In recent years, object detection algorithms have achieved great success in the field of machine vision. To pursue the detection accuracy of the model, the scale of the network is constantly increasing, which leads to the continuous increase in computational cost and a large requirement for memory. The larger network scale allows their execution to take a longer time, facing the balance between the detection accuracy and the speed of execution. Therefore, the developed algorithm is not suitable for real-time applications. To improve the detection performance of small targets, we propose a new method, the real-time object detection algorithm based on transfer learning. Based on the baseline Yolov3 model, pruning is done to reduce the scale of the model, and then migration learning is used to ensure the detection accuracy of the model. The object detection method using transfer learning achieves a good balance between detection accuracy and inference speed and is more conducive to the real-time processing of images. Through the evaluation of the dataset voc2007 + 2012, the experimental results show that the parameters of the Yolov3-Pruning(transfer): model are reduced by 3X compared with the baseline Yolov3 model, and the detection accuracy is improved, realizes real-time processing, and improves the detection accuracy.

Online automatic fault diagnosis in industrial systems is essential for guaranteeing safe, reliable and efficient operations. However, difficulties associated with computational overload, ubiquitous uncertainties and insufficient fault samples hamper the engineering application of intelligent fault diagnosis technology. Geared towards the settlement of these problems, this paper introduces the method of dynamic uncertain causality graph, which is a new attempt to model complex behaviors of real-world systems under uncertainties. The visual representation to causality pathways and self-relied “chaining” inference mechanisms are analyzed. In particular, some solutions are investigated for the diagnostic reasoning algorithm to aim at reducing its computational complexity and improving the robustness to potential losses and imprecisions in observations. To evaluate the effectiveness and performance of this method, experiments are conducted using both synthetic calculation cases and generator faults of a nuclear power plant. The results manifest the high diagnostic accuracy and efficiency, suggesting its practical significance in large-scale industrial applications.

In data centers, workload consolidation is the common method to improve resource utilization. However, efficient workload consolidation faces challenges from two aspects: the first is the wide variety of program characteristics; the second is the multiple performance indexes in clusters or data centers, such as the program performance requirement from custom and the system utilization from the cluster provider. In this paper, multiple experiments are executed about program performance with restricted resource usage, and four conclusions are summarized. Then based on the conclusions, two individualized precise scheduling strategies are proposed for efficient consolidation. Sche-index2 schedule programs by considering the resource sensitivity hyper-plane on five resource dimensions, and Sche-utility scheduling programs by considering the sensitivity curve of five resource dimensions. The experiment results show that compared with the common scheduling strategy, Sche-index2 can improve the average performance of the program by 36%, and Sche-utility can improve the average performance of the program by 27.6%. Meanwhile, both of the scheduling strategies can improve the resource utilization of CPU, disk read/write bandwidth, memory, and network bandwidth.