Machine Health Monitoring Using Concurrent Simulation Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing condition monitoring systems face challenges in accurately determining the health status of complex machinery due to difficulties in accessing critical components for measurement and varying effects of stress on machine health based on location, configuration, modifications, and environmental conditions.
Innovation Solution
A monitoring device that continuously records current operating data, simulates the machine's behavior in real-time, derives performance values, and adjusts performance references dynamically to account for changes in operating conditions, environmental factors, and component modifications, using simulation models and predictive algorithms to assess and forecast the health status of machine components.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If sensors are installed on critical machine components like rotors to directly measure stress, then measurement precision is improved, but device complexity and ease of operation deteriorate due to installation difficulty and signal transmission complexity
Solution Approach 1:
The patent uses easily accessible machine components as intermediary measurement points. Instead of directly measuring stress on critical components like rotors, sensors are placed on accessible parts of the machine where vibrations and stresses can be indirectly measured and then correlated to the critical components through simulation models.
Solution Approach 2:
The patent creates virtual copies of critical machine components through simulation models. These digital twins replicate the behavior and stress states of hard-to-access components, allowing indirect measurement through easily accessible proxies while maintaining measurement accuracy for the critical parts.
2Measurement precision
If sensors are installed on critical machine components like rotors to directly measure stress, then measurement precision is improved, but ease of operation worsens due to difficulty in accessing highly stressed components
Solution Approach 1:
The patent uses easily accessible machine components as intermediary measurement points. Instead of directly measuring stress on critical components like rotors, sensors are placed on accessible parts of the machine where vibrations and stresses can be indirectly measured and then correlated to the critical components through simulation models.
3Ease of operation
If measured stresses from easily accessible locations are used to infer stress on less accessible components, then ease of operation is improved, but measurement precision deteriorates due to varying effects of stress based on location, configuration, and environmental conditions
Solution Approach 1:
The patent dynamically adjusts simulation model parameters based on actual machine configuration, location, and environmental conditions. By continuously updating parameters such as material properties, geometric dimensions, and boundary conditions in the simulation model, the system maintains accurate stress inference despite variations in operating conditions.
Solution Approach 2:
The patent implements a feedback loop where measured stresses from accessible locations are continuously fed into simulation models, which then predict stresses on critical components. The system continuously refines its predictions by comparing simulated results with actual measurements and adjusting model parameters accordingly, improving measurement precision over time.
4Reliability
If preventive maintenance is performed at regular intervals, then reliability is improved by preventing malfunctions, but productivity deteriorates due to unnecessary shutdowns and replacement of intact components
Solution Approach 1:
The patent transitions from static, time-based maintenance schedules to dynamic, condition-based maintenance. The system continuously monitors actual machine conditions and adjusts maintenance timing based on real-time health status, allowing maintenance to be performed only when actually needed rather than following fixed intervals.
Solution Approach 2:
The patent enables preliminary detection of component degradation through continuous monitoring and simulation. By identifying potential failures before they occur, the system allows for planned maintenance activities during convenient shutdowns rather than unexpected failures causing unplanned downtime, optimizing both reliability and productivity.
5Productivity
If reactive maintenance is performed only after malfunctions occur, then productivity is improved by avoiding unnecessary shutdowns, but reliability deteriorates due to unexpected downtime during critical operating phases
Solution Approach 1:
The patent enables preliminary detection of component degradation through continuous monitoring and simulation. By identifying potential failures before they occur, the system allows for planned maintenance activities during convenient shutdowns rather than unexpected failures causing unplanned downtime, optimizing both reliability and productivity.
Data Source
Figure 1
Figure 2~3
AI summary
In order to monitor the condition of a machine (M), current operating data (BD) relating to the machine (M) are continuously captured and are taken as a basis for continuously simulating a current operating behaviour of a machine component (C1, C2) by means of a concurrent simulation module (SIM). Furthermore, performance values (PV) quantifying a current performance of the machine component (C1, C2) are continuously derived from the simulated operating behaviour and are stored over the course of time. In addition, a performance normal value (PN) is regularly determined on the basis of a multiplicity of performance values which were derived earlier. Furthermore, the operating data (BD) and/or the performance values (PV) are monitored in order to determine whether a predefined first change pattern (CP) occurs. Detection of the first change pattern (CP) then causes a performance reference value (PR) to be updated with the current performance normal value (PN). In addition, the respective current performance values (PV) are continuously compared with the current performance reference value (PR) in each case. A current state of health (HS) of the machine component (C1, C2) is then displayed on the basis of the comparison result.