AI Ignition Diagnostics for Hydrogen Engine Misfire Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional spark ignition systems struggle to maintain stable combustion processes in internal combustion engines using hydrogen fuel, leading to abnormal combustion events like preignitions and misfires, and detecting these events is challenging without costly in-cylinder pressure sensors.
Innovation Solution
An ignition diagnostic system using artificial intelligence (AI) with machine learning algorithms to correlate diagnostic signals from ignition coils with combustion-related parameters, predicting abnormal combustion events without the need for in-cylinder pressure sensors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional spark ignition systems are used in hydrogen internal combustion engines, then the engine can operate with hydrogen fuel, but stable combustion cannot be maintained under critical operating conditions leading to abnormal combustion events
Solution Approach 1:
The system performs preliminary diagnostics by monitoring ignition coil parameters (primary/secondary current, voltage, resistance, inductance) before abnormal combustion events occur. The AI model analyzes these parameters in advance to predict potential combustion instability and adjust ignition timing or energy delivery preemptively, preventing preignitions and misfires before they happen.
Solution Approach 2:
The system implements continuous feedback by monitoring ignition coil electrical parameters during operation and using AI-based combustion quality assessment to detect early signs of abnormal combustion. This feedback loop allows real-time adjustments to ignition system parameters to maintain stable combustion and prevent abnormal events under critical operating conditions.
2Measurement precision
If in-cylinder pressure sensors are used to detect abnormal combustion events, then detection accuracy is improved, but system cost and complexity increase
Solution Approach 1:
The system uses electrical parameters from the ignition coil (primary current, secondary current, voltage, resistance, inductance) as intermediary measurements to infer combustion quality. These electrical parameters serve as proxies that correlate with combustion events, allowing the system to detect abnormal combustion without direct mechanical pressure sensors in the cylinder.
Solution Approach 2:
The system replaces mechanical pressure sensors with electrical parameter monitoring and AI-based analysis. Instead of using mechanical devices to directly measure in-cylinder pressure, the system uses electrical field measurements from the ignition coil circuit and processes them through machine learning models to detect combustion abnormalities, thereby reducing mechanical complexity.
3Object-generated harmful factors
If hydrogen is used as fuel in internal combustion engines, then carbon emissions are eliminated and thermal efficiency is improved, but abnormal combustion events like preignitions and misfires increase
Solution Approach 1:
The system enables the ignition system to self-diagnose and self-adjust by monitoring its own electrical parameters (primary/secondary current, voltage, resistance, inductance) and using AI analysis to detect combustion quality. This self-service capability allows the system to maintain stable hydrogen combustion by automatically detecting and responding to abnormal combustion trends without external intervention.
Solution Approach 2:
The system dynamically adjusts ignition parameters based on AI analysis of electrical measurements. By changing ignition timing, energy delivery, or coil operating parameters in response to detected combustion quality trends, the system optimizes stable combustion of hydrogen while preventing abnormal events, thereby maintaining the emission benefits of hydrogen while improving combustion reliability.
Data Source
AI summary
An ignition diagnostic system and method for evaluating and optimizing the ignition performance of internal combustion engines (ICEs), such as those that burn hydrogen (H2) and/or other fuels. According to one example, the ignition diagnostic system and method use an artificial intelligence (AI) model with one or more machine learning (ML) algorithm(s) to identify, predict and/or otherwise evaluate abnormal combustion events, and to provide such information to an electronic control unit (ECU) in real-time. The ECU, in turn, can make combustion-related modifications to one or more components of the ignition system to optimize performance. By integrating the AI model into the ignition diagnostic system and method, a fast and simplified solution is provided that can be implemented across a wide variety of ICEs, including those that burn alternative fuels, where detecting abnormal combustion events and monitoring combustion-related parameters can be important.