when full neutralisation of acids and bases are accomplished. An eTongue comprised of a pH sensor could monitor the condensed vapors of the grease cooking process to determine the conclusion of the reaction. In general, the intensity of most reactions or cooking byproducts are proportional to the heat input of the process. In some cases, the exothermic heat of the reaction also contributes to the rise in product temperature. Understandably, saponification reactions as practiced in grease making is an exothermic process that results in heat by chemical reaction. But such chemical heat input can be calculated and filed in the process data for AI learning algorithms.
There is an ongoing effort to use the byproduct of the cooking process combined with other traditional variables such as torque in drive motors, an indicator of thickening of product, to create an intelligent processing environment. WAVEtek Process Technology that markets wave-based production vessels, has produced AI-based monitoring options that in time can reproduce desired finished products by mimicking a process as produced by a master “chef”. Figure 3 shows the array of sensors presented as “eNose” that intermittently delivers a predetermined quanity of vapors to each sensor that is designed to sense and report a different chemical.
The eNose in this case contains “nostrils” with embedded tubes for delivering a minute quantity of vapor to each sensor. One tube sends the vapors through a condenser resulting in a small amount of liquid to be processed by the eTongue. In this case a pH sensor uses the liquid to determine the acidity of the product and send the results to the Ai process box. The sensor’s output voltages are recorded at regular time intervals and the results are compared with the data collected on the same process from the expert cooked process. The features of the AI supported process can be described as follows:
Figure 3: Vapors from cooking vessels are drawn at regular time intervals and sent to various sensors for AI algorithm to analyze and signal the microwave controller to adjust power.
Figure 2: A 100-kW generator applies microwaves to a wave-based cooking Vessel with the eNose and eTongue sensing the vapor condensates with AI analysis and integration with microwave.
12
LUBE MAGAZINE AR TIFICIAL INTELLIGENCE DECEMBER 2025
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
