Data processing: artificial intelligence – Fuzzy logic hardware – Fuzzy neural network
Reexamination Certificate
1998-01-26
2001-03-27
Powell, Mark R. (Department: 2762)
Data processing: artificial intelligence
Fuzzy logic hardware
Fuzzy neural network
C706S001000, C706S002000, C706S016000, C706S025000, C706S023000
Reexamination Certificate
active
06208981
ABSTRACT:
BACKGROUND OF THE INVENTION
1. Field of the Invention
The invention relates to a circuit configuration for controlling the engine or the drive system in a motor vehicle. The configuration includes a fuzzy system (10) in which sensor signals are evaluated and control signals for the engine or drive system are generated, wherein a drive situation is determined. Adaptive system components, particularly in the areas of running-gear and safety technology, as well as drive management, have become increasingly more important in the automobile industry. Specific equipment or systems in the vehicle, such as automatic transmissions, active suspension and level regulation, or power-steering assistance, are adjusted and controlled by adapting their settings to the respective driving situation.
2. Description of the Related Art
International publication WO 93/23689 describes a control system for shifting an automatic transmission on the basis of fuzzy logic methods. The system takes into account the drive power, fuel consumption, and the effort in setting shifting strategies. The control system thereby reacts to the driving style and the driving state. For this, it needs a relatively large number of different rule sets of fuzzy production rules, which reproduce the knowledge of a human expert and which thus all have to be prescribed by the developer of the control system. This entails considerable effort. In addition, human expert knowledge is also subject to uncertainties here.
SUMMARY OF THE INVENTION
It is accordingly an object of the invention to provide a circuit configuration for controlling a running-gear or drive system in a motor vehicle, which overcomes the above-mentioned disadvantages of the prior art devices and methods of this general type and which allows detecting the respective current driving situation of the motor vehicle, and which is able to learn in machine terms and thus also to elaborate and to improve nonlinear control rules independently.
With the foregoing and other objects in view there is provided, in accordance with the invention, a circuit configuration for controlling a system device in a motor vehicle, comprising:
a fuzzy system receiving sensor signals from the motor vehicle, the fuzzy system being programmed to evaluate the sensor signals, to determine a driving situation, to generate, during a driving operation of the motor vehicle, signals classifying a respective driving situation, and to generate driving-situation-dependent control signals for a system device in the motor vehicle;
a neural network connected to the fuzzy system, the neural network being programmed to evaluate the sensor signals and reference data from a recording of driving data of the motor vehicle, the neural network generating and optimizing the fuzzy system; and
a preprocessing circuit connected to the fuzzy system, the preprocessing circuit filtering and smoothing the sensor signals and/or control signals prior to an evaluation thereof in the fuzzy system, and wherein a linkage effects a dimensional reduction of the sensor signals.
In accordance with an added feature of the invention, a signal memory connected to the fuzzy system stores the sensor signals and/or the control signals prior to an evaluation thereof by the fuzzy system.
In accordance with an additional feature of the invention, a database storing video recordings of measurement trips taken by the motor vehicle is provided, and a reference data memory through which data contained in the database are delivered to the neural network.
In accordance with another feature of the invention, the neural network adapts a form and location of membership functions of input and output data, and a rule base of the fuzzy system.
In accordance with a further feature of the invention, the fuzzy system and the neural network have functionally equivalent, respective input and output behavior.
In accordance with a concomitant feature of the invention, the fuzzy system and the neural network each has a classification system, and the classification system of one is convertible into the classification system of the other by a correspondence-maintaining bidirectional transformation.
One advantage of the invention is that it provides a system for detecting the current driving situation in a motor vehicle. The classification system delivers statements about the current driving state in relation to driving dynamics, driving maneuvers and driver behavior, using various sensor data measured continuously in the motor vehicle. This information enables intelligent, time-adaptive, driving-situation-dependent control of various systems in the motor vehicle. The increasing use of such adaptive components in the areas of running-gear and drive systems is already becoming apparent at the present time, and will gain even greater significance in future vehicle generations, since in this way an increase in driving safety, economy and convenience may be achieved.
Further examples of adaptive vehicle systems, for which a driving-situation-dependent control can advantageously be used, are all-wheel steering systems, hybrid drives, so-called intelligent speed control systems and anti-slip control systems.
Other features which are considered as characteristic for the invention are set forth in the appended claims.
Although the invention is illustrated and described herein as embodied in a circuit configuration for controlling a running-gear or drive system in a motor vehicle, it is nevertheless not intended to be limited to the details shown, since various modifications and structural changes may be made therein without departing from the spirit of the invention and within the scope and range of equivalents of the claims.
The construction and method of operation of the invention, however, together with additional objects and advantages thereof will be best understood from the following description of specific embodiments when read in connection with the accompanying drawings.
REFERENCES:
patent: 5089963 (1992-02-01), Takahashi
patent: 5410477 (1995-04-01), Ishii
patent: 5687082 (1997-11-01), Rizzoni
patent: 5821412 (1998-10-01), Bryant et al.
patent: 5971747 (1999-10-01), Lemelson et al.
patent: 5993194 (1999-11-01), Lemelson et al.
patent: 42 09 150 A1 (1992-09-01), None
patent: 43 37 164 A1 (1994-05-01), None
patent: 06123706 (1994-05-01), None
Holzmann, H.; Halfmann, C.; Isermann, R., Representation of 3-D mappings for automotive control applications using neural networks and fuzzy logic, Control Applications, 1997., Proceedings of the 1997 IEEE International Conference on, Oct. 5-7, 1997, Pag.*
Harrison, G.A.; Taylor, F.J,. Gas turbine vibration analysis with fuzzy ART neural network, Neural Networks, 1999. IJCNN '99. International Joint Conference on, vol.: 6, Jul. 10-16, 1999 , pp. 4319-4323 vol 6.*
McNeil, A.R.; Sarkodie-Gyan, T., A neural network based recognition scheme for the classification of industrial components, Fuzzy Systems, 1995. International Joint Conference of the Fourth IEEE International Conference on Fuzzy Systems and The Second Int, Mar. 1995.*
Nishimori, K.; Hirakawa, S.; Hiraga, H.; Ishihara, N., Selection of fuzzy control rules using automatic tuning of membership functions, Fuzzy Information Processing Society Biannual Conference, 1984. Industrial Fuzzy Control and Intelligent Systems Confer, Jan. 1994.*
Ng, Kim C. et al., Multirobot Convoying Using Neuro-Fuzzy Control, Pattern Recognition, 1996, Proceedings of the 13th International Conference on vol.: 3, 1996, pp.: 417-421 vol, Jan. 1996.*
International Publication No. 93/23689 (Danz et al.), dated Nov. 25, 1993.
“Neuronal Nets: absolutely compatible in sample detection” (Kahler), Electronic vol. 10, 1991, pp. 98-104.
Graf Friedrich
Hauptmann Werner
Greenberg Laurence A.
Lerner Herbert L.
Powell Mark R.
Siemens Aktiengesellschaft
Starks Wilbert
LandOfFree
Circuit configuration for controlling a running-gear or... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Circuit configuration for controlling a running-gear or..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Circuit configuration for controlling a running-gear or... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2535518