Machine learning device, machine learning system, and machine learning method
一种机器学习、学习单元的技术，应用在辅助装置、通用控制系统、控制/调节系统等方向，能够解决无法适当地照射、内部反射镜劣化、内部反射镜安装位置不适当等问题
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
no. 2 Embodiment approach ＞
[0133] Next, a second embodiment will be described. In addition, since the first embodiment is common to the second embodiment in terms of basic configurations, repeated descriptions of the common parts will be omitted below, and the differences between the first embodiment and the second embodiment will be described in detail.
[0134] In the above-described first embodiment, the learning unit 13 performed machine learning using the image data of the burnt pattern formed in the acrylic block 40 as input data. Alternatively, the state observation unit 11 may acquire data on intensity distribution observed by other observation means such as a beam profiler, and the learning unit 13 may use the data on the intensity distribution as input data to perform machine learning.
[0135] In general, due to industrial use of CO 2 Beam analyzers for lasers are expensive, so when the observed object is CO 2 In the case of laser light, observation is performed using an acrylic block 40 as...
Deformed example 1
[0147] In the above-described embodiment, the learning unit 13 takes as input data the image data of six images of the burn pattern taken from the three directions of the mutually orthogonal X axis, Y axis, and Z axis in the Cold mode and the Hot mode, respectively. Machine learning was performed. It is also possible to reduce the amount of image data as input data.
[0148] For example, in either the Cold mode or the Hot mode, machine learning can be performed by using as input data three images of burnt patterns captured from three directions of the mutually orthogonal X-axis, Y-axis, and Z-axis.
[0149] In addition, it is also possible to have a configuration in which various cases such as "the case where three images for the Cold mode are used as input data" and "the case where three images for the Hot mode are used as input data" may be used. ", "The case where 6 images of the Cold mode and the Hot mode are set as input data". When a mixed structure like this is used, ...
Deformed example 2
[0152] In each of the above-mentioned embodiments, the respective functions of the machine learning device 10 , the laser processing machine 20 , and the imaging device 30 are realized by separate devices, but some or all of these functions may be realized by an integrated device.
[0153] In addition, one machine learning device 10 can be connected to a plurality of laser processing machines 20 and imaging devices 30 . Then, one machine learning device 10 can perform learning based on training data acquired from a plurality of laser processing machines 20 and imaging devices 30 . Furthermore, in the above-mentioned embodiment, one machine learning device 10 is illustrated, but there may be a plurality of machine learning devices 10 . That is to say, the relationship between the machine learning device 10 and the laser processing machine 20 and the photographing device 30 may be one-to-one, one-to-many, or many-to-many.
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More