Wyniki wyszukiwania - BazTech

1

Analysis of electricity consumption forecasting methods for the coal industry

Manusov Vadim Zinovievich, Orlov Dmitry, Karmanov Vitaly Sergeevich, Khusnutdinov Alexander Olegovich, Kokin Sergey Evgenevich, Safaraliev Murodbek

Przegląd Elektrotechniczny

|

2022

|

R. 98, nr 9

26--31

EN

The paper considers a forecast model of electricity consumption of a coal industry enterprise based on three forecast methods, namely the wavelet transform, the vector method, and the recurrent neutral network. A comparative analysis of these methods is performed. For preprocessing the data for forecasting by vector and recurrent methods, the Singular Spectrum Analysis method was chosen. The structure of the model allows taking into account individual features of the operating cycle of the production process and smoothing the noise components and outliers. The results of a short-term hourly forecast for one day ahead are presented with the comparison of the obtained values. The results of short-term electricity consumption forecast were verified based on the actual data of the coal industry enterprise in order to assess the adequacy of the model to the actual values. The proposed models can be applied in automated software systems for predictive control of a production process of a coal mining enterprise.

PL

W pracy uwzględniono model prognozowania zużycia energii elektrycznej przez przedsiębiorstwo przemysłu węglowego w oparciu o trzy metody prognozowania, a mianowicie transformatę falkową, metodę wektorową oraz sieć neutralną rekurencyjną. Przeprowadzana jest analiza porównawcza tych metod. Do wstępnego przetwarzania danych do prognozowania metodami wektorowymi i rekurencyjnymi wybrano metodę Singular Spectrum Analysis. Konstrukcja modelu pozwala na uwzględnienie indywidualnych cech cyklu operacyjnego procesu produkcyjnego oraz wygładzenie składowych i wartości odstających hałasu. Przedstawiono wyniki krótkookresowej prognozy godzinowej na jeden dzień do przodu wraz z porównaniem uzyskanych wartości. Wyniki prognozy krótkookresowego zużycia energii elektrycznej zostały zweryfikowane na podstawie danych rzeczywistych przedsiębiorstwa przemysłu węglowego w celu oceny adekwatności modelu do wartości rzeczywistych. Zaproponowane modele mogą znaleźć zastosowanie w zautomatyzowanych systemach oprogramowania do predykcyjnego sterowania procesem produkcyjnym przedsiębiorstwa górniczego.

2

Stable or not stable? Recognizing surge based on the pressure signal

Garcia D., Liśkiewicz G.

Transactions of the Institute of Fluid-Flow Machinery

|

2016

|

nr 133

55--68

EN

The surge protection may be worth millions of dollars. This is typical price of a centrifugal compressor repair combined with additional cost of nonfunctionality of an industry employing it. This threat is normally secured by application of an antisurge systems. Typically they are activated at predeﬁned working conditions when compressor mass ﬂow rate approaches region aﬀected by the surge. As a result those systems are vastly limiting its operational range usually by a desirable region where compressor attains large pressure ratio. Therefore, a modern antisurge systems are aiming at diminishing this tradeoﬀ by reacting to the real pressure signal gathered at high frequency. This paper presents one of those methods employing singular spectrum analysis. This algorithm has not been widely used for this application, while it was shown herein that it may bring clear distinction between stable and nonstable working condition, even at presurge conditions. Hence in further perspective it may bring anti-surge protection quality, that was not met with another methods.

3

Projekcje aktywności źródeł emisji : jak zacząć?

Zasina D., Dębski B., Zawadzki J., Zimakowska-Laskowska M.

Przemysł Chemiczny

|

2016

|

T. 95, nr 3

599--603

PL

Przedstawiono propozycję metodyki wyznaczania projekcji aktywności źródeł emisji na potrzeby Konwencji w sprawie transgranicznego zanieczyszczania powietrza na dalekie odległości (Konwencja LRTAP). Wykorzystano regresję metodą częściowych najmniejszych kwadratów oraz metodę SSA (singular spectrum analysis) w odniesieniu do produkcji kwasu siarkowego oraz używania farb na bazie rozpuszczalników.

EN

Preliminary forecasting metodol. of prodn. of H2SO4 and solvent-based paints in 2015–2030 by extrapolation, partial least squared regression and singular spectrum anal. was presented. A slight decrease in the prodn. of H2SO4 and a mild increase in the prodn. of paints in Poland were predicted. The forecast were made in order to est. atm. pollutant emissions in the context of the Convention on long-range transboundary air pollution.

4

Industry Energy Demand Forecast in Real Time via Singular Spectrum Analysis

Lopes R., Costa F. F., Lima A. C.

Przegląd Elektrotechniczny

|

2015

|

R. 91, nr 12

21-25

EN

This paper proposes a method for demand forecasting based on the Singular Spectrum Analysis (SSA). The method is to be used by large power utility's customers and to be implemented in real-time and prevents peaks from surpassing the contracted power demand with the utility. It can be applied as an auxiliary tool for management of electrical power demand in industrial plants. The effectiveness of the method is endorsed by the high correlation between the forecasted and actual time-series forecasted.

PL

W artykule zaproponowano metodę prognozowania popytu na podstawie analizy widma Singular (SSA).Metoda ma być wykorzystywane przez duże koncerny energetyczne i klientów do realizacji w czasie rzeczywistym i zapobiega piki przekroczenie zapotrzebowania mocy umownej za pomocą tego programu. Można ją stosować do zarządzania zapotrzebowania mocy elektrycznej w zakładach przemysłowych. Skuteczność metody jest potwierdzony korelację pomiędzy prognozowanym a faktycznym zużyciem energii.

5

Dynamical system analysis of unstable flow phenomena in centrifugal blower

Garcia D., Stickland M., Liśkiewicz G.

Zeszyty Naukowe. Cieplne Maszyny Przepływowe - Turbomachinery / Politechnika Łódzka

|

2014

|

nr 145

43--46

EN

Methods of dynamical system analysis were employed to analyze unsteady phenomena in the centrifugal blower. Pressure signals gathered at different control points were decomposed into their Principal Components (PCs) by means of Singular Spectrum Analysis (SSA). Certain number of PCs was considered in the analysis based on their statistical correlation. Projection of the original signal onto its PCs allowed to draw the phase trajectory that clearly separated non-stable blower working conditions from its regular operation.

6

Analysis of long-term fluctuations in stream flow time series: An Application to Litani River, Lebanon

Shaban A., Telesca L., Darwich T., Amacha N.

Acta Geophysica

|

2014

|

Vol. 62, no. 1

164--179

EN

Litani River is the largest river in Lebanon and has been affected by several physical and anthropogenic factors that influenced its flow dynamics. By means of the Singular Spectrum Analysis (SSA), the time dynamics of the stream flow of seven sites along the course of Litani River was investigated, extracting for each site the long-term trend. A clear decreasing trend characterizes all the long-term trends of the stream flow. Furthermore, several peaks were identified, consistent with the rainfall rate and snow cover variability.

7

Rainfall time series forecasting based on Modular RBF Neural Network model coupled with SSA and PLS

Wu Yu J., Yu J.

Journal of Theoretical and Applied Computer Science

|

2012

|

Vol. 6, nr 2

3-12

EN

Accurate forecast of rainfall has been one of the most important issues in hydrological research. Due to rainfall forecasting involves a rather complex nonlinear data pattern; there are lots of novel forecasting approaches to improve the forecasting accuracy. In this paper, a new approach using the Modular Radial Basis Function Neural Network (M–RBF–NN) technique is presented to improve rainfall forecasting performance coupled with appropriate data–preprocessing techniques by Singular Spectrum Analysis (SSA) and Partial Least Square (PLS) regression. In the process of modular modeling, SSA is applied for the time series extraction of complex trends and structure finding. In the second stage, the data set is divided into different training sets by Bagging and Boosting technology. In the third stage, the modular RBF–NN predictors are produced by a different kernel function. In the fourth stage, PLS technology is used to choose the appropriate number of neural network ensemble members. In the final stage, least squares support vector regression is used for ensemble of the M–RBF–NN to prediction purpose. The developed RBF–NN model is being applied for real time rainfall forecasting and flood management in Liuzhou, Guangxi. Aimed at providing forecasts in a near real time schedule, different network types were tested with the same input information. Additionally, forecasts by M–RBF–NN model were compared to the convenient approach. Results show that the predictions made using the M–RBF–NN approach are consistently better than those obtained using the other method presented in this study in terms of the same measurements. Sensitivity analysis indicated that the proposed M-RBF-NN technique provides a promising alternative to rainfall prediction.

8

Singular spectrum analysis as a smoothing method of load variability

Cempel C., Tabaszewski M.

Diagnostyka

|

2010

|

nr 4(56)

3-8

EN

Application of SVD to fault extraction from the machine symptom observation matrix (SOM) seems to be validated enough, especially by data taken from many real diagnostic cases. However, frequently we have situation of varying machine load during the production process, where by observed primary symptoms are influenced greatly. This concerns generalized symptoms too, so decision making process and forecasting is disturbed. But we can apply some new data smoothing procedure called singular spectrum analysis (SSA), to eliminate load influenced symptom fluctuation, and obtain the machine wear trend only. This seems to be true, as it was shown in the paper, but special care should be taken to choose smoothing approximation order properly.

PL

Zastosowanie rozkładu SVD do wydobycia informacji o uszkodzeniu z symptomowej macierzy obserwacji (ang. SOM) wydaje się być wystarczająco uzasadnione, szczególnie dla danych pochodzących z wielu rzeczywistych przypadków diagnostycznych. Jednakże w wielu przypadkach mamy do czynienia z sytuacją zmiennych obciążeń maszyny podczas procesu produkcji, silnie wpływających na obserwowane symptomy. Dotyczy to także symptomów uogólnionych, co utrudnia proces podejmowania decyzji i prognozowania. Możemy jednak zastosować pewną nową procedurę wygładzania nazywaną analizą widma szczególnego (ang. SSA), aby wyeliminować obciążenia wpływające na fluktuacje symptomu i otrzymać tylko trend zużycia maszyny. Wydaje się to być prawdą, jak zostało pokazane w pracy, jednak z zachowaniem szczególnej uwagi w poprawnym wyborze rzędu przybliżenia w procedurze wygładzania.

9

Wave Climate in the Gulf of Gdańsk vs. Open Baltic Sea near Lubiatowo, Poland

Różyński G.

Archives of Hydro-Engineering and Environmental Mechanics

|

2010

|

Vol. 57, nr 2

167-176

EN

The paper analyses long-term variability in the wave climate near Lubiatowo, ca. 15 km east of Łeba harbor, and in the Gulf of Gdańsk, near the Vistula river mouth. The wave climate was reconstructed for the 1958-2001 period by the German Institute for Coastal Research (GKSS). Using basic statistical tools - empirical mean values of significant wave height, estimation of the number of threshold crossings above a prescribed value of that height and conditional empirical probability density functions of wave approach directions - a comparison of wave height at the two locations was executed. A substantial reduction in wave height inside the Gulf (sheltering effect) was measured. Further, the increased storminess over the winter season was estimated for the open sea location. Finally, the analysis of wave approach direction in the open sea location revealed substantial growth in extreme waves from the western sector. Given the geographic configuration of the Gulf and the combined rise in storminess and evolution in extreme wave direction, it can be inferred that the sheltering effect of the Gulf can vary depending on locations within the Gulf. Identification of sheltering patterns in the Gulf emerges as obvious follow-up research. This study could also prove useful in analyses aiming at integrated management of coastal zones in the Gulf, mainly in the implementation of Coastal Protection Law (Apr. 2003), which postulates maintenance of the 2001 shoreline configuration along the entire Polish coast.

10

Long period oscillations in the longshore current on a sandy, barred coast investigated with Singular Spectrum Analysis

Kaczmarek J., Różyński G., Pruszak Z.

Oceanologia

|

2005

|

No. 47 (1)

5-25

EN

The presence of infragravity waves in nearshore regions can be sought in the records of both water levels and wave-driven longshore currents. For this reason, time series of such currents in close proximity to the shoreline were analysed using Singular Spectrum Analysis (SSA). Simultaneously, the results obtained with this method were confronted with the output of Discrete Wavelet Transform (DWT), which had previously been applied to this data. The records of longshore currents were collected on a daily basis during field experiments in the autumns of 2002 and 2003 with sampling rates of 3 Hz and 0.5 Hz. This produced a large data set that allowed for the use of an advanced signal processing technique, capable of extracting patterns characteristic of low-, medium- and high-frequency bands. It provided similar evidence to that produced by DWT for the existence of infragravity waves along a dissipative coast with multiple bars. The study also demonstrated the utility of SSA for studies on coastal hydrodynamics. It also showed up the better user-friendliness of DWT in terms of pattern extraction and interpretation. On the other hand, SSA demonstrated a higher precision of pattern extraction once the DWT output was known, which is a manifestation of the synergy of the two methods when applied jointly.