Fitting detection method, fitting detection device, and fitting detection system
AssigneePanasonic Intellectual Property Management Co., Ltd.
InventorsKei Tasaka, Yuki Iwamoto, Suguru Nakao, Hiroshi Kunimoto
Life of this patent
Estimating the term…
Abstract
A fitting detection method according to the present disclosure is a fitting detection method for detecting fitting which includes acquiring first data indicating information generated from vibration, acquiring second data output from a learned model by inputting the first data to the learned model having undergone machine learning using at least information generated from vibration generated by normal fitting as teacher data, determining whether or not the first data is related to fitting based on the second data, and determining whether or not normal fitting is performed based on the first data when the first data is related to fitting.
Claims19
A fitting detection method for detecting fitting, the method performed by a processor and comprising:
- acquiring first data indicating information generated from vibration detected by a vibration sensor;
- acquiring second data output from a learned model by inputting the first data to the learned model having undergone machine learning using at least information generated from vibration generated by normal fitting as teacher data;
- classifying whether or not the first data is related to fitting based on the second data;
- and
- determining whether or not normal fitting is performed based on the first data when the first data is related to fitting.
A fitting detection device for detecting fitting, comprising:
- a processor;
- and
- a storage device configured to store an instruction executable by the processor,
- the instruction including
- acquiring first data indicating information generated from vibration detected by a vibration sensor,
- acquiring second data output from a learned model by inputting the first data to the learned model having undergone machine learning using at least information generated from vibration generated by normal fitting as teacher data,
- classifying whether or not the first data is related to fitting based on the second data;
- and
- determining whether or not normal fitting is performed based on the first data when the first data is related to fitting.
A fitting detection system for detecting fitting, comprising:
- a vibration sensor configured to detect vibration;
- a processor;
- and
- a storage device configured to store an instruction executable by the processor,
- the instruction including
- acquiring first data indicating information generated from the vibration detected by the vibration sensor,
- acquiring second data output from a learned model by inputting the first data to the learned model having undergone machine learning using at least information generated from vibration generated by normal fitting as teacher data,
- classifying whether or not the first data is related to fitting based on the second data;
- and
- determining whether or not normal fitting is performed based on the first data when the first data is related to fitting.
Dependencies are inferred from the claim text.