Local AI Control Modules for Real-Time Industrial Diagnostics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Industrial automation systems face challenges in efficiently monitoring and diagnosing complex processes due to the increasing volume and complexity of process data, which often require real-time analysis and are hindered by the limitations of cloud-based systems in terms of cost, logistics, and security.
Innovation Solution
A local control system comprising modules that can analyze data in real-time without relying on cloud computing, using an AI module to model target variables, adjust operations, and encrypt data for secure communication within the local network, enabling efficient monitoring and diagnostics without transmitting data outside the local area network.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Power
If cloud-based systems are used for real-time analysis of process data, then computational power and data processing capability are improved, but cost, logistics complexity, and security risks increase
Solution Approach 1:
The patent segments the control system into multiple distributed control modules that can operate independently within the local network. Each module can process data locally, eliminating the need for centralized cloud processing while maintaining computational capabilities through distributed architecture
Solution Approach 2:
The patent introduces a local network as an intermediary between control modules, enabling secure data exchange and processing without requiring cloud connectivity. This intermediary layer provides the necessary computational power while maintaining system autonomy and security
2Measurement precision
If more process data is collected and analyzed in real-time, then monitoring precision and diagnostic accuracy are improved, but data processing complexity and computational requirements increase
Solution Approach 1:
The patent divides the data processing task into segments handled by different control modules. Each module processes specific data types or time windows locally, reducing the complexity burden on any single system while maintaining high monitoring precision through coordinated analysis
Solution Approach 2:
The patent implements selective data processing where only relevant data points are analyzed in real-time, while less critical data is processed asynchronously or aggregated. This partial action approach maintains monitoring precision for critical parameters without overwhelming the system with excessive processing complexity
3Adaptability or versatility
If data is transmitted to cloud systems for analysis, then access to advanced analytics and algorithms is improved, but security risks and network dependency increase
Solution Approach 1:
The patent enables control modules to perform advanced analytics locally through embedded algorithms and machine learning models. Each module is self-sufficient in processing and analyzing its data, eliminating security risks associated with data transmission while maintaining versatile analytics capabilities through distributed intelligence
Solution Approach 2:
Instead of transmitting data upward to centralized cloud systems for analysis, the patent inverts the architecture so that analytical capabilities are distributed downward to local control modules. This inversion maintains security by keeping data local while achieving versatility through distributed analytical power
Data Source
AI summary
An industrial automation system may include an automation device and a control system communicatively coupled to the automation device. The control system may include a first module of a number of modules, such that the first module may receive an indication of a target variable associated with the industrial automation device. The first module may then receive parameters associated with the target variable, identify a portion of data points associated with controlling the target variable with respect to the parameters, generate a model of each data point of the portion over time with respect to the parameters based on the data points, determine functions associated with the model. The functions represent one or more relationships between the each data point of the portion with respect to controlling the target variable. The first module may then adjust one or more operations of the automation device based on the functions.