Applications of artificial intelligence in power systems

A method to test the transient performance of a sampled-data relay is given. A model of one measuring unit of a digital relay is created on a personal computer. The simulations are compared with laboratory results obtained by applying digitally generated waveforms to the actual relay. Computer modeling of the digital relay is done within the models version of the Transient Analysis of Control System (TACS) subsection of the ElectroMagnetics Transient Program (EMTP). The input filter, analog-to-digital converter, Fourier fundamental frequency detector, and the relay measuring principle of one digital microprocessor-based relay are modeled. An actual 115 kV 150 mile long transmission line is simulated using the EMTP. >

EMTP transient modeling of a distance relay and a comparison with EMTP laboratory testing

Distribution automation (DA) is deployed to reduce outages and to rapidly reconnect customers following network faults. Recent developments in DA equipment have enabled the logging of load and fault event data, referred to as “pick-up activity.” This pick-up activity provides a picture of the underlying circuit activity occurring between successive DA operations over a period of time and has the potential to be accessed remotely for off-line or on-line analysis. The application of data analytics and automated analysis of this data supports reactive fault management and post fault investigation into anomalous network behavior. It also supports predictive capabilities that identify when potential network faults are evolving and offers the opportunity to take action in advance in order to mitigate any outages. This paper details the design of a novel decision support system to achieve fault diagnosis and prognosis for DA schemes. It combines detailed data from a specific DA device with rule-based, data mining, and clustering techniques to deliver the diagnostic and prognostic functions. These are applied to 11-kV distribution network data captured from Pole Mounted Auto-Reclosers as provided by a leading U.K. network operator. This novel automated analysis system diagnoses the nature of a circuit’s previous fault activity, identifies underlying anomalous circuit activity, and highlights indications of problematic events gradually evolving into a full scale circuit fault. The novel contributions include the tackling of “semi-permanent faults” and the re-usable methodology and approach for applying data analytics to any DA device data sets in order to provide diagnostic decisions and mitigate potential fault scenarios.

/pdf/a-data-analytic-approach-to-automatic-fault-diagnosis-and-1dnnh8mgl8.pdf

A Data Analytic Approach to Automatic Fault Diagnosis and Prognosis for Distribution Automation

This paper presents an expert system which performs detailed diagnosis of digital relay operation by analyzing data contained in relay files and reports Problem domain is discussed first Then the analysis strategy is detailed: forward chaining reasoning, logic reasoning and backward chaining reasoning are employed to predict protection operation, identify unexpected protection operation and diagnose symptoms respectively The implementation of knowledge representation by CLIPS rules is further described Finally, an example is given to demonstrate the capability of the expert system

An expert system for diagnosis of digital relay operation

Information systems and intelligent smart grid data analytics will have a critical role in managing the massive amount of data becoming available in power system substations. Digital protective relays are multi-functional intelligent electronic devices based on microprocessors, which are being installed in substations throughout the power grid. New digital relays are replacing old-fashioned electro-mechanical or solid-state relays, and besides their protective function, they are coming equipped with monitoring capabilities. These monitoring capabilities are creating potential for better observability of power systems, redundancy in measurements, and improved decision-making process when operating the system. This article discusses the implementation requirements for a fully automated data analytics solution that provides data integration, fault analysis, and visualization based on the event data recorded by digital protective relays.

https://link.springer.com/content/pdf/10.1007%2Fs10796-013-9434-9.pdf

Smart grid data analytics for digital protective relay event recordings

A new expert system application to power system protective relay evaluation testing, a crucial but time-consuming engineering task, is presented. An expert system called RETEX (relay testing expert) has been developed as a computer aid for analysis of relay testing data. A knowledge base for relay testing data analysis has been developed. A relay logic model is used to determine the expected relay operation for simulated faults. Hierarchical test reports and comparison reports can be automatically generated by RETEX, which is designed with basic language processing capabilities. The generality necessary for handling various relay models is provided by a description file approach. The expert system is implemented in a rule-based and object-oriented architecture with the expert system development tool NEXPERT Object. The feasibility of the prototype has been demonstrated with Bonneville Power Administration (BPA) relay testing data. >

M. Hofmann

Papers

RETEX (RElay Testing EXpert): an expert system for analysis of relay testing data