Distributed IoT based sensor analytics for power line diagnosis

• US 10,481,195 B2
• Filed: 12/02/2015
• Issued: 11/19/2019
• Est. Priority Date: 12/02/2015
• Status: Active Grant

• Current Assignee: Machinesense LLC
• Original Assignee: Machinesense LLC
• Inventors: Pal, Biplab, Manna, Utpal, Zaman, Maniruz
• Primary Examiner(s): Le, John H
• Application Number:
  US14/956,403
• Publication Number:
  US 20170160328A1
• Time in Patent Office: 1,448 Days
• Field of Search: 702 57, 702 58, 702 60, 702 62, 702 68, 702183, 340536, 340657, 700295, 701 1, 706 46, 709204, 324117 H, 324543
• CPC Class Codes: G01R 31/088 Aspects of digital computing
• CPC Class Codes: G06N 20/00 Machine learning

Abstract

A method and system of a distributed power line diagnosis includes one or more electrical readings received at a firmware board computation engine and an output of firmware board engine computation being transmitted through a wide communication network to a data hub computation engine. An output of the data hub computation engine is transmitted through the communication network to a big data server. One or more electrical line issues are visualized based on an analysis through the big data server and the same can be indicated through a user interface dynamic and an alarm can be set as well through the processor for the one or more electrical line issues.

Claims

1. A method of predicting electrical line issues, the method comprising:

a) collecting through a processor, data associated with at least one electrical line reading from one or more sensors capable of local computation of time series data of electrical sensors transmitted over a communication network;

i) wherein the data collected is over a finite time period and transmitted to a machine learning engine, and

ii) wherein the machine learning engine is associated with a computer database hosting real time and historical data;

b) visualizing, through a processor, at least one electrical line issue based on an analysis through a big data engine;

c) determining the at least one electrical line issue based on one or more computations;

d) indicating the at least one electrical line issue through a user interface dynamic; and

,

e) setting an alarm, through a processor, for the at least one electrical line issue;

wherein a computation engine enables the one or more computations;

wherein the alarm is set through at least one of a rule based engine and multi-classification machine learning engine;

wherein the user interface dynamic is a predictive maintenance circular gauge; and

wherein the electrical line issue includes at least one of swell, surge, harmonics, sag and flickering.

2. A distributed power line diagnosis systenciin which at least one power line issue is determined based on one or more computations comprising;

a) a firmware to receive a plurality of electrical line data over a communications network;

b) a real time data processing system associated with distributed databases;

c) a local firmware board;

d) a data hub;

e) an IoT server;

f) a multi-classification machine learning engine associated with the IoT server;

g) a display module associated with one or more processors and user interface;

wherein a power line issue is mapped onto a depiction on a user interfaces; and

wherein the power line issue is determined based on a computation through at least one of the local firmware board, the data hub, and the IoT server; and

h) an alarm module to raise an alarm when a pre-set condition is breached;

wherein the alarm module is associated with the multi-classification machine learning engine.

3. The system of claim 2, wherein the IoT server further comprises a computation engine, operatively connected to the data processing system, the distributed databases, the data hub and the learning engine enabling one or more computations.

4. The system of claim 3, wherein the distributed computation engine computes in one or more of:

i) the local firmware board;

ii) the data hub; and

iii) the IoT server.

5. The system of claim 4, wherein the alarm is set through at least one of a rule based engine and a multi-classification machine learning engine;

wherein the depiction on the user interface is a predictive maintenance circular gauge;

wherein the communication network is one of Wi-Fi, 2G, 3G, 4G, GPRS, EDGE, Bluetooth, ZigBee, Piconet, Zwave, or a combination thereof;

wherein the alarm is raised over the communication network through one of a notification on the mobile application, Short Message Service (SMS), email or a combination thereof.

6. A method of diagnosing distributed power line issues comprising:

a) receiving at least one electrical reading at a firmware board computation engine;

b) transmitting an output of firmware board computation engine to a data hub computation engine over a communication network;

c) transmitting an output of the data hub computation engine to a big data server, wherein a machine learning engine is associated with at least one of the big data server and a computer database hosting historical data;

d) determining at least one electrical line issue based on one or more computations on the big data server using the historical data;

e) visualizing at least one electrical line issue based on an analysis through the big data server;

f) indicating at least one electrical line issue through a user interface dynamic; and

g) setting, through a processor, an alarm for at least one electrical line issue through at least one of a rule based engine and a multi-classification machine learning engine;

wherein the alarm is set through at least one of a rule based engine and multi-classification machine learning engine;

wherein the user interface dynamic is a predicative maintenance circular gauge;

wherein the communications network is one of WiFi, 2G, 3G, 4G, GPRS, EDGE, Bluetooth, ZigBee, Piconet of BLE, Zwave or a combination thereof;

wherein the alarm is raised over the communication network through one of a notification on the mobile application, Short Message Service (SMS), email or a combination thereof.