Abstract:Existing detection methods of electricity theft have low detection accuracy for new means of electricity theft. This paper proposes a new theft detection method based on multi-level non-negative sparse coding and SVM. Using the monthly electricity consumption curve as the detection object, firstly, the multi-level electricity consumption pattern characteristics of the sample are extracted based on the multi-level non-negative sparse coding; next, the numerical statistical characteristics of the sample are extracted based on the electricity theft scenario analysis; then, the fusion detection features of the above two characteristics are input into the SVM classifier for electricity theft detection. Finally, the Irish smart meter data set is used as the example to verify the effectiveness of the proposed method, showing the improved accuracy and recall rate of the detection.

Abstract:In order to realize the coordinated control of conventional AGC and renewable energy AGC under the high penetration of renewable energy to grid, this paper proposes an AGC multi-objective coordination optimization method with Wind-PV-Hydro-Thermal. This method not only ensures the economic operation of the power grid, but also considers the frequency quality and power transmission capacity of the grid. Firstly, based on the long-term AGC historical data in a certain region, the regulate frequency characteristics of different types of units are analyzed, and the regulate frequency indexes are calculated. Secondly, based on the requirements of the "Two Rules" of the Central China Power Grid, using the regulate frequency cost, power loss cost, regulate frequency speed and regulate frequency accuracy as objectives, a multi-objective AGC active power coordination optimization model including Wind-PV-Hydro-Thermal is proposed. Finally, considering the power grid structure and AGC data in an inland region, the model is solved using the multi-objective particle swarm algorithm, and the active power of each AGC station is obtained, verifying the effectiveness of the proposed method in this paper.

Abstract:Bearing-type shear connection of 32 sets of Q690 steel-highstrength bolts (property grade 10.9 or 12.9) were studied through experiments. Tear-out failure, splitting failure, bearing failure, net cross section failure, and bolt shear failure were observed. Through the analysis of the test data, it is found that Q690 highstrength steel had good local deformation ability. Furthermore, the effects of bolt grade, size, pretension, end distance, and edge distance on the bearing capacity and deformation of the specimen were studied. The experimental data in several papers were collected and analyzed, showing that the geometric limit between the tear-out failure and splitting failure was about from 0.7e₁/e₂ to 0.9e₁/e₂, and the stress ratio of the net section failure specimen was greater than 1.0.

Abstract:With the rapid development and utilization of urban underground space, the phenomenon of excavation adjacent to tunnels is becoming more and more common. Therefore, the influence of excavation on adjacent tunnels has become a serious problem that cannot be ignored in engineering. This study proposed a back propagation neural network (BPNN) to predict the tunnel deformation caused by adjacent excavation. Firstly, the finite element software Plaxis (3D) based on a small-strain stiffness constitutive model was used to generate a complete database of tunnel deformation. The accuracy of the BPNN model was trained and tested by this database. Furthermore, the relative importance of each input variable (i.e., the relative horizontal distance of the tunnel as opposed to a supporting structure, the tunnel buried depth, the maximal displacement of retaining structure) was estimated by this BPNN model. Finally, the prediction of BPNN model showed great agreement with the measured deformations of 17 case histories. The analysis results show that the BPNN model can accurately predict the tunnel deformation caused by adjacent excavation, and can provide a more convenient prediction method for practical engineering.

Abstract:To study the deep foundation pit excavation of the high confined water foundation in the Yangtze River floodplain area, a Nanjing I-shaped 6 floor underground metro transfer station foundation pit excavation was selected as research object. Using finite difference software FLAC3D, numerical simulation on semi-normal and semi-reversed construction method and the cut and follow method was carried out separately, and the effects of the coupling action of the foundation pit excavation and stress seepage of precipitation on the surrounding surface settlement, lateral displacement of diaphragm wall and supporting axial force were analyzed. The findings show that: 1) in the deep foundation pit excavation project of high confined water foundation of the Yangtze River floodplain, both the surface settlement value and the continuous wall deformation value are large; 2) in the excavation of I-shaped deep foundation pit, the maximum value of surface settlement and continuous lateral displacement of wall occurs at the midpoint of the upper and lower transverse edges; 3) the surface settlement, lateral displacement of continuous wall and axial force value of transverse support in the semi-normal and semi-reversed construction method are all lower than that in the cut and follow method, conducive to controlling the lateral wall deformation of foundation pit and reducing the risk of foundation pit excavation.

Abstract:In this study, a phase change thermal storage plate, heated by hot air, was designed. It could be mounted on the internal wall of the building and applied in the building heating system. The thermal characteristics of the model room assisted by the phase change thermal storage system was experimentally studied and compared with that of ordinary room. The TRNSYS model of the phase change thermal storage building was employed to simulate the transient thermal characteristics. The measured and simulated results show that the temperature of the room assisted by the thermal storage system increased from 4 ℃~5 ℃ compared with the ordinary room, suggesting that the proposed system can improve the thermal comfort of the room. In addition, the TRNSYS model of the phase change thermal storage building can precisely forecast the transient thermal characteristics.

Abstract:Previous studies on thermal comfort mainly focus on air-conditioned rooms, whereas passive houses mainly rely on passive technology to ensure comfortable indoor environment. In order to study the thermal environment and the influence of passive technology on thermal comfort of passive houses in winter in cold regions, a passive house in Tianjin area was selected as the research object. The experiment was carried out in two conditions: with heating and without heating. Through indoor environmental test and questionnaire survey, the actual thermal sensation polling value TSV under each working condition was obtained. After data fitting, the TSV model was compared with the PMV model. The original thermal comfort prediction model without heating was modified due to the large deviation of the model. Finally, a thermal comfort evaluation model for passive houses in cold regions was obtained under heating condition and without heating condition. The results show that 44% of the people want the temperature to rise under the condition of no heating. Passive technology alone cannot completely satisfy the thermal comfort requirement of passive housing in cold areas in winter. However, the actual acceptable temperature limit was reduced by 1.93 degrees centigrade under the condition of no heating, suggesting that users are more adaptable to the thermal environment and the transition season can be appropriately extended.

Abstract:The goal of smart tourism construction is to improve tourism service and tourist experience by using the latest information technologies. To enable tourists to dialog with the electronic explanation system of scenic spots by natural voice, an intelligent tourism explanation system based on natural language processing and ontology knowledge retrieval was proposed in this study. Firstly, the physical view and logical view of the system architecture was designed. Secondly, the key technologies of text vector, named entity recognition, dialogue policy management and tourism knowledge retrieval were analyzed. Finally, a prototype was developed, verifying the feasibility of the system.

Abstract:To solve the problem that the output signal-to-interference-plus-noise ratio (SINR) of the traditional beamforming algorithm decreases seriously under the condition of the mismatch of the steering vector and the error of the covariance matrix, a kind of robust adaptive beamforming algorithm based on the combination of steering vector optimization and covariance matrix reconstruction was proposed. By estimating the power and direction of signal and interference, interference plus noise covariance matrix was reconstructed. At the same time, combined with projection and spatial integral, the assumed steering vector was optimized to make it approximate to the actual steering vector. Then the complex weight was obtained by related calculation and the beamforming could be realized. The proposed algorithm can effectively suppress interference and improve the output SINR. For comparison, the performances of the proposed algorithm were simulated in six experiments. The simulation results show that the proposed algorithm has better performances. Compared with the worst-case performance optimization algorithm, the proposed algorithm has about 5 dB improvement in output SINR under the condition that the number of snapshots is fixed and the steering vector is mismatched. Compared with algorithms for comparison, in the case where the signal-to-noise ratio (SNR) is fixed and the steering vector is mismatched, the performance is improved by more than 4 dB. The simulation results verify the effectiveness of the proposed algorithm.

Abstract:In social networks, people tend to visit places that are more interesting and close to themselves. Point-of-interest recommendation based on user’s interest preferences can effectively help users choose places which they are interested in. In this paper, a point-of-interest recommendation method based on location and time information was proposed. Three steps from the perspective of the point-of-interest were involved. Firstly, the similarity between the user history access point-of-interest and the point-of-interest that the user has not visited was calculated by using the location information of the point-of-interest accessed by the user. Then, the day is divided into different time periods, during which the number of times all points of interest are checked in is counted. The similarity between the user’s historical visit of point-of-interest and the point-of-interest that the user has not visited was calculated by using the time information. Finally, the similarity between the user history access point of interest and the user’s non-visited point-of-interest was calculated according to the location and time information of the point-of-interest. The point-of-interest that the user has not visited was recommended according to the Top-N policy. Experimental verification was carried out on the real data set in the real society. The experimental results show that the proposed method is effective.

Abstract:As a kind of special equipment, the safety of pressure vessels attracts more and more attention. To ensure their safe operation, using the pressure vessel crack image as the research object, this paper constructed an algorithm model for the crack detection and identification. Generally, the algorithm model is constrained by various hardware conditions, such as memory space and processor computing power during actual deployment. Therefore, a lightweight method based on NewEfficientNet-B0 was proposed. The results show that the algorithm model reduces the number of model parameters by 78%. To deal with the difficulty of recognizing tiny crack images, an improved multi-scale prediction method was proposed. The detection and recognition accuracy rate of 81% was achieved on the test data set.

Abstract:Due to the fracture, tilt, and deformation of railway freight train number and characters, the traditional segmentation method faces the problem of low segmentation accuracy. In this paper, a segmentation method based on improved enclosing circle was proposed. Firstly, the adaptive run length algorithm was used to segment the double line train number and characters based on the single line and double line arrangement of railway freight trains. With the characteristics of foreground processing of background pixels in run length algorithm, the run length algorithm was used to remove the breaks in advance, and then the enclosing circle method was used for character segmentation. The experimental results show that, in the case of low image quality, the proposed method can achieve good segmentation accuracy. Compared with the traditional algorithms, it is superior in segmentation accuracy and robustness.

Abstract:To meet the diversified personalized service needs of teachers and students for scientific research resources in universities, a personalized service system for university scientific research resources was designed (PSRSS for short). Firstly, the personalized service needs of users for research resources were comprehensively analyzed. Then, the architecture of multiengine fusion recommendation system was designed with the data layer, the recommendation computing layer which integrates multiple recommendation strategies, and the application presentation layer. Different recommendation algorithms were compared and the selected algorithms were optimized in accordance with the different recommendation scenarios. Next, the user model and scientific research resource model were constructed. Finally, the Top-N recommendation based on the popularity of research resources, similarity of resource content and collaborative filtering of similar users was implemented. The proposed system improves the experience of teachers and students in obtaining scientific research resources and provides new ideas for the development of the personalized service system for scientific research resources in universities.