Asee peer logo

A Framework for Integrating Intelligent Sensor Measurement Data into Engineering Education

Download Paper |

Conference

2015 ASEE Annual Conference & Exposition

Location

Seattle, Washington

Publication Date

June 14, 2015

Start Date

June 14, 2015

End Date

June 17, 2015

ISBN

978-0-692-50180-1

ISSN

2153-5965

Conference Session

Systems Engineering Division Poster Session

Tagged Division

Systems Engineering

Page Count

13

Page Numbers

26.44.1 - 26.44.13

DOI

10.18260/p.23385

Permanent URL

https://peer.asee.org/23385

Download Count

49

Request a correction

Paper Authors

biography

David O. Olowokere Texas Southern University

visit author page

Dr. Olowokere received his Ph.D. from the State University of New York (Buffalo, N.Y.), and currently heads the engineering programs at Texas Southern University (TSU). He also directs the TSU Aviation and Flight programs. In addition, he has been the principal investigator for a University–Industry partnership providing engineering support for Safety and Mission Assurance Program at the Johnson Space Center in Houston, and the NASA Marshall Center in Huntsville. He served as principal investigator for research grants from several organizations including U.S. National Science Foundation, NASA, U.S. Department of Energy and the U.S. Department of Defense.
Dr. Olowokere was on faculty at the University of Alabama, the University of Detroit, Wayne State University in Detroit, and Bucknell University (Lewisburg, Pa.).

visit author page

biography

Abayomi Ajofoyinbo Ph.D. Texas Southern University

visit author page

Dr. Abayomi Ajofoyinbo received his Ph.D. in Systems Engineering from the University of Lagos, Nigeria, in 2008. He is a Visiting Assistant Professor in the Department of Engineering at the Texas Southern University (TSU) in Houston, Texas. He is currently in charge of Assessment for the engineering programs at TSU, teaching courses in electrical/electronic and computer engineering. Between September 2013 and August 2014, Dr. Ajofoyinbo worked for TSU as Postdoctoral Fellow at the NSF CREST Centre for Research on Complex Networks.
Dr. Ajofoyinbo is a Senior Lecturer in the Department of Systems Engineering, Faculty of Engineering, at the University of Lagos, Nigeria. His research interests are: intelligent control, embedded systems, wireless communications, wireless sensor networks, and engineering systems modeling & analysis.

visit author page

Download Paper |

Abstract

ANFIS based intelligent system model for self-compensation of sensor measurementsPhysical quantities measured by sensors such as temperature, humidity, pressure, displacement,etc., are continuous in nature. Output signal of a sensor can become “corrupted” with unwantedsignals that prevent the actual useful signal from being measured correctly. The characteristics ofa sensor may be classified as being static or dynamic. Whereas static characteristics describe theproperties of a sensor after all transient effects have stabilized to their steady state, dynamiccharacteristics describe the transient properties (or time-dependent characteristics) of a sensor.In the literature, researchers have investigated different aspects of sensor with differentimprovement objectives but mostly focusing on static characteristics. However, the need toreduce both systematic and random errors to improve quality of sensor measurements hasbecome a critical requirement for design of modern day measurement systems. This paperpresents an Adaptive Neuro-Fuzzy Inference System (ANFIS) based intelligent system model forself-compensation of sensor measurements; in which unwanted signals are removed, and therebyimproving the quality of measurement data. The intelligent self-compensation system modelconsists of four modules namely: sensing, measurement error-correction, ANFIS, and Digital-to-Analog (A/D) conversion modules. The ANFIS builds a Fuzzy Inference System (FIS) whosemembership function parameters are tuned to learn from the data being modeled. It is noted thatour consideration in the current paper is not on errors related to sampling and A/D conversion,which can be controlled by selecting appropriate multiplexers, sample-and-hold circuits and A/Dconverter. A sensor that incorporates two energy storage components is considered in this paper;for example, an accelerometer. Such a sensor is modeled by a second-order differentialequation, which is translated into a state-space model for analysis and determination of“corrupted” output of the sensing module. For this case, the input to the sensing module is afunction of the actual sensed quantity, effects of temperature, humidity and other environmentalfactors. Moreover, in view of the effects of environmental conditions on sensor’s performance,this “corrupted” output serves as input to an error-correction module whose output consequentlybecomes input to the ANFIS module. It is noted that the self-compensation occurs in the error-correction module. Output of the ANFIS module is subsequently sent to the A/D conversionmodule for further processing. The efficacy of this intelligent system model is tested using theMATLAB Fuzzy Logic Toolbox. It is shown by the results obtained that the ANFIS basedintelligent model presented in this paper can indeed be implemented for self-compensation ofsensor measurements, and thereby improving quality of measurement data. 1References[1] Wang L., Yan Y.; Mathematical modeling and experimental validation of electrostatic sensors for rotational speed measurement. Measurement Science and Technology, 2014, vol. 25, 12pp.[2] Miljic N.L., Tomic M.V.; A Neuro-Fuzzy based combustion sensor for the control of optimal engine combustion efficiency. Thermal Science, 2013, vol. 17, no. 1, pp. 135-151.[3] Rivera-Mejia, J., Carrillo-Romero, M., Herrera-Ruiz, G.; Self-compensation to build reconfigurable measurement systems. Instrumentation & Measurement Magazine, IEEE, April 2013, vol.16, no.2, pp.10-19.[4] Maria-Alexandra P., Jean-Michel S., M. Kayal.; Offset and Drift Analysis of the Hall Effect sensors: The geometrical parameters influence. Digest Journal of Nanomaterials and Biostructures, July - September 2012, vol. 7, no. 3, pp. 883–891.[5] Mahajan A, Oesch C., Padmanaban H., Utterback L., Chitikeshi S., Figueroa F.; Physical and virtual intelligent sensors for integrated health management systems. International Journal on Smart Sensing and Intelligent Systems, 2012, vol. 5, no. 3, pp. 559-575.[6] Pop, S. , Pitica, D. , Ciascai, I. ; Sensor measurement errors detection methods; IEEE 34th International Spring Seminar on Electronics Technology (ISSE), 11-15 May 2011; Tratanska Lomnica, pp. 414–418.[7] Petra N., Zweck J., Minkoff S.E., Kosterev A. A., Doty J.H.; Modeling and design optimization of a resonant optothermoacoustic trace gas sensor. Society for Industrial and Applied Mathematics Journal of Applied Mathematics, 2011, vol. 71, no. 1, pp. 309-332.[8] Nanayakara T., Halgamuge M. N., Sridhar P. and Madni A. M.; Intelligent sensing in dynamic environments using Markov decision process. Sensors, 2011, vol. 11, pp. 1229-1242.[9] Sanchez J.E.R., Vellasco M.M.B.R., Tanscheit R.; An intelligent model for self-compensation and self-validation of sensor measurements. Fuzzy logic and applications: Proceedings of the 9th International Workshop 9th International Workshop, WILF 2011, Trani, Italy, August 29-31, 2011, pp. 269-276.[10] Liu H., Zhang Y. , Liu Y.-W., Jin M.-H.; Measurement errors in the scanning of resistive sensor arrays, (Elsevier) Sensors and Actuators A: Physical, September 2010, vol. 163, issue no. 1, pp. 198–204.[11] Fraden J.; Sensor Characteristics. Handbook of modern sensors, 2010, pp. 13-52.[12] Bolton W.; Instrumentation and Control. Elsevier Publishing, First Edition, 2008.[13] Chan E., Wang D., Pasquier M.; Towards intelligent self-care: multi-sensor monitoring and neuro- fuzzy behavior modeling. Proceedings of IEEE International Conference on Systems, Man and Cybernetics, SMC, Singapore, 2008, pp. 3083-3088.[14] Ausserlechner U., Infineon T.A.G., Austria M.M. , Holliber M.; Drift of magnetic sensitivity of smart Hall sensors due to moisture absorbed by the IC-package [automotive applications]; Proceedings of 3rd IEEE International Conference on Sensors, 2004; Vienna, Austria, vol.1, pp. 455–458.[15] Jang J-S.R.; ANFIS: Adaptive-Network-Based Fuzzy Inference System. IEEE Transactions on Systems, Man, and Cybernetics, vol. 23, no. 3, 1993, pp. 665-684. 2

Olowokere, D. O., & Ajofoyinbo, A. (2015, June), A Framework for Integrating Intelligent Sensor Measurement Data into Engineering Education Paper presented at 2015 ASEE Annual Conference & Exposition, Seattle, Washington. 10.18260/p.23385

ASEE holds the copyright on this document. It may be read by the public free of charge. Authors may archive their work on personal websites or in institutional repositories with the following citation: © 2015 American Society for Engineering Education. Other scholars may excerpt or quote from these materials with the same citation. When excerpting or quoting from Conference Proceedings, authors should, in addition to noting the ASEE copyright, list all the original authors and their institutions and name the host city of the conference. - Last updated April 1, 2015