Building Material Identification via Virtual BIM Model Inference
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing building control and management technologies require significant time and effort for manual verification of building materials, and it is challenging to assign experienced workers to multiple construction sites effectively.
Innovation Solution
An information processing apparatus that uses BIM data to create a virtual building model, sets a route, generates virtual images, and applies machine learning to identify building materials from measured data through a neural network, reducing the need for manual verification and optimizing worker allocation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual verification of building materials is performed, then accuracy of identification is improved, but time consumption and labor effort increase significantly
Solution Approach 1:
The patent creates a virtual building model that copies the physical building's structure and materials. This virtual model serves as a reference for automated comparison with captured images, enabling accurate material identification without manual verification. The virtual model contains pre-defined material information that can be directly compared against real-world observations.
Solution Approach 2:
The patent replaces the mechanical manual verification process with an automated image processing and machine learning system. The system uses captured images, virtual model data, and AI algorithms to automatically identify building materials, substituting human labor with computational processes that are both faster and equally accurate.
2Reliability
If experienced workers are assigned to multiple construction sites, then verification quality is maintained, but the number of sites they can cover is limited
Solution Approach 1:
The system creates a virtual replica of the building that encapsulates all material information and verification criteria. This virtual model can be accessed and processed automatically at multiple sites without requiring the physical presence of experienced workers, thereby maintaining verification quality while enabling coverage of numerous construction sites simultaneously.
Solution Approach 2:
The system enables self-service verification by automatically comparing captured images against the virtual building model using machine learning algorithms. The automated system performs verification tasks independently without human intervention, allowing unlimited site coverage while maintaining consistent verification quality across all locations.
3Productivity
If automated image processing is used to identify building materials, then processing speed increases, but accuracy may deteriorate without expert verification
Solution Approach 1:
The virtual building model serves as a precise reference copy that contains accurate material information. By comparing captured images against this detailed virtual model, the system achieves both high processing speed through automated image matching and high accuracy through the reliability of the virtual reference data.
Solution Approach 2:
The virtual building model is prepared in advance with complete and accurate material information before the verification process begins. This preliminary preparation of reference data enables the automated system to perform rapid and accurate comparisons without requiring real-time expert intervention, thus achieving both speed and accuracy.
Data Source
AI summary
The data set receiving unit 13 of the information processing apparatus 1 of an aspect example receives a data set that includes at least BIM data. The route setting processor 151 sets a route, which is arranged inside and/or outside a virtual building represented by the BIM data, based on the data set received. The virtual image set generating processor 152 generates a virtual image set of the virtual building along the route, based on the received data set and the set route. The inference model creating processor 153 creates an inference model by applying machine learning with training data that includes at least the generated virtual image set to a neural network. The inference model created is used to identify data of a building material from data acquired by measuring a building.