Search

The domain terms in power grid operation management documents are professional and complex. In the process of information extraction, excellent and applicable event detection methods are needed to extract event subjects. However, most of the current Chinese event detection methods use the word embedding technology to capture semantic representation, but it is difficult for these methods to capture the dependency between trigger words and other domain words in the same sentence. Based on the above situation, this paper proposes a novel hybrid representation architecture to represent the semantic and structural information of two characters and words. The model can capture rich semantic features through the semantic representation generated by the dependency parser. The experiment is based on the corpus of dispatching log, dispatching maintenance ticket, and dispatching plan. The results show that this method can significantly improve the performance of power grid dispatching text event detection.

To meet the demand of scalability and decision-making foresight of the traditional dispatching automation system in the new power system, a novel pre-dispatching method of new generation dispatching and control was proposed. First, the power grid digital twin was established in the description subsystem layer, which can reflect the state of power grid primary equipment, secondary equipment, and environment. Then, in the prediction subsystem level, the deep learning models were used to learn and predict future situation or accident risk of power grid operation in power grid digital twin. Finally, the feasibility of the proposed method was verified by the implementation example of East China Grid. The application results show that the pre-dispatching method improves the efficiency of system in dealing with the operation control problems of the new power system, which also provides a useful reference for comprehensive construction, popularization, and application of new generation power systems.

[Objective] We attempted to determine the cause of the large difference in paleoenvironment characteristics during the Jurassic Da'anzhai period and the unclear distribution law of the shale source and reservoir in the Sichuan Basin. [Methods] Based on the geological drilling cores and field profiles of the Jurassic Da'anzhai member in the central and eastern Sichuan Basin, combined with elemental geochemical analysis methods, we performed a comparative analysis of the paleo-climate,paleo-redox conditions,and the paleo-salinity in the Da'anzhai period. [Results] The results show that the Da'anzhai member can be divided into shale, shell shale, mudstone, silty mudstone, argillaceous siltstone, shell limestone, and argillaceous shell limestone facies. The paleoenvironment of different sub-members in the Da'anzhai member is different to a certain extent. During the sedimentation period of the Third sub-member, the climate was dry to semi dry, and the water environment was fresh to semi-saline under sub-reducing conditions, located in a shallow to semi-deep lake environment. During the sedimentation of the Second submember, the climate was semi dry to semi humid, with more precipitation and lower temperatures, and the water environment was fresh water with sub-reducing conditions. It was a semi-deep lake environment. During the sedimentation of the First sub-member, the climate was dry to semi-dry, and the water environment was semi-saline to saline under oxidation sub-reduction conditions, located in a shallow lacustrine environment. Wells RA1 and YT1 both exhibited the following conditions: the climate was dry→wet→dry, the precipitation was less→more→less, the temperature was high→low→high, the reducibility of water was weak→strong→weak, and the paleo-salinity was high→low→high. From the sedimentation period of the Third sub-member to the early sedimentation period of the Second sub-member, the lacustrine basin depositional center migrated from the eastern to central Sichuan Basin. The middle sedimentation period of the Second sub-member was a transitional stage during which the migration direction of the lake basin depositional center changed. From the late sedimentation period of the Second sub-member to the sedimentation period of the First sub-member, the lacustrine basin depositional center migrated from the central to eastern Sichuan Basin. The average total organic carbon (TOC) of the Second sub-member is 1.70%, and the average porosity is 4.93%, significantly higher than the First and Third sub-members. The fluorescence display is strong, and it is the main source and reservoir of shale oil in the Da'anzhai section. The paleoenvironmental factors have a significant influence on the source and reservoir configuration. The more humid climate, more precipitation, lower temperature, stronger reducibility and lower salinity are conducive to shale deposition, organic matter enrichment, and pore development. [Conclusions] The study on the paleoenvironment of the Da'anzhai member in the central-eastern Sichuan Basin is important to the regularity of shale deposition, organic matter enrichment, and pore development degree. This research understanding can provide a theoretical basis for shale oil exploration in the Sichuan Basin. [ABSTRACT FROM AUTHOR]

In view of the imprecise sedimentary facies division, unclear favorable rock assemblage and undefined favorable exploration area of Jurassic Da'anzhai Member in Central Sichuan, a study was conducted on the rock type, sedimentary facies type, sedimentary facies distribution, sedimentary model, rock assemblage and favorable exploration area in the study area by the core description of three fully cored wells and the observation results of six field profiles in combination with thin slice identification, logging interpretation and organic geochemical analysis methods. The study results show that Rock was divided into 10 types. The sedimentary facies was divided into 3 subfacies (shore lake, shallow lake and fairly deep lake) and 10 microfacies (including fairly deep lake mud, organic bank and gravity flow). Gongshanmio-Lianchi-Yingshan line is the sedimentary center developed in a fairly deep lake environment, and three rock assemblage types (C, D and E) were identified. Nanchong-Quxian-Yilong line was circularly developed in a shallow lake environment, and three rock assemblage types (A, B and F) were identified. The study results were applied from conventional tight oil to shale oil exploration. According to the TOC, porosity, permeability, fracturing effect and other evaluation indicators, it was considered that Type A rock assemblage was a favorable combination for tight oil carbonate rock exploration under the matching of fractures and cracks, and Type F was the most favorable combination for shale oil exploration, which was mainly distributed in the shallow lake facies at Sub-member 1 to Sub-member 2a of Da'anzhai Member. The study results are of great significance for shale oil exploration in the future. [ABSTRACT FROM AUTHOR]

Automatic classification of heart sounds plays an important role in the early diagnosis of congenital heart disease. A kind of heart sound classification algorithms based on sub-band envelope feature and convolution neural network was proposed in this paper, which did not need to segment the heart sounds according to cardiac cycle accurately. Firstly, the heart sound signal was divided into some frames. Then, the frame level heart sound signal was filtered with Gammatone filter bank to obtain the sub-band signals. Next, the sub-band envelope was extracted by Hilbert transform. After that, the sub-band envelope was stacked into a feature map. Finally, type Ⅰ and type Ⅱ convolution neural network were selected as classifier. The result shown that the sub-band envelope feature was better in type Ⅰ than type Ⅱ. The algorithm is tested with 1 000 heart sound samples. The test results show that the overall performance of the algorithm proposed in this paper is significantly improved compared with other similar algorithms, which provides a new method for automatic classification of congenital heart disease, and speeds up the process of automatic classification of heart sounds applied to the actual screening.

Wolfberry fruit is very popular among consumers because it is rich in nutrients. However, it is vulnerable to diseases caused by insect pest feeding and microbial pathogen infection. Pesticide application is the main approach for controlling wolfberry disease; however, various concerns have been raised regarding chemical residues in foodstuffs and consequent environmental contamination. Matrix interference is a significant challenge in trace analysis. Chromatography, coupled with MS techniques with high sensitivity and selectivity, proved to be a powerful tool for the detection of multi-pesticide residues in complex matrices. The traditional MRM mode has been gradually replaced by the dynamic MRM (dMRM) mode, which could dynamically allocate the retention time window of each target pesticide, significantly adjust the loading cycle time of multiple compounds, and improve the analysis efficiency. The QuEChERS pretreatment method, based on dispersive solid-phase extraction, has been widely used in the detection of pesticide residues in food because it is simple and rapid. In this study, a robust and high-throughput method was established for the simultaneous determination of 118 pesticide residues in wolfberry using the modified QuEChERS method, combined with gas chromatography-triple quadrupole mass spectrometry in dMRM mode. The optimal pretreatment method was determined by comparing the recovery rates obtained with different volumes of added water (5, 10, 15, and 20 mL), different extraction solvents (acetone, n -hexane, acetonitrile, and acetonitrile containing 0.1% formic acid), different extraction temperatures (normal temperature, -18 ℃ for 10 min and 20 min), water absorbent (anhydrous magnesium sulfate), and purification with primary secondary amine (PSA) and octadecylsilane (C 18 ). The results showed that 5 g samples were rehydrated with 10 mL ultrapure water, extracted with 10 mL acetonitrile, frozen at -18 ℃ for 10 min, partitioned with buffer system salt package containing 4.0 g anhydrous magnesium sulfate, 1.0 g sodium chloride, 1.0 g sodium citrate, and 0.5 g disodium citrate, purified up with 800 mg MgSO 4 , 150 mg PSA, and 150 mg C 18 . Pesticides were separated on a capillary column HP-5MS UI (30 m×0.25 mm×0.25 μm), and quantified by a matrix-matched external standard method. The results showed that the 118 pesticides exhibited good linearity in the range from 20 to 640 μg/L, with correlation coefficients R 2 ≥0.9923. The limits of detection and quantification were 0.006-28.344 μg/kg and 0.021-94.480 μg/kg, respectively. The average recoveries at four spiked levels of 0.01, 0.04, 0.10, and 0.20 mg/kg were in the range of 64.97%-126.21%, with relative standard deviations (RSDs) of 0.69%-18.86% ( n =6). The results of the matrix effect showed that 82% of the pesticides exhibited matrix enhancement effects, while others showed matrix inhibition effects. In addition, 9% of the pesticides showed a strong matrix effect, while others showed moderate or weak matrix effects. The matrix effects could be reduced by the matrix-matched standard curve method. The proposed method was employed for the analysis of 10 real samples purchased from local markets. The results demonstrated that pesticides were detected in all the samples, 22 pesticides were detected in total, and 3-12 pesticides were found in a single sample. Chlorpyrifos, fipronil, cypermethrin, pyridaben, and difenoconazole were detected at high detection rates. The captan content in a batch of samples was 1.4066 mg/kg. Thus, the optimized method is simple, fast, accurate, and reliable, and it is suitable for the routine detection and rapid screening of the multi-pesticide residues in wolfberry.