Build a transparent, testable, human-in-the-loop Energy Management and Information System based on recognized EMIS practices.
This repository supports monthly utility analytics, interval energy analysis, data quality, benchmarking, demand, cost, carbon, findings, M&V, and optional future FDD and EnergyPlus integrations.
Audience: agents / engineers reviewing Plots validation cards and FDD DOCX.
One section per cookbook rule, grouped by mechanical family (same order as sidebar / Results). Each chart plots required (+ optional) roles present on the mapped frame, plus a confirmed-fault swim lane.
| Source | Path |
|---|---|
| Catalog | app/rules/cookbook_catalog.py |
| #!/usr/bin/env python3 | |
| """ | |
| Tiny Modbus TCP temperature sensor simulator for Open-FDD testing. | |
| Dependency-free: | |
| - Supports FC03 Read Holding Registers | |
| - Supports FC04 Read Input Registers | |
| - Supports FC06 Write Single Holding Register | |
| - Supports FC16 Write Multiple Holding Registers |
Goal: Build Open-FDD skills around Arrow-native HVAC fault detection, PyArrow, DataFusion SQL, Parquet, Rust migration, and future edge-to-central analytics.
Note: I did not find a widely recognized official Apache Arrow Foundation certification. The best path is a practical Arrow/DataFusion/data-engineering learning stack.
| Priority | Course / Resource | Cost Found | Certificate? | Why it matters for Open-FDD |
|---|---|---|---|---|
| 1 | Apache Arrow + PyArrow Official Docs | Free | No | Best source for PyArrow Arrays, Tables, Schemas, RecordBatches, Parquet, compute kernels, datasets, and Arrow memory concepts. |
| 2 | Apache Arrow and PyArrow for Data Scientists - Codefinity | Codefinity Pro listed at $49/mo, $99/3 mo, or $144/yr promo | Yes, shareable certificate | Most direct structured course I found fo |
| import operator | |
| import pandas as pd | |
| import numpy as np | |
| import pandas.api.types as pdtypes | |
| class HelperUtils: | |
| def float_int_check_err(self, col): | |
| err_str = " column failed with a check that the data is a float" | |
| return str(col) + err_str |
It is structured by equipment type, starting from the zone level and moving up to the central plant. Within each category, the rules are ordered by difficulty to implement: starting with the "low-hanging fruit" (simple boolean logic, schedules, and basic setpoint math) down to the more complex FDD rules (requiring thermodynamic models, enthalpy, or network-level data rollups).
These rules apply across multiple equipment types and rely on simple binary states, schedules, or BAS overrides, making them the easiest FDD rules to deploy.
A beginner-friendly experiment showing how a Graph Neural Network-style idea could be used for smart building / HVAC / BACnet fault detection.
This is not a production machine learning system. It is a simple teaching demo that uses made-up HVAC data, a small building graph, and probability-based fault scores to show the basic idea behind graph-based FDD.
Most HVAC fault detection starts with flat time-series data:
Generate cinematic, human-sounding AI dialogue for game cut scenes using Microsoft Neural Voices, completely scriptable from Python.
The script takes a dialogue script with two characters, generates separate voice lines, then merges them into a single cutscene_edge.wav ready for Unity, Unreal, Godot, etc.
⚠️ This uses Microsoft’s neural TTS over the internet via Edge-TTS. Text is sent to Microsoft’s service; audio comes back. No API key required.
Works great with:
| import pandas as pd | |
| import numpy as np | |
| import matplotlib.pyplot as plt | |
| import os | |
| # Load the CSV data into a DataFrame | |
| df = pd.read_csv("Merged_Weather_System_Data.csv") | |
| # Convert timestamp to datetime and set as index | |
| df['ts'] = pd.to_datetime(df['ts']) |
| import asyncio | |
| import BAC0 | |
| """ | |
| not tested yet | |
| """ | |
| async def main(): | |
| bacnet = BAC0.lite() |