A company has a fleet of devices transmitting daily sensor readings. They would like to create a predictive maintenance solution to proactively identify when maintenance should be performed. This approach promises cost savings over routine or time based preventive maintenance, because tasks are performed only when warranted.

The task is to build a predictive model using machine learning to predict the probability of a device failure. When building this model, be sure to minimize false positives and false negatives. The column you are trying to Predict is called failure with binary value 0 for non-failure and 1 for failure.

Source:

Da Silva, D. G.; Geller M. T. B., Moura M. S. S., Meneses, A. A. M., 2022. Performance Evaluation of LSTM Neural Networks for Consumption Prediction. E-Prime - Advances in Electrical Engineering, Electronics and Energy, 2, 100030. https://doi.org/10.1016/j.prime.2022.100030.

Data Set Information:

The LABIC-Building data set is related to a building of the Federal University of Western Pará (Universidade Federal do Oeste do Pará, UFOPA - Coordinated by Professor DSc Anderson Alvarenga De Moura Meneses) with high power demand of AC systems, which is a characteristic of the Amazon region.

Data were obtained is Santarém city, Pará State, Brazil (Da Silva et al., 2021, 2022).

The time series contains 256.092 points of aggregated active power in Watts (W). After downsampling the data in 10 minutes intervals, the data set remained with 33.830 points.

Attribute Information: Date: Date YYYY/MM/DD and Time: HH:MM:SS Active Power: active power in Watts (W)

Citation Request: If you use this dataset in your research, please cite the following paper: Da Silva, D. G.; Geller M. T. B., Moura M. S. S., Meneses, A. A. M., 2022. Performance Evaluation of LSTM Neural Networks for Consumption Prediction. E-Prime - Advances in Electrical Engineering, Electronics and Energy, 2, 100030. https://doi.org/10.1016/j.prime.2022.100030.

Relevant Papers: Da Silva, D. G.; Geller M. T. B., Moura M. S. S., Meneses, A. A. M., 2022. Performance Evaluation of LSTM Neural Networks for Consumption Prediction. E-Prime - Advances in Electrical Engineering, Electronics and Energy, 2, 100030. https://doi.org/10.1016/j.prime.2022.100030.

Da Silva, D. G.; Geller M. T. B., Moura M. S. S., Meneses, A. A. M., 2021. A Deep Learning Prediction Module for the IoT system EnergySaver for Monitoring and Estimating Power Consumption. In 16th Conference on Sustainable Development of Energy, Water and Environment Systems (SDEWES), Dubrovnik, Croácia.

DA SILVA, D. G.; TEIXEIRA, Y. B.; VARÃO, D. F. S.; SANTOS, C. A. M.; MOURA, M. S. S.; GELLER, M. T. B.; BENTES, J; MENESES, A. A. M. EnergySaver Software Manual. arXiv preprint arXiv:2107.06664, 2021. Disponível em: