3D Printer Failure Detection With Preemptive Part Assignment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Additive manufacturing machines face challenges in maintaining production speed, accuracy, and reliability, with machine failures disrupting manufacturing businesses and impacting customers, necessitating new approaches to predict and prevent failures.
Innovation Solution
A system for preemptive detection and remediation of component failures in additive manufacturing machines, incorporating sensors, processors, and inventory management to identify potential failures and assign replacement components based on unique printer identifiers, with remote processors and subdivided inventory locations for efficient component delivery and service notification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional reactive maintenance is used, then machine failure can be detected after it occurs, but production downtime and business disruption increase
Solution Approach 1:
The system performs preliminary actions by continuously monitoring sensor data and identifying patterns that indicate potential failures before they occur. The processor analyzes sensor signals to detect predetermined patterns associated with component degradation, enabling proactive replacement of components before actual failure happens, thus preventing production downtime.
Solution Approach 2:
The system implements feedback by continuously collecting sensor data from the printer, analyzing it through pattern recognition algorithms, and using this information to predict potential failures. This closed-loop feedback mechanism enables the system to adapt and improve its predictions over time, maintaining high reliability while minimizing unexpected downtime.
2Measurement precision
If comprehensive sensor monitoring is implemented, then failure detection accuracy improves, but system complexity and cost increase
Solution Approach 1:
The system extracts only the essential and most informative sensor data that is directly relevant to predicting component failures. Rather than processing all possible sensor inputs, the processor is configured to identify predetermined patterns in specific sensor signals that are most indicative of failure conditions, reducing system complexity while maintaining high detection accuracy.
Solution Approach 2:
The monitoring system applies different levels of analysis to different sensor data streams based on their importance and reliability. Critical sensors that provide early warning signs of failure receive more intensive analysis and pattern matching, while less critical sensors are monitored with simpler algorithms, optimizing the balance between detection accuracy and system complexity.
3Productivity
If preemptive component replacement is performed, then machine availability increases, but component usage efficiency decreases
Solution Approach 1:
The system schedules component replacements in advance based on predicted failure timelines, allowing for planned maintenance during non-critical periods. By identifying components that will fail soon and scheduling their replacement proactively, the system minimizes the impact on productivity while avoiding emergency replacements that would cause greater disruption.
Solution Approach 2:
The component replacement schedule is dynamically adjusted based on actual sensor data and changing operational conditions. The system continuously updates its predictions and can extend or shorten the timeline for component replacement based on real-time wear indicators, optimizing the balance between maintaining machine availability and maximizing component usage efficiency.
Data Source
AI summary
Systems, methods, and devices may be configured to detect and remediate component failures in three-dimensional object printers (10, 10a-f) preemptively. For example, systems may include: (a) a plurality of printers (10, 10a-f) each configured to produce three-dimensional objects (13), each printer including: (i) a plurality of subsystems; and (ii) at least one sensor; and (b) processor(s) (41, 42) and memory resource(s) (21) storing an inventory of available replacement components for at least some of said subsystems. The one or more memory resources may (21) store instructions that may cause the one or more processors to: (i) identify a predetermined pattern in data sensed during a process of producing a three-dimensional object by a sensor of a printer as an indicator of likely failure of a subsystem or component thereof; and (ii) assign a component in inventory to said printer based on a unique identifier of the printer and the indicator of likely failure identified in the signal.