3D Welded Product Monitoring via Simulated Sensor Placement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing manufacturing monitoring systems struggle to accurately detect abnormalities in welded products due to reliance on design data, which often differs from actual product forms, leading to overlooked defects.
Innovation Solution
A manufacturing monitoring assistance device that creates a computation model based on the actual three-dimensional form of a normal product and generates a corrective model by simulating abnormalities, allowing for the determination of optimal sensor positions and methods to detect abnormalities through simulations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If design data is used to create computation models for simulation, then cost is reduced compared to using actual members, but the model accuracy deteriorates because on-site weld forms often differ from design data
Solution Approach 1:
The patent creates a computation model that copies the actual three-dimensional form of the welded product obtained through measurement, rather than using design data. This copying approach maintains high model accuracy while avoiding the need for costly trial and error with actual members, as the computational model can be repeatedly used for simulations.
Solution Approach 2:
The patent changes the input parameters for model creation from design data to actual measured three-dimensional form data. This parameter change ensures the computation model reflects the true geometry of the welded product, improving accuracy without requiring physical prototypes or trial assemblies.
2Measurement precision
If sensors are placed based on trial and error to detect abnormalities, then detection capability may be improved, but the time and cost for sensor placement optimization increases
Solution Approach 1:
The patent performs preliminary simulation calculations using the computation model to determine optimal sensor positions and monitoring methods before actual sensor deployment. By conducting virtual experiments with the computational model, the system identifies the most effective sensor placements for detecting specific abnormalities, eliminating the need for time-consuming trial and error with actual sensors on the production line.
Solution Approach 2:
The patent introduces a computation model as an intermediary between the welded product and the sensor placement decision-making process. This intermediary allows for virtual testing and optimization of sensor positions without requiring actual sensors to be physically trial-and-error placed on the product, saving time and resources.
3Reliability
If actual members are used for trial and error in sensor placement, then realistic testing is achieved, but cost and time consumption increase significantly
Solution Approach 1:
The patent creates a computational copy of the actual welded product that can be used for unlimited simulation and testing. This digital copy provides realistic testing conditions identical to actual members but without the associated costs and time consumption of physical trial and error with real components.
Solution Approach 2:
The patent replaces expensive, time-consuming physical trial members with a cheap, reusable computational model. The digital model can be used indefinitely for simulations without degradation or additional cost, whereas actual members would require repeated fabrication or availability for each testing iteration.
Data Source
AI summary
A manufacturing monitoring assistance device includes: a model creation unit creating a computation model when a product as a sample is normal, based on a three-dimensional form acquired from the product; a simulation unit creating a corrective computation model when the product is abnormal, by adding a sample of an abnormal portion in the product to the created computation model, and performing a simulation on each of the computation model and the corrective computation model; and a monitoring method determination unit determining a method for monitoring a manufacturing process for the product, based on an abnormality index being a difference between an output from a sensor as a result of the simulation performed on the computation model and an output from a sensor as a result of the simulation performed on the corrective computation model, and causing an output device to display the determined method and the abnormality index.