Search

The microcontroller units often use communication buses to interface with sensors or actuators. The communication bus must be selected with respect to communication speed, reliability and also overall solution price. Transmitted data needs to be organised according predefined structures in case of using any communication. Combination of rapid prototyping tools for automatic code generation and communication busses can be problematic for this reason. This paper deals with possibility to use MATLAB/Simulink code generation for communication interfaces. Local Interconnect Network (LIN) interface was used for testing. Same principles can be used also for Controller Area Network (CAN) interface. Presented method can simplify using of communication buses in Simulink.

The microcontroller units often use communication buses to interface with sensors or actuators. The communication bus must be selected with respect to communication speed, reliability and also overall solution price. Transmitted data needs to be organised according predefined structures in case of using any communication. Combination of rapid prototyping tools for automatic code generation and communication busses can be problematic for this reason. This paper deals with possibility to use MATLAB/Simulink code generation for communication interfaces. Local Interconnect Network (LIN) interface was used for testing. Same principles can be used also for Controller Area Network (CAN) interface. Presented method can simplify using of communication buses in Simulink.

The microcontroller units often use communication buses to interface with sensors or actuators. The communication bus must be selected with respect to communication speed, reliability and also overall solution price. Transmitted data needs to be organised according predefined structures in case of using any communication. Combination of rapid prototyping tools for automatic code generation and communication busses can be problematic for this reason. This paper deals with possibility to use MATLAB/Simulink code generation for communication interfaces. Local Interconnect Network (LIN) interface was used for testing. Same principles can be used also for Controller Area Network (CAN) interface. Presented method can simplify using of communication buses in Simulink.

The microcontroller units often use communication buses to interface with sensors or actuators. The communication bus must be selected with respect to communication speed, reliability and also overall solution price. Transmitted data needs to be organised according predefined structures in case of using any communication. Combination of rapid prototyping tools for automatic code generation and communication busses can be problematic for this reason. This paper deals with possibility to use MATLAB/Simulink code generation for communication interfaces. Local Interconnect Network (LIN) interface was used for testing. Same principles can be used also for Controller Area Network (CAN) interface. Presented method can simplify using of communication buses in Simulink.

The microcontroller units often use communication buses to interface with sensors or actuators. The communication bus must be selected with respect to communication speed, reliability and also overall solution price. Transmitted data needs to be organised according predefined structures in case of using any communication. Combination of rapid prototyping tools for automatic code generation and communication busses can be problematic for this reason. This paper deals with possibility to use MATLAB/Simulink code generation for communication interfaces. Local Interconnect Network (LIN) interface was used for testing. Same principles can be used also for Controller Area Network (CAN) interface. Presented method can simplify using of communication buses in Simulink.

The microcontroller units often use communication buses to interface with sensors or actuators. The communication bus must be selected with respect to communication speed, reliability and also overall solution price. Transmitted data needs to be organised according predefined structures in case of using any communication. Combination of rapid prototyping tools for automatic code generation and communication busses can be problematic for this reason. This paper deals with possibility to use MATLAB/Simulink code generation for communication interfaces. Local Interconnect Network (LIN) interface was used for testing. Same principles can be used also for Controller Area Network (CAN) interface. Presented method can simplify using of communication buses in Simulink.

This article focuses on the Real-time Operating System (RTOS) implementation for Hardware-in-the-loop (HIL) simulation. Three-core AURIX microcontroller TC277 was chosen for testing. This work describes the distribution of software to individual core to reach required functionality. Basic features of HIL simulation and its usage along with RTOS features are discused.

This article focuses on the Real-time Operating System (RTOS) implementation for Hardware-in-the-loop (HIL) simulation. Three-core AURIX microcontroller TC277 was chosen for testing. This work describes the distribution of software to individual core to reach required functionality. Basic features of HIL simulation and its usage along with RTOS features are discused.

This article focuses on the Real-time Operating System (RTOS) implementation for Hardware-in-the-loop (HIL) simulation. Three-core AURIX microcontroller TC277 was chosen for testing. This work describes the distribution of software to individual core to reach required functionality. Basic features of HIL simulation and its usage along with RTOS features are discused.

This article focuses on the Real-time Operating System (RTOS) implementation for Hardware-in-the-loop (HIL) simulation. Three-core AURIX microcontroller TC277 was chosen for testing. This work describes the distribution of software to individual core to reach required functionality. Basic features of HIL simulation and its usage along with RTOS features are discused.

This article focuses on the Real-time Operating System (RTOS) implementation for Hardware-in-the-loop (HIL) simulation. Three-core AURIX microcontroller TC277 was chosen for testing. This work describes the distribution of software to individual core to reach required functionality. Basic features of HIL simulation and its usage along with RTOS features are discused.

This article focuses on the Real-time Operating System (RTOS) implementation for Hardware-in-the-loop (HIL) simulation. Three-core AURIX microcontroller TC277 was chosen for testing. This work describes the distribution of software to individual core to reach required functionality. Basic features of HIL simulation and its usage along with RTOS features are discused.

This article focuses on the design and subsequent implementation platform for controlling multi-phase motors. Article describes the functionality of the assembled platform and the possibility of its usage to control either the individual motors or a single multi-phase motor. Platform is able to control Maximum nine-phases motor. The platform uses the three core AURIX TriCore microcontroller TC275. This paper also describes the distribution control program to initialization of device and separated control application generated by the Simulink automatic code generation. Finally interconnection these partial programs into a single control application.

This article focuses on the design and subsequent implementation platform for controlling multi-phase motors. Article describes the functionality of the assembled platform and the possibility of its usage to control either the individual motors or a single multi-phase motor. Platform is able to control Maximum nine-phases motor. The platform uses the three core AURIX TriCore microcontroller TC275. This paper also describes the distribution control program to initialization of device and separated control application generated by the Simulink automatic code generation. Finally interconnection these partial programs into a single control application.

This article focuses on the design and subsequent implementation platform for controlling multi-phase motors. Article describes the functionality of the assembled platform and the possibility of its usage to control either the individual motors or a single multi-phase motor. Platform is able to control Maximum nine-phases motor. The platform uses the three core AURIX TriCore microcontroller TC275. This paper also describes the distribution control program to initialization of device and separated control application generated by the Simulink automatic code generation. Finally interconnection these partial programs into a single control application.

Cache memories are one of the hardware resources with higher potential to reduce worst-case execution time (WCET) costs for software programs with tight real-time constraints. Yet, the complexity of cache analysis has caused a large fraction of real-time systems industry to avoid using them, especially in the automotive sector. For measurement-based timing analysis (MBTA) - the dominant technique in domains such as automotive - cache challenges the definition of test scenarios stressful enough to produce (cache) layouts that causing high contention. In this paper, we present our experience in enabling the use of caches for a real automotive application running on an AURIX multiprocessor, using software randomization and measurement-based probabilistic timing analysis (MBPTA). Our results show that software randomization successfully exposes - in the experiments performed for timing analysis - cache related variability, in a manner that can be effectively captured by MBPTA., The research leading to these results has received funding from the European Community’s FP7 [FP7/2007-2013] under the PROXIMA Project (http://www.proxima project.eu), grant agreement no 611085. This work has also been partially supported by the Spanish Ministry of Science and Innovation (grant TIN2015-65316-P) and the HiPEAC Network of Excellence. Jaume Abella has been partially supported by the Ministry of Economy and Competitiveness under Ramon y Cajal fellowship RYC-2013-14717. This work was conducted as part of a collaboration with the CONCERTO project (ARTEMIS-JU grant nr. 333053), which provided the automotive application and the build automation. Authors thank Benjamin Lesage for his support in execution time collection infrastructure on the AURIX board., Peer Reviewed, Postprint (published version)

This article focuses on the design and subsequent implementation platform for controlling multi-phase motors. Article describes the functionality of the assembled platform and the possibility of its usage to control either the individual motors or a single multi-phase motor. Platform is able to control Maximum nine-phases motor. The platform uses the three core AURIX TriCore microcontroller TC275. This paper also describes the distribution control program to initialization of device and separated control application generated by the Simulink automatic code generation. Finally interconnection these partial programs into a single control application.

This article focuses on the design and subsequent implementation platform for controlling multi-phase motors. Article describes the functionality of the assembled platform and the possibility of its usage to control either the individual motors or a single multi-phase motor. Platform is able to control Maximum nine-phases motor. The platform uses the three core AURIX TriCore microcontroller TC275. This paper also describes the distribution control program to initialization of device and separated control application generated by the Simulink automatic code generation. Finally interconnection these partial programs into a single control application.

This article focuses on the design and subsequent implementation platform for controlling multi-phase motors. Article describes the functionality of the assembled platform and the possibility of its usage to control either the individual motors or a single multi-phase motor. Platform is able to control Maximum nine-phases motor. The platform uses the three core AURIX TriCore microcontroller TC275. This paper also describes the distribution control program to initialization of device and separated control application generated by the Simulink automatic code generation. Finally interconnection these partial programs into a single control application.

Cache memories are one of the hardware resources with higher potential to reduce worst-case execution time (WCET) costs for software programs with tight real-time constraints. Yet, the complexity of cache analysis has caused a large fraction of real-time systems industry to avoid using them, especially in the automotive sector. For measurement-based timing analysis (MBTA) - the dominant technique in domains such as automotive - cache challenges the definition of test scenarios stressful enough to produce (cache) layouts that causing high contention. In this paper, we present our experience in enabling the use of caches for a real automotive application running on an AURIX multiprocessor, using software randomization and measurement-based probabilistic timing analysis (MBPTA). Our results show that software randomization successfully exposes - in the experiments performed for timing analysis - cache related variability, in a manner that can be effectively captured by MBPTA.

Henkel Corporation has developed two extractants, based on the guanidine functionality, for the recovery of gold and silver from alkaline cyanide leach liquors: a solvent extraction reagent, LIX 79, and a resin, Aurix resin. The guanidine functionality is sufficiently basic to be protonated at pH values below 12, resulting in extraction by an ion-pair mechanism and stripping upon contact with sufficiently strong caustic solutions. The application of LIX 79 to the treatment of clarified leach liquors from copper-gold ores, clarified silver leach liquors and the detoxification of spent heap leaching operations is described. Aurix resin possesses fast kinetics, excellent attrition resistance and high selectivity for gold over copper. The results of trials on re-pulped filter cake in an AAC pump cell and laboratory ammonia-cyanide resin-in-leach are reported., Henkel Corporation has developed two extractants, based on the guanidine functionality, for the recovery of gold and silver from alkaline cyanide leach liquors: a solvent extraction reagent, LIX 79, and a resin, Aurix resin. The guanidine functionality is sufficiently basic to be protonated at pH values below 12, resulting in extraction by an ion-pair mechanism and stripping upon contact with sufficiently strong caustic solutions. The application of LIX 79 to the treatment of clarified leach liquors from copper-gold ores, clarified silver leach liquors and the detoxification of spent heap leaching operations is described. Aurix resin possesses fast kinetics, excellent attrition resistance and high selectivity for gold over copper. The results of trials on re-pulped filter cake in an AAC pump cell and laboratory ammonia-cyanide resin-in-leach are reported.

Táto diplomová práca sa zaoberá realizáciou SIL a PIL simulácie pre mikrokontrolér Aurix TriCore TC277D vykonávanou v prostredí Matlab/Simulink. Realizácia simulácie predstavuje okrem iného aj implementáciu simulovaného modelu do mikrokontroléra, ako aj tvorbu rozhrania pre komunikáciu mikrokontroléra s programom Matlab Simulink. Správnosť SIL a PIL simulácie bola overená porovnaním simulovaných priebehov zo simulácie v Simulinku. Simulovaným modelom bol použitý tepelný model kabíny automobilu vytváraný v predchádzajúcej bakalárskej práci autora tejto diplomovej práce. Model v TC277D, ako aj konfigurácia pre SIL/PIL je vytvorená pre použitie s programovacím jazykom C. Súčasťou práce je taktiež návod, podľa ktorého je možné model a konfiguráciu upraviť tak, aby bolo možné uvedené simulácie vykonávať na akomkoľvek zariadení obsahujúcom potrebný softvér. Z porovnania odsimulovaných údajov jednotlivých simulácii je jasné, že vytvorenú konfiguráciu je možné použiť pre SIL alebo PIL simuláciu., This diploma thesis deals with the implementation of SIL and PIL simulation for the microcontroller Aurix TriCore TC277D performed in the Matlab Simulink. The realization of the simulation represents, among other things, the implementation of the simulated model into the microcontroller, as well as the creation of an interface for the communication of the microcontroller with the Matlab Simulink. The accuracy of SIL and PIL simulations was verified by comparing the simulated waveforms from the simulation in Simulink. The simulated model used a thermal model of a car cabin created in the previous bachelor's thesis of the author of this diploma thesis. The model in TC277D, as well as the configuration for SIL / PIL is created for use with the C programming language. The work also includes instructions according to which the model and configuration can be modified so that the simulations can be performed on any device containing the necessary software. From the comparison of the simulated data is it clear that the created configuration can be used for SIL or PIL simulation.

Část této práce pojednává o dopředných neuronových sítích FNN a způsobu jejich vývoje pomocí MATLAB Deep Learning Toolboxu a API Keras v jazyce Python. Následně se práce zabývá převodem těchto sítí do jazyka C/C++ pomocí knihoven Keras2c, AIfES, TFLM a NNoM. Tento teoretický základ byl nezbytný pro navazující část, která je zaměřena na implementaci a testování natrénované FNN na platformě AURIX TC397 3.3V Application Kit. Tato FNN slouží k diagnostice PMS motoru za účelem detekce mezizávitového zkratu. V práci je blíže popsána konfigurace periferií GPT12 a GETH mikrokontroléru AURIX TC397, které byly využity v aplikaci pro testování FNN. S využitím knihovny Keras2c byla ověřena možnost spuštění inference na 2 jádrech mikrokontroléru AURIX a v rámci knihovny NNoM byla provedena kvantizace natrénované FNN. Nakonec bylo provedeno srovnání knihoven Keras2c, AIfES, TFLM a NNoM z hlediska jednoduchosti implementace, přesnosti klasifikace a rychlosti klasifikace na platformě AURIX., Part of this thesis discusses FNNs and how to develop them using MATLAB Deep Learning Toolbox and Keras API in Python. Subsequently, the thesis deals with the conversion of these networks into C/C++ using the Keras2c, AIfES, TFLM and NNoM libraries. This theoretical background was essential for the follow-up section, which focuses on the implementation and testing of the trained FNN on the AURIX TC397 3.3V Application Kit platform. This FNN is used to diagnose the PMS motor in order to detect inter turn faults. The configuration of the GPT12 and GETH peripherals of the AURIX TC397 microcontroller, which were used in the FNN testing application, is described in detail in this thesis. Using the Keras2c library, the possibility of running inference on 2 cores of the AURIX microcontroller was verified and quantization of the trained FNN was performed within the NNoM library. Finally, a comparison of the Keras2c, AIfES, TFLM and NNoM libraries was performed in terms of ease of implementation, classification accuracy and classification speed on the AURIX platform.

Část této práce pojednává o dopředných neuronových sítích FNN a způsobu jejich vývoje pomocí MATLAB Deep Learning Toolboxu a API Keras v jazyce Python. Následně se práce zabývá převodem těchto sítí do jazyka C/C++ pomocí knihoven Keras2c, AIfES, TFLM a NNoM. Tento teoretický základ byl nezbytný pro navazující část, která je zaměřena na implementaci a testování natrénované FNN na platformě AURIX TC397 3.3V Application Kit. Tato FNN slouží k diagnostice PMS motoru za účelem detekce mezizávitového zkratu. V práci je blíže popsána konfigurace periferií GPT12 a GETH mikrokontroléru AURIX TC397, které byly využity v aplikaci pro testování FNN. S využitím knihovny Keras2c byla ověřena možnost spuštění inference na 2 jádrech mikrokontroléru AURIX a v rámci knihovny NNoM byla provedena kvantizace natrénované FNN. Nakonec bylo provedeno srovnání knihoven Keras2c, AIfES, TFLM a NNoM z hlediska jednoduchosti implementace, přesnosti klasifikace a rychlosti klasifikace na platformě AURIX., Part of this thesis discusses FNNs and how to develop them using MATLAB Deep Learning Toolbox and Keras API in Python. Subsequently, the thesis deals with the conversion of these networks into C/C++ using the Keras2c, AIfES, TFLM and NNoM libraries. This theoretical background was essential for the follow-up section, which focuses on the implementation and testing of the trained FNN on the AURIX TC397 3.3V Application Kit platform. This FNN is used to diagnose the PMS motor in order to detect inter turn faults. The configuration of the GPT12 and GETH peripherals of the AURIX TC397 microcontroller, which were used in the FNN testing application, is described in detail in this thesis. Using the Keras2c library, the possibility of running inference on 2 cores of the AURIX microcontroller was verified and quantization of the trained FNN was performed within the NNoM library. Finally, a comparison of the Keras2c, AIfES, TFLM and NNoM libraries was performed in terms of ease of implementation, classification accuracy and classification speed on the AURIX platform.

Část této práce pojednává o dopředných neuronových sítích FNN a způsobu jejich vývoje pomocí MATLAB Deep Learning Toolboxu a API Keras v jazyce Python. Následně se práce zabývá převodem těchto sítí do jazyka C/C++ pomocí knihoven Keras2c, AIfES, TFLM a NNoM. Tento teoretický základ byl nezbytný pro navazující část, která je zaměřena na implementaci a testování natrénované FNN na platformě AURIX TC397 3.3V Application Kit. Tato FNN slouží k diagnostice PMS motoru za účelem detekce mezizávitového zkratu. V práci je blíže popsána konfigurace periferií GPT12 a GETH mikrokontroléru AURIX TC397, které byly využity v aplikaci pro testování FNN. S využitím knihovny Keras2c byla ověřena možnost spuštění inference na 2 jádrech mikrokontroléru AURIX a v rámci knihovny NNoM byla provedena kvantizace natrénované FNN. Nakonec bylo provedeno srovnání knihoven Keras2c, AIfES, TFLM a NNoM z hlediska jednoduchosti implementace, přesnosti klasifikace a rychlosti klasifikace na platformě AURIX., Part of this thesis discusses FNNs and how to develop them using MATLAB Deep Learning Toolbox and Keras API in Python. Subsequently, the thesis deals with the conversion of these networks into C/C++ using the Keras2c, AIfES, TFLM and NNoM libraries. This theoretical background was essential for the follow-up section, which focuses on the implementation and testing of the trained FNN on the AURIX TC397 3.3V Application Kit platform. This FNN is used to diagnose the PMS motor in order to detect inter turn faults. The configuration of the GPT12 and GETH peripherals of the AURIX TC397 microcontroller, which were used in the FNN testing application, is described in detail in this thesis. Using the Keras2c library, the possibility of running inference on 2 cores of the AURIX microcontroller was verified and quantization of the trained FNN was performed within the NNoM library. Finally, a comparison of the Keras2c, AIfES, TFLM and NNoM libraries was performed in terms of ease of implementation, classification accuracy and classification speed on the AURIX platform.

Táto diplomová práca sa zaoberá realizáciou SIL a PIL simulácie pre mikrokontrolér Aurix TriCore TC277D vykonávanou v prostredí Matlab/Simulink. Realizácia simulácie predstavuje okrem iného aj implementáciu simulovaného modelu do mikrokontroléra, ako aj tvorbu rozhrania pre komunikáciu mikrokontroléra s programom Matlab Simulink. Správnosť SIL a PIL simulácie bola overená porovnaním simulovaných priebehov zo simulácie v Simulinku. Simulovaným modelom bol použitý tepelný model kabíny automobilu vytváraný v predchádzajúcej bakalárskej práci autora tejto diplomovej práce. Model v TC277D, ako aj konfigurácia pre SIL/PIL je vytvorená pre použitie s programovacím jazykom C. Súčasťou práce je taktiež návod, podľa ktorého je možné model a konfiguráciu upraviť tak, aby bolo možné uvedené simulácie vykonávať na akomkoľvek zariadení obsahujúcom potrebný softvér. Z porovnania odsimulovaných údajov jednotlivých simulácii je jasné, že vytvorenú konfiguráciu je možné použiť pre SIL alebo PIL simuláciu., This diploma thesis deals with the implementation of SIL and PIL simulation for the microcontroller Aurix TriCore TC277D performed in the Matlab Simulink. The realization of the simulation represents, among other things, the implementation of the simulated model into the microcontroller, as well as the creation of an interface for the communication of the microcontroller with the Matlab Simulink. The accuracy of SIL and PIL simulations was verified by comparing the simulated waveforms from the simulation in Simulink. The simulated model used a thermal model of a car cabin created in the previous bachelor's thesis of the author of this diploma thesis. The model in TC277D, as well as the configuration for SIL / PIL is created for use with the C programming language. The work also includes instructions according to which the model and configuration can be modified so that the simulations can be performed on any device containing the necessary software. From the comparison of the simulated data is it clear that the created configuration can be used for SIL or PIL simulation.

Část této práce pojednává o dopředných neuronových sítích FNN a způsobu jejich vývoje pomocí MATLAB Deep Learning Toolboxu a API Keras v jazyce Python. Následně se práce zabývá převodem těchto sítí do jazyka C/C++ pomocí knihoven Keras2c, AIfES, TFLM a NNoM. Tento teoretický základ byl nezbytný pro navazující část, která je zaměřena na implementaci a testování natrénované FNN na platformě AURIX TC397 3.3V Application Kit. Tato FNN slouží k diagnostice PMS motoru za účelem detekce mezizávitového zkratu. V práci je blíže popsána konfigurace periferií GPT12 a GETH mikrokontroléru AURIX TC397, které byly využity v aplikaci pro testování FNN. S využitím knihovny Keras2c byla ověřena možnost spuštění inference na 2 jádrech mikrokontroléru AURIX a v rámci knihovny NNoM byla provedena kvantizace natrénované FNN. Nakonec bylo provedeno srovnání knihoven Keras2c, AIfES, TFLM a NNoM z hlediska jednoduchosti implementace, přesnosti klasifikace a rychlosti klasifikace na platformě AURIX., Part of this thesis discusses FNNs and how to develop them using MATLAB Deep Learning Toolbox and Keras API in Python. Subsequently, the thesis deals with the conversion of these networks into C/C++ using the Keras2c, AIfES, TFLM and NNoM libraries. This theoretical background was essential for the follow-up section, which focuses on the implementation and testing of the trained FNN on the AURIX TC397 3.3V Application Kit platform. This FNN is used to diagnose the PMS motor in order to detect inter turn faults. The configuration of the GPT12 and GETH peripherals of the AURIX TC397 microcontroller, which were used in the FNN testing application, is described in detail in this thesis. Using the Keras2c library, the possibility of running inference on 2 cores of the AURIX microcontroller was verified and quantization of the trained FNN was performed within the NNoM library. Finally, a comparison of the Keras2c, AIfES, TFLM and NNoM libraries was performed in terms of ease of implementation, classification accuracy and classification speed on the AURIX platform.

Táto diplomová práca sa zaoberá realizáciou SIL a PIL simulácie pre mikrokontrolér Aurix TriCore TC277D vykonávanou v prostredí Matlab/Simulink. Realizácia simulácie predstavuje okrem iného aj implementáciu simulovaného modelu do mikrokontroléra, ako aj tvorbu rozhrania pre komunikáciu mikrokontroléra s programom Matlab Simulink. Správnosť SIL a PIL simulácie bola overená porovnaním simulovaných priebehov zo simulácie v Simulinku. Simulovaným modelom bol použitý tepelný model kabíny automobilu vytváraný v predchádzajúcej bakalárskej práci autora tejto diplomovej práce. Model v TC277D, ako aj konfigurácia pre SIL/PIL je vytvorená pre použitie s programovacím jazykom C. Súčasťou práce je taktiež návod, podľa ktorého je možné model a konfiguráciu upraviť tak, aby bolo možné uvedené simulácie vykonávať na akomkoľvek zariadení obsahujúcom potrebný softvér. Z porovnania odsimulovaných údajov jednotlivých simulácii je jasné, že vytvorenú konfiguráciu je možné použiť pre SIL alebo PIL simuláciu., This diploma thesis deals with the implementation of SIL and PIL simulation for the microcontroller Aurix TriCore TC277D performed in the Matlab Simulink. The realization of the simulation represents, among other things, the implementation of the simulated model into the microcontroller, as well as the creation of an interface for the communication of the microcontroller with the Matlab Simulink. The accuracy of SIL and PIL simulations was verified by comparing the simulated waveforms from the simulation in Simulink. The simulated model used a thermal model of a car cabin created in the previous bachelor's thesis of the author of this diploma thesis. The model in TC277D, as well as the configuration for SIL / PIL is created for use with the C programming language. The work also includes instructions according to which the model and configuration can be modified so that the simulations can be performed on any device containing the necessary software. From the comparison of the simulated data is it clear that the created configuration can be used for SIL or PIL simulation.

Táto diplomová práca sa zaoberá realizáciou SIL a PIL simulácie pre mikrokontrolér Aurix TriCore TC277D vykonávanou v prostredí Matlab/Simulink. Realizácia simulácie predstavuje okrem iného aj implementáciu simulovaného modelu do mikrokontroléra, ako aj tvorbu rozhrania pre komunikáciu mikrokontroléra s programom Matlab Simulink. Správnosť SIL a PIL simulácie bola overená porovnaním simulovaných priebehov zo simulácie v Simulinku. Simulovaným modelom bol použitý tepelný model kabíny automobilu vytváraný v predchádzajúcej bakalárskej práci autora tejto diplomovej práce. Model v TC277D, ako aj konfigurácia pre SIL/PIL je vytvorená pre použitie s programovacím jazykom C. Súčasťou práce je taktiež návod, podľa ktorého je možné model a konfiguráciu upraviť tak, aby bolo možné uvedené simulácie vykonávať na akomkoľvek zariadení obsahujúcom potrebný softvér. Z porovnania odsimulovaných údajov jednotlivých simulácii je jasné, že vytvorenú konfiguráciu je možné použiť pre SIL alebo PIL simuláciu., This diploma thesis deals with the implementation of SIL and PIL simulation for the microcontroller Aurix TriCore TC277D performed in the Matlab Simulink. The realization of the simulation represents, among other things, the implementation of the simulated model into the microcontroller, as well as the creation of an interface for the communication of the microcontroller with the Matlab Simulink. The accuracy of SIL and PIL simulations was verified by comparing the simulated waveforms from the simulation in Simulink. The simulated model used a thermal model of a car cabin created in the previous bachelor's thesis of the author of this diploma thesis. The model in TC277D, as well as the configuration for SIL / PIL is created for use with the C programming language. The work also includes instructions according to which the model and configuration can be modified so that the simulations can be performed on any device containing the necessary software. From the comparison of the simulated data is it clear that the created configuration can be used for SIL or PIL simulation.

Táto diplomová práca sa zaoberá realizáciou SIL a PIL simulácie pre mikrokontrolér Aurix TriCore TC277D vykonávanou v prostredí Matlab/Simulink. Realizácia simulácie predstavuje okrem iného aj implementáciu simulovaného modelu do mikrokontroléra, ako aj tvorbu rozhrania pre komunikáciu mikrokontroléra s programom Matlab Simulink. Správnosť SIL a PIL simulácie bola overená porovnaním simulovaných priebehov zo simulácie v Simulinku. Simulovaným modelom bol použitý tepelný model kabíny automobilu vytváraný v predchádzajúcej bakalárskej práci autora tejto diplomovej práce. Model v TC277D, ako aj konfigurácia pre SIL/PIL je vytvorená pre použitie s programovacím jazykom C. Súčasťou práce je taktiež návod, podľa ktorého je možné model a konfiguráciu upraviť tak, aby bolo možné uvedené simulácie vykonávať na akomkoľvek zariadení obsahujúcom potrebný softvér. Z porovnania odsimulovaných údajov jednotlivých simulácii je jasné, že vytvorenú konfiguráciu je možné použiť pre SIL alebo PIL simuláciu., This diploma thesis deals with the implementation of SIL and PIL simulation for the microcontroller Aurix TriCore TC277D performed in the Matlab Simulink. The realization of the simulation represents, among other things, the implementation of the simulated model into the microcontroller, as well as the creation of an interface for the communication of the microcontroller with the Matlab Simulink. The accuracy of SIL and PIL simulations was verified by comparing the simulated waveforms from the simulation in Simulink. The simulated model used a thermal model of a car cabin created in the previous bachelor's thesis of the author of this diploma thesis. The model in TC277D, as well as the configuration for SIL / PIL is created for use with the C programming language. The work also includes instructions according to which the model and configuration can be modified so that the simulations can be performed on any device containing the necessary software. From the comparison of the simulated data is it clear that the created configuration can be used for SIL or PIL simulation.

Část této práce pojednává o dopředných neuronových sítích FNN a způsobu jejich vývoje pomocí MATLAB Deep Learning Toolboxu a API Keras v jazyce Python. Následně se práce zabývá převodem těchto sítí do jazyka C/C++ pomocí knihoven Keras2c, AIfES, TFLM a NNoM. Tento teoretický základ byl nezbytný pro navazující část, která je zaměřena na implementaci a testování natrénované FNN na platformě AURIX TC397 3.3V Application Kit. Tato FNN slouží k diagnostice PMS motoru za účelem detekce mezizávitového zkratu. V práci je blíže popsána konfigurace periferií GPT12 a GETH mikrokontroléru AURIX TC397, které byly využity v aplikaci pro testování FNN. S využitím knihovny Keras2c byla ověřena možnost spuštění inference na 2 jádrech mikrokontroléru AURIX a v rámci knihovny NNoM byla provedena kvantizace natrénované FNN. Nakonec bylo provedeno srovnání knihoven Keras2c, AIfES, TFLM a NNoM z hlediska jednoduchosti implementace, přesnosti klasifikace a rychlosti klasifikace na platformě AURIX., Part of this thesis discusses FNNs and how to develop them using MATLAB Deep Learning Toolbox and Keras API in Python. Subsequently, the thesis deals with the conversion of these networks into C/C++ using the Keras2c, AIfES, TFLM and NNoM libraries. This theoretical background was essential for the follow-up section, which focuses on the implementation and testing of the trained FNN on the AURIX TC397 3.3V Application Kit platform. This FNN is used to diagnose the PMS motor in order to detect inter turn faults. The configuration of the GPT12 and GETH peripherals of the AURIX TC397 microcontroller, which were used in the FNN testing application, is described in detail in this thesis. Using the Keras2c library, the possibility of running inference on 2 cores of the AURIX microcontroller was verified and quantization of the trained FNN was performed within the NNoM library. Finally, a comparison of the Keras2c, AIfES, TFLM and NNoM libraries was performed in terms of ease of implementation, classification accuracy and classification speed on the AURIX platform.