Embedded System for ECG Biometrics

Comunication in Internationa Conference with Peer Review First International Congress on Cardiovasular Technologies - CARDIOTECHNIX, Vilamoura, Portugal, 2013

Sviluppo di un sistema per l'effettuazione di cicli di guida per motoveicoli sul banco a rulli

Il lavoro svolto in questa tesi fa parte di un progetto volto alla realizzazione di un sistema per svolgere test di guida di motoveicoli al banco a rulli, gestendo l’intera prova in remoto, ossia dall’esterno della cella. Tale sistema, denominato RideIT, è stato progettato da Alma Automotive per conto della nota casa motociclistica MV Augusta. Tramite il sistema RideIT, è possibile automatizzare la guida di motoveicoli sul banco a rulli, riproducendo via software, tramite un modello che governa degli attuatori, il comportamento del pilota per quel che riguarda gli azionamenti di acceleratore, frizione, cambio e freno durante un test. I vantaggi di questa soluzione riguardano soprattutto la sicurezza degli addetti, che possono effettuare tutte le prove del caso rimanendo al di fuori della sala prove, oltre alla possibilità di incrementare la ripetibilità e la riproducibilità dei risultati dei test, grazie all’eliminazione del fattore di soggettività legato al guidatore. Il sistema nasce con la specifica di poter eseguire test di omologazione al banco a rulli anche se, grazie alla flessibilità che è in grado di garantire, può essere perfettamente riconfigurato, anche in vista di futuri sviluppi del progetto.

Sviluppo di una interfaccia per l'integrazione della piattaforma inerziale X-Nucleo con una rete di sensori wireless

Questo elaborato presenta il progetto di una interfaccia per l'aggiunta di sensori inerziali ad un nodo di una WSN (Wireless Sensor Network) �finalizzato al monitoraggio delle frane. Analizzando i vantaggi che avrebbe portato l'utilizzo di ulteriori sensori, si �e cercato di fornire un valido approccio di progettazione; in particolare l'idea �e quella di integrarli con un giroscopio ed un accelerometro aventi applicazioni in altri settori. Con questo particolare utilizzo, essi possono portare ad un miglior monitoraggio riuscendo a rilevare i movimenti in modo dettagliato ed a riconoscere i falsi allarmi. Nell'approccio che si intende suggerire verranno sfruttate schede per la prototipazione rapida, user-friendly e con costi decisamente accessibili, adatte alla sperimentazione elettronica e per lo sviluppo di nuovi dispositivi. Attraverso l'utilizzo di ambienti di sviluppo appositamente creati, si sono simulate le comunicazioni tra nodo e scheda di sensori, mettendo in evidenza i vantaggi ottenuti. Buona parte del progetto ha riguardato la programmazione in linguaggio C/C++, con una particolare attenzione al risparmio energetico.

Flexible Computing Systems For AI Acceleration At The Extreme Edge Of The IoT

Embedding intelligence in extreme edge devices allows distilling raw data acquired from sensors into actionable information, directly on IoT end-nodes. This computing paradigm, in which end-nodes no longer depend entirely on the Cloud, offers undeniable benefits, driving a large research area (TinyML) to deploy leading Machine Learning (ML) algorithms on micro-controller class of devices. To fit the limited memory storage capability of these tiny platforms, full-precision Deep Neural Networks (DNNs) are compressed by representing their data down to byte and sub-byte formats, in the integer domain. However, the current generation of micro-controller systems can barely cope with the computing requirements of QNNs. This thesis tackles the challenge from many perspectives, presenting solutions both at software and hardware levels, exploiting parallelism, heterogeneity and software programmability to guarantee high flexibility and high energy-performance proportionality. The first contribution, PULP-NN, is an optimized software computing library for QNN inference on parallel ultra-low-power (PULP) clusters of RISC-V processors, showing one order of magnitude improvements in performance and energy efficiency, compared to current State-of-the-Art (SoA) STM32 micro-controller systems (MCUs) based on ARM Cortex-M cores. The second contribution is XpulpNN, a set of RISC-V domain specific instruction set architecture (ISA) extensions to deal with sub-byte integer arithmetic computation. The solution, including the ISA extensions and the micro-architecture to support them, achieves energy efficiency comparable with dedicated DNN accelerators and surpasses the efficiency of SoA ARM Cortex-M based MCUs, such as the low-end STM32M4 and the high-end STM32H7 devices, by up to three orders of magnitude. To overcome the Von Neumann bottleneck while guaranteeing the highest flexibility, the final contribution integrates an Analog In-Memory Computing accelerator into the PULP cluster, creating a fully programmable heterogeneous fabric that demonstrates end-to-end inference capabilities of SoA MobileNetV2 models, showing two orders of magnitude performance improvements over current SoA analog/digital solutions.

Simulation and Implementation of a PMSM Sensorless Control Algorithm for Submarine Applications

In this thesis, the study and the simulation of two advanced sensorless speed control techniques for a surface PMSM are presented. The aim is to implement a sensorless control algorithm for a submarine auxiliary propulsion system. This experimental activity is the result of a project collaboration with L3Harris Calzoni, a leader company in A&D systems for naval handling in military field. A Simulink model of the whole electric drive has been developed. Due to the satisfactory results of the simulations, the sensorless control system has been implemented in C code for STM32 environment. Finally, several tests on a real brushless machine have been carried out while the motor was connected to a mechanical load to simulate the real scenario of the final application. All the experimental results have been recorded through a graphical interface software developed at Calzoni.

Design and Implementation of Single phase 230V to Three Phase Inverter Based on the Embedded System STM-32 Applied to motor control

In the field of Power Electronics, several types of motor control systems have been developed using STM microcontroller and power boards. In both industrial power applications and domestic appliances, power electronic inverters are widely used. Inverters are used to control the torque, speed, and position of the rotor in AC motor drives. An inverter delivers constant-voltage and constant-frequency power in uninterruptible power sources. Because inverter power supplies have a high-power consumption and low transfer efficiency rate, a three-phase sine wave AC power supply was created using the embedded system STM32, which has low power consumption and efficient speed. It has the capacity of output frequency of 50 Hz and the RMS of line voltage. STM32 embedded based Inverter is a power supply that integrates, reduced, and optimized the power electronics application that require hardware system, software, and application solution, including power architecture, techniques, and tools, approaches capable of performance on devices and equipment. Power inverters are currently used and implemented in green energy power system with low energy system such as sensors or microcontroller to perform the operating function of motors and pumps. STM based power inverter is efficient, less cost and reliable. My thesis work was based on STM motor drives and control system which can be implemented in a gas analyser for operating the pumps and motors. It has been widely applied in various engineering sectors due to its ability to respond to adverse structural changes and improved structural reliability. The present research was designed to use STM Inverter board on low power MCU such as NUCLEO with some practical examples such as Blinking LED, and PWM. Then we have implemented a three phase Inverter model with Steval-IPM08B board, which converter single phase 230V AC input to three phase 380 V AC output, the output will be useful for operating the induction motor.