US 2018/0121793 A1 · METHOD AND SYSTEM FOR MACHINE FAILURE PREDICTION

Abstract

Embodiments of the invention provide a method and system for machine failure prediction. The method comprises: identifying a plurality of basic memory depth values based on a machine failure history; ascertaining a basic weight range for each of the plurality of basic memory depth values according to a pre-stored table including a plurality of mappings each mapping between a basic memory depth value and a basic weight range, or a predetermined formula for calculating the basic weight range based on the corresponding basic memory depth value; ascertaining a composite initial weight range by calculating an average weight range of the ascertained basic weight range for each identified basic memory depth value; generating initial weights based on the composite initial weight range; and predicting a future failure using a Back Propagation Through Time (BPTT) trained Recurrent Neural Network (RNN) based on the generated initial weights.

Claims21

Dependent claims

A method for machine failure prediction, the method comprising:

identifying, by a first processor in a first computer system, a plurality of basic memory depth values based on a machine failure history;
ascertaining, by the first processor, a basic weight range for each of the plurality of basic memory depth values according to a pre-stored table which is stored in a memory and includes a plurality of mappings wherein each mapping relates a basic memory depth value to a basic weight range, or according to a predetermined formula for calculating the basic weight range based on the corresponding basic memory depth value;
ascertaining, by the first processor, a composite initial weight range by calculating an average weight range of the ascertained basic weight range for each identified basic memory depth value;
generating, by the first processor, initial weights based on the composite initial weight range;
and
predicting, by the first processor, a future failure using a Back Propagation Through Time (BPTT) trained Recurrent Neural Network (RNN) based on the generated initial weights.

3 more elements

A system for machine failure prediction, the system comprising:

a first processor and a memory communicably coupled thereto,
wherein the first memory is configured to store data to be executed by the first processor,
wherein the first processor is configured to
identify a plurality of basic memory depth values based on a machine failure history;
ascertain a basic weight range for each of the plurality of basic memory depth values according to a pre-stored table which is stored in the memory and includes a plurality of mappings wherein each mapping relates a basic memory depth value to a basic weight range, or according to a predetermined formula for calculating the basic weight range based on the corresponding basic memory depth value;
ascertain a composite initial weight range by calculating an average weight range of the ascertained basic weight range for each identified basic memory depth value;
generate initial weights based on the composite initial weight range;
and
predict a future failure using a Back Propagation Through Time (BPTT) trained Recurrent Neural Network (RNN) based on the generated initial weights.

6 more elements

Dependencies are inferred from the claim text.

Method and system for machine failure prediction

Life of this patent

Method and system for machine failure prediction

Life of this patent

Abstract

Claims21