Printing Press Sensor Monitoring for Error Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current optical inspection methods for printed substrates, particularly in security document production, are limited in detecting progressive printing errors and rely heavily on human expertise, leading to delayed detection and potential loss of critical operational knowledge.
Innovation Solution
An expert system with multiple sensors monitoring the printing press's behavior and performing in-line analysis, coupled with optical inspection, to predict and explain printing errors, reducing false positives and enabling early warnings and corrective actions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If threshold-based optical inspection methods are used, then inspection speed can keep up with high production rates, but progressive printing errors cannot be detected early and false positives occur in regions with abrupt contrast changes
Solution Approach 1:
The inspection system is segmented into multiple independent analysis modules: optical inspection module for traditional quality checks, sensor monitoring module for printing press behavior parameters, and predictive analysis module for early error detection. Each module operates independently but contributes to the overall inspection system, allowing parallel processing that maintains high speed while improving detection accuracy through multiple analysis perspectives.
Solution Approach 2:
The system performs preliminary detection of printing errors by monitoring printing press behavior parameters (speed, temperature, pressure, vibrations) before actual printing errors occur on the substrate. This predictive approach allows corrective actions to be taken in advance, preventing errors rather than detecting them after they appear on the printed material.
2Stability of the object's composition
If tolerance thresholds are increased to prevent false positives in high-contrast regions, then inspection stability improves, but the ability to detect real errors in those regions is lost
Solution Approach 1:
Printing press behavior parameters (speed, temperature, pressure, vibrations) serve as intermediary indicators that correlate with the likelihood of printing errors occurring. Instead of directly inspecting the printed substrate in difficult-to-detect regions, the system monitors these intermediate parameters that predict error occurrence, enabling detection without relying on problematic optical threshold comparisons in high-contrast areas.
3Reliability
If optical inspection tolerances are used, then false positives are reduced, but detection of progressive printing errors is delayed until errors exceed tolerance thresholds
Solution Approach 1:
The system continuously monitors printing press behavior parameters and compares them against reference values or historical data to detect deviations that indicate progressive errors. This feedback mechanism operates in real-time throughout the printing process, providing continuous information about printing quality trends without the need to wait for errors to exceed fixed optical inspection thresholds.
4Measurement precision
If human expertise is relied upon for error detection, then complex printing errors can be identified, but operational knowledge is lost when personnel change and detection consistency decreases
Solution Approach 1:
The system captures and stores printing press behavior parameter data and inspection results automatically during operation, creating a self-documenting process. This automated record-keeping allows the system to learn from historical data and maintain consistent detection criteria independent of personnel changes, while still capturing the complexity of various error types that human experts could identify.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
There is described a method for detection of occurrence of printing errors on printed substrates during processing thereof on a printing press (1) comprising the steps of providing multiple sensors on functional components of the printing press to monitor the behaviour of the printing press (1) during processing of the printed substrates and performing an in-line analysis of the behaviour of the printing press (1) to determine occurrence of a characteristic behaviour of the printing press (1) which leads or is likely to lead to occurrence of printing errors on the printed substrates or which leads or is likely to lead to good printing quality of the printed substrates. In-line analysis of the behaviour of the printing press (1) preferably includes performing fuzzy pattern classification of the behaviour of the printing press (1) . According to one embodiment of the proposed method in-line analysis of the behaviour of the printing press (1) is coupled with an in-line optical inspection of the printed substrates.