received by the International Bureau on 12 October 2016 (12.10.2016)

CLAIMS

What is claimed is:

1. Canceled.

2. Canceled.

3. Canceled.

4. Canceled.

5. Canceled.

6. Canceled.

7. Canceled.

8. Canceled.

9. In a method of predicting rotor driven equipment issues using data harvested from the equipment the improvement comprising:

a. over a finite time collecting, through a processor, real time data associated with at least one machine wearable sensor associated with a rotor driven equipment;

b. transmitting the data collected at the at least one machine wearable sensor over a communication network to a mobile data collector,

c. sampling, through a processor, the data at random to estimate a maximum value;

d. controlling a sampling error associated with the data to within a predefined value;

e. transforming the data from cartesian to spherical coordinates;

f. transmitting the data to a machine learning engine associated with a computer database hosting the collected real time data and historical data for the equipment;

g. analyzing, through a processor, at least one rotor driven equipment issue based on an analysis through a combination of a big data engine and the machine learning engine; h. displaying the at least one rotor driven equipment issue through a user interface dynamic; and i. setting an alarm, through a processor, for the at least one rotor driven equipment issue.

10. Canceled.

1 1. Canceled.

12. The method of claim 9, wherein the al arm is set through at least one of a rule based engine and a multi-classification machine learning engine.

13. Canceled.

14. Canceled.

15. Canceled.

16. Canceled.

17. In a method for maintenance and upkeep, of a machine having a rotating shaft, using data respecting performance of that machine, the improvement comprising:

a. providing multiple loT sensors for detecting data of physical parameters including temperature, vibration, current, voltage, phase lag, vacuum, magnetic field parameters and gyroscopic parameters, associated with the machine at least during operation thereof;

b. providing a data collection device;

c. providing a communications network wirelessly connected to the loT sensors and the data collection device for real time data communication therebetween;

d. using the device, collecting data from the sensors in real time during machine "on" and "off" periods;

e. storing the data in a Cassandra data base connected to the communications

network.

f. sampling the data at random for each of the parameters;

g. for each of the parameters, estimating a maximum value of the physical parameter data from the sampled data;

h. controlling data sampling error according to a preselected protocol; i. providing a data analytics engine communicatively connected to the data collection device;

j. providing a machine learning engine communicatively connected to the data analytics engine;

k. using the data analytics engine and the machine learning engine, analyzing the data according to preselected criteria to predict a machine fault;

1. displaying the predicted fault on a user interface communicatively associated with the machine.

1 8. In the method of claim 17 the improvement further comprising transforming any data stored in cartesian coordinates into spherical coordinates.

19. The method of claim 17 wherein the data collection device is mobile.

20. The method of claim 17 wherein the improvement further comprises the data collection device being selected from the group including personal computers, tablets, personal digital assistants, set-top boxes, cellular telephones, web appliances; network routers, network switches, and network bridges.

21 . The method of claim 17 wherein the improvement further comprises providing a communications network connected to the IoT sensor and the data collection device

22. The method of claim 21 wherein the step of collecting the data from the sensors in real time further includes storing the data in a Cassandra data base connected to the communications network.

23. The method of claim 22 herein the data analytics engine and the machine learning engine analyze the data using at least one of Apache Kafka and Apache Spark.

24. The method of claim 17 wherein the step of collecting the data from the sensors in real time further includes storing the data in a Cassandra data base using the communication network and the data analytics engine and the machine learning engine analyze the data using at least one of Apache Kafka and Apache Spark by accessing the aata using the communications network.

25. Apparatus for maintenance and upkeep, of machine having a rotating shaft using data respecti ng performance of that machine, the improvement comprisi ng:

a. A collection of multiple loT sensors for detecting data of physical parameters including temperature, vibration, current, voltage, phase lag, vacuum, magnetic field parameters and gyroscopic parameters, connected to the machine during operation thereof;

b. a data collection device;

c. a communications network wirelessly connected to the loT sensors and the data collection device providing real time data communication therebetween;

d. a Cassandra data base connected to the communications network.

e. a data analytics engine communicatively connected to the data collection device via the communications network;

f. a machine learning engine communicatively connected to the data analytics engine via the communications network, for analyzing the data using at least one of Apache Kafka and Apache Spark according to preselected criteria to predict a machine fault;

g. a user interface display communicatively associated with the machine learning engine and the data analytics engine via the communications network, for providing a visible indication of any predicted machine fault.

26. The improved apparatus of clai m 25 wherein the data collection device is mobile.

27. The improved apparatus of claim 25 further comprising the data collection device being selected from the group including personal computers, tablets, personal digital assistants, and cellular telephones.