Artificial Intelligence (AI) has received increasing interest recently. AI refers to machines’ ability to perform activities that mimic human intelligence. AI could be implemented through different techniques in computer science, such as machine learning, heuristic algorithms, and fuzzy logic. Many applications have been demonstrated in different domains, such as chemical engineering, intelligent manufacturing and building energy conservation. AI applications to bioenergy systems are limited. However, previous studies indicated the tremendous potential of AI in addressing barriers in bioenergy development.
The bioenergy system is complex and usually involves biomass cultivation, biomass production and harvest, pretreatment, bioenergy production, distribution, and final usage.
A wide variety of biomass can be converted to bioenergy products – woody biomass, agricultural residues, aquatic biomass, animal biomass, industrial biomass and mixtures.Biomass has variations in composition and physicochemical properties such as ash content, moisture content, chemical compositions, heating value, density and particle size that affect the design and operation of biomass conversion.
There are two types of biomass conversion technologies:
a) Thermo-chemical conversion
b) Bio-chemical conversion.
Thermo-chemical conversion produces solid, liquid and gaseous products by thermally processing biomass. Common thermo-chemical technologies include gasification, pyrolysis, torrefaction and hydrothermal carbonization. Bio-chemical conversion converts biomass feedstocks to liquid (eg. biodiesel and bioethanol) and gaseous (eg. biogas) products by small molecules, bacteria, micro-organisms or enzymes. Matching the conversion technology with biomass feedstock and optimizing the conversion process from different perspectives (e.g., economic feasibility, environmental sustainability, and product quality) has been one of the main research areas for bioenergy.
Symbolic AI uses symbols to represent cognition and implements logic deduction to reflect the process of human cognition.Techniques with top–down paradigms have been developed based on symbolism. The symbolic AI has broad applications in process system engineering and some of them relate to bioenergy systems such as FL-based control for biomass-based power plants and boilers.
Machine learning is another subset of AI that can learn and improve from experience for specific tasks without being explicitly programmed.
Two types of machine learning are mostly used: connectivism and statistical learning. The connectivism includes techniques such as feedforward neural network (FNN), radial-basis functional network (RBF), recurrent neural network (RNN) and the state-of-the-art convolutional neural network. These AI techniques are also called “Artificial Neural Network (ANN).”
Applications of Artificial Intelligence to bioenergy Systems:
Recent developments in data science and machine learning (ML), can provide new opportunities. Accordingly, this critical review provides a deep insight into the application of ML in the bioenergy context. The latest advances in ML assisted bioenergy technology, including energy utilization of lignocellulosic biomass, microalgae cultivation, biofuels conversion and application, are reviewed in detail. The strengths and limitations of ML in bioenergy systems are comprehensively analyzed.
The following sections provide an in-depth discussion of each AI application.
- AI applications for the prediction of biomass feedstock properties.
- AI applications to biomass conversion (Thermo-chemical conversion and Bio-chemical conversion.)
- AI applications to bioenergy end-uses
- AI applications to bioenergy supply chain
Various bioenergy sources that can be used as energy resources have been determined and the amount, yield and energy potential of agricultural wastes expected to occur in the following years have been estimated using an artificial intelligence based method- support vector regression. Spatial analysis has been carried out using geographic information systems and the distribution of existing and possible agricultural lands has been determined. The amount of energy that can be obtained using wastes from different biomass sources under various scenarios has been calculated and solutions have been compared.
The need for energy increases day by day, new energy sources, efficient conversion methods and supply chain designs that enable more efficient transportation of energy resources are emerging.
The use of biomass resources in energy production is rising and new conversion facilities are commissioned every year in order to provide cleaner energy production minimizing environmental damage.
This review identified four aspects that previous AI applications focused on: predicting biomass feedstock properties, predicting process performance of biomass conversion to bioenergy/biofuels, predicting biofuel properties and the performance of bioenergy end-use systems and design and planning.
The review demonstrates the capability of AI in addressing research, measurement, and modeling challenges in the bioenergy areas.
Rishikesh Deshpande, Managing Director and Project Consultant, Sustainable Biobrikets Pvt. Ltd