The rate of penetration (ROP) is a critical indi-cator for evaluating drilling efficiency. Developing an accurate ROP model is essential for optimizing drilling performance and addressing process control challenges. H...
详细信息
ISBN:
(数字)9798331521950
ISBN:
(纸本)9798331521967
The rate of penetration (ROP) is a critical indi-cator for evaluating drilling efficiency. Developing an accurate ROP model is essential for optimizing drilling performance and addressing process control challenges. However, ROP modeling in deep geological drilling is complicated by nonlinearity, diverse working conditions, and high-dimensional variations. To overcome these challenges, a fusion modeling approach for ROP is proposed. First, the fuzzy C-means clustering method is applied to classify drilling data into different working con-ditions. Based on this classification, support vector regression is employed to develop ROP sub-models, effectively addressing nonlinearity. To further enhance model accuracy, an improved dung beetle optimization algorithm (IDBO) is designed to deter-mine optimal model parameters and integrate the sub-models, thereby resolving issues related to multiple working conditions and high-dimensional variations. The IDBO incorporates four key enhancements, average weight, chaos disturbance, modified local search, and re-updating of the best solution, to strength-en its global search capability. Comparative results using the IEEE CEC2017 benchmark test functions demonstrate that the proposed algorithm outperforms others in 12 test functions, highlighting its strong global optimization ability. Additionally, results from real-world drilling data validate the effectiveness of the proposed modeling approach in practical applications.
Geo-hazards have become one of the main disasters endangering the safety of people's lives and property in the world. In order to improve the early warning of disasters, a persistent monitoring method of multi-age...
Geo-hazards have become one of the main disasters endangering the safety of people's lives and property in the world. In order to improve the early warning of disasters, a persistent monitoring method of multi-agent systems is proposed in this work. To ensure that the agent's energy is never exhausted, the set invariance constraint is included in the optimization problem. The goal is to minimize the difference between the actual control input of the robot and the nominal control input corresponding to the task to be performed. Moreover, the control barrier function (CBF) is used to transform the forward invariance of a subset of the robot state space into a control input constraint. The coverage control method in an uncertain environment is verified by numerical simulation. This work provides new insights into effective monitoring and early warning of geo-hazards.
Sample generation is an effective method to improve the performance of hyperspectral image classification by generating virtual samples for training sample expansion in the training process of classification. However,...
详细信息
With the bursting of autonomous and assistant driving systems, traffic accident prediction has attracted increasing attention during the past few years. However, predicting traffic accidents is extremely challenging d...
详细信息
In this paper, a template matching and trend feature analysis-based data pre-processing method for seismic wave detection is proposed with two stages. In the first stage, it involves extracting the rock physical param...
In this paper, a template matching and trend feature analysis-based data pre-processing method for seismic wave detection is proposed with two stages. In the first stage, it involves extracting the rock physical parameters from seismic wave detection results using OCR (Optical Character Recognition) method, and extracting the original rock physical parameters from the raw rock property table using keyword matching method. Using the rock physical parameters as a template, a template matching approach is employed to eliminate abnormal values from the original rock physical parameters. In the next stage, a technique is proposed to extract trend features of rock physical parameters for conducting advanced geological forecasting, which considered the expertise of experts in interpreting seismic wave detection data. Finally, the effectiveness of the proposed method is verified by the compared simulation results.
For hybrid energy storage systems in DC microgrids, a droop control consisting of virtual capacitors and virtual resistors can decompose power into high-frequency components and low-frequency components, then assign t...
For hybrid energy storage systems in DC microgrids, a droop control consisting of virtual capacitors and virtual resistors can decompose power into high-frequency components and low-frequency components, then assign them to batteries and supercapacitors to respond respectively. However, aiming at the service life of the energy storage system, this paper considers the characteristics and key parameters of the hybrid energy storage structure and proposes an adaptive drooping comprehensive control strategy considering the SOC of the energy storage unit given the shortcomings of power distribution within the current hybrid energy storage. According to the self-regulation capacity of each energy storage unit, it is sorted and constrained, and protected by using SOC, which ensures the economy and safety of the system while ensuring power distribution. The traditional droop control and adaptive droop control are simulated to verify the effectiveness of the proposed control strategy.
Landslide displacement prediction is an important and indispensable part of landslide monitoring and warning. The change of the displacement is always considered being related to inducing factors, which are aimed at i...
Landslide displacement prediction is an important and indispensable part of landslide monitoring and warning. The change of the displacement is always considered being related to inducing factors, which are aimed at improving accuracy of the predicted model. However, the seasonal characteristic of the displacement, which has not been carefully analyzed, reveals the law of inducing factors. In order to gain a deeper understanding of characteristics, the Baijiabao landslide is taken as an example. The variational mode decomposition (VMD) method, which can extract effective information well, is introduced to decompose the displacement. Introducing the seasonal parameters, the seasonal autoregressive integrated moving average (SARIMA) model is established to predict the displacement subseries. Finally, accumulative displacement prediction values are obtained by superimposing the predicted subseries. With higher accuracy and lower error, the VMD-SARIMA model proves a better option in application compared with VMD-ARIMA, SARIMA and ARIMA models.
Molten iron is the primary output of blast furnace production. The content of silicon in molten iron clearly correlates with blast furnace temperature. However, due to the intricate conditions of blast furnace product...
详细信息
Molten iron is the primary output of blast furnace production. The content of silicon in molten iron clearly correlates with blast furnace temperature. However, due to the intricate conditions of blast furnace production, the silicon content in molten iron is nonlinear and unstable. Therefore, this paper adopts variational mode decomposition (VMD) to decompose and extract the feature information of the real silicon content data of LY Steel in March 2022, then uses Grey Wolf optimization (GWO) algorithm to optimize the parameters of the support vector regression (SVR) prediction model, and takes the decomposed data as model input for experimental verification. By comparing the predicted results with the real historical data of blast furnace production, it is found that the degree of fit is about 94.2%, which offers a new idea for the prediction of silicon content.
Deep learning is currently the mainstream method for ceramic defect detection, and it requires a large number of defect samples to train the network. However, collecting these defect samples is very time-consuming and...
详细信息
Deep learning is currently the mainstream method for ceramic defect detection, and it requires a large number of defect samples to train the network. However, collecting these defect samples is very time-consuming and deep learning suffers from few-shot learning problems. In this study, a StyleGAN3-based data augmentation method for ceramic defect detection was proposed which can generate ceramic defect samples and thus reduce the data collection work. Experiments show that our method uses less training time, has a more stable training process, and can improve the accuracy of the detection network.
This paper addresses the robust finite-time stabi-lization (FTS) issue for stochastic parabolic PDE systems via non-fragile spatial sampled-data control scheme. First, a class of distributed parameter systems characte...
This paper addresses the robust finite-time stabi-lization (FTS) issue for stochastic parabolic PDE systems via non-fragile spatial sampled-data control scheme. First, a class of distributed parameter systems characterized by the delayed stochastic parabolic partial differential equation is developed for analyzing the effects of stochastic disturbance, structural uncertainty, and discrete delay on the system performance. Then, a non-fragile spatial sampled-data control scheme is established by setting sampling points in the spatial domain, which effectively saves communication resources and ensures that the closed-loop system maintains good performance when the controller is perturbed. Moreover, based on the partial differential equation theory, stochastic analysis approach, and the extended Wirtinger's inequality technique, several criteria are provided to ensure the robust FTS of stochastic parabolic PDE systems in the mean square sense. Lastly, a numerical example is provided to verify the feasibility of the suggested stabilization criteria and control scheme.
暂无评论