Wavelet-based artificial neural net combustion sensing
Abstract
A method and apparatus for real-time measurement of combustion characteristics of each combustion event in each individual cylinder coupled with an ability to control the engine based upon the combustion characteristics are shown. The invention includes using selective sampling techniques and wavelet transforms to extract a critical signal feature from an ionization signal that is generated by an in-cylinder ion sensor, and then feeds that critical signal feature into an artificial neural network to determine a desired combustion characteristic of the combustion event. The desired combustion characteristic of the combustion event includes a location of peak pressure, an air/fuel ratio, or a percentage of mass-fraction burned, among others. The control system of the engine is then operable to control the engine based upon the combustion characteristic.
Claims
exact text as granted — not AI-modified1 . A method for controlling an internal combustion engine, comprising
determining a combustion characteristic of an individual combustion event of the engine by:
concurrently sampling an ionization signal and determining at least one engine operating parameter during a combustion event of the internal combustion engine, the at least one engine operating parameter including, but not limited to, an engine load, a spark advance, an amount of delivered fuel and a mass fraction of EGR delivered,
transforming the ionization signal with a wavelet filter,
extracting at least one critical signal feature from the ionization signal that has been transformed by the wavelet filter,
tuning the wavelet filter to the at least one critical signal feature, decomposing the ionization signal using the tuned wavelet filter, reconstructing the decomposed ionization signal,
processing the at least one critical signal feature reconstructed ionization signal and the at least one engine operating parameter through an artificial neural network; and
controlling the internal combustion engine based upon the combustion characteristic.
2 . The method of claim 1 , wherein determining a combustion characteristic of an individual combustion event of the engine occurs each combustion event.
3 . (Cancelled)
4 . The method of claim 1 , wherein concurrently sampling an ionization signal and at least one engine parameter during a combustion event of the internal combustion engine comprises sampling during a critical period of time after an ignition event.
5 . The method of claim 1 , wherein concurrently sampling an ionization signal and at least one engine parameter during a combustion event comprises using a sampling and processing scheduler to activate an analog data sampler during a time when the critical signal feature is present in the ionization signal.
6 . (Cancelled)
7 . A system to control an internal combustion engine, including at least one of a compression-ignition engine a spark-ignition engine, and a homogenous charge compression-ignition engine, the system comprising
a controller operably connected to:
at least one output device of the internal combustion engine, including engine torque,
at least one ion sensor operable to measure an ionization signal from a combustion event of the internal combustion engine, and
at least one engine sensor operable to measure at least one engine operating parameter;
wherein said controller is operable to:
concurrently sample an ionization signal using the at least one ion sensor and determine at least one engine operating parameter using the at least one engine sensor during a combustion event,
transform the ionization signal with a wavelet filter,
extract at least one critical signal feature from the ionization signal that has been transformed by the wavelet filter, and
process the at least one critical signal feature and the at least one engine operating parameter through an artificial neural network to determine at least one combustion characteristic of the engine; and
wherein the controller controls the engine torque based upon the at least one combustion characteristic of the engine.
8 . (Cancelled)
9 . (Cancelled)
10 . (Cancelled)
11 . (Cancelled)Join the waitlist — get patent alerts
Track US2005051136A1 — get alerts on status changes and closely related new filings.
We store only your email — no account needed. See our privacy policy.