Research data
Refine
Document Type
- Research data (2) (remove)
Institute
Language
- English (2)
Has Fulltext
- yes (2)
Keywords
- FDD (1)
- machine learning (1)
- predictive maintenance (1)
FrostByte Dataset
(2021)
It is with great pleasure that we announce the release of the “Frost Byte” dataset. The dataset was collected during research on fault detection and diagnosis (FDD) approaches and their transferability to heterogeneous systems of industrial refrigeration systems at the Technical University of Applied Sciences Wildau. The data collection took place between 2018 and 2019 and is intended to supplement the ASHRAE 1043-RP dataset (Comstock & Braun, 1999), which has been the only publicly available data source in this area to date. For comparison purposes, the method of data collection was chosen similarly, whereby this dataset collection was carried out using a ~ 100 kW refrigeration capacity ammonia system with plate heat exchangers.
The dataset contains steady-state data equally sampled from five classes:
1. Normal (fault-free operating condition)
2. Reduced Condenser Water Flow
3. Reduced Evaporator Water Flow
4. Non-Condensable Gases
5. Refrigeration Leak
Each class was investigated under changing operational conditions and varying fault severity levels (SL).
This repository contains various short driving scenarios of our vehicle fleet in 1:14 scale. These are part of our digital learning factory "Wildauer Maschinen Werke" (www.th-wildau.de/wmw) and are used for the development of autonomous driving functions. The data is recorded in the form of Rosbags in the underlying robotic operating system (www.ros.org) and can be played in their own ROS server instances, whereby the recorded journeys of the vehicles can be simulated and used for their own developments. The scenarios contain short driving scenarios with so-called ROS topics. This includes engine and steering control and frontal distance measurements of an ultrasonic sensor. Videos are also provided for each scenario for a better overview.
It is the 1st generation. Towards the end of 2020, data sets will follow that additionally contain camera data, GPS coordinates and speed as well as laser scanner data.