IoT based pump performance monitoring for agricultural irrigation and predictive maintenance with machine learning models
[ X ]
Tarih
2024
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Adana Alparslan Türkeş Bilim ve Teknoloji Üniversitesi
Erişim Hakkı
info:eu-repo/semantics/openAccess
Özet
Kırsal alanlarda tarım sulamaları için sulama pompaları kullanılmaktadır. Kırsal tarım alanında bulunan sulama pompalarının periyodik bakımı maliyetli ve zaman alıcıdır; gerçek zamanlı bilgi alınmasıyla sorunların önceden tespit edilmesi, maliyet ve zaman kayıplarını önler. Bu çalışmanın temel amacı, Nesnelerin İnternetini (IoT) kullanarak tarımsal sulama için kurulan pompanın performansını anlık olarak izlemek ve sistem verilerine regresyon modelleri uygulayıp genetik algoritma (GA) ile modeller için optimum parametre değerlerini sağlamaktır. İlk olarak otomasyon sistemi kurularak sıcaklık, nem, akım, gerilim ve pompa titreşim bilgileri "Thingspeak" adlı bir IoT platformuna aktarılmıştır. Ardından Qt kullanıcı arayüzü oluşturma araç seti ile bir uygulama oluşturulmuştur. Bu uygulama sayesinde sistemde meydana gelen arızalar anlık olarak kullanıcıya bildirilmiştir. Sistemin kestirimci bakımı, makine öğrenimi alanında iki aşamalı bir süreçten oluşmaktadır. İlk aşamada, dört farklı yöntem modeli değerlendirildi. Bu modeller doğrusal regresyon, polinom regresyon (PR), rastgele orman regresyonu (RFR) ve destek vektör regresyonudur (SVR). İkinci aşamada, GA kullanılarak PR, SVR ve RFR modellerinin en uygun parametreleri belirlendi. Sonuç olarak, veri seti için en uygun modelin rastgele orman regresyon modeli olduğu bulunmuştur. Bu tezin, tarımsal sulama için IoT tabanlı pompa performansı izleme ve makine öğrenimi modelleri kullanarak kestirimci bakım tahmini ile ilgilenen araştırmacılara katkı sağlayacağı umulmaktadır.
Irrigation pumps are used for agricultural irrigation in rural areas. Periodic maintenance of irrigation pumps in rural agricultural areas is costly and time-consuming; early detection of problems with real-time information avoids cost and time loss. The main objective of this study is to monitor the performance of the pump installed for agricultural irrigation using the Internet of Things (IoT) and to apply regression models to the system data and to provide the optimum parameter values for the models with genetic algorithm (GA). Firstly, the automation system was installed and the temperature, humidity, current, voltage and pump vibration data were transferred to an IoT platform the named "Thingspeak". Then, an application was created with the Qt user interface creation toolkit. Thanks to this application, malfunctions occurring in the system were instantly notified to the user. Predictive maintenance of the system consists of a two-stage process in the field of machine learning. In the first stage, four different method models were evaluated. These models are linear regression, polynomial regression (PR), random forest regression (RFR) and support vector regression (SVR). In the second stage, the optimal parameters of PR, SVR and RFR models were determined using GA. As a result, the random forest regression model was found to be the most appropriate model for the dataset. It is hoped that this thesis will contribute to researchers interested in IoT-based pump performance monitoring for agricultural irrigation and predictive maintenance estimation using machine learning models.
Irrigation pumps are used for agricultural irrigation in rural areas. Periodic maintenance of irrigation pumps in rural agricultural areas is costly and time-consuming; early detection of problems with real-time information avoids cost and time loss. The main objective of this study is to monitor the performance of the pump installed for agricultural irrigation using the Internet of Things (IoT) and to apply regression models to the system data and to provide the optimum parameter values for the models with genetic algorithm (GA). Firstly, the automation system was installed and the temperature, humidity, current, voltage and pump vibration data were transferred to an IoT platform the named "Thingspeak". Then, an application was created with the Qt user interface creation toolkit. Thanks to this application, malfunctions occurring in the system were instantly notified to the user. Predictive maintenance of the system consists of a two-stage process in the field of machine learning. In the first stage, four different method models were evaluated. These models are linear regression, polynomial regression (PR), random forest regression (RFR) and support vector regression (SVR). In the second stage, the optimal parameters of PR, SVR and RFR models were determined using GA. As a result, the random forest regression model was found to be the most appropriate model for the dataset. It is hoped that this thesis will contribute to researchers interested in IoT-based pump performance monitoring for agricultural irrigation and predictive maintenance estimation using machine learning models.
Açıklama
Lisansüstü Eğitim Enstitüsü, Elektrik-Elektronik Mühendisliği Ana Bilim Dalı
Anahtar Kelimeler
Elektrik ve Elektronik Mühendisliği, Electrical and Electronics Engineering
