No abstract

With the development of sensor technology, when facing the explosive growth of large power data, the existing data acquisition and monitoring system (SCADA) is increasingly inadequate in data processing ability and lack of intelligence. In this paper, a novel intelligent monitoring system for power distribution equipment based on cloud edge collaborative computing is designed to effectively improve the efficiency and intelligence of mass data processing. At the edge end, an improved intelligent data acquisition device is adopted as the edge computing node, where the original data is collected and uploaded with variable frequency, in order to enhance the value density of data and reduce the network load and cloud load. In addition, data monitoring cloud platform is designed in the cloud, where a data mining model is established by using Apriori frequent item set algorithm, to provide more accurate monitoring and diagnosis services for upper applications, and guide the edge end to conduct intelligent control of devices. The reliability and performance of the designed system are validated by the intelligent monitoring project of box substation power distribution equipment.

At present, the uncertainty and randomness between equipment are not fully considered in the remaining useful life (RUL) prediction. In order to solve this problem, firstly, we use the Weibull distribution to describe the influence of various uncertain factors on the RUL of equipment, and introduce the Weibull Time-To-Event Recurrent Neural Network (WTTE-RNN) framework to transform the RUL of equipment from the prediction of single life value to the prediction of Weibull distribution parameters. Then, in view of the problem that RNN is prone to have low prediction accuracy due to the vanishing of gradient, considering the advantages of Long-Short Term memory (LSTM) in time series modeling, we replace RNN with LSTM to improve the model and construct WTTE-LSTM model. Furthermore, in order to further improve the model's ability to extract data features, Convolutional Neural Network (CNN) is added after the original data is normalized because of its excellent feature extraction ability, and the time series features extracted by CNN are used as the input of LSTM to construct the WTTE-CNN-LSTM model. Finally, the LSTM life prediction model, WTTE-LSTM model and WTTE-CNN-LSTM model are established by taking a data set from a core component of construction machinery as an example. The results demonstrate that the improved WTTE-CNN-LSTM model has the highest prediction accuracy and the smallest error.

No abstract

Purpose Assembly is the last step in manufacturing processes. The two-sided assembly line balancing problem (TALBP) is a typical research focus in the field of combinatorial optimization. This paper aims to study a multi-constraint TALBP-I (MC-TALBP-I) that involves positional constraints, zoning constraints and synchronism constraints to make TALBP more in line with real production. For enhancing quality of assembly solution, an improved imperialist competitive algorithm (ICA) is designed for solving the problem. Design/methodology/approach A mathematical model for minimizing the weighted sum of the number of mated-stations and stations is established. An improved ICA is designed based on a priority value encoding structure for solving MC-TALBP-I. Findings The proposed ICA was tested by several benchmarks involving positional constraints, zoning constraints and synchronism constraints. This algorithm was compared with the late acceptance hill-climbing (LAHC) algorithm in several instances. The results demonstrated that the ICA provides much better performance than the LAHC algorithm. Practical implications The best solution obtained by solving MC-TALBP-I is more feasible for determining the real assembly solution than the best solution obtained by solving based TALBP-I only. Originality/value A novel ICA based on priority value encoding is proposed in this paper. Initial countries are generated by a heuristic method. An imperialist development strategy is designed to improve the qualities of countries. The effectiveness of the ICA is indicated through a set of benchmarks.