Data processing: artificial intelligence – Knowledge processing system
Patent
1997-12-29
2000-07-04
Hafiz, Tariq R.
Data processing: artificial intelligence
Knowledge processing system
706 46, 706 47, G06N 1700
Patent
active
06085183&
DESCRIPTION:
BRIEF SUMMARY
FIELD OF THE INVENTION
The present invention relates to an intelligent computerized control system for equipment in which technical or biological processes take place in a controlled manner, such as facilities for the production of goods or energy, communications facilities, etc., where the control system is designed to build on previously input knowledge to determine automatically, from the results of the processes taking place in such facilities, e.g., continuous manufacturing processes, work processes, etc., the respective status of the processes taking place in the facilities, and to give computer-generated instructions for achieving the objective of the process in a manner appropriate for the situation.
BACKGROUND INFORMATION
In industrial facilities, such as systems for manufacturing goods, power or for communication, etc., there has long been a demand for a control system that provides the best possible, automatic, intelligent management of the ongoing process in a reliable and inexpensive manner. There has also been a demand for an evolutionary self-improvement of the control system.
Control systems using so-called intelligent components are already known from the related art. For example, International Patent Application No. WO 93/08515 describes a control system for technical processes which works with knowledge-based control rules for selected process states. The control parameters for the other process states are formed in the apparatus using a continuous mathematical function that links knowledge-based control rules and thus creates control rules for all process states--in the manner of a non-linear interpolation. This conventional apparatus is not designed to act automatically in a controlled manner with regard to achieving a better process performance. The human operator's intelligence is still indispensable. This conventional apparatus does not provide for an evolutionary self-development of the intelligent components.
Another expert system is described in the article "The MODI expert system--a contribution toward reliable and cost-effective management of power plants, ABB Technik ABB Technology, 6/7 (1994) pages 38-46. This conventional system monitors the status of power plant processes by comparing characteristic features with a mathematical reference model and, when there are deviations from normal behavior, analyzing the causes. The plant-wide approach of this conventional expert system permits statements regarding the process as a whole, but automatic, self-optimizing process management is not possible with this expert system.
In addition, a computerized control system that uses models to automate the continuous casting of steel and monitors product quality is described in the article "Process optimization for maximum availability in continuous casting" in the journal Metallurgical Plant and Technology International, vol. 5 (1994) pages 52-58. This is accomplished using graphic plots, i.e., via a human-machine interface. This conventional control system likewise does not provide for automatic intelligent process control.
A control system described in European Patent Application No. 0 411 962 is provided specifically for continuous casting of steel and operates similarly. Here again, test runs in the plant provide the basis for the expert knowledge, which is used in the form of limit curves. There is no continuous or stepwise, automatic computerized optimization.
The systems described above, which work with intelligent components, do not achieve the quality of the object of the present invention.
SUMMARY OF THE INVENTION
An object of the present invention is to provide a control system which, as an intelligent system, permits the best possible, automatic, intelligent management of an ongoing process in a reliable and cost-effective manner while being capable of evolutionary self-improvement and being applicable to a wide range of facility types.
In particular, through conventional control technology or computer technology, partial processes that cannot be controlled especially w
REFERENCES:
patent: 4512747 (1985-04-01), Hitchens et al.
patent: 5161110 (1992-11-01), Dorchak
patent: 5179631 (1993-01-01), Guddanti et al.
patent: 5259066 (1993-11-01), Schmidt
patent: 5644686 (1997-07-01), Hekmaptour
patent: 5727127 (1998-03-01), Schulze Horn et al.
patent: 5787235 (1998-07-01), Smith et al.
patent: 5806056 (1998-09-01), Hekmatpour
patent: 5870768 (1999-02-01), Hekmatpour
Nowinski G: "Lernfahige Konnektionistische Structuren in der Automatisierungstechnik Connectionistic Structures with the ability of learning in automatic control", Automatisierungstechnik--AT, vol. 42, No. 11, Nov. 1, 1994, pp. A37-40, XP000483092. Translation of the International Search Report.
V. Rembold, "Methoden der Kunchenstlichen Intelligenz in der industriellen Fertigung", TR Technische Rundschau, 1992, pp. 66-71.
S. Kendra et al., "Intelligent Process Control with Supervisory Knowledge-Based Systems", IEEE Control Systems, Jun. 1994, pp. 37-47.
H. PreiBl et al., "Process optimization for maximum availability in continuous casting", der Zeitschrift Metallurgical Plant and Technology International, May 1994, pp. 52-58.
W.J. Leech: "A rule based process control method with feedback", Advances in Instrumentation, vol. 41, No. 1, 1986, Research Triangle Park US, pp. 169-175.
ABB Technik Jun./Jul. 1994, pp 38-46.
A. Varsek Et a.: "Genetic algorithms in controller design and tuning", IEEE Transactions on Systems, Man and Cybernetics, vol. 23, No. 5, 1993, New York US, pp. 1330-1339.
Centeno et al,"Databases and artificial intelligence: enabling technologies for simulation modeling", Proc. of the winter simulation conf., pp. 181-189, 1992.
Almanzor et al, "The model methodolgy, model specifications and development of CASE CASE/Architecture simulation integration", Proc. of winter simulation conf. pp. 657-661, 1993.
Rozenbilt et al", Towards an implemention of a knowledge based system design and simulation environment", Proc. of winter simulation conf. pp 226-230, 1988.
Kunnathur et al, "Dynamic rescheduling of job shop: a simulation study", Proc. of winter simulation conf., pp. 1091-1098, 1996.
Hopkinson et al, "Real time validation of man in the loop simulations", Proc. of winter simulation conf., pp. 1250-1256, 1995.
Manivannan et al, "Real time control of a manufacturing cell useing knowledge based simulation", Proc. of winter simulation conf., pp. 251-260, 1991.
Ducasse et al, "A review of automated debugging system: Knowledge, strategies and techniques", IEEE, pp. 162-171, 1988.
Tiben, Knowledge bases for user guidance in information seking dialogues, ACM IUI, pp 149-156, Jul. 1992.
Luh et al., "Abstraction morphisms for world modelling in high autonomy systems", Proc. of winter simulation conf. pp. 1129-1138, 1991.
Factor et al. " The process trellis: a software architecture for intelligent monitors", Tools for artificial intelligence TAI 89, pp. 174-180, Oct. 1989.
Fox et al., "The role of database in knowledge based system", On knowledge base management system, pp. 407-430, 1986.
Rabelo et al., "Synergy of artificial neuarl networks and knowledge based expert system for intelligent FMS scheduling", Synergy of artificial, pp. 359-366, Jun. 1990.
Lee, "A self learning rule based controller employing approximate reasoning and neural net concepts", Int. Jor. of Intelligent Sys., vol. 6, pp. 71-93, 1991.
Adamy Jurgen
Horn Hannes Schulze
Hafiz Tariq R.
Khatri Anil
Siemens Aktiengesellschaft
LandOfFree
Intelligent computerized control system does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Intelligent computerized control system, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Intelligent computerized control system will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1495259