Failure predicting apparatus and machine learning device
A fault prediction and machine learning technology, applied in machine learning, neural learning methods, instruments, etc., can solve problems such as inability to predict high-precision faults, achieve high-precision fault prediction, and reduce operating time
Inactive Publication Date: 2019-01-04
FANUC LTD
View PDF2 Cites 8 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, in the techniques disclosed in JP-A-2002-090266 and JP-A-07-051993, failure prediction is performed according to a specific estimation model, and various environmental factors in which the machine operates are not considered. Because of failure prediction, there is a problem that high-precision failure prediction cannot be performed when a failure occurs in an unexpected mode
[0005] In addition, when maintaining a machine, it is necessary to determine which printed circuit board (main board, CPU card, servo card, etc.) constituting the machine is to be operated. In the disclosed technology, it is not helpful to reduce the operation time and cost of maintenance because it does not output the predicted failure of which printed circuit board or component constituting the machine with respect to the environmental factors in which the machine operates. Technology
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0020] Embodiments and drawings of the present invention will be described below.
[0021] figure 1 It is a schematic hardware configuration diagram showing a main part of a failure prediction device and a machine tool controlled by the failure prediction device according to the first embodiment. The failure prediction device 1 can be installed as, for example, a control device (not shown) that manages a plurality of machine tools (not shown) arranged in a factory or the like, and a controller (not shown) that controls a robot (not shown). upper device (host computer, unit controller, etc.) The CPU 11 included in the failure prediction device 1 of the present embodiment is a processor that controls the failure prediction device 1 as a whole. The CPU 11 reads the system / program stored in the ROM 12 via the bus 20, and controls the failure prediction device 1 as a whole according to the system / program. Temporary calculation data and display data are temporarily stored in the ...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The present invention relates to a failure predicting apparatus and a machine learning device, and more particularly to a control device and a machine learning device for predicting failure of a printed circuit board and components constituting a numerical control device. The machine learning device included in the failure predicting apparatus includes a state observing unit that observes, as state variables indicating a current environmental state, operating state data indicating an operating state of the management target device and device configuration data indicating a device configurationof the management target device, a label data acquiring unit that acquires, as label data, maintenance history data indicating a maintenance history of the management target device, and a learning unit that, by using the state variables and the label data, learns a failure timing of a printed circuit board included in the management target device, the operating state data, and the device configuration data such that the failure timing is associated with the operating state data and the device configuration data.
Description
technical field [0001] The present invention relates to a failure prediction device and a machine learning device, and more particularly to a control device and a machine learning device for predicting failures of printed circuit boards and components constituting a numerical control device. Background technique [0002] In order to avoid a decrease in productivity of machines such as numerical controllers and machine tools due to failures, it is strongly required to perform machine maintenance before failures occur. Typically, such advance maintenance is performed on predetermined dates as periodic inspections. In addition, in recent years, there have been proposed techniques for predicting in advance the possibility of occurrence of the same failure in other devices of the same type using information on failures occurring in a certain device. [0003] As a prior art related to machine failure prediction, for example, JP-A-2002-090266 discloses a technique of diagnosing ma...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G05B23/02
CPCG05B23/0224G05B13/0265G05B19/4065G05B23/0229G05B23/024G05B23/0254G05B23/0283G05B2219/37251G06F11/008G06F11/3031G06F11/3058G06F11/3062G06N3/08G05B17/02G06F11/3051G06N20/00
Inventor 五岛数哉
Owner FANUC LTD