Influence Model Initialization for Environmental Control Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The initialization and updating of influence models for supervisory controllers in environmental management systems are time-consuming and challenging, especially when retrofitting or updating systems with changes in the environmentally controlled space, leading to inefficiencies and potential model inaccuracies.
Innovation Solution
The system updates the influence model by running in a first production mode, identifying events such as performance degradation, and entering a second production mode where the operation levels of actuators are varied along a predetermined trajectory to initialize or update the model, allowing for reduced costs and installation time while maintaining desired physical conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a separate initialization process is used to initialize the influence model, then the model accuracy is improved, but the installation time and system downtime are increased
Solution Approach 1:
The system performs preliminary data collection and model initialization during normal production operation before the supervisory controller is fully deployed. Sensors continue to collect data during production mode, and this data is used to pre-initialize the influence model, so that when the controller switches to supervisory mode, the model is already prepared and no separate initialization downtime is needed.
Solution Approach 2:
The system maintains continuous operation without interruption during model initialization. The environmental management system continues to control physical conditions throughout the initialization process, and sensors continue collecting data. The initialization occurs in the background during normal operation, eliminating the need to stop the system for model preparation.
2Productivity
If the system enters production mode immediately without initialization, then the productivity is improved, but the model accuracy deteriorates
Solution Approach 1:
The system initializes and updates its own influence model automatically during normal operation without requiring external intervention or separate initialization procedures. The supervisory controller continuously collects sensor data and uses it to initialize and update the influence model in the background, allowing the system to maintain both high productivity and model accuracy simultaneously.
Solution Approach 2:
The system performs preliminary data collection and model preparation during normal production operation. Sensors collect data continuously, and this data is used to pre-initialize the influence model before supervisory control fully engages, ensuring the model is accurate while the system remains productive throughout the process.
3Measurement precision
If actuators are varied along a predetermined trajectory to update the model, then the model accuracy is improved, but the power consumption increases
Solution Approach 1:
The system varies actuator operation levels partially along predetermined trajectories only when needed for model updates, not continuously. During normal operation, actuators maintain optimal settings for power efficiency. The trajectory-based variation is applied selectively during scheduled model updates or when performance degradation is detected, balancing model accuracy requirements with power consumption constraints.
Solution Approach 2:
The system performs actuator trajectory variations periodically for model updates rather than continuously. The supervisory controller schedules model updates at appropriate intervals, varying actuator operation levels along predetermined trajectories only during these periodic update cycles, while maintaining power-efficient operation during normal control periods.
4Measurement precision
If the influence model is updated frequently to maintain accuracy, then the model accuracy is improved, but the computational load and processing time increase
Solution Approach 1:
The system updates the influence model periodically rather than continuously, balancing accuracy requirements with processing efficiency. The supervisory controller schedules model updates at appropriate intervals based on operational conditions, performing comprehensive model updates periodically while using faster approximation methods or maintaining current models between updates when conditions allow.
Solution Approach 2:
The system uses feedback mechanisms to determine when model updates are necessary. The supervisory controller monitors system performance and sensor data quality, triggering model updates only when performance degradation is detected or when sufficient new data has accumulated, avoiding unnecessary processing while maintaining model accuracy.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Systems and methods are described for updating an influence model used to manage physical conditions of an environmentally controlled space. A method comprises operating an environmental maintenance system in a first production mode with the influence model until an event causes the system to enter a second production mode. In the second production mode a first actuators operation level is varied and operation levels of other actuators are optimized. The influence model is adjusted based on the operation levels.