ARTIFICIAL NEURAL NETWORKS TO PREDICT EFFICIENCIES IN SEMI-MECHANIZED BEAN (<i>Phaseolus vulgaris</i> L.) HARVEST

Souza, Cristiano M. A. de; Padilha, Marcondes de S.; Arcoverde, Sálvio N. S.; Rafull, Leidy Z. L.

doi:10.1590/1809-4430-Eng.Agric.v42nepe20210097/2022

Acessibilidade / Reportar erro

Brasil

Español English

sumário « anterior atual seguinte »

Sumário

Scientific Paper, Special Issue: Artificial Inteligence • Eng. agríc. (Online) 42 (spe) • 2022 • https://doi.org/10.1590/1809-4430-Eng.Agric.v42nepe20210097/2022 copy

ARTIFICIAL NEURAL NETWORKS TO PREDICT EFFICIENCIES IN SEMI-MECHANIZED BEAN (Phaseolus vulgaris L.) HARVEST

Authorship SCIMAGO INSTITUTIONS RANKINGS

ABSTRACT

Bean is among the most consumed and produced crops in Brazil. Given the high demand for food, the search for technologies and controllers to increase the efficiency of agricultural systems has grown. This study aimed to model artificial neural network (ANN) architectures to predict mechanical efficiencies in the semi-mechanized bean harvest. We used a multilayer perceptron network with three inputs (harvest moisture, threshing rotor rotation, and feed rate), two hidden layers of neurons, and one output (efficiency). We evaluated the efficiency in the header, separation on the threshing rotor, cleaning of sieves, and the total efficiency of the machine. ANN was processed by a scripted algorithm to model the network, alternate the number of neurons in hidden layers, as well as to select, test, and validate ANN with less error. ANN was validated by comparing its results with the experimental data. The architectures selected to predict efficiencies were 3-8-15-1 for the header, 3-9-7-1 for the thresher and separation, 3-5-11-1 for cleaning, and 3-15-10-1 for the total operation. ANN predicted satisfactory results with errors below 1% and a high hit rate, thus being valid to predict the efficiencies in the semi-mechanized bean harvest.

KEYWORDS
harvest losses; mathematical modeling; controllers

Efficiency	Er (%)	R²	F(H₀)	t_e	R>(1-e)
Header	0.63	0.70	8.73^* * – Significant at 5% by the F-test, ns - not significant.	0.02^ns	Yes
Separation	0.42	0.86	31.59^* * – Significant at 5% by the F-test, ns - not significant.	0.45^ns	Yes
Cleaning	0.09	0.72	51.00^* * – Significant at 5% by the F-test, ns - not significant.	1.3 0^ns	Yes
Total	0.94	0.74	2.04^ns	0.98^ns	Yes
Total	0.94	0.74	2.04^ns	0.98^ns	Yes

Associação Brasileira de Engenharia Agrícola SBEA - Associação Brasileira de Engenharia Agrícola, Departamento de Engenharia e Ciências Exatas FCAV/UNESP, Prof. Paulo Donato Castellane, km 5, 14884.900 | Jaboticabal - SP, Tel./Fax: +55 16 3209 7619 - Jaboticabal - SP - Brazil
E-mail: revistasbea@sbea.org.br

Acompanhe os números deste periódico no seu leitor de RSS

[1] *Corresponding author. Universidade Federal da Grande Dourados - UFGD/ Dourados - MS, Brasil. E-mail: csouza@ufgd.edu.br

G=xlsread(‘losses’);	%Inputs
T=xlsread(‘target’);	%Targets
mseot=30;
for i=1:20
for j=1:20
for k= 1:15	%Generator of a Perceptron Multilayer Network
net = feedforwardnet([i, j], ‘trainlm’);	%Backpropagation
net.divideParam.trainRatio=0. 7 ;	%Randomized separation of the dataset
net.divideParam.valRatio=0.15;
net.divideParam.testRatio=0.15;
net.layers{ 1 }.transferFcn = ‘tansig’;	%Parameters for network training
net.layers{2}.transferFcn = ‘logsig’;
net.trainparam.epochs= 100;
net.trainparam.show = 100;
net.trainparam. max_fail= 100;
[net,tr] = train(net,G’,T’);	%Network training
y = net(G’);	%Network performace
perf = perform(net,y,T’);
mse=perf;
if mse < mseot;
boanet = net;	%Selection of the best network
boatr=tr;	%Best training
mseot = mse;
end
end
end
end
disp ‘Best MSE’;
mseot	%Best MSE
rn_losses = boanet;	%Saving the best network
rn_losstr = boatr;
save rn_losses rn_losses;
save rn losstr rn losstr;

S =xlsread(‘sample’);	%Samples
w=xlsread(‘prev_target’) ;	%Expected network targets (graph)
load rn_losses	%loads the data from rn_losses
load rn_losstr
nt = rn_losses;	%Network simulation
u = nt(S’);
u = u’;
uu=[S, w, u];	%Output file
[li,co] = size(uu);
fid = fopen(‘saida.txt’,’wb’);	%Output file generation
for i= 1 :li
fprinf(fid,%o6.2ft %6.2f\t %6.2f\t %6.2ft %6.2ft\n %6.2ft\n %6.2f\n’, uu(i, 1:co));
end
fclose(fid);
view(boanet);	%Viewing the best network
figure, plotperform(boatr);	% Plotting the Graphs
figure, plottrainstate(boatr);
Outputs = nt (G’);	%Selected ANN performance
trOut = Outputs (tr.trainInd);
vOut = Outputs (tr.valInd);
tsOut =Outputs (tr.testInd);
Targets= T’;
trTarg = Targets (tr.trainInd);
vTarg =Targets (tr.valInd);
tsTarg =Targets (tr.testInd);
figure, plotregression (trTarg, trOut, ‘Train’ , vTarg, vOut, ‘Validation’ , tsTarg, tsOut, ‘Testing’ );
%End