Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: real time computation

Sortuj według:

Ogranicz wyniki do:

Real-time operational load monitoring of a composite aerostructure using FPGA-based computing system

Mucha Waldemar

Bulletin of the Polish Academy of Sciences. Technical Sciences

2024

Vol. 72, nr 1

art. no. e148251

Operational load monitoring (OLM) is an industrial process related to structural health monitoring, where fatigue of the structure is tracked. Artificial intelligence methods, such as artificial neural networks (ANNs) or Gaussian processes, are utilized to improve efficiency of such processes. This paper focuses on moving such processes towards green computing by deploying and executing the algorithm on low-power consumption FPGA where high-throughput and truly parallel computations can be performed. In the following paper, the OLM process of typical aerostructure (hat-stiffened composite panel) is performed using ANN. The ANN was trained using numerically generated data, of every possible load case, to be working with sensor measurements as inputs. The trained ANN was deployed to Xilinx Artix-7 A100T FPGA of a real-time microcontroller. By executing the ANN on FPGA (where every neuron of a given layer can be processed at the same time, without limiting the number of parallel threads), computation time could be reduced by 70% as compared to standard CPU execution. Series of real-time experiments were performed that have proven the efficiency and high accuracy of the developed FPGA-based algorithm. Adjusting the ANN algorithm to FPGA requirements takes some effort, however it can lead to high performance increase. FPGA has the advantages of many more potential parallel threads than a standard CPU and much lower consumption than a GPU. This is particularly important taking into account potential embedded and remote applications, such as widely performed monitoring of airplane structures.

Real-time evolutionary optimization of metallurgical processes using ARM microcontroller

Mrozek A., Kuś W., Sztangret Ł.

Computer Methods in Materials Science

2016

Vol. 16, No. 1

20--26

The real time (RT) computations with the use of microcontrollers have been present in everyday life for years. They are very useful in e.g. online control of processes due to the ability to determine the proper control in case of any environment changes. The algorithms employed in RT computation must be as simple as possible to meet the imposed time limits. On the other hand, the continuous increase in computational power of modern microcontrollers and embedded platforms causes that more complex algorithms can be performed in the real time. However, during implementation of any algorithm the specific structure and requirements of the microcontroller must be taken into consideration. Another way of fulfilling the time limits of the RT computations is application of metamodel instead of model of controlling process. Within this paper the possibility of application of evolutionary algorithm (EA) to solve three chosen optimization problems in real time using microcontroller of ARM architecture was considered. Analyzed optimization problems were as follows: aluminum alloy anti-collision side beam hot stamping process, laminar cooling of dual phase (DP) steel sheets and minimization of the potential energy of the atomic clusters. All computations were performed using two different approaches i.e. low-level and object- oriented approach. Obtained results and drawn conclusions are presented.

W artykule rozważano zastosowanie mikrokontrolerów w optymalizacji parametrów procesów metalurgicznych z użyciem algorytmów ewolucyjnych. Do wyznaczenia wartości funkcji przystosowania użyto metamodeli, zbudowanych w oparciu o funkcje wielomianowe i sztuczną sieć neuronową. Jako platformę testową wykorzystano zestaw uruchomieniowy ST-DISCOVERY. wyposażony w mikrokontroler STM32F429Z1T6 (rdzeń ARM-CortexM4F. architektura ARMv7M). Jest to 32-bitowy jednoukładowy mikrokomputer, wyposażony w sprzętową jednostkę zmiennoprzecinkową pojedynczej precyzji i wszystkie niezbędne peryferia pozwalające tworzyć samodzielny system mikroprocesorowy. Do implementacji algorytmu ewolucyjnego zastosowano dwa podejścia. W pierwszym użyto języka C ze wstawkami asemblera, a w drugim użyto środowiska programowania opartego o Visual Studio oraz bibliotekę .NET Micro Framework. W artykule przedstawiono optymalizację z użyciem metamodelu pozwalającego dobrać parametry procesu gorącego tłoczenia belki samochodowej, chłodzenia laminamego blach ze stali DP po walcowaniu na gorąco oraz minimalizację energii potencjalnej prostych układów kilkuatomowych. Porównano czasy pracy implementacji niskopoziomowej oraz wykorzystującej współczesny język obiektowy.