Features

• Emphasizes basic design principles and applications of intelligent sensors using case studies and numerical examples
• Discusses signal processing operations such as linearization, calibration, and compensation on which intelligent sensors rely
• Investigates artificial intelligence as a critical component of intelligent sensors in real world applications
• Uses MATLAB programs to validate design approaches

Summary

With the advent of microprocessors and digital-processing technologies as catalyst, classical sensors capable of simple signal conditioning operations have evolved rapidly to take on higher and more specialized functions including validation, compensation, and classification. This new category of sensor expands the scope of incorporating intelligence into instrumentation systems, yet with such rapid changes, there has developed no universal standard for design, definition, or requirement with which to unify intelligent instrumentation.

Explaining the underlying design methodologies of intelligent instrumentation, Intelligent Instrumentation: Principles and Applications provides a comprehensive and authoritative resource on the scientific foundations from which to coordinate and advance the field. Employing a textbook-like language, this book translates methodologies to more than 80 numerical examples, and provides applications in 14 case studies for a complete and working understanding of the material.

Beginning with a brief introduction to the basic concepts of process, process parameters, sensors and transducers, and classification of transducers, the book describes the performance characteristics of instrumentation and measurement systems and discusses static and dynamic characteristics, various types of sensor signals, and the concepts of signal representations, various transforms, and their operations in both static and dynamic conditions. It describes smart sensors, cogent sensors, soft sensors, self-validating sensors, VLSI sensors, temperature-compensating sensors, microcontrollers and ANN-based sensors, and indirect measurement sensors.

The author examines intelligent sensor signal conditioning such as calibration, linearization, and compensation, along with a wide variety of calibration and linearization techniques using circuits, analog-to-digital converters (ADCs), microcontrollers, ANNs, and software. The final chapters highlight ANN techniques for pattern classification, recognition, prognostic diagnosis, fault detection, linearization, and calibration as well as important interfacing protocols in the wireless networking platform.