Printing Machine Service-State Prediction Using Scatter Baselines
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current predictive maintenance systems for printing machines are inefficient in predicting failures due to the lack of association between sensor values and failure probabilities, leading to unnecessary downtimes and costs, as they require manual baseline setting and are dependent on skilled personnel.
Innovation Solution
A method that measures process values, determines scatter values to establish a baseline, and calculates a health value to predict the service state of a printing machine, allowing for automatic assessment of service needs without manual intervention, applicable to various printing machines.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual baseline setting by skilled personnel is used, then prediction accuracy is improved, but time consumption and cost are increased
Solution Approach 1:
The system performs automatic baseline determination and health value calculation without requiring manual intervention by skilled personnel. The evaluation unit automatically processes sensor data, determines baselines, and predicts service states, enabling the system to serve itself and eliminating dependency on expert operators for routine predictive maintenance tasks.
2Measurement precision
If manual baseline setting by skilled personnel is used, then prediction accuracy is improved, but operational independence is reduced
Solution Approach 1:
The evaluation unit autonomously determines baselines and calculates health values using automatic algorithms that process sensor data without human intervention. The system independently identifies local minima in scatter values, establishes baselines, and predicts service states, achieving full operational independence from skilled personnel while maintaining prediction accuracy.
3Reliability
If regular interval servicing is performed, then machine availability is improved, but unnecessary replacement costs are increased
Solution Approach 1:
The system performs preliminary assessment of the service state by continuously monitoring sensor data and calculating health values against established baselines. It predicts potential failures before they occur, allowing maintenance to be scheduled at the optimal moment rather than following fixed intervals, thus avoiding both premature replacements and unexpected failures.
Solution Approach 2:
The system establishes a feedback loop where sensor data is continuously evaluated against dynamically determined baselines. The health value calculation provides real-time feedback on component condition, enabling adaptive maintenance scheduling that responds to actual machine state rather than following predetermined service intervals, thereby reducing unnecessary replacements.
Data Source
AI summary
A method for predicting a service state of a printing machine at a defined point in time includes:measuring a plurality of successive process values of a process parameter which is an indicator of the functionality of the printing machine;determining a plurality of successive scatter values which describe the spread of the measured process values within a predetermined time range;determining a local scatter minimum of the scatter values;determining a baseline, in that a baseline value is established that correlates with the value of the process parameter at the point in time of the local minimum and that does not change up until a new determination of a baseline; anddetermining a health value at a specific point in time, with a predetermined relation of the process value to the baseline value at this point in time. A service state is assessedupon the health value exceeding a predetermined threshold.