Prof. Dr. -Ing. Hong–Seok Park

Laboratory for Production EngineeringSchool of Mechanical and Automotive Engineering

University of ULSAN

June 21st, 2012

a PLM 베스트 프랙티스 컨퍼런스 2012 a

인지 제조시스템- Cognitive Manufacturing System -

Lab. for Production Engineering

Contents

인지제조시스템- Cognitive Manufacturing System -

1. Introduction2. Classification of disturbances through analyzing current manufacturing system3. Elementary technology for developing self adapting manufacturing system

3.1. Cognitive agent3.2. Biology inspired strategy

4. Development of self adapting manufacturing system (SAMS)4.1. Concept of SAMS4.2. Information module of SAMS4.3. Algorithm of SAMS

5. Implementation of SAMS5.1. Hardware architecture of SAMS5.2. Software architecture of SAMS5.3. Communication network of SAMS

6. Conclusion.

Lab. for Production Engineering

Arriving Work-piece

Loadingmachine

Begin Machining

Machining

FinishMachining

Unloadingmachine

Next Machines

Disturbance

Tool-wear

Tool-break

Current manufacturing

Parameterchange

Tool change

Intervention of human operator

Adjustingparameter

request

Agent #1Tool-wear

Tool-break

Agent #n

New manufacturing

Intelligent&Genetic

behaviours

Self-adaptiveCooperation

Stop machine ExperienceDowntime

vReducing productivityvDecreasing the utilization

of machining shopvMeasures depending on

the experience of operators

vSelf-adaptingvReasoning ability in decision

makingvSelf-controlling ability

Necessity for developing a new manufacturing concept

Stop machine

Self-adapting system

Lab. for Production Engineering

Clutch housing

Machining ShopProduct

Clutch housing

vProcessing operations per product: 17

vMachines: 12

{ Downtime: 20-25% of total planned timeDisturbance

Recovery method

Current recovery method: Stop the machining shop to repair and reset

Centralized control system

§ Rigid Control: Top-down problem solving

§ Low scalability§ Low adaptability

Proposed method: Self-adaptive manufacturing system

MachineAgent 1

MachineAgent 2

Work-pieceAgent

TransporterAgent

Machine 1 Machine 2 Work-piece Transporter

…Self - Recovery

Analyzing current manufacturing in consideration of self adapting concept

Lab. for Production Engineering

Disturbance Classification and Management methods

Rescheduling type:Recovering time > 1 hour

Non-negotiationNegotiationRescheduling

11.4%47.7%

40.9%

Event

Malfunction of machine(long recovering time)

ReschedulingAgents

EventTool-break

Agent

NegotiationNon-negotiation

Malfunction of machine(short recovering time)Event

Tool-wear AgentEvent

Disturbance Machining System

Disturbance Classification

MES

Disturbance InformationvData collection time: 2006.08.31-2009.08.18vDisturbance numbers: 685

Disturbance class Type of disturbanceRelated to resources Machine breakdown

Maintenance of machineTool breakdownTool wearOperator absenteeism

Related to orders Unavailability of raw materialCancellation orderReworkArrival of a new job orderUrgent jobDelay in transport using materialhandling systemOut sourcing

Related to measurement of data Process time variationVariation of set-up timesChange of priority

Control softwareand Communication networks

Malfunction

Non-Negotiation type:Recovering time < 30 mins

Negotiation type:30 mins < Recovering time < 1 hour

Disturbance

Lab. for Production Engineering

Concept of cognitive agent

Rule- basedDecision makingConventional

agent

Percepts

Actions

Sensors

Effectors

Environment

Agent technology Cognitive technology

Perception

Reasoning

Actions

Synthesis of agent and cognitive technologies

Perception(Beliefs)

Interpretation

Learning

Decision Making

(Desires)

Action

Communication

Event

Knowledge& Experience(Intentions)

Reasoning

Eventrecognition

Informationinput

New situation

Updateknowledge

Familiar situation Plan

Commandoutput

Cooperation

CognitiveAgent

BDI ArchitectureBeliefsGrasping the information of the current states of an agent’s environment

DesiresAll the possible states of tasks that agent could carry out

IntentionsThe states of tasks that the agent has decided to work towards

Lab. for Production Engineering

Ability Machine tool

Task1 Machine 1

Task 2 Machine 2

Task 3 Machine 3

Task 2 Machine 1

Task 2 Machine 3

Ability list

Cognitiveagent

Ability Pheromone

Task 1 Pheromone value 1

Task 2 Pheromonevalue 2

Information Node

M1,T1M2,T2 M3,T3

M1,T1 M3,T2,T3

Machinebreakdown

Route 2

Work-piece

Product

Ants lay pheromone on the trail when they moves food back to nest

Pheromones accumulate with multiple ants using same path

Pheromones evaporate when no ant pass

Ant travel rule: Each ant always try to chose the trail has higher pheromone concentration

From Natural to Manufacturing Systems

The machine with the shortest processing time for carrying out a specific operation will has the highest pheromone

Biology inspired strategy to adapt to disturbance

Lab. for Production Engineering

Systematic procedure for developing a Self-Adaptive Manufacturing System (SAMS)

Product and Machining Shop

Inspired Biology : Ant Colony AlgorithmCognitive Agent

Elementary technologiesto develop a SAMS

Developing Architecture Of the machining shop

based on Cognitive agents

Model of the machining shop based on functional agentsInformation Model of SAMSMechanism of SAMS for adapting to disturbanceAlgorithm for making decision of SAMS Implementing

the Test-bed of SAMS

Architecture of the Test-bed

Mechanism of the implemented SAMS

for adapting to disturbances

Disturbance Analysis

Disturbance Classification

Finding measures against the

corresponding disturbances

Model of SAMSModel of SAMS Test-bedTest-bed Strategies for overcoming disturbancesStrategies for overcoming disturbancesNon-negotiation Negotiation

DiagnosisDisturbance

Cognitive Agent

Controller

Lab. for Production Engineering

Machine Agent #i

Machine #iMachine #3

Perception

Decision Making

ControlCommunication

Machine Agent #1Reasoning

Signals Tasks

Plan

Machine #1

Disturbance

Work-piece

MES

Transporter

Machining system

Work-pieceAgent

TransporterAgent

Interpretation

Machine Agent #3

Machine #2

Machine Agent #2

vBehaviours policies§ Rule-based§ Reasoning mechanismvPheromone value

Knowledge

Concept of a self adapting manufacturing system

Machine #1Machining

Shop

Work-piece Transporter Machine #2 Machine #2

Lab. for Production Engineering

Negotiation

Mean-endsreasoning

Deciding onHow to achieve this state

Previous stateI, B

Update stateb:=see

B:=update( B, b)

Comparisont:= compare (B, D)MES D:=process(task)

Inform normal state (t:=0)

Disturbance typec:=Diagnosis (type)

Type A: rescheduling

Disturbance

I:=filter(B,D,I)p:=plan(B, I, c)Rule-base

Type B: Reactive behavior

Execute (p)

End

NegotiationSelect (agents)+

Type C: Cooperative behavior

without (p) Agent (selected)

Execute (p)

End

MES

without (agent)

Deliberation reasoning

Deciding on what state to achieve

Deciding on what agent to be selected

rescheduling

Cognitive agent based disturbance handling

Lab. for Production Engineering

Implementing the Test-bed of SAMS

Hardware architecture of SAMS

Working sequence for implementing the SAMS

Software architecture of SAMS

Developing the database of SAMS

Non-negotiation mechanism of SAMS

Negotiation mechanism of SAMS

Evaluation of SAMS

Demonstration of SAMS

Lab. for Production Engineering

Hardware architecture of SAMS on the test-bed

Lab. for Production Engineering

PLC S7-300

Disturbanceinputs

RS232 cable

lightindicator

DI D0 CP341 module

CP343-1 module

Internet cable

Internet cardIP: 192.168.0.30

RFIDTag

RFID Reader

Work-piece

Light

Read/Write

Message for SEND/RECEIVE data

Flowchart SEND/RECEIVEbetween PLC and RFID

The communication of wire network between the devices in SAMS

Lab. for Production Engineering

Agent #1

IP: 192.168.1.1

IP: 192.168.1.2

IP: 192.168.1.n

Agent #2

Agent #n

Bridge in wireless network

IP: 192.168.1.3 Agent #3

Wireless

Access point

Access point

Access point

Access point

The communication bridge has function of the signal amplifier, and is amiddleware node in the communication wireless network.

The communication of wireless network between agents in SAMS

The communication mechanism between agents in the AMS

Lab. for Production Engineering

Software architecture of SAMS

SQL KepserverEXOPC

PLC1

Agent#1Disturbance

Disturbanceinformation

Work-pieceinformation

ProcessInformation

Task

Knowledge

SQL KepserverEXOPC

PLC2

Agent#2

SQL KepserverEXOPC

PLC3

Agent#3

MES

Message Message

ProcessInformation

Disturbance

ResourceInformation

SQLWire

Wireless

Machine1RFID

Machine2RFID

Machine3RFID

Lab. for Production Engineering

Machine agent state

Information collection

OPC items

A

A

Disturbance information

Disturbanceclassifying

Perception

Decision

Plan

Task InformationCooperation information

AB

A

B

A disturbance known

B disturbance unknown

Suggested method

Unknown Disturbances

Process Information

Machine Information

Database design and analysis

Lab. for Production Engineering

Algorithm for making decision of SAMS

Non-Negotiation Negotiation

Lab. for Production Engineering

11 Input disturbance

shown by turning on the red

light (alarm) at PLC 1

6

Simentic S7PLC #1

22 PLC 1 sends the signal to

agent

33

44

55

66The system overcomes the

disturbance shown by turning

on the green light at PLC 1

OPC protocol is used for

communicatingbetween PLC and

agent

In case of the disturbance

belongs to thenon-negotiation

type, agent generates a new

plan and sends the command to PLC

Collecting data

Agent diagnoses the disturbance

type

Machine agent

Reaction of the system in the case of non-negotiation

Lab. for Production Engineering

Demonstration for non-negotiation mechanism

Lab. for Production Engineering

PLC 1

Reaction of the system in the case of negotiation

MES

Registering network

Input disturbance

shown by turning on the red

light (alarm) at PLC 1

11

PLC 1 sends the signal to

agent

Collecting data

22

33

Agent diagnoses the disturbancebelonging to the negotiation type

Agents establish the wireless network

to server

44

55

Agent 1 Agent 2

(Selected agent)Agent 3

PLC 2

Agent negotiation

An appropriate agentis selected for carring

out the job of the failure machine

66

77

The system overcomes the

disturbance shown by turning

on the green light at PLC 2

88

Lab. for Production Engineering

Demonstration for negotiation mechanism

Lab. for Production Engineering

Conclusion

§ Summary§ The cognitive agent technology and the biology inspired strategy are applied to the SAMS

§ Disturbances and corresponding management methods in the machining shop of a clutch

housing are analyzed

§ Developing a SAMS to autonomously overcome these disturbances

§ Implementing a test-bed to demonstrate the functionalities of SAMS.

§ Implementing self-evolution mechanism for solving the new disturbance to be happened

§ Future work

§ This method could replace the traditional method that has been intervened by human operator

§ It has the functionalities of intelligent behaviour such as self-adapting, self-controlling, and

reasoning ability in decision making

§ Increasing the productivity and reducing downtime in the product line.

§ Benefits

Lab. for Production Engineering