Method and system for reducing work-in-process

A system for reducing a work-in-progress (WIP) in a process of a product, comprising:

• a plurality of tool groups configured to run the process;
• and
• a controlling computer coupled to the plurality of tool groups, and configured to:
• collect process profile data from the plurality of tool groups, and calculate a standard deviation of an output of a stage of a bottleneck tool group of the plurality of tool groups according to the process profile data to serve as values of at least one of a plurality of key-performance-indicators (KPIs) of each tool group, wherein tools running a main process step of at least critical stages are grouped into one of the plurality of tool groups, and tools running a metrology step of the at least critical stages are grouped into an other one of the plurality of tool groups;
• feed the values of the KPIs and the WIP of each tool group into a neural network model in order to output an impact on the WIP for each KPI of each tool group by the neural network model, wherein the neural network model is trained by feeding the values of the KPIs and the WIP of each tool group in the process profile data of a plurality of days collected in advance, and performing sensitivity analysis on the values of the KPIs and the WIP so as to output the impact showing a rate of change of the WIP resulting from a predetermined change of each KPI model;
• select a predetermined percentage of the KPIs for each tool group as a set of major KPIs according to the impact on the WIP for each KPI of each tool group output by the neural network model;
• and
• control the plurality of tool groups according to the impact of the set of major KPIs of each tool group in order to reduce a total WIP, wherein the total WIP is a summation of the WIP of each tool group.

A method for reducing a work-in-progress (WIP) in a process of a product, the method comprising:

• collecting process profile data from a plurality of tool groups running the process, wherein the process profile data comprises an output from each of a plurality of stages run by each tool group, and calculating a standard deviation of an output of a stage of a bottleneck tool group of the plurality of tool groups every a predetermined number of days according to the process profile data to serve as values of at least one of a plurality of key-performance-indicators (KPIs) of each tool group;
• feeding the values of the KPIs and the WIP of each tool group into a neural network model in order to output an impact on the WIP for each KPI of each tool group by the neural network model, wherein the neural network model is trained by feeding the values of the KPIs and the WIP of each tool group in the process profile data of a plurality of days collected in advance, and performing sensitivity analysis on the values of the KPIs and the WIP so as to output the impact showing a rate of change of the WIP resulting from a predetermined change of each KPI;
• selecting a predetermined percentage of the KPIs for each tool group as a set of major KPIs according to the impact on the WIP for each KPI of each tool group output by the neural network model;
• and
• controlling the plurality of the tool groups according to the impact of the set of major KPIs of each tool group in order to reduce a total WIP, wherein the total WIP is a summation of the WIP of each tool group.