This paper identifies and studies five match-tracking (MT) methods in the adaptive resonance theory (ART) literature and conducts a detailed comparative analysis of these in ARTMAP applications. We focus on model perf...
详细信息
Service robots are expected to autonomously perform a wide range of service tasks to satisfy users' needs, but are limited in practice by their weak decision-making capabilities. This work introduces a Knowledge A...
Service robots are expected to autonomously perform a wide range of service tasks to satisfy users' needs, but are limited in practice by their weak decision-making capabilities. This work introduces a Knowledge Acquisition Framework (KAFS) to help robots make autonomous decisions through this knowledge. This framework is divided into two parts: service knowledge acquisition and scene knowledge construction and uses a variety of intelligent methods to easily and accurately acquire a large amount of service and scene knowledge. We demonstrate the knowledge acquired by KAFS and validate the effectiveness of KAFS on robot service tasks.
Up to 75% of the geometric errors in milling processes can be traced back to the thermal expansions in high-speed motorized spindles due to changing operation conditions. In this study, we investigate various machine ...
详细信息
ISBN:
(数字)9798331508494
ISBN:
(纸本)9798331508500
Up to 75% of the geometric errors in milling processes can be traced back to the thermal expansions in high-speed motorized spindles due to changing operation conditions. In this study, we investigate various machine learning approaches to predict the thermal error and hereby improve the milling accuracy. First, we introduce an industrial dataset of milling processes with varying operation conditions. Second, we propose a hybrid model to combine physical domain knowledge with deep learning to reduce the amount of data required for successful prediction of the thermal error. Last, we evaluate the performance of the proposed models and benchmark our hybrid approach against established machine learning models. On unseen data, the best model of our study achieves a R 2 score of 0.96.
To optimize energy consumption is one of the major issues in wastewater treatment while maintaining effluent water quality standards. Aeration in biological processes requires more energy in wastewater treatment plant...
详细信息
ISBN:
(纸本)9781728190488
To optimize energy consumption is one of the major issues in wastewater treatment while maintaining effluent water quality standards. Aeration in biological processes requires more energy in wastewater treatment plants than other processes. In this study, simulations were conducted by using the ASM2d module of GPS-X. Several control strategies-namely, on/off dissolved oxygen control, proportional (P) / integral (I) dissolved oxygen control, and cascade ammonia control-are performed in biological processes to confirm the effects of ammonia reduction and optimize energy cost. According to the results of cascade control, it is 23 % smaller than the original energy cost. Sensitivity analysis was further proceeded to confirm the influence of tuning parameters, namely, proportional and integral gains. Consequently, proportional gain improves response speed and controls system accuracy. Integral gain is effective in decreasing the steady-state error of the system. The optimized values of proportional and integral gains lead to the best performance of aeration and provides a reference for first-phase plant operation.
The electromagnetic force in the magnetic levitation system is highly nonlinear, and the leakage flux brings in tremendous error to the conventional empirical formula, which makes the force feedback hard to use in a p...
详细信息
In this paper, adaptive backstepping control is investigated for coupled nonlinear springs. A dynamic model of coupled special nonlinear springs is established with uncertain parameters. The conventional adaptive appr...
In this paper, adaptive backstepping control is investigated for coupled nonlinear springs. A dynamic model of coupled special nonlinear springs is established with uncertain parameters. The conventional adaptive approaches for nonlinear systems’ control use Lyapunov’s second method that need full state estimation. To overcome this problem an FPI-based Model Reference Adaptive Backstepping controller has been invented. The adaptive backstepping algorithm is designed to achieve stability for the nonlinear system. The idea of backstepping design is to coerce the error signal to zero by implementing a virtual control strategy. The consequences of the unknown parameters of the system are compensated by adaptive law. Simulation results are presented to show the effectiveness of the proposed control.
Medical data is a valuable resource that is under privacy constraints and often requires a substantial effort and cost to obtain. This is the case for physiological cardiovascular data that is among others utilized to...
详细信息
ISBN:
(数字)9798331508333
ISBN:
(纸本)9798331508340
Medical data is a valuable resource that is under privacy constraints and often requires a substantial effort and cost to obtain. This is the case for physiological cardiovascular data that is among others utilized to develop assistive heart devices. In the present work, we aim to improve a GAN based generative approach from the literature by integrating physiological knowledge in form of pressure-value curves together with a dynamic time warping cost function into the model. We demonstrate that our adapted model generates more realistic cardiovascular signals as measured by targeted physiological markers and showcase that such generated signals can be used to improve a downstream task on real data.
Conventional aircraft encounter aerodynamic limitations at small scales and low Reynolds numbers, restricting the coordination of factors such as lift and thrust generation, flapping motion patterns, and flapping freq...
详细信息
Model-based therapy generation can open new horizons in medicine. Cancer chemotherapy can be optimized using control theoretic methods based on mathematical models of tumor growth. We carry out the qualitative analysi...
详细信息
ISBN:
(纸本)9781665426848
Model-based therapy generation can open new horizons in medicine. Cancer chemotherapy can be optimized using control theoretic methods based on mathematical models of tumor growth. We carry out the qualitative analysis of such a model using the simplest control scheme, i.e., P type control. We look for bifurcations for realistic values of tumor parameters. We show that it is possible to have bifurcations in the closed-loop system, and the qualitative behaviour depends on the initial conditions, and it is independent of the control gain. The analysis shows that the system has rich dynamics and the model can be used to reproduce complex phenomena occurring during real therapies.
Moving horizon estimation (MHE) is a well-known alternative to Kalman-like filtering due to its superior performance in terms of estimation accuracy, convergence speed, and robustness to poor initial state guesses. Ho...
详细信息
暂无评论