ISSN:
1572-8145
Keywords:
Process control
;
fuzzy logic
;
neural network
;
frequency trimming
;
crystal resonator
Source:
Springer Online Journal Archives 1860-2000
Topics:
Mechanical Engineering, Materials Science, Production Engineering, Mining and Metallurgy, Traffic Engineering, Precision Mechanics
Notes:
In the development of a process diagnostic system to monitor the condition of the frequency-trimming process in the production of crystal resonators, fuzzy logic can be applied in the recognition of unnatural statistical patterns in the control charts. The heuristics for reasoning are based on the principles behind statistical process control. Using expert experience and knowledge to troubleshoot the causes of problems, one can associate a characteristic chart pattern with a set of known physical causes. As these causes related to the unnatural statistical patterns are not independent of each other, it is difficult to precisely associate the chart distribution patterns with the known causes. Furthermore, as the trimming process is dynamic, the causes of problems dealt with will vary with time. Hence, by means of neural networks, it is possible to associate fuzzily deduced chart patterns with plausible causes to achieve optimum operating conditions.
Type of Medium:
Electronic Resource
URL:
http://dx.doi.org/10.1007/BF00123951
Permalink
