Power Supply Dimensioning Using AI Datasheet Extraction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The manual process of dimensioning electrical power supply systems for industrial automation is time-consuming, prone to human error, and requires high expertise, making it inefficient and non-compliant with industry standards.

Innovation Solution

A computer-implemented data preparation process using machine learning algorithms to automate the extraction of dimensioning-relevant data from component datasheets, select appropriate component models, and simulate the power supply system to ensure compliance with industry standards.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual data extraction and review is performed by electrical engineers, then expertise-based accuracy is maintained, but time consumption and human error increase

Engineering Contradiction:

Improvedimensioning accuracyVSAvoiddata preparation time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces the manual mechanical process of data extraction and review with an automated computer-based system that uses optical character recognition (OCR) and image processing techniques to extract dimensioning data from component datasheets, thereby reducing time consumption while maintaining accuracy through systematic automated processing

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service by automatically extracting dimensioning-relevant data from component datasheets without requiring manual intervention from electrical engineers, allowing the system to perform data collection, extraction, and preliminary analysis autonomously

Inventive Principle:

Principle #25Self-service

2Adaptability or versatility

If manual data extraction is performed, then flexibility in handling various datasheet formats is maintained, but human error and inconsistency increase

Engineering Contradiction:

Improvedatasheet format handlingVSAvoiddata extraction consistency

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The patent replaces manual data extraction with automated image processing and OCR techniques that consistently interpret various datasheet formats according to predefined rules, eliminating human error and inconsistency while maintaining the ability to handle diverse formats through systematic pattern recognition

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system changes the approach from manual interpretation to automated parameter-based extraction, where dimensioning data is identified and extracted based on specific parameters and patterns defined in the system, ensuring consistent and reliable extraction across different datasheet formats

Inventive Principle:

Principle #35Parameter changes

3Loss of information

If comprehensive component data is manually reviewed, then complete dimensioning information is obtained, but the complexity and expertise requirement increase

Engineering Contradiction:

Improvedimensioning data completenessVSAvoidprocess complexity

Core Design Contradiction:

Loss of informationVSDevice complexity

Solution Approach 1:

The patent extracts only the dimensioning-relevant data from complete component datasheets using automated rules and patterns, separating essential dimensioning information from other component details, thereby obtaining complete dimensioning information while simplifying the overall process by eliminating manual review complexity

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The system segments the data extraction process into distinct automated steps including OCR processing, pattern recognition, data validation, and model selection, breaking down the complex manual review process into manageable automated segments that reduce expertise requirements while maintaining data completeness

Inventive Principle:

Principle #1Segmentation

4Productivity

If automated data extraction is implemented, then time consumption and human error are reduced, but the need for AI algorithms and data processing infrastructure increases

Engineering Contradiction:

Improvedimensioning process efficiencyVSAvoidsystem infrastructure requirement

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent implements automated data extraction using OCR and image processing algorithms that enhance productivity by eliminating manual data entry and review, while the system infrastructure complexity is managed through integrated software modules that combine multiple functions into a unified automated dimensioning system

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentEP4687058A1Electric system dimensioning

Publication Date: 2026.02.04 ABB (SCHWEIZ) AG

Figure 1
Figure 2
Figure 3

AI summary

A computer-implemented data preparation process for dimensioning an electrical power supply system for an industrial automation system is provided. The process comprises: obtaining a component datasheet for at least one component of the industrial automation system; using a machine learning algorithm to extract dimensioning-relevant data from the obtained component datasheet; and selecting an appropriate component model for the component based on the extracted dimensioning-relevant data.