SCADAhthfhggff6776576765656756756767.pptx

hth

1. Supervisory Control and Data Acquisition(SCADA)

2. Supervisory control and data acquisition (SCADA)  is a system of software and hardware elements that allows industrial organizations to : Controlling & monitoring Process in real time from Remote location Analyze & calculation of complex the Process & maintain accordingly the Control Signals Data Acquisition, Historical Data Logging, Archiving & retrieving Trend & Alarm generation Recipe Management for Process & Chemical Industries Report Generation

3. Applications of SCADA SCADA  is widely used in different areas from chemical, gas, water, communications and power systems. The list of applications of SCADA can be listed as follows. Electric power system, operation and control: SCADA systems are used in electric power generation plants, transmission area and distribution system. Manufacturing Industries or plants: A  SCADA  helps in management of different inventory items or raw materials, controlling of automated systems in synchronous manner.

4. Telecom and IT based systems: Management of different RF based systems, communication mediums and large communication systems including data logging through antennas can be easily done through the SCADA. Water and sewage treatment plants and supply management: SCADA based systems are used by the state or municipal corporation to monitor, control and regulate water capacities in reservoir. Traffic controls: SCADA helps in regulation of traffic signals , controls the traffic flow in railway systems on road systems and air traffic controls.

5. Lift and Elevator controls: SCADA can also be used for  lift and elevator  controls. Buildings, facilities and environments: Facility managers use SCADA to control  HVAC , refrigeration units, lighting and entry systems. Mass transit and Railway Traction: Transit authorities use SCADA to regulate electricity to subways, trams and trolley buses; to automate  traffic signals  for rail systems; to track and locate trains and buses; and to control railroad crossing gates.

6. SCADA in Power Systems Comprehensive operational planning and control Fuel resource scheduling Optimum power flow Network security Economic dispatch Generation dispatch control

7. Supervisory Control and Data Acquisition(SCADA) FP growth algorithm can be very well used for finding frequent data items. This algorithm can be used in power plants for fault predictions. Main purpose of developing such system is to assist the operators in the control centers to take better decisions even in the absence of specialists. Various attributes are studied and from those certain rules are generated. FP Growth Contains 2 phases Constructs FP Tree Recursively outputs all frequent patterns

8. FP tree is base on partition-based, divide-and –conquer method. SCADA data of diesel power plant is used for rule formation in this example. Large number of sensors is connected at various parts of the complex machinery and operating data is collected by the SCADA system in every second. Generator measurements include winding, temperature, bearing temperature, phase current, voltage frequency etc., Other important monitoring parameters are fuel oil inlet temperature, oil flow rate, lube oil pressure, starting air pressure, temperature, vibration etc.,

9. Sample reference data

10. Based on the frequency analysis of alarm database and plant expert advice many important alarms are selected for failure forecast engine development. They include mechanical faults and electrical fault conditions such as generator winding temperature alarms, mechanical trip, electrical trip etc., By data mining techniques the learning engine has generated all the fault related rules and knowledge base contains these rules.

11. For example, in mechanical trip condition one rule generate by data mining is This means the main reasons for mechanical trip is generator Thrust bearing very high temperature(GENTVHT), Generator UG Bearing Very High Temperature,(GENUGVHT Generator LG Bearing VHT (GENLGVHT) and Turbine Guide bearing VHT. Thus various frequent items and rules could be generated using the FP growth algorithm. These various DB mining and machine learning algorithm tools which help in comparing the results of various algorithms

12. Snapshots of FP Tree

13. The FP growth provides the rules, in considerably small time and space complexity. The complexity builds as the size of the dataset increases. There are similar other applications, where FP tree algorithms provide accurate results.