| CPC G05B 23/0283 (2013.01) [G05B 19/4183 (2013.01); G05B 19/4188 (2013.01); G05B 19/41885 (2013.01)] | 18 Claims |
|
1. A method of facilitating predictive maintenance of a testing machine, the method comprising:
receiving a plurality of tested data of a plurality of products being tested by the testing machine, wherein each tested data comprises one or more output parameters generated by the testing machine on providing one or more input parameters associated with a respective product of the plurality of products;
applying a predictive model, having predictive model parameters, upon the plurality of tested data, including:
performing a latent variable modelling technique on the plurality of tested data;
predicting a plurality of future test data corresponding to the plurality of products based on the performed latent variable modelling technique, wherein the plurality of future test data is latent representation of the plurality of tested data;
determining a deviation between the plurality of tested data and the plurality of future test data, wherein the deviation indicates fault in the testing machine;
determining a fault level of the testing machine by comparing the deviation with a predefined threshold, wherein the predefined threshold indicates a maximum tolerance level up to which the testing machine is considered to be fit; and
comparing, based on the determined fault level of the testing machine, one or more output parameters of the plurality of future test data vis-a-vis reference data, wherein the reference data indicates standard parameter range of the one or more components of the testing machine; and
determining, during run-time, the maintenance required for the testing machine based on the comparison.
|