Article

Practical Control of a Cold Milling Machine using

an Adaptive PID Controller
Fanwei Meng 1, Yongbiao Hu 1, Pengyu Ma 1,*, Xuping Zhang 2 and Zhixiong Li 3
1 National Engineering Laboratory for Highway Maintenance Equipment, Chang’an University,
Xi’an 710064, China; [email protected] (F.M.); [email protected] (Y.H.)
2 Department of Engineering & School of Engineering, Aarhus University, 8000 Aarhus C, Denmark;

[email protected]
3 School of Mechanical, Materials, Mechatronic and Biomedical Engineering, University of Wollongong,

Wollongong 2522, Australia; [email protected]

* Correspondence: [email protected]; Tel.: +029-82334493

Received: 16 February 2020; Accepted: 1 April 2020; Published: 6 April 2020

Featured Application: Coal Mining.

Abstract: This paper presents a supervised Hebb learning single neuron adaptive
proportional-integral-derivative (PID) controller for the power control of a cold milling machine.
The proposed controller aims to overcome the deficiency of the current power control algorithm,
and to achieve as high an output power as possible for the cold milling machine. The control
process and system model are established and presented to provide the insight and guidance to the
controller design and analysis. The adaptive PID controller is developed using a supervised Hebb
learning single neuron method with detailed algorithm and structure analysis. The field test is
performed to validate the proposed single neuron adaptive PID control for the power control. In
the test, the 8 cm-depth milling is conducted on a cement concrete pavement in which the cement is
not well-distributed. The test results show that when the machine speed is adjusted by the machine
itself or manually without the adaptive power control system, the machine is often overloaded or
underloaded, and the average work speed is 2.4m/min. However, when the adaptive control
system is implemented on the machine, it works very close to its rated work condition during its
work process. With the developed controller, the machine work speed is adjusted in time to the
load variation and uncertain dynamics. The average machine work speed can reach up to 2.766
m/min, which is 15.25% higher than the wok speed of the machine without an adaptive power
control system.

Keywords: cold milling machine; supervised Hebb learning; single neuron; adaptive power control

1.Introduction
A cold milling machine is an off-highway vehicle which is widely used for the controlled
surface removal of existing pavement to the desired depth in highway maintenance and
reconstruction [1]. The amount of removal material can also be controlled to meet project specific
requirements. The resulting textured pavement can be used immediately as a driving surface.
The structure and the working process of a cold milling machine are illustrated in Figures 1 and
2. The machine is equipped with a cutting drum to mill the pavement surface to the specified grade
and cross-slope. The cutting drum is equipped with picks, and is driven by the engine to whirl and
mill the pavement as the machine moves. Milling removes material in a range varying anywhere
from just enough thickness to level and smooth the surface to a full depth removal. Recycling of the

Appl. Sci. 2020, 10, 2516; doi:10.3390/app10072516 www.mdpi.com/journal/applsci

Appl. Sci. 2020, 10, 2516 2 of 19

road surface is one of the main reasons for milling a road surface. Milling is widely used for
pavement recycling today, where the pavement is removed and ground up to be used as the
aggregate in new pavement. Milling can also remove distresses from the surface, providing a better
driving experience and longer roadway life. The cold milling machine is also a great tool for
performing utility maintenance cuts, and ripping out roadways to repair foundations.

Figure 1. Structure of a cold milling machine.

Figure 2. Working process of cold milling machine.

Due to variations of the thickness and material property to be milled at different construction
sites, the load of the cold milling machine changes at random. This situation often causes the
machine to being overloaded or underloaded, which leads to a low productivity of the machine. The
reasons include: (1) When the machine is overloaded significantly, the engine speed is under large
fluctuation. The speed of the cut rotator is changed with the engine speed. If the engine speed is
down, the cut rotator cannot transmit all of the milled materials into the conveyor in time. However,
the milled materials should be collected and put into the conveyor immediately after they are milled.
As a result, lots of milled materials are piled up in the milling chamber and the power consumption
on mixing milled materials increases. This consumption should be prevented to improve
productivity. (2) When the engine speed fluctuates due to overloaded or underloaded conditions, its
dynamic performance and fuel efficiency will decrease, and the average output power of the engine
comes down. (3) When the machine is overloaded, the slip rate of the drive wheel will increase,
which leads to the decrease of the work speed and a short life of the wheel.
Appl. Sci. 2020, 10, 2516 3 of 19

It is very difficult to make full use of the engine power and to make the cold milling machine
work in ideal conditions only by the operator’s experience and manual operation. The reason is that
the load of a cold milling machine is dynamic and uncertain during its work process. Furthermore,
the dynamics of the cold milling machine are nonlinear and uncertain, and therefore it is desirable to
develop a proper power control system that is capable of automatically adjusting the machine so
that it works at its rated power or in a highly efficient state. Guo and Duan [2] and Gu et al. [3]
designed novel cutters of the cold milling machines to reduce the power consumption. Wang et al. [4]
and Long [5] studied the theoretical methods of the power control for a cold milling machine, but
specific power control algorithms were not proposed for the machine power control. Chen et al. [6]
and Yuan [7] mainly conducted the hardware design of the power control system for a cold milling
machine. Ma et al. [8,9] investigated the vehicle dynamics to realize the power control of a cold
milling machine, but only numerical simulations were used to validate the
proportional-integral-derivative (PID) controller and the PID parameters were fixed. A traditional
PID controller with the fixed-control gains cannot achieve the optimal control performance and is
not adaptive to environment variations for the cold milling machine power control featured with a
nonlinear and uncertain system [10,11]. There are several alternative control methods, such as neural
network control [12–15], fuzzy control [16–18], robust control [19–22], and adaptive control [17–20].
The neural network control has strong self-study ability to control a nonlinear system, but it needs
lots of computation. It is not feasible as the cold milling machine is equipped with a 16 bit single chip
microcomputer, which has a very limited computation capability. The performance of fuzzy
controllers depends on the fuzzy rules which are difficult, if not possible, to be identified completely
from our work experience at present. Therefore the fuzzy control is not selected to be an appropriate
alternative for cold mining machines. Most of the robust control needs a reference model or sensitive
coefficients [19–22]. However, it is not possible for us to establish a reliable reference model and
determine sensitivity coefficients that are needed in the controller design of the cold milling
machine. Obviously, the robust control is not the option in the power control of a cold milling
machine. Two typical adaptive control methods are STC (self-tuning control) and MRAC (model
reference adaptive control). The MRAC needs a reference model which is not available for cold
mining machines [23,24]. The STC needs online identification and synthetic decision [25,26]. There
are little such synthetic decision algorithms and strategies for a cold milling machine at present.
Therefore, the typical adaptive control is ruled out in this work.
The single neuron control is a proper option as it possesses the strong ability of self-studying
and self-adapting. The single neuron is used to adjust the control gains of the PID controller online,
and hence it can overcome the shortage of the fixed control gains in traditional PID controllers. This
single neuron PID not only has the characteristics of the neural network control but also has the
characteristics of the PID control. Therefore, the single neuron PID can be implemented more easily
in engineering application than the neural network control, the fuzzy control, the robust control and
adaptive control. Furthermore, the strong ability of self-studying and self-adapting of the single
neuron PID control can improve the performance and robustness of the adaptive power control.
In order to address the practical control challenge for cold mining machines, this paper
proposes a supervised Hebb learning single neuron PID method. The contributions of this work
include: (1) this work attempts to develop and implement the proposed controller on a real machine
with field testing; (2) in this work the control gain is tuned by a supervised Hebb learning algorithm,
so the proposed controller can adapt to the environment variations; (3) the supervised Hebb
learning based PID controller does not need any Sign functions to adjust the PID gains; therefore,
the control performance is much more steady and accurate than that of the Sign function-based PID
controllers. Field testing result demonstrates the performance of the proposed method.
This paper is organized as follows. In Section 2 the control process and the system model of a
cold milling machine are established to provide the guidance to control design and analysis. Section
3 presents the integration of the single neuron adaptive power PID controller to the power control
for a cold milling machine. The control algorithm implementation is detailed in Section 4. Section 5 is
Appl. Sci. 2020, 10, 2516 4 of 19

dedicated to the analysis and discussion of the field test results. The conclusions are given in the last
section.

2. Control Model

2.1. Control System Overview

The power control process is illustrated in Figure 3. As shown in Figure 3, the engine has two
inputs: one from ECU (electronic control unit) and the other one from the load. The input from ECU
is fixed and should not be changed during the machine work process to meet the variable heavy
loads. This work focuses on how to control the duty cycle of the PWM so that the load of the
machine acting on the engine regulates the engine speed to be as constant as possible and achieve
the output power to be as high as possible.

M e (e , h) Md
e d id

e e ML
vT im
r Qb 1 2 vT
ML

Figure 3. The diagram of the power control process.

The displacement of the variable displacement hydraulic pump controls the flux Qb of the

variable pump. The flux Qb determines the hydraulic motor rotary speed 1 . The drive wheel is
connected with the motor through gearbox I whose ratio is fixed, i.e., the drive wheel rotary speed
2 is proportional to 1 and the wheel theoretical moving speed vT . As detailed in Equation
(15) and (20), the variation of vT leads to the load change of the cold milling machine. It is clear
that the power consumption of the cold milling machine is adjusted through this control process
when the load of the machine is changed. On the other hand, the cutting drum is connected with
the engine through gear box II whose ratio is about 10. In Figure 3, id is the transmission ratio

from the engine to the milling drum, im denotes the transmission ratio from the engine to the
hydraulic motor, and h refers to the position of the throttle. This process can be described using
the following system model.

2.2. System Model

2.2.1. Engine Model

According to [26], the dynamic model of the engine can be given as

J  e  M e ( e , h )  M Ic ( t ) (1)

where J is the moment of inertia of the engine, Me is the input torque to the engine, and MIc is the
resisting moment torque acted on the bent axle of the engine. Me (e , h) is related with the engine
speed e and a nonlinear throttle function h. Therefore, the diesel engine is a nonlinear system.
Taking Taylor expansion and Laplace transform, linearization through the Taylor series
concerns the development at a fixed working point. Therefore, after linearization, an increment of a
variable should be used instead of a variable. The model of the system linearizes around the rated
working parameter. When variables are fluctuated slightly around in the local region of working
Appl. Sci. 2020, 10, 2516 5 of 19

points, the result of numerical calculation is more accurate, which is proved in reference [26].
Equation (1) is rewritten as:
( M e' ( e 0 , h )  Js ) e ( s )  M Ic ( s ) (2)

2.2.2. Model of Drive System

The flux function of the variable hydraulic displacement pump can be described as,
Qb  K b ie e b  C ib ( P  Pr )  C eb P (3)

where Qb is the flux of the hydraulic pump, Kb is the displacement gradient of the hydraulic pump,

ie is the transmission ratio of the gearbox between the engine and the pump, Cib is the internal
leakage coefficient of the pump, P is the work pressure of the pump, Pr is the backpressure of the
hydraulic system, Ceb is the external leakage coefficient of the pump, and b is the angle of the

sliding shoes in the pump. Here, b is proportional to the control voltage u of the hydraulic
pump [27]:
b  k u (4)

where k is a constant.
Substituting Equation (4) into Equation (3), and taking the result linearization and Laplace
transform, it yields
Q b ( s )  K b ie k   e 0 u ( s )  K b ie k  u 0  e ( s )  C b P ( s ) (5)

where Cb =Cib +Ceb is the total leakage coefficient of the hydraulic pump, e 0 and u0 are the
initial values. Pr is the back pressure of the hydraulic system which is a constant in Equation (3),

when we take Laplace transform of Equation (3), Pr is zero.

The flux continuity function of the motor is given by [27]:
 V0 
Qb  Cim ( P  Pr )  Cem P  Dm  m  P (6)
e
Taking Laplace transform, Equation (6) is rewritten as
V0
Qb (s)  Cm P(s)  Dm sm (s)  sP(s) (7)
e
where Cim is the internal leakage coefficient of the hydraulic motor; Cem is the external leakage

coefficient of the motor, Dm is the displacement of the hydraulic motor, m is the rotation angle

of the motor axle, V0 is the total volume of the high pressure chamber of the pump, motor and

hydraulic pipe, e is the modulus elastic of the hydraulic oil volume, and Cm is the total leakage
coefficient of the hydraulic motor.
The torque balance function of the hydraulic motor can be derived as
 
Dm ( P  Pr )  J m  m  Bm  m  M L (8)

where ML is the load of the hydraulic motor.

The transform function of Equation (9) is given as

Dm P(s)  (Jms2  Bms)m (s)  ML (s) (9)

Appl. Sci. 2020, 10, 2516 6 of 19

The relationship between the work speed and the angular velocity of the hydraulic motor can
be expressed as
2 Rg s m ( s )
vT ( s )  (10)
ig
where ig is the transmission ratio from the hydraulic motor to the drive wheel.
Combining Equations (5) (7) (9) and (10), the model of the pump control motor system can be
established as
K vT v T ( s )  K T L M L ( s )  K b i e k   e 0 u ( s )  K b i e k  u 0  e ( s ) (11)

where

(1  0 s) , Ct  Cb  Cm ,
Ct V
KTL 
Dm Ct  e
D JV B V CJ C
KvT  m [ m2 0 s2  ( m2 0  t 2m  Jm )s  Bm (1 t2 )]
2 Rg Dm e Dm e Dm Dm

The torque balance function of the milling drum is expressed as


J d  d  C d  d  M d  M de (12)

where Mde is the part of engine output torque transmitted from Gearbox II in Figure 3, Jd the

moment of inertia of the milling rotor, Cd the rotational damp of the milling rotor d the rotary

speed of the cutting drum, Md the resistance torque of the milling rotor, and Mde the input
torque of the milling rotor.

In a cold milling machine J d  d  C d  d  M d , Equation (12) can be described as

Md  Mde (13)

The milling force of the milling equipment is given by

bkd B s aeap fZ (vT2  vT Rdd )
Fr  (14)
Zd aRd2d2
 
0  cos  0 sin  
where is the realistic milling angle of the cutting pick, b    ,
 sin     0     0 
     cos    
 4 2 2 4 2 2 
 is the friction angle of the pick front surface, Z is the cutting pick number on the cutting drum,
fz is the milling feed rate of each cutting pick on the cutting drum,  d is the milling drum rotary

  0  
speed, ap is the milling depth, ae is the milling thickness, a  cos    , s is the
4 2 2
splitting failure strength of the material to be milled which changes at random at a not
well-distributed pavement, B is the milling width, R d is the radius of the cutting drum, and kd
is a constant.
The milling torque Md can be calculated by
bkd B s ae ap f Z (vT2  vT Rd d )
Md  (15)
Z d aRd d2
Taking linearization and Laplace transform, Equation (15) is simplified as
Appl. Sci. 2020, 10, 2516 7 of 19

Md (s)  kdd (s)  kss (s)  kvT vT (s) (16)

where

bkd Bae ap f Z (vT20  vT 0 Rd d 0 )

ks  ,
Zd aRd d20
bkd B s0ae ap fZ vT 0 2bkd B s0ae ap f Z (vT20  vT 0 Rdd 0 )
kd   ,
Zd ad20 Zd aRdd30
bkd Bae ap f Z (2vT 0  Rd d 0 )
kvT 
Z d aRd d20

When the cold milling machine is running, it is driven by the driving wheel. The dynamics of
the tractive system can be described as

mvT  kvT  Ff  FH  FK (17)

where m is the mass of the machine, k the speed damp coefficient, FH the level component force

of the milling equipment, Ff the wheel rolling resistance which is a constant, and FK the tangent
tractive force.
When the machine is working along a straight road slowly, the speed resistance can be ignored.
Therefore, Equation (17) can be expressed as

mvT  FH  FK  Ff (18)

iM L
where FK  ,R is the dynamics radius of the driving wheel, and i the transmission ratio
R0 0
from the motor to the driving wheel.
Taking Laplace transform, Equation (18) is given as
iM L (s)
msvT (s)  FH (s)  (19)
R0
The working resistance FH is given by [8]:

Md
FH   kh Bae2vT (20)
kmd Rd
Based on Equations (15), (19) and (20), we can get the transform function of the ground drive
system of the machine:
msvT ( s )  k dr vT ( s )  ki 0 M L (s)  ki1 d ( s )  ki 2 s ( s ) (21)

where

i kd k s ( k vT  k md Rd k h Bae2 )
ki 0  , ki1  , ki 2  , k dr 
R0 kmd Rd kmd Rd k md Rd

The engine resisting moment torque can be expressed using the load of the hydraulic motor and
the milling torque as:
Appl. Sci. 2020, 10, 2516 8 of 19

M d (s) M L ( s )
M Ic ( s )   (22)
id im
Based on Equations (2), (11), (16), (21) and (22), we can get the transform function of the main
power consumption of the machine as
Jse ( s )  Ke ( s )e ( s )  K up ( s )u ( s )  K s ( s ) s ( s )  K P ( s ) P ( s ) (23)

where

2 kvT Rg ig V
KP (s)   (Ct  0 s) ,
id Dm e
[ K b ie k u0 ( ms  kdr )  K v ki1 ] 2 kv Rg ig K bie k u0 k d
K ( s )  T
 T
 2  M e' (e 0 , h) ,
e
im id [ KT (ms  k dr )  KT ki 0 ]
L L
id Dm id
K vT k i 2 k s ,
K s ( s )  
im [ K TL ( ms  k dr )  K TL k i 0 ] id
K b ie k  e 0 ( ms  k dr ) 2 k vT Rg ig K b ie k  e 0
K up ( s )   
im [ K TL ( ms  k dr )  K TL k i 0 ] id Dm

The engineering application shows that the fluctuation value of the hydraulic pressure P is
very small during the work process of the cold milling machine, and hence P can be treated as a
constant. As a result, Equation (24) can be described as
Jse (s)  Ke (s)e (s)  Kup (s)u(s)  Ks (s)s (s) (24)
To describe this system model much more simply and clearly, the model of the main power
consumption parts has been linearized. It is clear that the cold milling machine is a nonlinear system
that can be demonstrated by nonlinear terms, the engine model in Equation (1), the pump model in
Equation (3), and the work equipment in Equation (20). As is shown in Equation (24) that the cold
milling machine is a time varying system and there is a random disturbance s during the machine
work process. Equation (24) shows that the engine speed e will change if the splitting failure
strength s is changed. To control the engine speed, the controller output voltage u needs to be
regulated to control the work speed in time so that the engine speed can be kept as constant as
possible.
Obviously, the raditional PID controller cannot make the system achieve desirable performance
as the system is nonlinear, uncertain, and time-varying.
Therefore, a single neuron adaptive power control algorithm is chosen to design the power
control system of the milling machine.

3. The Proposed Adaptive PID Controller

The structure of the single neuron adaptive power control system of a cold milling machine is
similar to the fuzzy adaptive control system. In the single neuron adaptive power control system, the
fuzzy adaptive control unit is replaced by the single neuron adaptive control unit. The weights of the
PID controller are cumulated by the single neuron control algorithmic online continuously, which is
different to the fuzzy control [28,29]. To implement the digital control, the system must be
discretized.
The driver of a cold milling machine often places the throttle of the engine at its maximum
position to meet the variation of the heavy load when the machine is working. The load of the
machine can be adjusted by its work speed as the analysis in Section 2, if the throttle is fixed. The
machine work speed can be adjusted by the displacement of the variable pump. The adjustment of
the displacement is done through the single neuron adaptive power control system. Therefore, the
output power of the engine is controlled by the control system. Based on the control mechanism of a
traditional PID, the structure of the single neuron adaptive power PID controller designed for the
Appl. Sci. 2020, 10, 2516 9 of 19

cold milling machine is shown in Figure 4. The controller is used to improve the control responding
speed and robustness performance to increase the productivity of the cold milling machine. In
Figure 4, e (k ) is the engine speed, r (k ) denotes the engine reference speed, A is the converter,
u refers to the output of the control system, the output is to control the displacement of a pump, x1 ,
x2 , x3 are the inputs of the PID controller, K u is the control gain which can be tuned with the
control error, and i (k ) (I = 1, 2, 3) are the weights which are tuned by the single neuron adaptive
adjustment.

x1
e ( k ) w1 (k )

r ( k ) u (k )
x2
w2 ( k )  K u ( k ) u

x3
w3 (k ) Z 1


Figure 4. Structure of the adaptive power control of a cold milling machine.

According to the above structure, e (k ) and  r (k ) are the reference input (desired speed)
and actual output (measured engine speed) of the system, respectively, and the error satisfies
e(k )   r (k )  e (k ) . It is assumed that e (k ) is measurable. In the view of the single neuron
adaptive-PID controller, the input is e(k ) and the output is the incremental duty cycle of PWM
u(k ) driving the pump motor. Similar to a normal PID controller[30], the variables, x1 , x2 , x3
satisfy the following relations respectively:
x1 (k )   r (k )  e (k )  e(k ) 

x2 (k )  e(k )  e(k  1)  (25)
x3 (k )  e(k )  2e(k  1)  e(k  2) 
where e(k) is the deviated value.
In the algorithm of the single neuron PID control, the critical issue is to choose the learning rate.
If Ku in Equation (26) is a constant, we must set the learning rate i for PID respectively and
carefully, which is very tedious in the engineering application. To simplify the control parameter
setting in the engineering application, the online correction of nonlinear transformation about
parameter Ku is used in this control system and can be given by,
[r ( k )   ( k )]3
Ku (k )  K u 0  (26)
 2r (k )
where Ku0 is a constant,   0.1Ku 0 in this control system. Ku has a great impact on the system
stability and rapidity. When the value of Ku is small, the control system is comparatively of slow
response and the overshoot of system could decrease. When the value of Ku is large, the control
system is of fast response, but the overshoot of the system increases with the long adjustment time.
At the beginning of dynamic response, deviation e(k) is large, the value of Ku should be large in order
to accelerate response. The deviation e(k) approaches to zero in steady state, the value of Ku should
be decreases gradually until it reaches the steady value to ensure that the system is stable and small
Appl. Sci. 2020, 10, 2516 10 of 19

overshoot. Weights wi(k) changes adaptively with the value of deviation e(k), and ultimately the
process value will track the set value. Therefore it is necessary to select the online correction of
nonlinear transformation in the Equation (26). From Equation (26), one can see that Ku is changed
with the error of the engine speed. If the error is small, Ku = Ku0. If the error is large, Ku increases to be
very large which leads to increasing the convergence speed of the control system. The advantage of
this method is that we only need to select a proper Ku0, and there is no need to set the learning rate
repeatedly. The online correction of Ku is conduced to reduce the influence of the learning rate in this
method.
In the single neuron PID control [31,32], the control law can be expressed by
3
wi ( k ) xi ( k )
u ( k )  K u  3
(27)
i 1
 w (k )
i 1
i

The single neuron adaptive PID controller implements the function of the adaptive- and
self-learning by adjusting weight coefficients, which can form different control algorithms using
different learning rules. Unsupervised learning functions as self-organized learning, i.e., the
network learning is a completely self-learning process. The fundamental principle of Hebb learning
is that if two neurons are activated at the same time, then the increase of their connect intensity is
directly proportional to the product of their stimulation. Introducing a teacher signal into the Hebb
learning algorithm leads to changing the output to the difference between ideal output and actual
output. Basically, the supervised Hebb learning algorithm combines the unsupervised Hebb
learning algorithm with the supervised Delta learning algorithm in [33]. In this work, the
supervised Hebb learning algorithm is used to design the control law.
In the supervised Hebb learning algorithm, the weight value adjustment function is expressed
as [34,35]
wi (k  1)  wi (k )  i pi (k ) (28)

pi (k )  Ku (k ) z(k )u(k ) xi (k ) (29)

where pi (k ) is the recursive signal and hushes gradually during the process, i ( i  P, I , D ) is
the learning rate, and z(k)  e(k) is output error.
Substituting Equation (29) into Equation (28) one can get the weight increment wi (k ) ,

wi (k )  wi (k  1)  wi (k )  i Ku (k )e(k )u (k ) xi (k ) (30)

To ensure the astringency and robustness of Equation (30) and u(k) in the learning algorithm
of single neuron adaptive PID controller, learning algorithms should be disposed canonically as
3

wi (k ) xi (k )
u (k )  u (k  1)  Ku  3 
i 1 
i 1
wi (k )

(31)
w1 (k  1)  w1 (k )   I Ku e(k )u (k ) x1 (k ) 
w2 (k  1)  w2 (k )   P Ku e(k )u (k ) x2 (k ) 

w3 (k  1)  w3 (k )   D Ku e(k )u (k ) x3 (k ) 
The weights of the neuron are trained using the simulation method until getting satisfied
regulating results. Then the neuron adjuster operating mode is set by manual to non-automatic
correction weights mode. According to simulation results of the system and practical trials, the
system is convergent. For a cold milling machine, which is a very complicated system, the
parameters calculated with the training data significantly deviate from the actual condition. The
initial parameters in the system are determined through the trial and error method in the field tests.
Appl. Sci. 2020, 10, 2516 11 of 19

4. Simulation Redults

4.1. Parameters’ Confirmation in the Model of the Cold Milling Machine

Based on the design parameter of actual cold milling machine and references [8,36–38], the
parameters confirmation in the model is in Table 1.

Table 1. Parameters confirmation in the model.

Variable Value Variable Value

ie 1 h 100%
J(kg·m2) 0.459 Rg (m) 0.34
Dm(m3/rad) 4.16 × 10−5 Jd(kg·m2) 0.536
βe(MPa) 1.25 × 10 3 V0(m) 1.27 × 10−5
τs (MPa) 2.55 Cm(m−5·(N·s)−1) 1.4 × 10−12
n max (rev·min−1) 2200 Zd 112
nH (rev·min−1) 2000 nM max (rev·min−1) 1400
P H (kW) 196 M max (Nm) 1140
R0 (m) 0.34 M H (Nm) 937
B (m) 1.3 F f (N) 2800
Rd (m) 0.46 k 0.607
KP (m3·rad−1) 1.59 × 10−4 kd 0.9
β(rad) 0.174 kmd 2
ae(m) 0.08 γ0(rad) 0.209
ap(m) 0.08 im 230
id 12.5 ηP 2.6
m(kg) 20,000 ηD 0.05
ηI 1.25 w1 0.3
Ku0 0.065 w3 0.01
w2 0.13

Where nmax is the engine maximum speed, nM max is the engine speed when the torque is the
most maximum, M max is the maximum torque, nH is the rated speed, M H is the rated torque.

4.2. Simulation Results

It takes 60 s to finish the simulation. The simulations results in Figures 5 to 8 show the machine
with or without the power control system equipped. The load variation is simulated by an
interference load which is shown in Figure 5. In order to observe the laws which are changed with
the machine working load expediently, the sine wave with amplitude changing at random is
selected as the interferential load. The engine reference speed of the control system is 1980 rev/min.
The single neuron PID, the traditional PID and the manual operation are simulated with the model
to help us selected a suitable control algorithm.
Appl. Sci. 2020, 10, 2516 12 of 19

Figure 5. The interferential load curve.

Figure 6. The engine speed curves.

Figure 7. The engine output power curves.

Figure 8. The machine work speed curves.

Appl. Sci. 2020, 10, 2516 13 of 19

Figures 6 and 8 show that when a single neuron PID power controller is equipped on the
machine, the average work speed is 3.43 m/min and the engine rotary variation is 68 rev/min
during its normal work process. Figure 7 shows that the engine output power amplitude variation
is 9 kW and the average output power is 194.4 kW as well as the usage ratio of engine rated power
is 99.2%, it works very close to its rated work condition during its work process. When the PID
controller is equipped on the machine, the average work speed is 3.31 m/min and the engine rotary
variation is 157 rev/min during its normal work process. Figure 7 also shows that the engine output
power amplitude variation is 36 kW and the average output power is only 190.42 kW, as well as the
usage ratio of engine rated power is 97.2%. When the machine is operated manually, the average
work speed is 3.07m/min and the engine rotary variation is 413 rev/min during its normal work
process. Figure 7 also shows that the engine output power amplitude variation is 36 kW, the
average output power is only 181.67 kW and the usage ratio of the engine rated power is 92.69%.
The machine is often overloaded or underloaded. The work speed of the machine with a single
neuron PID controller is 11.7% higher than which the machine without a controller; the work speed
of the machine with a PID controller is 7.87% higher than that the machine operated manually.
When the engine rotary variation is smaller the engine work economy is better.
Therefore, the single neuron PID is selected as the control algorithm of this work, and this
control algorithm has been used on a cold milling machine to do some field research.

5. Field Test

5.1. Field Test Setup

To validate the control effect of the supervised Hebb learning PID control algorithm presented
in this work on the productivity of the cold milling machine, a field tested was conducted. The
parameters of the tested cold milling machine are given as below. The mass of the machine is 20 tons.
The milling depth of the cement concrete pavement is about 8 cm. The concrete strength is not
well-distributed in the pavement. The engine throttle is at its maximum position, and the milling
width of the machine is 1.3 m, the engine rated speed is 2000 rpm. To make full use of the engine
power, the engine reference speed is 1,950 rpm, and the permissible error is 50 rpm. According to
the field tests, the initial value of some control parameters are set respectively as  P = 2.6,  I =
1.5, D = 0.7, Ku 0 = 0.65. The sensors and data acquisition instrument are shown in Figure 9.
Figure 10 is the picture of the machine working in the test field. Figure 11 shows the pavement
milled by the cold milling machine.

(a) (b)
Appl. Sci. 2020, 10, 2516 14 of 19

(c) (d)

Figure 9. The sensors and data acquisition instrument: (a) the work speed sensor; (b) the drive
hydraulic pump pressure sensor; (c) the engine speed sensor; (d) the data acquisition instrument.

Figure 10. The field test of the cold milling machine.

Figure 11. The milled cement pavement.

The sensor used to test the work speed is an 11 bit rotary encoder with the resolution of 2048
pulses per revolution. The rotary encoder is provided by OMRON and the model of this encoder is
E6C3-CWZ3EH 2048 P/R 1M. The sensor used to test the hydraulic pressure of the drive system is a
pressure transducer, SENSOTEC Model Z serials. The measurement range of this pressure sensor is
0 to 15,000 psig. The engine speed sensor is a hall sensor which sends sinusoidal wave signals when
the engine is running. The engine speed sensor is built-in the engine. The data acquisition
instrument is DEWE-2010, and the sampling rate of the testing is set as 1000 Hz in this work.

5.2. Field Test Results

Appl. Sci. 2020, 10, 2516 15 of 19

The filed test is made up of two parts. In the first part, we operate the machine manually. When
the machine works in the middle of the pavement, we choose the ‘AUTO’ mode of the machine, and
then, the control system begins to work. The milling rotor of the machine gradually cuts into 8 cm
depth of the pavement within the first 40 s of Figures 12a, 13a and 14a; the milling rotor entails
enough power to meet the needs of consumers during this process, which make the engine speed
decreases in Figure 12a. The hydraulic driving system is in a closed state at this point; the pressure of
the hydraulic driving system in Figure 14a is the system back pressure. As the milling rotor of the
machine gradually cuts into the depth of setting, the machine is slow-moving under the action of the
level component of forces, so the work speed of the milling machine in Figure 13a is not zero.
Fluctuations are mainly caused by the driver operation in Figures 12a, 13a and 14a. If the operator
drives too fast the load increases sharply because of hard and rough usage over pavement. The
driver needs to stop and loses time in a stationary position while powering up or reworking.
Fluctuations are caused by local downhill pavement and the uneven distribution of pavement
material within 161 s to 200 s in Figures 12a, 13a and 14a. When the machine works on the downhill
pavement, the work speed of the milling machine will increase under the gravity along the ramp as
the tractive force. Then, the forces of milling rotor increase with the depth of cut and feed rate, the
milling rotor entails enough power to meet the needs of consumers during this process, which
makes the engine speed decrease as in Figure 12a. The pressure of the hydraulic driving system in
Figure 13a did not change significantly during this process, because the level component of forces
and the gravity along the ramp as the tractive force was counteracting. The testing results are given
in Figures 12–14.

(a) (b)

Figure 12. Engine speeds of (a) proportional-integral-derivative (PID) controller and (b) the
proposed adaptive power controller.

(a) (b)
Appl. Sci. 2020, 10, 2516 16 of 19

Figure 13. Work speed of the milling machine: (a) PID controller and (b) with the proposed
controller.

(a) (b)

Figure 14. The drive system hydraulic pressure: (a) PID controller and (b) the proposed controller.

In Figure 12a, the engine is overloaded and the maximum fluctuation of the engine speed is 419
rpm when the machine is not equipped with the controller. The maximum engine speed is 2103 rpm;
the machine is underloaded in this condition. When the machine is operated manually, the machine
is often overloaded or underloaded. If the engine works on this condition, the output power is not at
its desirable value. During this work process, the load of the machine with the fixed transmission
ratio of the ground drive system is adjusted by the engine. If the machine load increases, the engine
speed will go down. The work speed changes with the engine speed, i.e., the decline of the engine
speed leads to the decline of the work speed. As a result the work load descends. When the work
speed is at the certain value, the work load and the engine torque is in balance. This adjustment is a
passive adaptation to the machine load for the system without the proposed controller.
As shown in Figure 12b, the fluctuation of the engine speed is 129 rpm, the engine average
speed is 1954 rev/min and both values are near to the setting values and the engine is not seriously
overloaded. When the engine speed deviates from the reference value for its overload or under load,
the adaptive controller begins to adjust the displacement of the variable hydraulic pump to reduce
or increase the machine work speed, i.e., when the machine is under load the controller will increase
the work speed, and if the machine is under load the controller will reduce the work speed. This
adjustment of the controller makes the work load descend or ascend and makes the engine work
almost at its rated speed. Although the work speed in Figure 12b presents some fluctuation when the
machine meets the great impulse load, the engine speed is almost at 1950 rpm mostly during the
machine work process and the engine output power has increased near to its rated value. This
adjustment is active adaptation to the machine load in this case.
Figure 13a shows that the average work-speed is 2.4 m/min when the machine is working
without an adaptive controller and the work speed is adjusted manually or by the engine. Figure 13b
shows that once the load of the machine changes, the controller will adjust the work speed. The
average work speed is 2.766 m/min, which is 15.25% higher than that the machine without an
adaptive controller. That is to say, the productivity of the machine increases 15.25%. The machine is
not overloaded seriously and the engine speed is near to its rated value during its work process. The
milled materials in the milling chamber are conveyed in time and the power consumption on mixing
milled materials decreases. If the power consumption on mixing milled materials decreases and the
average output power of the engine goes up, there will be more power, which can be used for the
work of the machine. At the same time, the machine often works near to its rated conditions, and the
dynamic performance and fuel economy of the engine is better than that with overloaded or
underloaded conditions. When the machine works close to its rated conditions, the slip rate of the
Appl. Sci. 2020, 10, 2516 17 of 19

drive wheel is less than that in serious overloaded conditions, and the work speed will increase.
When the machine is under loaded, the engine speed will go up, and then, the controller will
increase the work speed to make the machine work near its rated condition. All these factors lead to
a higher productivity of the machine with the developed controller in this work.
The tractive force of the milling force is reflected by the hydraulic pressure as shown in Figure
14. Analyzing Figure 13 and Figure 14, it is clear that the change trend of the hydraulic pressure is
the same as the work speed. This is can be explained by Equation (9) which shows that the hydraulic
pressure of the drive system increases with the speed of the hydraulic motor if the load is a constant.

6. Conclusions
In this work, a supervised Hebb learning single neuron adaptive PID controller has been
developed and implemented for the power control of a cold milling machine. The power control
process and the system model of a cold milling machine have been established to provide insight
and guidance to the analysis, design and control of the power control system. The control algorithm
and method has been validated by a field test. We can conclude that:
The cold machine with the adaptive power controller almost worked at its rated load. The
minimum engine speed has achieved up to 1891 rev/min from 1684 rev/min. When the throttle is
fixed at its maximum position, if the machine is overloaded, the minimum engine speed can reflect
the overloaded level of the cold milling machine. The productivity of the cold milling machine with
the control system increased by 15.25% compared to the machine without the control system.
This supervised Hebb learning single neuron adaptive PID control meets the need of the
adaptive power control of the cold milling machine. The control system which uses this algorithm
can increase the engine output power and productivity of a cold milling machine in practice.
Author Contributions: Conceptualization, P.M. and Z.L.; methodology, F.M. and Y.H.; software, P.M. and
X.Z.; validation, F.M., Y.H. and P.M.; formal analysis, F.M.; investigation, Y.H.; resources, P.M. and X.Z.; data
curation, F.M. and Z.L.; writing—original draft preparation, F.M. and Y.H.; writing—review and editing, Z.L.
and X.Z.; supervision, P.M.; funding acquisition, P.M. and Z.L. All authors have read and agreed to the
published version of the manuscript.

Funding: This research was funded by Special Fund for Basic Scientific Research of Central Colleges under
Grant No. 300102259504 and Grant No. 310825150017, and Australia ARC DECRA (No. DE190100931).

Acknowledgments: Authors would like to thank the reviewers for their valuable comments and constructive
suggestions.

Conflicts of Interest: The authors declare no conflict of interest.

References
1. Wang, Q. The Study on Milling Drum System of Road Cold Miller. M.S. Thesis, Dept. Mech. Eng., Xi’an
University of Technology, Xi’an, China, 2006.
2. Guo, Y.; Duan, M. Computer Simulation of Load Fluctuation of Milling Cylinder of Pavement Planer. J.
Hunan Univ. Sci. Technol. Nat. Sci. Ed. 2007, 24, 17–20.
3. Gu, H.; Jiao, S.; Xiao, A.C. Analysis and Test on Asphalt Milling Machine Cutting Load Characteristic.
China J. Highw. Transp. 2012, 25, 154–158.
4. Wang, A.; Li, Z.; Yao, H. Discussion of automatic power apportioning of milling machine. Road Mach.
Constr. Mech. 2005, 22, 34–36.
5. Long, J. Study on Working Principle and Power Allocation of Tracked Milling Machine. Road Mach. Constr.
Mech. 2010, 27, 73–75.
6. Chen, Y.; Zou, X.; Yang, Y. Design of Digital Control System of Hydraulic Milling Machine. Mech. Eng.
Autom. 2012, 19, 123–125.
7. Yuan, F. Design of Traveling Control System for Milling Machine Based on DSP. Road Mach. Constr. Mech.
2010, 27, 79–81.
8. Ma, P.; Hu, Y.; Zhang, X. Research on adaptive power control parameter of a cold milling machine. Simul.
Model. Pract. Theory 2008, 16, 1136–1144.
Appl. Sci. 2020, 10, 2516 18 of 19

9. Ma, P.; Hu, Y.; Zhang, Z. The dynamical model of a cold milling machine and its adaptive power control
simulation. Simulation 2011, 87, 809–817.
10. Atherton, D.P. PID controller tuning. Comput. Control. Eng. J. 1999, 10, 44–50.
11. Nasr, M.B.; Chtourou, M. Neural network control of nonlinear dynamic systems using hybrid algorithm.
Appl. Soft Comput. 2014, 24, 423–431.
12. Kumara, N.; Panwarb, V.; Sukavanam, N.; Sharma, S.P.; Borm, J.H. Neural network-based nonlinear
tracking control of kinematic ally redundant robot manipulators. Math. Comput. Model. 2011, 53, 1889–
1901.
13. Ge, S.S.; Hong, F.; Lee, T.H. Adaptive neural network control of nonlinear systems with unknown time
delays. IEEE Trans. Autom. Control. 2003, 48, 2004–2010.
14. Yang, Q.; Yang, Z.; Sun, Y. Universal Neural Network Control of MIMO Uncertain Nonlinear Systems.
IEEE Trans. Neural Networks Learn. Syst. 2012, 23, 1163–1169.
15. Baloochy, B. A Robust Approach in Nonlinear Fuzzy Control of Chemical Process. Chem. Eng. Res. Bull.
2013, 16, 45–60.
16. Sofianos, N.A.; Boutalis, Y.S. Robust adaptive multiple models based fuzzy control of nonlinear systems.
Neurocomputing 2016, 173, 1733–1742.
17. Harb, A.M.; Smadi, I.A. Tracking control of DC motors via mimo nonlinear fuzzy control. Chaos Solitons
Fractals 2009, 42, 702–710.
18. He, Z.; Ji, X. Nonlinear robust control of integrated vehicle dynamics. Veh. Syst. Dyn. 2012, 50, 247–280.
19. Tian, B.; Fan, W.; Zong, Q.; Wang, J.; Wang, F. Nonlinear robust control for reusable launch vehicles in
reentry phase based on time-varying high order sliding mode. J. Frankl. Inst. 2013, 350, 1787–1807.
20. Raffo, G.V.; Ortega, M.G.; Rubio, F.R. Robust Nonlinear Control for Path Tracking of a Quad-Rotor
Helicopter. Asian J. Control. 2015, 17, 142–156.
21. Isidori, A.; Marconi, L.; Serrani, A. Robust nonlinear motion control of a helicopter. IEEE Trans. Autom.
Control. 2003, 48, 413–426.
22. Abdeddaim, S.; Betka, A.; Drid, S.; Becherif, M. Implementation of MRAC controller of a DFIG based
variable speed grid connected wind turbine. Energy Convers. Manag. 2014, 79, 281–288.
23. Mirkin, B.; Gutman, P.-O.; Shtessel, Y. Coordinated decentralized sliding mode MRAC with control cost
optimization for a class of nonlinear systems. J. Frankl. Inst. 2012, 349, 1364–1379.
24. Zilletti, M.; Elliott, S.J.; Gardonio, P.; Rustighi, E. Experimental implementation of a self-tuning control
system for decentralized velocity feedback. J. Sound Vib. 2012, 331, 1–14.
25. Wang, R.; Chen, L.; Wang, D. Self-tuning Control on Integrated System of EPS and SAS Based on Pole
Placement. Procedia Eng. 2011, 16, 271–277.
26. Yao, H. The Hydraulic Dynamics and Control Mechanism of Construction Vehicles; China Communications
Press: Beijing, China, 2006.
27. Hu, Y.; Ma, P.; Zhang, X. Modelling and simulating of cold milling machine. J. Chang’an Univ. Nat. Sci. Ed.
2008, 28, 92–95.
28. Galichet, S.; Foulloy, L. Fuzzy controllers: synthesis and equivalences. IEEE Trans. Fuzzy Syst. 1995, 3, 140–
148.
29. Ding, J.; Xu, Y. Single Neuron Adaptive PID Controller and its Applications. Control Eng. China 2004, 11,
27–30.
30. Yadav, R.; Kalra, P.K.; John, J. Time series prediction with single multiplicative neuron model. Appl. Soft
Comput. 2007, 7, 1157–1163.
31. Cai, Z. Intelligent Control, 2nd ed.; Publishing House of Electronics Industry: Beijing, China, 2004.
32. He, L.; Wan, Z.; Cheng, L.; Liao, X. Simulink simulation of single neuron PID and smith predictive control
based on the s-Function. In Proceedings of the 2013 Third International Conference on IMCCC, Shenyang,
China, 21–23 September 2013; pp. 1548–1551.
33. Zhao, X.; Jiao, Y. Single Neuron Self-Adaptive PSD Control and Its Application in Reheat Steam
Temperature Control System. Chin. Soc. Elec. Eng. 2001, 21, 93–96.
34. Cheng, Q.; Wan, D.; Huang, L. The Single Neuron Adaptive PID/PSD Controller of Ship Autopilot. J.
Southeast Univ. 1997, 27, 133–137.
35. Astrom, K.J.; Hagglund, T. PID Controllers: Theory, Design and Tuning, 2nd ed.; Instrument Society of
America: Research Triangle Park, NC, USA, 1995.
Appl. Sci. 2020, 10, 2516 19 of 19

36. Jiao, S. Research on the Hydraulic Drive and Control Systems of an Asphalt Concrete Spreader. Ph.D
Thesis, Dept. Mech. Eng., Chang’an University, Xi’an, China, 2002; pp. 36–51.
37. Lei, T. New Manual of Hydraulic Engineering; Beijing Institute of Technology Press: Beijing, China, 1998; pp.
3–6.
38. Zeng, W.; Zhao, M.; He, T. Working performance for asphalt road plane milling machine. J. Chang’an Univ.
Nat. Sci. Ed. 2004, 24, 58–61.

© 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access
article distributed under the terms and conditions of the Creative Commons Attribution
(CC BY) license (http://creativecommons.org/licenses/by/4.0/).