Leveraging blockchain for intelligent predictive maintenance frameworks in the industrial internet of things
Endüstriyel nesnelerin internetinde akıllı öngörücü bakım çerçeveleri için blokzincir kullanımı
- Tez No: 853420
- Danışmanlar: DOÇ. DR. ADIB HABBAL
- Tez Türü: Doktora
- Konular: Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve Kontrol, Computer Engineering and Computer Science and Control
- Anahtar Kelimeler: Belirtilmemiş.
- Yıl: 2024
- Dil: İngilizce
- Üniversite: Karabük Üniversitesi
- Enstitü: Lisansüstü Eğitim Enstitüsü
- Ana Bilim Dalı: Bilgisayar Mühendisliği Ana Bilim Dalı
- Bilim Dalı: Belirtilmemiş.
- Sayfa Sayısı: 203
Özet
The Industrial Internet of Things (IIoT) is a transformative area that represents a significant leap in industrial and technological advancement. IIoT integrates advanced digital technologies into industrial settings, enabling a level of automation and data exchange that revolutionizes manufacturing and industrial practices. Central to this evolution is predictive maintenance (PdM), a proactive approach that utilizes data analytics to predict equipment failures before they occur, thereby minimizing downtime and extending machinery lifespan. Within this context, determining the Remaining Useful Life (RUL) of industrial equipment is a critical aspect of PdM in IIoT, as it guides maintenance decisions and enhances operational efficiency. Deep Learning (DL) emerges as a powerful tool in the PdM landscape due to its ability to handle complex, multivariate data and uncover patterns that traditional analytical methods might miss. However, the integration of DL in PdM within IIoT presents significant challenges, including handling large data volumes, adapting to dynamic industrial environments, and overcoming the limitations of centralized data processing systems. To address these challenges, this research introduces two innovative frameworks: the Decentralized Predictive Maintenance Framework (DPdMF) and the Blockchain and Dynamic Deep Learning Framework (BDDLF). DPdMF leverages blockchain technology and the InterPlanetary File System (IPFS) to create a decentralized architecture that enhances data security and scalability. It incorporates a two-tiered structure with advanced deep-learning models for feature extraction and RUL prediction. BDDLF builds on these features with a three-tier architecture that includes dynamic deep learning pipelines that can adapt to changing IIoT environments and provides a complete solution for RUL forecasting. Both frameworks mark a significant step forward in predictive maintenance for IIoT, addressing the key research challenges of large data management, dynamic adaptability, and decentralized processing. DPdMF and BDDLF make a big difference in the progress of PdM in the age of Industry 4.0 by providing scalable, secure, and effective ways to accurately predict RUL. The DPDMF and BDDLF frameworks have significant implications for the IIoT sector, offering robust solutions for predictive maintenance by harnessing the power of blockchain for security and deep learning for analytical precision.
Özet (Çeviri)
The Industrial Internet of Things (IIoT) is a transformative area that represents a significant leap in industrial and technological advancement. IIoT integrates advanced digital technologies into industrial settings, enabling a level of automation and data exchange that revolutionizes manufacturing and industrial practices. Central to this evolution is predictive maintenance (PdM), a proactive approach that utilizes data analytics to predict equipment failures before they occur, thereby minimizing downtime and extending machinery lifespan. Within this context, determining the Remaining Useful Life (RUL) of industrial equipment is a critical aspect of PdM in IIoT, as it guides maintenance decisions and enhances operational efficiency. Deep Learning (DL) emerges as a powerful tool in the PdM landscape due to its ability to handle complex, multivariate data and uncover patterns that traditional analytical v methods might miss. However, the integration of DL in PdM within IIoT presents significant challenges, including handling large data volumes, adapting to dynamic industrial environments, and overcoming the limitations of centralized data processing systems. To address these challenges, this research introduces two innovative frameworks: the Decentralized Predictive Maintenance Framework (DPdMF) and the Blockchain and Dynamic Deep Learning Framework (BDDLF). DPdMF leverages blockchain technology and the InterPlanetary File System (IPFS) to create a decentralized architecture that enhances data security and scalability. It incorporates a two-tiered structure with advanced deep-learning models for feature extraction and RUL prediction. BDDLF builds on these features with a three-tier architecture that includes dynamic deep learning pipelines that can adapt to changing IIoT environments and provides a complete solution for RUL forecasting. Both frameworks mark a significant step forward in predictive maintenance for IIoT, addressing the key research challenges of large data management, dynamic adaptability, and decentralized processing. DPdMF and BDDLF make a big difference in the progress of PdM in the age of Industry 4.0 by providing scalable, secure, and effective ways to accurately predict RUL. The DPDMF and BDDLF frameworks have significant implications for the IIoT sector, offering robust solutions for predictive maintenance by harnessing the power of blockchain for security and deep learning for analytical precision.
Benzer Tezler
- Blokzincir tabanlı ıot sağlık platformu ile hasta verilerinin güvenli paylaşımı ve izlenmesi
Secure sharing and monitoring of patient data through a blockchain-based iot healthcare platform
GALAL ABDULRAHEEM ALI AHMED
Yüksek Lisans
Türkçe
2025
Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve KontrolSakarya ÜniversitesiBilgisayar ve Bilişim Mühendisliği Ana Bilim Dalı
PROF. DR. ÜNAL ÇAVUŞOĞLU
- Digitalization in construction claim management
İnşaat hak talebi yönetiminde dijitalleşme
NİL DENİZMEN
Yüksek Lisans
İngilizce
2025
İnşaat Mühendisliğiİstanbul Teknik Üniversitesiİnşaat Mühendisliği Ana Bilim Dalı
DOÇ. DR. DENİZ ARTAN
- Digital transformation in the west and east: Lessons for the Muslim majority countries
Batı ve doğu'da dijital dönüşüm: Müslüman çoğunluklu ülkeler için dersler
SHAH FAHAD
Doktora
İngilizce
2025
Ekonomiİstanbul Sabahattin Zaim Üniversitesiİslam Ekonomisi ve Finansı Ana Bilim Dalı
Prof. Dr. MEHMET BULUT
- Gemi siber güvenlik dinamiklerinin belirlenmesi ve köprüüstü seyir ekipmanlari özelinde siber güvenlik risk değerlendirme uygulamalari
Determination of ship cyber security dynamics and cyber security risk assessment applications specifically for bridge navigation equipment
BÜNYAMİN GÜNEŞ
Doktora
Türkçe
2025
Denizcilikİstanbul Teknik ÜniversitesiDeniz Ulaştırma Mühendisliği Ana Bilim Dalı
DOÇ. DR. PELİN BOLAT
- Blokzincir (blockchaın) teknolojisinin inşaat sektöründe kullanım potansiyelinin incelenmesi
Investigation of the potential use of blockchain technology in the construction industry
ONUR KUZU