Catalyst Deterioration Detection Using Machine Learning Maps

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing catalyst deterioration detection methods deviate the air-fuel ratio from optimal values for extended periods, leading to increased deviation and reduced purification performance, and require manual association of data, which is time-consuming and inefficient.

Innovation Solution

A catalyst deterioration detection device using machine learning-based map data to calculate the deterioration level of a catalyst by analyzing time series data of excess fuel and downstream air-fuel ratio sensor values without deviating the air-fuel ratio, allowing for accurate detection with reduced computational load and man-hours.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If the air-fuel ratio is deviated from optimal values for extended periods to detect catalyst deterioration, then the deterioration detection capability is improved, but the purification performance deteriorates and the deviation accumulation increases

Engineering Contradiction:

Improvecatalyst deterioration detection capabilityVSAvoidpurification performance

Core Design Contradiction:

Measurement precisionVSReliability

Solution Approach 1:

The system performs preliminary calculations using pre-stored map data that contains the relationship between excess air-fuel ratio and downstream sensor responses. By having this reference data prepared in advance, the system can detect catalyst deterioration without needing to deviate the air-fuel ratio from optimal values, thus maintaining purification performance while achieving accurate detection.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The invention introduces map data as an intermediary element that mediates between the upstream and downstream air-fuel ratio sensors. This map data stores the characteristic relationships in advance, allowing the system to detect catalyst deterioration by comparing actual sensor responses against the stored reference data, eliminating the need for aggressive air-fuel ratio deviations.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If manual association of detection data is performed to calculate deterioration level, then the detection accuracy can be maintained, but the time consumption and labor requirements increase significantly

Engineering Contradiction:

Improvedeterioration level detection accuracyVSAvoiddata processing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system implements self-service by automatically performing the deterioration level calculation through a dedicated calculation unit that processes sensor data and compares it against stored map data. This automated process eliminates the need for manual data association and calculation, significantly reducing time consumption and labor requirements while maintaining detection accuracy.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The invention replaces the manual mechanical process of data association and calculation with an automated electronic calculation system. The calculation unit electronically processes sensor signals and performs comparisons with stored reference data, substituting manual operations with automated computational processes that are both faster and more accurate.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Measurement precision

If the air-fuel ratio deviation amount is increased to improve detection sensitivity, then the detection capability is enhanced, but the accumulation of deviation from appropriate composition amount increases

Engineering Contradiction:

Improvedetection sensitivityVSAvoiddeviation accumulation

Core Design Contradiction:

Measurement precisionVSObject-generated harmful factors

Solution Approach 1:

The system uses partial action by utilizing normal operational air-fuel ratio variations rather than excessive deviations. The map data captures the relationship between moderate excess air-fuel ratios and downstream sensor responses, allowing detection sensitivity to be achieved through normal operating conditions rather than extreme deviations that would cause harmful accumulation.

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS11473477B2Catalyst deterioration detection device, catalyst deterioration detection system, data analysis device, control device of internal combustion engine, and method for providing state information of used vehicle

Publication Date: 2022.10.18 TOYOTA JIDOSHA KK

AI summary

A catalyst deterioration detection device is provided to detect deterioration of a catalyst provided in an exhaust passage of an internal combustion engine. The catalyst deterioration detection device includes a storage device and processing circuitry. The storage device stores map data specifying a mapping that uses time series data of an excess amount variable in a first predetermined period and time series data of a downstream detection variable in a second predetermined period as inputs to output a deterioration level variable. The processing circuitry executes an acquisition process that acquires data, a deterioration level variable calculation process that calculates a deterioration level variable of the catalyst based on an output of the mapping using the data acquired by the acquisition process as an input. The map data includes data that is learned through machine learning.