Application of neural-network computing in intelligent alarm processing (power systems)

Chan, Edward H. P.

doi:10.1109/pica.1989.39002

Cited by 51 publications

(14 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A paper recommended and approved by the IEEE Power System Engineering Committee of the IEEE Power Engineering Society f o r presentation a t the IEEE/PES 1990 Summer Meeting, Minneapolis, Minnesota, July [15][16][17][18][19]1990. Manuscript submitted August 31, 1989; made available f o r printing April 24, 1990. load forecasting problem.…”

Section: S M 377-2 Pwrsmentioning

confidence: 99%

Electric load forecasting using an artificial neural network

Park

El-Sharkawi

Marks

et al. 1991

IEEE Trans. Power Syst.

1,237

356

View full text Add to dashboard Cite

This paper presents an artificial neural network(ANN) approach t o electric load forecasting. The ANN is used to learn the relationship among past, current and future temperatures and loads. In order to provide the forecasted load, the ANN interpolates among the load and temperature data in a training data set. The average absolute errors of the one-hour and 24-hour ahead forecasts in our test on actual utility data are shown to be 1.40% and 2.06%, respectively. This compares with an average error of 4.22% for 24hour ahead forecasts with a currently used forecasting technique applied to the same data.

show abstract

Section: S M 377-2 Pwrsmentioning

confidence: 99%

Electric load forecasting using an artificial neural network

Park

El-Sharkawi

Marks

et al. 1991

IEEE Trans. Power Syst.

1,237

356

View full text Add to dashboard Cite

show abstract

“…Only Circuit Breaker (CB) information from TTS is available for cause isolation and fault diagnosis in the power system network. Also, intelligent agents like genetic algorithms, and fuzzy logic have not been used in the present version of the RTAPS 1 The software and intelligent agents have been identified:…”

Section: Software Agent and Intelligent Agent Layers Of Rtapsmentioning

confidence: 99%

“…17. RTAPS has been implemented as an agentoriented, continuous, concurrently processed distributed system with object-oriented properties on a distributed 1 The primary reason for this is that intelligent agents like (SANN, and (ES) have accomplished the present set of the RTAPS objectives sufficiently well. Unix OS platform.…”

Section: Multi-agent Oriented Distributed Implementationmentioning

confidence: 99%

“…remain only partially addressed or solved. On the other hand, the existing neural network approaches (Chan 1989, Kim 1991) on alarm processing have been on small scale systems (Kirschen 1992) only. In this paper we describe the application of five layers of the IMAHDA in the process of addressing the above problems in design and implementation of a distributed Real-Time Alarm Processing System (RTAPS).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Unified problem modeling language for knowledge engineering of complex systems-part II

KhoslaR.¹,

LiQ.²

2004

Soft Comput

View full text Add to dashboard Cite

Real time applications to control industrial, medical, scientific, consumer, environmental and other processes is rapidly growing. Today such systems can be found in nuclear power stations, computer-controlled chemical plants, flight control, etc. This growth, however, has also brought to the forefront some of problems with the existing technologies. In domains like real-time alarm processing in a power system control centre existing technologies like expert systems cannot efficiently cope with. These problems have pushed for research into new techniques which could be used for solving these problems. The problems range from among other aspects, the enormous size of the power system and the fast response time constraints in emergency situations. In this paper we describe the application of the Intelligent Multi-Agent Hybrid Distributed Architecture for real-time alarm processing in a power system control centre. We show how the IMAHDA architecture is able to model the complexity and size of the power system as well as meet the desired response time constraints. Implementation of a large scale real time system like alarm processing involves realization of various objectives. These include methodology related objectives, domain related objectives, and management related objectives. This paper also describes the realization of these objectives.

show abstract

“…The transfer of neural networks to pattern recognition in intensive care data is difficult: every patient has to be controlled individually, and it is not clear how to construct training phases. It is also difficult to decide with the help of neural networks whether or not the state of a critically ill patient is improving, because too little information about the health of the patient is available for the training phase [30,31].…”

Section: Introductionmentioning

confidence: 99%

Statistical pattern detection in univariate time series of intensive care on-line monitoring data

Imhoff

Bauer

Gather

et al. 1998

Intensive Care Medicine

View full text Add to dashboard Cite

Objectives: To determine how different mathematical time series approaches can be implemented for the detection of qualitative patterns in physiologic monitoring data, and which of these approaches could be suitable as a basis for future bedside time series analysis. Interventions: None. Measurements and results:Hemodynamic data were acquired in 1-minute intervals from a clinical information system and exported into statistical software for further analysis. Altogether, 134 time series for heart rate, mean arterial pressure and mean pulmonary artery pressure were visually classified by a senior intensivist into five patterns: no change, outlier, temporary level change, permanent level change, and trend. The same series were analyzed with low order autoregressive (AR) models and with phase space (PS) models. The resulting classifications from both models were compared to the initial classification. Outliers and level changes were detected in most instances with both methods. Trend detection could only be done indirectly. Both methods were more sensitive to pattern changes than they were clinically relevant. Especially with outlier detection, 95% confidence intervals were too close. AR models require direct user interaction, whereas PS models offer opportunities for fully automated time series analysis in this context. Conclusion:Statistical patterns in univariate intensive care time series can reliably be detected with AR models and with PS models. For most bedside problems both methods are too sensitive. AR models are highly interactive, and both methods require that users have an explicit knowledge of statistics. While AR models and PS models can be extremely useful in the scientific off-line analysis, routine bedside clinical use cannot yet be recommended.

show abstract

Application of neural-network computing in intelligent alarm processing (power systems)

Cited by 51 publications

References 5 publications

Electric load forecasting using an artificial neural network

Electric load forecasting using an artificial neural network

Unified problem modeling language for knowledge engineering of complex systems-part II

Statistical pattern detection in univariate time series of intensive care on-line monitoring data

Contact Info

Product

Resources

About