IIoT Sampling Parameters for Targeted Multi-Part Quality Inspection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing production and assembly processes face challenges in efficiently performing targeted quality inspections on diverse parts and components due to varying quality inspection standards, necessitating differentiated sampling strategies.
Innovation Solution
A system and method utilizing Industrial Internet of Things (IIoT) platforms for intelligent sampling and quality inspection, including an IIoT management platform, sensing network, perception and control platform, and quality inspection equipment, to dynamically adjust sampling conditions and parameters based on model, production, and equipment data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional quality inspection methods are used for diverse parts and components, then comprehensive coverage of all parts can be achieved, but inspection efficiency and productivity decrease due to lack of targeted sampling
Solution Approach 1:
The patent dynamically changes sampling parameters (sampling rate, sampling quantity, inspection project) based on risk assessment results. Different parts and components have different sampling parameters determined by their quality risk levels, production status, and equipment state, achieving targeted inspection that improves efficiency while maintaining adequate coverage
Solution Approach 2:
The sampling strategy transitions from static to dynamic through real-time adjustment. The system continuously monitors production data and equipment data, then dynamically adjusts sampling parameters according to changing conditions, allowing the inspection system to adapt to different scenarios and maintain optimal efficiency
2Measurement precision
If increased sampling is performed to ensure quality coverage of all components, then inspection accuracy improves, but manpower consumption and costs increase
Solution Approach 1:
The patent applies differentiated sampling strategies to different parts based on their specific characteristics and risk levels. Critical components with high quality risk receive intensive inspection with higher sampling rates, while non-critical components receive reduced sampling, achieving accurate inspection where needed while reducing overall manpower and cost consumption
Solution Approach 2:
The system uses feedback from quality inspection results, production data, and equipment data to continuously optimize sampling parameters. By analyzing historical quality data and real-time production status, the system adjusts sampling intensity to maintain inspection accuracy while minimizing resource consumption through evidence-based decision making
3Ease of operation
If fixed sampling standards are applied to all parts, then ease of operation is maintained, but adaptability to different part requirements and quality standards decreases
Solution Approach 1:
The system automatically determines appropriate sampling parameters for different parts through integrated data analysis. By self-service functionality that combines production data, equipment data, and quality standards, the system adapts to different part requirements without requiring manual configuration, maintaining ease of operation while achieving high adaptability to diverse sampling needs
Data Source
AI summary
Method for sampling product quality based on Industrial Internet of Things, including: obtaining model data, production data, and equipment data, determining a first preset condition, a first sampling parameter, a second preset condition, and a second sampling parameter; obtaining production feature data, and in response to the production feature data satisfying first preset condition, generating a first sampling inspection instruction based on the first sampling parameter and obtaining a first quality inspection result; obtaining historical sampling inspection results and historical model data, and in response to the historical sampling inspection results and/or the historical model data satisfying second preset condition, generating a second sampling inspection instruction based on the second sampling parameter and obtaining a second quality inspection result; adjusting the first preset condition, the first sampling parameter, the second preset condition, and the second sampling parameter based on the first quality inspection result and the second quality inspection result.