Hybrid Control Switching for Disturbance-Adaptive Equipment Operation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing control systems for facilities with multiple equipment types struggle to efficiently manage and optimize operations due to variations in environmental disturbances and operational states, leading to inefficiencies and suboptimal performance.

Innovation Solution

A control apparatus that integrates feedback and AI-based control methods, utilizing a switching mechanism to dynamically switch between feedback control and AI control based on measured differences and environmental conditions, optimizing operation amounts through learning and reinforcement learning.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If a single control method (feedback or feed-forward) is used, then the control system is simple, but it cannot adapt to varying environmental disturbances and operational states

Engineering Contradiction:
Improveadaptability to environmental disturbancesVSAvoidcontrol system complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The control system dynamically switches between feedback control and feed-forward control based on operational conditions. A switching unit selects which control method to use, allowing the system to adapt to varying environmental disturbances and operational states rather than relying on a fixed control approach

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The control apparatus integrates multiple control methods (feedback control and feed-forward control) into a single system. This multi-functional approach allows the system to handle different types of control scenarios and environmental conditions using appropriate control strategies

Inventive Principle:
Principle #6Universality (Multi-functionality)

2Productivity

If learning-based control is always used, then optimal performance is achieved, but the system becomes complex and difficult to implement

Engineering Contradiction:
Improveoperational efficiencyVSAvoidcontrol system complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The system dynamically switches between learning-based control and traditional control methods based on operational conditions. The switching unit determines when to use the learned model for optimal performance and when to revert to simpler control approaches, balancing efficiency and complexity

Inventive Principle:
Principle #15Dynamics

3Adaptability or versatility

If switching between control methods is implemented, then adaptability improves, but control stability may deteriorate due to frequent switching

Engineering Contradiction:
Improveadaptability to operational statesVSAvoidcontrol stability
Core Design Contradiction:
Adaptability or versatilityVSStability of the object's composition

Solution Approach 1:

The switching logic is designed to prevent frequent or unnecessary switching between control methods. By establishing clear switching criteria and hysteresis mechanisms, the system avoids instability caused by oscillatory switching while maintaining adaptability to genuine changes in operational conditions

Inventive Principle:
Principle #9Preliminary anti-action

Data Source

PatentUS12602026B2Control apparatus, control method, and storage medium
Publication Date: 2026.04.14 YOKOGAWA ELECTRIC CORP
  • US12602026B2 patent drawing
  • US12602026B2 patent drawing
  • US12602026B2 patent drawing

AI summary

Provided is a control apparatus including an acquisition unit configured to acquire a measurement value measured regarding control target equipment, a first control unit configured to output an operation amount of the control target equipment according to the measurement value by at least one of feedback control or feed-forward control, a second control unit configured to output an operation amount of the control target equipment according to the measurement value using a model learnt by using learning data, and a switching unit configured to perform switching between the first control unit and the second control unit by which the control target equipment is controlled.