Wyniki wyszukiwania - Biblioteka Nauki

Nowa wersja platformy, zawierająca wyłącznie zasoby pełnotekstowe, jest już dostępna.
Przejdź na https://bibliotekanauki.pl

Ograniczanie wyników

Znaleziono wyników: 3

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: system czujników

Sortuj według:

Ogranicz wyniki do:

Conception of robotic leg design

100%

Krejci P. , Vlach R. , Grepl R.

Zeszyty Naukowe Katedry Mechaniki Stosowanej / Politechnika Śląska

2006

tom z. 31

95-98

This paper deals with design of robotic leg for biped robot. This robot is developed on Brno University of Technology. This project is motivated by ambitions to improve sensory system of mentioned robot. The robotic leg will by able to inform main control system unit of robot about collisions with another object as well as about characteristic of contact with ground. The sensory system is based on combination between measuring of deformation by strain gages in several positions and using artificial neural network for contact characteristic determination.

Diagnostics of modern diesel engines on the example of Fiat 1.3 JTD MultiJet engine

100%

Prajwowski K.

Journal of KONES

2016

tom Vol. 23, No. 3

403--409

Initially, electronic components replaced the mechanical ones to make various systems more reliable. Mechanical control systems, due to the wear of movable parts and imprecise adjustment, were affected by large errors, which are not shown by electronic circuits operating according to constant set-points. Then, a sharp increase in electronisation was associated with the tightening of exhaust gas emission regulations. Progress in some cases is forced by environmental protection, in other ones by market competition. Modern motor vehicles, slow moving vehicles, military vehicles, etc., are the technical systems being constructed using the latest developments in many fields of science, first of all in mechanics and machine engineering, electrical engineering, electronics, information technology, and chemistry. The rapid development of electronics has led to an increase in the number of electronic components in motor vehicles in all systems, starting with an engine, which has been modified first, to comfort and infotainment systems. The paper presents example measurements of sensors and actuators of an engine with Common Rail fuel supply system on the example of Fiat 1.3 JTD MultiJet engine. The measurements were made using various diagnostic instruments, such as a diagnostic tester, a multimeter or an oscilloscope. Sometimes, the reading of error codes with a diagnostic tester itself is not enough and it is necessary to check the signal waveform with an oscilloscope, which has been presented in this paper.

Continual learning of a time series model using a mixture of HMMs with application to the IoT fuel sensor verification

67%

Głomb P. , Cholewa M. , Foszner P. , Bularz J.

Annals of Computer Science and Information Systems

2023

tom Vol. 35

259--264

This paper presents an application of a mixture of Hidden Markov Models (HMMs) as a tool for verification of IoT fuel sensors. The IoT fuel sensors report the level of fuel in tanks of a petrol station, and are a key component for monitoring system reliability (billing), safety (fuel/oil leak detection) and security (theft prevention). We propose an algorithm for learning a mixture of HMMs based on a continual learning principle, i.e. it adapts the model while monitoring a sensor over time, signalling unexpected or anomalous sensor reports. We have tested the proposed approach on a real-life data of 15 fuel tanks being monitored with the FuelPrime system, where it has shown a very good performance (average area under ROC curve of 0.94) of detecting anomalies in the sensor data. Additionally we show that the proposed method can be used for trend monitoring and present qualitative analysis of the short and long term learning performance. The proposed method has promising performance score, the resulting model has a high degree of explainability, limited memory and computation requirements and can be easily generalized to other domains of sensor verification.