Search

Distributed power networks have a large number of photovoltaic power sources. The bidirection of power flow, different transient control strategies, and installation locations make the transient characteristics highly complex and unpredictable. The vast network of the distribution system makes it almost impossible to predict the electrical quantities of each branch. Reasonable aggregation modeling of the distribution network can greatly simplify the network topology, facilitating transient control and the setting of relay protection settings. An aggregated equivalent modeling method based on the LSTM neural network for distributed PV fault external characteristics is proposed. This method equates the complex distribution network to a highly nonlinear but controllable current source. The method can output the I–V curves of equivalent PV system parallel points under any output power and is able to predict the fault characteristics of the equivalent system after a voltage drop at the parallel point. Compared to traditional mechanistic modeling, this method does not require specific modeling of complex physical systems and is able to accurately map the strong nonlinear inputs and outputs of distribution networks. The established LSTM model first uses a one-dimensional convolutional layer for feature extraction of the PV power coefficients (input), and then two hidden layers are utilized to process the sequence data; the vectors are mapped into a sequence of external characteristic curves (output) in a fully connected layer. A typical distribution network is built based on the traditional PV power model, and a large number of different output combinations are selected for simulation to provide an effective training set and validation set data for LSTM model training. By using the training set data, the weights and offset coefficients of each layer of the LSTM are continuously optimized until the model with the smallest overall error is obtained, which is the optimal model. Finally, the optimal model is utilized to establish an equivalent distribution network system, different degrees of voltage drops are set up at the grid-connected points, the fault characteristics are compared with those of the complete model, and the simulation results can prove the reliability and practicality of the proposed method. [ABSTRACT FROM AUTHOR]

In order to research the effect of the steel fiber volume and the rubber powder diameter on the mechanics performance of the layer steel fiber reinforced rubber concrete, the cube compression tests, splitting tensile tests and four-point bending tests are performed on steel fiber reinforced rubber concrete with steel fiber content of 0.5%, 1%, 1.5%, 2%, 2.5% and rubber powder mesh 20, 40, 60. When 40 mesh rubber powder is added and the volume ratio of steel fiber is 1.5%, the compressive strength of laminated steel fiber rubber concrete reaches the peak value. The splitting tensile strength of laminated steel fiber rubber concrete mixed with2.0% steel fiber and mesh 40 rubber powder is the best. The flexural strength of laminated steel fiber rubber concrete mixed with 2.5% steel fiber and mesh 40 rubber powder is highest in this paper.

The task personalized recommendation problems in software crowdsourcing systems have unique characteristics, i.e., large task flow, high task complexity, long development cycle, winning task competitions, professional ability requirements, etc. However, existing software crowdsourcing recommendation mechanisms do not consider the contextual information of crowdsourcing tasks. In particular, the effects of crowdsourcing workers' interest changes and capability constraints on task selection are usually ignored. Therefore, this study proposes a new worker capability-correction long- and short-term attention network (CLSAN) recommendation framework. Firstly, explicit and implicit features are obtained from the feature data of crowdsourcing workers and historical crowdsourcing tasks. The long-term and short-term feature layers are extracted by adding LSTM to the historical tasks; the attention weight of user preference is calculated by integrating the attention mechanism to obtain each user's personalized preference. Secondly, this study considers that the capabilities of the worker need to be matched with the skills required for the software task. We design a worker capability correction model that uses Word2Vec software to obtain competency similarities between crowdsourcing workers and tasks, thereby determining the priority of tasks that satisfy the worker's capability. The experimental results show that CLSAN can accurately evaluate the changes of interest preferences of crowdsourcing workers, and effectively improve the quality and efficiency of crowdsourcing recommendations. [ABSTRACT FROM AUTHOR]