On-Chip Voltage Classification for Automatic Slew Rate Adjustment

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing integrated circuit devices require manual adjustment of slew rates, which is inconvenient due to the need for large oscilloscopes and human intervention after the inference stage of machine-learning circuits, limiting efficiency and convenience.

Innovation Solution

An integrated circuit device with a measurement circuit and a classifier circuit that acquires practical voltage, compares it to a default voltage, updates the default voltage to a learned voltage using a neural network, and adjusts the slew rate based on this learned voltage, eliminating the need for human intervention.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual adjustment of slew rates is used, then measurement and control can be performed, but the process requires large oscilloscopes and human intervention, reducing convenience and efficiency

Engineering Contradiction:

Improvevoltage measurement capabilityVSAvoidconvenience of slew rate adjustment

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

The system uses an on-chip measurement circuit to automatically measure voltage and a machine-learning circuit to automatically adjust slew rate without requiring external oscilloscopes or human intervention. The measurement circuit captures voltage data, the machine-learning circuit processes this data to determine optimal slew rate settings, and applies adjustments automatically, making the system self-sufficient.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical/manual adjustment process with an automated electronic system. Instead of manually operating oscilloscopes and adjusting controls, the system uses electronic measurement circuits integrated on-chip and machine-learning-based automatic control algorithms to perform voltage measurement and slew rate adjustment, eliminating the need for manual mechanical operations.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If manual adjustment of slew rates is used, then voltage measurement can be performed, but human intervention is required after the inference stage, limiting efficiency

Engineering Contradiction:

Improvepractical voltage measurementVSAvoidefficiency of slew rate adjustment process

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The measurement circuit automatically captures voltage data from the signal, and the machine-learning circuit autonomously processes this data through inference to determine optimal slew rate settings. The entire process from measurement to adjustment is self-executing without requiring human intervention at any stage, including after inference, thereby maximizing productivity.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system establishes a continuous automated loop where the measurement circuit continuously monitors voltage, the machine-learning circuit continuously processes the data and generates control decisions, and the slew rate adjustment is continuously applied. This continuous automated operation eliminates idle time and manual intervention delays, maintaining constant productive operation.

Inventive Principle:

Principle #20Continuity of useful action

3Extent of automation

If on-chip measurement circuit and machine-learning circuit are integrated, then automation is achieved, but device complexity increases

Engineering Contradiction:

Improveautomated slew rate adjustmentVSAvoidcircuit integration complexity

Core Design Contradiction:

Extent of automationVSDevice complexity

Solution Approach 1:

The patent integrates the measurement circuit and machine-learning circuit directly onto the same chip, merging previously separate functions (external oscilloscope measurement and manual control) into a unified on-chip system. This consolidation achieves full automation while managing complexity through integrated design rather than separate interconnected components.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The on-chip measurement circuit serves multiple functions: it measures voltage for machine-learning processing, provides feedback for automatic control, and enables various measurement modes. The machine-learning circuit also handles multiple tasks including data processing, inference, and control decision generation. This multi-functionality reduces the need for separate dedicated circuits, managing overall device complexity.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS10769553B2Integrated circuit device and circuitry

Publication Date: 2020.09.08 NAN YA TECH

AI summary

The present disclosure provides an integrated circuit (IC) device and a circuitry. The IC includes a measurement circuit and a classifier circuit. The measurement circuit is configured to acquire a practical voltage. The classifier circuit is configured to: generate an information on an immature classification by comparing a default voltage and the practical voltage; receive an information on a reference classification, wherein the reference classification is acquired by manually comparing the default voltage and the practical voltage; update the default voltage to a learned voltage based on the immature classification and the reference classification; and generate a prediction, based on the learned voltage, for adjusting a slew rate.