ML-Controlled Environmental Subsystem for Photoconductive Image Plate Lifespan

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Liquid electrophotography (LEP) printing devices face issues with the premature failure of the photoconductive image plate (PIP), leading to print defects and reduced productivity, primarily due to temperature fluctuations affecting its lifespan.

Innovation Solution

A machine learning model is employed to control the environmental subsystem parameters of the printing device, such as heat exchangers, blowers, and humidifiers, based on measured characteristics like temperature, humidity, and printing conditions, to maintain a stable PIP temperature and extend its lifespan.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If the environmental subsystem parameters are controlled using traditional methods, then the printing device can operate, but the PIP temperature fluctuates causing premature failure

Engineering Contradiction:

ImprovePIP lifespanVSAvoidPIP temperature stability

Core Design Contradiction:

ReliabilityVSTemperature

Solution Approach 1:

The patent implements a feedback control system where sensors continuously monitor PIP temperature and environmental conditions, and the machine learning model adjusts environmental subsystem parameters (heat exchanger speed, blower operation, humidifier settings) in real-time based on this feedback to maintain optimal PIP temperature and extend lifespan

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system dynamically changes operational parameters of the environmental subsystem (heat exchanger speeds, blower rates, humidifier levels) based on machine learning model predictions and sensor readings to optimize PIP temperature control and prevent premature failure

Inventive Principle:

Principle #35Parameter changes

2Reliability

If a machine learning model is used to control environmental subsystem parameters, then PIP lifespan is maximized, but the device complexity increases

Engineering Contradiction:

ImprovePIP lifespanVSAvoidcontrol system complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The machine learning model operates autonomously to control environmental subsystem parameters, using sensor data to automatically adjust heat exchanger speeds, blower operation, and humidifier settings without requiring manual intervention or complex external control systems

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces traditional mechanical control systems with a machine learning-based control architecture that uses computational algorithms to predict optimal environmental parameters and automatically adjust subsystem operations, reducing mechanical complexity while improving PIP lifespan

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Duration of action of stationary object

If PIP temperature is stabilized to extend lifespan, then replaceable item lifespan is maximized, but energy consumption increases

Engineering Contradiction:

ImprovePIP lifespanVSAvoidenvironmental subsystem energy consumption

Core Design Contradiction:

Duration of action of stationary objectVSUse of energy by stationary object

Solution Approach 1:

The machine learning model applies partial action by adjusting environmental subsystem parameters only to the extent necessary to maintain PIP temperature within optimal ranges, rather than continuously maximizing cooling or heating, thereby extending PIP lifespan while minimizing energy consumption

Inventive Principle:

Principle #16Partial or excessive action

Solution Approach 2:

The system uses periodic sensing and control adjustments, where sensors monitor PIP temperature at intervals and the machine learning model makes discrete parameter adjustments to environmental subsystem components, balancing temperature stabilization with energy efficiency

Inventive Principle:

Principle #19Periodic action

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 maximizes the lifespan of the PIP by optimizing environmental conditions, thereby improving print quality and reducing the frequency of replacements, enhancing the overall productivity of the printing device.

Implementation Method 1

A machine learning model is employed to control the environmental subsystem parameters of the printing device, such as heat exchangers

Methodology Applied

Scientific EffectHeat exchange: Heat Exchanger

Implementation Method 2

A machine learning model is employed to control the environmental subsystem parameters of the printing device, such as heat exchangers, blowers, and humidifiers

Methodology Applied

Scientific EffectForced convection: Forced Convection

Data Source

PatentUS11774895B2Printing device parameter control using machine learning model, in order to maximize replaceable item lifespan

Publication Date: 2023.10.03 HEWLETT PACKARD DEVELOPMENT COMPANY LP

AI summary

A printing device includes a printing engine to selectively output print material, a replaceable item of the printing engine, and a subsystem for the printing engine. A machine learning model is used to control controllable parameters of the subsystem for the printing engine, based on physical characteristic measurements of the printing device, to maximize a lifespan of the replaceable item.