Predicting Performance of Briquette Made from Millet Bran: A Neural Network Approach

Abstract

Millet bran possesses good fuel quality and can be successfully used as a professional feedstock for producing solid biofuel. In this paper, a framework for developing an Artificial Neural Network (ANN) to estimate the performance of millet bran briquettes is presented by using experimental data to train, test, and validate the ANN. With the capacity of the developed multi-layer ANN, the effects of moisture content, temperature, and applied pressure on the density, durability, and impact resistance are predicted. Different cases considering three parameters as inputs to the ANN, namely, moisture content, temperature, and applied pressure were analyzed. The outputs of the ANN are the density, durability, and impact resistance for each of the input parameters separately. By comparing with the experimental values, it is shown that the ANN-based method can predict the data well with a Mean Square Error (MSE) value ~ 0.2%. Further, Multiple Linear Regression (MLR) model is used to check the efficiency of ANN prediction from which it is shown that the proposed ANN-based method provides useful guidance for the prediction of the physical parameters efficiently, with the least deviation and high accuracy.

Artificial neural network-based modelling of optimized experimental study of xylanase production by Penicillium citrinum xym2

“…ANNs are trained by frequently exploring the most suitable relationship between the input and target (output) values which help in creating a model after a sufficient number of learning repetitions, or training known as epochs. 22 Figure 5 represents the coefficient of correlation (R) values for best ANN models from each group (single and double hidden layers). R-value (as shown in Equation ( 5)) is used to measure the extent of correlation between the actual and predicted value.…”

“…It is well reported in several studies that TANSIG–PURELIN combination demonstrated better adaptation to the ANN. 22,26,27 Demonstration of the ANN prediction is done in Table 2. The actual activity values are converted to normalized value to get a better standard comparison.…”

“…However, in the present analysis, a double hidden layer is also introduced and it should be noted that the performance of ANNs also depends on the learning algorithms utilized to train the weighting vectors. 22…”

Biomass valorization for energy applications: A preliminary study on millet husk

“…Based on the large amount of millet grown, millet husk a by-product is gotten in large quantities. There are nine species of millet in the world, according to [16], with a total production of 28.38 million tons, of which 11.36 million tons (40 %) were produced in Africa. Nigeria produces about 40% of Africa's millet (4.53 tons, with the northern part of the country producing more than 80% of the millet [17].…”

A virtual imprint of the artificial neural networks

“…However, these layers interface is that the different portion of the "craftsmanship" of engineering systems to resolve the complicated issues of the real world. therefore, neural systems, with their a lot of grounded capability to derive which means from diffi cult or inexact information, are often utilized to disengage styles and observe trends that are additionally complicated to be taken note by either folks or different laptop procedure[7][8][9][10][11].the topology diagrams shown, every arrow represents an association between 2 neurons and indicates the pathway for the fl ow of knowledge. Every association encompasses a weight, Associate in nursing the whole number that controls the signal between the 2 neurons.…”