View: |
Part 1: Document Description
|
Citation |
|
---|---|
Title: |
Data for Fault Diagnosis in Adaptive Buildings |
Identification Number: |
doi:10.18419/darus-3332 |
Distributor: |
DaRUS |
Date of Distribution: |
2023-02-07 |
Version: |
1 |
Bibliographic Citation: |
Stiefelmaier, Jonas, 2023, "Data for Fault Diagnosis in Adaptive Buildings", https://doi.org/10.18419/DARUS-3332, DaRUS, V1 |
Citation |
|
Title: |
Data for Fault Diagnosis in Adaptive Buildings |
Identification Number: |
doi:10.18419/darus-3332 |
Authoring Entity: |
Stiefelmaier, Jonas (Universität Stuttgart) |
Grant Number: |
279064222 - SFB 1244 |
Distributor: |
DaRUS |
Access Authority: |
Stiefelmaier, Jonas |
Depositor: |
Stiefelmaier, Jonas |
Date of Deposit: |
2023-01-24 |
Holdings Information: |
https://doi.org/10.18419/DARUS-3332 |
Study Scope |
|
Keywords: |
Computer and Information Science, Engineering, Fault detection and isolation |
Abstract: |
<p> <b>General information:</b><br> This dataset is meant to serve as a benchmark problem for fault detection and isolation in dynamical systems. It contains pre-processed sensor data from the adaptive high-rise demonstrator building D1244, built in the scope of the <a href="https://www.sfb1244.uni-stuttgart.de/en/">CRC1244</a>. Parts of the measurements have been artificially corrupted and labeled accordingly. Please note that although the measurements are stored in Matlab's .mat-format (Version 7.0), they can easily be processed using free software such as the SciPy library in Python. </p> <p> <b>Structure of the dataset:</b><br> <ul> <li><b>train</b> contains the training data (only nominal)</li> <li><b>test_easy</b> contains test data (nominal and faulty with high fault amplitude). Faulty samples were obtained by manipulating a single signal in a random nominal sample from the test data.</li> <li><b>test_hard</b> contains test data (nominal and faulty with low fault amplitude)</li> <li><b>meta</b> contains textual labels for all signals and fault types</li> </ul> </p> <p> <b>File contents:</b><br> Each file contains the following data from 16384 timesteps: <ul> <li><b>t:</b> time in seconds</li> <li><b>u:</b> demanded actuator forces in newtons</li> <li><b>y:</b> measured outputs (relative elongations measured by strain gauges and actuator displacements in meters measured by position encoders)</li> <li><b>label:</b> categorical label of the present fault class, where 0 denotes the nominal class and faults in the different signals are encoded according to their index in the list of fault types <code>meta/labels.txt</code></li> </ul> Faulty samples additionally include the corresponding nominal values for reference <ul> <li><b>u_true:</b> delivered actuator forces</li> <li><b>y_true:</b> measured outputs without faults</li> </ul> A sample's textual fault label is also contained in its filename (between the first and second underscore). </p> |
Methodology and Processing |
|
Sources Statement |
|
Data Access |
|
Other Study Description Materials |
|
Label: |
adaptive_building_diagnosis_data.zip |
Notes: |
application/zip |