A novel bagged tree ensemble regression method with multiple correlation coefficients to predict the train body vibrations using rail inspection data

Peng, Lele; Zheng, Shibao; Zhong, Qianwen; Chai, Xiaodong; Lin, Jenshan

doi:10.1016/j.ymssp.2022.109543

Cited by 16 publications

(3 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…1. Mediante el uso de datos de mediciones diarias de vibraciones en trenes, Peng et al (2023) diseñaron un algoritmo para predecir las vibraciones del cuerpo de los trenes sin la necesidad de instalar nuevos sensores y otros equipos de monitoreo, con el propósito de asegurar la comodidad de los pasajeros. Esto permitirá a las empresas reducir los costos de operación y mantenimiento y mejorar con ello la seguridad, comodidad y eficiencia de la operación de los trenes.…”

Section: Análisis Prevención Y Predicción De Accidentesunclassified

Análisis, predicción y prevención de accidentes: un camino a la creación de trenes inteligentes

Sandoval Valencia,

Jáuregui-Correa,

Hurtado-Hurtado

2025

inventio

View full text Add to dashboard Cite

Los accidentes de trenes son eventos trágicos en los cuales ocurren pérdidas materiales y humanas. Estudiar a fondo estos siniestros permite conocer los factores que los originan, con lo cual es posible establecer una estrategia para reducir su aparición o evitarlos en su totalidad. En este artículo se exploran los estudios que se están realizando en este tema, a fin de analizar, predecir y prevenir accidentes. Asimismo, se da a conocer al lector la importancia de seguir estudiando los datos históricos de los accidentes y cómo las tecnologías emergentes cumplen un papel relevante en su disminución. El hallazgo más significativo es que las metodologías, algoritmos y tecnologías creadas en este campo van encaminadas hacia la creación de trenes inteligentes.

show abstract

Section: Análisis Prevención Y Predicción De Accidentesunclassified

Análisis, predicción y prevención de accidentes: un camino a la creación de trenes inteligentes

Sandoval Valencia,

Jáuregui-Correa,

Hurtado-Hurtado

2025

inventio

View full text Add to dashboard Cite

show abstract

“…Since we expected the given data to exhibit a linear relationship between variables, we determined that the Pearson correlation coefficient was the most suitable for our research objectives. In Figures 3-5, the Pearson correlation coefficient is used to characterize the degree of linear correlation between two variables [23]. The Pearson correlation coefficient between two variables (x, y) is the quotient of the covariance and standard deviation between the two variables, which is defined as:…”

Section: Exploratory Data Analysismentioning

confidence: 99%

A Negative Emotion Recognition System with Internet of Things-Based Multimodal Biosignal Data

Ham,

Lee,

Lim

et al. 2023

Electronics

View full text Add to dashboard Cite

Previous studies to recognize negative emotions for mental healthcare have used heavy equipment directly attaching electroencephalogram (EEG) electrodes to the head, and they have proposed binary classification methods to identify negative emotions. To tackle this problem, we propose a negative emotion recognition system to collect multimodal biosignal data such as five EEG signals from an EEG headset and heart rate, galvanic skin response, and skin temperature from a smart band for classifying multiple negative emotions. This consists of an Android Internet of Things (IoT) application, a oneM2M-compliant IoT server, and a machine learning server. The Android IoT application uploads the biosignal data to the IoT server. By using the biosignal data stored in the IoT server, the machine learning server recognizes the negative emotions of disgust, fear, and sadness using a multiclass support vector machine (SVM) model with a radial basis function kernel. The experimental results demonstrate that the multimodal biosignal data approach achieves 93% accuracy. Moreover, when considering only data from the smart band, the system achieved 98% accuracy by optimizing the hyperparameters of the multiclass SVM model. Based on these results, we plan to develop a metaverse system that detects and expresses negative emotions in real time.

show abstract

“…Fault features are crucial for bearing fault diagnosis. However, the failure of various components of the bearing leads to various characteristic frequencies [5][6][7][8].…”

Section: Introductionmentioning

confidence: 99%

Bearing fault diagnosis of rail vehicles traction motor based on adaptive periodic segment matrix and singular value decomposition

Zou,

Chen,

Peng

et al. 2023

Eng. Res. Express

View full text Add to dashboard Cite

The early fault characteristics of rolling bearings are relatively weak and accompanied by large amounts of noise, resulting in the collected bearing vibration signal having an extremely low signal-to-noise ratio, hence creating challenges in diagnosing faults in rail vehicle bearings. This paper proposes a method based on an adaptive period segment matrix and singular value decomposition to extract fault information from bearing fault impulse signals, in response to the problem of unstable period recognition in existing rolling bearing fault diagnosis methods due to strong background noise. Firstly, a periodic segment estimation method based on the average envelope spectrum is proposed. By calculating the envelope spectrum of the vibration signal, a method is proposed for assessing period length and period constraint F in segments. Then this method is applied to pinpoint the fault impact peak and the position of the vibration signal. Utilizing the fault impact peak and the calculated period constraint F, a strict rank-1 adaptive period segment matrix (APSM) is introduced. Finally, singular value decomposition is performed on this matrix, the bearing impulse vibration signal can be reconstructed through the first maximum singular value. The simulation and experimental analysis results of rolling bearings signals demonstrate the performance of the proposed method, even under severe background noise conditions (-20 dB), and the calculated envelope spectrum signal-to-noise ratio further supports the adaptive periodic segment matrix has an excellent ability to identify and extract periodic components, thus validating its usefulness as a fault diagnosis approach for rolling bearings.

show abstract

A novel bagged tree ensemble regression method with multiple correlation coefficients to predict the train body vibrations using rail inspection data

Cited by 16 publications

References 50 publications

Análisis, predicción y prevención de accidentes: un camino a la creación de trenes inteligentes

Análisis, predicción y prevención de accidentes: un camino a la creación de trenes inteligentes

A Negative Emotion Recognition System with Internet of Things-Based Multimodal Biosignal Data

Bearing fault diagnosis of rail vehicles traction motor based on adaptive periodic segment matrix and singular value decomposition

Contact Info

Product

Resources

About