The reliability of a high-capacity power transformer is fundamental to the stable operation of power systems. However, characterization of the transformer aging process is a difficult task, considering the diverse aging factors in its life cycle. This prevents effective management of such equipment. In the work, we study the aging phenomenon of power system transformers, whose representative degeneration variables are extracted from real transformer operational data. Combining with the average life of the equipment, the extracted features are used as indicators for the transformer reliability evaluations. We developed a deep learning–based approach using a convolutional neural network for effective equipment life prediction. The performance of the transformer life prediction model is verified using field-test data, which demonstrates the superior accuracy of the presented approach.

Presently, the State Grid Corporation of China has accumulated a large amount of maintenance records for power primary equipment. Unfortunately, most of these records are unstructured data which lead to difficultly analyze and utilize them. The emergence of natural language processing technology and deep learning methods provide a solution for unstructured text data. This paper proposes a progressive multitype feature fusion model to recognize Chinese named entity of unstructured maintenance records for power primary equipment. Firstly, the textual characteristics and word separation difficulties of maintenance records are analyzed, then 7 main entity categories of power technical terms from unstructured maintenance records are chosen, and 3452 maintenance records are labeled by these categories, which is so called EPE-MR training dataset. Secondly, the standard test reports, standard maintenance, and fault analysis reports for three types of power primary equipment (namely, main transformer, circuit breaker, and isolating switch) are employed as corpus to train character embedding in order to obtain certain words representation ability of maintenance records. After that, progressive multilevel radicals feature extraction module is designed to get detailed and fine semantic information in a hierarchical manner. Further, radicals feature representation and character embedding are concatenated and sent to BiLSTM module to extract contextual information in order to improve Chinese entity recognition ability. Moreover, CRF is introduced to handle the dependencies among prediction labels and to output the optimal prediction sequence, which can easily obtain structured data of maintenance records. Finally, comparative experiments on public MSRA dataset, China People’s Daily corpus, and EPE-MR dataset are implemented, respectively, which show the effectiveness of the proposed method.

No abstract

No abstract

On the basis of collecting a large number of practical engineering cases, this paper uses the improved neural network prediction model based on multiple linear regression to build an improved substation project cost prediction model based on the division of substation projects. Using the actual project sample data for empirical research, the results show that the prediction model has high accuracy for the prediction of substation engineering. This research work provides a reliable technical scheme for the cost prediction of power transmission project.