Data processing: vehicles – navigation – and relative location – Vehicle control – guidance – operation – or indication – With indicator or control of power plant
Reexamination Certificate
1999-06-02
2002-06-11
Wolfe, Willis R. (Department: 3747)
Data processing: vehicles, navigation, and relative location
Vehicle control, guidance, operation, or indication
With indicator or control of power plant
C701S104000, C701S109000, C701S102000, C706S027000, C706S031000
Reexamination Certificate
active
06405122
ABSTRACT:
BACKGROUND OF THE INVENTION
1. Field of the Invention
The invention relates to a method for estimating the data for controlling a controlled plant such as an internal combustion engine.
2. Description of the Related Art
A Fuzzy Neural Network (INN), formed by combining a fizzy inference system and a neural network, possess the advantages of both a fuzzy inference system and a neural network. The fuzz inference system allows linguistically descriptive algorithms including obscurity, such as decisions by humans, using if-then type fuzzy rules. The neural network allows regulating an input-output relationship by updating coupling coefficients using a learning function.
The FNN allows, for example, modifying the shape of a membership function by using a learning method such as a back propagation method, wherein a membership function in the first-half portion of a fuzzy inference system is constructed using, for example, a sigmoid function; and the central value and the slope of the membership function of the first-half portion, as well as output of fuzzy rules, are made to correspond to weighting values for coupling in a neural network. When the number of fuzzy rules is too small, errors in output become large. On the other hand, when the number of fuzzy rules is too high, the probability of outputting appropriate values for inputs other than teacher data is reduced (decreased adaptability).
In a FNN, antecedent membership functions of the fuzzy reasoning set are realized with various functions including the sigmoidal function. Each membership function typically includes a center position, a slope, and outputs of fuzzy rules corresponding to coupling weights for the neural network. During training, the configurations of the membership functions are modified using learning methods such as back-propagation.
Because it can learn, the FNN can optimize output information even when the input information is incomplete, unobservable, or estimated. In these instances, selection of the appropriate inputs to achieve optimization of the desired outputs depends on the designer of the FNN. In other words, the designer typically selects the most suitable input information based on a presumption of the desired output information and the expected operating conditions.
For example, in a control system for an internal combustion engine, some desirable input quantities are either too expensive or too difficult to measure economically. One such quantity is the volume of airflow into the engine (i.e., the volume of the intake air charge to the cylinders). Measuring the input airflow usually requires an expensive sensor known as an airflow meter. Another such quantity is the adhesion rate of the fuel that adheres on internal walls of intake manifolds or the like. Another such quantity is the evaporation speed of the adhered fuel.
Control of an engine is generally practiced by using a plurality of sensors to detect the operating state of the engine. Typical sensor data includes the engine revolution speed, engine temperature, etc. The data collected by the sensors is provided as inputs to (control parameters) to engine control system.
There are various types of data relating to the operating state of the engine that can be used as control parameters. However, in many cases, not all of the data needed by the control system can be easily (or inexpensively) detected by the engine sensors. In some cases, the desired sensors are too expensive, too delicate, too unreliable etc. Moreover, in some cases too many sensors may be needed in order to sense every type of data desired for use as a control parameter.
For example, airflow meters and heat wire anemometers used for detecting the intake airflow rate are expensive, large, and vulnerable to salt damage; and therefore cannot be mounted on outboard motors. As another example, there is no inexpensive sensor capable of measuring the rate of fuel that is injected into the intake manifold by a fuel injector; and there is there is no inexpensive sensor capable of measuring the evaporation speed of fuel adhering to the walls of the intake manifold. While the torque variation produced by an engine can be measured using a torque sensor attached to the crankshaft of the engine, such a torque sensor is generally too expensive and too large to be a commercially useful item. While the combustion chamber temperature can be measured with a special thermometer in a laboratory, there is no sensor that is so small, inexpensive, and durable that it can be mounted on individual engines sold to consumers. Furthermore, while the intake manifold wall temperature can be measured by installing a sensor in the intake manifold, the temperature profile of the intake manifold changes according to the operating state of the engine, and the desired location for the intake manifold sensor changes with the operating state. Thus, to cover all operating states, several sensors are typically needed at various locations on the intake manifold.
While a sensor capable of detecting the exhaust air-fuel (A/F) ratio is available, it is expensive and prone to failure. Moreover, there is no simple, inexpensive sensor for measuring the A/F ratio near the ignition point of the sparkplug. A sensor for measuring the amount of NO
x
contained in the exhaust gas in a catalytic converter exists, but the sensor is large and expensive.
Finally, while it is desirable to optimizing engine performance to meet the expectations of a user (e.g., a driver), there is no sensor that can directly detect the state of the user. Therefore, the user must typically record his or her feelings for later use in evaluating and optimizing the performance of the engine. Clearly, it is difficult to control individual vehicles based on such sensory evaluation values, especially when real-time control is desired.
SUMMARY OF THE INVENTION
The present invention solves these and other problems by providing a method and apparatus for optimizing a FNN whereby input information, and combinations thereof, that are most useful for computing a desired control output are selected. In one embodiment, a FNN calculation process for fuzzy reasoning values includes a neural network structure. Output parameters are identified and computed by fuzzy reasoning using the neural network. An adjustment of fuzzy rules and/or membership functions is provided by a learning process. The learning process includes selecting candidate input data types (e.g. selecting sensors) that can provide input data for the fuzzy neural network. The input data is categorized and coded into chromosomes (individuals) for use by a genetic algorithm. The genetic algorithm is used to optimize the chromosomes, by evolving and selecting the individuals (chromosomes) that specify the number(s) and type(s) of input data for the FNN so as to optimize the operation of a controller that uses the FNN.
In one embodiment, the optimization method for the FNN also includes coding the coupling load corresponding to the FNN membership functions into the chromosomes, and evolving these individuals with the genetic algorithm using a desired fitness function.
In one embodiment, the optimized FNN is employed for control of an Internal Combustion Engine (ICE), and the candidate input data types include data relating to operation of the engine.
In one embodiment, the input “candidate” data types include an intake pressure. In one embodiment, the FNN output data includes an engine air intake volume. In one embodiment, the input candidate data types include a combustion chamber pressure, an engine speed (i.e. revolutions per minute), a fluctuation of the engine speed, and/or an air intake volume. In one embodiment, control output data includes torque fluctuations of the engine. In one embodiment, the candidate input data types include an intake manifold wall temperature, an ambient temperature of the intake manifold, and/or elapsed time from engine start. In one embodiment, output data includes a combustion chamber temperature of the engine.
In one embodiment, candidate input data includes an engine co
Knobbe Martens Olson & Bear LLP
Vo Hien T.
Wolfe Willis R.
Yamaha Hatsudoki Kabushiki Kaisha
LandOfFree
Method and apparatus for estimating data for engine control does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method and apparatus for estimating data for engine control, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and apparatus for estimating data for engine control will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2935488