Field Device Drift Prediction for Adaptive Service Intervals
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for determining service intervals for field devices in automation technology are inadequate as they do not account for individual environmental and process-specific conditions, leading to unpredictable measurement errors and potential uncontrolled production stops, with existing methods failing to accurately predict when a field device will exceed its maximum permissible tolerance.
Innovation Solution
A method using continuously sampled data and statistical prediction, such as Monte Carlo Simulation, to determine the remaining time interval until a field device's measurement characteristic exceeds its maximum permissible tolerance, providing status messages and confidence levels to guide maintenance actions, and incorporating nonlinear transformations for confidence level determination.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If fixed service intervals are used for field devices, then maintenance can be performed regularly, but service actions may occur too frequently causing production disruptions and costs
Solution Approach 1:
The service interval is transformed from a fixed static value to a dynamic value that adapts to actual device conditions. The system continuously monitors measurement characteristics and adjusts the service interval based on drift behavior, environmental conditions, and process requirements, allowing the interval to extend or shorten automatically rather than following a rigid schedule
Solution Approach 2:
The system implements continuous feedback by monitoring measurement characteristics and comparing them against tolerance limits. This feedback loop enables real-time assessment of device health and dynamic adjustment of service intervals, ensuring maintenance is performed only when actually needed rather than on arbitrary fixed schedules
2Productivity
If service intervals are extended to reduce maintenance frequency, then productivity improves, but measurement errors may go undetected leading to uncontrolled production stops
Solution Approach 1:
The system performs preliminary actions by continuously monitoring measurement characteristics and predicting future drift behavior before the device actually fails. This allows proactive scheduling of maintenance activities at optimal times, preventing unexpected failures while avoiding premature maintenance that would disrupt production
Solution Approach 2:
The traditional mechanical approach of fixed-schedule maintenance is replaced with an intelligent prediction system using statistical methods and continuous monitoring. Instead of relying on predetermined time intervals, the system uses data-driven predictions to determine when maintenance is actually needed, substituting rigid mechanical scheduling with adaptive intelligent control
3Reliability
If frequent service actions are performed to ensure measurement accuracy, then reliability improves, but false alarms increase and operational costs rise
Solution Approach 1:
The system changes parameters by using multiple measurement characteristics (drift behavior, environmental conditions, process variables) rather than relying on a single parameter. This multi-parameter approach enables more accurate prediction of actual device performance and reduces false alarms caused by normal variations in single parameters
4Ease of manufacture
If manufacturer-recommended service intervals are used, then standardization is maintained, but application-specific conditions are not adequately considered
Solution Approach 1:
The system segments the maintenance approach by device, location, and application conditions rather than applying a uniform schedule to all devices. Each field device receives a customized service interval based on its specific environmental conditions, measurement characteristics, and process criticality, allowing standardization at the methodology level while adapting to individual application needs
Data Source
Figure 1
Figure 2~3
Figure 4
AI summary
Method of determining the remaining time interval until a measurement characteristic of a field device (FD) will have drifted outside of a predetermined tolerance range and a service action is required, wherein the field device (FD) is measuring or monitoring at least one process variable of a medium in a process specific application (AP) of automation technology, comprising the steps of: Predetermining a maximum tolerance (T) of the measurement characteristic (MC) correlated/related to the measuring performance of the field device (FD), wherein the measurement performance of the field device (FD) in the process specific application (AP) is unacceptable if the measurement characteristic (MC) reaches or exceeds the predetermined maximum tolerance (T); Registering continuously the measurement characteristic (MC) of the field device (FD); Estimating a lag time interval (LTI) wherein the estimated lag time interval (LTI) depends on the drift of the measurement characteristic (MC) of the field device (FD) in the process specific application (AP); Using a method of Artificial Intelligence to determine, at the end of the estimated lag time interval (LTI), the remaining time interval (RTI) until the measurement characteristic of a field device (FD) will have drifted outside the predetermined maximum tolerance (T); Generating a message (M) informing of the remaining time interval (RTI) until the service action is required.