Search

With the overall advancement of UHV AC and DC lines and the gradual development of large cross-regional power grids, the effective grounding of power equipment plays an important role in the safe and stable operation of the power system. Regarding the numerical uncertainty caused by the measurement of grounding grid parameters, this paper proposes a multi-dimensional safety evaluation method for grounding grids based on the gray correlation degree of interval numbers. First, construct an evaluation index system and use the coefficient of variation to determine the index weight, avoiding the subjectivity brought about by expert empowerment. Second, determine the evaluation level and construct an interval number evaluation matrix. Then, the kernel density estimation is used to fit the interval number evaluation value into a probability density distribution. Finally, the final evaluation results are gotten by evaluating the weighted JS divergence between the probability density distribution and the optimal distribution. Through an empirical analysis of a 220kV substation in Zhejiang, the effectiveness of the method is verified.

In this paper, we propose a 3D object pose estimation method based on the frustum point cloud for industrial picking robot to grab the express. The core of our idea is to segment the point cloud of the object which should to be pick up first, then extract the best grab plane and grab point on the object point cloud. First of all, a mature 2D detection framework Faster RCNN is used to detect the object in RGB images. Then the 2D bounding box and category of the object closest to the camera will be output. On the basis of this, the frustum point cloud data of the detected object is generated by the combination of the depth map and the projection relationship of the RGB-D camera. Then we used PointNet network to extract the feature of each point in the generated frustum point cloud. Finally, the instance segmentation of the point cloud and the subsequent extraction of the best grab plane and grab point are performed. We show results on both real dataset and synthetic dataset which we collected by ourselves, and our 3D instance segmentation network accuracy on real dataset reached 88%.

With the wide use of reverse osmosis technology in power plants, many produce water distribution networks of first-order reverse osmosis of seawater have severe corrosion, which is a threat for the normal and efficient operation of power plant. This paper studied the effect of corrosion factors such as dissolved oxygen, chloride ion, flow velocity, temperature on first-order reverse osmosis corrosion by carrying out coupon tests, explored the measure of adding corrosion inhibitors to produce water in order to reduce product water corrosion on the based of the above research results, and then proposed a useful anticorrosive method which suits for power plant. The research result of this paper can provide operation guidance to power plant and has obvious social benefits and practical application value.

Prediction of breakdown voltage of transformer oil has a great significance to the fault diagnosis and daily maintenance of transformer. Based on the correlation of performance parameters of transformer oil and the prominent fault-tolerance, non-linear approximation, and self-learning capabilities of BP neural network, this paper constructed a prediction method of breakdown voltage via multi-parameter correlation under the development environment of Matlab. Through examining the routine monitoring data of transformer oil by gray correlation analysis, this paper excavated some parameters which have strong correlation with breakdown voltage. Then a relational model of breakdown voltage and those parameters was further constructed using BP neural network. The clustering centers used to train network were acquired through clustering the original monitoring data samples with fuzzy C-means clustering algorithm. This method which uses clustering centers to train network can resolve natural problems of neural networks caused by large sample capacity, such as complication of net structure, inferior astringency, poor generalization ability, and so on. Test results show that the relative errors between predicted values and real values are all less than 10%, which indicates the significant practical values of this model.

Prediction of breakdown voltage of transformer oil facilitates the early fault diagnosis, prevention and treatment of transformer. In this article, a prediction method of breakdown voltage via multi-parameter correlation was proposed considering the lack of research in this field. Through examining the routine monitoring data of transformer oil by gray correlation analysis, some parameters which have strong correlation with breakdown voltage were excavated, then a relational model of breakdown voltage and those parameters was further constructed using back-propagation neural network, since BP neural network has prominent fault-tolerant, non-linear approximation, and self-learning capabilities. The clustering centers which were used to train network were acquired through clustering the original monitoring data samples with fuzzy C-means clustering algorithm. The adoption of this method can resolve natural problems of neural networks caused by large sample capacity, such as complication of net construction, inferior astringency, poor generalization ability, and so on. Test results show that the precision of the prediction model is high and that the relative prediction errors of test samples are all less than 10%, which indicates the significant practical value of the model.