Secure Model Interfaces for Proprietary Control Optimization

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional model-based optimization and control solutions require full disclosure of models to decision engines, which can be undesirable when models contain sensitive information, leading to increased costs and security concerns, hindering collaborative decision-making and cloud-based solutions.

Innovation Solution

The system instantiates model objects on servers, generating approximations of proprietary models to prevent sensitive information disclosure, using a communication protocol that precludes transmission of proprietary data, allowing secure control command generation and execution.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If full model disclosure is used for model-based optimization and control, then control accuracy and optimization performance are improved, but proprietary information security deteriorates

Engineering Contradiction:
Improvecontrol accuracyVSAvoidproprietary information security
Core Design Contradiction:
Measurement precisionVSLoss of information

Solution Approach 1:

The patent introduces an intermediary mechanism where the decision engine communicates with the model through a secure interface that provides necessary information for control decisions without exposing proprietary model details. This mediator layer enables control accuracy while protecting intellectual property by selectively disclosing only essential operational parameters.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent creates simplified copies or approximations of the proprietary model that can be shared with the decision engine. These copies contain only the necessary information for control purposes, allowing accurate control decisions to be made without exposing the full proprietary model structure and sensitive parameters.

Inventive Principle:
Principle #26Copying

2Loss of information

If model ownership is centralized to protect proprietary information, then information security is improved, but system complexity and cost increase

Engineering Contradiction:
Improveproprietary information securityVSAvoidsystem complexity
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The patent segments the system into distinct functional modules: the proprietary model module that protects intellectual property, the decision engine module that performs optimization, and the control module that executes actions. This segmentation allows each component to operate independently with clearly defined interfaces, reducing overall system complexity while maintaining security.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent creates a universal interface protocol that enables the decision engine to interact with multiple different proprietary models without needing to understand their internal structures. This multi-functional interface handles various model types through standardized communication rules, simplifying system integration and reducing complexity.

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

3Loss of information

If full model disclosure is required, then collaborative decision-making is hindered, but information security is maintained

Engineering Contradiction:
Improveinformation securityVSAvoidcollaborative decision-making capability
Core Design Contradiction:
Loss of informationVSAdaptability or versatility

Solution Approach 1:

The patent establishes an intermediary communication protocol that enables multiple stakeholders to collaborate on decision-making without exposing their proprietary models to each other. The intermediary translates and mediates information exchange, allowing collaborative optimization while maintaining individual information security boundaries.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent enables collaborative decision-making by allowing participants to work with copies or representations of models rather than the full proprietary versions. These copies suffice for collaborative optimization purposes while protecting original intellectual property, thus enabling versatility in collaboration without compromising security.

Inventive Principle:
Principle #26Copying

Data Source

PatentEP2728426B1Secure models for model-based control and optimization
Publication Date: 2021.07.28 ROCKWELL AUTOMATION TECH INC
  • EP2728426B1 patent drawingFigure 1
  • EP2728426B1 patent drawingFigure 2
  • EP2728426B1 patent drawingFigure 3

AI summary

In certain embodiments, a control/optimization system includes an instantiated model object stored in memory on a model server. The model object includes a model of a plant or process being controlled. The model object comprises an interface that precludes the transmission of proprietary information via the interface. The control/optimization system also includes a decision engine software module stored in memory on a decision support server. The decision engine software module is configured to request information from the model object through a communication network via a communication protocol that precludes the transmission of proprietary information, and to receive the requested information from the model object through the communication network via the communication protocol.