Presentation is loading. Please wait.

Presentation is loading. Please wait.

© 2002 Franz J. Kurfess Expert System Examples 1 CPE/CSC 481: Knowledge-Based Systems Dr. Franz J. Kurfess Computer Science Department Cal Poly.

Similar presentations


Presentation on theme: "© 2002 Franz J. Kurfess Expert System Examples 1 CPE/CSC 481: Knowledge-Based Systems Dr. Franz J. Kurfess Computer Science Department Cal Poly."— Presentation transcript:

1 © 2002 Franz J. Kurfess Expert System Examples 1 CPE/CSC 481: Knowledge-Based Systems Dr. Franz J. Kurfess Computer Science Department Cal Poly

2 © 2002 Franz J. Kurfess Expert System Examples 2 Course Overview u Introduction u Knowledge Representation u Semantic Nets, Frames, Logic u Reasoning and Inference u Predicate Logic, Inference Methods, Resolution u Reasoning with Uncertainty u Probability, Bayesian Decision Making u Expert System Design u ES Life Cycle u CLIPS Overview u Concepts, Notation, Usage u Pattern Matching u Variables, Functions, Expressions, Constraints u Expert System Implementation u Salience, Rete Algorithm u Expert System Examples u Conclusions and Outlook

3 © 2002 Franz J. Kurfess Expert System Examples 3 Overview ES Examples u Motivation u Objectives u Chapter Introduction u Review of relevant concepts u Overview new topics u Terminology u R1/XCON u System Configuration u Knowledge Representation u Reasoning u Important Concepts and Terms u Chapter Summary

4 © 2002 Franz J. Kurfess Expert System Examples 4 Logistics u Introductions u Course Materials u textbooks (see below) u lecture notes u PowerPoint Slides will be available on my Web page u handouts u Web page u u Term Project u Lab and Homework Assignments u Exams u Grading

5 © 2002 Franz J. Kurfess Expert System Examples 5 Bridge-In

6 © 2002 Franz J. Kurfess Expert System Examples 6 Pre-Test

7 © 2002 Franz J. Kurfess Expert System Examples 7 Motivation  reasons to study the concepts and methods in the chapter  main advantages  potential benefits  understanding of the concepts and methods  relationships to other topics in the same or related courses

8 © 2002 Franz J. Kurfess Expert System Examples 8 Objectives  regurgitate  basic facts and concepts  understand  elementary methods  more advanced methods  scenarios and applications for those methods  important characteristics  differences between methods, advantages, disadvantages, performance, typical scenarios  evaluate  application of methods to scenarios or tasks  apply  methods to simple problems

9 © 2002 Franz J. Kurfess Expert System Examples 9 Evaluation Criteria

10 © 2002 Franz J. Kurfess Expert System Examples 10 R1/XCON  one of the first commercially successful expert systems  application domain  configuration of minicomputer systems  selection of components  arrangement of components into modules and cases  approach  data-driven, forward chaining  consists of about 10,000 rules written in OPS5  results  quality of solutions similar to or better than human experts  roughly ten times faster (2 vs. 25 minutes)  estimated savings $25 million/year

11 © 2002 Franz J. Kurfess Expert System Examples 11 System Configuration  complexity  tens or hundreds of components that can be arranged in a multitude of ways  in theory, an exponential problem  in practice many solutions ``don't make sense'', but there is still a substantial number of possibilities  components  important properties of individual components  stored in a data base  constraints  functional constraints derived from the functions a component performs  e.g. CPU, memory, I/O controller, disks, tapes  non-functional constraints  such as spatial arrangement, power consumption,

12 © 2002 Franz J. Kurfess Expert System Examples 12 Knowledge Representation  configuration space  constructed incrementally by adding more and more components  the correctness of a solution often can only be assessed after it is fully configured  subtasks are identified  make the overall configuration space more manageable  component knowledge  retrieved from the external data base as needed  control knowledge  rules that govern the sequence of subtasks  constraint knowledge  rules that describe properties of partial configurations

13 © 2002 Franz J. Kurfess Expert System Examples 13 Example Component  partial description of RK611* disk controller  facts are retrieved from the data base and then stored in templates RK611* Class:UniBus module Type:disk drive Supported:yes Priority Level:buffered NPR Transfer Rate:212...

14 © 2002 Franz J. Kurfess Expert System Examples 14 Example Rule  rules incorporate expertise from configuration experts, assembly technicians, hardware designers, customer service, etc. Distribute-MB-Devices-3 If the most current active context is distributing Massbus devices & there is a single port disk drive that has not been assigned to a Massbus & there are no unassigned dual port disk drives & the number of devices that each Massbus should support is known & there is a Massbus that has been assigned at least one disk drive and that should support additional disk drives & the type of cable needed to connect the disk drive to the previous device is known Then assign the disk drive to the Massbus

15 © 2002 Franz J. Kurfess Expert System Examples 15 Configuration Task  check order; identify and correct omissions, errors  configure CPU; arrange components in the CPU cabinet  configure UniBus modules; put modules into boxes, and boxes into expansion cabinets  configure panels; assign panels to cabinets and associate panels with modules  generate floor plan; group components and devices  determine cabling; select cable types and calculate distances between components  this set of subtasks and its ordering is based on expert  experience with manual configurations

16 © 2002 Franz J. Kurfess Expert System Examples 16 Reasoning  data-driven (forward chaining)  components are specified by the customer/sales person  identify a configuration that combines the selected components into a functioning system  pattern matching  activates appropriate rules for particular situations  execution control  a substantial portion of the rules are used to determine what to do next  groups of rules are arranged into subtasks

17 © 2002 Franz J. Kurfess Expert System Examples 17 Performance Evaluation  notoriously difficult for expert systems  evaluation criteria  usually very difficult to define  sometimes comparison with human experts is used  empirical evaluation  Does the system perform the task satisfactorily?  Are the users/customers reasonably happy with it?  benefits  faster, fewer errors, better availability, preservation of knowledge, distribution of knowledge, etc.  often based on estimates

18 © 2002 Franz J. Kurfess Expert System Examples 18 Development of R1/XCON  R1 prototype  the initial prototype was developed by Carnegie Mellon University for DEC  XCON commercial system  used for the configuration of various minicomputer system families  first VAX 11/780, then VAX 11/750, then other systems  reimplementation  more systematic approach to the description of control knowledge  clean-up of the knowledge base  performance improvements

19 © 2002 Franz J. Kurfess Expert System Examples 19 Extension of R1/XCON  addition of new knowledge  wider class of data  additional computer system families  new components  refined subtasks  more detailed descriptions of subtasks  revised descriptions for performance or systematicity reasons  extended task definition  configuration of ``clusters''  tightly interconnected multiple CPUs  related system XSEL  tool for sales support

20 © 2002 Franz J. Kurfess Expert System Examples 20 Summary R1/XCON  commercial success  after initial reservations within the company, the system was fully accepted and integrated into the company's operation  widely cited as one of the first commercial expert systems  domain-specific control knowledge  the availability of enough knowledge about what to do next was critical for the performance and eventual success of the system  suitability of rule-based systems  appropriate vehicle for the encoding of expert knowledge  subject to a good selection of application domain and task

21 © 2002 Franz J. Kurfess Expert System Examples 21 Figure Example

22 © 2002 Franz J. Kurfess Expert System Examples 22 Post-Test

23 © 2002 Franz J. Kurfess Expert System Examples 23 Evaluation u Criteria

24 © 2002 Franz J. Kurfess Expert System Examples 24 Important Concepts and Terms  agenda  backward chaining  common-sense knowledge  conflict resolution  expert system (ES)  expert system shell  explanation  forward chaining  inference  inference mechanism  If-Then rules  knowledge  knowledge acquisition  knowledge base  knowledge-based system  knowledge representation  Markov algorithm  matching  Post production system  problem domain  production rules  reasoning  RETE algorithm  rule  working memory

25 © 2002 Franz J. Kurfess Expert System Examples 25 Summary Chapter-Topic

26 © 2002 Franz J. Kurfess Expert System Examples 26


Download ppt "© 2002 Franz J. Kurfess Expert System Examples 1 CPE/CSC 481: Knowledge-Based Systems Dr. Franz J. Kurfess Computer Science Department Cal Poly."

Similar presentations


Ads by Google