Difference between revisions of "Advanced automation/Self-maintenance and repair"
| Line 1: | Line 1: | ||
If complicated physical systems were able to be serviced and repaired completely automatically there would be many advantages. There would be higher productivity and efficiency without people in the loop - we tend to slow things down and are error prone; also people could be freed up to do something less menial; and the systems could scale quickly when more capacity is needed. | If complicated physical systems were able to be serviced and repaired completely automatically there would be many advantages. There would be higher productivity and efficiency without people in the loop - we tend to slow things down and are error prone; also people could be freed up to do something less menial; and the systems could scale quickly when more capacity is needed. | ||
| − | Machines today, such as industrial machinery, are designed to be looked after and serviced by people, and it would need artificial intelligence beyond our current capabilities to maintain or repair these systems completely autonomously. However it is perfectly feasible to design them from the outset to be maintainable this way; physically designed to be modular with components easily extracted and many embedded wired or wireless sensors giving the ability to diagnose faults on all components and assemblies. | + | Machines today, such as industrial machinery, are designed to be looked after and serviced by people, and it would need artificial intelligence beyond our current capabilities to maintain or repair these systems completely autonomously. However it is perfectly feasible to design them from the outset to be maintainable this way; physically designed to be modular with components easily extracted by another machine and many embedded wired or wireless sensors giving the ability to diagnose faults on all components and assemblies. |
| − | + | Many parameters can now be sensed with solid-state sensors, manufactured on tiny silicon chips. They cost very little and can be hidden away effectively. If the signature from multiple sensors relating to each component function of a machine is known when operating normally, the source of any problems can be pin-pointed with reasonable accuracy. Vibration, temperature, rotation, pressure, distance, current and acceleration. The defective parts, or whole assemblies can then be replaced with no human intervention. | |
The physical aspects of the machines would also have to be designed with autonomous replacement in mind, with magnetic, RFID or optic cues that can be read by a repair robot, and modular physical design of components that can easily be extracted and replaced. For instance, a gearbox that slots in or out as a single cartridge. | The physical aspects of the machines would also have to be designed with autonomous replacement in mind, with magnetic, RFID or optic cues that can be read by a repair robot, and modular physical design of components that can easily be extracted and replaced. For instance, a gearbox that slots in or out as a single cartridge. | ||
<noinclude>{{refresh|Closed-loop automation}}</noinclude> | <noinclude>{{refresh|Closed-loop automation}}</noinclude> | ||
Revision as of 15:40, 4 December 2006
If complicated physical systems were able to be serviced and repaired completely automatically there would be many advantages. There would be higher productivity and efficiency without people in the loop - we tend to slow things down and are error prone; also people could be freed up to do something less menial; and the systems could scale quickly when more capacity is needed.
Machines today, such as industrial machinery, are designed to be looked after and serviced by people, and it would need artificial intelligence beyond our current capabilities to maintain or repair these systems completely autonomously. However it is perfectly feasible to design them from the outset to be maintainable this way; physically designed to be modular with components easily extracted by another machine and many embedded wired or wireless sensors giving the ability to diagnose faults on all components and assemblies.
Many parameters can now be sensed with solid-state sensors, manufactured on tiny silicon chips. They cost very little and can be hidden away effectively. If the signature from multiple sensors relating to each component function of a machine is known when operating normally, the source of any problems can be pin-pointed with reasonable accuracy. Vibration, temperature, rotation, pressure, distance, current and acceleration. The defective parts, or whole assemblies can then be replaced with no human intervention.
The physical aspects of the machines would also have to be designed with autonomous replacement in mind, with magnetic, RFID or optic cues that can be read by a repair robot, and modular physical design of components that can easily be extracted and replaced. For instance, a gearbox that slots in or out as a single cartridge.
