Project Details
Description
Diagnosing a complex industrial process is a challenging task much akin to a health check-up that must be done in a continuous and timely manner. Just as a doctor uses various tests and observations to understand a patient’s condition, this PhD project aims to use simulation models to diagnose and improve the performance of the material handling process in one of the big pharmaceutical companies. The goal is to ensure these models accurately represent real-world scenarios and can reliably predict outcomes that can be used to streamline the operations.
The project is structured around four key phases. Initially, it focuses on validating both offline and real-time simulation models to ensure, that our diagnostic tool is accurate and reliable. By establishing a set of key performance indicators (KPIs) such as delivery times and downtime, the project seeks to confirm that the models work correctly and can be trusted.
In the sensitivity analysis phase, the project examines how changes in various parameters affect the model's outputs. The project identifies which parameters have the most significant impact on the model’s performance, enabling the development of strategies of mitigating potential negative effects.
Following this, the project conducts the what-if analysis and hypothesis testing on the validated simulation model. This phase explores potential outcomes of various scenarios, such as scaling up the capacity or dealing with equipment breakdowns, to find the best course of action.
Finally, the project focuses on generating short-term predictions based on real-time data. Much like a doctor providing immediate care based on the latest test results, the project aims to provide timely and accurate predictions to enhance decision-making processes.
Overall, the project establishes a robust approach that continuously improves material handling simulation models with up-to-date data. This framework can be used to optimize operations, reduce downtimes, and enhance overall process performance, ensuring that industrial processes run as smoothly and efficiently as possible.
The project is structured around four key phases. Initially, it focuses on validating both offline and real-time simulation models to ensure, that our diagnostic tool is accurate and reliable. By establishing a set of key performance indicators (KPIs) such as delivery times and downtime, the project seeks to confirm that the models work correctly and can be trusted.
In the sensitivity analysis phase, the project examines how changes in various parameters affect the model's outputs. The project identifies which parameters have the most significant impact on the model’s performance, enabling the development of strategies of mitigating potential negative effects.
Following this, the project conducts the what-if analysis and hypothesis testing on the validated simulation model. This phase explores potential outcomes of various scenarios, such as scaling up the capacity or dealing with equipment breakdowns, to find the best course of action.
Finally, the project focuses on generating short-term predictions based on real-time data. Much like a doctor providing immediate care based on the latest test results, the project aims to provide timely and accurate predictions to enhance decision-making processes.
Overall, the project establishes a robust approach that continuously improves material handling simulation models with up-to-date data. This framework can be used to optimize operations, reduce downtimes, and enhance overall process performance, ensuring that industrial processes run as smoothly and efficiently as possible.
| Status | Not started |
|---|
Fingerprint
Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.