Register now After registration you will be able to apply for this opportunity online.
Predictive Modeling for Energy Consumption and Emissions in Robotic 3D Printing
Digital and robotic fabrication techniques are increasingly being explored to create building components with embedded functionalities, offering unparalleled opportunities for customization.
As the adoption of robotic 3D printing grows, it becomes crucial to evaluate the environmental impacts of these processes, particularly their energy consumption and associated emissions. Understanding these impacts is essential to assess the sustainability of robotic 3D printing processes.
This project, enabled by real-world data provided by Saeki Robotics, aims to develop a predictive model to assess and forecast energy consumption and emissions in robotic 3D printing.
Keywords: robotic 3D printing, energy, and emissions, machine learning, additive manufacturing
**Objectives**
The project's main goal is to develop a predictive model for energy consumption and emissions in robotic 3D printing to support data-driven process analysis.
Additional Objectives:
- Analyze company-provided data to identify key drivers of energy consumption.
- Build a machine learning-based model to predict energy usage under various printing conditions.
- Integrate emissions estimation into the model using energy source emission factors.
- Provide insights into the environmental performance of robotic 3D printing processes.
**Methodology and Tools**
- Data Analysis: Utilize fabrication data provided by Saeki Robotics.
- Predictive Modeling: Use machine learning techniques to develop forecasting models.
- Validation and Process Insights: Validate the data-driven model with physics-based/analytical models and extract key findings on process energy and emissions profiles.
**Expected Outcomes**
- A validated predictive model for energy consumption and emissions.
- Insights into the main contributors to energy usage and emissions in robotic 3D printing.
- A comprehensive analysis of the environmental performance of printing processes.
**We are looking for**
A motivated student with a background in engineering, data science, or sustainability. Experience with programming, machine learning, and 3D printing technologies is a plus.
**References:**
Yan, Z., et al. (2023): Hybrid mechanism-based and data-driven approach to forecast energy consumption of FDM. Journal of Cleaner Production.
DOI: 10.1016/j.jclepro.2023.137500
Ghungrad, S., et al. (2024): Kinematics-guided data-driven energy surrogate model for robotic additive manufacturing. Journal of Manufacturing Processes.
DOI: 10.1016/j.mfglet.2024.09.017
Yan, Z., et al. (2022): A new method of predicting the energy consumption of additive manufacturing considering the component working state. Sustainability.
DOI: 10.3390/su14073757
**Objectives** The project's main goal is to develop a predictive model for energy consumption and emissions in robotic 3D printing to support data-driven process analysis.
Additional Objectives:
- Analyze company-provided data to identify key drivers of energy consumption.
- Build a machine learning-based model to predict energy usage under various printing conditions.
- Integrate emissions estimation into the model using energy source emission factors.
- Provide insights into the environmental performance of robotic 3D printing processes.
**Methodology and Tools**
- Data Analysis: Utilize fabrication data provided by Saeki Robotics.
- Predictive Modeling: Use machine learning techniques to develop forecasting models.
- Validation and Process Insights: Validate the data-driven model with physics-based/analytical models and extract key findings on process energy and emissions profiles.
**Expected Outcomes**
- A validated predictive model for energy consumption and emissions.
- Insights into the main contributors to energy usage and emissions in robotic 3D printing.
- A comprehensive analysis of the environmental performance of printing processes.
**We are looking for**
A motivated student with a background in engineering, data science, or sustainability. Experience with programming, machine learning, and 3D printing technologies is a plus.
**References:**
Yan, Z., et al. (2023): Hybrid mechanism-based and data-driven approach to forecast energy consumption of FDM. Journal of Cleaner Production. DOI: 10.1016/j.jclepro.2023.137500
Ghungrad, S., et al. (2024): Kinematics-guided data-driven energy surrogate model for robotic additive manufacturing. Journal of Manufacturing Processes. DOI: 10.1016/j.mfglet.2024.09.017
Yan, Z., et al. (2022): A new method of predicting the energy consumption of additive manufacturing considering the component working state. Sustainability. DOI: 10.3390/su14073757
Not specified
For more information or to apply, contact piccioni@arch.ethz.ch.
For more information or to apply, contact piccioni@arch.ethz.ch.
SP_VP_PredictiveModelling_Robotic3DP_Emissions.pdf
