Edge AI Data Acquisition Module for Low-Latency Shop-Floor Evaluation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional automation devices lack the computing power for AI technology, and cloud-based solutions are not easily implemented for shop-floor applications, leading to high communication overhead and data sovereignty issues in industrial systems.
Innovation Solution
A module with a freely programmable measuring unit and AI microcontroller integrated into a decentralized peripheral, allowing on-site AI evaluation and data preprocessing, reducing data load by transmitting only results through the backplane bus.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Power
If cloud-based AI solutions are used for data evaluation, then AI processing capability is improved, but communication load on the backplane bus increases enormously and data sovereignty is compromised
Solution Approach 1:
The system segments the AI processing function from the central control system and places it in a decentralized peripheral module at the data source. This segmentation allows AI evaluation to occur locally without requiring continuous communication with the cloud or central system, thereby reducing communication load while maintaining AI processing capability.
Solution Approach 2:
The solution moves AI processing from the traditional cloud-based dimension to an edge computing dimension by integrating an AI microcontroller directly in the peripheral module. This dimensional shift enables local real-time processing while maintaining the benefits of centralized system architecture.
2Loss of information
If data is transferred from the source via the backplane bus to the cloud for evaluation, then AI evaluation capability is improved, but the load on the backplane bus becomes enormous
Solution Approach 1:
The invention extracts the AI evaluation function from the central data processing path and implements it locally in the peripheral module. Only the essential measurement data needs to be transferred via the backplane bus, while the computationally intensive AI evaluation occurs locally, thereby reducing communication overhead significantly.
Solution Approach 2:
The AI evaluation is performed preliminarily at the data source before data needs to be transmitted to higher-level systems. By conducting the evaluation locally first, the system prepares the data in advance, reducing the amount of data that needs to be communicated and simplifying the overall system architecture.
3Adaptability or versatility
If conventional automation devices like PLCs are used, then system compatibility is improved, but computing power for AI technology is insufficient
Solution Approach 1:
The invention merges conventional automation device compatibility with modern AI processing capabilities by integrating an AI microcontroller into the peripheral module. This combination allows the system to maintain compatibility with existing automation architectures while gaining the computing power necessary for AI technology.
Solution Approach 2:
The AI microcontroller acts as an intermediary between conventional automation devices and AI processing requirements. It bridges the gap by providing AI capabilities at the edge while maintaining compatibility with traditional automation protocols and architectures.
Data Source
Figure 1
Figure 2~3
Figure 4
AI summary
The invention relates to a module (1) configured for sequential data acquisition with integrated AI evaluation, comprising a measuring unit (2) configured to acquire measured values from a test object (40) via a sensor (6), an AI microcontroller (3) configured to receive and execute an AI algorithm, a data storage device (9), an operating system module (7), further configured for a modular design in an automation system to forward data to a higher-level unit via a backplane bus (RWB), wherein the measuring unit (2) is configured to receive a measurement instruction (V) with at least the following measurement parameters: a type (KM, SM, IM) of measurement, a number (K) of desired measurements, further configured to perform the number (K) of measurements consecutively according to the specified type of measurement (KM, SM, IM) and to record a series of measurements (Mi).wherein the AI microcontroller (3) is configured to cyclically retrieve a first measurement series (M1) from the measuring unit (2) and store it in an array (A), furthermore the AI microcontroller (3) is configured to apply the AI algorithm to the measured values of the first measurement series (M1) and to output the result via the backplane bus (RWB) using the operating system module (7), furthermore configured after evaluating the first measurement series (M1) to evaluate a further measurement series (M2,..,M10) from the array (A) with the AI algorithm.