Target Setting Model for Learning Equipment Operation Plans
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies face challenges in efficiently learning and optimizing control parameters for operating complex equipment, such as chemical and bio-industrial plants, due to the lack of effective methods for setting target ranges and integrating operator expertise into the learning process.
Innovation Solution
An apparatus and method that includes a target setting model to output identification information and target ranges for learning an operation model, utilizing both supervised and reinforcement learning to adapt control parameters based on operator input and historical data, ensuring alignment with predefined targets.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If conventional control systems are used for equipment operation, then the system structure is simple and easy to implement, but the operational efficiency is low and energy consumption is high
Solution Approach 1:
The patent replaces conventional mechanical control systems with an AI-based operation model that uses machine learning algorithms to optimize equipment operation. The operation model learns from historical operation data and automatically generates optimized operation plans, substituting traditional control mechanisms with intelligent algorithms that improve operational efficiency while reducing energy consumption through data-driven decision making.
Solution Approach 2:
The patent changes the operational parameters by introducing a target setting model that dynamically determines optimal target values for operation parameters based on learned patterns from historical data. This allows the system to adapt parameter settings in real-time, improving productivity while minimizing energy consumption through optimized parameter selection rather than fixed conventional settings.
2Manufacturing precision
If conventional control systems are used for equipment operation, then the implementation is straightforward, but the ability to achieve target settings is insufficient
Solution Approach 1:
The patent segments the control system into distinct functional modules: a target setting model that determines optimal target values, an operation model that generates operation plans, and a learning processing unit that trains these models. This segmentation allows each component to specialize in specific tasks, improving target setting accuracy while managing system complexity through modular architecture where each module can be developed and optimized independently.
Solution Approach 2:
The patent introduces a target setting model as an intermediary between the operation model and the equipment control system. This intermediary layer processes historical operation data to determine optimal target values before passing them to the operation model, thereby improving target setting accuracy. The intermediary manages complexity by providing a structured interface that decouples the complexity of learning algorithms from the simplicity of equipment control requirements.
3Productivity
If AI-based operation models are implemented, then operational efficiency and target setting accuracy improve, but the system complexity increases
Solution Approach 1:
The patent applies preliminary action by pre-training the operation model and target setting model using historical operation data before actual equipment operation. The learning processing unit continuously trains these models in advance using accumulated data, so that when the system operates, the models are already optimized and ready to provide efficient operation plans. This preliminary training phase separates the complexity of model development from operational complexity, allowing efficient operation once the models are established.
Solution Approach 2:
The operation model and target setting model are designed to self-improve through continuous learning from historical operation data. The learning processing unit automatically trains these models using accumulated data without requiring constant manual intervention or system reconfiguration. This self-service capability allows the system to maintain high operational efficiency while managing complexity through automated model optimization rather than manual system adjustments.
Data Source
AI summary
Provided is an apparatus including: a first acquisition unit acquiring an operation plan of a piece of equipment, and at least identification information of a parameter among target setting data used for learning of an operation model operating the piece of equipment, the target setting data including identification information of a parameter for which a target range is to be set among parameters relating to the piece of equipment and a target range set for the parameter; and a first learning processing unit performing, by using learning data including the identification information of the parameter and the operation plan acquired by the first acquisition unit, learning processing of a target setting model outputting at least one of the identification information or the target range of the parameter among the target setting data that should be used for learning of the operation model, in response to the operation plan being input.