Inferred Engine Local Temperature Estimator Using Neural Network
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing engine temperature measurement systems, particularly those using hardware sensors, fail to accurately capture local metal temperatures in regions like the exhaust valve bridge of a cylinder head, leading to suboptimal thermal management and energy wastage, as they often rely on bulk temperature measurements that do not account for localized hotspots.
Innovation Solution
A method and system that utilize a trained neural network model to infer local metal temperatures in the exhaust valve bridge, allowing the coolant pump to operate independently of engine speed and adjust parameters based on these estimates, thereby optimizing thermal management by comparing local temperatures to bulk temperatures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If hardware sensors are used to measure temperature in the exhaust valve bridge region, then measurement precision is improved, but device complexity and manufacturing cost increase due to packaging difficulties in the engine compartment
Solution Approach 1:
The patent uses web sensors as intermediary elements positioned in the exhaust bridge region to indirectly measure local temperatures. These web sensors act as mediators between the combustion chamber environment and the measurement system, allowing temperature estimation without direct sensor placement in the harsh exhaust valve bridge region. This resolves the contradiction by providing measurement capability while avoiding the packaging and robustness issues of direct sensor installation.
2Device complexity
If bulk temperature measurements are used, then device complexity is reduced, but measurement precision deteriorates as bulk temperature does not capture local hotspots
Solution Approach 1:
The patent segments the temperature measurement function by using multiple web sensors positioned at different locations (inlet valve bridge, outlet valve bridge, exhaust valve bridge) to capture local temperature variations. This segmentation allows the system to obtain localized temperature data without implementing a complex direct sensor array in the combustion chamber, thereby achieving improved measurement precision while maintaining relative system simplicity.
Solution Approach 2:
Web sensors serve as intermediary measurement elements that can be positioned in the exhaust bridge region to capture local temperature information. These intermediaries provide a practical solution for obtaining localized temperature data without requiring direct sensor placement in the most harsh thermal environment, thus improving measurement precision while avoiding excessive device complexity.
3Measurement precision
If direct sensor placement in the exhaust valve bridge region is implemented, then measurement precision is improved, but reliability decreases due to sensor robustness issues in harsh environments
Solution Approach 1:
The patent employs web sensors as intermediary measurement devices positioned in the exhaust bridge region rather than direct contact sensors. These web sensors are less susceptible to the harsh thermal and mechanical environment, thereby maintaining measurement precision while significantly improving reliability and reducing concerns about sensor degradation over time.
4Reliability
If conservative conditional controls are enforced for thermal management, then reliability is improved, but productivity decreases due to restricted flow device operation
Solution Approach 1:
The patent implements a feedback-based thermal management system that continuously monitors local temperatures via web sensors and adjusts coolant flow accordingly. This feedback mechanism allows the system to operate reliably by responding to actual temperature conditions rather than following conservative fixed rules, thereby improving productivity by optimizing coolant flow efficiency while maintaining thermal safety.
Solution Approach 2:
The patent employs dynamic control of coolant flow devices based on real-time temperature measurements from web sensors. This dynamic approach allows the system to adapt coolant flow rates to actual thermal conditions, improving productivity by avoiding unnecessarily conservative restrictions while maintaining reliability through continuous monitoring and adjustment.
Data Source
AI summary
A system and methods for inferring a local engine temperature based on various engine conditions input to a dynamic model are disclosed. In the example system provided, an inferential temperature sensor uses a trainable model to estimate a local metal temperature in an exhaust valve bridge of a cylinder head which thereby allows closed loop control of a coolant flow device independent from engine speed, engine state, coolant flow state or system temperature. In response to estimated local metal temperatures, the methods described further allow thermal management of the engine system to be optimized.