NAND Flash Bus Parameter Training Using a Genetic Algorithm

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The reliability of data transmission on the bus of a NAND flash memory is reduced due to changes in ambient temperature, leading to increased error bits and affecting read and write performance.

Innovation Solution

An operation method for a memory controller that uses a genetic algorithm to iteratively update control parameter sets for signal transmission, determining a target set with the greatest fitness based on the area of an eye diagram to adjust signal quality.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional parameter adjustment methods are used to adapt to ambient temperature changes, then signal quality can be maintained, but the adjustment time becomes excessively long

Engineering Contradiction:
Improvesignal transmission reliabilityVSAvoidparameter adjustment time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent pre-establishes multiple control parameter sets corresponding to different ambient temperature ranges before actual operation. When temperature changes occur, the system can directly select the pre-prepared parameter set matching the current temperature range, eliminating the need for time-consuming real-time adjustment and iteration.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent implements dynamic parameter selection based on real-time ambient temperature detection. The system continuously monitors temperature and automatically switches between different control parameter sets according to the detected temperature range, enabling adaptive adjustment without manual intervention or lengthy optimization processes.

Inventive Principle:
Principle #15Dynamics

2Reliability

If control parameters are adjusted to maintain signal quality under varying temperature conditions, then transmission reliability improves, but system complexity increases

Engineering Contradiction:
Improvedata transmission reliabilityVSAvoidparameter management complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent segments the control parameters into multiple independent parameter sets, each optimized for specific ambient temperature ranges. This segmentation allows the system to manage complexity by handling only the relevant parameter set for the current temperature condition, rather than managing all parameters simultaneously across all temperature ranges.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent changes the approach from continuously tuning parameters to selecting from discrete, pre-optimized parameter sets. Each parameter set contains specific configurations tailored to particular temperature ranges, simplifying the management process by transforming a continuous optimization problem into a discrete selection problem based on temperature thresholds.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP4657267A1Operation method for storage controller, and storage controller and storage system
Publication Date: 2025.12.03 YANGTZE MEMORY TECH CO LTD
  • EP4657267A1 patent drawingFigure 1
  • EP4657267A1 patent drawingFigure 2
  • EP4657267A1 patent drawingFigure 3

AI summary

The present disclosure provides an operation method of a memory controller, a memory controller and a memory system, which relate to the field of memory technologies and are intended to improve the problem such as a long time required to adjust control parameters related to signal quality of a bus of a NAND flash memory. The method includes: in response to the processor receiving a training instruction, generating a plurality of control parameter sets randomly, the control parameter sets being used to adjust a size of an eye diagram for signal transmission between the memory controller and the memory; determining fitness of the plurality of control parameter sets; updating the plurality of control parameter sets iteratively using a genetic algorithm until an iteration stop condition is satisfied; and after the iteration is stopped, determining, as a target control parameter set, a control parameter set with the greatest fitness among the plurality of control parameter sets obtained in the latest iterative update.