Method and apparatus for pump failure prediction

Abstract

Proposed is a pump failure prediction apparatus which includes at least one processor, a storage, which is communicably connected with the processor and stores a program code which operates in the processor, and a communicator, which is communicably connected with the processor, wherein the program code includes a data collection module, and an abnormality detection module which detects three abnormalities. The first abnormality appears before failure occurrence by inputting the real-time data into a first model which has performed supervised learning of history data. The second abnormality appears outside of a normal operation range of the pump by inputting the real-time data to a second, which has performed unsupervised learning of normal operation data. The third abnormality appears outside an initial normal operation range of the pump by inputting the real-time data to a third model, which has performed unsupervised learning of initial operation data.

What is claimed is: 
     
         1 . A pump failure prediction apparatus, comprising:
 at least one processor;   a storage, which is communicably connected with the processor and stores a program code which operates in the processor; and   a communicator, which is communicably connected with the processor,   wherein the program code comprises:
 a data collection module which collects real-time data related to a state of a pump which is installed in an oil well and operates; and 
 an abnormality detection module which detects three abnormalities, the three abnormalities comprising a first abnormality appearing before failure occurrence by inputting the real-time data into a first model, which has performed supervised learning of history data, a second abnormality outside of a normal operation range of the pump by inputting the real-time data to a second model, which has performed unsupervised learning of normal operation data, and a third abnormality outside of an initial normal operation range of the pump by inputting the real-time data to a third model, which has performed unsupervised learning of initial operation data. 
   
     
     
         2 . The apparatus of  claim 1 , wherein the history data comprise two types of operation data, the operation data labeled as normal and operation data labeled as abnormal,
 the first model utilizes linear discriminant analysis to classify the operation data comprised in the history data as a normal class or an abnormal class, and   the abnormality detection module determines that the first abnormality occurs when the real-time data are classified as the abnormal class according to linear discriminant criteria generated by the first model.   
     
     
         3 . The apparatus of  claim 1 , wherein the normal operation data are operation data obtained while the pump operates in a normal state,
 the second model is generated through obtaining an average of a plurality of normal section errors between original operation data (the normal operation data) and reconstructed operation data (an reconstruction data) calculated after application of a principal component analysis,   the principal component analysis is applied to the original operation data to obtain feature vectors,   based on the feature vectors, the second model reconstructs reconstruction data, and a process of obtaining a normal section error between the original operation data and the reconstructed operation data is repeated at every time step of the operation data in order to obtain the plurality of normal section errors, and   the abnormality detection module determines that the second abnormality occur when an error level of real-time data increases over time when real-time feature vectors are obtained by applying the principal component analysis to the real-time data, and   based on the real-time feature vectors, real-time reconstruction data are obtained; a real-time error between the real-time data and the real-time reconstruction data is obtained; the error level is obtained by dividing the real-time error by an average of the plurality of normal section errors generated by the second model; and the error level is recorded over time.   
     
     
         4 . The apparatus of  claim 1 , wherein the initial operation data are operation data obtained for a predetermined period from time at which the pump is assumed to operate normally in a stable condition without any issues,
 the third model is trained by applying principal component analysis to the data, feature vectors which consist of at least two components are obtained,   a center point of the feature vectors is obtained based on distribution of the vectors in multi-dimensional space, and   based on the distribution of the feature vectors and the center point of the initial operation data, the third model calculates a Mahalanobis distance from the center point to each feature vectors of the data, wherein from the range of the Mahalanobis distance, a reference distance is statistically determined, wherein the principal component analysis is applied to the real-time operation data and the third model calculates Mahalnobis distance from the center point to each real-time data and determines whether the state of a pump is abnormal if the Mahalanobis distance is greater than the reference distance.   
     
     
         5 . The apparatus of  claim 4 , wherein the reference distance is determined as a multiple of an average value of a plurality of Mahalanobis distances obtained from the initial operation data. 
     
     
         6 . The apparatus of  claim 1 , wherein the program code further comprises a reporting module providing a notification that an abnormality is detected in the pump based on an output of the abnormality detection module. 
     
     
         7 . The apparatus of  claim 3 , wherein the second model is generated and trained even before a pump normally operates by using normal operation data of another pump, which operates in a similar environment, and is regenerated by updating the normal operation data with its own operation data in a normal state. 
     
     
         8 . The apparatus of  claim 1 , wherein the program code further comprises: a training data generation module which generates training data for training the first model, the second model, and the third model by using preprocessed operation data in such a manner that the real-time data are recorded over time to generate operation data, and the operation data are preprocessed, and
 the training data generation module generates the history data to generate training data of the first model, in such a manner that time series data are standardized in the operation data, wherein operation data corresponds to a failure state recorded previously are labeled as abnormal, and data of a normal operation section are labeled as normal;   the training data generation module further generates the normal operation data to generate training data of the second model, in such a manner that a principal component analysis is applied to the operation data at every time step thereof to extract feature vectors; wherein reconstruction data are obtained from reconstructing the feature vectors; wherein an error between the reconstruction data and the operation data is calculated; wherein when the error is smaller than or equal to a reference error, the operation data are comprised in the normal operation data; and when the error is greater than the reference error, the operation data are excluded from the normal operation data; and   the training data generation module further generates operation data, which are collected for a predetermined period from time at which the pump operates in a normal state after the pump is installed, as the initial operation data for generating training data of the third model.   
     
     
         9 . A pump failure prediction method, comprising:
 collecting real-time data related to a state of a pump installed in an oil well;   generating training data by preprocessing operation data collected by recording the real-time data over time;   training a first model, a second model, and a third model by using the training data;   detecting a first abnormality occurring before failure occurrence by inputting the real-time data of the pump to the first model, which has performed supervised learning of history data, detecting a second abnormality outside a normal operation range of the pump by inputting the real-time data of the pump to the second model, which has performed unsupervised learning of a normal operation data, and detecting a third abnormality outside an initial normal operation range of the pump by inputting the real-time data of the pump to the third model, which has performed unsupervised learning of initial operation data; and   providing a notification that abnormality is detected in the pump, based on an output of the detecting of the abnormalities.   
     
     
         10 . The method of  claim 9 , wherein in furtherance of the step of detecting the first abnormality, determining that the first abnormality occurs when the real-time data are classified as an abnormal class according to a linear discriminant criteria generated by the first model, based on the first model, which is a linear discriminant analysis model trained to classify the history data comprising operation data labeled as normal and operation data labeled as abnormal into a normal class and the abnormal class. 
     
     
         11 . The method of  claim 9 , wherein in furtherance of the step of detecting the second abnormality, determining that the second abnormality occurs when an error level of real-time data increases over time when a principal component analysis is applied to the normal operation data comprising operation data obtained while the pump operates in a normal state to obtain feature vectors, wherein reconstruction data are obtained by reconstructing the feature vectors; a process of obtaining a normal section error between the original operation data (the normal operation data) and the reconstructed operation data (the reconstruction data) calculated after application of a principal component analysis is repeated at every time step of the operation data to obtain a plurality of normal section errors; based on the second model generated through training of obtaining an average of the plurality of normal section errors, the principal component analysis is applied to the real-time data to obtain real-time feature vectors; based on the real-time feature vectors, real-time reconstruction data are obtained; a real-time error between the real-time data and the real-time reconstruction data is obtained; the real-time error is divided by the average of the plurality of normal section errors generated by the second model to obtain the error level; and the error level is recorded over time. 
     
     
         12 . The method of  claim 9 , wherein in furtherance of the step of detecting the third abnormality, determining that the third abnormality occurs when a Mahalanobis distance is greater than a reference distance when a principal component analysis is applied to the initial operation data which are operation data obtained for a predetermined period from time at which the pump is installed in the oil well and assumed to operate normally in a stable condition without any issues, based on the distribution of the feature vectors and the center point of the initial operation data, the third model calculates a Mahalanobis distance from the center point to each feature vectors of the data, wherein from the range of the Mahalanobis distance, a reference distance is statistically determined, wherein the principal component analysis is applied to the real-time operation data and the third model calculates Mahalnobis distance from the center point to each real-time data and determines whether the state of a pump is abnormal if the Mahalanobis distance is greater than the reference distance. 
     
     
         13 . The method of  claim 9 , wherein in the step of generating the training data,
 to generate training data of the first model, generating history data in such a manner that time series data are standardized in the operation data, wherein operation data corresponds to a failure state recorded previously are labeled as abnormal, and data of a normal operation section are labeled as normal,   to generate training data of the second model, generating the normal operation data in such a manner that a principal component analysis is applied to the operation data every specific time thereof to extract feature vectors; reconstruction data are obtained from the feature vectors; an error between the reconstruction data and the operation data is calculated; when the error is smaller than or equal to a reference error, the operation data are comprised in the normal operation data; and when the error is greater than the reference error, the operation data are excluded from the normal operation data, and   to generate training data of the third model, collecting operation data for a predetermined period from time at which the pump operates in a normal state after the pump is installed are generated as the initial operation data.   
     
     
         14 . The method of  claim 9 , wherein in the step of training of the second model generating the second model even before a pump normally operates by using normal operation data of another pump, which operates in a similar environment, and regenerating the second model by updating the normal operation data with its own operation data in a normal state.