Printing Press Maintenance Prediction Using Scatter-Based Baselines

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current predictive maintenance systems for printing presses are inefficient in predicting maintenance needs due to the complexity of assigning failure probabilities, requiring specialist intervention and leading to unnecessary downtime and costs, as they often rely on arbitrary baseline settings and are not adaptable to varying operating conditions.

Innovation Solution

A method that measures consecutive process values and determines a baseline by identifying a local scattering minimum, allowing for the calculation of a health value that automatically indicates maintenance needs without requiring specialist calibration, using a predetermined threshold to assess the maintenance status of a printing press.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional regular interval servicing is used, then maintenance is performed systematically, but unnecessary replacement of components occurs and downtime increases

Engineering Contradiction:
Improvemaintenance reliabilityVSAvoiddowntime
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system uses the printing press's own operational data to automatically determine maintenance needs without external specialist intervention. The printing press monitors its own process parameters and autonomously identifies when maintenance is required, eliminating the need for scheduled servicing and specialist calibration.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system continuously monitors process parameters and uses the scatter of these values as feedback to determine maintenance status. When the scatter exceeds a threshold, the system automatically triggers a maintenance indication, creating a closed-loop feedback system that adapts to actual machine condition rather than following fixed schedules.

Inventive Principle:
Principle #23Feedback

2Measurement precision

If specialist calibration is required for predictive maintenance systems, then accurate failure probability prediction is achieved, but time consumption and costs increase significantly

Engineering Contradiction:
Improvefailure prediction accuracyVSAvoidcalibration time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system eliminates the need for specialist calibration by using the printing press's own operational data. The scatter calculation is performed automatically on existing process parameters, and the system self-determines maintenance thresholds based on observed variability, making it independent of external specialist intervention.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

Instead of requiring specialists to create custom calibration models for each machine, the system uses a universal approach where the scatter of process values serves as a direct indicator of maintenance needs. This copied methodology can be applied uniformly across different printing presses without machine-specific calibration.

Inventive Principle:
Principle #26Copying

3Measurement precision

If multiple operating cycles are monitored to determine baseline values, then accurate maintenance thresholds are established, but productivity is reduced due to interruptions

Engineering Contradiction:
Improvebaseline accuracyVSAvoidproduction output
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The system performs preliminary analysis of process parameter scatter during normal operation to establish maintenance thresholds. By continuously monitoring the scatter of process values, the system prepares maintenance indications in advance without requiring dedicated calibration periods that would interrupt production.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The maintenance prediction system operates continuously during normal printing operations without interrupting production. The scatter calculation and maintenance status determination are performed in real-time alongside regular printing tasks, maintaining continuous useful action in both monitoring and production.

Inventive Principle:
Principle #20Continuity of useful action

4Ease of manufacture

If arbitrary baseline settings are used, then the system is easy to implement, but maintenance predictions become inaccurate and unreliable

Engineering Contradiction:
Improvesystem implementation easeVSAvoidmaintenance prediction reliability
Core Design Contradiction:
Ease of manufactureVSReliability

Solution Approach 1:

The system automatically determines appropriate baseline thresholds by analyzing the scatter of process values during normal operation. Instead of requiring arbitrary manual setting, the printing press itself provides the data needed to establish accurate maintenance criteria, combining ease of implementation with reliable predictions.

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP4331854A1Method for predicting the maintenance state of a printing machine
Publication Date: 2024.03.06 CANON PRODN PRINTING HLDG BV
  • EP4331854A1 patent drawingFigure 1
  • EP4331854A1 patent drawingFigure 2a~2c
  • EP4331854A1 patent drawingFigure 3

AI summary

A method for predicting the maintenance status of a printing press at a specific point in time involves the following steps: a) measuring several successive process values ​​of a process parameter that is an indicator of the printing press's operational readiness; b) determining several successive standard deviation values ​​that describe the variation of the measured process values ​​within a predetermined time interval; c) determining a local minimum of the standard deviation values; d) determining a baseline by establishing a baseline value that correlates with the value of the process parameter at the time of the local minimum and remains unchanged until a new baseline is established; and e) determining a health value at a specific point in time with a predetermined ratio of the process value to the baseline value at that point in time.where exceeding a predetermined threshold value due to the health value indicates a maintenance condition.