https://github.com/vbs360/conditional_base_monitoring_in_marine_system

Model to proactively schedule maintenance activities and avoid unexpected failures.
https://github.com/vbs360/conditional_base_monitoring_in_marine_system

Last synced: 25 days ago
JSON representation

Model to proactively schedule maintenance activities and avoid unexpected failures.

• Host: GitHub
• URL: https://github.com/vbs360/conditional_base_monitoring_in_marine_system
• Owner: VBS360
• Created: 2024-08-04T02:44:32.000Z (5 months ago)
• Default Branch: main
• Last Pushed: 2024-08-24T04:14:30.000Z (5 months ago)
• Last Synced: 2024-08-24T05:24:59.131Z (5 months ago)
• Language: Jupyter Notebook
• Size: 12.1 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
![Maritime Monitoring system](https://github.com/user-attachments/assets/f70eab10-209e-42f4-9b4f-0dd2de33991b)

# Conditional_Base_Monitoring_in_Marine_System

* Maintaining optimal performance and preventing failures in maritime propulsion systems is crucial for the safety, efficiency, and longevity of vessels. 

* Gas turbines, which are critical components of these propulsion systems, require advanced techniques for effective monitoring and analysis. 

* Predictive maintenance and condition-based monitoring can prevent costly failures and enhance operational efficiency, but they depend heavily on accurate forecasting models.

* Fleet of ships and requires a predictive maintenance system to reduce downtime and maintenance costs.

* The task is to predict the decay state coefficients of the gas turbine (GT) and gas generator (GG) based on various features.

* The maritime industry faces significant challenges in ensuring the reliability and performance of gas turbine propulsion systems. 

* Unplanned downtime due to failures can lead to substantial financial losses and safety risks. Traditional maintenance strategies often fall short in preventing such failures, as they do not leverage the full potential of the available operational data.

* Traditional maintenance strategies often fall short in preventing such failures, as they do not leverage the full potential of the available operational data.

* Our task is to predicts the decay state coefficients with a high degree of accuracy.