# US 10,478,887 B2 · Die abnormality prediction system, press machine provided with the same, and die abnormality prediction method > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,478,887 B2 - Document ID: US10478887B2 - Status: Granted - Kind: B2 - Application number: 15/204,062 - Filed: 2016-07-07 - Published: 2017-02-09 - Granted: 2019-11-19 - Earliest claimed: 2015-07-07 - Assignees: Nidec-Shimpo Corporation; Nidec Corporation - Applicants: Nidec-Shimpo Corporation; Nidec Corporation - Inventors: Tetsuya Iwakuro; Takayuki Sawada; Masayuki Otani; Kazuyoshi Koga; Takafumi Maeda; Takeshi Honda; Nobuyuki Kita - Web page: https://patentgrep.com/patent/US10478887B2 ## CPC - B21D 55/00: Safety devices protecting the machine or the operator, specially adapted for apparatus or machines dealt with in this subclass (for presses in general B30B; safety devices in general F16P) - B21D 22/02: Stamping using rigid devices or tools - B21D 28/24: Perforating, i.e. punching holes - G01L 5/0076: {Force sensors associated with manufacturing machines (G01L5/0066, G01L5/0071 and B23Q17/09 take precedence; for the specific machine or operation involved see relevant class, e.g. B21 - B42)} - G01N 29/04: Analysing solids (using acoustic emission techniques G01N29/14) - G01N 29/14: using acoustic emission techniques {(echo of particles G01N29/046; measuring mechanical vibrations or acoustic waves in solids in general G01H1/00)} - G01N 29/4472: {Mathematical theories or simulation} - G01N 2291/0234: Metals, e.g. steel - G01N 2291/0289: Internal structure, e.g. defects, grain size, texture - G01N 2291/2698: Other discrete objects, e.g. bricks - B21D: WORKING OR PROCESSING OF SHEET METAL OR METAL TUBES, RODS OR PROFILES WITHOUT ESSENTIALLY REMOVING MATERIAL; PUNCHING METAL (working or processing of wire B21F) - G01L: MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE (weighing G01G) - G01N: INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES (measuring or testing apparatus or processes other than immunoassay, involving enzymes or microorganisms C12M, C12Q) ## Abstract Provided is an abnormality prediction system and an abnormality prediction method that are capable of predicting an abnormality occurring in a die that is used in a press machine. A die abnormality prediction system (50) includes: an acoustic emission (AE) sensor (62) configured to detect an elastic wave that occurs in a processing portion of a die during processing performed by a press machine using the die; a stamping load detection sensor (61) configured to detect a parameter (a stamping load) other than a parameter regarding the elastic wave, out of parameters regarding a state of the die during the processing performed by the press machine using the die; a score calculation unit (56) configured to calculate an abnormality prediction score of the die based on an output signal from the AE sensor (62) and an output signal from the stamping load detection sensor (61); and an abnormality prediction unit (57) configured to predict an abnormality occurring in the die, based on a result of the calculation performed by the score calculation unit (56). ## Claims ### Claim 1 A die abnormality prediction system for predicting an abnormality in a die that is used in a press machine, comprising: an acoustic emission (AE) sensor configured to detect an elastic wave that occurs in a processing portion of the die during stamping performed by the press machine using the die; a stamping state detection unit configured to detect a parameter other than a parameter regarding the elastic wave, out of parameters regarding a state of the die during the stamping performed by the press machine using the die; a score calculation unit configured to calculate an abnormality prediction score of the die based on an output signal from the AE sensor and an output signal from the stamping state detection unit; and an abnormality prediction unit configured to predict an abnormality occurring in the die, based on a result of the calculation performed by the score calculation unit. ### Claim 2 (depends on 1) The die abnormality prediction system according to claim 1, wherein the score calculation unit is configured to calculate weighted values by assigning a weight to a value calculated based on the output signal from the AE sensor, and to a value calculated based on the output signal from the stamping state detection unit, and to obtain a sum of the weighted values as the abnormality prediction score. ### Claim 3 (depends on 1) The die abnormality prediction system according to claim 1, wherein the die is a die that is used for shearing. ### Claim 4 (depends on 1) The die abnormality prediction system according to claim 1, wherein the stamping state detection unit is a force sensor configured to detect a stamping load during the stamping performed by the press machine using the die. ### Claim 5 (depends on 4) The die abnormality prediction system according to claim 4, wherein the score calculation unit is configured to calculate weighted values by assigning a weight to an area value obtained by calculating an area of power values in each frequency band, using a result of power spectrum calculation based on the output signal from the AE sensor, and to a maximum amplitude of the stamping load obtained based on the output signal from the stamping state detection unit, and to obtain a sum of the weighted values as the abnormality prediction score. ### Claim 6 (depends on 1) The die abnormality prediction system according to claim 1, wherein the stamping state detection unit is a die position detection sensor configured to detect a position of the die during the stamping performed by the press machine using the die, in terms of a direction in which the stamping is performed. ### Claim 7 (depends on 6) The die abnormality prediction system according to claim 6, wherein the score calculation unit is configured to calculate weighted values by assigning a weight to a power value of a predetermined frequency band obtained by performing a power spectrum calculation based on the output signal from the AE sensor, and to position data obtained based on the output signal from the die position detection sensor, and to obtain a sum of the weighted values as the abnormality prediction score. ### Claim 8 (depends on 1) A press machine provided with the die abnormality prediction system according to claim 1. ### Claim 9 A die abnormality prediction method for predicting an abnormality in a die that is used in a press machine, comprising: an elastic wave component obtaining step of detecting, using an acoustic emission (AE) sensor, an elastic wave that occurs in a processing portion of the die during stamping performed by the press machine using the die, and obtaining a value regarding the elastic wave based on an output signal from the AE sensor; a die state component obtaining step of detecting, using a stamping state detection unit, a parameter other than a parameter regarding the elastic wave, out of parameters regarding a state of the die during the stamping performed by the press machine using the die, and obtaining a value regarding the state of the die based on the output signal from the stamping state detection unit; a score calculation step of calculating an abnormality prediction score of the die based on the value obtained in the elastic wave component obtaining step and the value obtained in the die state component obtaining step; and an abnormality prediction step of predicting an abnormality occurring in the die, based on a result of the calculation performed in the score calculation step. ### Claim 10 (depends on 9) The die abnormality prediction method according to claim 9, wherein in the score calculation step, weighted values are calculated by assigning a weight to a value obtained in the elastic wave component obtaining step and to a value obtained in the die state component obtaining step, and a sum of the weighted values is obtained as the abnormality prediction score. ### Claim 11 (depends on 9) The die abnormality prediction method according to claim 9, wherein the die is a die that is used for shearing. ### Claim 12 (depends on 9) The die abnormality prediction method according to claim 9, wherein the stamping state detection unit is a force sensor that is configured to detect a stamping load during the stamping performed by the press machine using the die. ### Claim 13 (depends on 12) The die abnormality prediction method according to claim 12, wherein in the score calculation step, a power area value is obtained by calculating an area of power values in each frequency band, using a result of power spectrum calculation based on the output signal from the AE sensor, a maximum amplitude of the stamping load is obtained based on the output signal from the stamping state detection unit, and weighted values are obtained by assigning a weight to the power area value and to the maximum amplitude, and a sum of the weighted values is obtained as the abnormality prediction score. ### Claim 14 (depends on 9) The die abnormality prediction method according to claim 9, wherein the stamping state detection unit is a die position detection sensor configured to detect a position of the die during the stamping performed by the press machine using the die. ### Claim 15 (depends on 14) The die abnormality prediction method according to claim 14, wherein in the score calculation step, weighted values are calculated by assigning a weight to a power value of a predetermined frequency band obtained by performing a power spectrum calculation based on the output signal from the AE sensor, and to position data obtained based on the output signal from the die position detection sensor, and a sum of the weighted values is obtained as the abnormality prediction score.