In paper, forecasting models using Prophet algorithm for occupational diseases incidence rate for Polish coal mining are presented. Prior to this, data is analyzed and approach for building forecasting models in Proph...
In paper, forecasting models using Prophet algorithm for occupational diseases incidence rate for Polish coal mining are presented. Prior to this, data is analyzed and approach for building forecasting models in Prophet is described in details. Forecasting models for occupational diseases incidence rate are revealed, respectively for all sectors in Poland, mining industry and finally for coal mining including only pneumoconiosis. Improved forecast accuracy with presented models might provide coal mine enterprises more precise data, supporting safety management in those organizations.
the error-based active disturbance rejection control (EADRC) structure is investigated to obtain precise tracking control of a mechanical system with one degree of freedom. We formally take into account the uncertaint...
the error-based active disturbance rejection control (EADRC) structure is investigated to obtain precise tracking control of a mechanical system with one degree of freedom. We formally take into account the uncertainty of the input gain, which affects the performance of the controller, and consider stability of the closed-loop system for the full-order and reduced-order extended-state observers (ESOs). Apart from theoretical analysis, we present experimental results, which confirm that the application of the reduction-order observer can improve control performance. We also investigate whether the explicit formulation of the feedforward in EADRC makes it possible to improve the tracking precision under real conditions.
Gaussian processes (GP) are becoming more and more popular way to solve statistics and machine learning problems. One of the reasons is the increase in computational power that can handle the inherent computational pr...
Gaussian processes (GP) are becoming more and more popular way to solve statistics and machine learning problems. One of the reasons is the increase in computational power that can handle the inherent computational problem for GP models. Still, in the case of big data, the computational burden can be impractical. For this reason, various approximation methods are *** our work, we would like to present an alternative to the internal approximation by using the properties of Chebyshev polynomials. the idea is to calculate the GP model only at Chebyshev nodes and use the property of transforming function values in them to Chebyshev coefficients giving a solution to the original problem. In our research, we propose our version of the algorithm and test it on cases of various functions.
A high roll rate can decrease the chance of the research-oriented rocket mission success. there is scant information about the effective roll-motion stabilizer solutions for sounding rockets. thus, a roll-motion stabi...
A high roll rate can decrease the chance of the research-oriented rocket mission success. there is scant information about the effective roll-motion stabilizer solutions for sounding rockets. thus, a roll-motion stabilizer for a sounding rocket using the active disturbance rejection control (ADRC) methodology is proposed. the presented roll-motion stabilizer is designed for a subsonic sounding rocket. An effectiveness of the designed control system was verified by simulations and experiments in a wind tunnel. Results of the verification show that the designed control system enables robust roll-motion stabilization despite large uncertainty of a rocket model. Practical guidelines for designing of the roll-motion stabilizer are provided.
Object detection in 3D is a crucial aspect in the context of autonomous vehicles and drones. However, prototyping detection algorithms is time-consuming and costly in terms of energy and environmental impact. To addre...
Object detection in 3D is a crucial aspect in the context of autonomous vehicles and drones. However, prototyping detection algorithms is time-consuming and costly in terms of energy and environmental impact. To address these challenges, one can check the effectiveness of different models by training on a subset of the original training set. In this paper, we present a comparison of three algorithms for selecting such a subset – random sampling, random per class sampling, and our proposed MONSPeC (Maximum Object Number Sampling per Class). We provide empirical evidence for the superior effectiveness of random per class sampling and MONSPeC over basic random sampling. By replacing random sampling with one of the more efficient algorithms, the results obtained on the subset are more likely to transfer to the results on the entire dataset. the code is available at: https://***/vision-agh/monspec.
In the Two Rotor Aerodynamical System the aim of the control is to achieve the azimuth and pitch angles reference values. However, TRAS is a non-linear system in which cross-coupling occurs - each of the two rotors af...
In the Two Rotor Aerodynamical System the aim of the control is to achieve the azimuth and pitch angles reference values. However, TRAS is a non-linear system in which cross-coupling occurs - each of the two rotors affects both angular values. therefore, to prepare two control values one should use both angular values for each of them. the obvious solution is a system that uses four controllers. In the article it was decided to use only FOPID and to check the behavior of the system in three different arrangements: parallel, cascade and hybrid. the tests were carried out in the Matlab / Simulink environment. For optimization purposes the Grey Wolf Optimizer algorithm was used, which helped to find coefficients.
In this paper, we deal withthe problem of self-collision detection for a mobile-manipulating robot. Typically, this problem is solved by the method that precisely checks the collision between triangles in the 3D mesh...
In this paper, we deal withthe problem of self-collision detection for a mobile-manipulating robot. Typically, this problem is solved by the method that precisely checks the collision between triangles in the 3D meshes. In this case, the iterative methods for collision checking use techniques like Bounding Volume Hierarchy that reduce the computation time. However, collision checking is still time-consuming during motion planning when this procedure is executed multiple times. To deal withthis problem, we propose to define collision detection as a binary classification problem. then, we show how to collect samples to train the machine learning model for classification. We systematically compare a set of techniques and evaluate them in the task of motion planning for a robotic arm taking into account the accuracy and computation time. the obtained collision classifier is implemented and verified in the Robot Operating System.
this paper presents a solution to the set-point control problem for nonholonomic mobile robots in the presence of time and control input constraints. We consider the kinematics of a unicycle mobile robot, in which the...
this paper presents a solution to the set-point control problem for nonholonomic mobile robots in the presence of time and control input constraints. We consider the kinematics of a unicycle mobile robot, in which the constraints on the control inputs are longitudinal and angular velocity limitations, while the time constraints impose an upper bound on a settling time for stabilization errors. We show a solution based on the Vector-Field-Orientation (VFO) methodology, which is characterized by non-oscillatory transient states and well-predictable time evolution of these states. Formally derived upper bounds of settling time for configuration errors are verified by results of numerical simulations and experimental results obtained in a fast prototyping system.
the aim of this paper is to check whenever usage of sequence based neural networks for predicting compressed air demand can be useful in screw compressor room supervisory control systems. Industrial enterprises freque...
the aim of this paper is to check whenever usage of sequence based neural networks for predicting compressed air demand can be useful in screw compressor room supervisory control systems. Industrial enterprises frequently employ compressed air systems to generate the compressed air needed for daily operations. Data was gathered from three different compressor rooms with different air demand characteristics and configuration over the period of one month. then data was prepared, analyzed, trained and tested followed by simulation tests which determined usefulness of trained networks. Since nowadays high energy prices force energy saving build of the screw compressor itself the purpose of this text was to check if there is any room for optimization in less modern and also modern applications.
One of the most critical challenges in Robotic Eye Surgery (RES) is the applied force of the surgical instrument of the robot as it penetrates the human eye. Safe surgery requires accurate control of this force. In a ...
One of the most critical challenges in Robotic Eye Surgery (RES) is the applied force of the surgical instrument of the robot as it penetrates the human eye. Safe surgery requires accurate control of this force. In a teleoperated eye surgical system, there is likely to be a time delay that can affect the system control. this paper focuses on designing a predefined-time Sliding Mode Control (SMC) method to control a teleoperated robotic eye surgical system under an unknown time delay of the communication channel. the Lyapunov theory is used to prove the system stability. For the master and slave parts, manipulator robots are considered for designing and testing the controller. MATLAB software is used to simulate the controller. the simulation results show the robustness of the controller against the time delay of the communication channel.
暂无评论