System, controller, and method for decortication processing

A controller executed on a computing device for decortication processing on one or more input units of agricultural biomass comprising dicotyledonous plants, the controller comprising at least one processing unit and a data storage, the at least one processing unit in communication with the data storage and configured to execute:

• a data science module to:
• using a trained machine learning model to take spectral analysis data as input and to estimate chemical composition of the agricultural biomass after decortication as output, the chemical composition comprising at least one of cellulose, hemicellulose, lignin, extractives and ash, the machine learning model trained using training data comprising sampling data comprising spectral analysis data analyzed from sample-units and corresponding measured chemical composition of the sample-units;
• and
• a control module to:
• receive one or more characteristics of the one or more input units from sensors, the sensors comprising a spectral sensor to produce the spectral analysis data;
• instruct a cutting unit to cut the one or more input units into a predetermined size, the predetermined size based on the estimated chemical composition;
• instruct an opening unit to open the one or more cut input units;
• instruct a decorticator to decorticate the one or more opened input units to separate the one or more opened input units into components, the components comprising bast, short fibre, hurd, and dust;
• instruct a blending unit to blend hurd, short fibre and cut bast;
• instruct a pulverizer to pulverize the hurd and the bast;
• instruct a compounder to combine the pulverized hurd and bast with thermoplastic polymers into a resultant product, the resultant product is a bio-composite product that comprises the blend combined with the thermoplastic polymers.