System and method for unsupervised prediction of machine failures

A non-transitory computer readable medium having stored thereon instructions for causing a processing circuitry to perform a process, the process comprising:

• monitoring sensory inputs related to at least one machine;
• analyzing, via at least unsupervised machine learning, the monitored sensory inputs, wherein the output of the unsupervised machine learning includes at least one indicator, and wherein analyzing the monitored sensory inputs further comprises preprocessing the monitored sensory inputs, wherein the preprocessing includes extracting at least one feature raw sensory data;
• identifying, based on the at least one indicator, at least one pattern;
• and
• determining, based on the at least one pattern and the monitored sensory inputs, at least one prediction of machine failure that will occur in the future;
• and
• selecting, based on the preprocessed sensory inputs, at least one unsupervised machine learning model from an available plurality of unsupervised machine learning models, wherein the unsupervised machine learning includes running the selected at least one unsupervised machine learning model using the preprocessed sensory inputs;
• wherein each selected at least one unsupervised machine learning model is selected for at least one parameter represented by the preprocessed sensory inputs.

A system for unsupervised prediction of machine failures, comprising:

• a processing circuitry;
• and
• a memory, the memory containing instructions that, when executed by the processing circuitry, configure the system to:
• monitor sensory inputs related to at least one machine;
• analyze, via at least unsupervised machine learning, the monitored sensory inputs, wherein the output of the unsupervised machine learning includes at least one indicator, and wherein analyzing the monitored sensory inputs further comprises preprocessing the monitored sensory inputs, wherein the preprocessing includes extracting at least one feature raw sensory data;
• identify, based on the at least one indicator, at least one pattern;
• and
• determine, based on the at least one pattern and the monitored sensory inputs, at least one prediction of machine failure that will occur in the future;
• and
• select, based on the preprocessed sensory inputs, at least one unsupervised machine learning model from an available plurality of unsupervised machine learning models, wherein the unsupervised machine learning includes running the selected at least one unsupervised machine learning model using the preprocessed sensory inputs;
• wherein each selected at least one unsupervised machine learning model is selected for at least one parameter represented by the preprocessed sensory inputs.