Automated and emerging technologies flashcards

Topic 6: Automated and emerging technologies

What are the three main parts of an automated system?

Sensors measure a physical property. A microprocessor reads the data, compares it with stored values and decides what to do. Actuators carry out the physical action, e.g. a motor, pump or heater.

Why does an automated system need an ADC?

Sensors usually produce analogue signals that vary continuously, but the microprocessor can only process digital data, so an analogue-to-digital converter is needed between them.

Describe the feedback loop in an automated system

The sensor takes a reading, which is converted to digital. The processor compares it with the preset value and, if action is needed, signals an actuator. The next reading reflects the effect, and the loop repeats continuously.

Give two advantages and two disadvantages of automated systems

Advantages: work continuously; consistent quality; faster response; remove people from danger. Disadvantages: high set-up and maintenance cost; job losses; need skilled technicians; a fault can be repeated at speed.

What are the characteristics of a robot?

It has a mechanical structure (such as arms, wheels or legs), electrical components (sensors, motors, a processor), and it is programmable.

Give two advantages and two disadvantages of robots in a factory

Advantages: work non-stop; very consistent and accurate; can work in hazardous places. Disadvantages: high purchase and maintenance cost; cannot cope well with unexpected situations; can cause unemployment.

What is artificial intelligence (AI)?

The ability of a computer system to carry out tasks that normally need human intelligence. An AI system collects data, uses rules to reason about it, and can adapt its behaviour.

Knowledge base, rule base and inference engine

Knowledge base: stores the facts. Rule base: stores the rules, usually IF condition THEN conclusion. Inference engine: applies the rules to the facts to reach a conclusion.

What is machine learning?

A branch of AI in which the system improves its performance by learning from data, rather than being given every rule by a programmer, e.g. a spam filter trained on labelled emails.