Search

In order to solve the problem that the data distribution of the source domain and the target domain of rolling bearing is different in the variable working condition environment and the samples of the target domain do not contain labels, a fault diagnosis model of the rolling bearing based on the deep adaptive transfer learning network (DATLN) is proposed. Firstly, a domain-shared characteristic extraction network is built, and multiscale convolutional neural network (MSCNN) is used to suppress noise interference, so as to effectively extract local fault information contained in vibration signals. Secondly, combined with a bi-directional long short-term memory network (BiLSTM), the temporal characteristics in the local fault information are further learned. Finally, transfer learning is introduced to build a domain adaptive module with domain adversarial (DA) training combined with adaptive joint distribution (AJD) metrics. By maximizing the domain classification loss and minimizing the AJD distance, the source and target domain characteristic samples are aligned. The anti-noise experiment and transfer experiment are carried out on the open source CWRU data set and the measured data set of the mechanical fault platform respectively. The anti-noise experiments show the following points. ① The identification accuracy of MSCNN-BiLSTM network is above 99% in the noise-free environment, which shows that MSCNN-BiLSTM network has a good characteristic extraction capability. ② The identification accuracy of MSCNN-BiLSTM, LeNet-5, MSCNN and BiLSTM decreases with the increase of noise intensity. ③ Under the noise environment of 3, 5 and 10 dB, the average identification accuracy of MSCNN-BiLSTM network is higher than that of LeNet-5, MSCNN and BiLSTM networks, indicating that MSCNN-BiLSTM network has better anti-noise interference performance. ④ The MSCNN-BiLSTM network converges first with less fluctuation in both the noise-free environment and the 3 dB noise environment. The transfer experiments show the following points. ① The average identification accuracy of DA+AJD method is 97.36% on unlabeled target domain dataset, which is higher than that of Baseline, transfer component analysis(TCA) and domain adversarial neural network (DANN). ② On the test set confusion matrix, only one sample of the DA+AJD method is incorrectly identified, indicating that the DA+AJD method based on domain adaptation has better fault transfer diagnosis performance. ③ The t-SNE algorithm is used to visualize the processed source and target domain characteristic samples. The DA+AJD method only has a small number of rolling element fault and outer ring fault characteristic samples in the target domain that are incorrectly aligned to the inner ring fault characteristic samples area in the source domain. This result indicates that the DA+AJD method can effectively reduce the edge distribution and conditional distribution differences between the source domain and the target domain, and thus achieves better characteristic sample alignment.

The extreme weather disasters before winter caused by global climate change seriously affect the formation of strong seedlings of wheat. Cultivating strong seedlings is the premise of realizing high yield, high efficiency, and high quality of wheat. The cultivation of strong wheat seedlings is closely related to seed quality, straw returning quality, land preparation quality, sowing quality, water and fertilizer operation and meteorological factors. Seed quality and tillage measures are the primary factors affecting the cultivation of strong wheat seedlings, which determine the quality of wheat seedling emergence. Secondly, meteorological factors determine growth rate and photosynthetic production of wheat seedlings. Mounting studies have addressed the cultivation of strong seedlings and the evaluation of seedling conditions of wheat. This research focused on comparing and summarizing the evaluation methods and indices of strong seedlings of winter wheat, the historical changes of evaluation standards and the main technical measures for cultivating strong seedlings, and proposed the cultivation and evaluation methods of strong seedlings of winter wheat in the future. We aimed to further improve the evaluation method of winter wheat strong seedlings, advance the classification management, precise guidance and fine service of winter wheat seedlings, and realize strong seedlings through scientific and technological ways. [ABSTRACT FROM AUTHOR]

The influence of different NH4+/NO3- ratios on nitrogen metabolism of cotton was studied under controlled hydroponics. The results showed that compared with single nitrate nutrition, solutions with 25/75, 50/50, 75/25 and 100/0 of NH4+/NO3- significantly increased the soluble protein accumulation in leaves and roots of cotton, and the maximum content of soluble protein in leaves and roots appeared respectively in the solution with 50/50 and 75/25 of NH4+/NO3-. The soluble protein content in roots was increased with the increase of NH4+ percentage, but was slightly less in the solution of 100/0 than 75/25, which was probably related to the excess NH4+ limiting boot metabolism. With the increase of NH4+ percentage, the nitrate content in petiole and the nitrate reductase activity in functional blade declined, but ammoniac nitrogen content increased in every organ of cotton. These results showed that foreign nitrogen affected the nitrogen metabolism of cotton in a different way, and the nitrogen absorption by cotton was probably related to different forms of foreign nitrogen.

Objective: To explore new source of skin for burn wound coverage., Methods: Split-thickness consanguineous skin was harvested from New Zealand white rabbit and was soaked in 200 g/L of multi-peptides of Tripterygium wilfordii, 50 g/L of dexamethasonel, on 9 g/L of normal saline solution for 15 - 30 mins, respectively. The consanguineous skin was thereafter grafted onto the whole layer skin defects in filial generation of rabbits with non-consanguineous skin as the control. The survival time and rejection of the grafted skin was observed., Results: The rejection appeared evidently less intense and survived significantly longer (43 +/- 3.5 days) when the consanguineous skin was pretreated by Tripterygium wilfordii. However the grafted consanguineous skin survived for 30 +/- 2.5 days when it was pretreated by dexamethasone. The grafted skin was quickly rejected and survived only for 11 +/- 1.6 days when the skin was pretreated by normal saline or the skin was non-consanguineous., Conclusion: Consanguineous skin possessed partial compatibility with the recipient due to similar antigen, which was beneficial to the its survival, especially after the skin was pretreated.