Optimization of the selection process of the co-substrates for chicken manure fermentation using neural modeling

Andrzej Lewicki,Aleksandra Lewicka,Marta Cieślik,Hanna Piekarska-Boniecka,Artur Bugała,Piotr Boniecki,I Demetrescu,N.K Kaushik,F Othman,A Butu,K Oh

doi:10.1051/matecconf/20166004007

Abstract

Intense development of research equipment leads directly to increasing cognitive abilities. However, along with the raising amount of data generated, the development of the techniques allowing the analysis is also essential. Currently, one of the most dynamically developing branch of computer science and mathematics are the Artificial Neural Networks (ANN). Their main advantage is very high ability to solve the regression and approximation issues. This paper presents the possibility of application of artificial intelligence methods to optimize the selection of co-substrates intended for methane fermentation of chicken manure. 4-layer MLP network has proven to be the optimal structure modeling the obtained empirical data.

Highlights

ArtificialNeural Networks(ANN) are an importantapplicationof cognitivemethodsusedin the areaof empirical researchcarried out inthe area of widelyunderstoodartificial intelligence[1,2,3,4].In particular,promising results are related to an application one of the importantcharacteristics ofANN, i.e. the ability to solve the problems concerning regressionandapproximation issues
It givesthe possibility of using of efficientANNsimulators,among others, in order toshape up the predictiveissues
Inavailable literature related to the discussed topic there is little informationconcerning the use ofANNtomodelthe process of biomethane emission[8, 9].It seems highly appropriateto tryto buildthe regressionneural model, generatedbased onempirical datacollectedduringresearch conductedunder laboratory conditions.Developed andtestedneural modelcanserve as a toolsupporting thedecision-making processesthat occur during operationof biogas plants[10].Itscorrect applicationimproves and rationalizes thesystem forselecting theproper mixture ofinput substratesso that themethane fermentation processtakes placeunderpossibly optimal conditions

Summary

Introduction

ArtificialNeural Networks(ANN) are an importantapplicationof cognitivemethodsusedin the areaof empirical researchcarried out inthe area of widelyunderstoodartificial intelligence[1,2,3,4].In particular,promising results are related to an application one of the importantcharacteristics ofANN, i.e. the ability to solve the problems concerning regressionandapproximation issues. It givesthe possibility of using of efficientANNsimulators,among others, in order toshape up the predictiveissues. The objective of the paper was todevelopthe neuralestimatorintendedto predictthe amount ofemittedbiomethanefrom the fermentation process ofchicken manurewithadditions of othersubstrates.As atraining setwas usedthe databaseof the biogasefficiency ofthe substrates andtheirmixtures obtainedin the Laboratory ofEcotechnologyat the PoznanUniversity of. Inavailable literature related to the discussed topic there is little informationconcerning the use ofANNtomodelthe process of biomethane emission[8, 9].It seems highly appropriateto tryto buildthe regressionneural model, generatedbased onempirical datacollectedduringresearch conductedunder laboratory conditions.Developed andtestedneural modelcanserve as a toolsupporting thedecision-making processesthat occur during operationof biogas plants[10].Itscorrect applicationimproves and rationalizes thesystem forselecting theproper mixture ofinput substratesso that themethane fermentation processtakes placeunderpossibly optimal conditions.

Objectives

Methods

Results

Conclusion