1. Reconfigurable Fuzzy Automaton for Software Agents Janos L. Grantner, Paolo A. Tamayo, Ramakrishna Gottipati, George A. Fodor Presentation By Dr. Janos L. Grantner WCCI/FUZZ-IEEE 06

2. 2 Introduction HFB-FSM Model Intelligent Software Agents Reconfigurable Architecture Design Simulation Results Conclusion Presentation Outline

3. 3 Introduction The problems that characterize industrial process control innovation are: 1.Introducing new knowledge into a system 2.Activating stored domain knowledge in an autonomous way 3.Validating the knowledge 4.Recovering the system if the new, activated knowledge is not suitable to handle the situation

4. 4 Introduction (contn’d) These problems can be addressed using intelligent software agents with fuzzy automata New knowledge can be implemented by adding agents –New knowledge is introduced by means of states in the goal path of an event driven, sequential control algorithm –Fuzzy automata is an effective approximation method to model continuous and discrete signals in a single theoretical framework Knowledge validation is achieved –By quantifying the degree of deviation from the nominal operating conditions due to unexpected events –Execution monitoring is also performed with fuzzy automata

5. 5 Intelligent Software Agent Object State Application To FSA-BROKER: architecture, Supervision, real-time To ALARM SERVER To HMI Server Connection to other objects Commissioning Panel All ports are bi-directional All ports have a named type ARCHITECTURE APPLICATION Fuzzy Automaton

6. 6 Hardware Implementation of Agents IP (Intellectual Property) modules are designed as generic fuzzy automaton agents Agents communicate via NoC (Network on Chip) to decrease the real estate needed for pathways on the chip Agent broker can be implemented on an FPGA A set of specialized architecture operations are needed to implement an agent broker on an FPGA Example of such implementation: NoC

7. 7 Synthesis of Network on Chip (NoC) Input: IP components with cost figures: U 1, U 2, U 3, V 1, V 2, V 3 Clustered constraints (clustering is NP-complete): U 1,2,3 is one cluster, V 1,2,3 is another cluster Communication Constrained Graph: U i communicates with V i, i=1,2,3 Optimal synthesis – quadratic programming approach: have only one communication channel Method: CDCS (constrained driven communication synthesis) At present, software implementation takes minutes u1u1 u2u2 u3u3 u1u1 u2u2 u3u3 v1v1 v1v1 v2v2 v2v2 v3v3 v3v3

8. 8 HFB-FSM Model

9. 9 Example for Designing a Reconfigurable Fuzzy Automaton It is based upon the computational model of HFB-FSM Assumes a multi-fuzzy input and one fuzzy output (MISO) configuration Digital inputs and analog inputs with threshold are omitted at this point Each fuzzy input is mapped to a set of Boolean variables using the B-Algorithm (Fuzzy-to- Boolean mapping)

10. 10 Example (Contn’d) k overlapping linguistic sub – intervals are mapped to n (n = 2k-1) non overlapping Boolean sub – intervals, and Xbi = 1 if the xc position of the fuzzy input maximum falls into Boolean sub – interval i(i = 1,…,n) and XBj = 0 for all j = i(j = 1,……,n)

11. 11 Example (Contn’d)

12. 12 Reconfigurable Architecture Design (Contn’d)

13. 13 Example (Contn’d)

14. 14 Example (Contn’d)

15. 15 Example (Contn’d)

16. 16 Example (Contn’d)

17. 17 Example (Contn’d)-Parameters ComponentDescription Number of Fuzzy Inputs Defines the number of fuzzy inputs of the system. This value also determines the number of parallel MOM and Interval Detection circuits. Resolution The resolution of the degree of membership is resizable. This determines the number of bits needed to represent the degree of membership. Granularity This resizable property depends upon the number of elements in the universal set. Boundary Count This is the number of Boolean sub-intervals. It can be reset from problem to problem. Boundary Limits The right-most element of each Boolean sub- interval. The total number of limits is equal to the Boundary Count. Number of Fuzzy States The number of fuzzy states in the particular state cluster to be implemented.

18. 18 Validation Container Crane Problem The Container-Crane problem simulates the operation of transferring a container van from a ship into a railcar platform. The Container-Crane problem is developed using the fuzzyTech software

19. 19 Validation (Contn’d) Container Crane Problem The two fuzzy inputs are –Angle of displacement of the suspended load (X) Left swing results in a negative angle Right swing results in a positive angle –Distance of the load from the rail car (Y) Far, Near, Close (also the states of the system) Output is the power applied to the crane (Z) –Positive power, negative power and zero power A simplified HFB-FSM will have 3 states, each of which will be made of just one crisp state

20. 20 Validation (Contn’d) RulesRule Description For Crisp State 1 (far) Rule 1If X is zero and Y is far then Z is positive. Rule 2If X is negative and Y is far then Z is positive. Rule 3If X is positive and Y is far then Z is positive. For Crisp State 2 (near) Rule 1If X is zero and Y is near then Z is positive. Rule 2If X is negative and Y is near then Z is positive. Rule 3If X is positive and Y is near then Z is negative. Rule 4If X is zero and Y is close then Z is zero. Rule 5If X is positive and Y is close then Z is negative. Rule 6If X is negative and Y is close then Z is zero. For Crisp State 3 (close) Rule 1If X is zero and Y is close then Z is zero. Rule 2If X is positive and Y is close then Z is negative. Rule 3If X is negative and Y is close then Z is zero.

21. 21 Validation (Contn’d) Normalized universal set

22. 22 Validation (Contn’d) Present State Next State Fuzzy Input (Angle) Fuzzy Input (Distance) Fuzzy Output (Power)Defuzzified Value 11ZeroFar[0.0 0.0 0.0 0.0 0.5 1.0 1.0]7 11NegativeFar[0.0 0.0 0.0 0.0 0.5 1.0 1.0]7 11PositiveFar[0.0 0.0 0.0 0.0 0.5 1.0 1.0]7 12NegativeNear[0.0 0.0 0.0 0.0 0.5 0.5 0.5]6 22ZeroNear[0.0 0.0 0.5 0.5 0.5 1.0 1.0]7 22NegativeNear[0.0 0.0 0.5 0.5 0.5 1.0 1.0]7 22PositiveNear[1.0 1.0 0.5 0.5 0.5 0.5 0.5]2 23ZeroClose[0.5 0.5 0.5 1.0 0.5 0.5 0.5]4 33PositiveClose[1.0 1.0 0.5 0.5 0.5 0.0 0.0]2 33NegativeClose[0.0 0.0 0.5 1.0 0.5 0.0 0.0]4

23. 23 Validation (Contn’d) Simulation

24. 24 Validation (Contn’d) Inference and Model Building Operation Performance Summary Type of Operation Number of Rules per State Size of 1 Fuzzy State Rule Number of Elements in the Universal Set Number of Clock Cycles Needed Inference RNxNN N + K Model Building RNxNN (SxNxNxR) + 1 + K Where :K is the constant overhead cycles when performing the operation, currently 4 clock cycles. S is the number of States

25. 25 Validation (Contn’d) For the example: Inference will be N+K = 7 + 4 = 11 clock cycles. Model Building will be (SxNxNxR) + 1+K = (3x7x7x3) + 1+4 = 446 clock cycles At 100MHZ clock rate we can run approximately 220,000 Model Building Operations and 10 Million Inferences per second

26. 26 Conclusion An intelligent software agent architecture with fuzzy automaton was introduced Online reconfiguration of this architecture is needed to introduce new knowledge and for fault detection and identification and recovery IP (Intellectual property) modules are implemented on hardware in contemporary control systems Hardware implementation of a reconfigurable fuzzy automaton was presented.