In the analysis of regional landslide susceptibility, the geological data used usually have the characteristics of multiplicity and nonlinearity. At the same time, in the past researches, the selection of non-landslid...
详细信息
In the analysis of regional landslide susceptibility, the geological data used usually have the characteristics of multiplicity and nonlinearity. At the same time, in the past researches, the selection of non-landslide units in the training set is usually random or subjective, and there is no guarantee sample accuracy. In this paper, the deep forest algorithm combined with the twice-sample method is used to evaluate the landslide susceptibility in the Zigui Badong area of the Three Gorges Reservoir area. First, 11 landslide impact factors were selected according to the geological data to initially construct a sample set, and the cleaned data set was obtained by twice-sample. After dividing the training set and the test set, the deep forest model was used to predict the landslide susceptibility and evaluate the accuracy. The results show that the AUC of the susceptibility prediction model built using the deep forest is 1%-10% higher than that of GBDT, MLP and other methods, while the Twice-Sample method improves the AUC by 2%.
Wind power prediction is the basis of power grid energy dispatching. However, wind instability increases the difficulty of wind power prediction. The paper proposes a wind power prediction method based on long and sho...
详细信息
Wind power prediction is the basis of power grid energy dispatching. However, wind instability increases the difficulty of wind power prediction. The paper proposes a wind power prediction method based on long and short-term memory network to improve the accuracy of wind power prediction. First, wind power sequence is decomposed by empirical mode decomposition(EMD) method, and the noise in the original sequence was removed by effective component reconstruction. Then, long shortterm memory(LSTM) with the ability of information memory predicts model of wind power sequence. The improved particle swarm optimization algorithm(IPSO) optimized the parameters of LSTM to solve the problem that the parameters of LSTM, such as the number of neurons, the learning rate and the number of iterations, are difficult to determine and thus affect the prediction accuracy of the model. Finally, the proposed EMD-IPSO-LSTM method makes rolling prediction of wind power series of actual wind farm, and the prediction results are compared with other prediction models. The results show that the prediction model has higher accuracy.
In this work,an adaptive event-triggered control approach is developed for a virtual player(VP) to generate the human-like trajectories in the mirror game,a simple yet effective paradigm for studying interpersonal ***...
详细信息
In this work,an adaptive event-triggered control approach is developed for a virtual player(VP) to generate the human-like trajectories in the mirror game,a simple yet effective paradigm for studying interpersonal *** taking into account individual motor signature,an online control algorithm is designed to produce joint improvised motions with a human player or another virtual player while exhibiting some desired kinematic *** the proposed control algorithm,the control actions can be adaptively switched according to the movement status of ***,stability analysis of the VP model driven by the feedback controller is ***,the proposed control approach is validated by matching the experimental data.
Rate of penetration(ROP) prediction is crucial for the drilling optimization and cost-savings. In this paper, a novel drilling ROP prediction method is proposed and the prediction model can be divided into two stages(...
详细信息
Rate of penetration(ROP) prediction is crucial for the drilling optimization and cost-savings. In this paper, a novel drilling ROP prediction method is proposed and the prediction model can be divided into two stages(data pre-processing and T-S fuzzy inference modeling). In the first stage, four data pre-processing techniques(Reduction, re-sampling, wavelet filtering, and normalization) are used step by step to improve the quality of drilling data. In the second stage, T-S fuzzy inference method is introduced to establish the ROP prediction model. The experiment is executed by using the data from actual drilling process and the results demonstrate the effectiveness of proposed method in prediction accuracy compared with two conventional methods(response surface method and support vector regression).
3D formation drillability field is crucial for drilling optimization and control due to its vital role in describing the spatial formation environment. Conventional geostatistical and machine learning methods are intr...
详细信息
3D formation drillability field is crucial for drilling optimization and control due to its vital role in describing the spatial formation environment. Conventional geostatistical and machine learning methods are introduced to establish the ***, the modeling accuracy should be further improved to meet the high-level requirement of drilling engineering. In this paper, a novel deep learning-based spatial modeling method is proposed for 3D formation drillability field. First of all, the drilling process and its characteristics are described and analyzed. After that, long short-term memory(LSTM), a deep learning method is proposed to establish the 3D formation drillability field model. The inputs of the model are the ground and depth coordinates and the output of the model is the formation drillability. Finally, 3D modeling and final test experiments are executed and the drilling data are from Xujiawei area, Northeast China. The results show the effectiveness of proposed method in modeling accuracy compared with four conventional methods(Random forest, Support vector regression, Scattered Interpolation, and Kriging).
Determining the position and orientation of the camera is a crucial problem with the rapidly developing technology in visual Simultaneous Localization and Mapping(SLAM),augmented reality and 3 D *** the Pn P(perspecti...
详细信息
Determining the position and orientation of the camera is a crucial problem with the rapidly developing technology in visual Simultaneous Localization and Mapping(SLAM),augmented reality and 3 D *** the Pn P(perspective-n-point) problem is an effective method to calculate the pose of the camera and is also the most widely used method in many *** this paper,the methods for Pn P problem,including special Pn P problem and general Pn P problem are summarized ***,due to importance of performing Pn P methods in practical applications,ability to handle outliers for Pn P methods is ***,the main problems of the current researches on Pn P problem are presented.
In view of the loss of speed caused by the attack of the four-rotor UAV executor, an adaptive control method is designed to maintain the altitude and posture of the UAV without the attack diagnostic mechanism. Adaptiv...
详细信息
In view of the loss of speed caused by the attack of the four-rotor UAV executor, an adaptive control method is designed to maintain the altitude and posture of the UAV without the attack diagnostic mechanism. Adaptive event trigger control methods also consider the mechanism of event triggering. The main impact of attacks on UAVs is the loss of thrust from UAVs. The attack-tolerant method designed in this paper can ensure that the tracking error of multi-acting device can maintain altitude and attitude when attacked is gradually convergent. At the same time, the event trigger method reduces the use of communication resources. Simulation proves the validity of the method.
In view of the difficulty and low accuracy of small object detection for remote sensing images, this paper proposes a small object detection algorithm based on contextual information fusion to solve the problem of rea...
详细信息
In view of the difficulty and low accuracy of small object detection for remote sensing images, this paper proposes a small object detection algorithm based on contextual information fusion to solve the problem of real-time detection accuracy of small object. In this paper, we use bottom-up VGG16 network to realize multi-scale feature extraction to deal with the problem of insufficient image feature extraction. To direct at the problem that the feature information of each feature layer is single, the shallow feature layer and the deep feature layer are fused through the feature fusion module, which achieves the purpose that some feature layers have more abundant fusion features in the structure level. Aiming at the problem that the detection objects in remote sensing images are mainly small and medium-sized objects, this paper proposes to use the multivariate information of four different scale feature layers for classification prediction and regression prediction, so as to reduce the complexity of network *** experimental results show that the proposed small object detection algorithm based on the fusion of four scale deep and shallow contextual information can obtain good accuracy and real-time performance on the NWPU VHR-10 dataset, improve the detection accuracy on the basis of ensuring the real-time detection, and perform well in the small object detection task of remote sensing images.
In modern complex industrial processes,due to poor rationalization of alarm systems and the complexity of process interconnections,alarm floods are commonly *** floods are also identified as the main causes of many in...
详细信息
In modern complex industrial processes,due to poor rationalization of alarm systems and the complexity of process interconnections,alarm floods are commonly *** floods are also identified as the main causes of many industrial *** valid approach to deal with alarm floods is to mine meaningful alarm sequential patterns from alarm *** identified patterns can help to analyze root causes or to configure dynamic alarming *** this paper,a method based on the combination of ClaSP and Top-K is proposed to mine interesting alarm sequential patterns from historical alarm *** contributions of this study are twofold:1) A pattern mining approach is adapted to mine interesting patterns from alarm flood sequences;2) A pattern compression strategy is proposed to reduce pattern redundancy.A case study is presented to demonstrate the effectiveness of the proposed method.
In this paper, we focus on the formation control problems of MAS over a directed graph with actuator and communication attacks. The considered system is composed of a leader, some followers and an attacked communicati...
详细信息
In this paper, we focus on the formation control problems of MAS over a directed graph with actuator and communication attacks. The considered system is composed of a leader, some followers and an attacked communication network. Firstly,a new distributed observer is proposed to estimate the leader information despite communication attacks. Then, for high-order nonlinear systems, we develop an adaptive control strategy to solve the actuator attack by using Nussbaum function and backstepping technique, so that the agent with actuator attacks can follow the leader’s trajectory. Finally, a simulation example is proposed to verify the results of this paper.
暂无评论