bim-classification-ai
Classify BIM elements using AI and standard classification systems. Map elements to UniFormat, MasterFormat, OmniClass, and CWICR codes.
git clone --depth 1 https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction /tmp/bim-classification-ai && cp -r /tmp/bim-classification-ai/1_DDC_Toolkit/BIM-Analysis/bim-classification-ai ~/.claude/skills/bim-classification-aiSKILL.md
# BIM Classification AI
## Business Case
### Problem Statement
BIM models often lack proper classification:
- Elements without classification codes
- Inconsistent naming conventions
- Manual classification is tedious
- Difficult to map to cost databases
### Solution
AI-powered classification system that analyzes BIM element properties and suggests appropriate classification codes from multiple standards.
### Business Value
- **Automation** - Reduce manual classification effort
- **Consistency** - Standardized classification across projects
- **Integration** - Enable cost estimation and QTO
- **Quality** - Improved data quality in BIM models
## Technical Implementation
```python
import pandas as pd
from typing import Dict, Any, List, Optional, Tuple
from dataclasses import dataclass, field
from enum import Enum
import re
class ClassificationSystem(Enum):
"""Classification standards."""
UNIFORMAT = "uniformat"
MASTERFORMAT = "masterformat"
OMNICLASS = "omniclass"
UNICLASS = "uniclass"
CWICR = "cwicr"
@dataclass
class ClassificationCode:
"""Classification code with metadata."""
code: str
title: str
system: ClassificationSystem
level: int
parent_code: Optional[str] = None
keywords: List[str] = field(default_factory=list)
@dataclass
class ClassificationResult:
"""Result of classification attempt."""
element_id: str
element_name: str
element_category: str
suggested_codes: List[Tuple[ClassificationCode, float]] # (code, confidence)
selected_code: Optional[ClassificationCode] = None
manual_override: bool = False
class ClassificationDatabase:
"""Classification codes database."""
def __init__(self):
self.codes: Dict[ClassificationSystem, List[ClassificationCode]] = {
system: [] for system in ClassificationSystem
}
self._load_standard_codes()
def _load_standard_codes(self):
"""Load standard classification codes."""
# UniFormat II codes
uniformat_codes = [
("A", "Substructure", 1, None, ["foundation", "basement", "excavation"]),
("A10", "Foundations", 2, "A", ["footing", "pile", "foundation"]),
("A1010", "Standard Foundations", 3, "A10", ["spread footing", "strip footing"]),
("A1020", "Special Foundations", 3, "A10", ["pile", "caisson", "mat foundation"]),
("B", "Shell", 1, None, ["superstructure", "exterior", "roof"]),
("B10", "Superstructure", 2, "B", ["floor", "roof", "structure"]),
("B1010", "Floor Construction", 3, "B10", ["slab", "deck", "floor"]),
("B1020", "Roof Construction", 3, "B10", ["roof", "deck", "truss"]),
("B20", "Exterior Enclosure", 2, "B", ["wall", "window", "door"]),
("B2010", "Exterior Walls", 3, "B20", ["curtain wall", "masonry", "cladding"]),
("B2020", "Exterior Windows", 3, "B20", ["window", "glazing", "storefront"]),
("B30", "Roofing", 2, "B", ["roof", "membrane", "insulation"]),
("C", "Interiors", 1, None, ["partition", "ceiling", "floor finish"]),
("C10", "Interior Construction", 2, "C", ["partition", "door", "glazing"]),
("C20", "Stairs", 2, "C", ["stair", "railing", "ladder"]),
("C30", "Interior Finishes", 2, "C", ["finish", "paint", "flooring"]),
("D", "Services", 1, None, ["mechanical", "electrical", "plumbing"]),
("D10", "Conveying", 2, "D", ["elevator", "escalator", "lift"]),
("D20", "Plumbing", 2, "D", ["pipe", "fixture", "drain"]),
("D30", "HVAC", 2, "D", ["duct", "hvac", "air handling"]),
("D40", "Fire Protection", 2, "D", ["sprinkler", "fire", "suppression"]),
("D50", "Electrical", 2, "D", ["electrical", "power", "lighting"]),
]
for code, title, level, parent, keywords in uniformat_codes:
self.codes[ClassificationSystem.UNIFORMAT].append(
ClassificationCode(code, title, ClassificationSystem.UNIFORMAT, level, parent, keywords)
)
# MasterFormat codes (simplified)
masterformat_codes = [
("03", "Concrete", 1, None, ["concrete", "formwork", "reinforcing"]),
("03 30 00", "Cast-in-Place Concrete", 2, "03", ["concrete", "pour", "slab"]),
("03 41 00", "Precast Structural Concrete", 2, "03", ["precast", "concrete", "panel"]),
("04", "Masonry", 1, None, ["brick", "block", "stone"]),
("05", "Metals", 1, None, ["steel", "metal", "aluminum"]),
("05 12 00", "Structural Steel Framing", 2, "05", ["beam", "column", "steel"]),
("06", "Wood, Plastics, Composites", 1, None, ["wood", "timber", "lumber"]),
("07", "Thermal and Moisture Protection", 1, None, ["insulation", "roofing", "waterproofing"]),
("08", "Openings", 1, None, ["door", "window", "glazing"]),
("09", "Finishes", 1, None, ["drywall", "paint", "flooring"]),
("21", "Fire Suppression", 1, None, ["sprinkler", "fire", "suppression"]),
("22", "Plumbing", 1, None, ["pipe", "fixture", "plumbing"]),
("23", "HVAC", 1, None, ["hvac", "duct", "mechanical"]),
("26", "Electrical", 1, None, ["electrical", "power", "lighting"]),
]
for code, title, level, parent, keywords in masterformat_codes:
self.codes[ClassificationSystem.MASTERFORMAT].append(
ClassificationCode(code, title, ClassificationSystem.MASTERFORMAT, level, parent, keywords)
)
def search(self, query: str, system: ClassificationSystem = None) -> List[ClassificationCode]:
"""Search classification codes by keyword."""
results = []
query_lower = query.lower()
systems = [system] if system else list(ClassificationSystem)
for sys in systems:
for code in self.codes.get(sys, []):
# Check titGenerate automated daily progress reports from site data. Track work completed, labor hours, equipment usage, and weather conditions.
Analyze labor productivity from site data. Compare planned vs actual, identify trends, benchmark against industry standards.
Create interactive KPI dashboards for construction projects. Track schedule, cost, quality, and safety metrics in real-time.
Detect and analyze geometric clashes in BIM models. Identify MEP, structural, and architectural conflicts before construction.
Generate comprehensive BIM model validation reports. Check data quality, completeness, and compliance with standards.
Calculate CO2 emissions and carbon footprint from BIM model data. Analyze embodied carbon by material, element, and building system.
Extract quantities from IFC/Revit models for quantity takeoff. Uses DDC converters to get element counts, areas, volumes, lengths with grouping and reporting.
Analyze field progress photos. Catalog, tag, and compare against planned progress.