Gear transmission monitoring 4.

0: What can be expected

from upcoming diagnostic and prognostic systems? 1

Gear transmission monitoring 4.0: What can

be expected from upcoming diagnostic and
prognostic systems?

Sebastian Felix Wirtz, M.Sc.,

Nejra Beganovic, M.Sc.,
Univ.-Prof. Dr.-Ing. Peter Tenberge*
Univ.-Prof. Dr.-Ing. Dirk Söffker
Chair of Dynamics and Control,
University of Duisburg-Essen
*Chair of Industrial and Automotive Drivetrains,
Ruhr-Universität Bochum

1 Introduction
Gears are key components of modern power transmission systems in different
industrial applications. Particularly in case of high power density and depending
on operating conditions, different damage modes such as micro-pitting, pitting,
or scuffing are observed on the tooth flanks of gears. Therefore, the interest in
the development of monitoring systems for online diagnosis and prediction of
different machine states, which enable condition-based or predictive mainte-
nance, grew recently.
Condition-based maintenance (CBM) has been developed as a maintenance
policy, which contributes to the improvement of reliability and availability of
technical systems through maintenance decisions based on real-time infor-
mation regarding the current health state of a system. This multidisciplinary field
of research comprises two major aspects, namely diagnostics and prognostics
[1]. To detect damages present in structures or systems (diagnosis) and to ob-
tain a prediction of the remaining useful life (RUL) (prognosis), the data ac-
quired during continuous online monitoring of technical systems are used along

Institut für Maschinentechnik der Rohstoffindustrie, RWTH Aachen, 2016

 Gear transmission monitoring 4.0: What can be expected
2 from upcoming diagnostic and prognostic systems?

with data- and/or physics-based models to schedule optimal preventive mainte-

nance actions.
In context of data-driven approaches, non-destructive testing (NDT) methods
are frequently employed in conjunction with pattern recognition algorithms that
are also based on statistical learning theory. Regarding rotating machinery, vi-
bration-based analysis is a well-established diagnostic technology. Recently,
Acoustic Emission (AE) technique, which relies on stress waves emerging from
localized sources in materials under load or stress, gained interest in this field.
These stress waves, which occur due to the release of elastic energy are locat-
ed in the ultrasound regime at frequencies between 10 kHz - 1 MHz and propa-
gate through the bulk material and across interfaces. This technique is highly
sensitive to incipient damages, particularly in connection with large-scale gears
operating at low shaft speeds [2]. Compared to vibration analysis, improved
sensitivity with respect to incipient damages is achieved with the AE technique
[3, 4]. In this field, Support Vector Machine (SVM) and Artificial Neural Network
(ANN) are used for automated classification of vibration or AE measurements.
Also for prognosis purposes, AE measurements can be utilized with deployed
lifetime models to predict system’s end-of-lifetime enabling thereby operation
and maintenance actions done in a timely manner. Herein, the calculation of
features capable to reveal wear initiation and growth processes is necessary.
Lifetime model deployment and optimization appears as a challenging task.
This contribution is structured as follows. In section 2 results of recent efforts on
gear diagnosis by means of the AE technique and wavelet analysis are pre-
sented. In section 3, empirical diagnostic and prognostic models for spur gear
based on operational variables are considered. Section 4 provides a short
summary of this paper.

2 Diagnosis: Damage detection in spur gear systems

During operation of gears, cyclically repeated rolling and sliding contact of gear
teeth lead to deterioration of tooth flank surfaces. Besides wear, gears are sub-
ject to distinct types of surface fatigue damages. Here, micro-pitting and pitting
faults occur depending on the lubrication conditions. Examples of micro-pitting
and pitting are presented in Figure 1 (a) and (b), respectively. Micro-pitting is a
surface fatigue damage which is characterized by microscopic pits on the tooth
flanks. During visual inspection, micro-pitting is recognized from a matte gray
appearance of the tooth flank surfaces. In contrast to this, pitting is initiated by
subsurface cracks which nucleate just below the tooth flank surface. The cyclic

Institut für Maschinentechnik der Rohstoffindustrie, RWTH Aachen, 2016

Gear transmission monitoring 4.0: What can be expected
from upcoming diagnostic and prognostic systems? 3

(a) (b)
Figure 1: Examples of micro-pitting (a) and pitting (b) faults
© Chair of Industrial and Automotive Drivetrains, Ruhr-Universität Bochum

loading causes these cracks to propagate in the material until finally reaching
the surface forming macroscopic craters due to extensive loss of material.
Recently, Acoustic Emission (AE) technique gained attention in the context of
gear transmission monitoring for detection of different damages, i.e. pitting [5] or
tooth root crack [4]. In this regard, asperity contact was identified as major
source of AE in meshing gears [6, 7]. Here, mixed AE waveforms are observed,
where burst type and continuous AE are presumably related to rolling and slid-
ing contact of asperities, respectively [6]. Furthermore, the AE related to mesh-
ing gears reportedly masks possible bearing faults [8].
Signal processing of AE typically involves the extraction of time-domain features
(i.e. count rate, peak amplitude or rise time) which are extracted with respect to
a predefined threshold value to characterize AE measurements. However, this
method is not viable for processing of continuous AE signals. Therefore, statis-
tical features of AE waveforms including Root Mean Square (RMS) [9], Kurtosis
(KUR) [4] or Crest Factor (CF) [7] are frequently used in context of gears to
identify damage-specific features of different gearbox damages. However, these
statistical features usually provide only the distinction of two different states in a
fault/no fault manner. For instance, Samanta [10] discriminated two different
states (healthy and pitting fault) of a two-stage gearbox using 45 statistical fea-
tures which were extracted from vibration measurements using SVM and ANN
for classification. To implement a damage detection strategy capable to discrim-
inate multiple damage modes advanced feature extraction techniques are re-
quired. Li et al. [11] used different features from the time and time-frequency
domain and proposed a feature selection scheme based on Genetic Algorithm
(GA) for damage detection in a single-stage gearbox. Using the proposed
scheme, good performances could be achieved on the classification of 8 differ-
ent gearbox faults using different classification algorithms.

Institut für Maschinentechnik der Rohstoffindustrie, RWTH Aachen, 2016

 Gear transmission monitoring 4.0: What can be expected
4 from upcoming diagnostic and prognostic systems?

Furthermore, using a supervised learning scheme, damage specific signatures

must be identified and correlated to different damage modes. Toutounzakis et
al. [12] identified the frequency range of AE measurements associated with
gear meshing as 25 kHz – 350 kHz. Scheer et al. [13] used wavelet analysis to
extract damage specific frequency domain features from AE measurements. In
this context, tooth root crack and pitting faults are considered. By comparing AE
measurements of each fault to a reference condition, short time pulses showing
frequencies between 200 kHz – 250 kHz are identified and attributed to tooth
root crack. In contrast to this, a broad-band response of increased duration is
observed in context of pitting, where different effects below 100 kHz and up to
400 kHz are observed. Therefore, similarly precise mapping of frequencies is
not provided in this case.
In this section, recent experimental results in the context of frequency-based
damage detection in lubricated spur gears are reported. Experiments were con-
ducted on a gear test rig in a back-to-back arrangement located at the Chair of
Automotive and Industrial Drivetrains, Ruhr-Universität Bochum. The test rig
was equipped with custom AE measurement technology provided by the Chair
of Dynamics and Control, University of Duisburg Essen [14], where piezoelectric
sensors were mounted outside the housing of the gearbox. Damage specific
features could be identified in the time-frequency domain using wavelet trans-
form. Besides normal operation, the damage modes micro-pitting and pitting are
considered. More detailed results of this study are also published in [15].

Experimental setup
Measurements were performed on a standard gearbox test rig, which is usually
used in connection with standardized procedures for wear-testing of lubricated
gears. Originally, this test rig was developed at Forschungsstelle für Zahnräder
und Getriebebau (FZG). A schematic drawing of the FZG test rig is shown in
Figure 2. The test rig contains two cylindrical gear stages, namely testing and
slave gears in a back-to-back arrangement. The slave gears are driven by an
electric drive. Static torque loading of the gears is achieved via a torque clutch.
Defined loads, which are specified in terms of load stages (LS), can be applied
by means of calibrated weights and a lever arm. Thus, the electric drive only
provides energy losses due to friction resulting from the gears and bearings ac-
cording to the principle of circulating power. During the experiments, similar
pairs of gears in different condition, including normal operation, micro-pitting
and pitting, are used. The pinion of each pair has 16 teeth and meshes with a
wheel with 24 teeth providing a transmission ratio of i = -1.5. The wheel is driv-

Institut für Maschinentechnik der Rohstoffindustrie, RWTH Aachen, 2016

Gear transmission monitoring 4.0: What can be expected
from upcoming diagnostic and prognostic systems? 5

en at a speed of 1450 rpm providing rotational speed of 2175 rpm at the pinion
shaft, which corresponds to a gear meshing frequency of approximately 580 Hz.
In context of gearbox monitoring using AE, sensor placement is challenging. To
achieve low attenuation of the AE amplitudes, AE sensors are frequently
mounted directly on the gears. To this end, a slip-ring is most frequently used to
connect sensors attached to rotating parts to the acquisition hardware [3, 6, 7,
16–18]. To avoid attaching sensors to moving parts, AE sensors are frequently
mounted on fixed parts of gearbox bearings (i.e. bearing races) [17, 18]. Moreo-
ver, Loutas et al. [19] developed a custom mounting fixture for AE sensors
based on friction contact, where constant contact force between the fixed sen-
sor and the rotating wheel is achieved by a spring element. The mounting tech-
nique was verified using attenuation tests, where pencil-lead break tests were
performed at different locations. In this study, the AE sensor was mounted out-
side the housing of the gearbox in a horizontal orientation above the roller bear-
ing of the pinion, as indicated in Figure 2. Besides the interface between the AE
sensor and the housing, several interfaces are encountered along the propaga-
tion path including gear/shaft as well as shaft/bearing and bearing/housing inter-

Figure 2: Illustration of FZG standard test rig,

© Chair of Industrial and Automotive Drivetrains

Institut für Maschinentechnik der Rohstoffindustrie, RWTH Aachen, 2016

 Gear transmission monitoring 4.0: What can be expected
6 from upcoming diagnostic and prognostic systems?

faces. As this bearing supports mainly radial loads, optimal transmission of AE

is expected in this position.

Experimental results
In the sequel, results of AE measurements from a FZG gearbox test rig are pre-
sented. First, the sensitivity of the measurement chain to the meshing of the
gears is verified by comparing the measurement results obtained under different
operating conditions. Hereafter, joint time-frequency domain representation of
measurement results obtained from different machine states is studied in detail.
Here, different patterns are recognized depending on the wear state of the
gearbox and the causal relation to different damage modes is discussed.
In Figure 3, measurement results of the gearbox under normal operation and
with pitting fault are compared in time domain representation. In case of Fig-
ure 3 (a), the gears are fault free, which is considered the reference condition.
Here, the signal is characterized by transient waveforms, which show a periodic
pattern of similar peak amplitudes. Furthermore, the period duration of approxi-
mately 1.7 ms corresponds to a frequency of 588 Hz, which correlates with the
theoretical meshing frequency of the gears. Compared to this, the measurement
signal obtained from a pair of gears with pitting fault is presented in Figure 3 (b).
Visual inspection of the gears prior to the experiment revealed pitting at a single
tooth of the pinion, while the wheel was classified as fault free. Here, the pitting
Normalized Amplitude

1
0.5
0
−0.5
−1
0 5 10 15 20 25 30
Time [ms]
(a) Normal Operation
Normalized Amplitude

1
0.5
0
−0.5
−1
0 5 10 15 20 25 30
Time [ms]
(b) Pitting Fault
Figure 3: Time domain representation of AE measurement

Institut für Maschinentechnik der Rohstoffindustrie, RWTH Aachen, 2016

Gear transmission monitoring 4.0: What can be expected
from upcoming diagnostic and prognostic systems? 7

defect acts as a marker indicating a full rotation of the pinion. From the meas-
urements, a similar periodic pattern is observed. However, compared to the
baseline pattern, additional discrete events are observed showing comparably
large peak amplitudes. In between each peak amplitude event, 16 periods of
the baseline pattern are observed.
From the above considerations it can be concluded that the measurement chain
is sensitive to AE which is related the gear meshing. Apparently, the observed
baseline pattern is related to the meshing of the fault free pinion teeth and the
wheel whereas peak amplitude events occur each time the faulty tooth enters
the mesh. Also, gear meshing seems to be dominant component of the meas-
urement signal compared to possible additional sources of AE, i.e. roller bear-
ings of the gearbox, which is consistent with literature [8].
In the following, the measurement results are considered in the joint time-
frequency domain. Here, different operating conditions are considered, includ-
ing normal operation (fault free) under different loads as well as micro-pitting
and pitting. Time-frequency domain analysis of the measurement signal is per-
formed by means of continuous wavelet transform. This method is particularly
suitable for the analysis of low amplitude, high frequency signals such as AE.
Due to variable time-frequency resolution, this transform provides improved
time resolution on increasing frequencies and thus enhanced interpretability.
Furthermore, rescaling of the obtained matrix of wavelet coefficients was per-
formed for illustrative purposes. Due to increasingly low signal intensities on
increasing frequencies, each row was normalized to a maximum value of unity.
Thus, decoupling of the color scales at different frequencies is achieved. This
procedure allows highlighting of low intensity effects at high frequencies.
In Figure 4 (a) characteristic patterns observed during normal operation are
presented. This is considered as reference condition. Besides a noise floor at
approximately 400 kHz, repetitively occurring peak frequencies are observed in
the spectrogram at frequencies between 40 kHz – 60 kHz. These observations
are similar among different loads. Considering Figure 4 (b), a different set of
gears is used. Prior to the experiments, visual inspection of the gears revealed
matte grey surface appearance of several tooth flanks indicating micro-pitting as
damage mode. Besides increased activity in the lower frequency range, a
downshift of the peak frequencies to approximately 30 kHz – 40 kHz is ob-
served. Furthermore, additional effects in the frequency range above 100 kHz
are apparent. In principle, increase in surface roughness leads to a reduction in
specific oil film thickness causing increase in asperity contacts [20]. Hence, en-
ergy in this frequency range is suspected to be related to an increase in surface
roughness indicating deteriorated surfaces of the tooth flanks. Presumably, AE

Institut für Maschinentechnik der Rohstoffindustrie, RWTH Aachen, 2016

 Gear transmission monitoring 4.0: What can be expected
8 from upcoming diagnostic and prognostic systems?

activity at increased frequencies above 100 kHz is attributed to wear related

processes. Here, Geometric Stress Concentration (GSC) due to surface defects
(i.e. tooling, debris dents, and disruption of the lubrication film) as well as hy-
draulic pressure propagation are suspected as underlying mechanisms causing
fatigue cracking of the material [21]. Finally, similar measurements were per-
formed with a pair of gears containing pitting damage. During visual inspection
of the gears, pitting was identified at a single tooth of the pinion whereas the
wheel was fault free. Additional surface deterioration was not apparent. Results
of the time-frequency decomposition of the signal obtained during meshing of
the damaged tooth are presented in Figure 4 (c). Here, a broad-band response
in the range of 30 kHz – 400 kHz is observed. Similar results were reported by
Scheer et al. [13]. Compared to the frequency content associated with micro-
pitting, an upshift of peak frequencies in the lower frequency band is observed.
These are mainly located between about 40 kHz – 60 kHz. However, these re-
sults are matching the reference condition, indicating the absence of abnormal
surface roughness. Furthermore, disruption of the lubrication film at the pitting

(a) Normal operation (b) Micro-pitting

(c) Pitting

Figure 4: Time-frequency domain representation of AE measurements

under different operating conditions

Institut für Maschinentechnik der Rohstoffindustrie, RWTH Aachen, 2016

Gear transmission monitoring 4.0: What can be expected
from upcoming diagnostic and prognostic systems? 9

damage is expected. Therefore, peak frequencies below 60 kHz are suspected

to result from asperity contacts between damaged gear surface and the mating
gear. This is again a strong indication that peak frequencies below 60 kHz are
related to the wear state of tooth flank surfaces.

3 Prognosis: Lifetime prediction of spur gear system

An assessment of remaining service life plays, along with diagnostic related
issues, major role and prerequisite for reliability-oriented system usage. Predic-
tion of RUL requires the development of appropriate lifetime models, which in
general use acquired condition monitoring data as input into the model. The
data to be utilized into lifetime models has to be capable to describe gradual
degradation of the system as in most cases failure does not occur suddenly.
An overview and the state-of-the-art of prognostic techniques related to rotating
machinery, as that also spur gears, is given in [22]. According to [22], prognos-
tic models are divided in physics-based and data-driven approaches, whereas
some particular models include both: physics- as well as data-based approach-
es. Physic-based approaches include mathematical models to describe the
physics of the failure (crack initiation/propagation, spall growth, spur gear crack,
and similar), whilst data-based approaches purely rely on condition monitoring
data, including history of system loading, to describe system’s reliability.
As that, Lee et al. [23] propose usage of Paris’ law, Finite Element Analysis
(FEA), and vibration data to describe crack growth in spur gear. Similarly, Op-
penheimer et al. [24] propose Forman law for crack modeling and condition
monitoring data to estimate remaining number of loading cycles up to failure. A
number approaches used for lifetime modeling such as Neural Networks [25],
Particle Filtering [26], Hidden Markov Models [27], or Recursive Bayesian mod-
els [28] are used to predict RUL. From the contributions given above, it may be
concluded that proposed models require accurate modeling of physics-related
processes and/or condition monitoring data. It is also noticeable that a lack of
lifetime models using AE-based features as input into lifetime model, especially
concerning spur gears exists.
An example of parametric lifetime model which uses AE condition monitoring
data from tribological system is given in [29]. In this case, AE measurements
are used to model accumulated damage over time, whereas the failure criterion
is defined in accordance with predefined threshold of damage accumulation
(here: threshold equal to unity).

Institut für Maschinentechnik der Rohstoffindustrie, RWTH Aachen, 2016

 Gear transmission monitoring 4.0: What can be expected
10 from upcoming diagnostic and prognostic systems?

According to this discussion, it is noticeable that further examination of AE

measurements utilization in lifetime modeling of spur gear is necessary.

4 Summary and outlook

The development of CBM is driven by the need to schedule optimal mainte-
nance actions based on real-time information from continuous monitoring of
structures or systems. In this context, diagnosis and prognosis provide suitable
methodologies to extract information from the measurement data which can be
used to support maintenance decision making processes [1].
Regarding gear transmission systems, AE technique is presented as a NDT
method to detect damages present within systems or structures. Moreover, ex-
perimental results from a spur gear test rig under different operating conditions
including normal operation of fault free gears under different loads as well as
different damage modes (i.e. micro-pitting and pitting) are presented. Depend-
ing on the condition of the gears damage specific signatures in the joint time-
frequency representation of the measurement signal could be identified. Based
on these damage-specific signatures, classifiers can be trained to detect the
presence of damage. Furthermore, using appropriate lifetime models and pre-
defined failure criterion, either RUL or similar indicator of gradual degradation of
the gears can be predicted.
One future direction is to include the information from both diagnostic and prog-
nostic systems into process control in the sense of actively interfering with
damage mechanisms and wear processes. To achieve this, quantifiable and
high reliability of the diagnostic and prognostic systems is required.

5 Bibliography
[1] A. K. S. Jardine, D. Lin, and D. Banjevic, “A review on machinery
diagnostics and prognostics implementing condition-based maintenance,”
Mech. Syst. Signal Process., vol. 20, no. 7, pp. 1483–1510, 2006.
[2] B. Lu, Y. Li, X. Wu, and Z. Yang, “A review of recent advances in wind
turbine condition monitoring and fault diagnosis,” in Power Electronics
and Machines in Wind Applications, 2009.
[3] B. Eftekharnejad and D. Mba, “Seeded fault detection on helical gears
with acoustic emission,” Appl. Acoust., vol. 70, no. 4, pp. 547–555, 2009.
[4] T. H. Loutas, G. Sotiriades, I. Kalaitzoglou, and V. Kostopoulos,
“Condition monitoring of a single-stage gearbox with artificially induced

Institut für Maschinentechnik der Rohstoffindustrie, RWTH Aachen, 2016

Gear transmission monitoring 4.0: What can be expected
from upcoming diagnostic and prognostic systems?
11

gear cracks utilizing on-line vibration and acoustic emission

measurements,” Appl. Acoust., vol. 70, no. 9, pp. 1148–1159, 2009.
[5] C. K. Tan, P. Irving, and D. Mba, “A comparative experimental study on
the diagnostic and prognostic capabilities of acoustics emission, vibration
and spectrometric oil analysis for spur gears,” Mech. Syst. Signal
Process., vol. 21, no. 1, pp. 208–233, 2007.
[6] C. K. Tan and D. Mba, "Experimentally established correlation between
acoustic emission activity, load, speed, and asperity contact of spur gears
under partial elastohydrodynamic lubrication," Proceedings of the
Institution of Mechanical Engineers, Part J: Journal of Engineering
Tribology, vol. 219, no. 6, pp. 401–409, 2005.
[7] M. Hamel, A. Addali, and D. Mba, “Investigation of the influence of oil film
thickness on helical gear defect detection using Acoustic Emission,” Appl.
Acoust., vol. 79, pp. 42–46, 2014.
[8] F. Elasha, M. Greaves, D. Mba, and A. Addali, “Application of Acoustic
Emission in Diagnostic of Bearing Faults within a Helicopter Gearbox,”
Procedia CIRP, vol. 38, pp. 30–36, 2015.
[9] R. I. Raja Hamzah and D. Mba, “The influence of operating condition on
acoustic emission (AE) generation during meshing of helical and spur
gear,” Tribol. Int., vol. 42, no. 1, pp. 3–14, 2009.
[10] B. Samanta, “Gear fault detection using artificial neural networks and
support vector machines with genetic algorithms,” Mech. Syst. Signal
Process., vol. 18, no. 3, pp. 625–644, 2004.
[11] B. Li, P. L. Zhang, H. Tian, S. S. Mi, D. S. Liu, and G. Q. Ren, “A new
feature extraction and selection scheme for hybrid fault diagnosis of
gearbox,” Expert Syst. Appl., vol. 38, no. 8, pp. 10000–10009, 2011.
[12] T. Toutountzakis, C. K. Tan, and D. Mba, “Application of acoustic
emission to seeded gear fault detection,” NDT E Int., vol. 38, no. 1, pp.
27–36, 2005.
[13] C. Scheer, W. Reimche, and F. Bach, “Early fault detection at gear units
by acoustic emission and wavelet analysis,” J. Acoust. Emiss., vol. 25, pp.
331–340, 2007.
[14] D. Baccar and D. Söffker, “Wear detection by means of wavelet-based
acoustic emission analysis,” Mech. Syst. Signal Process., vol. 60–61, pp.
198–207, 2015.
[15] S. F. Wirtz, N. Beganovic, P. Tenberge, and D. Söffker, “Frequency-
based damage detection of spur gear using wavelet analysis,” in
European Workshop on Structural Health Monitoring, Bilbao, 2016.
[16] R. I. Raja Hamzah and D. Mba, “The influence of operating condition on

Institut für Maschinentechnik der Rohstoffindustrie, RWTH Aachen, 2016

 Gear transmission monitoring 4.0: What can be expected
12 from upcoming diagnostic and prognostic systems?

acoustic emission (AE) generation during meshing of helical and spur

gear,” Tribol. Int., vol. 42, no. 1, pp. 3–14, 2009.
[17] T. Toutountzakis and D. Mba, “Observations of acoustic emission activity
during gear defect diagnosis,” NDT E Int., vol. 36, no. 7, pp. 471–477,
2003.
[18] C. K. Tan, P. Irving, and D. Mba, “A comparative experimental study on
the diagnostic and prognostic capabilities of acoustics emission, vibration
and spectrometric oil analysis for spur gears,” Mech. Syst. Signal
Process., vol. 21, no. 1, pp. 208–233, 2007.
[19] T. H. Loutas, J. Kalaitzoglou, G. Sotiriades, and V. Kostopoulos, “A Novel
Approach for Continuous Acoustic Emission Monitoring on Rotating
Machinery Without the Use of Slip Ring,” J. Vib. Acoust., vol. 130, no. 6,
p. 64502, 2008.
[20] G. Blake and J. Reynolds, “Case Study Involving Surface Durability and
Improved Surface Finish,” Gear Technol., no. August, pp. 66–75, 2012.
[21] R. Errichello, “Morphology of Micropitting,” Gear Technol., vol. 4, pp. 74–
81, 2012.
[22] A. Heng, S. Tan, and J. Matthew, “Rotating machinery prognostics: State
of the art, challenges and opportunities,” Mechanical Systems and Signal
Processing, vol 23, no. 3, pp. 724–739, 2009.
[23] C. J. Li and H. Lee, “Gear fatigue crack prognosis using embedded mod-
el, gear dynamic model and fracture mechanics,” Mechanical Systems
and Signal Processing, vol 19, no. 4, pp. 836–846, 2005.
[24] C. H. Oppenheimer and K. A. Loparo, „Physically based diagnosis and
prognosis of cracked rotor shafts,” AeroSense, International Society for
Optics and Photonics, pp. 122–132, 2002.
[25] W. Wang, “An adaptive predictor for dynamic system forecasting,” Me-
chanical Systems and Signal Processing, vol. 21, no. 2, pp. 809–823,
2007.
[26] M. E. Orchard, B. Wu, and G. J. Vachtsevanos, “A particle-filtering
framework for failure prognosis,” Proceedings of World Tribology Con-
gress, Washington, DC, 2005, pp. 883–884.
[27] M. Dong and D. He, “A segmental hidden semi-Markov model (HSMM)-
based diagnostics and prognostics framework and methodology,” Me-
chanical Systems and Signal Processing, vol. 21, no. 5, pp. 2248–2266,
2007.
[28] S. Zhang, L. Ma, Y. Sun, and J. Mathew, “Asset health reliability estima-
tion based on condition data”, Proceedings of 2nd WCEAM and the 4th
ICCM, Harrogate, UK, 2007, pp. 2195–2204.
[29] N. Beganovic, D. Söffker, “Wear Process Lifetime Prediction Based on

Institut für Maschinentechnik der Rohstoffindustrie, RWTH Aachen, 2016

Gear transmission monitoring 4.0: What can be expected
from upcoming diagnostic and prognostic systems?
13

Parametric Model Applied to Experimental Data“, Proc. IEEE Conference

on Prognostics and Health Management (PHM), Austin, TX, USA, 2015,
pp. 1–6.

Institut für Maschinentechnik der Rohstoffindustrie, RWTH Aachen, 2016

 Gear transmission monitoring 4.0: What can be expected
14 from upcoming diagnostic and prognostic systems?

Institut für Maschinentechnik der Rohstoffindustrie, RWTH Aachen, 2016