Araştırma Makalesi
BibTex RIS Kaynak Göster

DALGACIK DÖNÜŞÜMÜ TABANLI NAİVE BAYES SINIFLANDIRICI İLE TÜRKİYE’NİN TAMAMINI İÇEREN BÖLGELERDEKİ LİNYİT KÖMÜRÜNÜN KALİTE TESPİTİ

Yıl 2025, Cilt: 28 Sayı: 1, 403 - 413, 03.03.2025

Sevcan Aytaç

Öz

Günümüzde Türkiye sondaj sahalarından elde edilen karmaşık linyit kömürünün kabul edilebilir kalite ve nispeten zayıf kalitede olduğunun tespiti işlemi enerji santrallerinde, diğer alanlarda ve enerji üretiminde hayati öneme sahiptir. Özellikle, birden fazla karmaşık parametrelerinin doğru bir şekilde kalitelerine göre belirlenmesi yatırım kararlarında büyük ölçüde önem kazanmıştır. Bu makalede, Türkiye Kömür İşletmeleri Genel Müdürlüğünden alınan, MTA tarafından yayınlanan linyit envanterinde Türkiye’nin tamamını içeren 96 linyit kömürünün 96 sondaj bölgesine ait nem, kül, kükürt ve kalori içerikleri ele alınmıştır. Belirtilen nem, kül ve kükürt gibi 3 parametre, bağımlı değişken olan kalori değeri üzerinde etkili olmaktadır. Kalori ne kadar yüksekse kömür kalitesi o kadar iyidir. İlk olarak verilere K-Ortalamalar kümeleme algoritması uygulanarak kömürünün kalori değerleri 2 gruba ayrılmıştır. 2 gruba ayrılan bu değerler doğrulama verisi olarak kullanılmıştır. Dalgacık katsayılarından elde edilen özellik değerleri Naive Bayes sınıflandırıcısı ile sınıflandırılmıştır. Sınıflandırma performansları kıyaslandığında Daubechies dalgacık ailesinden olan db4’ün diğer dalgacık ailelerine ve CA dalgacık katsayılarının CH, CV ve CD katsayılarına göre daha yüksek performans sergilediği tespit edilmiştir. Nem, kül ve kükürt içeriklerinin Dalgacık Dönüşümü katsayıları hesaplanarak, Naive Bayes yöntemi ile sınıflandırma performansları kıyaslanmıştır. Daubechies ailesinden olan db4’ün yaklaşımsal katsayıları ile elde edilen kömürün kalite tespit oranının en yüksek olduğu ve %100 olarak bulunduğu tespit edilmiştir.

Anahtar Kelimeler

Linyit Kömür K-Ortalamalar Dalgacık Dönüşümü Naive Bayes Sınıflandırıcı

Teşekkür

Yazar İnönü üniversitesinde öğretim üyesi olan Prof. Dr. Bülent TÜTMEZ’e teşekkür etmektedir.

Kaynakça

  • Aytac Korkmaz, S. (2020). Grade level of lignite coal datas in the different areas with decison tree, random forest, and discriminant analysis methods. Applied Artificial Intelligence, 34(11), 755-776.
  • Cheng, Y., Xu, L., Li, X., & Guo, Z. (2012, July). Online coal calorific value prediction from mutiband coal/air combustion radiation characteristics. In Instrumentation and Control Technology (ISICT), 2012 8th IEEE International Symposium on,309-313,IEEE.
  • Chelgani S C, Mesroghli S H, Hower J C. (2010). Simultaneous prediction of coal rank parameters based on ultimate analysis using regression and artificial neural network. International Journal of Coal Geology, 83(1), 31-34.
  • Doğan, G. & Ergen, B. (2022). Karayollarındaki Asfalt Çatlaklarının Tespiti İçin Yeni Bir Konvolüsyonel Sinir Ağı Tabanlı Yöntem . Fırat Üniversitesi Mühendislik Bilimleri Dergisi,34 (2) , 485-494 . DOI: 10.35234/fumbd.1014951.
  • Fırat M., Dikbaş F., Koç AC., ve Güngör M. (2012). K-Ortalamalar Yöntemi ile Yıllık Yağışların Sınıflandırılması ve Homojen Bölgelerin Belirlenmesi. İMO Teknik Dergi, 383, 6037-6050.
  • Galetakis M J, Theodoridis K, Kouridou O. (2002). Lignite quality estimation using ANN and adaptive neuro-fuzzy inference systems (ANFIS). APPCOM: 425-431.
  • IEA, (2000). International energy annual. France. International Journal of Coal Science & Engineering (China) Energy Agency.
  • Karhan Z., Ergen B. (2016). Content based medical image classification using discrete wavelet and cosine transforms. (2015). 23nd Signal Processing and Communications Applications Conference (SIU), (pp:1445-1448).
  • Korkmaz, S. A. (2021). Classification of histopathological gastric images using a new method. Neural Computing and Applications, 33(18), 12007-12022.
  • Korkmaz, S. A., & Binol, H. (2018). Classification of molecular structure images by using ANN, RF, LBP, HOG, and size reduction methods for early stomach cancer detection. Journal of Molecular Structure, 1156, 255-263.
  • Korkmaz, S. A., & Esmeray, F. (2018, March). Quality lignite coal detection with discrete wavelet transform, discrete fourier transform, and ANN based on k-means clustering method. In Digital Forensic and Security (ISDFS), 2018 6th International Symposium on (pp. 1-6). IEEE.
  • Korkmaz, S. A., & Poyraz, M. (2014). A New Method Based for Diagnosis of Breast Cancer Cells from Microscopic Images: DWEE—JHT. Journal of medical systems, 38(9), 92.
  • Leśniak, A., & Isakow, Z. (2009). Space–time clustering of seismic events and hazard assessment in the Zabrze-Bielszowice coal mine. Poland. International Journal of Rock Mechanics and Mining Sciences, 46(5), 918-928.
  • McCallum, A., & Nigam, K. (1998, July). A comparison of event models for Naive Bayes text classification. In AAAI-98 workshop on learning for text categorization,752, pp. 41-48.
  • Moon C J, Whateley M K G, Evans A M. (2006). “Introduction to mineral exploration” India: Blackwell Publishing. MTA, (2010). Lignite inventory of Turkey, general directorate of mineral research and exploration (MTA) in Turkey. Ankara (in Turkish).
  • Muda, Z., Yassin, W., Sulaiman, M. N., & Udzir, N. I. (2011, July). Intrusion detection based on K-Means clustering and Naïve Bayes classification. In Information Technology in Asia (CITA 11), 2011 7th International Conference on (pp. 1-6). IEEE.
  • Ozcift, A., & Gulten, A. (2008). Assessing effects of pre-processing mass spectrometry data on classification performance. European Journal of Mass Spectrometry, 14(5), 267-273.
  • Özdemir, E. & Türkoğlu, İ. (2022). Yazılım Güvenlik Açıklarının Evrişimsel Sinir Ağları (CNN) ile Sınıflandırılması, Fırat Üniversitesi Mühendislik Bilimleri Dergisi,34 (2) , 517-529 . DOI: 10.35234/fumbd.1076870.
  • Pandit, Y. P., Badhe, Y. P., Sharma, B. K., Tambe, S. S., & Kulkarni, B. D. (2011). Classification of Indian power coals using K-means clustering and Self Organizing Map neural network. Fuel, 90(1), 339-347.
  • Sahu, H. B., Mahapatra, S. S., & Panigrahi, D. C. (2012). Fuzzy c-means clustering approach for classification of Indian coal seams with respect to their spontaneous combustion susceptibility. Fuel processing technology, 104, 115-120.
  • Sahu, H. B., Mahapatra, S. S., Sirikasemsuk, K., & Panigrahi, D. C. (2011). A discrete particle swarm optimization approach for classification of Indian coal seams with respect to their spontaneous combustion susceptibility. Fuel processing technology, 92(3), 479-485.
  • Senguler I. (2010). Lignite explorations in Turkey: new projects and new reserves. //17th Annual International Pittsburgh Coal Conference, İstanbul, Turkey.
  • Sengur, A., Turkoglu, I., & Ince, M. C. (2007). Wavelet packet neural networks for texture classification. Expert systems with applications, 32(2), 527-533.
  • Sengur, A., Turkoglu, I., & Ince, M. C. (2008). Wavelet oscillator neural networks for texture segmentation. Neural Network World, 18(4), 275.
  • Tuncer, T., & Ertam, F. (2020). Neighborhood component analysis and reliefF based survival recognition methods for Hepatocellular carcinoma. Physica A: Statistical Mechanics and its Applications, 540, 123143.
  • Tuncer, T., Dogan, S., & Akbal, E. (2019). A novel local senary pattern based epilepsy diagnosis system using EEG signals. Australasian physical & engineering sciences in medicine, 42(4), 939-948.
  • Tutmez B., HOZATLI B., CENGIZ A.K. (2013). An overview of Turkish lignite qualities by logistic analysis, Journal of Coal Science& Engineering China, 19:2, 113-118.
  • Yang, X. L., Wang, F., Wang, W. C., Chen, Y. X., & Chen, J. S. (2014). DWT-PLS Regression on Near-Infrared Spectra for Moisture Determination of Coal. In Advanced Materials Research, 827, 209-212. Trans Tech Publications.
  • Yilmaz, I., Erik, N. Y., & Kaynar, O. (2010). Different types of learning algorithms of artificial neural network (ANN) models for prediction of gross calorific value (GCV) of coals. Scientific Research and Essays, 5(16), 2242-2249.
  • Yongkui, S., Pengrui, L., Ying, W., Jingyu, Z., & Meijie, L. (2014). The Prediction of the Caving Degree of Coal Seam.

QUALITY DETERMINATION OF LIGNITE COAL IN THE REGIONS INCLUDING THE WHOLE OF TURKEY USING WAVELET TRANSFORM BASED NAIVE BAYES CLASSIFIER

Yıl 2025, Cilt: 28 Sayı: 1, 403 - 413, 03.03.2025

Sevcan Aytaç

Öz

Today, the process of determining whether the complex lignite coal obtained from Turkey's drilling fields is of acceptable quality or relatively poor quality is of vital importance in power plants, other areas and energy production. In particular, the accurate determination of multiple complex parameters according to their quality has gained great importance in investment decisions. In this article, the moisture, ash, sulfur and calorie contents of 96 drilling regions of 96 lignite coals covering the whole of Turkey in the lignite inventory published by MTA, received from the General Directorate of Turkish Coal Enterprises, are discussed. The 3 parameters mentioned, such as moisture, ash and sulfur, affect the caloric value, which is the dependent variable. The higher the calories, the better the coal quality. First, by applying the K-Means clustering algorithm to the data, the caloric values of coal were divided into 2 groups. These values, divided into 2 groups, were used as validation data. Feature values obtained from wavelet coefficients were classified with the Naive Bayes classifier. When the classification performances were compared, it was determined that db4, which is from the Daubechies wavelet family, showed higher performance than other wavelet families and CA wavelet coefficients compared to CH, CV and CD coefficients. Wavelet Transform coefficients of moisture, ash and sulfur contents were calculated and classification performances were compared with the Naive Bayes method. It has been determined that the quality detection rate of coal obtained with the approximation coefficients of db4, which is from the Daubechies family, is the highest and is 100%.

Anahtar Kelimeler

Lignite coal k-means wavelet transform naive bayes classifier

Kaynakça

  • Aytac Korkmaz, S. (2020). Grade level of lignite coal datas in the different areas with decison tree, random forest, and discriminant analysis methods. Applied Artificial Intelligence, 34(11), 755-776.
  • Cheng, Y., Xu, L., Li, X., & Guo, Z. (2012, July). Online coal calorific value prediction from mutiband coal/air combustion radiation characteristics. In Instrumentation and Control Technology (ISICT), 2012 8th IEEE International Symposium on,309-313,IEEE.
  • Chelgani S C, Mesroghli S H, Hower J C. (2010). Simultaneous prediction of coal rank parameters based on ultimate analysis using regression and artificial neural network. International Journal of Coal Geology, 83(1), 31-34.
  • Doğan, G. & Ergen, B. (2022). Karayollarındaki Asfalt Çatlaklarının Tespiti İçin Yeni Bir Konvolüsyonel Sinir Ağı Tabanlı Yöntem . Fırat Üniversitesi Mühendislik Bilimleri Dergisi,34 (2) , 485-494 . DOI: 10.35234/fumbd.1014951.
  • Fırat M., Dikbaş F., Koç AC., ve Güngör M. (2012). K-Ortalamalar Yöntemi ile Yıllık Yağışların Sınıflandırılması ve Homojen Bölgelerin Belirlenmesi. İMO Teknik Dergi, 383, 6037-6050.
  • Galetakis M J, Theodoridis K, Kouridou O. (2002). Lignite quality estimation using ANN and adaptive neuro-fuzzy inference systems (ANFIS). APPCOM: 425-431.
  • IEA, (2000). International energy annual. France. International Journal of Coal Science & Engineering (China) Energy Agency.
  • Karhan Z., Ergen B. (2016). Content based medical image classification using discrete wavelet and cosine transforms. (2015). 23nd Signal Processing and Communications Applications Conference (SIU), (pp:1445-1448).
  • Korkmaz, S. A. (2021). Classification of histopathological gastric images using a new method. Neural Computing and Applications, 33(18), 12007-12022.
  • Korkmaz, S. A., & Binol, H. (2018). Classification of molecular structure images by using ANN, RF, LBP, HOG, and size reduction methods for early stomach cancer detection. Journal of Molecular Structure, 1156, 255-263.
  • Korkmaz, S. A., & Esmeray, F. (2018, March). Quality lignite coal detection with discrete wavelet transform, discrete fourier transform, and ANN based on k-means clustering method. In Digital Forensic and Security (ISDFS), 2018 6th International Symposium on (pp. 1-6). IEEE.
  • Korkmaz, S. A., & Poyraz, M. (2014). A New Method Based for Diagnosis of Breast Cancer Cells from Microscopic Images: DWEE—JHT. Journal of medical systems, 38(9), 92.
  • Leśniak, A., & Isakow, Z. (2009). Space–time clustering of seismic events and hazard assessment in the Zabrze-Bielszowice coal mine. Poland. International Journal of Rock Mechanics and Mining Sciences, 46(5), 918-928.
  • McCallum, A., & Nigam, K. (1998, July). A comparison of event models for Naive Bayes text classification. In AAAI-98 workshop on learning for text categorization,752, pp. 41-48.
  • Moon C J, Whateley M K G, Evans A M. (2006). “Introduction to mineral exploration” India: Blackwell Publishing. MTA, (2010). Lignite inventory of Turkey, general directorate of mineral research and exploration (MTA) in Turkey. Ankara (in Turkish).
  • Muda, Z., Yassin, W., Sulaiman, M. N., & Udzir, N. I. (2011, July). Intrusion detection based on K-Means clustering and Naïve Bayes classification. In Information Technology in Asia (CITA 11), 2011 7th International Conference on (pp. 1-6). IEEE.
  • Ozcift, A., & Gulten, A. (2008). Assessing effects of pre-processing mass spectrometry data on classification performance. European Journal of Mass Spectrometry, 14(5), 267-273.
  • Özdemir, E. & Türkoğlu, İ. (2022). Yazılım Güvenlik Açıklarının Evrişimsel Sinir Ağları (CNN) ile Sınıflandırılması, Fırat Üniversitesi Mühendislik Bilimleri Dergisi,34 (2) , 517-529 . DOI: 10.35234/fumbd.1076870.
  • Pandit, Y. P., Badhe, Y. P., Sharma, B. K., Tambe, S. S., & Kulkarni, B. D. (2011). Classification of Indian power coals using K-means clustering and Self Organizing Map neural network. Fuel, 90(1), 339-347.
  • Sahu, H. B., Mahapatra, S. S., & Panigrahi, D. C. (2012). Fuzzy c-means clustering approach for classification of Indian coal seams with respect to their spontaneous combustion susceptibility. Fuel processing technology, 104, 115-120.
  • Sahu, H. B., Mahapatra, S. S., Sirikasemsuk, K., & Panigrahi, D. C. (2011). A discrete particle swarm optimization approach for classification of Indian coal seams with respect to their spontaneous combustion susceptibility. Fuel processing technology, 92(3), 479-485.
  • Senguler I. (2010). Lignite explorations in Turkey: new projects and new reserves. //17th Annual International Pittsburgh Coal Conference, İstanbul, Turkey.
  • Sengur, A., Turkoglu, I., & Ince, M. C. (2007). Wavelet packet neural networks for texture classification. Expert systems with applications, 32(2), 527-533.
  • Sengur, A., Turkoglu, I., & Ince, M. C. (2008). Wavelet oscillator neural networks for texture segmentation. Neural Network World, 18(4), 275.
  • Tuncer, T., & Ertam, F. (2020). Neighborhood component analysis and reliefF based survival recognition methods for Hepatocellular carcinoma. Physica A: Statistical Mechanics and its Applications, 540, 123143.
  • Tuncer, T., Dogan, S., & Akbal, E. (2019). A novel local senary pattern based epilepsy diagnosis system using EEG signals. Australasian physical & engineering sciences in medicine, 42(4), 939-948.
  • Tutmez B., HOZATLI B., CENGIZ A.K. (2013). An overview of Turkish lignite qualities by logistic analysis, Journal of Coal Science& Engineering China, 19:2, 113-118.
  • Yang, X. L., Wang, F., Wang, W. C., Chen, Y. X., & Chen, J. S. (2014). DWT-PLS Regression on Near-Infrared Spectra for Moisture Determination of Coal. In Advanced Materials Research, 827, 209-212. Trans Tech Publications.
  • Yilmaz, I., Erik, N. Y., & Kaynar, O. (2010). Different types of learning algorithms of artificial neural network (ANN) models for prediction of gross calorific value (GCV) of coals. Scientific Research and Essays, 5(16), 2242-2249.
  • Yongkui, S., Pengrui, L., Ying, W., Jingyu, Z., & Meijie, L. (2014). The Prediction of the Caving Degree of Coal Seam.
Toplam 30 adet kaynakça vardır.

Ayrıntılar

Birincil Dil Türkçe
Konular Karar Desteği ve Grup Destek Sistemleri, Yarı ve Denetimsiz Öğrenme
Bölüm Elektrik Elektronik Mühendisliği
Yazarlar

Sevcan Aytaç 0000-0002-6796-5101

Yayımlanma Tarihi 3 Mart 2025
Gönderilme Tarihi 24 Ekim 2024
Kabul Tarihi 10 Aralık 2024
Yayımlandığı Sayı Yıl 2025Cilt: 28 Sayı: 1

Kaynak Göster

APA Aytaç, S. (2025). DALGACIK DÖNÜŞÜMÜ TABANLI NAİVE BAYES SINIFLANDIRICI İLE TÜRKİYE’NİN TAMAMINI İÇEREN BÖLGELERDEKİ LİNYİT KÖMÜRÜNÜN KALİTE TESPİTİ. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, 28(1), 403-413.
 Kapak Resmi İndir