Model Generation System for Selective Sensor Data Collection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for monitoring machine component wear and predicting maintenance needs are inefficient, as they often require continuous sensor data collection, which is costly, or periodic collection that may miss critical events, leading to increased downtime and reduced machine utilization.
Innovation Solution
A model generation system that includes a database, memory, and a controller to generate interrelated data tables for sensor, calculation, and fault indicator data, allowing for selective data collection and highlighting of relevant sensor data based on tag identifiers, enabling targeted maintenance scheduling.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If continuous sensor data collection is implemented to capture all wear trends and unexpected events, then measurement precision and reliability are improved, but cost and device complexity increase significantly
Solution Approach 1:
The patent segments the data collection process by creating separate data tables for different sensor types and parameters, allowing selective collection and processing of specific data subsets rather than continuous collection from all sensors, thereby reducing system complexity while maintaining monitoring reliability
Solution Approach 2:
The system implements periodic data collection at strategically determined intervals based on machine operational states and wear patterns, rather than continuous collection, which reduces data volume and system complexity while still capturing critical wear trends and unexpected events
2Device complexity
If periodic sensor data collection is used to reduce cost and complexity, then device complexity decreases, but measurement precision deteriorates due to missed wear trends and unexpected events
Solution Approach 1:
The patent implements dynamic data collection intervals that adjust based on machine operational conditions, wear rates, and criticality of monitored parameters, allowing the system to collect data more frequently when wear accelerates or unexpected events occur, thereby maintaining measurement precision while reducing overall system complexity
Solution Approach 2:
The system uses feedback mechanisms where collected sensor data is analyzed to determine whether additional data collection is needed, allowing the system to adaptively adjust collection frequency based on actual wear patterns and machine states, ensuring precise wear detection without continuous expensive monitoring
3Measurement precision
If comprehensive sensor data is collected and stored to identify all wear patterns, then measurement precision is improved, but loss of time increases due to data processing requirements
Solution Approach 1:
The patent extracts and stores only the most critical sensor data and wear indicators in structured data tables, filtering out redundant information, which reduces the volume of data requiring processing while maintaining precise wear rate measurements and trend identification
4Reliability
If maintenance is performed immediately when wear is detected to ensure reliability, then component reliability is improved, but productivity decreases due to increased downtime
Solution Approach 1:
The system performs preliminary wear analysis and trend prediction using the collected sensor data, allowing maintenance to be scheduled in advance during planned downtime or non-critical periods rather than performing immediate unplanned maintenance, thereby maintaining component reliability while maximizing machine productivity
Data Source
AI summary
A model generation system for a machine having a database, a memory to store instructions, and a controller configured to execute the instructions to generate a plurality of interrelated data tables. The data tables may have a sensor table having a sensor row including sensor attributes, a calculation table having a calculation row including calculation attributes associated with a measurement from the sensor, and a fault indicator table including fault indicator attributes based on the measurement or the calculation. The controller may highlight the sensor row using a first color when the sensor table includes a tag identifier associated with the sensor, and highlight the sensor row using a second color when the sensor table does not include the tag identifier. The controller may display the highlighted sensor table on a display device and store the data tables in the database.