检索结果-内蒙古大学图书馆

Fault Detection, Classification and Localization Along the Power Grid Line Using Optimized Machine Learning algorithms

引用

INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE SYSTEMS 2024年第1期17卷 49-49页

作者： Najafzadeh, Masoud Pouladi, Jaber Daghigh, Ali Beiza, Jamal Abedinzade, Taher Islamic Azad Univ Dept Elect Engn Shabestar Branch Shabestar Iran

Distributed energy generation increases the need for smart grid monitoring, protection, and control. Localization, classification, and fault detection are essential for addressing any problems immediately and resuming the smart grid as soon as possible. Simultaneously, the capacity to swiftly identify smart grid issues utilizing sensor data and easily accessible frequency and voltage data from PMU devices is a prerequisite of this task. Therefore, this paper proposes new methods using fuzzy logic and adaptive fuzzy neural networks as well as machine learning and meta-heuristic algorithms. First, line voltage is used by a fuzzy thresholding method to estimate when a transmission line defect would develop in less than 1.2 clock cycles. Next, features taken from frequency signals in the real-time interval are utilized to classify the type of error using machine learning systems (decision tree algorithm and random forest algorithm) optimized with wild horse meta-heuristic algorithm. To locate the precise problem location, we finally use a neural fuzzy inference system that is capable of adapting to new data. We employ a simulated power transmission system in MATLAB to test our proposed solutions. Mean square error (MSE) and confusion matrix are used to assess the efficiency of a classifier or detector. For the decision tree algorithm method, the detector attained an acceptable MSE of 2.34e-4 and accuracy of 98.1%, and for the random forest algorithm method, an acceptable MSE of 3.54e-6 and accuracy of 100%. Furthermore, the placement error was less than 153.6 m in any direction along the line.

关键词： Fault detection and classification Smart network Fault localization Wild horse optimization algorithm Fuzzy neural inference system decision tree algorithm Random forest algorithm

来源：评论

学校读者我要写书评

暂无评论

Environmental cost control system of manufacturing enterprises using artificial intelligence based on value chain of circular economy

引用

ENTERPRISE INFORMATION SYSTEMS 2022年第8-9期16卷 Article: 1856422页

作者： Chen, Min Liu, Qian Huang, Shuai Dang, Chenlu Wenzhou Univ Acad Financial Res Sch Business Wenzhou Peoples R China Suihua Univ Sch Literature & Media Suihua Peoples R China Shanghai Univ Finance & Econ Sch Publ Econ & Adm Shanghai Peoples R China Xian Int Studies Univ Sch Econ & Finance Xian 710128 Peoples R China

In this study, expecting to form a virtuous circle conducive to socio-economic development. The problems of environmental cost control mode, and the relationship between the value chain and environmental cost control was discussed. The decision tree algorithm of artificial intelligence (AI) was applied in designing the environmental cost control system of manufacturing enterprises to realise the internalisation of environmental cost. The external environmental consumption cost was calculated by taking an oil production plant as the research object according to the environmental cost report of the oil production plant, and relevant suggestions were proposed for the enterprise's environmental cost scheme control.

关键词： Circular economy manufacturing enterprises environmental cost control artificial intelligence decision tree algorithm value chain

来源：评论

学校读者我要写书评

暂无评论

Copper particle detection method by in-situ resistance background implemented in conductance-path recognition algorithm (iRB-CPR) among dominant aluminum particles

引用

MEASUREMENT 2022年 193卷 1页

作者： Sejati, Prima Asmara Baidillah, Marlin Ramadhan Prayitno, Yosephus Ardean Kurnianto Ibrahim, Kiagus Aufa Kawashima, Daisuke Takei, Masahiro Chiba Univ Grad Sch Sci & Engn Dept Mech Engn Div Fundamental Engn Chiba 2638522 Japan Univ Gadjah Mada Vocat Coll Dept Elect Engn & Informat Yogyakarta 55281 Indonesia Natl Res & Innovat Agcy Jakarta 10340 Indonesia Univ Gadjah Mada Vocat Coll Dept Mech Engn Yogyakarta 55281 Indonesia Chiba Univ Grad Sch Engn Dept Mech Engn Div Fundamental Engn Chiba Japan

Copper particle has been detected among dominant aluminum particles by in-situ resistance background implemented in conductance-path recognition algorithm (iRB-CPR). The iRB is a particle volume fraction prediction from a resistance background database measured by shifted-four-wire measurement (SRM) in various particle arrangements. The CPR is adopted from a decision tree algorithm to predict the particle conductance path by comparing the real-condition resistances classified by iRB. The selected resistance background is used as a denominator to normalize the resistance measurement by SRM under unknown particle arrangement in the real condition. Finally, Cu is detected by comparing the normalized resistances with the normalized spatial-mean resistance. The iRB-CPR successfully suppress the resistance deviation ratio in the simulation (r)(sim) 93.8% and experiment (r)(exp) 73.9%. Moreover, the Cu detection by iRB-CPR satisfies give a low error E-S = 6.11% at S = 180 under alpha = 10%. This research opens a new detection modality as a part of non-ferrous metal particles recovery.

关键词： Electrical resistance measurement Conducting path Non-ferrous metal particles decision tree algorithm

来源：评论

学校读者我要写书评

暂无评论

Fault diagnosis of antifriction bearings through sound signals using support vector machine

引用

JOURNAL OF VIBROENGINEERING 2012年第4期14卷 1601-1606页

作者： Kumar, Hemantha Kumar, T. A. Ranjit Amarnath, M. Sugumaran, V. Birla Inst Technol & Sci Pilani Pilani Rajasthan India Indian Inst Informat Technol Design & Mfg Jabalpu Jabalpur Madhya Pradesh India Vellore Inst Technol Madras 600048 Tamil Nadu India

Bearings constitute a crucial part of machinery that need to be continuously monitored. Major breakdowns can be prevented if bearing defects are identified at the earlier stage. Sound signals of the bearings can be used to continuously monitor bearing life. This paper uses sound signals acquired in bearings under healthy and simulated faulty conditions for the purpose of fault diagnosis through machine learning approach. The statistical features were extracted from the sound signals. Significantly important features were selected using J48 decision tree algorithm. Support Vector Machine (SVM) is used as a classifier. The selected features were given as inputs for the c-SVM and v-SVM (nu - SVM) model of SVM and their classification accuracies were compared.

关键词： bearing fault diagnosis decision tree algorithm feature selection machine learning approach Support Vector Machine

来源：评论

学校读者我要写书评

暂无评论

Analysis of Seasonal Driving Factors and Inversion Model Optimization of Soil Moisture in the Qinghai Tibet Plateau Based on Machine Learning

引用

WATER 2023年第16期15卷 2859页

作者： Deng, Qinghai Yang, Jingjing Zhang, Liping Sun, Zhenzhou Sun, Guizong Chen, Qiao Dou, Fengke Shandong Univ Sci & Technol Coll Earth Sci & Engn Qingdao 266590 Peoples R China Shandong Prov Res Inst Coal Geol Planning & Explo Jinan 250104 Peoples R China

The accuracy of soil moisture retrieval based on traditional microwave remote sensing models in the Qinghai Tibet Plateau (QTP) is unstable due to its unique plateau climate. However, considering the impact of multiple multi-scale factors effectively improves the accuracy and stability of soil moisture inversion. This article uses Sentinel-1 and seasonal climate data to analyze factors and influencing mechanisms of soil moisture in the QTP. First, an artificial neural network (ANN) was used to conduct a significance analysis to screen significant influencing factors to reduce the redundancy of the experimental design and insert information. Second, the normalization effect of each factor on the soil moisture inversion was determined, and the factors with significant normalization influences were input to fit the model. Third, different fitting methods combined the semi-empirical models for soil moisture inversion. The decision tree Chi-square Automatic Interaction Detector (CHAID) analyzed the model accuracy, and the Pearson correlation coefficient between the sample and measured data was tested to further validate the accuracy of the results to obtain an optimized model that effectively inverts soil moisture. Finally, the influencing mechanisms of various factors in the optimization model were analyzed. The results show that: (1) The terrain factors, such as elevation, slope gradient, aspect, and angle, along with climate factors, such as temperature and precipitation, all have the greatest normalized impact on soil moisture in the QTP. (2) For spring (March), summer (June), and autumn (September), the greatest normalized factor of soil moisture is the terrain factor. In winter (December), precipitation was the greatest factor due to heavy snow cover and permafrost. (3) Analyzing the impact mechanism from various factors on the soil moisture showed a restricted relationship between the inversion results and the accuracy of the power fitting model, meaning it is uns

关键词： Sentinel-1 semi-empirical model artificial neural networks decision tree algorithm

来源：评论

学校读者我要写书评

暂无评论

Impedance technique combined with supervised algorithms-based internal degradation state classification and its economic analysis for safety in retired battery pack

引用

JOURNAL OF ENERGY STORAGE 2023年 73卷

作者： Lee, Miyoung Han, Dongho Yoo, Kisoo Kim, Jonghoon Chungnam Natl Univ Dept Elect Engn Energy Storage & Convers Lab Daejeon 34134 South Korea Yeungnam Univ Sch Mech Engn Gyoungsan 38541 South Korea

As the growth of lithium-ion batteries (LIBs) applications accelerates, future problems for waste LIB disposal are also appeared. When LIB reaches 80 % of the initial capacity, it is defined as the End-of-life (EOL). Since power and capacity of the LIB abruptly decreases at this point, it is determined that the LIB can't be used. However, in the case of the battery pack, even if it reaches 80 % of its initial capacity, it can be reused with secondary applications such as energy storage devices and uninterruptible power supplies (UPS). Therefore, in order to reduce environmental problems, such a battery pack reuse technique is required. However, as the internal degradation state of the LIB differs depending on the operating environment, research is needed to select the LIB in the same state through classification algorithm and configure the waste battery pack. Since the internal degradation of LIB cannot be evaluated qualitatively with existing technology, like capacity and internal resistance, so a new qualitative evaluation factor is required. This research classified an internal degradation state according to LIB environment using an impedance technique and supervised algorithms (decision tree, Support vector machine, K-nearest neighbor) that could qualitatively represent LIB degradation mechanism. And it is validated that new parameters are good at classifying operating environment compared with existing parameters. Also, Economic analysis was performed for comparison with existing methods, and as a result, it was proved that it showed superior performance compared to existing techniques in both classification accuracy and economic analysis.

关键词： Electrochemical impedance spectroscopy (EIS) Classification algorithm Support vector machine (SVM) decision tree algorithm K-nearest neighbor algorithm (KNN) Battery operating environment classification

来源：评论

学校读者我要写书评

暂无评论

Fault Diagnosis of Welded Joints through Vibration Signals Using Naïve Bayes algorithm

引用

Procedia Materials Science 2014年 5卷 1922-1928页

作者： M. Girish Kumar K. Hemanth N. Gangadhar Hemantha Kumar Prasad Krishna Nano Manufacturing Technology Centre Central Manufacturing Technology Institute Tumkur RoadBangalore-560022India Department of Mechnaical Engineering National Institute of Technology Karanataka Surathkal Mangalore-575025 India

Inspection of welded joints plays a crucial role in finding internal flaws and defects in specimens, finding quality of welded joint in early stage will reduce damage and provides safety in many manufacturing industries. For this reason many testing methods have been used to test a material for surface or internal flaws without interfering in any way with its suitability for service. Vibration analysis can be used to identify the defect in welded joints. This paper uses the vibration signals acquired using the accelerometer in welded specimen for defect free welded joint and induced defect in welded joint for fault diagnosis through machine learning approach for online welded joint quality monitoring. The statistical features were extracted from the vibration signals. Significantly important features were selected using decision tree (J48) algorithm and Naive Bayes algorithm is used as a classifier. The selected features were given as inputs for the classifier and their classification accuracies were compared. Results of Naive Bayes Classifier algorithm were used to learn and classify the condition of welded joints, also found its accuracy as of 85.56%. Hence, the Naive Bayes Classifier model can be practically used for diagnosing the condition of the welded joint quality successfully.

关键词： Condition monitoring decision tree algorithm Accelerometer feature selection Naïve Bayes algorithm.

来源：评论

学校读者我要写书评

暂无评论

Analyzing the impact of social capital on US based Kickstarter projects outcome

引用

HELIYON 2021年第7期7卷 e07425页

作者： Onginjo, Joseph Ochieng Zhou, Dong Mei Berhanu, Tesema Fiseha Belihu, Sime Welde Gebrile Univ Elect Sci & Technol China Sch Management & Econ Qingshuihe Campus2006 Xiyuan Ave Chengdu 611731 Sichuan Peoples R China Zhejiang Lab Bldg 101818 Wenyi West RdICP 18016057 Icp No 18016057 Zhejiang Peoples R China Fayetteville State Univ Dept Mkt Management & Entrepreneurship 1200 Murchison Rd Fayetteville NC 28301 USA

The essence of this paper is to analyse the ripple effects caused from the intertwining and complex relationship between the relational and structural dimensions of social capital on the US based Kick starter projects' outcomes. This will be measured based on real time data collected from the Kick starter. com in form of 1157 projects organised in the structure of the number of backers, amount of time taken to fund the projects and the converted amount pledged towards the projects, as classified according to various project categories and geographical locations. This research applies qualitative and quantitative statistical analysis methods as well as data mining techniques;k-Nearest Neighbour, Naive Bayes and decision tree algorithms. The results from this research confirm that relational social capital i.e. the number of backers involved in the projects, has significantly strong and positive impact on the converted amount pledged towards a project and the project outcome. This paper also offers a feasible decision-making model that will be used by the entrepreneurs in the future to determine which type of project categories an entrepreneur can choose to host and the project outcome.

关键词： Social capital theory dimensions Crowdfunding k-nearest neighbor Naive Bayes decision tree algorithm

来源：评论

学校读者我要写书评

暂无评论

Modeling the prediction of business intelligence system effectiveness

引用

SPRINGERPLUS 2016年第1期5卷 737页

作者： Weng, Sung-Shun Yang, Ming-Hsien Koo, Tian-Lih Hsiao, Pei-I Natl Taipei Univ Technol Dept Informat & Finance Management 1Sec 3Zhongxiao E Rd Taipei 10608 Taiwan Fu Jen Catholic Univ Dept Informat Management 510 Zhongzheng Rd New Taipei 24205 Taiwan Shih Chien Univ Dept Accounting 70 Ta Chih St Taipei 10462 Taiwan

Although business intelligence (BI) technologies are continually evolving, the capability to apply BI technologies has become an indispensable resource for enterprises running in today's complex, uncertain and dynamic business environment. This study performed pioneering work by constructing models and rules for the prediction of business intelligence system effectiveness (BISE) in relation to the implementation of BI solutions. For enterprises, effectively managing critical attributes that determine BISE to develop prediction models with a set of rules for self-evaluation of the effectiveness of BI solutions is necessary to improve BI implementation and ensure its success. The main study findings identified the critical prediction indicators of BISE that are important to forecasting BI performance and highlighted five classification and prediction rules of BISE derived from decision tree structures, as well as a refined regression prediction model with four critical prediction indicators constructed by logistic regression analysis that can enable enterprises to improve BISE while effectively managing BI solution implementation and catering to academics to whom theory is important.

关键词： Business intelligence Prediction model decision tree algorithm Logistic regression analysis

来源：评论

学校读者我要写书评

暂无评论

ANALYSIS OF ABNORMAL FREEZING DATA AND UPDATING algorithm FOR ELECTROMECHANICAL ENERGY METER TERMINALS

引用

SCALABLE COMPUTING-PRACTICE AND EXPERIENCE 2024年第5期25卷 3342-3354页

作者： Zhao, Shuzhi Du, Yue He, Shanshan Bian, Jiao Shi, Jiabo State Grid Jibei Elect Power Co Ltd Tangshan Power Supply Co Tangshan 063000 Hebei Peoples R China

Due to the rapid development of science and information technology, electricity information acquisition system has been widely used in the electricity data collection of users. With the massive electricity data collection, it is difficult to adopt traditional data processing methods to meet the abnormal data processing. In order to effectively mine abnormal information in electricity consumption data, an anomaly detection model based on the Isolation Forest (iForest) algorithm is proposed. Firstly, the daily load curve with strong regularity is used as the characteristic index of anomaly monitoring, and the users with abnormal electricity consumption data are preliminarily screened. Secondly, on the basis of electrical variables, the suspected abnormal users are further analyzed, and the anomaly identification model of electricity data is established to automatically classify the voltage at the metering point. Moreover, combined with the current data, the abnormality of the electric energy metering device is identified, and then the validity of the model is determined through on-site verification. Finally, according to the participating voltage of the fault phase, the 96-point voltage data frozen during the failure period is analyzed and the correction coefficient is adjusted. The results reveal that the electricity data detection model based on the iForest algorithm has significant advantages in computational efficiency. Through the cumulative recall and Precision-Recall (P-R) curves of the model, it is found that the majority of abnormal users can be detected only by detecting a few users with high abnormal scores, which shows that the model has high efficiency. The decision tree algorithm combined with the current data can effectively identify the anomalies of the energy metering device, which verifies the validity of the anomaly identification model of the electricity consumption data.

关键词： Energy meter Electricity information acquisition system Abnormal electricity consumption data Isolated Forest algorithm decision tree algorithm

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：