Methods of optimizing stochastic processing parameters in crop harvesting machines
View Patent ↗A precision farming method including a stochastic parameter , which is continuously optimized to adjust the model to the latest prevailing working conditions. Such parameter may be considered to constitute a variable which characterizes the instantaneously prevailing readiness of the harvesting process. Such variable can be used for establishing field maps showing the evolution of the harvesting operation itself. It can also be used in automatic routines which adjust the harvester speed in order to limit the grain losses.
1. A method of operating a harvesting machine comprising the steps of:
continuously optimizing a stochastic parameter that characterizes the instantaneously prevailing readiness with which the harvesting machine processes crop; and
continuously adjusting a performance variable of the harvesting machine in dependence on the instantaneous, optimized value of said parameter, in order to optimize a load of the harvesting machine so as to keep a value y(r) indicative of the effectiveness of said harvesting machine below a predetermined value, wherein the step of adjusting a performance variable of the harvesting machine occurs in dependence on the output of an inverted form of a yield loss estimation function:
ŷ( t , )=exp( u ( t ))−1
wherein:
{circumflex over (γ)}(t, ) is the estimated yield loss;
t is for time;
is a stochastic parameter;
u(t) is the feedrate of crop; and
exp is an exponential function.
2. A method according to claim 1 , wherein:
processing the crop comprises separating useable crop parts from other plant matter;
optimizing the load of the harvesting machine comprises optimizing the feedrate u(t) of crop into the harvesting machine; and
the effectiveness value comprises losses y(t) of useable crop parts.
3. A method according to claim 1 , wherein the step of continuously optimizing a stochastic parameter includes the step of recursively calculating the optimized parameter value in accordance with the following algorithm:
( t )− f ( ( t 1),ε( t ( t 1))) (A)
wherein:
(t) is the optimized stochastic parameter value at time t; and
ε(t, (t)) is an error prediction function.
4. A method according to claim 1 , wherein adjusting a performance variable comprises adjusting a travel speed of said harvesting machine or an actual cutting width of a header of said harvesting machine.
5. A method of mapping one or more field lots for variations in a stochastic parameter that characterizes the instantaneously prevailing readiness with which crop is processed in a harvesting machine, the method comprising the steps of:
operating a harvesting machine to harvest crop in a field lot;
simultaneously measuring a machine load and the machine effectiveness and determining the position of the machine in the field lot;
storing data indicative of the position of the harvesting machine at time t;
using the measured machine load data u(t), and machine effectiveness data y(t) in an optimization of said parameter; and
mapping optimized parameter values obtained from the step of using the measured machine load data u(t) and machine effectiveness data y(t) in an optimization of said parameter; so as to produce a parameter map of the field lot.
6. A method according to claim 5 , wherein the step of using the measured machine load data u(t), and machine effectiveness data y(t) in an optimization of said parameter includes the step of recursively calculating the optimized parameter value in accordance with the following algorithm:
( t )= f ( ( t −1),ε( t , ( t −1))) (A)
wherein:
(t) is the optimized stochastic parameter value at time t; and
ε(t, (t)) is an error prediction function.