inner tube also plays cushioning role
against unpredictable impacts. Owing to these advantages, PAM
is considered an attractive and safe actuator to use in devices operating in human proximity compared to electric or hydraulic
actuators.
Corresponding author. Tel.: +86 13437161368.
E-mail address: song_chsh@163.com (C. Song).
http://dx.doi.org/10.1016/j.mechatronics.2015.04.021
0957-4158/ 2015 Elsevier Ltd. All rights reserved.

Recently, PAM has been regarded as a suitable alternative to

hydraulic and electric actuators in medical and rehabilitation robot
applications. A few examples of the successful use of PAMs in
mechatronic devices for rehabilitation purposes can be found in
the literature. Applications in the form of an exoskeleton exist
for upper limbs [1,2] lower limbs [3], hand [4], elbow [5], and
the ankle joint [6].
Unfortunately, PAM exhibits highly nonlinear pressurelength
characteristics and time-variant properties due to compressibility
of air, elastic-viscous properties of the inner tube and geometrically complex behaviors of the PAM shell. Rubber like behavior of
the inner tube also lead to hysteresis and hence the PAM shows
different characteristics during inating and deating. Thus, it is
not easy to control them and obtain the required performance features. In view of this, previous studies have focused on methods for
modeling of pneumatic muscles and controller design to improve
control performance in recent years, including [7,8].
Considering that the precise modeling of PAMs can be the rst
step in improving the control performance of system, this paper
presents the dynamic modeling of PAM. In order to identify behavior of a PAM, many models to estimate behavior of PAMs have been
proposed in the past. The pioneering work in the eld of PAM modeling can be classied into two aspects, analytical modeling and
articial intelligence-based modeling identication.

125

C. Song et al. / Mechatronics 31 (2015) 124131

Analytical modeling method is a common method and an early

adopter. Initially, to reduce the model complexity, elastic energy
contained in the inner tube was ignored and the relations between
axial force, length and pressure were formulated based on the principle of virtual work [9]. Later, nonlinear characteristics of PAM
were addressed which included, irregular geometric shape of the
rubber tube [10,11], elastic energy of the inner tube [12], and hysteresis behaviors of PAMs. A friction model was also developed for
the thread-on-thread friction in the braided shell [9,10,13]. Until
recently, most researches have been focused on the static characteristics of PAMs assuming no pressure variance inside the tube
during very slow motions. Chou and Hannafordpresented a simple
lumped-parameter model of pneumatic circuits to estimate
dynamic response of pneumatic circuits [14]. Kang and Kothera
proposed a dynamic modeling of PAM [15]. The quasi-static characteristics of the PAM are modeled followed by the dynamic characteristics through spectral analysis [16]. A new approach to model
the hysteresis of a basic antagonistic manipulator joint constructed
by a pair of Festo uidic muscles is present [17].
While lot of work has been done to analytically model the pneumatic muscles, the accurate prediction of their dynamic behavior
could not be achieved. These analytical models still have limitations in predicting on behavior of the PAM [18]. This is due to lake
of knowledge of PAM behavior in the light of its conical ends, friction between the inner tube and outer sheath, valves and uid ow
characteristics and large hysteresis. It is evident from the discussion in the preceding section that the conventional tools cannot
fully comprehend the non-linear and time dependent muscle characteristics. Therefore, the articial intelligence-based modeling
identication methods are introduced and quantiable work has
been done in this direction. Ahn and Anh applied a Modied
Genetic Algorithm (MGA) for optimizing parameters of a linear
auto-regressive with exogenous (ARX) model of the PAM manipulator, which can be modied online with an adaptive self-tuning
control algorithm. Through experimental investigation, the proposed MGA-based identication algorithm achieves excellent performance in comparison with conventional SGA and LMS methods
[19]. However, the work has been done for constant loading it cannot be used for force control applications of PMA. A neural network
ARX (NNARX) model has been applied to non-linear modeling and
identication of the PAM manipulator using a new INCBP algorithm [1921]. The parametric values of the ARX model have been
optimized using modied GA (MGA). The MSE of this model has
been reported as 0.02616 rad. Incremental back propagation algorithm used to train the NN to further reduce MSE of the model as
0.0035 radians. Prashant proposed a PAM modeling method using
modied fuzzy inference mechanism. To tune the parameters of
fuzzy model three approaches namely, Gradient Descent (GD)
method, Genetic Algorithm (GA) and Modied Genetic Algorithm
(MGA) are used. MGA based fuzzy model was found to be more
accurate [22]. A novel implementation of a SOFC is proposed for
the control of a single PAM. In order to assess the advantage of
the intelligent adaptive control system, a comparison of the performance of three types of nonparametric control algorithms (PD, FFC
and SOFC) is also presented [23].
Summarizing the above discussion, most of the research on
PAM modeling has been done in no-load load or constant conditions, neglecting loads, especially the change in loads. However,
in this paper, the PAM will be used for ankle rehabilitation robot
application, the loads cannot be taken as constant, moreover the
load may change rapidly sometimes. And also, to obtain more
accuracy control performance in rehabilitation robot eld, the
prediction accuracy from the previous models also needs to be
improved.
Articial neural networks can effectively model systems, which
possess non-linearity and uncertainties [24]. In order to address

above problems of PAM modeling, this paper proposes a multilayer

articial neural network to solve the PAMs dynamic modeling
problems. To get greater modeling accuracy, the parameters of
the ANN model are optimized by three different approaches,
namely, Back Propagation (BP) algorithm, Genetic Algorithm (GA)
approach and hybrid approach combing with BP algorithm and
Modied Genetic Algorithm (MGA). The results obtained from
the three approaches are analyzed and compared in terms of mean
square error (MSE) and maximum deviation of prediction pressure
errors.

2. The basic characteristics of pneumatic articial muscle

PAMs converts pneumatic energy into mechanical form by
transferring the pressure applied on the inner surface of its tube
into the shortening action. The relationship between pressure (P),
length (L) and force (F) can be written as shown below based on
the principle of virtual work [14]:
2

F P  dV=dL P  D2o p=4 sin h  3 cos2 hk  1

where k L=L0 , and L0, D0 are the initial length and the diameter of
the tube respectively, h is the initial pitch angle of the braid.
However, since the tube shape is not perfectly cylindrical when
pressurized and large hysteresis is present in PAM, above models
cannot be used in their present form, instead improved model has
been built to compensate these variations. However, the model
parameters are difcult to obtain because of the inuence of uncertain factors, such as time-variety, nonlinearity and environment.
In order to construct a neural network based model of PAM,
training data is required to be obtained. The experimental set up
used for this purpose shown in Fig. 1.
Tests are conducted on a single PAM which is placed in a rigid
hanger as shown in Fig. 1(a). Linear position sensor is positioned
parallel to the PAM to record instantaneous length of PAM. A
FUTEK load cell is connected to the PAM and used to measure
the force dynamically.
Pneumatic muscle is inated by connecting it to the pressure
supply from a compressor. The supply pressure was xed at
2 bar and two Isonic pressure regulating valves are used to control
pressure inside the PAM. These valves are capable to provide a
switching frequency of 10 ms and are used to ll, leave inated
and empty the PAM actuator.
As shown in Fig. 1(b), a dSPACE (DS1104) data processing system is used to provide interface to a PC allowing MATLAB and
Simulink programs to be used. The dSPACE has a number of
Input/Output (I/O) capabilities including serial, analogue, and digital, which are used to read data from various sensors and generator control signals. The PAM is controlled by compiling a Simulink
model and downloading it to the DS1104 through the I/O interface.
The dSPACE is connected to PC through RS-232 serial port.
Under different loads and different pressures, the experimental
data are received through serial port from various sensors. The
actual behaviors of the PAM obtained from the experiment setup
is shown in Figs. 2 and 3. Results from the experiments (Fig. 2)
show that the characteristic between length and pressure of PMA
is non-linear. The variable external loading on the PAM also affects
the characteristic considerably. Moreover, from Fig. 3, the plot is
some of different while inating or deating the PAM and a lager
hysteresis exists.
ANN is usually used to model complex relationships between
inputs and outputs or to nd patterns in data. Therefore, in this
paper, a multilayered feed forward ANN is being proposed to
model PAM.

126

C. Song et al. / Mechatronics 31 (2015) 124131

Fig. 1. Experiment setup for a PAM using in an ankle rehabilitation robot. (a) Experiment setup for single PAM. (b) Overall structure of the system.

3. ANN architecture of PAM model identication

Through the analysis of Section 2, the purpose of modeling is to
nd out a precise relationship among the parameters of length,
force and pressure. However, from Figs. 2 and 3, we nd that the
change in load and the change in length may well inuence the
relationship. The ANN model developed for PAM modeling in the
present work has four input variables, which are instantaneous
values of length, change in length, load and change in load. The
model has a single hidden layer containing ve neurons; the number of neurons in the layer is roughly determined by experience
formula and then it is determined to ve by the method of trial
and error. A hyperbolic tangent sigmoid transfer function is
selected to best emulate the non-linear behavior of the PAM in hidden layer. Linear transfer function is used for the output layer as a
usual practice.
The detailed architecture of the ANN is shown in Fig. 4 wherein
x1, x2, x3, x4 are inputs, namely, length, change in length, load and
Fig. 2. Extension length of PAM when inating.

change in load. Further, wij is the input-hidden layer weight from

2

input neuron j to hidden neuron I and wki is the hidden-output

weight from hidden neuron i to output neuron k. Bias weights
1

are shown by bi

Fig. 3. Extension length characteristics of PAM when ination and deation

(100 N).

and bk for hidden neuron i and output neuron

Fig. 4. Architecture of ANN model for PAM dynamic modeling.

127

C. Song et al. / Mechatronics 31 (2015) 124131

Table 1
Whole structured parameter variables of the ANN model.
w11

w12

w13

w14

w21

w22

w23

w24

w31

w32

w33

w34

w41

w42

w43

1
w51

1
w52

1
w53

1
w53

1
w54

1
b1

1
b2

1
b3

1
b4

1
b5

2
w1

2
w2

2
w3

2
w4

2
b1

k respectively. Mathematical relationship between the layers is

expressed in term of these weights.
According to the ANN model shown in Fig. 4, there are 31
parameter variables required to be optimized. All the variables
are structured and listed in Table 1. For comparison, in the
research, three training approaches of the ANN model, namely,
BP, GA and hybrid approach will be developed as discussed in
the following section.
4. Hybrid approach
Optimum parameters of ANN using efcient optimization algorithms, is the key to achieve higher accurate modeling of PAM. As
mentioned in the previous section, 31 variables of ANN are
required to be optimized. There are numerous algorithms available
for training ANN models such as Reinforced, Hebbian, Gradient
Descent (GD) and Evolutionary Algorithm (EA). GD method is a
widely used method for training ANN model [25]. Back
Propagation (BP) algorithm, a type of GD method, is the most
widely used approach for training ANN model. Due to simplicity,
BP is a common method of training articial neural network, however, it has some limitations, such as slow and local minimum.
Because of inherent limitations of BP algorithm, it and its
improved BP algorithms, such as additional momentum method,
adaptive learning rate [26] are hard to resolve the problems of local
optimal and sensitivity to initial values completely.
Genetic Algorithm (GA) belongs to the larger class of evolutionary algorithm, which generates solutions to optimization problems
using techniques inspired by natural evolution, such as mutation,
selection and crossover. In theory, GA can gain global optimum
solution in a certain condition, which is widely used in many areas
for its favorable global searching. However, it also has some shortcomings such as premature and slow convergence.
Therefore in this paper, the modied genetic algorithm are proposed to resolve the problems. We have proposed two modications in conventional GA, rst, an elitism and worst eliminated
selection method has been used to ensure that the best solution
does not become extinct in the process of evolution. Second,
self-adjusting mutation and crossover rate method are used.
However, the weak local search capabilities cannot also be solved.
Therefore a hybrid approach is proposed. First, a Modied Genetic
Algorithm (MGA) is proposed to improve the convergence speed
and avoid premature solution. Second, in view of the high capability of BP algorithm in local search and GA in global search, a hybrid
approach combing with BP algorithm and MGA is developed and
proposed. MGA is used to search a global solution initially and
BP algorithm is used to ne tune the solution afterwards.
The tness function (F) of MGA is dened as:

F 1=1 T

where T is the quadratic sum of the difference (T) between reference

output and actual output in Eq. (3).
The quadratic sum of the difference (T) between reference output and actual output is described rstly, and it is written as:

T
T
X
X
2
2
ek
yd k  ya k
k1

k1

where k (k = 1, 2, . . . , T) is the number of output values; yd k is the

reference output values, obtained from the experiment; ya(k) is the

w44

ANN model actual output values as shown by Eq. (4), it can be written as:

ya f 2

5
X
i1

2
wi

 f1

4 
X

1
wij

 xj

1
bi

!!


!
2

j1

Here, i = 1, 2, . . . , 5 is the number of the hidden neurons; j = 1, 2, 3, 4

is the number of the input neurons; f 1 is the activation function of
hidden neuron; f 2 is the activation function of output neuron. The
objective of training the ANN model is to minimize the difference
between reference output and actual output.
Thirty-one variables listed in Table 1 are grouped in a
chromosome-like structure, which in turn is interpreted as the
ANN model. The chromosome-like individual is coded using real
number string to describe 31 variables of the ANN model. 100 individual solutions are randomly generated to form an initial population. Each variable in the individual solution is assigned for short
type and the tness accuracy of the order is 10e4, and the maximum tness value is 0.9999, which is the ttest solution.
There are two main steps of the hybrid approach. First, search
the optimal weights and bias weights values using the MGA.
Then, switch to the BP algorithm to ne tune the weights, when
some transition conditions are satised. The essence of the hybrid
approach is that the initial weights and bias weights values of BP
algorithm are provided by MGAs solution. The BP algorithm can
nd solution in global optimal path. The approach can make good
use of both merits of the MGA, namely, global searching capability
and BP algorithm namely, local searching capability.
The rough solution is searched initially using MGA and ne
tuned using the BP algorithm next. This process is repeated until
a termination condition has reached. The termination conditions
are, (1) Fixed number (NMax) of iterations has reached; (2) The ne
tuned solution has reached the optimum solution (MSEmin).
Various steps used in the whole hybrid approach are explained
as below in detail.
Step 1. Select the termination conditions. In the present, the
approach will switch to BP algorithm if the tness value reaches
0.9999 or the number of epochs is GMax.
Step 2. Initialize a population of 100 individual solutions
randomly.
Step 3. Append the maximum tness (Max (gen  1)) solution
obtained from the preceding iteration into the present generation. Calculate the tness value of each solution and sort the
solutions ascending by tness value. Then nd the maximum
tness (Max (gen)) from present generation. Compare it with
the termination conditions. Continue if the tness is less than
0.9999 and the number of epochs is less than GMax, then gen = gen + 1; go to Step7 otherwise.
Step 4. Save a copy of the ttest solution (Max (gen)) separately.
Eliminate the worst 20 percent individual solutions and ll in
by the equal numbers of random data.
Step 5. Apply crossover and mutation operations to form a new
generation. The crossover rate and mutation rate are changed
dynamically. The top 20% epochs, the crossover rate is 0.9 and
mutation rate is 0.04. The middle 40 percent epochs, the crossover rate is 0.85 and mutation rate is 0.08. The nal 40% epochs,
the crossover rate is 0.8 and mutation rate is 0.12.
Step 6. Return to Step 3.
Step 7. Switch into the BP algorithm with adaptive learning rate.

128

C. Song et al. / Mechatronics 31 (2015) 124131

Fig. 5. The process of hybrid approach.

Step 8. Calculate the MSE value of each iteration (MSE (N)).

Compare it with the termination criterion. Continue if the
MSE (N) is more than MSEmin and the number of iterations is
less than Maximum iterations (NMax); terminate otherwise.
Step 9. Forward propagation and back propagation.
Step 10. Update the weights and bias weights of ANN to reduce
the difference between actual output and reference output.
Step 11. Return to Step 7.
In order to get better understanding of the steps of the hybrid
approach, the process of the hybrid approach is displayed as in
Fig. 5.
5. Experimental result and discussion
Experiments are carried out to validate the proposed ANN
model and evaluate the performance of the BP, GA and hybrid
approaches. The experimental setup as shown in Fig. 1(b) is located
at he mechanic laboratory, university of Auckland, New Zealand.
Because the PAM is used in an ankle robot ultimately to realize
range of motion and strength training treatments for ankle injuries.
Therefore, the experimental setup of the PAM was moved through
a sinusoid motion trajectory. The frequency of the motion is 0.2 Hz.
The amplitude of the motion is 0.1 m. The total of data are 1200,

which obtained from sensors are divided equally into three parts;
one part is used for training the ANN model and the remaining
parts are used for validation and testing.
The ANN for PAM modeling has been discussed in Section 3. To
provide accuracy model of PAM, three approaches, namely, the BP,
the GA and the hybrid approach are used to train the ANN model
using the training experiment data respectively.
Firstly, the adaptive learning rate BP algorithm is used to train
the ANN model. After 30,000 iterations, results from the training
data show that the MSE to predict pressure inside of the PAM is
found to be 0.0020 bars and the maximum deviation is 11.30% as
shown in Fig. 6. However, from the discussion provided in
Section, we know the error in pressure has an import inuence
on the PAM characteristic and then may affect the control performance of PAM. To investigate whether the BP algorithm has converged at a local optimal solution and there exists a better
solution, the GA approach is used to train the ANN model with
the same training data as BP algorithm. The initial population of
GA is 100. The crossover rate of GA is 0.85 and mutation rate of
GA is 0.08. After around 100 epochs, the MSE and maximum deviation are 0.0011% and 5.96% respectively as shown in Fig. 6. Finally,
the hybrid approach is used to train the ANN model, after only 40
epochs of MGA and 3000 iterations of BP discussed in Section 4, the
MSE and maximum deviation are only 4.9725e05 bar and 2.5%.

129

C. Song et al. / Mechatronics 31 (2015) 124131

Fig. 6. Prediction errors in pressure (Training Data), using three training approaches.

The ANN model 31 parameter variable values using both BP, GA

and hybrid approach are listed in Tables 24. According to these
values, we can obtain the three trained ANN models of the PAM.

The test data has been used to check up on the performance of

the three trained ANN models. Results from the test data of the
three trained ANN models are shown in Fig. 7. The curves of the

Table 2
Variables values of trained ANN model using BP algorithm.
Variables
Values
Variables
Values
Variables
Values
Variables
Values

w12
8.9996

w33
2.2143

w54
18.0255

w4
0.2121

w11
1.8865
w32
30.2450
w53
1.3906
w3
0.5498

w13
0.6904

w14
94.4721

w34
33.3589

b1
2.1277

w41
9.0617

w5
0.0683

w21
0.8834

w42
15.7800

b2
0.0984

w22
35.2783

w43
3.8057

w23
1.1611

w44
7.8467

b3
1.9565

w24
58.2131

w51
9.1710

b4
4.0210

b5
0.8115

w31
6.7941

w52
26.0014

w2
0.6225

w1
0.3112

b1
1.2638

Table 3
Variables values of trained ANN model using GA approach.
Variables
Values
Variables
Values
Variables
Values

w12
1.2597

w41
1.3205

w11
0.9991
w34
1.5959
1

b3
0.9390

w13
0.6889

w42
0.7246

b4
1.2309

w14
1.7253

w43
0.8699

b5
1.7410

w21
0.1098

w44
1.0578

w2
1.1059

w1
0.6087

w22
0.5190

w23
0.7927

w51
0.9073

w3
0.0900

w24
0.6427

w52
1.4820

w31
0.5095

w53
0.8407

w4
0.8914

w5
1.0290

w24
0.8425

w53
1.1139

w5
0.0118

w32
1.7005

w54
0.3324

b1
0.0004

b1
0.9429

b2
0.3191

w33
0.8234

w33
1.4898
1

Table 4
Variables values of trained ANN model using hybrid approach.
Variables
Values
Variables
Values
Variables
Values

w12
0.2627

w41
1.0881

w11
0.0586
w34
1.3249
1

b3
0.0096

w13
1.6091

w42
0.2467

b4
0.0338

w14
0.0518

w43
0.9576

b5
1.2911

w21
1.1907

w44
0.1673

w2
0.0152

w1
1.1343

w22
0.3147

w23
1.3745

w51
1.0797

w52
0.9960

w3
0.0713

w4
1.0319

w31
0.0001

w32
0.0000

w54
0.8296

b1
1.2710

b1
1.2419

b2
1.3957

130

C. Song et al. / Mechatronics 31 (2015) 124131

Fig. 7. Predict pressure (Test Data), using three training approaches.

trained ANN model output results using BP, GA and hybrid

approach are compared with the curve of reference data (experimental data) in Fig. 7. It can be seen that the GA approach has
achieved better performance than the BP algorithm, and hybrid
approach shows the best performance.

The prediction errors in pressure are calculated between the

three trained ANN model outputs and the reference data. The deviations of three ANN models with reference data are shown in Fig. 8.
It can be seen that the MSE is 0.0026 bars and the maximum deviation is 13.64%, using BP algorithm which are 0.0010 bars and
6.36% using GA approach.

Fig. 8. Prediction errors in pressure (Test Data), using three training approaches.

C. Song et al. / Mechatronics 31 (2015) 124131

The last subgure in Fig. 8 shows the errors using hybrid

approach. The MSE is 9.3398e5, which is one tenth of the GA
approach. The maximum deviation is 3.28%, which is only half of
the GA approach. Clearly, hybrid approach based ANN model
shows improved performance compared to other approaches. The
proposed approach shows improvement over a similar work by
Chang and Lilly that 23,340 iterations were required to achieve a
MSE of 0.0011 [27]. Three strategies were introduced in the MGA
based NARX fuzzy model, and these strategies can ensure a global
optimal solution, but they do not enhance the local search capabilities of GA. Their proposed best approach can provide a MD of 10%
[28]. It is clear that the modeling performance for PAM using ANN
model trained by hybrid approach is much better than these three
strategies.
6. Conclusion
This paper proposed an articial neural network approach to
model the non-linear and time variant behavior of PAM. In order
to train the parameters of the ANN model, BP algorithm, GA and
hybrid approach were developed. Research showed that the three
trained ANN models were able to represent the relationship
between force, length, and pressure of the PAM to certain degree
of accuracy. The results obtained from the BP algorithm, the GA
approach and the hybrid approach were analyzed in terms of their
MSE, maximum deviation and convergence rate. The GA approach
was found to be more accurate than the BP algorithm, and showed
faster convergence rate. The hybrid approach showed the best
preference among the three approaches.

[5]

[6]
[7]

[8]

[9]

[10]
[11]

[12]

[13]
[14]
[15]

[16]
[17]

[18]

Acknowledgment

[19]

The authors would like to acknowledge the nancial support by

the National Natural Science Foundation of China (No. 51205296).

[20]

[21]

Appendix A. Supplementary material

Supplementary data associated with this article can be found, in
the online version, at http://dx.doi.org/10.1016/j.mechatronics.
2015.04.021.

[22]

References

[24]

[1] Balasubramanian S, Wei H, Perez M, ShepardB, Koeneman E. RUPERT: an

exoskeleton robot for assisting rehabilitation of arm functions. Virt Rehabil
2008;4625154:1637.
[2] Kousidou S, Tsagarakis N, Caldwell DG, Smith C. Assistive exoskeleton for task
based physiotherapy in 3-dimensional space. In: Proceedings of the rst IEEE/
RAS-EMBS international conference on biomedical robotics and
biomechatronics; 2006. p. 26671 [art. no. 1639097].
[3] Costa N, Caldwell DG. Control of a biomimetic soft-actuated 10 DoF lower
body exoskeleton. In: Proceedings of the rst IEEE/RAS-EMBS international
conference on biomedical robotics and biomechatronics; 2006. p. 495501.
[4] Xing K, Xu Q, He J, Wang Y, Liu Z, Huang, X. A wearable device for repetitive
hand therapy. In: Proceedings of the 2nd biennial IEEE/RAS-EMBS

[23]

[25]

[26]
[27]
[28]

131

international conference on biomedical robotics and biomechatronics; 2008.

p. 91923 [art. no. 4762789].
Zhang JF, Yang CJ, Chen Y, Zhang Y. Modeling and control of a curved
pneumatic muscle actuator for wearable elbow exoskeleton. Mechatronics
2008;18(8):44857.
Ferris DP, Czerniecki JM, Hannaford B. An ankle-foot orthosis powered by
articial pneumatic muscles. J Appl Biomech 2005;21(2):18997.
Chan SW, Lilly JH, Repperger DW, Berlin JE. Fuzzy PD+I learning control for a
pneumatic muscle. In: IEEE international conference on fuzzy systems, vol. 5;
2003. p. 27883.
Hesselroth T, Sarkar K, Patrick Van der Smagt P, Schulten K. Neural network
control of a pneumatic robot arm. IEEE Trans Syst Man Cybern
1994;24(1):2838.
Chou CP, Hannaford B. Static and dynamic characteristics of Mckibben
pneumatic articial muscles. In: IEEE robotic and automation conference,
vol. 1; 1994. p. 2816.
Tondu B, Lopez P. Modeling and control of Mckibben articial muscle robot
actuators. IEEE Control Syst Mag 2000;20(2):1538.
Tsagarakis N, Caldwell D. Improved modelling and assessment of pneumatic
muscle actuators. In: IEEE international conference on robotics and
automation, vol. 4; 2000. p. 36416.
Kothera CS, Jangid M, Sirohi J, Wereley NM. Experimental characterization and
static modeling of Mckibben actuators. J Mech Des 2009;131. 091010-1
091010-10.
Caldwell DG, Medrano-Cerda GA, Goodwin MJ. Control of pneumatic muscle
actuators. IEEE Control Syst Mag 1995;15(1):408.
Chou CP, Hannaford B. Measurement and modeling of Mckibben pneumatic
articial muscles. IEEE Trans Robot Autom 1996;12(1):90102.
Kang BS, Kothera CS, Woods BKS, Wereley NM. Dynamic modeling of
mckibben pneumatic articial muscles for antagonistic actuation. In:
Proceedings IEEE international conference on robotics and automation;
2009. p. 1827 [art. no. 5152280].
Ganguly S, Garg A, Pasricha A. Control of pneumatic articial muscle system
through experimental modelling. Mechatronics 2012;22(8):113547.
Tri VM, Kamers B, Ramon H. Modeling and control of a pneumatic articial
muscle manipulator joint Part I: Modeling of a pneumatic articial muscle
manipulator joint with accounting for creep effect. Mechatronics
2012;22(7):92333.
Wickramatunge KC, Leephakpreeda T. Study on mechanical behaviors of
pneumatic articial muscle. Int J Eng Sci 2010;48(2):18898.
Ahn KK, Anh HPH. System modeling and identication the two-link pneumatic
articial muscle (PAM) manipulator optimized with genetic algorithms. In:
SICEICASE international joint conference; 2006. p. 47449 [art. no. 4108518].
Ahn KK, Anh HPH. A new approach for modelling and identication of the
pneumatic articial muscle manipulator based on recurrent neural networks.
Proc Inst Mech Eng. Part I: J Syst Control Eng 2007;221(8):110121.
Ahn KK, Anh HPH. System modeling identication and control of the two-link
pneumatic articial muscle manipulator optimized with genetic algorithms.
In: IEEE international conference on control and automation; 2007. p. 5016
[art. no. 4376407].
Jamwal PK, Hussain S, Xie SQ. Dynamic modeling of pneumatic muscles using
modied fuzzy inference mechanism. In: IEEE international conference on
robotics and biomimetics; 2009. p. 14516 [art. no. 5420384].
Chandrapal M, Chen XQ, Wang WH, Hann C. Nonparametric control algorithms
for a pneumatic articial muscle. Expert Syst Appl 2012;39(10):863644.
Chandrapal M, Chen XQ, Wang WH, Stanke B, Pape NL. Investigating
improvements to neural network based EMG to joint torque estimation,
special issue on assistive and rehabilitation robotics. Paladyn J Behav Robot
2011;2(4):18592.
Li Y, Liu Y, Liu X. Active vibration control of a modular robot combining a backpropagation neural network with a genetic algorithm. J Vib Control
2005;11(1):317.
Moreira M, Fiesler E. Neural networks with adaptive learning rate and
momentum terms, IDIAP technical report; 1995. p. 130.
Chang X, Lilly JH. Fuzzy control for pneumatic muscle tracking via
evolutionary tuning. Intell Autom Soft Comput 2003;9:22744.
Anh HPH, Ahn KK. Identication of pneumatic articial muscle manipulators
by a MGA-based nonlinear NARX fuzzy model. Mechatronics
2009;19(1):10633.