Hemp Decortication Control Using Spectral Sensing and ML

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The existing decortication process for hemp straw relies heavily on manual inspections and subjective quality assessments, leading to inefficiencies and increased costs due to the need for specialized labor and inconsistent material selection, which affects the production of high-value products.

Innovation Solution

A method and system utilizing spectral sensors and machine learning models to analyze agricultural biomass characteristics, enabling precise cutting, separation, and blending of hemp straw components, followed by combination with thermoplastic polymers to produce bio-composite products, with a controller managing the process.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual inspections and subjective quality assessments are used for material selection, then specialized labor can identify quality characteristics, but processing costs increase and efficiency decreases

Engineering Contradiction:
Improvequality assessment accuracyVSAvoidprocessing efficiency
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The patent replaces manual visual inspection and subjective quality assessment with an automated optical inspection system that uses image processing and machine learning algorithms to objectively evaluate material quality characteristics, thereby eliminating the need for specialized manual labor while improving both accuracy and processing speed

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces an intermediate automated inspection system that acts as a mediator between raw material input and processing operations, using sensors and computational algorithms to bridge the gap between physical material properties and quality decision-making, enabling automated sorting and selection without direct human intervention

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If manual inspections and subjective quality assessments are used for material selection, then specialized labor can identify quality characteristics, but processing costs increase

Engineering Contradiction:
Improvequality assessment accuracyVSAvoidprocessing cost
Core Design Contradiction:
Measurement precisionVSEase of manufacture

Solution Approach 1:

The patent replaces expensive manual inspection processes with a cost-effective automated optical inspection system that uses standard imaging equipment and software-based analysis, significantly reducing labor costs while maintaining or improving quality assessment accuracy through objective, repeatable measurements

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent uses optical imaging to create digital copies or representations of the physical material being inspected, allowing quality assessment to be performed on these digital replicas through image processing algorithms, thereby eliminating the need for physical handling and expert manual examination while reducing costs

Inventive Principle:
Principle #26Copying

3Device complexity

If inconsistent material selection is performed, then processing can be simplified, but product quality and consistency deteriorate

Engineering Contradiction:
Improveprocessing complexityVSAvoidproduct quality consistency
Core Design Contradiction:
Device complexityVSManufacturing precision

Solution Approach 1:

The patent performs preliminary quality assessment and material classification before the main processing operations, using the automated inspection system to pre-sort and identify suitable materials, thereby simplifying subsequent processing steps while ensuring consistent product quality through pre-selected, standardized input materials

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent establishes specific quantitative parameters and thresholds for material quality assessment through the automated inspection system, transforming subjective quality characteristics into measurable, controllable parameters that can be consistently evaluated and maintained throughout production, ensuring product quality consistency

Inventive Principle:
Principle #35Parameter changes

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

This approach allows for automated, low-cost, high-capacity, and scalable processing, reducing material handling costs and optimizing production for different customer demands, while enhancing the quality and consistency of hemp-derived products.

Implementation Method 1

analyzing one or more characteristics of a sample of the input units with a spectral sensor to produce spectral analysis data

Methodology Applied
Scientific EffectSpectral analysis: Absorption Spectroscopy

Data Source

PatentEP3695030B1Controller, and method for decortication processing
Publication Date: 2025.12.17 CZINNER ROBERT
  • EP3695030B1 patent drawingFigure 1
  • EP3695030B1 patent drawingFigure 2
  • EP3695030B1 patent drawingFigure 3

AI summary

A system, controller, and method for decortication processing on one or more input units of hemp into one or more resultant products. The method includes: analyzing one or more characteristics of the input units; cutting the input units into a predetermined size; opening the cut input units; performing decortication on the opened input units to separate the hemp into components, the components including bast, fibre, and hurd; densifying the fibre into bales; pulverizing the hurd and bast; combining the pulverized hurd and bast with thermoplastic polymers into a resultant product; receiving analyzer data from at least one of the decortication, the densifying, the pulverizing, and the combining; training a machine learning model based on the analyzer data; using the trained machine learning model to adjust one or more aspects to achieve a desired resultant product.