Opto-Electronic Sensor System

[srj.misra]

[attachment=4579]

---

ABSTRACT

Optical techniques are used for large number of sensing and metrological applications. The conventional methods based on free- space monitoring is effective only for line of sight and suffers from undesired misalignments and external perturbations. Guided- wave sensing adds to intrinsic advantages of optical techniques the possibility of guiding the light beam in a confined and inaccessible medium, thus allowing more versatile and less perturbed measurements.
Fiber and integrated optics technology were primarily developed for telecommunication applications. However, the development of high quality and competitive price optoelectronic components and fibers have largely contributed to the expansion of guided wave technology for sensing as well.

Fundamental of Wave Guiding
According to ray theory of light propagation, when light impinges at the interface between two transparent media, it is partially reflected and partially refracted.
An optical fiber consists of layered cylinders of glass or plastic. Inner and outer cylinders, namely core and cladding , have refractive indices n1 and n2, respectively. Any ray impinging at the core-cladding interface with an incident angle greater than c is undergoing multiple reflections within the core, in which it results trapped and propagates.

---

[naisam sayed]

Tool wear has long been identified as the most undesirable characteristic of the machining operations. Flank wear, is particular directly affects the work piece dimensions and the surface quality. A reliable and sensitive technique for monitoring the tool wears with out interrupting the process, is curtail in realization of the modern manufacturing concepts like unmanned machining centers, adaptive control optimization, etc. in this work an opto-electronic sensor is used in conjunction with a multilayered neural network for predicting the flank wear on the cutting tool.
The gap sensing system consists of a bifurcated optical fiber laser source and a photodiode circuit. The output of the photodiode circuit is amplified and converted to the digital from using an A/D converter. The digitized sensor signal along with the cutting parameters from the input to a three layered, feed forward, fully connected neural network. The neural network, trained off-line using a back propagation algorithm and the experimental data, is used to predict flank wear..