电流互感器负荷箱测量结果不确定度评定

文章通过实例对电流互感器负荷箱标准装置的示值误差不确定度进行了分析和评定。     

Modeling and real-time fault identification in transformers

In this paper, a different internal fault modeling and an identification algorithm are presented. There has been an increasing concern about turn-to-turn faults in transformers because of the high costs of unexpected outages. It is not always possible to analyze the transformer behavior under such faults at rated conditions, since the tests are highly destructive. To develop transformer internal fault detection technique, a transformer model to simulate internal faults is required. This paper describes a novel technique and methodology for modeling and identifying transformer internal faults by using transmission line method (TLM) and fuzzy reasoning technique based on dynamic principal component analysis (PCA), respectively. The transformer has been modeled considering non-linearities as hysteresis and saturation. Transformer internal fault currents are successfully discriminated from the rated currents. The degree and priority of transformer internal faults are obtained by the proposed method. It is suited for implementation on computers because of no computation complexity. Hence, the proposed algorithm can be used effectively in real-time fault identification problems.     

Chemistry behind the life of a transformer

Conclusion Scientific assessment of the insulation conditions rather than years of service determine the remnant life of the transformer. Insulation age of a transformer is exclusively decided by the life of cellulosic materials. Extent of degradation of cellulosic materials can be quantified by measuring dissolved CO₂ gas content in oil, degree of polymerization of paper and furan content in oil. Transformer life is shortened by a number of events. Taking action to prevent failure from any of these causes is a method of life extension. Maintaining the insulation system in good order and controlling loads by the use of dynamic loading of the equipment make it possible to improve the utilization of the existing transformer capacity.     

Hierarchical template transformer for fine-grained sentiment controllable generation

Existing methods for text generation usually fed the overall sentiment polarity of a product as an input into the seq2seq model to generate a relatively fluent review. However, these methods cannot express more fine-grained sentiment polarity. Although some studies attempt to generate aspect-level sentiment controllable reviews, the personalized attribute of reviews would be ignored. In this paper, a hierarchical template-transformer model is proposed for personalized fine-grained sentiment controllable generation, which aims to generate aspect-level sentiment controllable reviews with personalized information. The hierarchical structure can effectively learn sentiment information and lexical information separately. The template transformer uses a part of speech (POS) template to guide the generation process and generate a smoother review. To verify our model, we used the existing model to obtain a corpus named FSCG-80 from Yelp, which contains 800K samples and conducted a series of experiments on this corpus. Experimental results show that our model can achieve up to 89.93% aspect-sentiment control accuracy and generate more fluent reviews.     

On the class separability of contextual embeddings representations – or “The classifier does not matter when the (text) representation is so good!”

The literature has not fully and adequately explained why contextual (e.g., BERT-based) representations are so successful to improve the effectiveness of some Natural Language Processing tasks, especially Automatic Text Classifications (ATC). In this article, we evince that such representations, when properly tuned to a target domain, produce an extremely separable space that makes the classification task very effective, independently of the classifier employed for solving the ATC task. To demonstrate our hypothesis, we perform a thorough class separability analysis in order to visualize and measure how well BERT-based embeddings separate documents of different classes in comparison with other widely used representation approaches, e.g., TFIDF BoW, static embeddings (e.g., fastText) and zero-shot (non-tuned) contextual embeddings. We also analyze separability in the context of transfer learning and compare BERT-based representations with those obtained from other transformers (e.g., RoBERTa, XLNET). Our experiments covering sixteen datasets in topic and sentiment classification, eight classification methods and three class separability metrics show that the fine-tuned BERT embeddings are highly separable in the corresponding space (e.g., they are 67% more separable than the static embeddings). As a consequence, they allow the simplest classifiers to achieve similar effectiveness as the most complex methods. We also find moderate to high correlations between separability and effectiveness in all experimented scenarios. Overall, our main finding is that more discriminative (i.e., separable) textual representations constitute a critical part of the ATC solutions that, given the current state-of-the-art in classification algorithms, are more prominent than the algorithmic (classifier) method for solving the task.