Paperboard Quality Estimation Using Real-Time Sensor Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for estimating paperboard quality parameters are inefficient, leading to high scrap rates due to delayed and non-linear quality changes, as samples must be manually taken and analyzed, resulting in a prolonged period of unknown quality status.
Innovation Solution
A computer-implemented method using a data-driven module with a preprocessing and machine learning module to continuously estimate quality parameters by analyzing sensor data from a paperboard production pipeline, utilizing cloud storage and machine learning to predict quality parameters with reduced latency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional offline sampling and laboratory testing are used to measure paperboard quality parameters, then measurement precision can be achieved for certain properties, but productivity is reduced due to production interruptions and time delays
Solution Approach 1:
The patent replaces offline mechanical/laboratory testing methods with online optical sensing systems that use light scattering and absorption measurements to detect paperboard quality parameters continuously during production, eliminating the need for production interruptions
Solution Approach 2:
The patent introduces optical sensors as intermediary devices that indirectly measure paperboard properties (such as brightness, opacity, and composition) through light interaction, providing accurate measurements without direct physical contact or sampling interruptions
2Reliability
If multiple separate measurements are performed for different paperboard quality parameters, then comprehensive quality assessment is achieved, but device complexity and measurement time increase
Solution Approach 1:
The patent combines multiple quality parameter measurements into a single integrated online measurement system that simultaneously assesses multiple paperboard properties (brightness, opacity, composition, etc.) using coordinated optical sensors, reducing device complexity while maintaining comprehensive quality assessment
Solution Approach 2:
The patent creates a universal measurement system that can assess multiple different paperboard quality parameters using the same optical sensing platform, allowing one system to perform multiple measurement functions without requiring separate dedicated devices for each parameter
3Measurement precision
If offline sampling methods are used to measure paperboard properties, then measurement accuracy for sampled areas is achieved, but loss of information occurs due to non-representative sampling and production interruptions
Solution Approach 1:
The patent implements continuous online measurement of paperboard quality parameters throughout the production process, ensuring that quality data is collected continuously without gaps or interruptions, thereby providing representative information about the entire production batch rather than just isolated samples
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
Enables precise control of paperboard production, reduces scrap and downgrading, and improves efficiency by providing real-time quality estimation and proactive detection of potential flaws.
Implementation Method 1
an optical sensor is used to measure a light scattering/absorption property of the paperboard
Implementation Method 2
an optical sensor is used to measure a light scattering/absorption property of the paperboard
Data Source
Figure 1~2
Figure 3~5
AI summary
The invention relates to a computer-implemented method for estimating at least one quality parameter of paperboard produced in a paperboard production subprocess (PP) of a paperboard processing pipeline (P) by a data-driven module (DD) comprising a preprocessing module (PM) and a machine-learning module (ML). Sensor data (D1 to D5, D1' to D5') is acquired along the processing pipeline (P). Features (F, F') are extracted from the sensor data (D1 to D5, D1' to D5') by the preprocessing module (PM). The machine-learning module (ML) is trained to reproduce target quality values from historical features (F'). After training, the machine-learning module (ML) processes real-time features (F) and estimates at least one quality parameter. The invention further relates to a system implementing said computer-implemented method and to a paperboard production machine comprising such a system.