Accelerometer-based combustion sensing in diesel engines has the potential of providing feedback for combustion control to reduce fuel consumption and engine emissions at a lower cost than in-cylinder pressure sensors. In this work, triaxial block-mounted accelerometers were used to measure the engine vibration, and pressure transducers were installed to measure the in-cylinder pressure. The in-cylinder pressure can be further utilized to compute combustion metrics, including the apparent heat release rate (AHR). Engine tests were conducted for various speeds, torques, and start of injections, on a 9 L in-line six-cylinder diesel engine equipped with a common rail high pressure injection system. The relationship between engine block acceleration and AHR was modeled using a radial basis function neural network (RBFNN). By inputting the accelerometer signal to the fixed network, AHR and other combustion metrics were estimated. As the primary concern for radial basis network training is the hidden layer weight vector selection, two algorithms for weight vector selection (modified Gram–Schmidt orthogonalization and principal component analysis) were evaluated by examining the robustness of the resulting network. One-third of the conducted tests were utilized to train the network. The network was then applied to estimate the AHR for the remaining validation tests which were not used to train the network. Comparisons were made based on the combustion metrics estimation results and the selection efficiency among the two weight vector selection methods and the random selection method. Moreover, the capability concerning the network's tolerance for additive noise was also investigated. Results confirmed that the modified Gram–Schmidt method achieved much more accurately estimated combustion metrics with the highest efficiency. On the basis of this study, a real-time closed-loop control strategy was proposed with the feedback provided based on the application of the trained RBFNN.

References

References
1.
Docquier
,
N.
, and
Candel
,
S.
,
2002
, “
Combustion Control and Sensors: A Review
,”
Prog. Energy Combust. Sci.
,
28
(
2
), pp.
107
150
.10.1016/S0360-1285(01)00009-0
2.
Moro
,
D.
,
Cavina
,
N.
, and
Ponti
,
F.
,
2002
, “
In-Cylinder Pressure Reconstruction Based on Instantaneous Engine Speed Signal
,”
ASME J. Eng. Gas. Turb. Power
,
124
, pp.
220
225
.10.1115/1.1391430
3.
Taglialatela
,
F.
,
Lavorgna
,
M.
,
Mancaruso
,
E.
, and
Vaglieco
,
B. M.
,
2013
, “
Determination of Combustion Parameters Using Engine Crankshaft Speed
,”
Mech. Syst. Sig. Process.
,
38
(
2
), pp.
628
633
.10.1016/j.ymssp.2012.12.009
4.
EI-Ghamry
,
M.
,
Steel
,
J. A.
,
Reuben
,
R. L.
, and
Fog
,
T. L.
,
2005
, “
Indirect Measurement of Cylinder Pressure From Diesel Engines Using Acoustic Emission
,”
Mech. Syst. Sig. Process.
,
19
(
4
), pp.
751
765
.10.1016/j.ymssp.2004.09.004
5.
Polonowski
,
C.
,
Mathur
,
V.
,
Naber
,
J.
, and
Blough
,
J.
,
2007
, “
Accelerometer Based Sensing of Combustion in a High Speed HPCR Diesel Engine
,”
SAE
Technical Paper 2007-01-0972.10.4271/2007-01-0972
6.
Morello
,
A.
,
Blough
,
J.
,
Naber
,
J.
, and
Jia
,
L.
,
2011
, “
Signal Processing Parameters for Estimation of the Diesel Engine Combustion Signature
,”
SAE Int. J. Passeng. Cars Mech. Syst.
,
4
(
2
), pp.
1201
1215
.10.4271/2011-01-1649
7.
Villarino
,
R.
, and
Bohme
,
J.
,
2003
, “
Fast In-Cylinder Pressure Reconstruction From Structure-Borne Sound Using the EM Algorithm
,”
IEEE International Conference
on Acoustics, Speech, and Signal Processing (
ICASSP '03
), Hong Kong, April 6-10.10.1109/ICASSP.2003.1201752
8.
Bizon
,
K.
,
Continillo
,
G.
,
Mancaruso
,
E.
, and
Vaglieco
,
B.
,
2011
, “
Reconstruction of In-Cylinder Pressure in a Diesel Engine From Vibration Signal Using a RBF Neural Network Model
,”
SAE
Paper No. 2011-24-0161.10.4271/2011-01-0161
9.
Heywood
,
J. B.
,
1988
,
Internal Combustion Engine Fundamentals
,
McGraw-Hill
,
New York
.
10.
Demuth
,
H.
, and
Beale
,
M.
, 2004,
Neural Network Toolbox, User's Guide
, version 4,
The Mathworks
, http://cda.psych.uiuc.edu/matlab_pdf/nnet.pdf
11.
Chen
,
S.
,
Cowan
,
D. F. N.
, and
Grant
,
P. M.
,
1991
, “
Orthogonal Least Square Learning Algorithm for Radial Basis Function Networks
,”
IEEE Trans. Neural Networks
,
2
(2), pp. 302–309.10.1109/72.80341
12.
Mao
,
K. Z.
, and
Huang
,
G.
,
2005
, “
Neuron Selection for RBF Neural Network Classifier Based on Data Structure Preserving Criterion
,”
IEEE Trans. Neural Networks
,
16
(6), pp. 1531–1540.10.1109/TNN.2005.853575
13.
Bosch
,
1999
,
Diesel-Engine Management
,
2nd ed.
,
SAE Society of International of Engineers
,
Robert Bosch GmbH, Stuttgart, Germany.
14.
Wu
,
Z.
, and
Chen
,
L.
,
2008
, “
Method to Efficiently Implement Automotive Application Algorithms Using Signal Processing Engine (SPE) of Copperhead Microcontroller
,”
SAE
Technical Paper No. 2008-01-12.10.4271/2008-01-12
You do not currently have access to this content.