Substrate Sensor Synchronization for Targeted Maintenance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing substrate processing devices with multiple sensors face challenges in accurately analyzing time series data to determine sensor anomalies and device status, leading to inefficiencies in maintenance and operational performance.
Innovation Solution
A data analysis method that generates rarity data from time series data, normalizes it using hyperbolic tangent, estimates probability density functions, and calculates synchronization rates between sensors to identify synchronized data clusters, allowing for targeted maintenance operations based on sensor correlations and anomalies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple sensors are installed in substrate processing devices to monitor various parameters, then measurement coverage and monitoring capability are improved, but data analysis complexity and difficulty of detecting anomalies increase
Solution Approach 1:
The patent segments the data analysis process into distinct modules: rarity data generation for each sensor, probability density function estimation, synchronization rate calculation between sensor pairs, and anomaly detection. This segmentation allows complex multi-sensor data to be processed through systematic, manageable steps, reducing overall analysis complexity while maintaining comprehensive monitoring capability
Solution Approach 2:
The patent introduces rarity data and synchronization rate as intermediary metrics that bridge raw sensor data and final anomaly detection. Rarity data transforms raw measurements into normalized rarity values, while synchronization rate compares patterns across sensors. These intermediaries simplify the detection process by providing standardized metrics that facilitate anomaly identification without requiring direct analysis of complex multi-sensor datasets
2Reliability
If comprehensive analysis of time series data from all sensors is performed to identify anomalies, then detection accuracy is improved, but processing time and computational resources increase
Solution Approach 1:
The patent applies partial action by analyzing synchronization rates between sensor pairs rather than performing comprehensive joint analysis of all sensors simultaneously. By computing synchronization metrics for individual sensor pairs and comparing them against thresholds, the system achieves reliable anomaly detection without the computational burden of full multi-sensor correlation analysis, thus reducing processing time while maintaining detection reliability
Solution Approach 2:
The patent transforms raw time series data into rarity data through parameter transformation, then further processes this into synchronization rates. This parameter change approach converts complex temporal patterns into simplified statistical metrics that are easier and faster to compute. By working with transformed parameters (rarity values and synchronization rates) rather than raw data, the system maintains detection reliability while significantly reducing computational requirements and processing time
3Reliability
If sensors are monitored continuously to detect anomalies early, then operational reliability is improved, but energy consumption and operational costs increase
Solution Approach 1:
The patent implements periodic action through the synchronization rate calculation, which compares data patterns at discrete time points rather than requiring continuous processing. By evaluating synchronization at specific intervals and comparing against threshold values, the system maintains operational reliability through timely anomaly detection while reducing energy consumption associated with continuous real-time analysis of all sensor data streams
Data Source
AI summary
A method includes generating first rarity data from first time series data acquired from a first source of a substrate processing device, the first time series data including a plurality of first component data acquired at a plurality of time points, the first rarity data indicating how rare each of the plurality of first component data is; generating second rarity data from second time series data acquired from a second source of the substrate processing device, the second time series data including a plurality of second component data acquired at a plurality of time points, the second rarity data indicating how rare each of the plurality of second component data is; generating first binary data on the basis of the first rarity data; generating second binary data on the basis of the second rarity data; generating a synchronization rate between the first time series data and the second time series data, by the use of the first binary data and the second binary data; and initiating a maintenance operation for the first source, the second source or the substrate processing device based on the first binary data, the second binary data, and the synchronization rate.