Electronic device for predicting occurrence of air leakage of air compressor and method of operating the same

Abstract

An electronic device for predicting an occurrence of air leakage of an air compressor and a method of operating the same are provided. The electronic device includes a processor and a memory configured to store instructions, wherein the instructions, when executed by the processor, may cause the electronic device to obtain suction data about air sucked by an air compressor and emission data about air emitted from the air compressor, determine whether air leakage occurs in the air compressor, based on the suction data and the emission data, obtain air leakage data related to an occurrence of the air leakage from a plurality of sensors mounted on the air compressor, and train a model for predicting the occurrence of the air leakage of the air compressor in advance by matching whether the air leakage occurs to the air leakage data before a predetermined time from a time of the occurrence of the air leakage.

What is claimed is: 
     
         1 . An electronic device comprising:
 a processor; and   a memory configured to store instructions,   wherein the instructions, when executed by the processor, cause the electronic device to:   obtain suction data about air sucked by an air compressor and emission data about air emitted from the air compressor;   determine whether air leakage occurs in the air compressor, based on the suction data and the emission data;   obtain air leakage data related to an occurrence of the air leakage from a plurality of sensors mounted on the air compressor; and   train a model for predicting the occurrence of the air leakage of the air compressor in advance by matching whether the air leakage occurs to the air leakage data before a predetermined time from a time of the occurrence of the air leakage.   
     
     
         2 . The electronic device of  claim 1 , wherein
 the air leakage data is data about items in which a correlation coefficient between the emission data and pieces of data about a plurality of items obtained from the plurality of sensors is greater than a predetermined value, in a time interval where the air leakage has occurred.   
     
     
         3 . The electronic device of  claim 1 , wherein
 the air leakage data comprises data about temperature of air sucked by the air compressor, temperature and pressure of air emitted, temperature and pressure of oil inside the air compressor, and vibration and power consumption of the air compressor.   
     
     
         4 . The electronic device of  claim 2 , wherein the correlation coefficient represents a Spearman correlation coefficient. 
     
     
         5 . The electronic device of  claim 1 , wherein
 the instructions, when executed by the processor, cause the electronic device to determine that the air leakage has occurred when the air compressor emits air while sucking the air, based on the suction data and the emission data.   
     
     
         6 . The electronic device of  claim 1 , wherein
 the instructions, when executed by the processor, cause the electronic device to train the model through a classification algorithm for whether the air leakage occurs after the predetermined time from a time the air leakage data is obtained.   
     
     
         7 . The electronic device of  claim 1 , wherein
 the instructions, when executed by the processor, cause the electronic device to train the model by determining a case in which the air leakage occurs as a first value and a case in which the air leakage does not occur as a second value.   
     
     
         8 . The electronic device of  claim 1 , wherein
 the instructions, when executed by the processor, cause the electronic device to remove an outlier from the air leakage data, based on distribution of the air leakage data in a predetermined time interval.   
     
     
         9 . An electronic device comprising:
 a processor; and   a memory configured to store instructions,   wherein the instructions, when executed by the processor, cause the electronic device to:   obtain air leakage data related to an occurrence of air leakage of an air compressor;   determine a possibility of the air leakage occurring after a predetermined time from a time the air leakage data is obtained, using a model trained to predict the occurrence of the air leakage of the air compressor in advance, by matching whether the air leakage occurs to the air leakage data before the predetermined time from a time of the occurrence of the air leakage of the air compressor; and   output the possibility of the air leakage occurring.   
     
     
         10 . The electronic device of  claim 9 , wherein
 the instructions, when executed by the processor, cause the electronic device to control an amount of air supplied to the air compressor, based on the possibility of the air leakage occurring.   
     
     
         11 . A method of operating an electronic device, the method comprising:
 obtaining suction data about air sucked by an air compressor and emission data about air emitted from the air compressor;   determining whether air leakage occurs in the air compressor, based on the suction data and the emission data;   obtaining air leakage data related to an occurrence of the air leakage from a plurality of sensors mounted on the air compressor; and   training a model for predicting the occurrence of the air leakage of the air compressor in advance by matching whether the air leakage occurs to the air leakage data before a predetermined time from a time of the occurrence of the air leakage.   
     
     
         12 . The method of  claim 11 , wherein
 the air leakage data is data about items in which a correlation coefficient between the emission data and pieces of data about a plurality of items obtained from the plurality of sensors is greater than a predetermined value, in a time interval where the air leakage has occurred.   
     
     
         13 . The method of  claim 11 , wherein
 the air leakage data comprises data about temperature of air sucked by the air compressor, temperature and pressure of air emitted, temperature and pressure of oil inside the air compressor, and vibration and power consumption of the air compressor.   
     
     
         14 . The method of  claim 12 , wherein the correlation coefficient represents a Spearman correlation coefficient. 
     
     
         15 . The method of  claim 11 , wherein
 the determining of whether the air leakage occurs comprises determining that the air leakage has occurred when the air compressor emits air while sucking the air, based on the suction data and the emission data.   
     
     
         16 . The method of  claim 11 , wherein
 the training of the model comprises training the model through a classification algorithm for whether the air leakage occurs after the predetermined time from a time the air leakage data is obtained.   
     
     
         17 . The method of  claim 11 , wherein
 the training of the model comprises training the model by determining a case in which the air leakage occurs as a first value and a case in which the air leakage does not occur as a second value.   
     
     
         18 . The method of  claim 11 , wherein
 the obtaining of the air leakage data comprises removing an outlier from the air leakage data, based on distribution of the air leakage data in a predetermined time interval.