Peripheral Machine Feedback Control for Factory Energy Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing industrial control systems for manufacturing facilities require specialized knowledge and are difficult to adapt to changes in the manufacturing process, leading to inefficient resource usage and diminished performance.
Innovation Solution
A machine learning-based control system that uses sensor data to train a model for real-time control of peripheral machines, optimizing energy consumption while meeting the energy demands of manufacturing machines, without requiring specialized knowledge of the facility.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If custom-made control solutions are implemented by experts, then energy optimization is improved, but device complexity and difficulty of adaptation increase
Solution Approach 1:
The control system automatically optimizes energy consumption without requiring expert intervention. The system self-adjusts operational parameters of peripheral machines based on real-time sensor data and pre-defined optimization algorithms, eliminating the need for manual energy surveys and expert planning while maintaining energy optimization benefits
Solution Approach 2:
The system dynamically adapts to changes in the manufacturing facility by continuously monitoring sensor data and adjusting control parameters in real-time. This dynamic approach replaces static custom-made solutions with adaptive automation that automatically responds to facility changes without requiring reevaluation by experts
2Productivity
If custom-made control solutions are tailored to the factory, then initial performance is improved, but adaptability to changes deteriorates
Solution Approach 1:
The system incorporates continuous feedback loops that monitor sensor data from the manufacturing facility and automatically adjust operational parameters. This feedback mechanism enables the system to adapt to changes in real-time, maintaining high performance without requiring manual reevaluation when facility conditions change
Solution Approach 2:
The system pre-defines optimization algorithms and control strategies that automatically activate based on detected conditions. This preliminary configuration enables immediate adaptation to changes without requiring expert intervention, while maintaining the performance benefits of customized solutions
3Loss of energy
If manual energy surveys and planning are conducted, then energy efficiency is improved, but loss of time and manual labor increase
Solution Approach 1:
The system replaces manual energy surveys and planning activities with automated electronic monitoring and control. Sensors continuously collect data on energy consumption and operational parameters, and algorithms automatically analyze this data to optimize efficiency, eliminating the need for manual survey procedures and reducing both time and labor requirements
Solution Approach 2:
The system provides continuous automated monitoring and optimization of energy efficiency rather than periodic manual surveys. This continuous action maintains energy efficiency improvements over time without requiring repeated manual interventions, significantly reducing the time and labor associated with traditional energy management approaches
Data Source
Figure 1
Figure 2
Figure 3~4
AI summary
A method of applying feedback control on peripheral units supplying energy to manufacturing units in a manufacturing facility uses a trained model, and includes: mapping supply relations between peripheral units and manufacturing units into a schema; establishing communications with sensors monitoring peripheral unit metrics indicative of energy transfer from the peripheral units to the manufacturing units; training the model based on the schema and training data gathered by communication with the sensors during a training period, the trained model predicting energy usage by the peripheral machines with a specified degree of accuracy; and during a control period following the training period, gathering further data from the sensors and minimizing energy usage by the peripheral units while supplying the total energy demanded by the manufacturing units by controlling at least one of the peripheral units based on an outcome of inputting the further data into the trained model.