检索结果-内蒙古大学图书馆

Intelligent detection of hidden distresses in asphalt pavement based on GPR and deep learning algorithm

CONSTRUCTION AND BUILDING MATERIALS 2024年 416卷

作者： Liu, Wenchao Luo, Rong Xiao, Manzhe Chen, Yu Shandong High Speed Engn Inspection Co Ltd Jinan Shandong Peoples R China Wuhan Univ Technol Sch Transportat & Logist Engn Wuhan Peoples R China Hubei Highway Engn Res Ctr Wuhan Peoples R China

Hidden distresses of asphalt pavement are hidden dangers in the service of expressways. Efficient and accurate detection of hidden distresses is of great importance for maintaining and managing the expressways suffering from them. In this study, the intelligent detection technology of asphalt pavement hidden distresses was studied using the object detection algorithm and ground penetrating radar (GPR) image data. A GPR image data set was established to train and test the object detection model. And the distresses samples in the data set include settlement, hidden cracks and loosening. According to the distribution of hidden distresses in GPR image data, a two-way object detection model for targets of different scales was proposed, and each part of the two-way model was optimized and improved based on the basic model. At the same time, a copy-and-paste data enhancement scheme was designed to expand and balance the number of distress data samples. The final model greatly improved the detection accuracy of asphalt pavement hidden distresses. The results of the model test showed that the two-way object detection model proposed in this paper can effectively improve the detection accuracy of small-sized distress objects. Compared to the basic model, the final model had an increase of 17.9% in the average precision (AP) of small objects and a 9.9% increase in the comprehensive index AP (0.5: 0.95). The results of the ablation experiment show that the optimization methods for each part of the model improved the comprehensive detection effect of the model. When compared with other object detection models, the final model was superior to other models in all AP indicators, and had obvious advantages in the detection accuracy of the three types of hidden distresses. The confusion matrix of the test results of the final model showed that the recall rate of the final model for the three types of hidden distresses was above 96%. Thus, applying the final model established in this s

关键词： Asphalt pavement Hidden distress Ground penetrating radar (GPR) deep learning algorithm Object detection

来源：评论

学校读者我要写书评

暂无评论

Intelligent PM 2.5 mass concentration analyzer using deep learning algorithm and improved density measurement chip for high-accuracy airborne particle sensor network

引用

JOURNAL OF AEROSOL SCIENCE 2023年 167卷

作者： Lee, Seung-Soo Song, Woo-Young Kim, Yong-Jun Yonsei Univ Sch Mech Engn Seoul 03722 South Korea

The concentration of ultrafine airborne particles is continuously increasing, and research has shown that it has adverse effects when inhaled into the human body. Accordingly, there is a growing demand for a measurement network utilizing sensors to evaluate an individual's expo-sure to these airborne particles. However, the current low-cost sensors have the limitation of low accuracy. To solve this, we devised a method to calibrate a low-cost mass concentration sensor accurately in real time. In a previous study, we developed an analyzer that could measure the effective density and nanoparticles that cause the low accuracy of the mass concentration sensor. However, it had a hardware stability problem when used to monitor the outside air for a long period. This has been improved by modifying the shape of the Micro-electromechanical system (MEMS)-based chip integrated with the electrical/inertial analysis technology. Hence, the device can now operate with sufficient stability in the outdoor air. In addition, the retrieval algorithm used to convert the measured current values into the effective density and nanoparticle size distribution was prone to errors. It was modified to a deep learning-based physical parameter conversion algorithm to minimize the errors. Thus, we developed a standalone analyzer that integrates the improved nanoparticle and effective density analyzer, temperature and humidity sensor, and low-cost mass concentration sensor. In addition, we developed a technique to cali-brate the mass concentration sensor data accurately in real time based on the data measured by each sensor and analyzer and a deep learning-based mass concentration calibration algorithm. The calibration precision was confirmed through comparative evaluation of the analyzer with the results of a beta attenuation mass monitor. In the future, this analyzer can be utilized to build a sensor network that precisely monitors the mass concentration in a large area through multi-point deploy

关键词： PM 2 5 mass concentration deep learning algorithm Nanoparticle size distribution Effective density Real-time measurement Airborne particle sensor network Air quality monitoring

来源：评论

学校读者我要写书评

暂无评论

Accelerating flash calculations in unconventional reservoirs considering capillary pressure using an optimized deep learning algorithm

引用

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING 2020年 195卷 107886-107886页

作者： Zhang, Tao Li, Yiteng Sun, Shuyu Bai, Hua King Abdullah Univ Sci & Technol KAUST Computat Transport Phenomena Lab CTPL Thuwal 239556900 Saudi Arabia Petrochina Beijing Oil & Gas Pipeline Control Ctr 9 Dongzhimen North St Beijing 100007 Peoples R China

An increasing focus was placed in the past few decades on accelerating flash calculations and a variety of acceleration strategies have been developed to improve its efficiency without serious compromise in accuracy and reliability. Recently, as machine learning becomes a powerful tool to handle complicated and time-consuming problems, it is increasingly appealing to replace the iterative flash algorithm, due to the strong nonlinearity of flash problem, by a neural network model. In this study, an NVT flash calculation scheme is established with a thermodynamically stable evolution algorithm to generate training and testing data for the proposed deep neural network. With a modified network structure, the deep learning algorithm is optimized by carefully tuning neural network hyperparameters. Numerical tests indicate that the trained model is capable of accurately estimating phase compositions and states for complex reservoir fluids under a wide range of environmental conditions, while the effect of capillary pressure can be captured well. Thermodynamic rules are preserved well through our algorithm, and the trained model can be used for various fluid mixtures, which significantly accelerates flash calculations in unconventional reservoirs.

关键词： Phase equilibrium NVT Flash calculation Capillary pressure deep learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Prediction method for thermal-hydraulic parameters of nuclear reactor system based on deep learning algorithm

引用

APPLIED THERMAL ENGINEERING 2021年 196卷 117272-117272页

作者： Lu, Qi Yuan, Yuan Li, Fengchen Yang, Bo Li, Zhe Ma, Yu Gu, Yiyu Liu, Dingming Sci & Technol Reactor Syst Design Technol Lab Chengdu 610041 Peoples R China Nucl Power Inst China Chengdu 610041 Peoples R China Sichuan Univ Coll Phys Sci & Technol Chengdu 610065 Peoples R China Tianjin Univ Sch Mech Engn Tianjin 300350 Peoples R China Sun Yat Sen Univ Sino French Inst Nucl Engn & Technol Zhuhai 519082 Peoples R China

The nuclear reactor core and the steam generator are the core components of nuclear reactor system, which directly determine the heat releasing and carrying capacity of nuclear reactor system. The traditional thermalhydraulic design of nuclear reactor system generally selects the linear iterative mode, which requires the repeated "calculation-evaluation-correction". The whole process is tedious and time-consuming, which also relies on the design experience. In recent years, the successful application of artificial intelligence technology in many fields has brought new enlightenment to the innovation for the thermal-hydraulic design of nuclear reactor system. In this paper, a prediction program for the thermal-hydraulic parameters of nuclear reactor system was established by means of deep learning algorithm, which was mainly composed of the neural network module, the activation function module, the error function module, the optimization algorithm module and the data initialization module. Then, the KLT-40S nuclear reactor core and the tube-in-tube once-through steam generator were selected as the analysis objects, and the corresponding input card of RELAP5/SCDAPSIM program was built. Based on the prediction program, the calculation results of RELAP5/SCDAPSIM program were studied, which could realize the rapid prediction for the thermal-hydraulic parameters of nuclear reactor system, and were in good agreement with the calculation results of RELAP5/SCDAPSIM program.

关键词： Nuclear reactor core Once-through steam generator Thermal-hydraulic design deep learning algorithm Neural network

来源：评论

学校读者我要写书评

暂无评论

Data-driven method based on deep learning algorithm for detecting fat, oil, and grease (FOG) of sewer networks in urban commercial areas

引用

WATER RESEARCH 2021年 207卷 117797-117797页

作者： Jiang, Yiqi Li, Chaolin Zhang, Yituo Zhao, Ruobin Yan, Kefen Wang, Wenhui Harbin Inst Technol Sch Civil & Environm Engn Shenzhen 518055 Peoples R China Harbin Inst Technol State Key Lab Urban Water Resource & Environm Harbin 150090 Peoples R China

The content of fat, oil and grease (FOG) in the sewer network sediments is the key indicator for diagnosing sewer blockage and overflow. However, the traditional FOG detection is time-consuming and costly, and the establishment of mathematical models based on statistical methods to predict the content of FOG fail to provide satisfactory accuracy. Herein, a deep learning algorithm used a data-driven FOG content prediction model is proposed to achieve a more accurate prediction of FOG content. Meanwhile, global sensitivity analysis (GSA) is exploited to evaluate the contribution of input indicators to the output indicator (FOG) in the model, so that some input indicators that have less impact on the prediction performance can be screened out, the best combination of input indicators can be determined, and the operation cost of the model can be reduced. To evaluate the effectiveness of the proposed model, a case study was conducted in a city in southern China. The experimental results indicate that the prediction model obtains good FOG estimations and performs well from a single site to multiple sites with a mean R-2 of 0.922, showing a good generalization performance. Through GSA, the key input indicators in the model were identified as pH, water temperature (T), relative humidity (RH), sewage flow (Flow), drinking water supply (DWS), velocity (V) and conductivity (sigma), and the input indicators such as air pressure (AP), population (Pop.), and liquid level (LV) can be reduced without affecting the prediction accuracy of the model.

关键词： Fat, oil, and grease (FOG) Sewer networks deep learning algorithm Gated recurrent unit (GRU) Multi-source data global sensitivity analysis (GSA)

来源：评论

学校读者我要写书评

暂无评论

Research on color fusion model of historic and cultural blocks in Shanghai based on deep learning algorithm-take Tianzifang as an example

引用

CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE 2023年第4期35卷 e7530-e7530页

作者： Wei, Zhen Nie, Jinghuan East China Normal Univ Shanghai Peoples R China Shanghai Univ Engn Sci Shanghai 201620 Peoples R China

Color fusion is an extremely important part in the reconstruction design of historic and cultural blocks in the process of China's urban historic and cultural blocks transformation. Based on the deep learning algorithm, this paper constructs the color analysis model of cultural blocks, uses the multiscale feature semantic segmentation algorithm analysis technology of dual channel fusion for color research, extracts and analyzes the color of historic and cultural blocks, thus establishes its color fusion model, analyzes the color defects of Tianzifang historic and cultural scenic spot, and proposes to use plants, buildings and pavements to improve the color fusion degree of Shikumen cultural blocks.

关键词： architectural color protection deep learning algorithm historic and cultural blocks multiscale feature semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

High Throughput Blood Analysis Based on deep learning algorithm and Self-Positioning Super-Hydrophobic SERS Platform for Non-Invasive Multi-Disease Screening

引用

ADVANCED FUNCTIONAL MATERIALS 2021年第51期31卷 2103382-2103382页

作者： Lin, Xueliang Lin, Duo Chen, Yang Lin, Jincheng Weng, Shuyun Song, Jibin Feng, Shangyuan Fujian Normal Univ Digital Fujian Internet Things Lab Environm Monit Fujian Prov Key Lab Photon Technol Minist EducKey Lab OptoElect Sci & Technol Med Fuzhou 350007 Peoples R China Fujian Med Univ Dept Lab Med Fuzhou 350007 Peoples R China Fuzhou Univ Coll Chem MOE Key Lab Analyt Sci Food Safety & Biol Sch Math & Comp Sci Fuzhou 350116 Peoples R China

Blood analysis is crucial for early cancer screening and improving patient survival rates. However, developing an effective strategy for early cancer detection using high-throughput blood analysis is still challenging. Herein, a novel automatic super-hydrophobic platform is developed together with a deep learning (DL)-based label-free serum and surface-enhanced Raman scattering (SERS), along with an automatic high-throughput Raman spectrometer to build an effective point-of-care diagnosis system. A total of 695 high-quality serum SERS spectra are obtained from 203 healthy volunteers, 77 leukemia M5, 94 hepatitis B virus, and 321 breast cancer patients. Serum SERS signals from the normal (n = 183) and patient (n = 443) groups are used to assess the DL model, which classify them with a maximum accuracy of 100%. Furthermore, when SERS is combined with DL, it exhibits excellent diagnostic accuracy (98.6%) for the external held-out test set, indicating that this method can be used to develop a high throughput, rapid, and label-free tool for screening diseases.

关键词： deep learning algorithm high throughput assays label-free detection super-hydrophobic platforms surface-enhanced Raman scattering

来源：评论

学校读者我要写书评

暂无评论

Research on internet financial risk control based on deep learning algorithm

引用

SOFT COMPUTING 2023年

作者： Wu, Ziai Zhou, Qiao Wang, Lijuan Zhao, Di Chizhou Univ Local Res Ctr Ecommerce Serv Chizhou 247000 Anhui Peoples R China Philippine Christian Univ Ctr Int Educ Manila 1006 Philippines Chi Zhou Emerging Ind Grp Co Chizhou 247000 Anhui Peoples R China

With the rapid development of Internet technology, Internet finance has entered thousands of households, bringing a lot of convenience to people's lives. As a financial model based on Internet technology, compared with traditional bank loans, online loans have lower operating costs and faster returns, so they are developing rapidly. Providing users with better and faster services while standardizing operations has always been the development goal of various Internet finance companies. At present, many domestic Internet financial enterprises are facing many problems such as difficulty in risk control. Therefore, this paper makes full use of deep learning algorithms to build an Internet financial risk control system. After in-depth analysis and research on the deep learning algorithm, the Internet financial risk control system is divided into several modules. The project mainly includes model management module, user behavior analysis module, alarm management module, monitoring module, product management module, etc., and then by analyzing the test results of each test scenario, it is concluded that the performance test of the system design meets the actual needs of users, and simulates the test. It is carried out in accordance with the constraints and regulations of the test plan, and the performance test meets the standard. The system not only ensures the safety of the company's funds, but also helps the company to form a smooth and effective financial risk control process. This paper designs a class of effective management systems by applying deep learning algorithms to the field of Internet financial risk control.

关键词： deep learning algorithm Internet Financial risk control System design

来源：评论

学校读者我要写书评

暂无评论

Network Mathematical Virtual Data Analysis Model Based on deep learning algorithm

引用

Procedia Computer Science 2024年 243卷 372-379页

作者： Xiaojie Teng Shandong Vocational College of Science and Technology Weifang Shandong China

In today's era of big data, people need to extract valuable and nutritious information from these data, but for the huge database, manual browsing and manual retrieval by ordinary users are obviously inefficient. Network data analysis can help users to study network data and deeply understand the embedded value of big data, which is popular in both civil and industrial and academic circles. This article aimed to use intelligent mathematical models to assist in the construction of network data analysis models and enabled the model to be repeatedly trained in the training set based on deep learning algorithms, becoming increasingly able to identify patterns between data.

关键词： deep learning algorithm Intelligent Mathematical Model Network Data Analysis Model Regularization Processing Convolutional Neural Network

来源：评论

学校读者我要写书评

暂无评论

Application Exploration of Visual Recognition Technology Based on deep learning algorithm in Website Development

引用

Procedia Computer Science 2024年 247卷 438-444页

作者： Huixin Zhu Department of Information Engineering Shandong Vocational College of Science and Technology Weifang Shandong China

With the rapid development of Internet technology, the amount of information we face is becoming more and more enormous. Traditional recognition methods have been unable to meet the needs of acquiring image content quickly and effectively. In this Internet age, developing websites is an essential job. From the perspective of deep learning algorithm, this paper studies and discusses a system based on deep neural network model, which aims to meet the user's personalized demand feature extraction. Through this system, the compatibility of users in different browsers can be obtained in real time, and the characteristics of images can be analyzed according to this information. This performance was then tested and analyzed, and the results showed that Chrome performed well in terms of compatibility, achieving the highest score of 9 out of all browsers. It was followed by Firefox and Safari, which scored 8 and 7 points, respectively. However, Edge and Opera had low compatibility scores of just 6 and 5, placing them at the bottom of the list.

关键词： deep learning algorithm Visual Recognition Website Development Application Exploration

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：