This paper presents a microcomputer-based method that can be used to categorize mineral deposits in petroleum pipelines using ultrasonic measurements. The system was developed for use in the field in order to avoid expensive and time-consuming procedures. The identification of mineral deposits is based on an intelligent method using a multi-layer perceptron neural network consisting of three layers of neurons. The artificial neural network was trained to identify six different materials (calcium carbonate, wax, marble, barium sulphate, strontium sulphate and steel) and implemented using a microcontroller.
AndersonMI (1996) Ultrasonic instrumentation for on-line monitoring of deposits in pipes. Presented at the conference on Controlling Hydrates, Waxes and Asphaltenes, organised by IBC UK Conference Limited supported by Oil and Gas Journal, Skean Dhu Hotel, Aberdeen, September 1996.
2.
GunarathneGPPChristidisK (2002) Material characterisation in situ using ultrasound measurements. IEEE Transactions on Instrumentation and Measurements51: 368–373.
3.
GunarathneGPPKeatchRW (1996) Novel techniques for monitoring and enhancing dissolution of mineral deposits in petroleum pipelines. Ultrasonics Sonochemistry34: 411–419.
4.
GunarathneGPPZhouQChristidisK (1998) Ultrasonic feature extraction techniques for characterisation and quantification of scales in petroleum pipelines. Proceedings of the Conference IEEE Ultrasonic ‘98, Japan, October, pp. 859–864.
5.
HamiltonJCMoonRD (1995) Understanding ultrasonic pipeline inspection: the experience of T. D. Williamson Inc. Pipes and Pipelines International, Jul.–Aug.: 13–20.
6.
HullDR (1985) Measurements of ultrasonic velocity using phase-slop and cross-correlation methods. Materials Evaluation43: 1455–1460.
7.
KeatchRWGunarathneGPP (1996) Novel techniques for quantification and enhancement of chemical dissolution of oil field mineral scale deposits. Presented at the 8th International Symposium of Oil Field Chemists, Gello, 2–5 March.
8.
KhashmanA (2012) An emotional system with application to blood cell type identification. Transactions of the Institute of Measurement and Control34(4): 125–147.
9.
McShaneJ (1992) An introduction to neural nets. Hewlett-Packard JournalFeb.: 62–64.
10.
PapadakisEP (1967) Ultrasonic phase velocity by pulse-echo-overlap method incorporating diffraction phase corrections. Journal of the Acoustical Society of America42: 1045–1051.
11.
RaadJA (1990) Cable and other special ultrasonic pigs. Pipes and Pipelines InternationalMar.–Apr.: 15–24.
12.
SelfridgeAR (1985) Approximate material properties in isotropic materials. IEEE Transactions on Sonics and Ultrasonics SU-32: 381–384.
13.
UdreaRMVizireanuDN (2008) Quantized multiple sinusoids signal estimation algorithm. Journal of Instrumentation3: 1–7.
14.
VaryA (1980) Ultrasonic measurements of material properties. Research Techniques in Nondestructive Testing4: 159–204.
15.
VizireanuDN (2012) A fast, simple and accurate time-varying frequency estimation method for single-phase electric power systems. Measurement45(6): 1331–1333.
16.
VizireanuDNHalungaSV (2012) Simple, fast and accurate eight points amplitude estimation method of sinusoidal signals for DSP based instrumentation. Journal of Instrumentation7: 1–10.
17.
WangDBaiYZhaoJ (2012) Robot manipulator calibration using neural network and a camera-based measurement system. Transactions of the Institute of Measurement and Control34(2–3): 105–121.
18.
WendelRDualJ (1996) Application of neural networks to quantitative nondestructive evaluation. Ultrasonics34: 461–465.
19.
ZhaoLSunZTatibouetJJenC (2010) Ultrasonic diagnoses of melting and degradation of poly(ethylene terephthalate). Transactions of the Institute of Measurement and Control32(6), 756–766.
