A demo on how M2M Telematics Sensor Data can be used in real-time to calculate MTTF to predict machine failure rate and schedule 'predictive Maintenance'.
Condition based maintenance aims at: Estimating the Failure Rate of assets, with the goal of,
+ finding 'Remaining Useful Life' of assets
+ Scheduling 'Predictive Maintenance'
+ Maintaining 'Right Levels of Inventory' for spare parts
+ Evaluate 'What If' alternate scenarios
+ Determining the right 'Warranty Period' for assets at the design ....
The video covers an 'Electric Locomotive Air-brake' system as a case study to estimate the Mean-Time-To-Failure (MTTF) using the sensor data collected from M2M Telematics Frameworks. Also indicates how 'What If' analysis works for this scenario and how Big Data can improve the cost effectiveness.
More details can be found in Gopalakrishna's Predictive Analytics Journal Paper Publications, available at: gopalakrishna.palem.in/Publications.html
This video continues from the Condition based Maintenance Part 1 and discusses,
+ Predicting the failures in the next year
+ Comparing multiple designs for reliability
+ Calculating the right Warranty period
from historic failure data. More details on Big data M2M Predictive Analytics and its application can be gathered from Gopalakrishna Journal papers at: gopalakrishna.palem.in/Publications.html
GK (Gopalakrishna) demonstrates HBase API usage in this video on Big-data Hadoop framework tutorial series.
Gopalakrishna is a big-data consultant with experience in designing large-scale NOSQL databases, Stream-processing architectures on big-data and hadoop.
Contact Gopalakrishna at: gopalakrishna.palem.in/
M2M Telematics Big Data Predictive Analytics
Demo, Case Study Videos on M2M Telematics and Predictive Analytics by Big Data Expert Gopalakrishna
More from: gopalakrishna.palem.in/Publications.html