Internal-combustion engines – Charge forming device – Including cylinder pressure or temperature responsive means
Reexamination Certificate
2002-10-31
2004-10-19
Kwon, John (Department: 3747)
Internal-combustion engines
Charge forming device
Including cylinder pressure or temperature responsive means
C701S106000, C073S035080, C123S406220, C123S406410
Reexamination Certificate
active
06805099
ABSTRACT:
TECHNICAL FIELD
This invention pertains generally to internal combustion engine control systems, and more specifically to real-time digital signal processing for engine control and diagnostics.
INCORPORATION BY REFERENCE
Applicant incorporates by reference U.S. Pat. No. 6,367,462, entitled Engine Torque Management Method with High Dilution EGR Control, issued to McKay, et al., in that the method for engine torque management need not be fully described in detail herein.
BACKGROUND OF THE INVENTION
There is a need to be able to effectively collect and analyze data related to combustion characteristics of an internal combustion engine and to control the engine based upon that data. Current engine control systems use exhaust gas sensors, primarily oxygen sensors, to provide feedback about the overall combustion operation of the engine. Other feedback devices that have been proposed for engine control systems include in-cylinder pressure sensors and in-cylinder temperature sensors
A combustion quality measurement technique utilizing flame ionization detection wherein a spark plug is also used as a sensor has been in production for some time. The ionization signal is a measure of changes in electrical conductivity of a combustion flame front that is created in a cylinder during each combustion cycle. As shown in
FIG. 4
, information that is gleaned from an ionization signal includes location of a peak combustion pressure, air to fuel ratio, or percentage of mass fraction burned. Present versions of the sensor and measurement system are currently used for control and diagnostic purposes. These systems include detection and control of charge pre-ignition or ‘knock’, detection of engine misfire, and control of cam phasing systems.
The ability to use an ionization signal for engine control is limited by the ability to glean critical signal features from the signal. Fluctuations in the ionization signal caused by variations within an engine, engine to engine variations, and external factors have made more complete interpretation and utilization of the ionization signal difficult. Variations within an engine that affect the combustion process include engine operating temperature, cylinder-to-cylinder maldistribution of air, fuel, and EGR, spark timing and energy, and the age and level of deterioration of the components, among others. Variations between engines that affect the combustion process, and hence the ionization current, include part-to-part differences, vehicle application differences, and operator usage differences, and component age. Variations in external factors that affect the combustion process include in-use fuel type, use of fuel additives, ambient air humidity, ambient temperature, and elevation. These factors, among others, make it difficult to perform a straightforward interpretation of an ionization signal created as an output of the combustion process.
The prior art has been unable to accomplish demonstrable advanced engine control and engine diagnostic capability using information from an ionization signal. The prior art has been unable to provide real-time signal processing that leads to information related to critical signal features such as the location of peak pressure, air to fuel ratio, or percentage of mass fraction burned, when measured over a wide range of engine operating conditions. The prior art has not been robust to changes in conditions that affect measured engine operating conditions, including external conditions such as fuel quality and ambient temperature. The prior art also has not been robust to changes in operating conditions such as engine operating temperature and variations in in-cylinder temperatures.
There is a need to be able to more completely determine combustion characteristics from an ionization signal to make it useful as a system for combustion control. Conventional analytical methods have not provided a level of robustness necessary for mass production application of an ionization system. The prior art has attempted to solve the problem using artificial neural networks (ANN) for analytical interpretation of ionization signals. A properly trained ANN-based ionization sensor and system has been shown to be able to accommodate combustion fluctuations. A comprehensive training of the ANN that covered a broad range of possible engine operating conditions has enhanced performance of an engine control system. A limitation of artificial intelligence is that an ANN device only knows what it was taught; it can not extrapolate beyond the range of its training, nor can it perform any better than it was taught during training. Training of the ANN also consumes time both to collect appropriate data sets for training, and to train so that it can acquire effective coefficients and biases for internal equations. The ANN also takes an amount of time to process the input array and provide an output. An ANN works effectively only if the pre-production algorithm formulation and ANN training resulted from an experimental data set representing all future engine operating conditions. In practice, this might be impossible or at least extremely time and resource consuming. A reasonable solution can instead include a limited training with well chosen, most-representative sets of operating conditions. This can be combined with a fuzzy logic block that overrules unusual sensor readings to control an engine.
The prior art has implemented ANN using a dedicated digital signal processing (DSP) electronic chip implemented in the controller, as well as using algorithms. Dedicated ANN DSP chips can be costly, and are generally dedicated to a specific application, which limits the flexibility of the device, and makes the operating characteristics of the ANN difficult to change.
The prior art has also sought to use statistical analysis tools such as principal component analysis (PCA). The PCA method generates a new set of input vector components from a linear combination of original vector components. All the new components are orthogonal to each other so there is no redundant information. However, it is commonplace for the sum of the variances of the first few new components to almost match the total variance of the components of the original vector. The PCA method entails the need to collect and process massive amounts of data to extract useful information from the input signal. The PCA method requires acquisition of a large quantity of data (vector array of 123 input elements in one case), and takes an extended amount of time to reduce to a useful signal. This limits the throughput of the controller, and therefore the dynamic range over which the method is used to control a system.
Accordingly, a need exists for a more complete method to analyze the input from an ionization signal, to extract critical signal features from the ionization signal, to determine combustion characteristics from the critical signal features, and to control an internal combustion engine over a wide range of operating conditions, using the combustion characteristics. There is a further need to have data acquisition hardware and a controller that are flexible and meet the requirements for an automotive microprocessor system. Implementation of an engine control system that determines a combustion characteristic based upon an ionization signal can offer improvements in engine control and diagnostics, including an ability to extract critical signal features including a location of peak cylinder pressure, air/fuel ratio, and EGR dilution fraction, among others. A system that analyzes input from an ionization signal obtained through an in-cylinder plug can be used to reduce engine development and calibration time as well as provide opportunities to remove or redesign components such as knock sensors, exhaust gas sensors, cam sensors, and others.
SUMMARY OF THE INVENTION
The present invention provides an improvement over conventional engine controls in that it provides a method and apparatus for real-time measurement of combustion characteristics of each combustion event in each individual cylind
Baker Michael Edward
Malaczynski Gerard Wladyslaw
Delphi Technologies Inc.
Funke Jimmy L..
Kwon John
LandOfFree
Wavelet-based artificial neural net combustion sensing does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Wavelet-based artificial neural net combustion sensing, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Wavelet-based artificial neural net combustion sensing will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3284186