This model predicts the energy consumption of plastic bottle manufacturing. Inputs are product type and production plan; output is energy required. Predicting the consumption of energy is important for energy management and system control. This model also accounts for dynamic and seasonal changes. (SK can also offer similar models which can be tailored to bespoke data sets.)
See the model in action with a Modzy MLOps platform demo or start a trial
93.7% Average Accuracy – Model provides accuracy of power usage according to production performance.
This model was trained using the power consumption data for 1 hour at each of the 3 plastic bottle manufacturing factories. After that, several models with the minimum error rate were selected.
Model performance represents a minimum error of 4.7% to a maximum error of 7.6% compared to past production performance, with an average error of 6.3%.
This model predicts the energy consumption of plastic bottle manufacturing. Predicting the consumption of energy is important for energy management and system control and can be leveraged to predict bottle demand. Ultimately, this maximizes energy storage system (ESS) utilization and helps anticipate demand response (DR).
The model was trained on a dataset created based on plastic bottle production and product specifications. The input data set consists of hourly units of 18 months, production lines/products, and product specifications. It learns by reorganizing the input data set into production volumes by product group based on product specifications. The LightGBM model was trained on roughly 80% of the full dataset.
The model was tested on a 20% subset of the full dataset and achieves 93.7% accuracy.
See how quickly you can deploy and run models, connect to pipelines, autoscale resources, and integrate into workflows with Modzy MLOps platform
d o n o t fill t h i s . f i e l d d o n o t fill t h i s . f i e l d
