This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
A Neural Network and Electrohydraulic Based Variable Rate Fertilizer Application System
Annotation ability available
Sector:
Language:
English
Abstract
Most fertilizer application systems are not capable of variable rate adjustments “on-the-fly”. To change the application rate, the farmer must dismount the tractor and change the gear ratio mechanically (i.e. via gears, chains, etc.). Air seeder manufacturers have come up with their own unique solutions to address this problem, usually involving electrohydraulics. At present there are older seeding units that perform adequately, but do not have the variable rate option. A retrofit is therefore very desirable for these units. In this paper, the feasibility of a simple hydraulic proportional valve and variable speed motor circuit is employed to replace the gears and chains. The unit is integrated with a microcontroller to provide compensation to the nonlinear properties of a proportional valve, and in turn provide a very accurate feedrate. In addition, direct user input from the cab of the tractor is possible, allowing on-the-go rate changes. The system has proven to be very flexible, and should be easy to retrofit too most existing systems.
Of equal concern is the problem of applying fertilizer across a field of variable landscape in an optimal fashion. It is well known that, in general, knolls and valleys vary in fertility due to erosion processes. Consequently, optimal fixed rate application over a typical field is at best an approximation. Having a variable feedrate system enhances the process in that the farmer can visually, and hence manually, compensate for varying landscapes. Since fertility requirements are generally related to landscape profile, it should be possible to monitor the landscape using some appropriate transducer and so automate the system. The particular retrofit system discussed in this paper accommodates such an approach in that a microcomputer, required for automation, is already integral to the system.
This paper considers a first attempt at using a neural network to find a relationship between landscape profile and fertility requirements for a particular field site. An electronic tilt meter is used to provide a real time profile of the field immediately surrounding the implement. The controller provides a real time interface between the transducer and variable rate system. Preliminary results are presented which show cautious optimism for the concept.
Authors
Citation
Mourre, D., Burton, R., and Ukrainetz, P., "A Neural Network and Electrohydraulic Based Variable Rate Fertilizer Application System," SAE Technical Paper 981967, 1998, https://doi.org/10.4271/981967.Also In
References
- Bens, R.J. Hamm, J.W. 1986 Evaluation of Technology Required for Continuous Variation in Nitrogen Fertilizer Application Rates Saskatoon, Saskatchewan, Canada
- Anderson, D.W. Gregorich, E.G. Verity, G.E. 1985 Erosion and Cultivation Effects on the Loss of Organic Matter From Prairie Soils, Soils and Crops Workshop Saskatoon, Saskatchewan, Canada 319
- Roberts, T. Stewart, J.B Bettany, J.R. 1985 The Influence of Topography on the Nature and Distribution of Soil Sulfur Canadian Journal Soil Science 65 651 655
- Sales Phamphlet for Case IH, Advanced Farming Systems
- Sales Phamphlet for John Deere, Green Star System
- Mourre D. A Neural Network and Electrohydraulic Based Variable Rate Fertilizer Application System University of Saskatchewan Saskatoon, Saskatchewan, Canada
- Haak Dennis Field Data From the Prairie Farm Rehabilitation Administration Rosetown Saskatchewan, Canada 1998
- Chen, S. Cowan, C.F.N. Billings, S.A. Grant, P. M. 1990 Parallel Recursive Error Algorithm for Training Layered Neural Recursive International Journal of Control 55 6 1215 1228
- Narendra, K. S. Parthasarathy, K. 1990 Identification and Control of Dynamical Systems Using Neural Networks IEEE Trans. Neural Networks 1 4 27
- Demuth, H. Beale, M. Matlab Neural Network Toolbox, User's Guide The Math Works, Inc. 1997