Adama Science and Technology University School of Engineering and Information Technologies Department of Mechanical and Vehicle Engineering

Post Graduate program Manufacturing Engineering

Artificial Intelligence in Mechatronics System

Presented by: Tadele Belay November 2011

Description
‡ ‡ ‡ ‡ Definition of Artificial Intelligence Features and Characteristics of AI Fundamental technologies of AI Applications of AI in manufacturing system

Objectives
‡ be aware of the distinction between strong and weak AI; ‡ be aware of the concepts of human-computer systems and human-computer interaction; ‡ know the benefits of building more intelligence into machines; ‡ realize that there are currently limits to how much intelligence can be built into machines; ‡ know the five critical features of AI and the ten enduring characteristics suggested by Schank; ‡ be aware of how AI can be implemented in manufacturing systems. ‡ Understand the technologies of artificial intelligence ‡ Know the characteristics of intelligence of manufacturing system

Introduction
‡ The massive use of digital technology is assured by its continuous improvement in performance/price ratio. === > every eighteen to twenty four months chip density and hence computing power doubles while cost remains constant. ‡ We can expect therefore physical objects, including living systems, to be tagged and thus endowed with the ability to communicate with each other, opening extraordinary opportunities for advanced Mechatronics. ‡ Artificial Intelligence (AI) has matured and is now capable of providing innovative solutions to many practical problems where there is a need to replace automation with intelligence.

4.What is Articial Intelligence? Some definitions that have been proposed: 1. 2. Systems that think like humans Systems that think rationally Systems that act like humans Systems that act rationally . 3.

 By contrast. A very important aspect of this is the relationship between humans and computers. but that there are limits which mean that machines will always be intellectually inferior to humans. . Within the weak AI camp there is an active research area called cognitive science which uses computers to model human behavior with the intention of learning more about human beings. the proponents of weak AI believe that machines can exhibit what might be called intelligent behavior.STRONG AI. WEAK AI AND COGNITIVE SCIENCE AI has two main camps:  The proponents of strong AI believe that it will be possible to build machines with human-like intelligence.

In other words. No machine works without some level of human supervision. Suppose the intelligent part played by machines in any particular system can be quantified between 0% (no machine intelligence) and 100% (no human intelligence.HOW MUCH INTELLIGENCE CAN BE BUILT INTO MACHINES ‡ The simple answer to this question is that no one knows. all machines are part of a human-computer system. . which we claim is impossible).

The cost of increasing the machine component of the system's intelligence can be sketched as shown The running costs of systems combining human and machine intelligence decrease with the introduction of greater machine intelligence. but the capital costs increase .

FEATURES AND CHARACTERISTICS OF AI: Schank suggests five critical features of AI: communication internal knowledge world knowledge goals and plans creativity. He also suggests ten 'enduring characteristics' of AI (we have added the comments in parentheses): Representation Decoding (real systems encoded into and from machine representations) Inference Control of combinatorial explosion Indexing (for recalling knowledge) Prediction and recovery Dynamic modification (including learning) Generalization Curiosity Creativity. .

realized right from the outset that for a machine to become 'intelligent' it would have to: ‡learn. one of the founding fathers of machine intelligence. .Alan Turing (1912-54).(Prediction) ‡detect that mistake and recover from it ‡constantly seeking to know 'what's out there (curiosity) Although there is a substantial body of applicable knowledge arising from AI. and to generalize from specific information in order to acquire new knowledge. ‡know what is possible and choose between the options. the subject remains young with many more questions than answers.

. They are designed to support the operators. not to replace them. none of the intelligent systems is capable of replacing their human counterparts. They can provide knowledge and respective facts filtered out from the huge amount of stored knowledge and increase the speed of decision making capability of the operators.ARTIFICIAL INTELLIGENCE & INTELLIGENT MANUFACTURING SYSTEMS Intelligent manufacturing systems are those performing the manufacturing functions as if the human operators are doing the job However. it would be wise to briefly review AI technologies at this point. Since it is necessary to equip the systems with intelligent capabilities in order to accomplish this. They can utilize decision-making capability of computers and make it available to the operators.

monitoring. reasoning. to perform problem solving and generate the respective actions and control them. that are popularly known are: ‡ expert systems.TECHNOLOGIES OF ARTIFICIAL INTELLIGENCE Intelligence is to perceive the environment in which the system is operating. learning. the computers or systems should be equipped with the capability of planning. to relate events taking place around the system. to make decisions about those events. . In order to achieve these. ‡ artificial neural networks. etc. ‡ genetic algorithms. control. Some AI techniques. and ‡ intelligent agents. ‡ fuzzy logic.

they utilize their knowledge.EXPERT SYSTEMS are widely used in most of the industrial applications. make it possible to create intelligent software systems capable of solving problems in the same way as human experts would do when facing the same problems. is stored in so-called knowledge bases. Similarly. which is represented in machine-readable format. to human experts. The knowledge. This is possible when respective knowledge is stored in a specific format understandable to the computer. It is utilized by expert systems for a decision-making process similar to that of a human being in order to produce solutions to the problems . experience and talents.

maintenance. etc. control. . monitoring. repair. diagnosis. and inspection.Basic components and architecture of an expert system Expert systems are proven to be useful especially in:‡planning.

‡Knowledge acquisition: acquire and elicit respective knowledge from the expert and represent that to the computer in a machine-readable format. ‡Knowledge base is the place where acquired knowledge is stored. The knowledge base is populated with the domain knowledge using these formats. This process is called knowledge acquisition. filter the required knowledge out and reason about those in order to be able to solve the problem posed by the user through the user interface. ‡Inference engines search and scan the knowledge base. knowledge frames. classes and procedures. Traditional ways of knowledge representation may include using IF THEN rules. .

‡It may explain how and why certain conclusions are reached.‡There are two general approaches for inference: ‡Forward chaining: this starts with the facts of the domain and tries to achieve a solution through available knowledge in the knowledge base. ‡Backward chaining: this starts with a solution and tries to find out respective facts supporting that particular solution. ‡User interface handles the communication between the expert system and the users. .

The main purpose of the learning is therefore to find out the right weight values of the connections. Since the weight values are distributed to the overall network. Each connection between the processing elements has a weight value indicating the effect of one processing element on the others. are formed by hierarchically connected process elements capable of information processing. generate new knowledge through learning the manufacturing events using the examples.ARTIFICIAL NEURAL NETWORKS are mainly designed to perform learning. the neural networks are assumed to have a distributed memory. are believed to indicate the knowledge of the network. These weight values. once the network is trained. .

.

‡They have a self-organizing capability. ‡They can perform graceful degradation and they are fault tolerant.They have various characteristics some of which may include the following: ‡They can only work with numeric information. ‡They are mainly used for perceptual information processing. ‡They automatically generate information for unseen examples. ‡They have distributed memory. ‡They perform learning well on pattern recognition and classification. ‡They have the capability to process incomplete information. ‡They can learn using examples. .

‡signal filtering. ‡optical character recognition. ‡sonar signal classification. ‡data fusion. ‡data mining. ‡non-linear system modelling. ‡production planning and scheduling. ‡intelligent and non-linear control. ‡robot motions. ‡non-linear signal processing. ‡life cycle estimation of mechanical parts. ‡optimum path planning for robotics. .Several examples of successful manufacturing applications can be realized especially in the following areas: ‡probabilistic function estimation. ‡time series analysis. ‡fingerprint recognition. ‡optimization. ‡pattern recognition and classification. ‡pattern matching.

These initial solutions are paired as parents and new solutions are produced (children) out of them. the solutions are aimed to be improved. In each production like this. Once new solutions are generated.GENETIC ALGORITHMS Genetic algorithms are very popular in solving especially very complex optimization problems. A set of some initial solutions to a specific manufacturing problem is randomly selected. The better solutions are sought through genetic operators and a fitness function. This process continues until no better solution is achieved. . some of them are carried out to the next generation in order to produce new solutions.

Basic elements and procedure of genetic algorithms .

The term high. turn the thermostat off when the temperature of the machine is 25 degrees .99 degrees? . suppose that the temperature is to be turned off when the temperature is 25 degrees. What happens if the temperature is 24. Some may consider 25 degrees high whereas others do not. they prefer to direct using the phrases like turn the system off when the temperature is high . which is called a fuzzy variable. Instead of saying for example. Since fuzzy logic is dealing with linguistic expressions like this. Most of the decisions experts make have some sort of uncertainty in them. For example.FUZZY LOGIC Fuzzy logic is particularly developed to handle uncertain knowledge. Experts tend to use vague phrases. it is also referred as computing with words . may be regarded differently by different people. Another good thing with fuzzy logic is that it may take a continuum approach and produce solutions for all alternatives and values.

Components of fuzzy logic .Fuzzification is to generate fuzzy propositions and identify linguistic variables and their membership functions Defuzzification is the process of finding a crisp value for the solution.

In this case. This may be difficult for some solution spaces as there may be more than one value having the same membership value. the average of those. or a value corresponding to the geometric average of the solution space is taken as the net solution to the problem. .Generally the value corresponding to the highest membership value is taken as the solution to the problem.

An example of a membership function An example of a solution space .

INTELLIGENT AGENTS Intelligent agents are independent and autonomous systems in performing their intended functions. The general architecture of an agent is given in Figure below: . They can be both hardware and software systems and they may incorporate more than one AI technology. They can learn and work concurrently.

cognition and action .There are three main components such as perception.

and prioritization according to the order of importance. This process may include filtering. Cognition is to process the information perceived and making decision accordingly. This could for example be to perform walking for a robot or stopping when an immediate barrier in front is encountered.Perception is to receive the inputs from the environment through sensors and convey them to the cognition module to be processed. Action is to perform the command received from the cognition using the respective effectors. . The cognition mechanism of an agent may also deal with unexpected situations and adapt itself to new situations as quickly as possible. This process may require various methods of intelligence systems such as learning to be implemented.

INTELLIGENT MANUFACTURING SYSTEMS Basic characteristics of intelligent manufacturing include the following: ªminimize human involvement in manufacturing activities. ªmonitor and control production processes and manufacturing operations. ªrecommend and take immediate actions to prevent faulty production. . ªmake sure that the processes are working properly and monitor their performance. ªdiagnose machines and sustain manufacturing integrity. ªperform maintenance activities. ªarrange material and production compositions automatically wherever possible.

Injection moulding design system developed by Mok et al. and simulation into account.APPLICATIONS OF INTELLIGENT MANUFACTURING SYSTEMS Pham and Oztemel (1996) reported their work on intelligent quality systems in their book. They have reported an expert system called XPC capable of performing statistical process control. which takes process planning. (2008). group technology. a Java-based intelligent design system equipped with AI technologies is introduced Tsourveloudis et al. (1990) recommended an integrated manufacturing management planning system. In this study. scheduling. Norrie et al. (2000) reported a neural network and fuzzylogic-based robot gripping system .

learn to control a system using methods such as neural networks and genetic algorithms which do not explicitly require a model. it can make do with very simple models. There are basically three ways that intelligent control overcomes the limitations or the lack of a model: 1.Intelligent control is most useful in situations where classical linear control is not suitable. it can use incomplete and imprecise models . and takes this description to produce a controller using fuzzy logic. 2. 3. such as descriptions of a system in words.

a problem called the broom-balancer will be investigated. a motor car engine may be modeled by relationships between numerical variables. To illustrate the application of different methods of intelligent control to a system which can be modeled using equations. but a road system containing many motor cars cannot adequately be modeled by formulae alone. or hierarchical. .Controlling systems can be represented by mathematical formulae. For example.

One more feature is added to the system. . the trolley is moved by applying a horizontal force in either direction. namely that the track has end-stops. so that not only has the broom got to be balanced but the trolley must stay near the centre of the track.left or right. When the broom starts to fall to the right.In the two-dimensional problem of the broombalancer. the trolley is moved to the right and the broom should move back to a vertical position.

The angle U must be kept as close as possible to zero and the position x from a fixed reference point must be kept as close as possible to zero. . It will be assumed that the system has sensors which allow it to measure U and x directly.The objective is to keep the broom upright and the trolley in the middle of the track.

.

In general: An intelligent mechatronic system adapts the controller to the mostly nonlinear behavior (adaptation). supervision may help to switch off the faulty component and to perform a reconfiguration of the controlled process. if a failure occurs. and performs a fault diagnosis (supervision) to request maintenance or. In the case of multiple components. and stores its controller parameters in dependence on the position and load (learning). supervises all relevant elements. . to request a fail safe action (decisions on actions).

CONCLUSIONS Intelligent manufacturing systems are evolving with an increasing speed. It is now apparent that intelligent manufacturing systems will be more dominant in industrial and manufacturing areas and: ‡They will make it possible to reduce the size of the product but increase their functionality as well as complexity. ‡They will be equipped with highly effective sensors for perceiving inputs and acting accordingly. ‡They will reconfigure themselves in the light of the progress in manufacturing systems and technologies. . ‡They will be capable of collecting/filtering and reasoning about the knowledge and data without any extra burden on the systems.

They will be able to define the best manufacturing methods for their intended purposes. They will increase their performance continuously and reduce the human involvement.They will have an extensive capability for learning and planning as well as up-dating their knowledge accordingly. It is now obvious that the next decade will be the decade of unmanned factories and new changes will continue to surprise both the academic and the industrial community . They will be able to adapt themselves to any kind of manufacturing environment.