Data processing for industrial machine learning
A computer-implemented method for automating the development of industrial machine learning applications includes one or more sub-methods that, depending on the industrial machine learning problem, may be executed iteratively. These sub-methods include at least one of a method to automate the data cleaning in training and later application of machine learning models, a method to label time series (in particular signal data) with help of other timestamp records, feature engineering with the help of process mining, and automated hyper-parameter tuning for data segmentation and classification.
1 . A computer-implemented method for developing a machine learning model for an industrial asset, the method comprising:
acquiring a first time series of data from a sensor of an industrial asset;
processing the first time series of data to obtain an event log, wherein processing the first time series of data comprises encoding the time series of data into discrete events associated with a change in a state of the industrial asset;
applying process mining to the event log to provide a bottleneck identification, the bottleneck identification comprising bottlenecks in batch processes and deviations from standard operating procedures of the industrial asset;
applying the process mining to the event log to provide conformity analysis relative to a learned normal operation of the industrial asset;
continuously determining a condition indicator of the industrial asset based on the conformity analysis and the bottleneck identification, wherein the condition indicator indicates a deviation of performance of the industrial asset from a baseline;
developing a first machine learning model to monitor the industrial asset with the continuously determined condition indicator being an input parameter of the first machine learning model; and
applying the first machine learning model to determine potential improvements, to perform condition-based monitoring, and/or to perform predictive maintenance of the industrial asset.
2 . The computer-implemented method of claim 1 , wherein applying the first machine learning model further includes to determine process deviations and/or to predict how a batch process will evolve.
3 . The computer-implemented method of claim 1 , wherein the processing of the first time series of data to obtain the event log comprises encoding the first time series of data by applying symbolic aggregate approximation or artificial intelligence techniques.
4 . The computer-implemented method of claim 3 , wherein the processing of the first time series of data to obtain the event log further comprises performing abstractions on the encoded first time series of data.
5 . The computer-implemented method of claim 4 , wherein the abstractions performed on the encoded first time series of data comprise data aggregations and/or noise suppression filters.
6 . The computer-implemented method of claim 1 , further comprising:
acquiring a second time series of data;
cleaning the second time series of data to obtain a third time series of data; and
training a data cleaning machine learning model using a plurality of first training samples;
wherein a first training sample comprises a clean data point from the third time series of data and a plurality of raw data points from the second time series of data.
7 . The computer-implemented method of claim 6 , wherein the cleaning of the second time series of data comprises handling missing values, removing noise, and/or removing outliers.
8 . The computer-implemented method of claim 1 , further comprising:
acquiring a fourth time series of data from the sensor or from a control system associated with the industrial asset; and
applying a data cleaning machine learning model to the fourth time series of data to obtain the first time series of data.
9 . The computer-implemented method of claim 1 , further comprising:
acquiring a first set of labels for training a machine learning model for automatic labelling;
acquiring one or more data sources;
extracting a first set of features from the one or more data sources; and
training the machine learning model for automatic labelling using a plurality of second training samples;
wherein a second training sample comprises a label from the first set of labels and one or more features from the first set of features.
10 . The computer-implemented method of claim 9 , wherein the one or more data sources comprise at least one of a shift book, an alarm list, an events list, and/or a data source from a computerized maintenance management system; and/or wherein the machine learning model for automatic labelling is a probabilistic model.
11 . The computer-implemented method of claim 9 , further comprising:
extracting a second set of features from the one or more data sources; and
applying the machine learning model for automatic labelling to features from the second set of features to obtain a second set of labels.
12 . The computer-implemented method of claim 9 , wherein the first machine learning model is trained using a plurality of third training samples; and wherein a third training sample comprises a label from the first or second sets of labels and/or the condition indicator of the industrial asset.
13 . The computer-implemented method of claim 1 wherein acquiring the first time series of data further includes acquiring data from a control system associated with the industrial asset.