Engine State Determination Device Dynamic Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
High rotation speeds in internal combustion engines increase the calculation load on devices using hierarchical neural networks for misfire detection and state determination, leading to the need for high-performance and costly equipment.
Innovation Solution
A state determination device that reduces the calculation load by omitting part of the determination process when the crankshaft rotation speed exceeds a threshold, using mapping data learned through machine learning to determine the engine state and execute coping processes for air-fuel ratio imbalances and misfires.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the determination process is performed every time the crankshaft rotates by a specified angle using a hierarchical neural network model, then the detection accuracy of misfire and engine state is improved, but the calculation load on the execution device becomes excessively large when the crankshaft rotation speed is high
Solution Approach 1:
The patent applies dynamics by making the determination process frequency adjustable based on operating conditions. The execution device dynamically changes the frequency at which the determination process is executed according to the detected crankshaft rotation speed, transitioning from continuous determination at low speeds to reduced-frequency determination at high speeds, thus adapting the system behavior to current operational requirements
Solution Approach 2:
The patent changes the parameter of determination process frequency based on the crankshaft rotation speed parameter. When the rotation speed exceeds a predetermined threshold, the system modifies the frequency parameter to execute the determination process less frequently, thereby reducing the calculation load while maintaining acceptable detection accuracy through the learned mapping data
2Speed
If the determination process is executed continuously at high crankshaft rotation speeds, then the responsiveness of misfire detection is improved, but the need for high-performance and high-cost execution devices increases
Solution Approach 1:
The system dynamically adjusts the determination process frequency based on real-time detection of crankshaft rotation speed, allowing the execution device to operate at lower performance requirements during high-speed conditions by reducing the frequency of complex neural network calculations while maintaining responsiveness through strategic execution at critical moments
Solution Approach 2:
The patent uses mapping data that has been learned through machine learning to represent the complex relationships in the hierarchical neural network model. This learned mapping serves as a simplified copy or approximation that can be executed with lower computational demand while preserving the essential detection capabilities, thereby reducing the performance requirements for the execution device
Data Source
AI summary
Provided is a state determination device for an internal combustion engine. The state determination device includes a storage device, and an execution device. The storage device stores mapping data that is data defining a mapping that outputs a determination result of a state of the internal combustion engine, by using an internal combustion engine state variable as an input. The execution device executes an acquisition process of acquiring the internal combustion engine state variable each time a crankshaft rotates by a specified angle, and a determination process of determining the state of the internal combustion engine based on an output of the mapping using the internal combustion engine state variable as an input. The execution device omits a part of the determination process performed each time the crankshaft rotates by the specified angle when a rotation speed of the crankshaft becomes equal to or higher than a predetermined threshold.