A CASE STUDY FOR PREVENTING ELECTRICITY OVER-CONSUMPTION USING DEEP LEARNING IN TEXTILE INDUSTRY

Ömer Güleç

Makale detayları

A CASE STUDY FOR PREVENTING ELECTRICITY OVER-CONSUMPTION USING DEEP LEARNING IN TEXTILE INDUSTRY

Yazarlar:

Ömer Güleç

Yayıncı:

Süleyman Demirel University

Ana Başlıklar:

Bilgisayar Yazılımı

Dergi:

Mühendislik Bilimleri ve Tasarım Dergisi Vol.11 Issue 4, pp.1383-1397

Belge Tipi:

Makale

Yayın Tarihi:

12/2023

Belge Dili:

İngilizce

Document ID (Org No.):

2001307542

pISSN:

1308-6693

Anahtar kelimeler:

Özet:

 Resources are the most critical input in the manufacturing industry therefore, resource consumption is an essential issue to be minimized. On the other hand, consumption depends on several parameters thus, it is difficult to estimate. Recently, Machine Learning ML and Deep Learning DL are powerful Artificial Intelligence AI subdomains for future prediction in any area. In this paper, a DL-supported electricity prediction method is designed for the textile industry as a case study in order to prevent resource over-consumption while the machines are in the standby state. This method provides dynamic consumption thresholds of electricity consumption by sliding window technique based Long-Short Term Memory LSTM model that helps the machines to interrupt manufacturing in their decision. These calculated thresholds are also compared with the results of Recurrent Neural Networks RNN and Gated Recurrent Units GRU as the other DL methods and Automated Regressive Integrated Moving Average ARIMA as a traditional method and then the results have been analyzed how close they are to real-time electricity consumption data at standby. According to the results, the LSTM model successfully predicts electricity consumption levels, sends an interrupt signal to Programmable Logic Controller PLC unit when the consumption levels reach the threshold and therefore prevents resource over-consumption.

 Resources are the most critical input in the manufacturing industry therefore, resource consumption is an essential issue to be minimized. On the other hand, consumption depends on several parameters thus, it is difficult to estimate. Recently, Machine Learning ML and Deep Learning DL are powerful Artificial Intelligence AI subdomains for future prediction in any area. In this paper, a DL-supported electricity prediction method is designed for the textile industry as a case study in order to prevent resource over-consumption while the machines are in the standby state. This method provides dynamic consumption thresholds of electricity consumption by sliding window technique based Long-Short Term Memory LSTM model that helps the machines to interrupt manufacturing in their decision. These calculated thresholds are also compared with the results of Recurrent Neural Networks RNN and Gated Recurrent Units GRU as the other DL methods and Automated Regressive Integrated Moving Average ARIMA as a traditional method and then the results have been analyzed how close they are to real-time electricity consumption data at standby. According to the results, the LSTM model successfully predicts electricity consumption levels, sends an interrupt signal to Programmable Logic Controller PLC unit when the consumption levels reach the threshold and therefore prevents resource over-consumption.

 Resources are the most critical input in the manufacturing industry therefore, resource consumption is an essential issue to be minimized. On the other hand, consumption depends on several parameters thus, it is difficult to estimate. Recently, Machine Learning ML and Deep Learning DL are powerful Artificial Intelligence AI subdomains for future prediction in any area. In this paper, a DL-supported electricity prediction method is designed for the textile industry as a case study in order to prevent resource over-consumption while the machines are in the standby state. This method provides dynamic consumption thresholds of electricity consumption by sliding window technique based Long-Short Term Memory LSTM model that helps the machines to interrupt manufacturing in their decision. These calculated thresholds are also compared with the results of Recurrent Neural Networks RNN and Gated Recurrent Units GRU as the other DL methods and Automated Regressive Integrated Moving Average ARIMA as a traditional method and then the results have been analyzed how close they are to real-time electricity consumption data at standby. According to the results, the LSTM model successfully predicts electricity consumption levels, sends an interrupt signal to Programmable Logic Controller PLC unit when the consumption levels reach the threshold and therefore prevents resource over-consumption.

 Endüstrinin en kritik girdileri kaynaklardır ve bu nedenle kaynak tüketimi endüstriyel süreçlerde en aza indirilmesi gereken önemli bir konudur. Öte yandan, kaynak tüketimi birçok parametreye bağlı olduğu için tahmin edilmesi zordur. Son dönemlerde, Makine Öğrenmesi MÖ ve Derin Öğrenme DÖ kavramları, herhangi bir alanda gelecek tahmini için kullanılan güçlü Yapay Zeka alt alanlarıdır. Bu çalışmada tekstil endüstrisi için bir vaka çalışması olarak, makinelerin bekleme durumunda aşırı kaynak tüketimini önlemek amacıyla DÖ destekli bir elektrik tahmin modeli tasarlanmıştır. Bu yöntem, makinelerin karar verme süreçlerini içeren ve aşırı tüketime nedeniyle üretimi kesintiye uğratmasına yardımcı olan Uzun-Kısa Süreli Bellek UKSB tabanlı kayan pencere tekniği sayesinde elektrik tüketiminin saatlik dinamik eşik değerlerini tahminlemektedir. Hesaplanan eşik değerleri, Tekrarlayan Sinir Ağları TSA ve Kapılı Tekrarlayan Birimler KTB gibi diğer Derin Öğrenme yöntemleri ve geleneksel bir yöntem olan Otomatik Regresif Entegre Hareketli Ortalama ARIMA yöntemi ile karşılaştırılmış, elde edilen sonuçların makinelerin bekleme durumundaki gerçek zamanlı elektrik tüketim verilerine ne kadar yaklaştığı analiz edilmiştir. Elde edilen sonuçlara göre, UKSB modeli elektrik tüketim seviyelerini başarılı bir şekilde tahmin etmekte, tüketim seviyeleri eşiğe ulaştığında Programlanabilir Mantık Denetleyicisi PMD ünitesine durma sinyali göndermekte ve bu sayede aşırı kaynak tüketimini engellemektedir.

Makale detayları

A CASE STUDY FOR PREVENTING ELECTRICITY OVER-CONSUMPTION USING DEEP LEARNING IN TEXTILE INDUSTRY

Yazarlar:

Ömer Güleç

Yayıncı:

Süleyman Demirel University

Ana Başlıklar:

Bilgisayar Yazılımı

Dergi:

Mühendislik Bilimleri ve Tasarım Dergisi Vol.11 Issue 4, pp.1383-1397

Belge Tipi:

Makale

Yayın Tarihi:

12/2023

Belge Dili:

İngilizce

Document ID (Org No.):

2001307542

pISSN:

1308-6693

Deep Learning

LSTM

Sliding Window Technique

Electricity Consumption

Textile IndustryDerin Öğrenme

UKSB

Kayan Pencere Tekniği

Elektrik Tüketimi

Tekstil Endüstrisi

Sayı

Makale detayları

Yazarlar: Ömer Güleç

Yayıncı: Süleyman Demirel University

Ana Başlıklar: Bilgisayar Yazılımı

Dergi: Mühendislik Bilimleri ve Tasarım Dergisi Vol.11 Issue 4, pp.1383-1397

Belge Tipi: Makale

Yayın Tarihi: 12/2023

Belge Dili: İngilizce

Document ID (Org No.): 2001307542

pISSN: 1308-6693

Sayı

Yazarlar:

Ömer Güleç

Yayıncı:

Süleyman Demirel University

Ana Başlıklar:

Bilgisayar Yazılımı

Dergi:

Mühendislik Bilimleri ve Tasarım Dergisi Vol.11 Issue 4, pp.1383-1397

Belge Tipi:

Makale

Yayın Tarihi:

12/2023

Belge Dili:

İngilizce

Document ID (Org No.):

2001307542

pISSN:

1308-6693