Fault Detection & Classification(FDC Lite)


Brief Introduction

FDC Lite is a lite version of standard FDC System. Use Web form user interface and user do not need to build MVA(Mutiple Variable Analysis) model in advance. Perform temporal Data monitoring and abnormality-detection directly. Alarm is sent once there is an abnormality, and actions (such as: make the tool out of service or notify the engineers…, etc) are taken to avoid continuing product-abnormality.


Features and Functions


Function Principle Benefits for USER
100% Monitor Cover Rate with Realtime Notice Llights and Monitoring Important Parameters of Equipment in Realtime 1. When there's new production detected, System will monitor the sensors based on the setting of General Rule Automatically.
2. Specific tool/recipe "Alarm Rate" setting. When alarm rate exceed the standard, tool/recipe will be marked in red for convenient management.
3. Provide OOS sensor list of each piece/run. One click to check temporal data of front 3 pieces which helps engineer find root cause of defect quickly.
Significantly Decrease the Monitor Burden
FDC Rule Management EQP Rule Comparison and Export
USER could set Monitor Rule based on Process, FDC Lite provides not only 8 common rule in Industry but Fourier transform, PAR, PAPR…etc. 1. Rule: Max / Min / Average / Std / Range / Slope / Counter / Accumulation / Mode / Fourier transform / PAR(Peak-to-Average Ratio) / PAPR(Peak-to-Average Power Ratio)
2. Perform sensor spec setting(By Manual, Sigma, Percentage) and data quality filter.
Data in Set Range is Processed by its Physical Meaning to Reduce/Decrease False Alarm and Signal-to-Noise Ratio
Data Noise Filtering User could set the range of noise which needs to be filtered then System will process this range of data in ways of delete, replace with other values or other way set by user.
Auto Daily Report System will send daily report automatically and alarm when tool abnormal to inform engineers that they need to take action. Avoid Continuous Defective Production
Report Inquire Classify data by time period, tool type, recipe and provide OOS/OOC statistic chart(by piece, daily, weekly, monthly). Significantly Decrease the Monitor Burden
Tool Metastable State Monitor System automatically separate the Stable State and Metastable State. User could set each state's rule for featuring the data. Reduce False Alarm
Single/Multi-Module GHI, GHIb Index and Sensor Group Monitor 1. User could set the sensors with same spec into one group and choose the Golden Data as samples for building the Multivariate Analysis Model.
2. System automatically choose the recent pieces' data as samples for Multivariate Analysis and New-In data's comparison.
3. Export the comparison results as GHI Index (Global Health Index) to help User checking the unshown problems(such as low quality of products).
Easier for User to Manage the Rule Settings and Quickly Check Hidden Problems
Rule Simulation Simulate the status of Rule setting to check the applicability of Rule. Avoid the False Alarm Caused by Inappropriate Rule Setting
Factory Integration Pages and "Warning" Category Enable User to view all situation of whole plant in real time. The information of insufficient data collection will be classified to “Warning” and stored for reference. Convenient for User to conduct real-time plant monitoring and the the "Warning" classification will not be notified which could reduce non-critical query

New Features and Functions in R2019a

Function Principle Benefits for USER
Add Multi-Module GHI, GHIb Index and Sensor Group Monitor 1. User could set the sensors with same spec into one group and choose the Golden Data as samples for building the Multivariate Analysis Model.
2. System automatically choose the recent pieces' data as samples for Multivariate Analysis and New-In data's comparison.
3. Export the comparison results as GHI Index (Global Health Index) to help User checking the unshown problems(such as low quality of products).
Much easier for User to manage the Rule settings and quickly check hidden problems.
Rule Simulation Simulate the status of Rule setting to check the applicability of Rule. Avoid the False Alarm caused by inappropriate Rule setting.
Tool Metastable State Monitor System automatically separate the Steady State and Metastable State. User could set each state's rule for featuring the data. Reduce False Alarm.
New Data Featuring Algorithm 1. Fourier Transform
2. PAR(Peak-to-Average Ratio)
3. PAPR(Peak-to-Average Power Ratio)
Enhance the signal to noise ratio (SNR) of Tool monitoring.
Data Noise Filtering User could set the range of noise which needs to be filtered then System will process this range of data in ways of delete, replace with other values or other way set by user. The data in set range is processed by its physical meaning to reduce False Alarm.
Add Factory Integration Pages and "Warning" Category Enable User to view all situation of whole plant in real time. The information of insufficient data collection will be classified to “Warning” and stored for reference. Convenient for User to conduct real-time plant monitoring and the the "Warning" classification will not be notified which could reduce non-critical query.

  • Applications

    • TFT LCD Process
    • MOCVD Process