CMP Pad Temperature Control With Learned PID Tuning

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Variations in temperature behavior among polishing units in CMP apparatuses lead to inconsistent polishing performance, affecting the yield of semiconductor devices due to the use of common PID parameters across multiple units.

Innovation Solution

A pad-temperature regulating apparatus and method that employs a controller with a learned model constructed by machine learning to adjust PID parameters based on temperature behavior parameters, ensuring the temperature behavior curve remains within a predetermined allowable range, thereby maintaining consistent polishing performance across units.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If common PID parameters are used across multiple polishing units, then device complexity is reduced and ease of operation is improved, but manufacturing precision deteriorates due to variations in temperature behavior

Engineering Contradiction:
Improvecontrol system complexityVSAvoidpolishing performance consistency
Core Design Contradiction:
Device complexityVSManufacturing precision

Solution Approach 1:

The system automatically adjusts PID parameters (proportional gain, integral gain, derivative gain) based on measured temperature behavior characteristics of each polishing unit. The controller changes these parameters dynamically to match the specific thermal response of each unit, thereby resolving the contradiction between using common control settings and achieving unit-specific precision.

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The system implements feedback control by measuring the actual temperature behavior of the polishing pad and using this information to adjust the PID parameters. The temperature sensor continuously monitors the pad temperature, and the controller uses this feedback to optimize the control parameters for each unit's specific characteristics.

Inventive Principle:
Principle #23Feedback

2Manufacturing precision

If PID parameters are individually adjusted for each polishing unit, then manufacturing precision is improved, but device complexity increases and ease of operation deteriorates

Engineering Contradiction:
Improvepolishing performance consistencyVSAvoidcontrol system complexity
Core Design Contradiction:
Manufacturing precisionVSDevice complexity

Solution Approach 1:

The system performs self-adjustment by automatically measuring its own temperature behavior characteristics and autonomously optimizing its PID parameters without requiring external intervention. The controller self-calibrates based on measured data, eliminating the need for manual parameter tuning while maintaining high precision.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system performs preliminary measurement of temperature behavior characteristics during an initial phase, and based on these measurements, pre-adjusts the PID parameters before actual polishing operations begin. This preliminary action ensures optimal parameters are ready in advance, avoiding the need for complex real-time adjustments during production.

Inventive Principle:
Principle #10Preliminary action

3Manufacturing precision

If PID parameters are individually adjusted for each polishing unit, then manufacturing precision is improved, but loss of time increases due to parameter adjustment requirements

Engineering Contradiction:
Improvepolishing performance consistencyVSAvoidparameter adjustment time
Core Design Contradiction:
Manufacturing precisionVSLoss of time

Solution Approach 1:

The system performs preliminary measurement and parameter optimization during initial setup or idle periods, so that when polishing operations begin, the optimal parameters are already configured. This eliminates time loss during actual production by preparing parameters in advance.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system automatically measures and adjusts its own parameters without requiring manual intervention or停机 (shutdown) for calibration. The self-service capability allows parameter optimization to occur seamlessly, minimizing disruption to production schedules and reducing time loss.

Inventive Principle:
Principle #25Self-service

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

The solution effectively suppresses variations in polishing performance between units, improving the yield of semiconductor products by maintaining the temperature behavior curve within a predetermined range, ensuring consistent polishing rates and product quality.

Implementation Method 1

a liquid supply system for supplying a heating liquid having a regulated temperature and a cooling liquid having a regulated temperature into the pad contact member

Methodology Applied
Scientific EffectHeat transfer: Conduction (thermal)

Implementation Method 2

the controller controls the flow rates of the heating liquid and the cooling liquid supplied into the pad contact member

Methodology Applied
Scientific EffectThermal convection: Convection

Data Source

PatentUS11919124B2Pad-temperature regulating apparatus, method of regulating pad-temperature, polishing apparatus, and polishing system
Publication Date: 2024.03.05 EBARA CORP
  • US11919124B2 patent drawing
  • US11919124B2 patent drawing
  • US11919124B2 patent drawing

AI summary

The present application relates to a pad-temperature regulating apparatus for regulating a temperature of a surface of a polishing pad. The pad-temperature regulating apparatus includes a pad-contact member, a supply system for supplying a heating liquid and a cooling liquid into the pad contact member, a pad-temperature measuring device for measuring the temperature of the surface of the polishing pad, and a controller for performing a PID control of manipulated variables of a first flow control valve and a second flow control valve. The controller includes a memory in which a learned model constructed to maintain a temperature behavior curve, created based on measured values of the pad-temperature measuring device, within a predetermined allowable range, is stored; and a processing device which inputs at least one temperature behavior parameter to the learned model, and performs a calculation to output a change value of PID parameter for the PID control.