Marking Printer Fault Classification for Faster Line Recovery
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Industrial printer failures cause significant production downtime, especially in 24x7 operations and for regulated or perishable products, due to limited excess capacity and the need for immediate recovery.
Innovation Solution
A system and method that utilizes sensor data and historical data to classify fault conditions, autonomously determine a self-repair process, and recommend it if the estimated time to repair is less than a line recovery time threshold, using a cloud-based analytics tool and remote monitoring service to facilitate quick recovery.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If traditional printer failure response is used, then production downtime is extended, but implementing rapid self-repair systems increases device complexity
Solution Approach 1:
The system performs preliminary actions by continuously monitoring printer health through sensor data collection and analysis before failures occur. The cloud-based analytics tool pre-processes sensor data and prepares diagnostic information, enabling rapid response when failures happen without adding complex on-site hardware.
Solution Approach 2:
A cloud-based analytics tool serves as an intermediary between the printer and maintenance personnel. This mediator collects sensor data, analyzes fault conditions, and provides repair recommendations remotely, reducing the need for complex local diagnostic systems while minimizing production downtime.
2Productivity
If spare printers are deployed to minimize downtime, then production continuity is improved, but operational costs increase
Solution Approach 1:
The system enables self-service through automated fault detection and diagnostic capabilities. The analytics tool analyzes sensor data and provides repair recommendations that allow operators to perform maintenance themselves, reducing the need for expensive spare printers and specialized service interventions.
Solution Approach 2:
The system implements continuous feedback loops where sensor data from operating printers is constantly monitored and analyzed. This feedback mechanism enables predictive maintenance by identifying degradation trends before failures occur, allowing scheduled maintenance during non-critical periods rather than emergency spare deployment.
3Measurement precision
If comprehensive sensor monitoring is implemented, then fault detection accuracy is improved, but device complexity increases
Solution Approach 1:
The cloud-based analytics tool acts as an intermediary that handles the complexity of comprehensive sensor monitoring. Sensors collect detailed operational data from multiple printer components, and the cloud platform processes this data using analytics algorithms, providing accurate fault detection without adding complex processing hardware to the printer itself.
Data Source
Figure 1
Figure 2A
Figure 2B
AI summary
A system comprising a plurality of marking and/or coding devices and a computing system coupled to the devices and having at least one processor configured to: receive sensor data associated with each device and to classify, by a classifying module, a fault condition of a respective one device based on one or more of received sensor data, device self-test data, current operational data and historical device condition data, to determine autonomously a repair process recommendation, in response to the classified fault condition and based on an estimated time to repair (ETR) a non-marking or non-coding device using a self-repair recovery process relative to a line recovery time LRT threshold.