Accurate State of Health (SOH) estimation of battery systems is critical to vehicle operation safety. However, it's difficult to guarantee the performance of a single model due to the unstable quality of raw data ...
详细信息
Accurate State of Health (SOH) estimation of battery systems is critical to vehicle operation safety. However, it's difficult to guarantee the performance of a single model due to the unstable quality of raw data obtained from lithium-ion battery aging and the complexity of operating conditions in actual vehicle operation. Therefore, this paper combines a long short-term memory (LSTM) network with strong temporality, and support vector regression (SVR) with nonlinear mapping and small sample learning. A novel LSTM-SVR combined model with strong input features, less computational burden and multiple advantage combinations is proposed for accurate and robust SOH estimation. The nonlinear constraint optimization is used to assign weights to individual models in terms of minimizing the sum of squared errors of the combined models, which can combine strengths while compensating for weaknesses. Furthermore, voltage, current and temperature change curves during the battery charging were analyzed, and indirect health features (IHFs) with a strong correlation with capacity decline were extracted as model inputs using correlation analysis and principal component analysis (PCA). The NASA dataset was used for validation, and the results show that the LSTM-SVR combined model has good SOH estimation performance, with MAE and RMSE all less than 0.75% and 0.97%.
This study emphasizes a multi-pronged approach to improving the energy efficiency of Multi-Effect Evaporator (MEE) in the paper industry. By incorporating traditional Energy-Saving Schemes (ESSs) and innovative renewa...
详细信息
This paper presents a comprehensive analysis of performance characteristics under varying load condition for asynchronous generator. Performance of asynchronous generator depends on variation in prime mover speed, exc...
详细信息
This paper presents a comprehensive analysis of performance characteristics under varying load condition for asynchronous generator. Performance of asynchronous generator depends on variation in prime mover speed, excitation capacitance and load. Estimation of magnetic characteristics involve complicated mathematical computation due to nonlinear nature of magnetization curve. It provides an opportunity to model nonlinear magnetization characteristics to get optimum impedance and optimal capacitance for better performance of asynchronous generator. The nonlinearity of magnetization curve has been analyzed by employing regression functions to estimate magnetization reactance. Thus, optimal value of magnetization reactance is obtained to calculate performance variables of asynchronous generator. Proposed technique provide optimal values of performance variables of asynchronous generator as compared to conventional piecewise linearization model. The effect of solution technique has been discussed while calculating performance variables of asynchronous generator at optimal value of magnetization reactance. Proposed technique of regression function and solution technique is applied on comprehensive data of induction machines as asynchronous generator to prove its validity and accuracy. (C) 2016 Karabuk University. Publishing services by Elsevier B.V.
The consumer's demand of more reliable and economic sources has made an impact on the new competitive electricity markets. In this regard, the accurate operation management of Micro-Grid (MG) with various types of...
详细信息
The consumer's demand of more reliable and economic sources has made an impact on the new competitive electricity markets. In this regard, the accurate operation management of Micro-Grid (MG) with various types of renewable power sources (RES) can be an effective approach. This paper presents a novel solution methodology based on Teacher-Learning-Based optimization (TLBO) algorithm to solve the optimal energy management of MG including several RESs with the back-up of Fuel Cell (FC), Wind Turbine (WT), photovoltaic (PV) and Micro Turbine (MT). Moreover, storage devices have been considered to meet the energy mismatch. The solution of this nonlinear constraint optimization problem minimizes the total cost of the grid and RESs, concurrently. Nevertheless, in finding the optimal solution, the interactive effects of MG and utility in a 24 hour time interval are taken into consideration which would increase the complexity of the problem intensely. In order to explore the total search space globally, a modification method is proposed which is compromised of two modification methods based on TLBO. In the end, the suggested algorithm is tested through a typical renewable MG as the test system to demonstrate the superiority of the proposed method over the other well-known algorithms.
This paper considers several single-server two-class queueing systems with different cost functions. Customers in the two classes are discriminated by service rates and relative priorities. Most attention is focused o...
详细信息
This paper considers several single-server two-class queueing systems with different cost functions. Customers in the two classes are discriminated by service rates and relative priorities. Most attention is focused on the ones with general quadratic bivariable and exponential cost functions that are usually applied in the relatively complicated systems. To the best of the authors' knowledge, there is no literature analyzing these two kinds of cost functions on the Subject of relative priority. We explicitly present the conditions under which relative priority outperforms absolute priority for reducing system cost and further provide the method to find the optimal DIPS policy. Moreover, we also discuss variations where service rates of the two classes are decision variables under service equalization and service discrimination disciplines, respectively. (C) 2009 Elsevier Inc. All rights reserved.
Nonmechanical beam steering technologies utilizing acousto-optics enable us to achieve the high-bandwidth laser beam positioning required for optical communications, laser scanners, ladars, etc. The properties of the ...
详细信息
Nonmechanical beam steering technologies utilizing acousto-optics enable us to achieve the high-bandwidth laser beam positioning required for optical communications, laser scanners, ladars, etc. The properties of the Bragg cell, which are chiefly responsible for the efficiency and attainable characteristics of the entire positioning system, are ensured by the successful design of this optical component. However, the design of Bragg cells is dominated by the experience and intuition of the designers, and the potential of this technology is not fully utilized. An optimal Bragg cell design problem is formulated on the basis of known equations of the underlying physical phenomena, and a genetic optimization scheme is applied for the solution of the resulting formidable problem. The approach not only yields a design solution, but also enables one to vary the design criterion and emphasize particular properties of the resultant component. The prowess of the proposed approach is demonstrated by design optimization examples. (C) 2002 Society of Photo-Optical Instrumentation Engineers.
Non-mechanical beam steering technologies, utilizing acousto-optics, allow for achieving the high bandwidth laser beam positioning required for optical communications, laser scanners, LADARs, etc. Properties of the Br...
详细信息
ISBN:
(纸本)0819441589
Non-mechanical beam steering technologies, utilizing acousto-optics, allow for achieving the high bandwidth laser beam positioning required for optical communications, laser scanners, LADARs, etc. Properties of the Bragg cell, chiefly responsible for the efficiency and attainable characteristics of the entire positioning system, are assured by successful design of this optical component. However, design of Bragg cells is dominated by experience and intuition of the designers and the potential of this technology is not fully utilized. An optimal design problem of a Bragg cell is formulated on the basis of known equations of the underlying physical phenomena, and a genetic optimization scheme is applied for the solution of the resultant formidable problem. The approach not only yields a design solution, but also allows for the variation of the design criterion and emphasizing particular properties of the resultant component. The prowess of the proposed approach has been demonstrated by design optimization examples.
暂无评论