Wyniki wyszukiwania - BazTech

1

Evolutionary and Sparse Regression Approach for Data-Driven Modelling of an Overhead Crane Dynamics

Kusznir Tom, Smoczek Jarosław, Karwat Bolesław

Advances in Science and Technology. Research Journal

|

2024

|

Vol. 18, no 4

282--295

EN

Identification of an accurate and simple model of a complex underactuated crane dynamics for varying operational conditions is a crucial step towards designing and implementation of real-time monitoring and control systems to enhance crane safety and operational efficiency. This paper considers a non-parametric data-driven identification of an overhead crane dynamics using symbolic regression techniques to find compromise between model complexity and predicted output accuracy. A grammar-guided genetic programming (G3P) combined with l0 sparse regression is applied with two different variants of grammar to automatically construct a nonlinear autoregressive exogenous (NARX) model of different forms, termed extended and polynomial models. The proposed method is compared with a linear parameter-varying ARX (LPV-ARX) model. Identification is performed on experimental data obtained from a laboratory-scale overhead crane. The identified models are compared in terms of prediction accuracy, model’s complexity measured using number of model terms, and execution time. The regularized G3P method outperformed the LPV-ARX model in terms of model predictive output accuracy. The G3P with the extended grammar resulted in more accurate crane velocity prediction models than the models with the polynomial grammar. The payload sway prediction model with the polynomial grammar was less complex in all measured metrics while there was no statistical significance in the accuracy when compared to the models with extended grammar.

2

Data-driven online modelling for a UGI gasification process using modified lazy learning with a relevance vector machine

Liu Shida, Ji Honghai, Hou Zhongsheng, Zuo Jiashuo, Fan Lingling

International Journal of Applied Mathematics and Computer Science

|

2021

|

Vol. 31, no. 2

321--335

EN

A modified lazy learning algorithm combined with a relevance vector machine (MLL-RVM) is presented to address a data-driven modelling problem for a gasification process inside a united gas improvement (UGI) gasifier. During the UGI gasification process, the measured online temperature of the produced crude gas is a crucial aspect. However, the gasification process complexities, especially severe changes in the temperature versus infrequent manipulation of the gasifier and the unknown noise in collected data, pose difficulties in dynamics process descriptions via conventional first principles. In the MLL-RVM, a novel weighted neighbour selection method is adopted based on the proposed dynamic cost functions. Moreover, the RVM is utilized in the implementation and design of the proposed online local modelling owing to its short test time and sparseness. Furthermore, the leave-one-out cross-validation technique is used for local model validation, by which the modelling performance is further improved. The MLL-RVM is applied to a series of real data collected from a pragmatic UGI gasifier, and its effectiveness is verified.

3

Data-driven discharge analysis: a case study for the Wernersbach catchment, Germany

Popat Eklavyya, Kuleshov Alexey, Kronenberg Rico, Bernhofer Christian

Meteorology Hydrology and Water Management. Research and Operational Applications

|

2020

|

Vol. 8, Iss. 1

54--62

EN

This study focuses on precipitationdischarge data-driven models, with regression analysis between the weighted maximum rainfall and maximum discharge of flood events. It is also the first of its kind investigation for the Wernersbach catchment, which incorporates data-driven models in order to evaluate the suitability of the model in simulating the discharge from the catchment and provide good insights for future studies. The input parameters are hydrological and climate data collected from 2001 to 2009, including precipitation, rainfall-runoff and soil moisture. The statistical regression and artificial neural network models used are based on a data-driven multiple linear regression technique, and the same input parameters are applied for validation and calibration. The artificial neural network model has one hidden layer with a sigmoidal activation function and uses a linear activation function in the output layer. The artificial neural network is observed to model 0.7% and 0.5% of values, with and without extreme values respectively. With less than 1% error, the artificial neural network is observed to predict extreme events better compared to the conventional statistical regression model and is also better suited to the tasks of rainfall-runoff and flood forecasting. It is presumed that in the future this study’s conclusions would form the basis for more complex and detailed studies for the same catchment area.

4

Some characteristic wave energy dissipation patterns along the Polish coast

Różyński G., Szmytkiewicz P.

Oceanologia

|

2018

|

No. 60 (4)

500--512

EN

The paper analyses cross-shore bathymetric profiles between Władysławowo (km 125 of the national coastal chainage) and Lake Sarbsko (km 174) commissioned in 2005 and 2011 by coastal authorities for monitoring purposes. The profiles, spaced every 500 m, cover beach topography from dune/cliff tops through the emerged beach to a seabed depth of about 15 m. They were decomposed by signal processing techniques to extract their monotonic components containing all major modes of the variability of beach topography. They are termed empirical equilibrium profiles and can be used for straightforward assessment of wave energy dissipation rates. Three characteristic patterns of wave energy dissipation were thus identified: one associated with large nearshore bars and several zones of wave breaking; a second, to which the equilibrium beach profile concept can be applied; and a third, characterized by mixed behaviour. Interestingly, most profiles showed significant seabed variations beyond the nearshore depth of closure – this phenomenon requires comprehensive studies in future.

5

Local Wave Energy Dissipation and Morphological Beach Characteristics along a Northernmost Segment of the Polish Coast

Różyński G.

Archives of Hydro-Engineering and Environmental Mechanics

|

2018

|

Vol. 65, nr 2

91--108

EN

This paper analyses cross-shore bathymetric profiles between Władysławowo (km 125 of the Polish coastal chainage) and Lake Sarbsko (km 174) done in 2005 and 2011. Spaced every 500 m, they cover beach topography from dune/cliff crests to a seabed depth of about 15 m. They were decomposed by signal processing techniques to extract the monotonic component of beach topography and to perform a straightforward assessment of wave energy dissipation rates. Three characteristic dissipation patterns were identified: one associated with large nearshore bars and 2–3 zones of wave breaking; a second, to which the equilibrium beach profile concept can be applied; and a third, characterized by mixed behaviour. An attempt was then made to interpret these types of wave energy dissipation in terms of local coastal morphological features and the underlying sedimentary characteristics.