No abstract

No abstract

This paper uses the Kohonen Self-Organising Map (KSOM) to detect, diagnose, and classify induction motor faults. A series of simulations using models of the 3-phase induction motor based on real industrial motor parameters were performed using MATLAB/Simulink under fault conditions such as inter-turn, power frequency variation, over-voltage and unbalance in supply voltage. The model was trained using the input signals of the various fault conditions. Various faults from an unseen induction motor were fed to the model to test the model’s ability to detect and classify induction motor faults. The KSOM adapted to the conditions of the unseen motor, detected, diagnosed and classified these faults with an accuracy of 94.12%.

In recent years, there has been the unpleasant advent of a new type of credit card fraud called Automated Teller Machine (ATM) skimming. This type of fraud poses a substantial threat to the banking sector because its modus operandi is quite subtler than other known types of ATM fraud. It consists of a criminal implanting a disguised dummy card reader very similar to the ATM's original card reader at the ATM. This is done to intercept the ATM card data of any unsuspecting customer who tries to withdraw cash. This paper seeks to design a system which will be able to detect and report such devices before they cause harm. The objective of this research was achieved by designing a skimmer incorporating the use of a metal detector for detecting new electronic components within the ATMs card slot region, an ultrasonic sensor for detecting unfamiliar skimmer overlays and the processing power of a microcontroller to coordinate theses sensors which monitor the status of the ATM terminal's original card reader and send a Short Message Service (SMS) text message whenever the system detects that a skimmer has been attached to the ATM terminal. This concept of skimming detection was designed, tested and simulated under several operating conditions in Proteus 8.0 simulation software to prove the detection method's efficacy. The simulation results showed that the proposed system provided a decent theoretical skimmer detection technique. However, other factors such as metal detector oscillator instability and the difficulty in accurately modelling the composition of ATM skimmers served as this design's major drawbacks.

No abstract