Manufacturing¶
In this section we cover data science use cases for the following sub-verticals of manufacturing:
Food Manufacturing¶
| Use Case | Sub-Group | Benefit | Dataset | Method | Paper |
|---|---|---|---|---|---|
| Prediction of Foam Evolution During Beverage Bottling | Chemical Process Prediction | During the bottling of beverages, foam can severely impair the process as overflowing foam causes underfilled bottles and poses a high contamination risk. Consequently, the filling speed is limited by the foaming properties of the beverage. This method can increase filling speed and manufacturing throughput. | Images, Video | Convolutional Neural Network, Recurrent Neural Network | Request Custom Report |
| Seafood tissue inspection | Visual Inspection | Increase Manufacturing Throughput | Images | Convolutional Neural Network | Request Custom Report |
| Evaluation of green tea sensory quality | Olafactory Analysis | Predict Desirability of Product | Sensor Data | xgBoost, Neural Network | Request Custom Report |
| Using computer vision for fruit selection | Visual Inspection | Increase Manufacturing Throughput | Images | Convolutional Neural Network | Request Custom Report |
| Cream Cheese Fermentation pH prediction | Food Attribute Prediction | Predict Quality of Product | Tabular Data | Gradient Boosting Trees | Request Custom Report |
| Predicting cow milk quality traits from milk spectra | Food Attribute Prediction | Predict Quality of Product | Image Data | Convolutional Neural Networks | Request Custom Report |
| Detecting claw lessions in dairy cows based on acoustic data | Detect defects in products | Increase yeild | Audio Data | Long-Short Term Neural Networks | Request Custom Report |
Chemical Manufacturing¶
| Use Case | Sub-Group | Benefit | Dataset | Method | Paper |
|---|---|---|---|---|---|
| Carrier surface design in carrier-based dry powder inhalation | Material Process Prediction | Effects of key surface roughness variables on DPI performance | SEM Images | Convolutional Neural Network, Neural Network | Request Custom Report |
| Forecasting industrial aging processes | Predictive Maintenance | Machine learning models can be used to accurately forecast industrial aging processes. Accurately predicting industrial aging processes makes it possible to schedule maintenance events further in advance, ensuring a cost-efficient and reliable operation of the plant. See our Predictive Maintenance Series for a live example |
Industrial Sensor Data | Long-Short Term Memory Network | Request Custom Report |
| Computational fluid dynamics-based in-situ sensor analytics of direct metal laser solidification process | Manufacturing Process Improvement | Better production of parts with ultra-high precision and variable geometries | Manufacturing Image Data | Convolutional Neural Network | Request Custom Report |
| Molecular design/screening methodology for fragrance molecules | Manufacturing Process Improvement | The odor of molecules are predicted using a data driven machine learning approach, improving the quality of the product and speed of new fragrance development. Predicted properties include: vapor pressure, solubility parameter and viscosity. | Fragrance chemical data | mixed-integer linear program (MILP) | Request Custom Report |
| Modeling and operation of plasma-enhanced atomic layer deposition of hafnium oxide thin films | Manufacturing Process Improvement | Model is demonstrated to accurately characterize the key aspects of the deposition process as well as the gas-phase transport profile while maintaining computational efficiency. | Sensor data from process | Recurrent Neural Network | Request Custom Report |