AI Control Feasibility Validation Using Equipment Simulation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems lack an effective method to determine whether artificial intelligence (AI) control of complex equipment is possible before initiating AI control, potentially leading to equipment malfunctions due to inadequate simulation and learning model validation.
Innovation Solution
A determination apparatus that acquires state and operation data, generates a control model through machine learning, simulates equipment states, and determines AI control feasibility based on simulation results, including thresholds for normal operation periods and convergence of machine learning, to prevent equipment abnormalities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If AI control is implemented without prior simulation and validation, then automation and productivity are improved, but equipment reliability and safety deteriorate due to potential malfunctions
Solution Approach 1:
The patent applies preliminary action by conducting simulation experiments and validation tests before implementing AI control on actual equipment. The system performs pre-validation of the learning model through simulated operations, ensuring that the AI control will not cause equipment malfunctions before actual deployment, thus maintaining both productivity improvement and equipment safety.
2Reliability
If comprehensive simulation and validation are performed before AI control implementation, then equipment reliability is improved, but time consumption and complexity increase
Solution Approach 1:
The patent applies copying by creating a virtual simulation environment that replicates the actual equipment's behavior. Instead of testing on real equipment, the system uses a copied virtual model to perform comprehensive validation experiments, ensuring reliability while avoiding time loss and physical risks associated with testing on actual equipment.
Solution Approach 2:
The simulation and validation processes are conducted in advance before actual AI control implementation. By performing all necessary validation experiments on the virtual model beforehand, the system ensures that when AI control is deployed on real equipment, it has already been proven safe and effective, thus minimizing the time impact of validation.
3Measurement precision
If the learning model is continuously optimized through re-generation, then control precision is improved, but computational resources and time are consumed
Solution Approach 1:
The patent applies feedback by using the results from simulation experiments to evaluate the learning model's performance. Based on the simulation outcomes, the system determines whether the learning model needs re-generation or optimization. This feedback mechanism ensures that computational resources are only used when necessary to improve control accuracy, balancing precision gains with energy consumption.
Data Source
AI summary
Provided is a determination apparatus comprising: a state data acquisition unit configured to acquire state data indicative of a state of equipment provided with a control target; an operation amount data acquisition unit configured to acquire operation amount data indicative of an operation amount of the control target; a control model generation unit configured to generate a control model, which outputs the operation amount corresponding to the state of the equipment, by machine learning by using the state data and the operation amount data; a simulation unit configured to simulate, by using a simulation model, the state of the equipment in a case where the operation amount, which is output by the control model, is given to the control target; and a determination unit configured to determine whether control of the control target by the control model is possible, based on a simulation result.