Application of kernel k-means and kernel x-means clustering to obtain soil classes from cone penetration test data

Carvalho, Lauro; Ribeiro, Dimas Betioli

doi:10.28927/sr.434607

Cited by 5 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As the scale of the system gradually increases and the structure becomes more complex, the disadvantages of the centralized control method become more obvious. In the development process of predictive control, in view of the shortcomings of centralized control methods, decentralized MPC (Model Predictive Control) was proposed [11][12]. Its core idea is to convert a single complex optimization problem into the solution of multiple subsystems, which has a simple structure and is easy to implement.…”

Section: Distributed Model Predictive Controlmentioning

confidence: 99%

Distributed System Optimization Based on K-means Clustering

2021

DPS

View full text Add to dashboard Cite

The regional energy internet is a distributed complex system with deep integration of energy and information. If different energy systems are planned and operated independently and lack of coordination with each other, problems such as low energy utilization rate, weak self-healing ability, and low system security and reliability will be caused. Therefore, scientific and reasonable planning methods and operation strategies are crucial to the overall efficiency and economy of distributed multi-energy systems. The main purpose of this paper is to study the optimization of distributed systems based on K-Means clustering. In this paper, a multi-energy unified clustering model based on the K-means algorithm is established to analyze the data characteristics in the cluster, and at the same time, the energy-side data is clustered to evaluate the available value of various types of energy. Experiments show that according to the 2/5/10 principle, when the system response time is within 2s, the user experience is very good. When the response time is between 2s and 5s, the user experience is better. Because the number of concurrent users of the system exceeds 500, the response time of the system is within the normal response time range acceptable to users and meets the needs of enterprises.

show abstract

Section: Distributed Model Predictive Controlmentioning

confidence: 99%

Distributed System Optimization Based on K-means Clustering

2021

DPS

View full text Add to dashboard Cite

show abstract

“…In the field of geotechnical engineering, it is commonly used with Cone Penetration Test (CPT) data for various purposes. For instance, in [2], a review of soil classification based on CPT data is presented, along with a novel methodology that employs the kernel k-means algorithm and artificial neural networks for soil classification. In [3], a cluster analysis technique is utilized to group CPT data based on normalized cone resistance, friction ratio, and soil behaviour index, which led to layer grouping used later to determine soil rigidity model.…”

Section: Introductionmentioning

confidence: 99%

Identifying Soft Soils using Pore-Pressure Parameters: A Machine Learning Approach

Viegas¹,

Gallardo²,

Bottaro³

et al. 2023

IJCI

View full text Add to dashboard Cite

The cone penetration test (CPT) is a widely used method for identifying soil profiles and estimating soil parameters. Numerous correlations have been established to facilitate geo-characterization of soils based on CPT data. However, caution must be exercised when applying these correlations and laboratory tests should be used to validate them. Tropical residual soils are highly variable, even for seemingly similar samples, which can make it difficult for project designers to accurately characterize them. The present work focuses on a case study where the goal was to distinguish and characterize two soft soils existent on the foundation of a tailings dam in the southwest of Brazil. The construction of the dam is still ongoing, and its foundation belongs to a complex geological environment with soft soils that can reach NSPT blows as low as its own weight. The geological survey identifies two horizons of residual soil of dolomitic phyllite: soft and very soft. However, spatially distinguishing this material regarding its consistence has shown to be a challenging task. Since they differ essentially on the degree of weathering, most parameters for both materials are quite similar, and from laboratory tests, the parameter that helps differentiate these soils is the pore pressure Skempton parameter at failure -Af. Based on these findings, it can be inferred that the pore-pressure parameter Bq in CPT represents the excess pore-pressure during the test, whereas Af describes the excess pore-pressure at failure during triaxial tests. Despite the lack of a currently established theoretical correlation between the two parameters, they can offer valuable insight into the soil's response to rapid loading. Notably, both measures have proven to be effective in distinguishing between residual soils, even though they are distinct measures. In this study, the Bq and Af parameters are employed to classify soils using an unsupervised learning method, specifically the K-means algorithm. The resulting clusters exhibit strong agreement with borehole profiles near the CPT locations.

show abstract

“…Then, a soil classification chart capable of typifying three distinct geotechnical behaviors was proposed. Carvalho and Ribeiro (2020) proposed a similar approach for the classification of partially saturated soils trough cone penetration test, suggesting that multivariate statistics is a useful tool for that purpose.…”

Section: Introductionmentioning

confidence: 99%

K-means Based Soil Classification System Applicable to a Brazilian Mineral Province

Coelho

Nogueira

Sala

et al. 2021

Preprint

View full text Add to dashboard Cite

This article presents a geotechnical soil classification system proposed for application on soils of a tropical mineral province, located in Minas Gerais state, Brazil. The system was constructed using data mining techniques, i.e., principal component analysis and k-means cluster analysis, which were applied to a dataset composed of 101 geotechnical characterization laboratory test results of soils from the Province of Quadrilátero Ferrífero. The main objective of the proposed soil classification method was to establish a regional soil classification system, which encompass the interpretability of the main geotechnical parameters of soils by means of the classification, given the little explanatory capacity of the Unified Soil Classification System classification system for the performance of such task. It was possible to establish a chart for soil classification capable of explaining 81.68% of the variability of the analyzed parameters, being established the soil classes A, B and C for the studied soils.

show abstract

Application of kernel k-means and kernel x-means clustering to obtain soil classes from cone penetration test data

Cited by 5 publications

References 17 publications

Distributed System Optimization Based on K-means Clustering

Distributed System Optimization Based on K-means Clustering

Identifying Soft Soils using Pore-Pressure Parameters: A Machine Learning Approach

K-means Based Soil Classification System Applicable to a Brazilian Mineral Province

Contact Info

Product

Resources

About