Data
Methane

Methane

active ARFF Public Domain (CC0) Visibility: public Uploaded 02-10-2020 by Michal Kozielski
0 likes downloaded by 0 people , 0 total downloads 0 issues 0 downvotes
Issue #Downvotes for this reason By


Loading wiki
Help us complete this description Edit
Author: Marek Sikora, Lukasz Wrobel Source: coal mine in Poland - March 2, 2014 - June 16, 2014 Please cite: Slezak, D., Grzegorowski, M., Janusz, A., Kozielski, M., Nguyen, S. H., Sikora, M., Stawicki, S. & Wrobel, L. (2018). A framework for learning and embedding multi-sensor forecasting models into a decision support system: A case study of methane concentration in coal mines. Information Sciences, 451, 112-133. Coal mining requires working in hazardous conditions. Miners in an underground coal mine can face several threats, such as, e.g. methane explosions or rock-burst. To provide protection for people working underground, systems for active monitoring of a production processes are typically used. One of their fundamental applications is screening dangerous gas concentrations (methane in particular) in order to prevent spontaneous explosions. Therefore, for that purpose the ability to predict dangerous concentrations of gases in the nearest future can be even more important than monitoring the current sensor readings. The data set contains raw data collected at an underground coal mine. It consists of a data stamp and measurements collected each second. The considered task related to this data set is to construct a model capable of predicting dangerous concentrations of methane at longwalls of a coal mine in a chosen time horizon, Therefore, in case of classification task the model has to predict weather the methane concentration for three methane meters: MM263, MM264 and MM256 exceeds the chosen threshold (e.g. 1.0) within the chosen period of time (e.g. three to six minutes). In case of regression task it is required to predict the value of methane concentration for the selected methane meters. ### Attribute Information: AN311 - anemometer (distant) [m/s] * sensor type: anemometer -5-5 * kind: alarming AN422 - anemometer [m/s] * sensor type: anemometer -5-5 * kind: switching off AN423 - anemometer [m/s] * sensor type: anemometer -5-5 * kind: switching off TP1721 - temperature [C] * sensor type: temperature THP (three-component sensor THP2/93) * kind: registering RH1722 - humidity [%RH] * sensor type: humidity THP (three-component sensor THP2/93) * kind: registering BA1723 - barometer [hPa] * sensor type: barometer THP (three-component sensor THP2/93) * kind: registering TP1711 - temperature [C] * sensor type: temperature THP (three-component sensor THP2/94) * kind: registering RH1712 - humidity [%RH] * sensor type: humidity THP (three-component sensor THP2/94) * kind: registering BA1713 - barometer [hPa] * sensor type: barometer THP (three-component sensor THP2/94) * kind: registering MM252 – methane meter (distant) [%CH4] * sensor type: methane meter MM-2PWk * kind: switching off * value of threshold A (alarm): 2.0% * value of threshold W (warning): 1.5% MM261 – methane meter [%CH4] * sensor type: methane meter MM-2PWk * kind: switching off * value of threshold A: 1.5% * value of threshold W: 1.0% MM262 - methane meter [%CH4] * sensor type: methane meter MM-2PWk * kind: switching off * value of threshold A: 1.0% * value of threshold W: 0.6% MM263 - methane meter [%CH4] - !target sensor! * sensor type: methane meter MM-2PWk * kind: switching off * value of threshold A: 1.5% * value of threshold W: 1.0% MM264 - methane meter [%CH4] - !target sensor! * sensor type: methane meter MM-2PWk * kind: switching off * value of threshold A: 1.5% * value of threshold W: 1.0% MM256 - methane meter [%CH4] - !target sensor! * sensor type: methane meter MM-2PWk * kind: switching off * value of threshold A: 1.5% * value of threshold W: 1.0% MM211 - methane meter [%CH4] * sensor type: methane meter MM-2PWk * kind: switching off * value of threshold A: 2.0% * value of threshold W: 1.5% CM861 – high concentration methane meter [%CH4] * sensor type: methane meter (0…100) * kind: registering CR863 – sensor for pressure difference on the methane drainage flange [Pa] * sensor type: pressure difference (0..250) * kind: registering CR863 - sensor for pressure difference on the methane drainage flange [Pa] * sensor type: pressure difference (0..250) * kind: registering P_864 – pressure inside the methane drainage pipeline [kPa] * sensor type: pressure (0..110) * kind: registering TC862 – temperature inside the pipeline [C] * sensor type: temperature (10..40) * kind: registering WM868 – methane delivery calculated according to CM, CR, P, TC [m3/mi] * sensor type: methane delivery (0..50) * kind: registering AMP1_IR - current of the left cutting head of the cutter loader [A] AMP2_IR - current of the right cutting head of the cutter loader [A] DMP3_IR - current of the left haulage in the cutter loader [A] DMP4_IR - current of the right haulage in the cutter loader [A] AMP5_IR – current of the hydraulic pump engine in the cutter loader [A] F_SIDE - driving direction, 1=left, {0, 0.5}=right V - cutter loader speed [Hz] (Vmin=3Hz, Vmax=100Hz. Herz values are then transformed into m/min - 100Hz equal to about 20 m/min)

34 features

MM263 (target)numeric41 unique values
0 missing
MM264 (target)numeric50 unique values
0 missing
MM256 (target)numeric38 unique values
0 missing
yearnumeric1 unique values
0 missing
monthnumeric4 unique values
0 missing
daynumeric31 unique values
0 missing
hournumeric24 unique values
0 missing
minutenumeric60 unique values
0 missing
secondnumeric60 unique values
0 missing
AN311numeric55 unique values
0 missing
AN422numeric25 unique values
0 missing
AN423numeric78 unique values
0 missing
TP1721numeric43 unique values
0 missing
RH1722numeric35 unique values
0 missing
BA1723numeric420 unique values
0 missing
TP1711numeric42 unique values
0 missing
RH1712numeric37 unique values
0 missing
BA1713numeric417 unique values
0 missing
MM252numeric38 unique values
0 missing
MM261numeric57 unique values
0 missing
MM262numeric50 unique values
0 missing
MM211numeric38 unique values
0 missing
CM861numeric622 unique values
0 missing
CR863numeric259 unique values
0 missing
P_864numeric212 unique values
0 missing
TC862numeric66 unique values
0 missing
WM868numeric597 unique values
0 missing
AMP1_IRnumeric1018 unique values
0 missing
AMP2_IRnumeric1060 unique values
0 missing
DMP3_IRnumeric262 unique values
0 missing
DMP4_IRnumeric270 unique values
0 missing
AMP5_IRnumeric142 unique values
0 missing
F_SIDEnominal3 unique values
0 missing
Vnumeric1061 unique values
0 missing

19 properties

9199930
Number of instances (rows) of the dataset.
34
Number of attributes (columns) of the dataset.
Number of distinct values of the target attribute (if it is nominal).
0
Number of missing values in the dataset.
0
Number of instances with at least one value missing.
33
Number of numeric attributes.
1
Number of nominal attributes.
0
Number of attributes divided by the number of instances.
97.06
Percentage of numeric attributes.
Percentage of instances belonging to the most frequent class.
2.94
Percentage of nominal attributes.
Number of instances belonging to the most frequent class.
Percentage of instances belonging to the least frequent class.
Number of instances belonging to the least frequent class.
0
Number of binary attributes.
0
Percentage of binary attributes.
0
Percentage of instances having missing values.
Average class difference between consecutive instances.
0
Percentage of missing values.

2 tasks

0 runs - estimation_procedure: 50 times Clustering
0 runs - estimation_procedure: 50 times Clustering
Define a new task