AI Engine and ATS Calibration for Real-World Emissions Control

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional calibration methods for internal combustion engines and after-treatment systems in vehicles are resource-intensive and do not account for real driving conditions, leading to suboptimal performance over the vehicle's lifetime.

Innovation Solution

An AI-based calibration system that adjusts engine and after-treatment system parameters in real-time to optimize performance, using an AI model to predict and adjust engine and ATS control parameters for improved efficiency and emission reduction.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If conventional calibration methods are used, then initial engine and ATS performance can be optimized under ideal conditions, but the system cannot adapt to real driving conditions and component aging over the vehicle's lifetime

Engineering Contradiction:

Improvelong-term performance stabilityVSAvoidadaptability to real driving conditions

Core Design Contradiction:

ReliabilityVSAdaptability or versatility

Solution Approach 1:

The calibration system transitions from static conventional calibration to dynamic adaptive calibration. The AI model continuously monitors real-time operating conditions (temperature, pressure, flow rate, sensor readings) and adjusts engine and ATS control parameters dynamically, enabling the system to adapt to changing driving conditions and component aging throughout the vehicle's lifetime.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system implements a closed-loop feedback mechanism where sensor data from the vehicle (exhaust gas composition, temperature, pressure, flow rate) is continuously fed into the AI model. The model processes this feedback and generates optimized control parameter adjustments, which are then applied to the engine and ATS, creating a continuous adaptation cycle that maintains optimal performance over time.

Inventive Principle:

Principle #23Feedback

2Reliability

If conventional calibration methods are used, then initial optimization can be achieved, but extensive human resources, expensive instruments, and time are required for calibration

Engineering Contradiction:

Improveinitial optimization qualityVSAvoidcalibration efficiency

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The calibration system becomes self-service through automation. The AI model autonomously processes sensor data, determines optimal control parameter adjustments, and implements calibration without requiring expert human intervention. The system performs self-diagnosis and self-optimization, eliminating the need for expensive calibration instruments and reducing calibration time from days to minutes.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical/manual calibration process (requiring physical instruments and expert technicians) with an intelligent software-based system. The AI model substitutes human expertise and manual measurement processes with automated algorithms that analyze sensor data and compute optimization parameters, dramatically improving calibration productivity.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Use of energy by moving object

If conventional calibration is performed, then engine efficiency can be maximized initially, but the calibration does not account for sensor accuracy degradation and component aging

Engineering Contradiction:

Improvefuel efficiencyVSAvoidsensor accuracy over lifetime

Core Design Contradiction:

Use of energy by moving objectVSMeasurement precision

Solution Approach 1:

The AI model is pre-trained during development using comprehensive data that includes sensor drift and component aging characteristics. This preliminary training enables the model to anticipate and compensate for sensor accuracy degradation and component aging before they significantly impact performance. The system proactively adjusts calibration parameters to maintain fuel efficiency despite aging effects.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The continuous feedback loop monitors actual versus predicted performance metrics. When sensor readings deviate from expected values due to aging or drift, the AI model detects these anomalies and compensates by adjusting control parameters accordingly, maintaining accurate fuel efficiency optimization throughout the vehicle's lifetime despite sensor degradation.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS20260055738A1Adaptive artificial intelligence LED calibration strategy for internal combustion engine and exhaust aftertreatment system optimization

Publication Date: 2026.02.26 SAUDI ARABIAN OIL CO

AI summary

A method for optimizing a motor assembly that includes an engine and an after-treatment system (ATS). The method includes obtaining an artificial intelligence (AI) model configured to receive an operating point for the motor assembly, engine control parameters controlling the engine and independent ATS control parameters controlling the ATS. The method further includes obtaining a performance model configured to return a predicted performance score for the motor assembly based on the AI model. The method further includes obtaining a first operating point, configuring the performance model to return a first predicted performance score based on the AI model receiving the first operating point, and determining optimum engine control parameters and optimum ATS control parameters that optimize the first predicted performance score. The method further includes adjusting the engine control parameters and ATS control parameters based on the optimum engine control parameters and optimum ATS control parameters.