LETI: LETI scientists create smart metal detectors – India Education | Latest Education News | World Education News
Researchers from ETU “LETI” have created a prototype of a unique metal detector based on a chaotic circuit.
Today, walk-through metal detectors can be found in airports and places of mass gatherings around the world. Devices that detect metal objects without contact are widely used in security, archeology, mining exploration, construction and industry.
“Artificial intelligence and neuromorphic systems are an in-demand and topical area of research. In our view, classical neural networks are not the future, structures based on biological neuron models are. Our development uses the principle of action of a sensor neuron to solve the problem of metal detection. There are many applications for such detectors.
Olga Druzhina, postgraduate student of the Computer Aided Design Department, engineer of the LETI Youth Research Institute
The main problem with modern metal detector designs is insufficient selectivity, that is, they cannot always determine what kind of metal the detected object is made of. “Qualities such as low power consumption, high sensitivity and resistance to interference are also important,” commented Timur Karimov, associate professor in the Department of Computer Aided Design, head of the Advanced Circuits Engineering Group. from the LETI Youth Research Institute.
Considering the existing shortcomings of modern metal detectors, scientists have created a new type of sensor, which can be used to detect metallic objects, determine what metal they are made of and how far away they are. In this case, the detection range is increased compared to conventional designs. The research results of the research group have been published in the journal Nonlinear Dynamics.
The developed sensor consists of two parts: a sensitive element in the form of an inductive coil and an electronic circuit in which chaotic oscillations occur, imitating the impulses of a biological neuron. Signals from the circuit go to the computer, which processes them with special algorithms and shows the type of target and the distance to it. According to the researchers, the combination of the properties of chaotic and neuromorphic systems in this development gives it favorable qualities of both high sensitivity to changes in parameters and relative ease in interpreting behavior.
“Our electrical circuit simulates a biological neuron, a sensitive coil that is part of the model. When a metallic object approaches the coil, eddy currents are induced in the object, altering the oscillations in the electrical circuit. The distribution of distances between pulses in the circuit changes. Using a computer, we calculate this distribution and decode it, since it contains information about the type of target and its range.
Timur Karimov, associate professor in the computer-aided design department of LETI
The device developed based on a chaotic oscillator has no direct equivalent. Scientists are confident that international colleagues engaged in nonlinear dynamics and chaotic sensors will be interested in this article.
The researchers plan to address the issue of the device’s unwanted sensitivity to temperature and interference. “Chaotic systems, unfortunately, are not very resilient to changes in operating conditions. We plan to solve this problem by moving from analog circuits to implementing most circuits on a microcontroller. The processing algorithms will also be implemented on the controller without the need for a separate ECU”, comments Timur Karimov.
The prospects are to further improve the design of the detector and to apply chaotic neuron-like systems to other tasks, for example to diagnose faults in electrical machines, such as electric motors in factories or wind turbines.