US 12,350,872 B2
Abnormality detection apparatus, abnormality detection method, and non-transitory computer readable recording medium
Takashi Ochiiwa, Tokyo (JP); Soma Mitani, Tokyo (JP); and Masato Kawakita, Tokyo (JP)
Assigned to The Japan Steel Works, Ltd., Tokyo (JP)
Appl. No. 17/772,723
Filed by The Japan Steel Works, Ltd., Tokyo (JP)
PCT Filed Oct. 30, 2020, PCT No. PCT/JP2020/040741
§ 371(c)(1), (2) Date Apr. 28, 2022,
PCT Pub. No. WO2021/090766, PCT Pub. Date May 14, 2021.
Claims priority of application No. 2019-201763 (JP), filed on Nov. 6, 2019.
Prior Publication US 2022/0402184 A1, Dec. 22, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. B29C 45/76 (2006.01)
CPC B29C 45/768 (2013.01) [B29C 2945/76033 (2013.01); B29C 2945/76163 (2013.01); B29C 2945/76187 (2013.01)] 9 Claims
OG exemplary drawing
 
9. A non-transitory computer readable recording medium storing a computer program for causing a computer to execute a process of detecting an abnormality of a ball screw provided in an injection molding machine, the computer program causing the computer to execute processes of:
operating the injection molding machine to perform injection molding;
detecting an alternating current of a motor for applying a driving force to the ball screw during operation of the injection molding machine;
performing frequency analysis on a detected alternating current; and
detecting an abnormality of the ball screw based on information related to a distribution of frequency components obtained by frequency analysis, and information related to a distribution of frequency components obtained by frequency analysis of an alternating current detected when the ball screw is normal comprising:
calculating a statistical distance between a statistic of the distribution of frequency components obtained by frequency analysis of the alternating current detected by a current sensor and a statistic of the distribution of frequency components obtained by frequency analysis of the alternating current detected when the ball screw is normal, and detecting an abnormality of the ball screw based on the calculated statistical distance.