Wyniki wyszukiwania - BazTech

1

Hybrid wavelet transform - MLR and ANN models for river flow prediction: Case study of Brahmaputra river (Pancharatna station)

Khandekar Sachin Dadu, Aswar Dinesh Shrikrishna, Sabale Pandurang Digamber, Khandekar Varsha Sachin, Bajad Mohankumar Namdeorao, Khaple Shivakumar

Przegląd Naukowy Inżynieria i Kształtowanie Środowiska

|

2024

|

Vol. 33, No. 1

69--94

EN

In this research, discrete wavelet transform (DWT) is combined with MLR and ANN to develop WMLR and WANN hybrid models, respectively, for the Brahmaputra river (Pancharatna station) flow forecasting. Daily flow data for the period of 10 year were decomposed (up to fifth level) into detailed and approximation coefficients (using Daubechies wavelets db1, db2, db3, db8 and db10) which were fed as input to MLR and ANN to get the predicted discharge values two days, four days, seven days and 14 days ahead. For all lead times, the WMLR-db10 model was found to be superior as compared to WANN-db1, WANN-db2, WANN-db3, WANN-db8, WMLR-db1, WMLR-db2, WMLR-db3, WMLR-db8 and single MLR and ANN models. During testing period, the values of determination coefficient (R2) and RMSE for WMLR-db10 model for two-, four-, seven- and 14-day lead time were found to be, respectively, 0.996 (751.87 m3·s–1), 0.991 (1,174.80 m3·s–1), 0.984 (1,585.02 m3·s–1), and 0.968 (2,196.46 m3·s–1). Also, it was observed that for lower order wavelets (db1, db2, db3) WANN’s performance was better, and for higher order wavelets (db8, db10) WMLR’s performance was better. Correspondingly, it was observed that all hybrid models’ efficiency increased with increase in the decomposition level.

2

Estimation of Photovoltaic Module Performance with L-Shaped Aluminum Fins Using Weather Data

Hamdan Mohammad, Abdelhafez Eman, Musa Akram, Ajib Salman

Journal of Ecological Engineering

|

2024

|

Vol. 25, nr 1

336--344

EN

Photovoltaic (PV) power prediction is vital for efficient and effective solar energy utilization within the energy ecosystem. It enables grid stability, cost savings, and the seamless integration of solar power into the broader energy infrastructure. In this work, previously obtained data on the estimation of the power produced by a PV, which is cooled by L-shaped aluminum fins attached to the backside of the PV at different spacings, is used to predict the power produced by the PV. This is achieved by employing both neural network models and multiple linear regression (MLR) techniques to assess the correlation between power generated by PV with L-shaped aluminum fins and its input variables. Two distinct approaches were employed for this purpose. The first approach involved the conventional MLR model, while the second utilized a neural network, specifically the multilayer perceptron (MLP) model. The estimated outcomes were subsequently compared against the previously measured data. The MLP model showed a great ability to identify the relationship between input and output variables, it was noted. The statistical error study provided evidence of data mining’s acceptable accuracy when using the MLP model. Conversely, the results indicated that the MLR technique exhibited the least ability to estimate the power generated by PV with L-shaped aluminum fins.

3

A comparative study of artificial neural networks and multivariate regression for predicting groundwater depths in the Arak aquifer

Hanifian Soadat, Khaleghi Mohammad Reza, Najarchi Mohsen, Jafarnia Reza, Varvani Javad

Acta Geophysica

|

2024

|

Vol. 72, no. 1

419--432

EN

In recent years, the groundwater resources of Arak plain have been under severe stress, so in some areas, due to the drying up of wells, the depth of wells has increased to access water. In some areas, the groundwater depth is high, which will lead to the salinization of those lands in the future. Regional modeling was used to organize and measure the response of the groundwater resources of Arak plain against the implementation of different management and implementation scenarios. This study aims to investigate the effective factors in the groundwater depth to provide a regional model with multiple linear regression (MLR) methods for Arak plain aquifer. For this purpose, the average groundwater potential maps (GPMs) in the Arak plain, as a dependent variable, and the transmissivity of the aquifer formations, groundwater exploitation values, altitude, average precipitation of the region, the amount of evaporation, and the distance from water resources are considered independent variables and regression analysis is done in SPSS software media. It was done to present a linear model. In the next stage, the presented model was evaluated by applying it to places where its statistics and information were not used to present the model, and finally, by applying this model in the GIS environment, the GPMs for the region were created. The study was prepared. Also, an artificial neural network (ANN) was used to simulate the depth of underground water. The performance of the ANN was measured through parameters such as root-mean-square error (RMSE) and correlation coefficient between real and desired outputs (R). The results of both methods indicate that factors such as the transmissivity of aquifer formations, GPMs drawdown, topography (the height of the well site on the level of the watershed), the groundwater exploitation values at the maximum operating radius of the well, and the distance from water resources are the main factors of GPMs drawdown. But the effectiveness of ANN in estimating GPMs drawdown is higher than the MLR method. The implemented methodology could be generalized to other watersheds with water scarcity problems for groundwater management.

4

Integration of Overall Equipment Effectiveness and Six Sigma Approach to Minimize Product Defect and Machine Downtime

Nurprihatin Filscha, Rembulan Glisina Dwinoor, Andry Johanes Fernandes, Lubis Maulidina, Widiwati Ivana Tita Bella, Vaezi Ali

Management and Production Engineering Review

|

2023

|

Vol. 14, No. 4

71--91

EN

This study was conducted in a company that produces palm oil-based products such as cooking oil and margarine. The study aimed to encounter defects in packaging pouches. This study integrated the overall equipment effectiveness (OEE) with the six sigma DMAIC method. The OEE was performed to measure the efficiency of the machine. Three factors were measured in OEE: availability, performance, and quality. These factors were calculated and compared to the OEE world-class value. Then, the Multiple Linear Regression was performed using SPSS to determine the correlation between measurement variables toward the OEE value. Lastly, the six sigma method was implemented through the DMAIC approach to find the solution and improve the packaging quality. Supposing the recommendations are implemented, the OEE is expected to increase from 82% to 85%, with availability ratio, performance ratio, and quality ratio at, 99%, 86%, and 99.8%, respectively.

5

An investigation of the effects of moderator variables on the lower heating value estimation of lignite deposits in Turkey

Aksoy Mehmet

Gospodarka Surowcami Mineralnymi

|

2023

|

T. 39, z. 3

199--216

EN

Turkey has 19.3 billion tons of lignite reserves and the vast majority of these Neogene lignite deposits are preferred for use in thermal power plants due to their low calorific value. The calorific value of lignite used in thermal power plants for electricity generation must be kept under constant control. In the control of calorific value, the estimation of the lower and higher heating values (LHV and HHV) of lignite is of great importance. In the literature, there are many studies that establish a relationship between the heating values of coal and proximate and ultimate analysis variables. In the studies dealing with proximate analysis data, it is observed that although the coefficients of the obtained multiple linear regression models (MRM) are statistically insignificant, these models are used to predict heating values because of the meaningful correlation coefficient. In this study, it is investigated whether moderator variables are effective on LHV estimation with proximate analysis data collected from forty-one lignite basins in different regions of Turkey, and a moderator variable analysis (MVA) model is developed to be used for the prediction of LHV. As a result of the study, it is found that the proposed MVA model is in accordance with observation values (coefficient of determination R2 = 0.951), and absolute and standard errors are also small. Therefore, it is concluded that the use of MVA to estimate the LHV of Turkey’s lignite is found to be more statistically meaningful.

PL

Turcja posiada 19,3 mld ton zasobów węgla brunatnego, a zdecydowana większość tych neogeńskich złóż węgla brunatnego jest preferowana do wykorzystania w elektrowniach cieplnych ze względu na ich niską wartość opałową. Wartość opałowa węgla brunatnego wykorzystywanego w elektrowniach ciepłowniczych do produkcji energii elektrycznej musi być stale kontrolowana. W procesie kontroli wartości opałowej bardzo ważne jest oszacowanie wartości opałowej i ciepła spalania węgla brunatnego. W literaturze istnieje wiele badań, które ustalają związek między wartościami opałowymi węgla a zmiennymi analizy przybliżonej (technicznej) i końcowej. W badaniach dotyczących danych analizy technicznej zaobserwowano, że chociaż współczynniki uzyskanych modeli wielokrotnej regresji liniowej (MRM) są statystycznie nieistotne, modele te są wykorzystywane do przewidywania wartości opałowych ze względu na znaczący współczynnik korelacji. W niniejszym artykule zbadano, czy zmienne moderatora są skuteczne w szacowaniu wartości opałowej (LHV) na podstawie danych z analizy technicznej zebranych z czterdziestu jeden zagłębi węgla brunatnego w różnych regionach Turcji, a także opracowano model analizy zmiennych moderatora (MVA), który ma być wykorzystywany do przewidywania LHV. W wyniku badań stwierdzono, że proponowany model MVA jest zgodny z wartościami obserwacji (współczynnik determinacji R2 = 0,951), a błędy bezwzględne i standardowe są również niewielkie. W związku z tym stwierdzono, że wykorzystanie MVA do oszacowania LHV tureckiego węgla brunatnego jest statystycznie uzasadnione.

6

Comparison of Solid Waste Generation During and Before Pandemic Covid-19 in Indonesia Border Island (Riau Islands Province, Indonesia)

Sari Mega Mutiara, Septiariva Iva Yenis, Istanabi Tendra, Suhardono Sapta, Sianipar Imelda Masni Juniaty, Tehupeiory Aarce, Suryawan I. Wayan Koko

Ecological Engineering & Environmental Technology

|

2023

|

Vol. 24, iss. 2

251--260

EN

Waste in the archipelagic border area must be appropriately managed to maintain diplomatic relations. Indonesia’s Riau Islands Province is an archipelagic region in Indonesia with limited solid waste infrastructure development. The capacity of the waste infrastructure depends on the rate of waste generation and is influenced by the socioeconomic conditions of the community. This study aims to study the model for estimating the rate of waste generation in the Riau Islands. This study uses data before and during the Covid-19 pandemic in 2019 and 2020. The estimation model uses a multiple linear regression model with independent variables such as gross regional domestic product, access sanitation, total population, and human development index. The fixed variable is the incidence of waste generation rate. During the pandemic Covid-19, the generation and composition of waste in the Riau Islands Archipelago did not experience significant changes, so the waste generation and composition characteristics are the same. However, the variable human development index (0.053) and the population (0.012) significantly increase the waste generation rate. The gross regional domestic product (0.017) negatively correlates, reducing the waste generation rate. The Riau Islands, which has an ocean area of 96%, is a source of life and significant to manage because the waste can be released into the ocean. Therefore, management from sources through policies considering the gross regional domestic product, total population, and human development index needs to be considered to reduce waste generation in the archipelago.

7

A comparative analysis of artificial neural network predictive and multiple linear regression models for ground settlement during tunnel construction

Zou Baoping, Chibawe Musa, Hu Bo, Deng Yansheng

Archives of Civil Engineering

|

2023

|

Vol. 69, nr 2

503--515

EN

Ground settlement during and after tunnelling using TBM results in varying dynamic and static load action on the geo-stratum. It is an undesirable effect of tunnel construction causing damage to the surface and subsurface infrastructure, safety risk, and increased construction cost and quality issues. Ground settlement can be influenced by several factors, like method of tunnelling, tunnel geometry, location of tunnelling machine, machine operational parameters, depth & its changes, and mileage of recording point from starting point. In this study, a description and evaluation of the performance of the artifcial neural network (ANN) was undertaken and a comparison with multiple linear regression (MLR) was carried out on ground settlement prediction. The performance of these models was evaluated using the coefficient of determination R2, root mean square error (RMSE) and mean absolute percentage error (MAPE). For ANN model, the R2, RMSE and MAPE were calculated as 0.9295, 4.2563 and 3.3372, respectively, while for MLR, the R2, RMSE and MAPE, were calculated as 0.5053, 11.2708, 6.3963 respectively. For ground settlement prediction, both ANN and MLR methods were able to predict significantly accurate results. It was further noted that the ANN performance was higher than that of the MLR.

8

A survey of applications of simple and multiple linear regression in wind power generation

Mbuli Nhlanhla, Mendu Bongumsa

Przegląd Elektrotechniczny

|

2022

|

R. 98, nr 3

32--35

EN

This paper presents the results of a survey on the application of simple and multiple linear regression in wind power generation research. Relevant publications were searched for, found, reviewed, and summarised. An increasing trend of number of publications on this topic was found. The main categories of publications forecasting of wind output power, forecasting of wind speed, and wind turbine generator temperature monitoring. The paper presents coincise summaries of publications and details the references identified, all of this in one repository.

PL

W artykule przedstawiono wyniki badań ankietowych dotyczących zastosowania prostej i wielokrotnej regresji liniowej w badaniach energetyki wiatrowej. Odpowiednie publikacje zostały wyszukane, znalezione, zrecenzowane i podsumowane. Stwierdzono rosnący trend liczby publikacji na ten temat. Główne kategorie publikacji: prognozowanie mocy wiatru, prognozowanie prędkości wiatru oraz monitorowanie temperatury generatorów turbin wiatrowych. W pracy przedstawiono zwięzłe streszczenia publikacji i wyszczególnienie zidentyfikowanych pozycji literaturowych, a wszystko to w jednym repozytorium.

9

Modeling Pollution Index Using Artificial Neural Network and Multiple Linear Regression Coupled with Genetic Algorithm

Abdulkareem Iman Ali, Abbas Abdulhussain A., Dawood Ammar Salman

Journal of Ecological Engineering

|

2022

|

Vol. 23, nr 3

236--250

EN

Shatt Al-Arab River in Basrah province, Iraq, was assessed by applying comprehensive pollution index (CPI) at fifteen sampling locations from 2011 to 2020, taking into consideration twelve physicochemical parameters which included pH, Tur., TDS, EC, TH, Na+, K+, Ca+2, Mg+2, Alk., SO4-2, and Cl-. The effectiveness of multiple linear regression (MLR) and artificial neural network (ANN) for predicting comprehensive pollution index was examined in this research. In order to determine the ideal values of the predictor parameters that lead to the lowest CPI value, the genetic algorithm coupled with multiple linear regression (GA-MLR) was used. A multi-layer feed-forward neural network with backpropagation algorithm was used in this study. The optimal ANN structure utilized in this research consisted of three layers: the input layer, one hidden layer, and one output layer. The predicted equation of the comprehensive pollution index was created using the regression technique and used as an objective function of the genetic algorithm. The minimum predicted comprehensive pollution index value recommended by the GA-MLR approach was 0.3777.

10

Development of pedotransfer functions for predicting soil bulk density : a case study in Indonesian small island

Yanti Evi Dwi, Mulyono Asep, Djuwansah Muhammad Rahman, Narulita Ida, Putra Risandi Dwirama, Surinati Dewi

Journal of Water and Land Development

|

2021

|

no. 51

181--187

EN

Unlike many other countries, tropical regions such as Indonesia still lack publications on pedotransfer functions (PTFs), particularly ones dedicated to the predicting of soil bulk density. Soil bulk density affects soil density, porosity, water holding capacity, drainage, and the stock and flux of nutrients in the soil. However, obtaining access to a laboratory is difficult, time-consuming, and costly. Therefore, it is necessary to utilise PTFs to estimate soil bulk density. This study aims to define soil properties related to soil bulk density, develop new PTFs using multiple linear regression (MLR), and evaluate the performance and accuracy of PTFs (new and existing). Seven existing PTFs were applied in this study. For the purposes of evaluation, Pearson’s correlation (r), mean error (ME), root mean square error (RMSE), and modelling efficiency (EF) were used. The study was conducted in five soil types on Bintan Island, Indonesia. Soil depth and organic carbon (SOC) are soil properties potentially relevant for soil bulk density prediction. The ME, RMSE, and EF values were lower for the newly developed PTFs than for existing PTFs. In summary, we concluded that the newly developed PTFs have higher accuracy than existing PTFs derived from literature. The prediction of soil bulk density will be more accurate if PTFs are applied directly in the area that is to be studied.

11

Applying the Wastewater Quality Index for Assessing the Effluent Quality of Recently Upgraded Meet Abo El-koum Wastewater Treatment Plant

Ayoub Mohamed, El-Morsy Ahmed

Journal of Ecological Engineering

|

2021

|

Vol. 22, nr 2

128--133

EN

The wastewater quality index (WWQI) can be defined as a single value, which reflects the overall wastewater quality related to its input constituent parameters. The major objective of the present study was to investigate the suitability of the effluent quality from Meet Abo El-koum wastewater treatment plant in Egypt for safe disposal based on the wastewater quality index approach. Moreover, statistical analysis was applied to develop a simple model using multiple linear regression (MLR) for accurate prediction of WWQI depending on different wastewater quality parameters. The results indicate good quality of the treated wastewater for safe disposal in general. Moreover, it is apparent that about 17% of the WWQI values reached excellent quality referring to the classification of the WWQI levels. For greater simplicity, a relationship between BOD5 and COD was deduced using linear regression, so that the results of the BOD5 analyses that appear after five days can be skipped. This approximation can be used to calculate WWQI on a specific day given the results of the treated wastewater analyses on that day.

12

Determination of soil infiltration rate equation based on soil properties using multiple linear regression

Harisuseno Donny, Cahya Evi N.

Journal of Water and Land Development

|

2020

|

no. 47

77--88

EN

Infiltration process plays important role in water balance concept particularly in runoff analysis, groundwater recharged, and water conservation. Hence, increasing knowledge concerning infiltration process becomes essential for water manager to gain an effective solution to water resources problems. This study employed multiple linear regression for estimating infiltration rate where the soil properties used as the predictor variable and measured infiltration rate as the response variable. Field measurement was conducted at sixteen points to obtain infiltration rate using double ring infiltrometer and soil properties namely soil porosity, silt, clay, sand content, degree of saturation, and water content. The result showed that measured infiltration rate had an average initial infiltration rate (f0) of 6.92 mm∙min–1 and final infiltration rate (fc) of 1.49 mm∙min–1. Soil porosity and sand content showed a positive correlation with infiltration rate by 0.842, 0.639, respectively, while silt, clay, water content, and degree of saturation exhibited a negative correlation by –0.631, –0.743, –0.66 and –0.49, respectively. Three types of regression equations were established based on type of soil properties used as predictor variables. The model performance analysis was conducted for each equation and the result shows that the equation with five predictor variables fMLR_3 = – 62.014 + 1.142 soil porosity – 0.205 clay, – 0.063 sand – 0.301, silt + 0.07 soil water content with R2 (0.87) and Nash–Sutcliffe (0.998) gave the best result for estimating infiltration rate. The study found that soil porosity contributes mostly to the regression equation that indicates great influence in controlling soil infiltration behavior.

13

Limited selectivity of amperometric gas sensors operating in multicomponent gas mixtures and methods of selectivity improvement

Dmitrzak Marta, Jasinski Piotr, Jasinski Grzegorz

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2020

|

Vol. 68, nr 6

1275--1282

EN

In recent years, smog and poor air quality have become a growing environmental problem. There is a need to continuously monitor the quality of the air. The lack of selectivity is one of the most important problems limiting the use of gas sensors for this purpose. In this study, the selectivity of six amperometric gas sensors is investigated. First, the sensors were calibrated in order to find a correlation between the concentration level and sensor output. Afterwards, the responses of each sensor to single or multicomponent gas mixtures with concentrations from 50 ppb to 1 ppm were measured. The sensors were studied under controlled conditions, a constant gas flow rate of 100 mL/min and 50 % relative humidity. Single Gas Sensor Response Interpretation, Multiple Linear Regression, and Artificial Neural Network algorithms were used to predict the concentrations of SO2 and NO2. The main goal was to study different interactions between sensors and gases in multicomponent gas mixtures and show that it is insufficient to calibrate sensors in only a single gas.

14

Prediction of electrical conductivity using ANN and MLR: a case study from Turkey

Ekemen Keskin Tülay, Özler Emre, Şander Emrah, Düğenci Muharrem, Mohammed Yadgar Ahmed

Acta Geophysica

|

2020

|

Vol. 68, no. 3

811--820

EN

The study areas are located in Turkey (Kastamonu, Bartın, Karabük, Sivas) and contain very diferent rock types, various mining and agricultural activity opportunities. So, the areas have groundwaters that have diferent chemical compositions and electrical conductivity (EC) values. The EC can be measured using EC meter, and it must be measured in situ. But, the measurement of EC in situ is laborious, time-consuming, expensive, and difcult in arduous terrain environments. In recent years, machine learning models have been a primary focus of interest for a lot of study by providing often highly accurate forecast for solutions of such problems. The aim of the study is to forecast EC of groundwater using artifcial neural networks (ANN) and multiple linear regressions (MLR). Twelve diferent hydrochemical parameters, which afect the EC, such as major/minor ions and trace elements, were used in the analysis. Multilayer feed-forward ANN trained with backpropagation in Python machine learning libraries was used in this study. In order to obtain the most appropriate ANN architecture, trialand-error procedure was used and diferent numbers of hidden layers, neurons, activation functions, optimizers, and test sizes were constructed. This study also tests the usability of input parameters in EC prediction studies. As a result, comparisons between the measured and predicted values indicated that the machine learning models could be successfully applied and provide high accuracy and reliability for EC and similar parameters forecasting.

15

Relationships between selected traits in maize (Zea mays L.). Part 2. Multiple linear regression

Bocianowski Jan, Cyplik Adrian, Szulc Piotr, Kobus-Cisowska Joanna

Journal of Research and Applications in Agricultural Engineering

|

2019

|

Vol. 64, nr 3

15--19

EN

The study comprised of 13 maize cultivars, evaluated at two years in a randomized complete block design, with four replicates. To assess the quantitative impact of individual traits on the grain yield the multiple regression analysis was used. We observed grain yield and seven quantitative traits: SPAD, length of ears, number of kernels in row, damage of maize caused by P. nubilalis, infection of maize by Fusarium spp., number of ears and content of chlorophyll a.

PL

Badanie obejmowało 13 odmian kukurydzy, analizowanych w dwóch latach w doświadczeniach polowych, w układzie bloków losowanych kompletnych, w czterech powtórzeniach. Do oceny wpływu poszczególnych cech ilościowych na plon ziarna zastosowano analizę funkcji regresji wielokrotnej. Obserwowano plon ziarna i siedem cech ilościowych: SPAD, długość kolby, liczba ziaren w rzędzie, procent roślin uszkodzonych przez P. nubilalis, porażenie przez Fusarium, liczba kolb oraz zawartość chlorofilu a.

16

A Life Factor Approach to the Yield Prediction: a Comparison with a Technological Approach in Reliability and Accuracy

Lykhovyd Pavlo

Journal of Ecological Engineering

|

2019

|

Vol. 20, nr 6

177--183

EN

There are a number of various approaches to the development of yield predictive models in agriculture. One of the most popular ones is based on the yield modeling from the parameters of crop cultivation technology. However, there is another view on the yield prediction models, which is based on the use of life factors as yielding parameters. Our study is devoted to the comparison of a conventional technological approach to the yield prediction with a less prevalent approach of life factor based yield modeling. The testing of two approaches was performed by using the yielding data of sweet corn cultivated in the field trials under the drip-irrigated conditions of the Southern Ukraine, under the different technological treatments, viz. plowing depth, nutrition, and crop density. We developed two multiple linear regression models to compare their efficiency in the yielding predictions. One of the models used cultivation technology parameters as the inputs while the other used life factors as the inputs. Life factors were expressed in numeric values by using the following converter: total water consumption of the crop was used as the factor of water, the total sum of positive temperatures was used as the factor of heat, and the total sum of the main nutrients (NPK) available in the soil was used as the factor of nutrition. The results of the study proved an equal accuracy and reliability of the studied models of sweet corn yields, which is obvious from the values of RSQ. RSQ of the both studied regression models was 0.897. However, additional check of the modeling approaches applied in the feed-forward artificial neural network showed that the life factor based model with the RSQ value of 0.953 provided better yield predictions than the technologically based model with the RSQ value of 0.913. Therefore, we concluded that the life factor approach should be preferred to the technological approach in the development of yield predictive models for agriculture.

17

Prediction of quality parameters of a dry air separation product using machine learning methods

Żogała Alina, Rzychoń Maciej

Gospodarka Surowcami Mineralnymi

|

2019

|

T. 35, z. 2

119--138

EN

The purpose of the work was to predict the selected product parameters of the dry separation process using a pneumatic sorter. From the perspective of application of coal for energy purposes, determination of process parameters of the output as: ash content, moisture content, sulfur content, calorific value is essential. Prediction was carried out using chosen machine learning algorithms that proved to be effective in forecasting output of various technological processes in which the relationships between process parameters are non-linear. The source of data used in the work were experiments of dry separation of coal samples. Multiple linear regression was used as the baseline predictive technique. The results showed that in the case of predicting moisture and sulfur content this technique was sufficient. The more complex machine learning algorithms like support vector machine (SVM) and multilayer perceptron neural network (MPL) were used and analyzed in the case of ash content and calorific value. In addition, k-means clustering technique was applied. The role of cluster analysis was to obtain additional information about coal samples used as feed material. The combination of techniques such as multilayer perceptron neural network (MPL) or support vector machine (SVM) with k-means allowed for the development of a hybrid algorithm. This approach has significantly increased the effectiveness of the predictive models and proved to be a useful tool in the modeling of the coal enrichment process.

PL

Celem pracy było prognozowanie wybranych parametrów produktu procesu suchej separacji za pomocą sortera pneumatycznego. Z punktu widzenia zastosowania węgla do celów energetycznych niezbędne jest określenie parametrów procesowych wydobycia, takich jak: zawartość popiołu, zawartość wilgoci, zawartość siarki czy wartość kaloryczna. Prognozowanie przeprowadzono przy użyciu wybranych algorytmów uczenia maszynowego, które okazały się skuteczne w prognozowaniu wyjścia różnych procesów technologicznych, w których zależności między parametrami procesu są nieliniowe. Źródłem danych wykorzystanych w pracy były eksperymenty procesu suchej separacji węgla. Zastosowano wieloraką regresję liniową jako bazową metodę predykcyjną. Wyniki pokazały, że w przypadku przewidywania zawartości wilgoci i siarki technika ta była wystarczająca. Bardziej złożone algorytmy uczenia maszynowego, takie jak maszyna wektorów nośnych (SVM) i perceptron wielowarstwowy (MLP) zostały wykorzystane i przeanalizowane w przypadku zawartości popiołu i wartości opałowej. Ponadto wdrożono technikę k-średnich. Rolą analizy skupień było uzyskanie dodatkowych informacji na temat próbek węgla będących wejściem procesu. Połączenie technik, takich jak perceptron wielowarstwowy (MLP) lub maszyna wektorów nośnych (SVM) z metodą k-średnich pozwoliło na opracowanie hybrydowego algorytmu. Takie podejście znacznie zwiększyło efektywność modeli predykcyjnych i okazało się użytecznym narzędziem w modelowaniu procesu wzbogacania węgla.

18

Predicting the vessel lumen area tree-ring parameter of Quercus robur with linear and nonlinear machine learning algorithms

Jevšenak J., Džeroski S., Levanič T.

Geochronometria

|

2018

|

Vol. 45, no. 1

211--222

EN

Climate-growth relationships in Quercus robur chronologies for vessel lumen area (VLA) from two oak stands (QURO-1 and QURO-2) showed a consistent temperature signal: VLA is highly correlated with mean April temperature and the temperature at the end of the previous growing season. QURO-1 showed significant negative correlations with winter sums of precipitation. Selected climate variables were used as predictors of VLA in a comparison of various linear and nonlinear machine learning methods: Artificial Neural Networks (ANN), Multiple Linear Regression (MLR), Model Trees (MT), Bagging of Model Trees (BMT) and Random Forests of Regression Trees (RF). ANN outperformed all the other regression algorithms at both sites. Good performance also characterised RF and BMT, while MLR, and especially MT, displayed weaker performance. Based on our results, advanced machine learning algorithms should be seriously considered in future climate reconstructions.

19

Micro-EDM process modeling and machining approaches for minimum tool electrode wear for fabrication of biocompatible micro-components

Puthumana G.

Journal of Machine Engineering

|

2017

|

Vol. 17, No. 3

97--111

EN

Micro-electrical discharge machining (micro-EDM) is a potential non-contact method for fabrication of biocompatible micro devices. This paper presents an attempt to model the tool electrode wear in micro-EDM process using multiple linear regression analysis (MLRA) and artificial neural networks (ANN).The governing micro-EDM factors chosen for this investigation were: voltage (V), current (I), pulse on time (Ton) and pulse frequency (f). The proposed predictive models generate a functional correlation between the tool electrode wear rate (TWR) and the governing micro-EDM factors. A multiple linear regression model was developed for prediction of TWR in ten steps at a significance level of 90%. The optimum architecture of the ANN was obtained with 7 hidden layers at an R-sq value of 0.98. The predicted values of TWR using ANN matched well with the practically measured and calculated values of TWR. Based on the proposed soft computing-based approach towards biocompatible micro device fabrication, a condition for the minimum tool electrode wear rate (TWR) was achieved.

20

Predicting the properties of corrugated base papers using multiple linear regression and artificial neural networks

Adamopoulos S., Karageorgos A., Rapti E., Birbilis D.

Drewno : prace naukowe, doniesienia, komunikaty

|

2016

|

vol. 59, nr 198

61--72

EN

The difficulty in predicting the properties and behaviour of paper products produced using heterogeneous raw materials with high percentages of recovered fibres poses restrictions on their efficient and effective use as corrugated packaging materials. This work presents predictive models for the mechanical properties of corrugated base papers (liner and fluting-medium) from fibre and physical property data using multiple linear regression and artificial neural networks. The most significant results were obtained for the prediction of the tensile strength of liners in the cross direction from the origin (wood type, pulp method) of the fibres using linear regression, and the prediction of the compressive strength of fluting-medium in the longitudinal (machine) direction, according to the short-span test, using a neural network with one hidden layer with 6 neurons, with coefficients of determination at 95.14% and 99.28%, respectively.