Transformer fault diagnosis based on adversarial generative networks and deep stacked autoencoder.

Establishing a deep learning model for transformer fault diagnosis using transformer oil chromatogram data requires a large number of fault samples. The lack and imbalance of oil chromatogram data can lead to overfitting, lack of representativeness of the model, and unsatisfactory prediction results on test set data, making it difficult to accurately diagnose transformer faults. A conditional Wasserstein generative adversarial network with gradient penalty optimization (CWGAN-GP) is adopted in this paper, which based on gradient penalty optimization and expand the oil chromatography fault samples of 500 sets of transformer oil chromatography data with 5 types of faults. The proposed method is used to classify transformer faults using a deep autoencoder, and the sample quality of the neural network model proposed in this paper is compared with several other variants of generative adversarial neural network models. The research results show that after using the method proposed in this paper for sample expansion, the overall accuracy of fault diagnosis can reach 93.2 %, which is 4.98 % higher than the original imbalanced samples. Compared with other sample expansion methods, the accuracy of fault diagnosis of the algorithm in this paper is improved by 1.70 %-3.05 %.

Serum leptin concentrations in relation to dietary patterns in Chinese men and women.

OBJECTIVE: The present study aimed to evaluate the independent associations between serum leptin concentration and dietary patterns in a Chinese population. DESIGN: A cross-sectional study. SETTING: Data obtained from the 2006 wave of the China Health and Nutrition Survey in Jiangsu Province, China. SUBJECTS: The sample contained 1061 Chinese adults (488 men and 573 women). BMI was calculated as a parameter of obesity. Factor analysis was used to derive dietary patterns. ANCOVA was performed to assess the associations between serum leptin concentration and the dietary patterns. RESULTS: Four dietary patterns were derived: Western, High-wheat, Traditional and Hedonic. The Western pattern (rich in meat, milk and cake) was significantly associated with a higher level of serum leptin in men and women, both in an unadjusted model (both P for trend < 0·001) and after adjusting for sex, age, income, total energy intake, physical activity, smoking status and BMI (P for trend = 0·007 for men and P for trend < 0·001 for women). The other three dietary patterns were not significantly associated with serum leptin after adjustment. Sensitivity analysis showed there was an interaction between age and the Western pattern in relation to leptin level. An interaction also existed between current smoking status and the Western pattern. CONCLUSIONS: Serum leptin concentration was positively associated with the Western dietary pattern in a Chinese population independent of BMI, energy intake and other factors.

[Comparison of dietary vitamin A intake of residents in Jiangsu Province between 2002 and 2007].

OBJECTIVE: To compare the change of dietary vitamin A intake between 2002 and 2007 in Jiangsu Province. METHODS: The data from the Nutrition Survey in Jiangsu province in 2002 and the fellow-up survey in 2007 were statistically analyzed with SAS 8.0. RESULTS: The average intake of retinol equivalent was 766.9 microg/d per reference man in 2007 (776.0 microg for man, 738.8 microg for women, 738.8 microg for urban and 776.0 microg for rural residents), which was higher than that in 2002. The percentage of retinol equivalent intake equal to or higher than RNI was 39.0% in 2007 and 16.1% in 2002. The dietary intake of vitamin A in northern Jiangsu was lower than that in southern Jiangsu and was positively correlated with the income. The dietary retinol equivalent from vegetable and fruits was increased, and from animal foods was decreased in 2007. CONCLUSION: The dietary vitamin A intake of residents in Jiangsu was improved in the past 5 years. The dietary vitamin A intake of low income population, women and residents in northern Jiangsu should be improved.

Iron intake and body iron stores, anaemia and risk of hyperglycaemia among Chinese adults: the prospective Jiangsu Nutrition Study (JIN).

OBJECTIVE: Fe supplementation has been used to prevent anaemia in China; however, high Fe intake and body Fe stores may increase diabetes risk. The present study aimed to prospectively examine the association between Fe intake/stores and hyperglycaemia, and to assess the joint effects on anaemia. DESIGN: We followed 1056 healthy adults aged 20 years and older from 2002 to 2007. Body Fe stores were measured. Dietary data were collected using a 3 d food record and FFQ. Hyperglycaemia was defined as fasting plasma glucose >5.6 mmol/l. RESULTS: Of the participants, 28.8 % were anaemic at baseline. During the 5 years of follow-up, we documented 125 incident cases of hyperglycaemia, among them twenty-three were diabetic. Haem Fe intake was positively associated with the risk of hyperglycaemia in men and women: the OR (95 % CI) across increasing quartiles of haem Fe intake was 1.00 (referent), 1.49 (0.74, 3.01), 2.16 (1.06, 4.42) and 3.48 (1.71, 7.11), respectively (P for trend <0.001). Comparing the fourth quartile of serum ferritin with the others, the age- and gender-adjusted OR (95 % CI) was 1.54 (1.01, 2.34), P for trend = 0.043. The association between total Fe intake and the risk of hyperglycaemia was significant in men (P for trend = 0.002). Anaemia added additional risk of hyperglycaemia on haem Fe intake. Comparing extreme quartiles of haem Fe intake, the OR (95 % CI) was 5.67 (1.43, 22.49) and 3.44 (1.51, 7.85) for hyperglycaemia among anaemic and non-anaemic participants (P for trend = 0.008 and 0.010, respectively). CONCLUSIONS: The present cohort study suggests that high haem Fe intake, anaemia and high ferritin are associated with an increased risk of hyperglycaemia in Chinese men and women. There was a joint effect between anaemia and haem Fe intake on the risk of hyperglycaemia.