You must log in to edit PetroWiki. Help with editing

Content of PetroWiki is intended for personal use only and to supplement, not replace, engineering judgment. SPE disclaims any and all liability for your use of such content. More information


Levels of automation

PetroWiki
Jump to navigation Jump to search

The oil and gas industry is becoming more technologically advanced every day. As automation, artificial intelligence (AI) and robotics improve, it may be increasingly tempting to employ automatic means to accomplish industry goals. The degree to which a task is automated is referred to as levels of automation (LOA). The most comprehensive list was developed by Thomas B. Sheridan and W. L. Verplank[1]. Levels of automation range from complete human control to complete computer control.

Gallery

Automation levels

Level 1
The human operator does the task and turns it over to the computer to implement.
Level 2
The computer helps by determining the options.
Level 3
The computer helps determine and suggests options. The human operator can choose to follow the recommendation,
Level 4
The computer selects the action and the human operator decides if it should or should not be done.
Level 5
The computer selects the action and implements it if the human operator approves the action.
Level 6
The computer selects the action and informs the human operator in case the operator wants to cancel the action.
Level 7
The computer does the action and tells the human operator what is did.
Level 8
The computer does the action and tells the human only if the human operator asks.
Level 9
The computer does the action when told and tells the human operator only if the computer decides the operator should be told.
Level 10
The computer does the action if it decides it should be done. The computer tells the human operator only if it decides the operator should be told.

Four-stage model of human information processing

Parasuraman, Sheridan, and Wickens[2] went on to introduce the idea of associating levels of automation to functions.

The four-stage model of human information processing includes:

  1. Sensory processing
  2. Perception and/or working memory[3]
  3. Decision making
  4. Response selection
Sensory processing
Refers to the acquisition and registration of multiple sources of information. This stage includes the positioning and orienting of sensory receptors, sensory processing, initial pre-processing of data prior to full perception, and selective attention.
Perception and/or working memory
Involves conscious perception,and manipulation of processed and retrieved information in working memory. This includes cognitive operations such as rehearsal, integration and inference, but these operations occur prior to the point of decision.
Decision making
Decisions are reached based on such cognitive processing.
Response selection
Involves the implementation of a response or action consistent with the decision choice.

These functions are based on a four-stage model of human information processing and can be translated into equivalent system functions[4]:

  1. Information acquisition
  2. Information analysis
  3. Decision and action selection
  4. Action implementation

The four functions can provide an initial categorization for types of tasks in which automation can support the human operator.

Information acquisition
Automation of information acquisition applies to the sensing and registration of input data.[2]
Information analysis
Automation of information analysis involves cognitive functions such as working memory and inferential processes.[2]
Decision and action selection
This stage, decision and action selection, involves selection from among decision alternatives[2]
Action implementation
This final stage of action implementation refers to the actual execution of the action choice.[2]

Levels of automation across any of the above functional types do not need to be fixed at the system design stage. Instead, the level of automation could be designed to vary depending on production demands during operational use.[2]

Human-centered automation[5]

  • Automation systems should be comprehensible.
  • Automation should ensure operators are not removed from command role.
  • Automation should support situation awareness.
  • Automation should never perform or fail silently.
  • Management automation should improve system management.
  • Designers must assume that operators will become reliant on reliable automation.

References

  1. Sheridan, T. B., & Verplank, W. L. 1978. Human and computer control of undersea teleoperators. Cambridge, Mass: Massachusetts Institute of Technology, Man-Machine Systems Laboratory. www.dtic.mil/cgi-bin/GetTRDoc?AD=ADA057655 PDF
  2. 2.0 2.1 2.2 2.3 2.4 2.5 Institute of Electrical and Electronics Engineers., & IEEE Systems, Man, and Cybernetics Society. 2000. A Model for Types and Levels of Human Interaction with Automation. IEEE transactions on systems, man, and cybernetics: A publication of the IEEE Systems, Man, and Cybernetics Society. New York, NY: Institute of Electrical and Electronics Engineers. Vol. 30. No. 3.
  3. Baddeley, A. D. 1986. Working memory. Oxford [Oxfordshire: Clarendon Press.
  4. Billings, C. E. 1997. Aviation automation: The search for a human-centered approach. Mahwah, N.J: Lawrence Erlbaum Associates Publishers.
  5. Billings, C. E. (1997). Aviation automation: The search for a human-centered approach. Mahwah, N.J: Lawrence Erlbaum Associates Publishers.

Noteworthy papers in OnePetro

Noteworthy books

External links

See also

Category