Method and apparatus for intelligent ozone estimation and mitigation in a system with ion drag cooling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Information handling systems generate ozone as a byproduct of their ion emitter/collector cooling systems, which can exceed safe exposure limits, necessitating effective estimation and mitigation to ensure user safety and comfort, but existing methods rely on bulky and expensive ozone detectors.
Innovation Solution
An intelligent ozone estimation and mitigation system using a trained machine learning model that integrates sensors for power consumption, voltage, temperature, and humidity data to estimate ozone production and adjust the ion emitter/collector operation or fan speed to maintain safe ozone levels without the need for internal ozone detectors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Object-affected harmful factors
If ozone detectors are installed to monitor and control ozone levels, then user safety and comfort are improved, but device complexity and cost increase due to bulky and expensive detection hardware
Solution Approach 1:
The patent uses machine learning models as an intermediary between the ion emitter/collector cooling system and direct ozone detection. The ML models estimate ozone production based on operating parameters (voltage, current, temperature, humidity) rather than directly measuring ozone, thereby avoiding the need for bulky detection hardware while still enabling safety monitoring and control
Solution Approach 2:
The patent replaces the mechanical/physical ozone detection system with a computational approach using machine learning algorithms. Instead of using physical sensors to detect ozone molecules, the system uses software-based ML models that process operating parameter data to estimate ozone levels, eliminating the need for complex detection hardware
2Temperature
If ion emitter/collector cooling systems operate at high performance levels, then cooling effectiveness is improved, but ozone generation increases beyond safe exposure limits
Solution Approach 1:
The patent implements a feedback control system where machine learning models continuously estimate ozone production based on real-time operating parameters (voltage, current, temperature, humidity). When estimated ozone levels approach safety thresholds, the system adjusts operating conditions to reduce ozone generation while maintaining acceptable cooling performance, creating a closed-loop control mechanism
Solution Approach 2:
The patent dynamically adjusts operating parameters (voltage, current, fan speed) of the ion emitter/collector cooling system based on estimated ozone levels. By changing these parameters in real-time, the system can reduce ozone generation when necessary while maintaining cooling effectiveness, resolving the contradiction between high-performance operation and safe ozone levels
3Device complexity
If machine learning models are used to estimate ozone production, then the need for expensive ozone detectors is eliminated, but computational requirements and data processing complexity increase
Solution Approach 1:
The patent enables the cooling system to self-monitor and self-regulate ozone production using machine learning models that run on existing system hardware. The system uses its own operating parameter data (voltage, current, temperature, humidity) to estimate ozone levels and automatically adjusts its operation, eliminating the need for external detection hardware while maintaining autonomous safety control
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
Effectively reduces ozone levels within the system to safe thresholds, enhancing user safety and comfort while eliminating the need for costly ozone detection hardware, thereby improving the efficiency and cost-effectiveness of ozone management.
Implementation Method 1
an ion emitter and ion collector of an ion emitter/collector cooling system. The ion emitter may be operatively coupled to a power management unit (PMU) controller that controls an ionic driving circuit to provide a high voltage to the ion emitter. When this high voltage is applied to the ion emitter, ions are created.
Implementation Method 2
these ions may be repelled from the ion emitter towards the oppositely-charged ion collector to apply a shear force on the molecules in the atmosphere between the ion emitter and ion collector creating an airflow towards and through thermal fins of the ion collector
Implementation Method 3
During this operation, any number of ions may be created including, but not limited to, ozone (O3)
Data Source
AI summary
An information handling system includes a hardware processor, a memory device, and a PMU to provide power to the processor and memory device. The information handling system includes an ion emitter/collector cooling system including an ion emitter and an ion collector, the ion emitter to generate ions from the atmosphere and the ion collector to collect and deionize those ions, the creation of ions by the ion emitter creating an airflow through and out of the ion collector and at least one sensor to detect and measure at least one non-static ozone predictor measurement describing ozone production at the ion emitter/collector cooling system. Further, the processor executing code instructions of an intelligent ozone estimation and mitigation system including a trained ozone estimation machine learning model to use, as input, the non-static ozone predictor measurement and provide, as output, an ozone estimation value estimating the amount of ozone produced at the ion emitter.