Surrogate model enabled deep reinforcement learning for hybrid energy community operation

In recent years, electromagnetic compatibility (EMC) has become progressively important because of the rise in the number of electronic auxiliary devices in motor vehicles. This article presents an angle modulated switching strategy for fractional horsepower drives. It allows decreasing the size of the necessary EMC filter, for the example case drive used, down to less than 50%, from nine to four capacitors. Simultaneously, it reduces the radiated electromagnetic emissions over a wide frequency range by almost 10 $\,\text{dB}_{\mu \text{V/m}}$ . The EMC measurements performed in a shielded chamber are compared with the results for two conventional switching strategies. Subsequently, the influence of the presented switching strategy on the efficiency and on the emitted airborne and structure-borne noise is investigated.

Analysis of the Angle Modulated Switching Strategy for use With Fractional Horse Power BLDC Motors

This study presents an automatic network balancing technique to limit the capacitive unbalance in resonant grounded power distribution systems (RGPDSs). The aim of this capacitive balancing technique is to minimise the unbalance current through the line to ground (which is the current through the neutral of the system) in order to automatically limit the neutral voltage. The proposed technique is designed by combining the weighted-sum technique and genetic algorithm (GA), where distributed switched capacitor banks (SCBs) are used for balancing RGPDSs. The proposed technique is employed to optimise available SCBs for limiting the network unbalance at the substation under a pre-defined threshold considering all possible network configurations. The unbalances at different locations of the network are also minimised to limit the system unbalance within the threshold due to minor changes in network parameters. Since the lifetime of capacitor banks relies on the switching, the proposed technique is designed in such a way that the system balance is achieved with the minimum switching. The performance of the proposed technique is evaluated through simulation studies in MATLAB/SimpowerSystems environment. Simulation results show that the proposed technique works well and capable to maintain the capacitive balance of the system with changes in network configurations.

Automatic network capacitive balancing technique for resonant grounded power distribution systems

Performance prediction and multi-objective optimization of metal seals in roller cone bits

The shearer drum undertakes the main function of coal falling and loading, and picks distributed on it have a great impact on the performance of the drum. However, few studies have optimized the pick and drum at the same time. In this paper, parameters of pick and drum are considered as design variables, and the response functions of design variables are established based on the central composite experiment method. The optimal structural and working parameters of the pick and the drum of MG500/1130-WD shearer are obtained by using the multi-objective bat algorithm and multi-objective bat algorithm with grid, respectively. Comparing results of the two algorithms, the multi-objective bat algorithm with grid is more effective in improving the comprehensive performance of the drum. According to the optimized design variables, a coal mining test is carried out to verify the optimization effect of the algorithm. The result provides some theoretical references for the design and production of the drum and has some engineering application value.

/pdf/optimization-of-shearer-drum-based-on-multi-objective-bat-r7gursve.pdf

Optimization of Shearer Drum Based on Multi-Objective Bat Algorithm with Grid (MOBA/G)

This paper develops an improved non dominated sorting genetic algorithm II (NSGA-II) based on objective importance vector γ, abbreviated as γ-NSGA-II. Different importance levels for the multiple objectives are incorporated in the objective importance vector, which is applied to determine the individual selection of sorting individuals in the critical layer. And such an individual selection strategy is developed to the NSGA-II algorithm in order to obtain the optimized solution for a task which has multiple objectives with different importance. The differences between the γ-NSGA-II algorithm and the traditional NSGA-II algorithm are discussed in detail. A notch filter is designed for the conducted emission suppression of a transformer rectifier unit (TRU) used in C919 flight testing, and then the parameters optimization design of a notch filter is discussed and conducted based on the γ-NSGA-II algorithm. The non-linear relationship between the filter's parameters and the suppression effect of the conducted emission is also discussed with the help of an electromagnetic compatibility (EMC) evaluation model based on a back propagation (BP) neural network. The experimental results show that the optimized design of the notch filter is effective and the improved γ-NSGA-II algorithm be more specific.

/pdf/multi-objective-optimization-design-of-a-notch-filter-based-1go09468dj.pdf

Multi-Objective Optimization Design of a Notch Filter Based on Improved NSGA-II for Conducted Emissions

The invention discloses an EMC evaluation model and Gamma-NSGA-II-based conduction interference trap multi-objective optimization design method and relates to the field of electromagnetic compatibility and a genetic algorithm improvement strategy. An EMC evaluation model is established on the basis of a BP neural network, and a conduction emission signal margin value and a total harmonic distortion rate which represent a conduction interference suppression effect are calculated. By taking the margin value, the total harmonic distortion rate, the weight of the wave trap and the cost as optimization objectives, an optimization objective vector Gamma containing an objective importance order is introduced. The Gamma-NSGA-II algorithm is used to continuously evolve the optimal parameters of interference trap. Compared with NSGA-II, when the critical layer individuals are selected, dimensionality reduction is performed on the optimization target vectors according to importance, then rapidnon-dominated sorting is carried out on the critical layer individuals. The trap parameter optimization design method provided by the invention can be selected for inhibiting conduction interference,reducing the weight of the trap, reducing the cost and the like, and is high in scientificity and good in practicability.

Lu Zhang

Papers

Multi-Objective Optimization Design of a Notch Filter Based on Improved NSGA-II for Conducted Emissions

EMC evaluation model and Gamma-NSGA-II-based conduction interference trap multi-objective optimization design method