Wyniki wyszukiwania - BazTech

1

Use of Selected Adaptive Models to Forecast Accidents During the Repair, Maintenance, Installation of Machines and Equipment

Małysa Tomasz

Multidisciplinary Aspects of Production Engineering

|

2020

|

Vol. 3, Iss. 1

141--149

EN

In the article the possibility of using selected adaptive models to forecast accidents at work during repairing, maintaining and installing machines, was presented. On the basis of statistical data on persons injured in accidents at work (2009-2018), the process of their forecasting was carried out (for 2019 and the years 2019-2021) and the errors of expired forecasts were determined. Prediction of empirical data allowed for the assessment of accident rates among persons injured in total accidents and allowed for the assessment of the state of occupational safety in the area with was analyzed. The presented models can be used to assess accidents in other sectors of the economy and be a tool used to assess the state of occupational safety in an enterprise.

2

Adaptation of models from determined chaos theory to short-term power forecasts for wind farms

Popławski T., Szeląg P., Bartnik R.

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2020

|

Vol. 68, nr 6

1491--1501

EN

The paper proposes an adaptation of mathematical models derived from the theory of deterministic chaos to short-term power forecasts of wind turbines. The operation of wind power plants and the generated power depend mainly on the wind speed at a given location. It is a stochastic process dependent on many factors and very difficult to predict. Classical forecasting models are often unable to find the existing relationships between the factors influencing wind power output. Therefore, we decided to refer to fractal geometry. Two models based on self-similar processes (M-CO) and (M-COP) and the (M-HUR) model were built. The accuracy of these models was compared with other short-term forecasting models. The modified model of power curve adjusted to local conditions (M-PC) and Canonical Distribution of the Vector of Random Variables Model (CDVRM). Examples of applications confirm the valuable properties of the proposed approaches.

3

Problemy kształtowania technologicznej warstwy wierzchniej w aspekcie odporności na zacieranie. Cz. 1, Prognozowanie zacierania

Wojciechowski Ł.

Tribologia

|

2015

|

nr 5

133--145

PL

Artykuł przedstawia przegląd współczesnej wiedzy dotyczącej mechanizmów inicjujących zacieranie i ocenę stopnia jej wykorzystania w prognozowaniu tego procesu. Wyróżniono pięć podstawowych parametrów/właściwości, które mogą determinować odporność warstwy wierzchniej na ten typ katastroficznego zużywania. Analiza zebranych informacji pozwoliła na stwierdzenie, że w zależności od indywidualnych cech tribosystemu (materiały pary trącej, rodzaj środka smarowego i reżim, w jakim pracuje, środowisko) modele przewidujące początek zacierania mogą bazować na innych przesłankach. Opierając się na takim podejściu do zagadnienia, zaproponowano topologiczną koncepcję kształtowania warstwy wierzchniej o podwyższonej odporności na zacieranie.

EN

The article presents a review of modern knowledge concerning mechanisms of scuffing activation and the evaluation of the level of its application in the prediction of this process. Five basic groups (temperature, debris, energetic, structural and boundary layer durability) of parameters/features were selected that can determine the resistance of the surface layer to this type of catastrophic wear. The analysis of acquired data indicated that models representing the interdependence of individual features of the tribosystem (friction pair materials, the type of the lubricating medium and the regime of its operation, and the environment), which are used to predict the onset of scuffing, can be based on different premises. A topological concept of the surface layer with increased scuffing performance was proposed using this approach. Additionally, a brief terminological analysis of the scuffing definitions was carried out. Some inaccuracies appearing in the scientific works in the context of determining scuffing were indicated.

4

Ranked designing of prognostic neural models for survival data

Bobrowski L., Krętowska M.

Biocybernetics and Biomedical Engineering

|

2002

|

Vol. 22, no. 2-3

223-239

EN

The procedure of designing the non-linear dependencies of survival time on a family of covariates is described in the paper. This dependence is treated as a prognostic model. The first stage of this procedure involves designing such layers of formal neurons which are ranked with respect to selected subsets of censored data. The model based on the hierarchical networks of formal neurons results in the piecewise constant dependence of the survival time on the covariates. The replacement of the formal neurons by the logistic ones made it possible transform this dependence into differentiable, regression-type function.