The quality text of nuclear power equipment describes the quality defects and other issues that occur during the design， procurement， construction， and commissioning stages of nuclear power equipment. Due to the different frequencies of quality events occurring at different stages， and the existence of the same keywords and similar expressions in quality texts corresponding to the same equipment at different stages， an improved recurrent pooling network classification model was proposed by integrating regularization and feedback for focus loss function to address the quality text classification problems with imbalanced number of categories and semantic description coupling. Firstly， BERT （Bidirectional Encoder Representation from Transformers） was used to convert nuclear power equipment quality text into word vectors. Then， an improved three-layer recurrent pooling network classification model structure was proposed， which expanded the extraction space for parameter training by adding intermediate layers and selecting appropriate weights， and enhanced the ability to represent semantic features of quality defects. Next， regularization and feedback for focus loss function was proposed to train the parameters of the proposed classification model. To solve the problem of uneven gradient bias of imbalanced samples during the training process， the regularization term was used to make the gradient change of the loss function more stable， and the feedback term was used to iteratively adjust the loss function based on the error between the true value and the predicted value. Finally， the corresponding stages of nuclear power equipment quality events were calculated using a normalized exponential function. On the real dataset of a certain nuclear power company and a public dataset， F1 value of this model was 2 percentage points and 1 percentage point respectively higher than that of Fast_Text network. The experimental results show that the proposed model has high accuracy in text classification tasks.

Unmanned Aerial Vehicle （UAV） swarm path planning and task allocation are the cores of UAV swarm rescue applications. However， traditional methods solve path planning and task allocation separately， resulting in uneven resource allocation. In order to solve the above problem， combined with the physical attributes and application environmental factors of UAV swarm， the Ant Colony Optimization （ACO） was improved， and a Joint Parallel ACO （JPACO） was proposed. Firstly， the pheromone was updated by the hierarchical pheromone enhancement coefficient mechanism to improve the performance of JPACO task allocation balance and energy consumption balance. Secondly， the path balance factor and dynamic probability transfer factor were designed to optimize the ant colony model， which is easy to fall into local convergence， so as to improve the global search capability of JPACO. Finally， the cluster parallel processing mechanism was introduced to reduce the time consumption of JPACO operation. JPACO was compared with Adaptive Dynamic ACO （ADACO）， Scanning Motion ACO （SMACO）， Greedy Strategy ACO （GSACO） and Intersecting ACO （IACO） in terms of optimal path， task allocation balance， energy consumption balance and operation time on the open dataset CVRPLIB. Experimental results show that the average value of the optimal paths of JPACO is 7.4% and 16.3% lower than of IACO and ADACO respectively in processing small-scale operations. Compared with GSACO and ADACO， JPACO has the solution time reduced by 8.2% and 22.1% in large-scale operations. It is verified that JPACO can improve the optimal path when dealing with small-scale operations， and is obviously superior to the comparison algorithms in terms of task allocation balance， energy consumption balance， and operation time consumption when processing large-scale operations.

In the indoor robot localization and 3D dense mapping, the existing methods can not satisfy the requirements of high-precision localization, large-scale and rapid mapping. The ORB-SLAM (Oriented FAST and Rotated BRIEF-Simultaneous Localization And Mapping) algorithm, which has three parallel threads including tracking, map building and relocation, was used to estimate the three-dimensional (3D) pose of the robot. And then 3D dense point cloud was obtained by using the depth camera KINECT. The key frame extraction method in spatial domain was introduced to eliminate redundant frames, and the sub-map method was proposed to reduce the cost of mapping, thereby the whole speed of the algorithm was improved. The experiment results show that the proposed method can locate the robot position accurately in a large range. In the range of 50 meters, the root-mean-square error of the robot is 1.04 m, namely the error is 2%, the overall speed is 11 frame/s, and the localization speed is up to 17 frame/s. The proposed method can meet the requirements of indoor robot localization and 3D dense mapping with high precision, large-scale and rapidity.

Concerning the low efficiency of present methods of IP lookup, a new data lookup algorithm based on Multi-Bit Priority Tries (MBPT) was proposed in this paper. By storing the prefixes with higher priority in dummy nodes of multi-bit tries in proper order and storing the prefixes for being extended in an auxiliary storage structure，this algorithm tried to make the structure find the longest matching prefix in the internal node instead of the leaf node. Meanwhile, the algorithm avoided the reconstruction of router-table when it needed to be updated. The simulation results show that the proposed algorithm can effectively minimize the number of memory accesses for dynamic router-table operations, including lookup, insertion and deletion, which significantly improves the speed of router-table lookup as well as update.

As it is known that the underwater environment is quite complicated and changeable, as a result, targets and pseudo targets always have a high degree of mixing, and one single segmentation method usually could not abstract ideal target regions. Therefore, this paper proposed a new segmentation method based on Blob analysis and Bayesian design-making. Firstly, the optimistic thresholds were calculated by the improved OTSU algorithm, and then the image was segmented according to this threshold. Through analyzing the connectivity characters, closed contours of regions were achieved. Secondly, the connected regions were described using 7 dimensions of Blob operators and pseudo-target regions were eliminated based on Bayesian decision-making rules. Finally, burrs and disturbances were wiped off through the usage of mathematical morphology operators and ideal target regions were achieved. Through dealing with the images grabbed during the pool experiments using the above method, accuracy and efficiency of the method were verified and the real target regions were acquired.

To overcome the shortcomings of conventional algal bloom forecast system in acquiring data, this study applied the Internet of Things (IoT) technology to establish a data transmission network with three-layer structure, and thus secured data continuity. With improved retrieval approach of water quality parameters, technology of Wireless Sensor Network (WSN) and forecast model of algal bloom, the blue-green algal bloom forecast platform was developed. The evaluation demonstrates that the platform achieves an overall accuracy of 80% in forecasting blue-green blooms in Taihu Lake in next three days.