Application of Multiregressive Linear Models, Dynamic Kriging Models and Neural Network Models to Predictive Maintenance of Hydroelectric Power Systems

Lucifredi, A.; Mazzieri, C.; Rossi, Mansueto

doi:10.1006/mssp.1999.1257

Cited by 30 publications

(22 citation statements)

References 1 publication

(1 reference statement)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Traditionally, statistical methods, such as exponential smoothing, linear regression, and the Box and Jenkins method, have been applied more frequently (Bevilacqua, Braglia, & Montanari, 2003;Huei-Shyang You, 1998;Kourti & MacGregor, 1996), but in the past few years computational intelligence techniques have also been used successfully. The earliest works made use of expert systems (Medsker, 1994); then came a number of studies using artificial neural nets (Caputo & Pelagagge, 2002;Ho, Xie, & Goh, 2002;Kiartzis, Zoumas, Theocharis, Bakirtzis, & Petridis, 1997;Lucifredi, Mazzieri, & Rossi, 2000;Radmer, Kuntz, Christie, Venkata, & Fletcher, 2002). More recently, several works have employed fuzzy logic systems (Chung Wu, 2004;Figueiredo, Vellasco, Pacheco, & Neto, 2000) and now also neuro-fuzzy systems (Javadpuor & Knapp, 2003;Wang, Golnaraghi, & Ismail, 2004).…”

Section: Introducing Soft Computing Techniquesmentioning

confidence: 97%

Managing the condition-based maintenance of a combined-cycle power plant: An approach using soft computing techniques

Ciarapica

Giacchetta

2006

Journal of Loss Prevention in the Process Industries

View full text Add to dashboard Cite

Section: Introducing Soft Computing Techniquesmentioning

confidence: 97%

Managing the condition-based maintenance of a combined-cycle power plant: An approach using soft computing techniques

Ciarapica

Giacchetta

2006

Journal of Loss Prevention in the Process Industries

View full text Add to dashboard Cite

“…Kriging [9,10] , also known as Kriging spatial interpolation, is a method realizing unbiased optimal estimations on regional variations in finite regions based on variation function theory and its structural analysis. It is one of the main content of the statistics.…”

Section: Kriging Interpolationmentioning

confidence: 99%

A Method of Electricity Utilization Load Analysis and Visualization Based on Data Mining of Electric Power Big Data

Wang¹,

Sun²,

Li³

et al. 2017

dtetr

View full text Add to dashboard Cite

Regional electricity utilization data is closely related to electrical load flow in terms of demand. The corresponding relation between electric power data and regional electricity load can be deeply analyzed through data mining technology in many aspects. Based on variation function theory and its structural analysis, the author realizes the unbiased optimal estimation on regional variations in finite regions through spatial local difference algorithm. According to the data of a number of known sample points in finite regions, a linear unbiased optimal estimation is carried out on unknown sample points after such things are taken into account as shape size and dimensional orientation of sample points, spatial position relation with unknown sample points and structural information provided by variation functions. The objective is to analyze real-time data of power operation with the combination of geographic information and to conclude the overall tendency of power demand so as to conclude the power demand tendency and social activity changes of an entire region and establish a demand model based on electric power data mining. The model is displayed through a new method of visualization based on authentic electric power data and GIS information.

show abstract

“…As recommended in [5,6], the following methods were selected for analysing and investigating these data to determine the wear of components under given conditions of use.…”

Section: Methodologiesmentioning

confidence: 99%

“…This paper examines two methodologies, linear multiple regression and artificial neural networks (ANN), to determine which is best for prediction [5]. Assessing wear using life cycle data is hampered because of the unavailability of operating information, particularly in the wear out phase of liner measurement.…”

Section: Introductionmentioning

confidence: 99%

Application of multi regressive linear model and neural network for wear prediction of grinding mill liners

Ahmadzadeh¹,

Lundberg²

2013

IJACSA

View full text Add to dashboard Cite

Abstract-The liner of an ore grinding mill is a critical component in the grinding process, necessary for both high metal recovery and shell protection. From an economic point of view, it is important to keep mill liners in operation as long as possible, minimising the downtime for maintenance or repair. Therefore, predicting their wear is crucial. This paper tests different methods of predicting wear in the context of remaining height and remaining life of the liners. The key concern is to make decisions on replacement and maintenance without stopping the mill for extra inspection as this leads to financial savings. The paper applies linear multiple regression and artificial neural networks (ANN) techniques to determine the most suitable methodology for predicting wear. The advantages of the ANN model over the traditional approach of multiple regression analysis include its high accuracy.

show abstract

Application of Multiregressive Linear Models, Dynamic Kriging Models and Neural Network Models to Predictive Maintenance of Hydroelectric Power Systems

Cited by 30 publications

References 1 publication

Managing the condition-based maintenance of a combined-cycle power plant: An approach using soft computing techniques

Managing the condition-based maintenance of a combined-cycle power plant: An approach using soft computing techniques

A Method of Electricity Utilization Load Analysis and Visualization Based on Data Mining of Electric Power Big Data

Application of multi regressive linear model and neural network for wear prediction of grinding mill liners

Contact Info

Product

Resources

About