Method for verifying bad pattern in time series sensing data and apparatus thereof
Abstract
A method for verifying bad pattern in time series sensing data by calculating a bad pattern error rate, which can be applied to the time series sensing data measured and produced from a predetermined sensor provided in predetermined equipment, and an apparatus thereof are provided. The method includes receiving information on the bad pattern applied to time series sensing data measured by a suspicious sensor, accessing the time series sensing data of each product, generated by the suspicious sensor during a verification period, calculating similarity measures between the bad pattern based on the bad pattern information and the time series sensing data for each product, and calculating an error rate of the bad pattern based on the similarity measures.
Claims
exact text as granted — not AI-modifiedWhat is claimed is:
1 . A method for monitoring sensing data of equipment, the method comprising:
receiving information on a bad pattern applied to sensing data measured from a sensor; receiving sensing data information from the sensor; calculating similarity measures of an Euclidean ratio, a correlation and a trend similarity between the bad pattern based on bad pattern information and the sensing data, each of the Euclidean ratio, the correlation and the trend similarity having a value in a range between 0, which means non-similarity, and 1 , which means sameness; and generating a warning signal when a calculated value of at least one from among the Euclidean ratio, the correlation and the trend similarity is 1, wherein the trend similarity is a measured value pattern one of increasing and decreasing according to a passage of time.
2 . Production equipment comprising:
one or more sensors generating sensing data; a sensing data stream receiving unit configured to receive a sensing data stream measured from the one or more sensors; a bad pattern information receiving unit configured to receive information on a bad pattern applied to sensing data measured by each of the one or more sensors; a similarity measure calculator configured to calculate similarity measures of an Euclidean ratio, a correlation and a trend similarity between the bad pattern based on the bad pattern information and the sensing data, each of the Euclidean ratio, the correlation and the trend similarity having a value in a range between 0, which means non-similarity, and 1, which means sameness; and a warning signal output unit configured to generate a warning signal when a calculated value of at least one from among the Euclidean ratio, the correlation and the trend similarity is 1.
3 . The production equipment of claim 2 , further comprising a stoppage controller configured to receive the warning signal from the warning signal output unit and generate a control signal for controlling a production operation to be stopped.
4 . The production equipment of claim 2 , wherein the sensing data based on the bad pattern information has a pattern including measured values in a range between an upper limit and a lower limit of a predefined measured value.
5 . A reference pattern detecting apparatus comprising:
a sensing data stream receiving unit configured to receive a sensing data stream measured from one or more sensors; a reference pattern information receiving unit configured to receive information on a reference pattern applied to the sensing data generated from each of the one or more sensors; and a similarity measure calculator configured to calculate and output similarity measures of an Euclidean ratio, a correlation and a trend similarity between the reference pattern based on reference pattern information and the sensing data, each of the Euclidean ratio, the correlation and the trend similarity having a value in a range between 0, which means non-similarity, and 1 , which means sameness.
6 . The reference pattern detecting apparatus of claim 5 , further comprising a warning signal output unit configured to generate and output a warning signal when the value of at least one from among the Euclidean ratio, the correlation and the trend similarity, calculated by the similarity measure calculator, is 1.
7 . The reference pattern detecting apparatus of claim 5 , wherein the one or more sensors include a first sensor measuring energy consumption of a building.
8 . The reference pattern detecting apparatus of claim 6 , wherein the one or more sensors include a first sensor measuring building energy consumption and a second sensor measuring an internal environment parameter of a building, the reference pattern information receiving unit receives first reference pattern information applied to the first sensor and second reference pattern information applied to the second sensor, the similarity measure calculator calculates and outputs similarity measures of an Euclidean ratio, a correlation and a trend similarity between a first reference pattern based on the first reference pattern information and the sensing data of the first sensor, and calculates and outputs similarity measures of the Euclidean ratio, the correlation and the trend similarity between a second reference pattern based on the second reference pattern information and the sensing data of the second sensor, and the warning signal output unit generates and outputs a warning signal when the calculated value of at least one from among the Euclidean ratio, the correlation and the trend similarity of the first sensor is 1 and the calculated value of at least one from among the Euclidean ratio, the correlation and the trend similarity of the second sensor is 1.Join the waitlist — get patent alerts
Track US2017060664A1 — get alerts on status changes and closely related new filings.
We store only your email — no account needed. See our privacy policy.