Power Supply Mode Control Using Neural Network Prediction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional power supplies face inefficiencies in active mode due to power losses and risks in bypass mode from providing unsuitable power, necessitating improved mode control for balancing efficiency and component safety.

Innovation Solution

A power supply mode control system using a trained neural network to predict incoming power characteristics, selecting between active and bypass modes based on historical data, weather, grid conditions, and load parameters, ensuring efficient operation while safeguarding downstream components.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If active mode is used to condition incoming power, then power quality and safety are improved, but energy efficiency deteriorates due to power losses

Engineering Contradiction:

Improvepower qualityVSAvoidpower losses

Core Design Contradiction:

ReliabilityVSLoss of energy

Solution Approach 1:

The power supply dynamically switches between active mode and bypass mode based on real-time power quality assessment. The system uses detection electronics to monitor incoming power characteristics and adaptively selects the operational mode, transitioning from static to dynamic operation to optimize both efficiency and safety.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system changes operational parameters by switching between two distinct modes: active mode with full power conditioning when power quality is poor, and bypass mode with minimal conditioning when power quality is acceptable. This parameter change approach allows the system to optimize efficiency without compromising safety.

Inventive Principle:

Principle #35Parameter changes

2Loss of energy

If bypass mode is used to circumvent power conditioning, then energy efficiency is improved, but power safety deteriorates due to risk of damaging downstream components

Engineering Contradiction:

Improvepower lossesVSAvoidpower safety

Core Design Contradiction:

Loss of energyVSReliability

Solution Approach 1:

The system performs preliminary detection and assessment of incoming power quality before selecting the operational mode. The detection electronics evaluate power characteristics in advance, ensuring that bypass mode is only selected when power quality is confirmed to be acceptable, thereby preventing downstream component damage.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements continuous feedback monitoring of incoming power quality parameters. Based on this feedback, the control logic dynamically adjusts the operational mode selection, switching from bypass to active mode when power quality deteriorates, thus maintaining power safety while optimizing efficiency.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS10879732B2Power supply mode selection

Publication Date: 2020.12.29 MICROSOFT TECHNOLOGY LICENSING LLC

AI summary

A system includes operation of a trained neural network to output a first signal indicative of one or more characteristics of a power signal based on an input plurality of power-related conditions data, determination of a first power supply mode based on the first signal, and control of a power supply to operate in the first power supply mode.