Knowledge engineering is still more of an art than a science. In the list presented here, we have tried to capture the art as it exists at the beginning of the 1980's. Many of his heuristics still apply.) 'David Barstow is a member of the Schlumberger-Doll Research Laboratory, Ridgefield, CT. This memo is also being published by SDR as Al Memo number 10. 1 In the course of building expert systems, knowledge engineers have developed intuitions about how best to proceed, heuristics to keep in mind when building a system for a particular task.
Inherent batch-to-batch variability, aging, and contamination are major factors contributing to variability in oil-field cement-slurry performance. Such variability imposes a heavy burden on performance testing and is often a major factor in operational failure. Our approach involves predicting cement compositions, particle-size distributions, and thickening-time curves from the diffuse reflectance infrared Fourier transform spectrum of neat cement powders. Our research shows that many key cement properties are captured within the Fourier transform infrared spectra of cement powders and can be predicted from these spectra using suitable neural network techniques.