Summary: Analyzing Energy Consumption and Environmental Impact in the Steel Industry.
| Parameter | Value |
|---|---|
| Name | Steel Industry datasets |
| Labeled | Yes |
| Time Series | Yes |
| Simulation | No |
| Missing Values | No |
| Dataset Characteristics | Multivariate, Time-Series |
| Feature Type | Real |
| Associated Tasks | Regression, Classification |
| Number of Instances | INA |
| Number of Features | INA |
| Date Donated | INA |
| Source | Kaggle |
Date_Time: Timestamp indicating when the energy consumption data was recorded.
Usage_kWh: Energy usage in kilowatt-hours (kWh), representing the amount of electricity consumed during a specific period, likely related to steel production processes or facility operations.
Lagging_Current_Reactive.Power_kVarh: Reactive power consumption in kilovolt-amperes reactive hour (kVarh). Reactive power is essential in steel industry equipment for tasks such as magnetization and induction heating.
Leading_Current_Reactive_Power_kVarh: Similar to lagging current reactive power but likely refers to leading reactive power consumption, which can occur in capacitive loads.
CO2(tCO2): Carbon dioxide emissions in metric tons of CO2. This could indicate the environmental impact of energy consumption in steel production, as CO2 emissions are a concern in terms of greenhouse gas emissions and climate change.
Lagging_Current_Power_Factor: Power factor measures the efficiency of electrical power usage. A lagging power factor indicates inefficient use of electricity, which could signify inefficiencies in certain steel production processes or equipment.
Leading_Current_Power_Factor: Similar to lagging power factor but likely refers to leading power factor, which indicates more efficient use of electricity.
NSM (Normalized Solar Energy): This could be a derived feature representing solar energy normalized against some baseline. It might indicate the integration of renewable energy sources like solar power into the steel production process or facility operations.
WeekStatus: Indicates whether the data corresponds to a weekday or a weekend. This could be useful for analyzing energy consumption patterns based on the day of the week.
Day_Of_Week: Indicates the day of the week when the data was recorded, providing further granularity for analyzing energy consumption patterns over weekdays.
Steel production, Energy consumption, Manufacturing process, Industrial data, Operational efficiency