Fault detection Automation in Distributed Control Systems using Data-driven methods: SVM and KNN

Distributed Control Systems ◽

Using Data ◽

<p>Fault diagnostic methods with fuzzy logic methods, SVM, KNN and artificial intelligence systems have been used in complex systems such as wind turbines, gas turbines, power distribution systems, power transformers and rotary machines, but in the specific field of distributed control systems, the vacancy of this topic is strongly felt. Due to the need of the industry to detect faults quickly and in a timely manner in all modes of sensors, actuators, outputs and control logics to maintain expensive, valuable resources, important and complex equipment, it is very necessary to enter this topic. In this paper, a suitable theoretical and practical basis for diagnosing various types of faults in the DCS of a gas refinery is done. The fact that the operator quickly identifies the area and the cause of the fault can avoid huge losses in terms of downtime. Automation of fault diagnosis in DCS has not been explicitly mentioned in any article or book, and here the plan is presented for the first time. In this design, we connect MATLAB classification apps to the industrial system like DCS, then data are analyzed by SVM and KNN methods to detect faults. The results show that faults can be detected with a probability of more than 85% accuracy without the need for on-site expert force and with much less time.</p>

Fault detection Automation in Distributed Control Systems using Data-driven methods: SVM and KNN

10.36227/techrxiv.15029739.v1 ◽

2021 ◽

Author(s):

Seyed Hossein Ahmadi

Keyword(s):

Control Systems ◽

Distributed Control ◽

Power Distribution ◽

Gas Turbines ◽

Distribution Systems ◽

Diagnostic Methods ◽

Distributed Control Systems ◽

Using Data ◽

<p>Fault diagnostic methods with fuzzy logic methods, SVM, KNN and artificial intelligence systems have been used in complex systems such as wind turbines, gas turbines, power distribution systems, power transformers and rotary machines, but in the specific field of distributed control systems, the vacancy of this topic is strongly felt. Due to the need of the industry to detect faults quickly and in a timely manner in all modes of sensors, actuators, outputs and control logics to maintain expensive, valuable resources, important and complex equipment, it is very necessary to enter this topic. In this paper, a suitable theoretical and practical basis for diagnosing various types of faults in the DCS of a gas refinery is done. The fact that the operator quickly identifies the area and the cause of the fault can avoid huge losses in terms of downtime. Automation of fault diagnosis in DCS has not been explicitly mentioned in any article or book, and here the plan is presented for the first time. In this design, we connect MATLAB classification apps to the industrial system like DCS, then data are analyzed by SVM and KNN methods to detect faults. The results show that faults can be detected with a probability of more than 85% accuracy without the need for on-site expert force and with much less time.</p>

Online Analysis and Control of Electric Power Distribution Systems

10.17918/d8xq01 ◽

2021 ◽

Author(s):

Nicholas Stephen Coleman

Keyword(s):

Electric Power ◽

Power Distribution ◽

Distribution Systems ◽

Online Analysis ◽

Electric Power Distribution ◽

Network-Integrated Protection and Control Strategy for Power Distribution Systems

2007 Large Engineering Systems Conference on Power Engineering ◽

10.1109/lescpe.2007.4437349 ◽

2007 ◽

Cited By ~ 5

Author(s):

Lin Wang ◽

Helen Cheung ◽

Alexander Hamlyn ◽

Cungang Yang ◽

Richard Cheung

Keyword(s):

Control Strategy ◽

Power Distribution ◽

Distribution Systems ◽

Protection And Control ◽

Development of an HMI using JAVA for monitoring and control of automated systems applied in distributed control systems

2018 19th International Carpathian Control Conference (ICCC) ◽

10.1109/carpathiancc.2018.8399593 ◽

2018 ◽

Author(s):

A. J. Carvalho ◽

M. M. Machado ◽

M. F. Santos ◽

M. J. do Carmo

Keyword(s):

Control Systems ◽

Distributed Control ◽

Automated Systems ◽

Monitoring And Control ◽

Distributed Control Systems ◽

Proceedings of the 37th IEEE Conference on Decision and Control (Cat. No.98CH36171) ◽

Passivity property of induction motors from the power supply: towards a new framework of stability analysis and control for power distribution systems

10.1109/cdc.1998.760826 ◽

2002 ◽

Cited By ~ 1

Author(s):

N. Lechevin ◽

P. Sicard ◽

Z. Yao

Keyword(s):

Stability Analysis ◽

Power Supply ◽

Power Distribution ◽

Distribution Systems ◽

Induction Motors ◽

And Control ◽

New Framework

Development of Modern Electronic Control Systems for Power Distribution

2002 International Joint Power Generation Conference ◽

10.1115/ijpgc2002-26004 ◽

2002 ◽

Author(s):

Brian D. Gaffney

Keyword(s):

Control System ◽

Control Systems ◽

Power Distribution ◽

Power Plants ◽

Distribution Systems ◽

Electronic Control ◽

Distributed Power ◽

Future Needs ◽

The power industry is increasingly affected by several trends, which require improvements in the distributed generation and control systems of on-site power. These trends include the ability to share load across generators more effectively, seamless sequencing of generators, and the ability to monitor and control power that is being produced. Electronic control systems can provide these advantages in a cost effective solution. The application of electronic controls to a power distribution system requires a thorough development program. It is imperative to assure that the controls will provide reliable, long-term performance, as well as meeting the plant’s current and future needs for power distribution. This paper describes the development and field evaluation required to apply electronic controls to existing switchgear and power distribution systems in the power generation industry. The microprocessor based electronic control system for today’s power plants replaces out-dated analog equipment and antiquated relay logic. The new systems incorporate three main functions: Paralleling generators, monitoring power requirements, and effective sequencing of generators in power plants. Integration of these functions into the microprocessor based control system provides increased reliability, reduced cost, and enhanced performance, while concurrently providing increased flexibility in the operation of the plant. Additional benefits can be realized including reduced operator requirements, reduced training costs, and reduced burden on instrumentation electricians. A primary focus of this paper is the process used to qualify the control system needed for specific types of existing distributed power systems. This process consists of current system evaluation and categorization, establishment of classification of plant (utility, merchant plant, peak shaving facility, IPP), and determining the future needs of individual plants for power distribution. Local regulatory and utility protection and interconnect requirements must also be assessed to assure that the new control system meets or exceeds them. Methods of accurately monitoring, improving performance, and providing generator sequencing are defined, including accounting for improvements in the long-term expansion of the distributed power control and monitoring system.