Conveyor Element Anomaly Detection for Predictive Maintenance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conveyor systems in assembly and production face malfunctions due to unknown system states, leading to unpredictable irregularities and high costs, as the current state of conveyor elements is not monitored, making it difficult to predict or prevent malfunctions.
Innovation Solution
A method involving sensor devices to measure parameter values, form data telegrams, and use an anomaly model, preferably with machine learning, to identify potential malfunctions by comparing parameter values against a threshold, issuing service instructions for maintenance when anomalies are detected.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conveyor elements operate without continuous monitoring, then device complexity is reduced, but reliability deteriorates due to unpredictable malfunctions
Solution Approach 1:
The system performs preliminary actions by continuously measuring conveying times and parameter values before malfunctions occur. The anomaly model evaluates this data in advance to detect early signs of deterioration, enabling preventive maintenance before actual failures happen, thus improving reliability without requiring complex real-time intervention systems
Solution Approach 2:
The system implements feedback by continuously monitoring conveying times and parameter values, comparing them against learned normal patterns through the anomaly model. This feedback loop identifies deviations that indicate potential malfunctions, allowing the system to maintain high reliability through data-driven insights rather than complex mechanical monitoring
2Loss of time
If no state monitoring is performed, then measurement precision is insufficient, but loss of time increases due to unplanned stoppages
Solution Approach 1:
The system performs preliminary measurements of conveying times and parameter values continuously during normal operation. By analyzing this data in advance through the anomaly model, the system identifies potential issues before they cause stoppages, reducing production time loss without requiring high-precision measurement of actual malfunction states
Solution Approach 2:
The conveyor system performs self-monitoring through automated measurement of its own conveying times and parameter values. The anomaly model enables the system to self-diagnose potential problems by comparing current data against learned normal patterns, reducing the need for external monitoring equipment and complex measurement systems while minimizing unplanned stoppages
3Manufacturing precision
If comprehensive data collection is implemented, then manufacturing precision of maintenance scheduling is improved, but device complexity increases
Solution Approach 1:
The conveyor elements perform self-measurement of their conveying times and operational parameters during normal operation. This self-service data collection approach eliminates the need for complex external monitoring equipment while providing comprehensive data for precise maintenance scheduling through the anomaly model's analysis of conveying time variations and parameter patterns
Data Source
AI summary
A method for operating a conveyor system, in which assembly line trays, which each serve to hold a component, can be conveyed (moved) along a conveyor line by stationary conveyor elements, said method comprising: recording a respective conveying moment for the respective conveyor while conveying the respective assembly line trays; recording at least one respective parameter value by a sensor device for the respective conveyor element at the respective conveying moment; forming a respective data telegram for the respective conveyor element at the respective conveying moment by a respective control device of the respective conveyor element: compiling the data telegrams into a dataset by a central electronic computing device; evaluating the dataset by an anomaly model; if the evaluation reveals that an anomaly of at least one of the parameter values is above a threshold value, issuing a service instruction.