There are many sources of disturbances for on-the-go weighing. This study was conducted to develop a new method
to remove those disturbances and to estimate more accurate dynamic masses in silage harvesting. A mathematically simple
procedure was developed using vertical movement information from a low-cost accelerometer, in addition to conventional
instrumentation using load cells for mass data, and was tested using a small scale model weighing bin and a commercial silage
wagon. Clear similarities were found between the patterns of low-pass filtered mass and acceleration data when both were
obtained simultaneously from the same harvesting system. Multiplication factors for acceleration data were calculated so
that the differences between the mass data and the multiplied acceleration data could be minimized. Thus, subtracting the
multiplied acceleration from the mass data corresponded to deleting load cell disturbances due to vertical movements. A
small-scale model weighing system was used to apply the developed approach to known dynamic masses. Mass estimation
showed less than 20 g measurement errors for experimental loads. The same method was applied to a commercial silage wagon
with harvested silage mass data in the 0 to 7,000 kg range. The proposed method showed that remaining error magnitudes
were reduced by 39% to 56% and standard deviations were reduced by 53% to 68 % with respect to the results of low-pass
filtering and moving average.
[1]
L. G. van Willigenburg,et al.
Dynamic weighing for accurate fertilizer application and monitoring
,
2001
.
[2]
Simon Blackmore,et al.
Remedial Correction of Yield Map Data
,
2004,
Precision Agriculture.
[3]
Wei-Qun Shu.
Dynamic weighing under nonzero initial conditions
,
1993
.
[4]
Stephen W. Searcy,et al.
YIELD DATA FILTERING TECHNIQUES FOR IMPROVED MAP ACCURACY
,
2001
.
[5]
Sina Balkir,et al.
Evolution-based design of neural fuzzy networks using self-adapting genetic parameters
,
2002,
IEEE Trans. Fuzzy Syst..
[6]
B. S. Blackmore,et al.
Yield Mapping; Errors and Algorithms
,
2015
.
[7]
K. A. Sudduth,et al.
Design and analysis of a grain weighing system.
,
2000
.
[8]
D. H. Horrocks,et al.
Dynamic weight estimation using an artificial neural network
,
1998,
Artif. Intell. Eng..
[9]
Neil M. White,et al.
Application of artificial neural networks to intelligent weighing systems
,
1999
.