Register now After registration you will be able to apply for this opportunity online.
Optimizing HVAC Commissioning: A Deep Learning Approach for Parameter Prediction and Error Reduction
The project is a collaboration between EPFL IMOS Lab and Belimo exploring Deep Learning algorithms for commissioning parameters of Heating, Ventilation, and Air Conditioning systems
Keywords: Deep Learning; HVAC Systems; Building Systems; Commissioning; Parameter Estimation
Modern buildings are equipped with a large number of HVAC (Heating, Ventilation, and Air Conditioning) devices, comprising sensors, actuators, control systems mounted in very different locations. The integration of these components into the overarching building control system necessitates a meticulous configuration process known as commissioning. This undertaking represents the predominant portion of the interaction time between the device and the human operator, excluding routine operational tasks such as temperature readings from room sensors. Consequently, commissioning emerges as the most time-consuming, expensive, and error-prone phase in the establishment of a seamlessly operating building. as Any errors during commissioning can significantly impact the overall efficiency and functionality of the building.
Modern buildings are equipped with a large number of HVAC (Heating, Ventilation, and Air Conditioning) devices, comprising sensors, actuators, control systems mounted in very different locations. The integration of these components into the overarching building control system necessitates a meticulous configuration process known as commissioning. This undertaking represents the predominant portion of the interaction time between the device and the human operator, excluding routine operational tasks such as temperature readings from room sensors. Consequently, commissioning emerges as the most time-consuming, expensive, and error-prone phase in the establishment of a seamlessly operating building. as Any errors during commissioning can significantly impact the overall efficiency and functionality of the building.
In the context of this Master Thesis, the objective is to investigate the feasibility of developing an algorithm capable of predicting and verifying parameter values during the commissioning process, aiming to mitigate the occurrence of human errors.
The tasks involved in achieving this goal encompass:
• Analysis of the Provided Dataset:
o Thoroughly examine the dataset provided by Belimo, which contains instances of commissioned devices.
o Extract meaningful insights and patterns from the dataset to understand the intricacies of the commissioning process.
• Identification of Patterns and Human Errors:
o Identify recurring patterns within the dataset to discern regularities in commissioning procedures.
o Pay special attention to potential human errors that may be evident in the dataset, contributing to a comprehensive understanding of common pitfalls.
• Development of a prediction Algorithm for commissioning parameters:
o Based on the analysis, develop a machine learning algorithm for predicting commissioning parameters.
o The algorithm should not only predict parameter values but also provide recommendations to the commissioner, acting as a valuable tool in the commissioning process.
• Evaluate the developed algorithm Real-World Testing Scenario:
o Implement a real-world testing scenario to validate and assess the effectiveness of the developed algorithm.
o Evaluate the algorithm's performance in predicting and checking commissioning parameters under practical conditions.
o Gather empirical evidence to demonstrate the potential of the proposed solution in reducing human errors during the commissioning process.
Through these tasks, the aim is to contribute valuable insights and a practical solution that can enhance the efficiency and accuracy of the commissioning process in the domain of HVAC devices.
Requirements :
• Engineering proficiency; HVAC familiarity beneficial
• Proficiency in Data Science and Deep Learning
In the context of this Master Thesis, the objective is to investigate the feasibility of developing an algorithm capable of predicting and verifying parameter values during the commissioning process, aiming to mitigate the occurrence of human errors.
The tasks involved in achieving this goal encompass:
• Analysis of the Provided Dataset: o Thoroughly examine the dataset provided by Belimo, which contains instances of commissioned devices. o Extract meaningful insights and patterns from the dataset to understand the intricacies of the commissioning process.
• Identification of Patterns and Human Errors: o Identify recurring patterns within the dataset to discern regularities in commissioning procedures. o Pay special attention to potential human errors that may be evident in the dataset, contributing to a comprehensive understanding of common pitfalls.
• Development of a prediction Algorithm for commissioning parameters: o Based on the analysis, develop a machine learning algorithm for predicting commissioning parameters. o The algorithm should not only predict parameter values but also provide recommendations to the commissioner, acting as a valuable tool in the commissioning process.
• Evaluate the developed algorithm Real-World Testing Scenario: o Implement a real-world testing scenario to validate and assess the effectiveness of the developed algorithm. o Evaluate the algorithm's performance in predicting and checking commissioning parameters under practical conditions. o Gather empirical evidence to demonstrate the potential of the proposed solution in reducing human errors during the commissioning process.
Through these tasks, the aim is to contribute valuable insights and a practical solution that can enhance the efficiency and accuracy of the commissioning process in the domain of HVAC devices.