ME290M Expert Systems in Mechanical Engineering Spring 1999, T-Th 12:30-2:00 pm 1165 Etcheverry Hall, Course Control No. 56369 http://best.me.berkeley.edu/~aagogino/me290m/s99

Introduction to expert systems, artificial intelligence and decision analysis in mechanical engineering. Fundamentals of logical inference, predicate calculus, multivariate logic, probability theory, diagnostic reasoning, risk assessment, qualitative reasoning, and analytical design. Applications to expert systems in automated manufacturing, mechanical engineering design, real time monitoring and supervisory control, and failure diagnostics. Use of automated influence diagrams/Bayes' networks to codify expert knowledge, perform probabilistic inference, and to evaluate optimal control or design decisions. All theory will be presented with engineering applications.

INSTRUCTOR: Prof. Alice M. Agogino, Mechanical Engineering, 5136 Etcheverry Hall, (510) 642-6450. email: aagogino@me.berkeley.edu

SCHEDULE

Week	Dates	Description
1	1-19,21	Overview of artificial intelligence, knowledge engineering, and expert systems.Historical perspective of computer intelligence. (Read Chap. 1.1-1.7 of Giarratano & Riley.)
2	1-26,28	Introduction to expert systems. Discuss advantages and limitations of expert systems. Selection criteria for rule-based systems. Summarize applications in mechanical engineering design, monitoring and supervisory control and failure diagnostics. (Read Chap. 1.8-1.10 and Chap. 6 of Giarratano & Riley; selected publications.)
3	2-2,2-4	Artificial intelligence, state space knowledge representation and heuristic search techniques: backward and forward chaining, Hill-climbing, generate-and-test, depth-first search, breadth-first search, best-first search, A* algorithm. (Read Chap. 2.1-2.10 of Giarratano & Riley. Scan 3.14.)
4 5	2-9,2-11, 2-16,2-18	Logic and sets. Deduction with formal logic; propositional logic. Introduction to first-order predicate logic: syntax, interpretation, and representation. Meaning, truth, and semantic interpretation. Logical implication: quantification, instantiation and unification. Completeness, and Decidability. Resolution. (Read Chap. 2.11-2.18, 3.1-3.14 of Giarratano & Riley.)
6	2-23,2-25	Languages for symbolic computation. (Read Chap. 1.11-1.12 and scan Chap. 7 of Giarratano & Riley. Handouts.) Guest speaker (by speakerphone Kent Cullers from SETI on 2-25, meeting in 3117B Etcheverry Hall, the Sheppard Room. Lecture Notes on Introduction to CLIPS.
7	3-2, 3-4	Reasoning under uncertainty, knowledge representation using other logics: nonmonotonic logic and subjective probability. Review basic concepts and theorems of probability theory using sample spaces, event sets and event algebra. (Read Chap. 3.15-3.17 and 4.1-4.6 of Giarratano & Riley.)
8 9	3-9, 3-11, 3-16, 3-18	Compound and conditional probabilities. Bayes' Theorem in event algebra. Dependence and independence and influence diagram/Bayes networks representation. Discrete probability functions. Conditional and joint probability distributions. Definition of moments. Bayes' Theorem. Expansion and probability trees. (Read Chap. 4.7-4.17 of Giarratano & Riley. Handout).
10	3-23,3-25	Spring Break
10	3-30,4-1	Application of probabilistic inference in expert systems for failure diagnostics. Review for midterm. Midterm
11	4-6,4-8	Inexact Reasoning: uncertainty factors, "idiot Bayes", Dempster-Shafer theory and fuzzy logic. (Read Chap. 5 of Giarratano & Riley. Handout).
12	4-13,4-15	Addition of control variables. Decision analysis and decision trees. Deterministic and stochastic dominance. Expected value optimization. (Revisit Chap. 4.9. Handout.)
13	4-20,4-22	Value of information and additional testing. Value theory, expected utility, and certain equivalence. (Handout.)
14	4-27,4-29	Knowledge acquisition, subjective probability and knowledge engineering. Assessment of expert opinion. Influence diagram based expert systems. Applications to real time monitoring, diagnostics and control of mechanical systems. (Handout).
15	5-4,5-6	Short project summaries. Second-generation expert systems: Machine learning, data mining, text analysis and misc. topics, time permitting. (Read Chap. 1.13-1.14 of Giarratano & Riley. Handouts.)

FINAL TERM PROJECTS: Project serves as a take-home final exam. Due on either last day of class or scheduled day of final exam (exam group 14; May 19), depending on class preference.

REQUIRED TEXTS: Joseph Giarratano and Gary Riley, Expert Systems: Principles and Programming, 3^rd Edition, PWS Publishing, 1998.

HOMEWORK: One homework set every 3 weeks and one individual project. Late homework will not be accepted. Solution sets will be provided on the due dates.

EXAMS: One midterm; individual project in lieu of final examination.