Difference between revisions of "Advanced automation/Self-maintenance and repair"

From AdCiv
Jump to: navigation, search
Line 1: Line 1:
Most machines today are designed to be looked after and serviced by people, and it would need artificial intelligence beyond our current capabilities to maintain current machinery autonomously. But it is perfectly feasible to design them to contain sensors able to diagnose faults on all components and sub-assemblies, using wired or wireless communication. Parts would also have to be designed with autonomous replacement and repair in mind, with magnetic, RFID or optic cues that can be read by a repair robot.
+
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 humans in the loop - we tend to slow things down and are error prone; people would be freed up to do something less menial; and the systems could scale quickly when more capacity is needed
  
Most parameters can 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 task of a machine is known when operating optimally, the source of any problem can be pin-pointed with reasonable accuracy. These parts, or perhaps whole sub-assemblies can then be replaced.
+
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 maintanable 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.
 +
 
 +
Most parameters can 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. These parts, or perhaps 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

Revision as of 10:13, 27 September 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 humans in the loop - we tend to slow things down and are error prone; people would 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 maintanable 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.

Most parameters can 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. These parts, or perhaps 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