Open Access

Research on Driving Conditions Based on Principal Component and K-means Clustering Optimization

Huifeng Wang

Huifeng Wang

School of Computer Science & Engineering Xi’an Technological University Xi’anChina
Search for this author on
Sciendo|Google Scholar
Wang, Huifeng
, 
Shuping Xu

Shuping Xu

School of Computer Science & Engineering Xi’an Technological University Xi’anChina
Search for this author on
Sciendo|Google Scholar
Xu, Shuping
, 
Huxiang Yang

Huxiang Yang

Shaanxi Coal Industry Chemical Technology Research Institute Co., Ltd. Xi’anChina
Search for this author on
Sciendo|Google Scholar
Yang, Huxiang
, 
Jiaxiang Fang

Jiaxiang Fang

School of Computer Science & Engineering Xi’an Technological University Xi’anChina
Search for this author on
Sciendo|Google Scholar
Fang, Jiaxiang
 and 
Feiyan Kou

Feiyan Kou

School of Computer Science & Engineering Xi’an Technological University Xi’anChina
Search for this author on
Sciendo|Google Scholar
Kou, Feiyan
  
Jun 16, 2025
Research on Driving Conditions Based on Principal Component and K-means Clustering Optimization's Cover Image
About this article
Previous Article
Next Article
Cite
Download Cover
Published Online: Jun 16, 2025
Page range: 53 - 61
DOI: https://doi.org/10.2478/ijanmc-2025-0016
Keywords
© 2025 Huifeng Wang et al., published by Sciendo
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1.

Comparison of noise reduction data results
Comparison of noise reduction data results

Figure 2.

Lithotripsy
Lithotripsy

Figure 3.

Contribution rate and cumulative contribution rate
Contribution rate and cumulative contribution rate

Figure 4.

Relationship between cluster number and CH index
Relationship between cluster number and CH index

Figure 5.

K-means clustering results
K-means clustering results

Figure 6.

Scatter plot of segments in two-dimensional feature space
Scatter plot of segments in two-dimensional feature space

Figure 7.

Clustering results of fragments in two-dimensional feature space
Clustering results of fragments in two-dimensional feature space

Figure 8.

Synthetic driving conditions
Synthetic driving conditions

Figure 9.

Time and acceleration diagram
Time and acceleration diagram

Figure 10.

Scatter plot of instantaneous fuel consumption of speed and acceleration
Scatter plot of instantaneous fuel consumption of speed and acceleration

Figure 11.

SAFD difference between experimental data and synthetic conditions
SAFD difference between experimental data and synthetic conditions

COMPARISON OF THE METHOD IN THIS PAPER AND TRADITIONAL K-MEANS RESULTS

Method Eigenvalue mean relative error/% Cluster average accuracy/% Average time/s SAFDdiff/%
Traditional K-means clustering 8.1 93 215 2.12
Clustering of this article 4.6 98 127 1.17

PRINCIPAL COMPONENT LOAD MATRIX

Characteristic parameters M1 M2 M3
Deceleration time ratio Td/% 0.323 0.351 -0.223
Driving Clustering S/km 0.893 0.234 0.065
Run time T/S 0.782 0.251 -0.342
Acceleration time ratio Ta/% 0.396 -0.186 0.061
Cruise time ratio Tc/% 0.641 0.335 -0.075
Average speed Va/(km·h−1) 0.499 0.763 0.125
Deceleration time ratio Vd/(km·−1) 0.778 0.415 0.132
Speed standard deviation Vstd/(km·h−1) 0.498 0.333 0.054
Acceleration standard deviation astd/(km·−1) 0.125 0.267 -0.077
Average acceleration aa/(m·s−2) 0.024 0.523 0.053
Average deceleration aa/(m·s−2) 0.266 -0.433 -0.059
Idle time ratio Ti/(m·s−2) 0.165 -0.351 0.853
Language:
English
Publication timeframe:
4 times per year
Journal Subjects:
Computer Sciences, Computer Sciences, other
Journal RSS Feed