Label rectification and classification/prediction for multivariate time series data

A non-transitory computer readable medium having stored thereon instructions which when executed by a control processor cause the control processor to perform a method of directional label rectification with adaptive graph for multivariate time-series data, the method comprising:

• obtaining an input matrix containing sensor data, the sensor data representing monitored time-series data of one or more features of an asset;
• obtaining a first event matrix containing event data, the event data containing failure event information corresponding to respective ones of the one or more features;
• identifying in the input matrix at least one feature pattern and a first corresponding time stamp;
• identifying in the first event matrix at least one fault signature and a second corresponding time stamp;
• if both a label matrix and an affinity matrix are known, then optimizing a weight matrix,
• else if both the label matrix and the weight matrix are known, then optimizing the affinity matrix,
• else optimizing the label matrix;
• creating a dynamically rectified event matrix by applying the label matrix, the affinity matrix, and the weight matrix to the first event matrix;
• and
• applying the dynamically rectified event matrix to forecast a future status of the asset.

A system for directional label rectification with adaptive graph for multivariate time-series data, the system comprising:

• a server including a control processor, the server in communication with a data store across an electronic communication network;
• the data store including sensor data records, the sensor data records including monitored data of one or more features of at least one asset;
• the data store including executable instructions, the executable instructions configured to cause the control processor to perform a method including:
• obtaining an input matrix containing sensor data, the sensor data representing monitored time-series data of one or more features of an asset;
• obtaining a first event matrix containing event data, the event data containing failure event information corresponding to respective ones of the one or more features;
• identifying in the input matrix at least one feature pattern and a first corresponding time stamp;
• identifying in the first event matrix at least one fault signature and a second corresponding time stamp;
• if both a label matrix and an affinity matrix are known, then optimizing a weight matrix,
• else if both the label matrix and the weight matrix are known, then optimizing the affinity matrix,
• else optimizing the label matrix;
• creating a dynamically rectified event matrix by applying the label matrix, the affinity matrix, and the weight matrix to the first event matrix;
• and
• applying the dynamically rectified event matrix to forecast a future status of the asset.