Figure 4: Actual components currently produced by 3D printing – this being modified and better images will be available by midweek.


Operation Explained - Vapor Input Port: Draws vapor from the top of the vessel via a small-diameter hose


- Internal Sensor Array: Captures vapor signatures (NH3


, VOCs, organics) using high-sensitivity gas sensors


- Integrated Microcontroller: Digitises signals and communicates with the AI engine


- AI Feedback Loop: Matches live vapor patterns to expert-defined cooking profiles


- Microwave Power Output Signal: Sends dynamic control signals to the microwave generator to adjust heating in real-time


AI interpretation of sensor signal Support Vector Machine (SVM) Algorithm is a supervised machine learning algorithm used for classification and regression.


It works by finding the best separating boundary (hyperplane) between data points of different classes. • The algorithm looks for the hyperplane that maximises the margin — the distance between the boundary and the closest data points (called support vectors).


• Because of this, SVM is more effective when classes are well-separated.


• With the help of the kernel trick, SVM can also classify data that is not linearly separable by mapping it into a higher-dimensional space.


Using SVM vapor pattern matching Used for classifying live vapor patterns captured by the sensor array and compare them to expert-defined cooking profiles. The AI programming board: 1. Extract features from the vapor signals (O2


, NH,


VOCs, organics) and perform the necessary preprocessing steps to prepare the features (data) for use in SVM model.


2. Trains the SVM with labeled data from expert profiles (each class = a cooking profile).


3. During real-time operation, the live vapor signal is processed into features and fed to the trained SVM.


4. The SVM then decides which cooking profile the current signal matches and triggers the appropriate microwave power adjustment.


Applications - Flowable product processing - Real-time recipe automation and repeatability - Quality assurance in food manufacturing environments


Benefits? - Make processes more science-based and reduce guesswork


- Improves repeatability - Mimics expert operators - Produces consistent products


Conclusions: Accurate control of process temperature by electromagnetic waves, be it at microwave or other frequencies is opening the door to new process control ideas. AI algorithms can interpret data from process vapors and adjust microwave input to control process temperature. The combination can produce consistent products with reduced human intervention. Ultimately, more consistent products and more efficient processes will benefit producers and consumers.


References 1. https://scholarworks.uni.edu/patents/2/ 2. eTongue (Wikipedia): https://en.wikipedia.org/ wiki/Electronic_tongue


3. eTongue: Wikipedia - https://en.wikipedia.org/ wiki/Electronic_nose


wavetekprocess.com/


LUBE MAGAZINE AR TIFICIAL INTELLIGENCE DECEMBER 2025


13


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28