Engineering, 2009, 1, 177-187
doi:10.4236/eng.2009.13021 Published Online November 2009 (http://www.scirp.org/journal/eng).
Condition-Based Diagnostic Approach for Predicting the
Maintenance Requirements of Machinery
C. I. UGECHI1, E. A. OGBONNAYA2, M. T. LILLY1, S. O. T. OGAJI3*, S. D. PROBERT3
1Department of Mechanical Engineering, Rivers State University of Science and Technology,
Port Harcourt, Nigeria
2Department of Marine Engineering, Rivers State University of Science and Technology,
Port Harcourt, Nigeria
3School of Engineering, Cranfield University, Bedfordshire, U K
Received January 10, 2009; revised February 21, 2009; accepted February 23, 2009
Abstract
Wise maintenance-procedures are essential for achieving high industrial productivities and low energy ex-
penditure. A major part of the energy used in any production process is expended during the maintenance of
the employed equipment. To ensure plant reliability and equipment availability, a condition-based mainte-
nance policy has been developed in this investigation. In particular, this project explored the use of vibration
parameters in the diagnosis of equipment failure. A computer-based diagnostic tool employing an artificial
neural-network (ANN) was developed to analyse the ensuing machinery faults, their causes and conse-
quences. For various categories of this type of machinery, a vibration-severity chart (ISO 12372 / BS 4675:
1971) appropriately colour coded according to defined mechanical faults, was used in training of the ANN.
The model was validated using data obtained from a centrifugal pump on full load and fed into the program
written in Visual Basic. The results revealed that, for centrifugal pumps within 15 to 300kw power range,
vibration-velocity amplitude of between 0.9 and 2.7mm/s was within acceptable limits. When the values rose
to between 2.8 and 7.0mm/s, closer monitoring and improved understanding of the equipment condition was
needed. The evolved diagnostic and prognostic model is applicable for other rotary equipment that is used
within the same power limits.
Keywords: Condition Based, Diagnostic Model, Predictive Maintenance, Machinery,
Centrifugal Pumps
1. The Challenge
Maintenance, although requiring the expenditure of sig-
nificant amounts of energy, is usually required in order
to keep (or restore) facilities at an acceptable operational
standard [1]. For most plants, maintenance practice is
predominantly based on routine-scheduled prevention as
well as previously unanticipated reactions to overcome
faults. Predictive maintenance (PdM) procedures, such as
that devised in this project, are evolving and results in
less wasted effort. According to Ogbonnaya [2], Con-
treras et al. [3] and Salva et al. [4] condition monitoring
(CM) an aspect of PdM is defined as the use of appropri-
ate technologies to determine the operational state of the
considered machinery. For instance, it may involve vi-
bration measurements, infrared thermography, and/or oil
analyses etc.
For decades, conventional wisdom suggested that the
best way to optimise the performance of physical assets
was to overhaul or replace them at fixed interval (PM).
This was based on the premise that there is a direct rela-
tionship between the amount of time (or number of cy-
cles) equipment spends in service and the likelihood that
it will fail. Moubray [5], stated that this relationship be-
tween running time (age) and failure is true for some
failure modes, but that it is no longer very productive as
equipment are now much more complex than it was even
fifteen years ago. He pointed out that fixed interval
overhaul ignores the fact that overhauls are extraordinar-
ily invasive undertakings that massively upset stable

C. I. UGECHI ET AL. 178
systems. As such, they are likely to induce infant mortal-
ity, and so cause the very failure, which they seek to
prevent.
This has led to startling changes in the patterns of
equipment failure. Unless there is a dominant age-related
failure mode, fixed interval overhauls or replacements do
little or nothing to improve the reliability of rotary
equipment [5]. There is no gain in overhauling a machine
that has nothing wrong with it [6]. Moubray [5] con-
cluded that “in the absence of any evidence to the con-
trary, it is more realistic to develop maintenance strate-
gies which will assume that equipment failure can occur
at any time and not at fixed amount of time in service”.
2. Maintenance Management
Direct on-line real-time continual monitoring and analy-
sis of machinery behavior is the most reliable way to
achieve a high productivity [3]. If an abnormal situation
can be detected early, when defects are minor and have
not affected machine output, with the cause of the fault
diagnosed while the machine is still running, then the
downtime for associated repairs can be reduced and other
attendant advantages achieved.
Figure 1 shows the various maintenance methods/
techniques/strategies. Reactive maintenance is usually
only implemented following an unforeseen event leading
to a partial or total failure of the system. Preventive
maintenance (PM) is initiated according to a predeterm-
ined time-schedule in order to try to avoid the occurrence
of failure. Predictive maintenance (PdM) is laun- ched as
a result of behaviour of the equipment/ machinery before
total failure, whereas proactive maintenance may require
redesigning and/or modification of the adopted mainte-
nance-procedure where necessary.
Each of these techniques has merits and frailties, but
PdM is the most advantageous [7]; it combines the advan-
tages of preventive and proactive strategies. Its basic
Figure 1. Maintenance procedures.
concept is shown in Figure 2. Predictive maintenance is
summarized as involving actions taken to improve one or
more of the following machinery characteristics: avail-
ability, reliability, maintainability, safety, efficiency etc
as well as reduce energy waste and environmental pollu-
tion [4]. As a result, the implementation of PdM usually
enables one to have sufficient lead-time to plan, schedule
and make necessary repairs before the equipment would
otherwise fail. So major breakdowns and costly down-
time can then be avoided.
2.1. Condition Monitoring
This has long been practiced by maintenance personnel
who relied on their innate senses of hearing, touch and
sight, but the judgment and conclusions were often not
reliable. All physical structures and machinery, that are
associated with rotating components, give rise to vibra-
tion. The vibrations so generated by machinery have be-
come a well-utilized parameter for assessment in CM. It
is one of the most versatile techniques, which is capable
of detecting about 70% of common mechanical faults
associated with rotating machinery [6].
Machinery vibrations are complex, but can be meas-
ured, processed and their interpretation simplified in or-
der to facilitate the implementation of recommended
action [8]. According to Okah-Avae [9], rotating ma-
chinery produce vibration patterns, which repeat peri-
odically and so have been found to be amenable to
analysis.
Figure 2. Basic behaviour of a failing system (machinery) [5].

C. I. UGECHI ET AL. 179
2.2. Vibration Monitoring and Analysis
Even though the wise maintenance of industrial equip-
ment may require the monitoring of additional parame-
ters, such as temperature, pressure, flow, voltage, electric
current, horsepower, torque, etc, vibration data usually
contain more information about a machine’s health and
operating characteristics than any other parameter – see
Table 1. This informed the choice of vibration monitor-
ing and analysis over other condition monitoring tech-
niques in this research.
Measurements of vibration parameters are important
in many industrial applications. The parameters desired
may be displacement, velocity, or acceleration; in time or
frequency domain. These quantities are useful in pre-
dicting the fatigue failure of a particular component of
machine and play important role in analysis, which are
used to reduce equipment vibration [8]. According to
Ralph [10], when measurement of both amplitude and
frequency are available, diagnostic methods can be used
to determine the magnitude of a problem and its probable
cause.
Vibration severity is a function of displacement and
frequency of rotation of the component. Measurements
of vibration-velocity take into account both displacement
and frequency: “vibration-velocity amplitude is a direct
measure of vibration severity” [11]. Vibration-velocity
gives an indication of vibration severity over a wide
range of frequencies and hence is extensively applied in
condition monitoring [9].
Each mechanical defect generates vibration in its own
unique way [11]. This makes it possible to identify a
mechanical problem by measuring and noting its vibra-
tion signature. When vibration measurements and analy-
sis are performed systematically and intelligently, they
ill not only allow determination of machine health but w
also permit the prediction of the mechanical fault and
when such condition most likely will have reached un-
acceptable levels [12].
Vibrations occurring in the 600 to 60,000 cpm fre-
quency range are generally described and measured by
their vibration-velocity amplitudes [11]. In practice, the
following relationships apply:
Displacement of vibrating component
(x) = a / (2πƒ)2 (1)
Velocity of vibrating component
(v) = a /2πƒ (2)
Acceleration of vibrating component
(a) = 2πƒv (3)
3. Research Methodology
The identification of incipient faults in a machine, in
order to diagnose an impending problem and locate the
fault while the machine is still running, through an inter-
pretation of its unique vibration characteristic (i.e. sig-
nature) is the main aim of PdM [13]. A good vibration
survey program sets different limits for different ma-
chines, as well as different limits for different regions of
the frequency domain spectra for the same machine.
The delineation of severity limits for good and bad
bearing conditions are best determined by “comparison”
or “trending” methods [11]. In establishing a program for
checking the spike energy conditions of rolling element
bearings; a “comparison method is used. The spike en-
ergy levels of similar machines are measured and any
level which significantly departs from the average are
singled out for further analysis of potential bearing prob-
lems. This method has led to the establishment of criteria
levels which distinguished good and bad bearings.
Table 1. Parameters indicating the occurrence of faulty conditions in a rotating machine.
PARAMETER MEASURED
DETECTED CONDITION
TEMPERTURE
OF MACHINE
PRESSURE
OF
PROCESS
FLUID
FLOW
OF
FLUID
OIL ANALY-
SIS
SPIKE EN-
ERGY OF
BEARING
VIBRATION
OF
MACHINE
OUT- OF - BALANCE X
MISALIGNMENT X X
BENT SHAFT X X
BALL-BEARING DAMAGE X X X X
JOURNAL-BEARING DAMAGE X X X X X
GEAR DAMAGE X X
MECHANICAL LOOSENESS X
MECHANICAL RUBBING X X
NOISE X
CRACKING X
C
opyright © 2009 SciRes. ENGINEERING

C. I. UGECHI ET AL. 180
Various ranges of vibration velocity amplitude and
spike energy were represented with colour codes for
corresponding level of vibration severity: green for
good/normal condition, blue for acceptable condition,
yellow for fair condition/ improvement required, and red
for unacceptable condition. The use of a real-time recur-
rent simulation was therefore adopted in this investiga-
tion in order to develop an artificial neural-network
(ANN) for the analysis of the vibration data [4].
3.1. Artificial Neural-Networks (Anns)
Ogbonnaya [8] showed that ANN is a promising tool to
articulate and analyze the numerous data associated with
catastrophic failures in rotating machinery. According to
Agbese and Mohammed [14], since ANN, a branch of
Artificial Intelligence (AI), are modelled after the bio-
logical neurons of the human brain, they hold consider-
able promise as building blocks in actualising the ulti-
mate aim of AI systems. Out of the various architecture
with which ANN is conveyed; the back propagation al-
gorithm has proved most promising and accurate for
analyzing machine vibration data [8]. Also of important
is training the neuron of the network on the basis of pat-
tern recognition; especially when there are large amount
of data to handle.
Simulated neural networks are software models de-
signed through suitable interpretation of the structure and
basic function of the biological neuron of the human
brain. Therefore the more physiology of the brain is un-
derstood the better the ability to design ANNs that will
handle more complex problems. According to Carlton et
al [15]; Agbese and Mohammed [14], the artificial neu-
ron is called the processing elements or nodes, which are
capable of handling information in response to external
input. It has many input parts and combines the input
Legend: ∆P – change in active power of driver; ∆F – change in equip-
ment’s frequency; ∆V – change in equipment’s vibration-amplitude;
∆SE – change in spike energy of bearing
Figure 3. Triple hidden-layer network.
values it receives usually by summation. The combined
input is then modified by a transfer function, which can
be chosen to suit a particular application. This new value
becomes the output and can be connected to the inputs of
other processing elements through weighting functions,
which correspond to the synaptic strength of biological
neural connection [15,16].
As in the biological brain, the neural network learns
by altering the value of its weights. In a simulated neural
network, the weights are altered as to reduce the error
between the outputs the network produces in relation to a
particular input pattern and the actual required outputs
[15]. This is an iterative process, carried out as the pat-
terns to be learnt are presented; an algorithm calculates
the error and changes the value of the weights accord-
ingly.
Typically, an engineering application of ANN tech-
nology consists of a set of input nodes that forms the
input layer and one or more hidden layers. This type of
ANN is called a multilayer perceptron, and usually a
popular back-propagation algorithm is used to train the
network [17].
The triple-hidden layer ANN shown in Figure 3 was
designed with 4 nodes in the input layer. Hidden layer 1
is to be used for processing of the measured values; the
summation is then passed to hidden layer 2 for exact
fault-classification, while hidden layer 3 is designed to
issue task specifications for achieving possible solutions.
The output layer is therefore able to determine and dis-
play the nature of the exact fault and provide a solution
for the fault to be overcome, thereby optimizing the use
of energy and human resources.
A vibration-severity chart for various classes of ma-
chinery, as illustrated in Table 2, was used in the training
of the network. Its inputs were vibration-velocity ampli-
tude, motor power, equipment frequency and spike en-
ergy of the equipment. A computer program in Visual
Basic (VB) was developed from the flowchart shown in
Appendix 1. Further details of it are available from the
authors. The faults considered included misalignment,
imbalance, bent shaft, mechanical looseness, and poor-
bearing condition.
The diagnostic model is programmed according to
various colour codes for corresponding pump conditions,
diagnosed faults and appropriate task instructions on how
to avert catastrophic failure of the vibrating equipment (in
the considered case, a pump). The software flagged up
defined information once the vibration values were within
a specified range. The solutions obtained from the diag-
nostic model were used to determine how unwanted vi-
bration problems could be eliminated or reduced to al-
lowable limits.
When analysing vibration severity of a machine to
pinpoint particular problem, it is essential to know the
C
opyright © 2009 SciRes. ENGINEERING

C. I. UGECHI ET AL 181
Table 2. Ranges of vibration severity for various classes of machinery (iso 12372 or bs 4675: 1971).
Range of Vibration SeverityMaximum Values
Class of Vibration of Machine
Range
Classification
Effective
Velocity:
RMS
(mm/s)
Vibration
Velocity
(mm/s)
Vibration
Displacement
(μm) Class I
Class II Class III Class IV
0.28 0.28 0.4 1.25
0.45 0.45 0.63 2
0.71 0.71 1.0 3.15
Good
1.12 1.12 1.6 5
Good
1.8 1.8 2.5 8
Acceptable /
Allowable
Good
2.8 2.8 4.0 12.5
Acceptable /
Allowable
Good
4.5 4.5 6.3 20
Improvement
Required
Acceptable /
Allowable
7.1 7.1 10 31.5
Improvement
Required
Acceptable /
Allowable
11.2 11.2 16 50
Improvement
Required
18.0 18 25 80
Improvement
Required
28.0 28 40 125
45.0 45 63 200
71.0
Not
Acceptable Not
Acceptable Not Acceptable Not
Acceptable
Legend:
Class I: Small machines; electric motors up to 15kW power.
Class II: Medium-size machines; electric motors of 15 to 300kW power.
Class III: Large prime-movers or machines on rigid foundations; electric motors of above 300kW power.
Class IV: Large prime-movers and other machines, Turbo Machines.
Good: Colour coded green.
Acceptable/Allowable: Colour coded blue.
Improvement Required: Colour coded yellow.
Not Acceptable: Colour coded red.
vibration frequency. Knowing the frequency helps in
identifying the exact nature of the problem and the loca-
tion of the faulty machine-component. Although all of the
frequencies in a complex vibration signal can be of con-
cern for analyzing machinery problems, the fundamental
and dominant frequencies are of special importance. The
fundamental frequency is equal to the speed of rotation of
the rotating element – first harmonic (1* RPM). The
dominant frequency is the frequency at which the largest
vibration amplitude occurs. The fundamental and the
dominant frequencies are not always the same. Where the
dominant frequency differs from 1* RPM (fundamental
frequency), the dominant frequency is usually more in
dicative of the trouble.
Therefore, during the analysis of the vibration data, in-
terest was devoted primarily to measuring the dominant
vibration amplitudes and determining the frequencies at
which they occurred. This helped in the identification of
the problem and isolation of the faulty machine compo-
nent. High vibration amplitudes occurring at integral mul-
tiples of the machine’s fundamental frequency (e.g. 2*
RPM, 3* RPM, 4* RPM, etc.) are associated to different
failure modes.
3.2. Instrumentation
In undertaking this investigation, the following instru-
ments were used: Vibration Data Collector (Model: IRD
880); Vibration Pick-Up Pen / Ear Piece; Laser Align-
ment Tools; Balancing Machine; Strobe Light; and a
Computer System.
The vibration analyser performs the function of meters
C
opyright © 2009 SciRes. ENGINEERING

C. I. UGECHI ET AL. 182
Legend: = Measurement Locations/Points, i.e. A, B, C and D
 = Plain bearing
= Anti-friction bearing
Figure 4. The tested pump assembly and location measur-
ing points.
and monitors, and is capable of carrying out more com-
plex operations. Vibration meters, monitors and analys-
ers, uses vibration transducers. This is often referred to
as vibration sensors or pick-up. The heart of the meas-
urement system is the transducer; it is a sensing device
which converts one form of energy to another. The vi-
bration transducer converts mechanical vibration energy
into electrical signal. The sensitivity of a velocity trans-
ducer is constant over a wide range of operating frequen-
cies [11], but there are few limitations, which are above
the scope of this work. The data collector is used in ac-
quiring vibration-velocity, spike energy at variable fre-
quencies. The rated power and frequency of the driver
are used in the analysis as power at full load and funda-
mental frequencies. The data were collected manually
and fed into the computer model for analysis.
4. Results and Discussions
Interpretation of the field-vibration data and the subse-
quent diagnosis of the failure mode, constituted the most
difficult tasks in running the vibration-based program.
Much depended on the experience and skill of the analyst.
In undertaking maintenance, the need to avoid costly
mistakes, minimize energy expenditure and achieve the
benefits of PdM, led to the model developed for this in-
vestigation.
Vibration-velocity data, presented as root means
square (RMS) values were collected, with the pump at
full load - see Figure 4 and Table 3. The numerical val-
ues in Table 3 and trends on the associated graphs in
Figure 5 displayed high axial and radial vibrations at
locations D7 and C5 respectively, suffered by the pump
bearings. Bearings A and B (see Figure 4) for the electric
motor also experienced significant vibrations; although
of lower amplitudes. Significant vibrations of the motor
bearings could be transmitted through the shaft from
bearings C and D. Points A to D shown on Table 3 are
the location points where vibration values were taken,
while positions 1 to 8 represent the sequence in which
data were collected on the same equipment at different
frequencies.
Results of the analysis of data presented in Table 3
using the software model were displayed on the com-
puter screen as in Figure 6. This indicated significant
vibration amplitudes (depicted by the red and yellow
colours). The program then proceeded to the second
phase of the analysis in order to reveal the fault classify-
cations and task instructions, as shown in Figure 7. The
analysis indicated the presence of high axial and radial
vibrations at 1RPM, 2RPM, and 3RPM, which suggests
misalignment, while the high spike energy at B was in-
dicative of a defective bearing.
The misalignment originating at the driven end of the
pump assembly was seen as the source of the failure be-
cause the vibration amplitude was largest there. The mis-
aligned shaft and bearings at C and D led to the damage
of the bearing at B
Table 3. Vibration-analysis data sheet for unit 1800-01A pump.
PUMP MAKE: GIABBIONETA
POWER: 36.5kW
RPM: 2950 / 2945
DATE: 09/10/06
ANALYZER MODEL: IRD 880
MS/LMS/SFrequencyVelocity (VH)Velocity (VV)Velocity (VA)Spike EnergyMultiple of Fundametal
cpm
mm /sec
mm/sec mm/sec g-SEFrequency (cpm/2950)
(RMS) (RMS) (RMS)
C5 3,0128.21.11.00.09671 * RPM
D7 3,0664.71.69.80.0761 * RPM
B3 3,8343.71.11.30.5571 * rpm
A1 5,9467.50.91.20.0942 * rpm
D8 8,0073.02.70.90.11173 * rpm
C6 12,7301.93.61.10.13134 * rpm
A2 13,6861.91.11.30.0975 * rpm
B4 33,6762.01.01.61.3811 * rpm

C. I. UGECHI ET AL 183
0.0
2.0
4.0
6.0
8.0
10.0
12.0
05,00010,000 15,000 20,000 25,000 30,000 35,000 40,000
Frequency (cycles per minute)
Vibration Velocity (mm /sec)
V HV VV A
Figure 5. Vibration velocities for the 1800-01A pump.
Figure 6. Computer screen presentation for1st phase of the analysis.
Figure 7. Computer screen presentation for 2nd phase of the analysis.
C
opyright © 2009 SciRes. ENGINEERING

C. I. UGECHI ET AL. 184
Table 4. Vibration-analysis data sheet for unit 1800-01A pump (AFE).
PUMP MAKE: GIAB BION ETA
POWER: 36.5kW
RPM: 2950 / 2945
DATE: 17/10/06
ANALYZER MODEL: IRD 880
Frequen c yVelocity (VH)Velocity (VV)Velocity (VA)Spike En ergyMultiple of Fundametal
MS/LMS/ S cpm
mm /sec
mm/sec mm/sec g-SEFrequency (cpm/2950)
(RMS) (RMS) (RMS)
A1 1,5002.5 2.6 1.30.070.5*RPM
B2 2,9452.42.11.30.1171 * RPM
B3 6,0202.62 .31.50.112 * RPM
C4 9,0002.32 .31.20.153 * RPM
D5 12,2002.32.61.10.044 * RPM
D6 15,1702.42.61.10.435 * RPM
0.0
0.5
1.0
1.5
2.0
2.5
3.0
02,0004,0006,0008,00010,00012,000 14,000 16,000
Frequency (cycles per minute)
Vibration V elocity (mm/sec)
V HV VV A
Figure 8. Vibration velocities for the 1800-01A pump (AFE).
Figure 9. Computer screen presentation for the analysis after fault elimination (AFE).

C. I. UGECHI ET AL. 185
Appendix 1. predictive maintenance program flow-chart.
The task instructions were executed and the data col-
lected after the fault elimination shown in Table 4. The
associated graph (i.e. Figure 8) showed almost smooth
trends with a maximum of 2.6mm/sec radial vibration
Did data exceed
limit?,
e.g ≤ 2.8mm/s
Input measured vibration
data
START
Define all variables used
Analyze status of equipment
Did data exceed
limit?,
e.g ≤ 2.8mm/s
Set values to ascertain vibra-
tion-fault class & task specifica-
tion
Generate report for the status of
the equipment
Proffer solutions & task in-
structions
No
Yes
Yes
STOP

C. I. UGECHI ET AL. 186
velocity amplitude and 1.5mm/sec amplitude in the axial
direction, which suggested an acceptable working condi-
tion, had been achieved.
Results of the analysis of these data are shown in Fig-
ure 9 and confirmed that the condition of the pump was
within acceptable range. This is evident in the displayed
green and blue colours. Therefore the program did not
proceed to a second phase of the analysis. Also compar-
ing the data in Table 4 with specified maximum vibra-
tion-level of 3.0mm/sec for the pump, as recommended
by the manufacturer, showed that the vibration values
were within the acceptable range.
5. Conclusions
A diagnostic condition-based model that can be used for
the PdM of rotary equipment has evolved from this study.
The complexities involved in the analysis of vibration
data have been simplified for the vibration analyst and
PDM personnel. The high level of human error associ-
ated with the analysis of vibration data could also be
reduced through this procedure. Faults of the rotating
machine, identified through this analysis of its vibration
characteristics, can be displayed numerately and graphi-
cally.
The results obtained from the model, which was de-
veloped using an ANN, revealed that the approach is
well suited to the diagnosis of vibration-based faults in
centrifugal pumps. Though the model was validated us-
ing vibration data obtained from a centrifugal pump, it
can be used to analyze vibration faults in other categories
of rotating equipment. The model can also therefore be
used for continuous real-time on-line condition monitor-
ing.
6. References
[1] L. R. Higgins, “Maintenance engineering handbook,”
McGraw-Hill Book Company, New York, USA, pp. 22–
35, 1995.
[2] E. A. Ogbonnaya, “Condition monitoring of a diesel en-
gine for electricity generation,” M. Tech. Thesis, De-
partment of Marine Engineering, Rivers State University
of Science and Technology, Port Harcourt, Nigeria, p. 68,
1998.
[3] L. R. Contreras, C. Modi, and A. Pennathur, “Integrating
simulation modelling and equipment condition diagnos-
tics for predictive maintenance strategies–A case study,”
Proceedings of the 2002 Winter Simulation Conference,
University of Texas, El Paso, USA, pp. 1–7, 2002.
[4] M, Salva, R. Hernandez, and C. Sanz, “Proposed of a
method for implementing infrared-scanning inspection
programs in merchant vessels,” Marine Technology and
Sname News, Vol. 41, No. 1, pp. 1–6, 2004.
[5] J. M.Moubray, “Maintenance management: A new para-
digm, strategic technologies,” Inc., Aladon Ltd, UK, pp. 7
–11, 2000. [Online] Available: http://www.maintenancere
sources.com/RCM/Maintparadigm, July 29, 2006.
[6] A. Veltkamp, “Vibration introduction course: SKF condi-
tion monitoring, in computerized maintenance manage-
ment system and enterprise resource planning,” Nigerian
Society of Engineers, Lagos, Nigeria, pp. 1.1–4.5, 2001.
[7] S. Jeff, PDM, “Secrets revealed: How to improve your
PDM program or start one from scratch,” 1st Edition, Al-
lied Reliability, Inc., Tulsa, Oklohoma, [Online] Avail-
able: http://www.alliedreliability.com, pp. 4–35, June 6,
2006.
[8] E. A. Ogbonnaya, “Modelling vibration-Basic faults in
rotor shafts of a gas turbine,” PhD Thesis, Department of
Marine Engineering, Rivers State University of Science
and Technology, Port Harcourt, Nigeria, p. 251, 2004.
[9] B. E. Okah-Avae, “The science of industrial machinery
and systems maintenance,” Spectrum Books Ltd, Lagos,
Nigeria, pp. 19–105, 1996.
[10] W. P. P. Ralph, “Maintenance management and control,”
in Handbook of Industrial Engineering: Technology and
Operations Management, 3rd Ed., Inc. New York, USA,
pp. 1611–1615, 2001.
[11] IRD Mechanalysis, “Vibration monitoring and analysis
handbook,” IRD Mechanalysis, Inc., Columbus, USA, pp.
1.7–5.7, 1993.
[12] J. T. Broch, “Mechanical vibration and shock measure-
ment,” 2nd Ed., K. Larsen & Son A/S, Denmark, pp. 197–
199, 1980.
[13] K. A. Oladejo and A. O. Oke, “Condition monitoring of a
centrifugal pump,” in Pump Maintenance, Arcedem Se-
minar Paper, Ibadan, Nigeria, pp. 6–10, 2005.
[14] E. P. Agbese and A. Mohammed, “Artificial neural net-
work and their applications,” Proceedings of First Na-
tional Conference of the Department of Mechanical En-
gineering on Manufacturing Technology and Engineering
in a Developing Economy, University of Uyo, Nigeria,
May 2–3, pp 51–55, 2001.
[15] J. S. Carlton, C. G. Holland, M. J. Newbury, D. Rhoden,
and D. A. Triner, “Recent operational experience and re-
search relating to marine machinery condition monitor-
ing,” Trans IMarE, Vol. 109, No. 1, pp. 75–95, 1997.
[16] E. A. Ogbonnaya, K. D. H. Bob-Mannual, I. E. Douglas,
and H. I. Hart, “Application of artificial neural networks
to gas turbine rotor shaft faults diagnosis,” Journal of
Science and Technology Research, Vol. 3, No. 1, pp.
12–15, 2004.
[17] K. Farhad, A. P. Mehmet, and M. Ehsan, “A new genera-
tion motion-control system for twin-hull vessels using a
neural optimal controller,” Marine Technology and
Sname News, Vol. 40, No. 3, pp. 168–180, 2003.

C. I. UGECHI ET AL. 187
Appendix
Abbreviations and Nomenclature
AFE After fault elimination
AI Artificial Intelligence
ANN Artificial neural-network
a vibration acceleration
BS British Standard
CM Condition monitoring
cpm Cycles per minute
ƒ vibration frequency
G Large machines having electric motors of above
300kW power
g-SE Unit of spike energy
ISO International Standards Organization
K Small machines having electric motors of up to
15kW power
M Medium machines having electric motors of be-
tween 15 and 300kW power
MS/L Measurement location
MS/S Measurement sequence
N Number of hidden layers
PdM Predictive maintenance
PM Preventive maintenance
RMS Root mean square
RPM Revolutions per minute
T Turbo machines
VA Vibration velocity in axial direction (mm/sec)
VB Visual Basic
VH Vibration velocity in horizontal direction (mm/sec)
VV Vibration velocity in vertical direction (mm/sec)
v vibration velocity (mm/sec)
x vibration displacement (mm)
Z Number of output layers
ΔF Change in vibration frequency
ΔP Change in active power
ΔSE Change in equipment spike energy
ΔV Change in vibration velocity amplitude
µm Micrometre
Glossary:
Dominant frequency: Frequency at which the largest vibra-
tion-amplitude occurs.
Field vibration-data: Measured vibration data collected from
running machines.
Fundamental frequency: Basic repetition of the rotating equip-
ment; i. e. the first harmonic.