An Improved Feature Selection Method Based on Random Forest Algorithm for Wind Turbine Condition Monitoring

Guo, Luobin; Wang, Chensheng; Zhang, Di; Yang, Gye Mo

doi:10.3390/s21165654

Cited by 16 publications

(12 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(2) HOG + KNN image classification method. Firstly, take the moldy tobacco leaves, green miscellaneous tobacco leaves, and variegated tobacco leaves in the data set as positive samples and normal tobacco leaves as negative samples, and then collect the HOG characteristics of positive and negative samples to establish Feature Engineering [18]. For the KNN algorithm, this paper uses the KNeighborsClassifier function encapsulated by sklearn, where the K value is set to 3. e experimental results of the convolution neural network model built in this paper are compared with the experimental results of the traditional image classification methods.…”

Section: Results Analysismentioning

confidence: 99%

Rapid Identification of Tobacco Mildew Based on Random Forest Algorithm

Jiang

Zhang

Huang

et al. 2022

Scientific Programming

View full text Add to dashboard Cite

In order to further improve the identification efficiency of tobacco mildew, a rapid identification model of tobacco mildew based on random forest algorithm was proposed in this study. In order to ensure the feasibility and pertinence of the model study, this study takes redried leaf tobacco as the research object, selects high-temperature and high-humidity environment as the experimental conditions, and obtains the sample data of the degree of tobacco mildew under different experimental conditions. At the same time, this paper constructs a rapid identification model of tobacco mildew with the help of random forest algorithm. Through the model experimental results, it is found that the accuracy of the model for the rapid identification of training samples can reach 93.82%, while the accuracy of independent testing is 94.84%. The experimental results fully reflect the availability and efficiency of the random forest algorithm model in the rapid identification of tobacco mildew.

show abstract

Section: Results Analysismentioning

confidence: 99%

Rapid Identification of Tobacco Mildew Based on Random Forest Algorithm

Jiang

Zhang

Huang

et al. 2022

Scientific Programming

View full text Add to dashboard Cite

show abstract

“…This includes gathering facts about the electric structures, which include sensor readings, gadget specifications, renovation records, and historic failure data. The accrued information ought to be preprocessed to eliminate brand new outliers, manage lacking values, and normalize the features to ensure correct evaluation and model development (Li et al, 2021).…”

Section: Statistics Collection and Preprocessingmentioning

confidence: 99%

Exploring Machine Learning Techniques to Maximize Efficiency in Construction Industry Electrical and Electronics Engineering Projects

Obinnaya Chikezie Victor

2023

IJAIML

View full text Add to dashboard Cite

The construction industry plays a vital role in the global economy but grapples with inefficiencies in electrical and electronics engineering projects, resulting in delays, increased costs, and reduced productivity. This study explores the application of machine learning techniques to enhance efficiency in these projects. Specifically, it focuses on developing and implementing machine learning algorithms for optimizing project scheduling, material procurement, and equipment utilization. Additionally, predictive analytics will be examined for risk identification and mitigation in electrical and electronics engineering tasks within construction. The research combines literature review and empirical analysis to understand industry challenges and the potential benefits of using machine learning. Empirical analysis involves creating and testing machine learning models using real-world project data. The expected outcome is a set of practical recommendations for project managers, engineers, and stakeholders in construction to improve efficiency and reduce costs. Overall, this research contributes to ongoing efforts to enhance construction industry efficiency and productivity through the application of machine learning techniques in electrical and electronics engineering projects.

show abstract

“…W ITH the progress of science and computer technology, the advanced manufacturing industry is developing rapidly in the direction of intelligence and information technology [1]- [3]. In the contemporary world, all industrialized developed countries carry out strategic layouts.…”

Section: Introductionmentioning

confidence: 99%

An Augmented AutoEncoder With Multi-Head Attention for Tool Wear Prediction in Smart Manufacturing

Dong,

Zhao

2024

IEEE Access

View full text Add to dashboard Cite

Computer numerical control (CNC) machine tools play a crucial role in the manufacturing industry, and cutting tools, as key functional components, directly impact the quality of the machining process. An improved autoEncoder with multi-head attention for tool wear prediction is proposed. MultiCNN-Attention-GRU (MCAG) consists of an encoder and decoder. The encoder contains multiple sets of Convolutional Neural Networks (CNNs) and CNNs adaptively extract signal features. The decoder includes Multi-Head Attention (MHA) and Gated Recurrent Unit (GRU), which can adaptively enhance the relevant feature weights and extract long-term, deep different features. For the model training, a monotonicity loss function is defined. The proposed method is validated on the 2010 PHM Data Challenge (PHM2010) public dataset. The original dataset is dimensionally reduced and then resampled. The experimental results demonstrate the effectiveness of the proposed algorithm, achieving an Mean Absolute Error (MAE) of 6.15 and Mean Square Error (MSE) of 79.6, which is approximately 1.6 and 13 lower than the second-place algorithm. The result validates the superior performance of the proposed model compared to other deep learning algorithms in predicting tool wear.

show abstract

An Improved Feature Selection Method Based on Random Forest Algorithm for Wind Turbine Condition Monitoring

Cited by 16 publications

References 34 publications

Rapid Identification of Tobacco Mildew Based on Random Forest Algorithm

Rapid Identification of Tobacco Mildew Based on Random Forest Algorithm

Exploring Machine Learning Techniques to Maximize Efficiency in Construction Industry Electrical and Electronics Engineering Projects

An Augmented AutoEncoder With Multi-Head Attention for Tool Wear Prediction in Smart Manufacturing

Contact Info

Product

Resources

About