Automated Optical Surface Roughness Measurement With Machine Learning

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing quality control procedures in manufacturing are labor-intensive, costly, and subject to human judgment, making them time-consuming and inconsistent.

Innovation Solution

A surface roughness measurement system utilizing an imaging system, coherent light source, light sensor, and processor with trained machine learning models to automate the measurement of surface roughness, depth, and material identification, enabling accurate and reliable quality control.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional quality control procedures are used, then human judgment and experience can identify defects, but the process becomes labor-intensive, time-consuming, and subject to human error

Engineering Contradiction:
Improvequality control accuracyVSAvoidinspection time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent replaces manual visual inspection and mechanical roughness gauges with an automated optical imaging system. The system uses a camera to capture surface images, processes them through machine learning models for depth perception and roughness analysis, eliminating the need for human technicians to perform manual measurements and visual inspections.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service quality control by using machine learning models that automatically analyze surface images and determine roughness values without human intervention. The trained models independently perform depth perception, material identification, and roughness measurement, making the system autonomous and eliminating dependency on human operators.

Inventive Principle:
Principle #25Self-service

2Adaptability or versatility

If multiple technicians perform quality control, then diverse expertise can be utilized, but consistency and uniformity of quality standards become difficult to maintain

Engineering Contradiction:
Improvequality control expertiseVSAvoidquality control consistency
Core Design Contradiction:
Adaptability or versatilityVSStability of the object's composition

Solution Approach 1:

The patent applies homogeneity by using a standardized machine learning-based measurement system that treats all surfaces uniformly. The same algorithms and criteria are applied consistently to every measurement, eliminating variations in judgment between different technicians and ensuring uniform quality standards across all inspections.

Inventive Principle:
Principle #33Homogeneity

3Measurement precision

If traditional roughness gauges are used, then direct surface roughness measurement is achieved, but the process requires significant training and experience to operate accurately

Engineering Contradiction:
Improvesurface roughness measurement accuracyVSAvoidoperator training requirements
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces complex mechanical roughness gauges that require skilled operation with an automated optical system. The complexity of operation is transferred to the machine learning models, which automatically perform the analysis without requiring human expertise in interpretation or technique.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

4Productivity

If automated systems are implemented, then productivity and consistency are improved, but the system complexity and initial cost increase

Engineering Contradiction:
Improvequality control throughputVSAvoidsystem complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent achieves multi-functionality by using a single imaging system that performs multiple tasks: capturing surface images, generating depth maps through machine learning, identifying materials, and measuring roughness. This consolidates what would traditionally require multiple separate devices and processes into one unified system, reducing overall complexity while maintaining high productivity.

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

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

The system allows for automated, accurate, and reliable surface roughness measurement, reducing human error and ensuring uniform quality control processes across various materials.

Implementation Method 1

illuminate, with the coherent light source, an area of interest of the target surface to create a speckle light pattern on the area of interest

Methodology Applied
Scientific EffectSpeckle pattern:

Implementation Method 2

detect light from the coherent light source that is reflected by the target surface

Methodology Applied
Scientific EffectLight reflection: Reflection

Data Source

PatentEP4278148B1A surface roughness measurement system
Publication Date: 2025.08.27 EATON INTELLIGENT POWER LTD
  • EP4278148B1 patent drawingFigure 1
  • EP4278148B1 patent drawingFigure 2
  • EP4278148B1 patent drawingFigure 3

AI summary

It is known for a product to be mass produced by way of a manufacturing process. Typically, a quality control step is used in a manufacturing process to monitor the quality of manufactured products. However, quality control procedures in manufacturing are typically labour intensive. A technician or other person must inspect the product and carry out any necessary tests. The present disclosure provides a surface roughness measurement system and method for determining a surface roughness of a product with an imaging system, a coherent light source, a light sensor and several trained machine learning algorithms.