<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>In order to solve the problem that the initial center of traditional clustering algorithm is easy to fall into local optimum and time-consuming. An improved combination optimization algorithm of principal component analysis and weighted K-means clustering is proposed. The algorithm introduces the maximum and minimum distance, weighted Euclidean distance, starting from the mean sum of the distances of the remaining clustering points, avoiding the influence of outliers and edge data. The proportion method is used to improve the principal component, and the characteristic influence factor obtained is used as the initial characteristic weight to construct a weighted Euclidean distance metric. According to the influence factors of feature contribution rate on clustering, a clustering method of feature weight influence factors is proposed. The representative feature factors are selected to highlight the clustering effect. Finally, the driving cycle of automobile is synthesized and the instantaneous fuel consumption is analyzed. The results show that: the difference value of speed acceleration joint distribution of the proposed method is only 1.05%, which saves 44.2% of the time compared with the traditional K-means clustering, and the driving cycle fitting degree is high, which can reflect the actual vehicle operation characteristics and fuel consumption.</p>
</abstract>

In order to solve the problem that the initial center of traditional clustering algorithm is easy to fall into local optimum and time-consuming. An improved combination optimization algorithm of principal component analysis and weighted K-means clustering is proposed. The algorithm introduces the maximum and minimum distance, weighted Euclidean distance, starting from the mean sum of the distances of the remaining clustering points, avoiding the influence of outliers and edge data. The proportion method is used to improve the principal component, and the characteristic influence factor obtained is used as the initial characteristic weight to construct a weighted Euclidean distance metric. According to the influence factors of feature contribution rate on clustering, a clustering method of feature weight influence factors is proposed. The representative feature factors are selected to highlight the clustering effect. Finally, the driving cycle of automobile is synthesized and the instantaneous fuel consumption is analyzed. The results show that: the difference value of speed acceleration joint distribution of the proposed method is only 1.05%, which saves 44.2% of the time compared with the traditional K-means clustering, and the driving cycle fitting degree is high, which can reflect the actual vehicle operation characteristics and fuel consumption.

Research on Driving Conditions and Fuel Consumption of Improved K-means Clustering Algorithm

International Journal of Advanced Network, Monitoring and Controls

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

In order to solve the problem that the initial center of traditional clustering algorithm is easy to fall into local optimum and time-consuming. An improved...

Clustering method	The number of wrong samples	Average running time / s	Average accuracy /%	SAFD_diff/%
k-means	184	260.5	89	1.98
Literature^[17]	121	202.75	97	1.54
Literature^[18]	98	181.5	99	1.25
The algorithm in this paper	101	145.25	98	1.05

Characteristic parameter	M₁	M₂	M₃	M₄
Deceleration time ratio T_d	0.423	0.341	−0.723	0.248
Distance traveled S	0.893	0.134	0.045	0.432
Fragment duration T	0.432	0.231	−0.142	0.768
Acceleration time ratio T_a	0.394	−0.156	0.060	0.491
Cruise time ratio T_c	0.341	0.835	−0.045	−0.138
Average velocity V_a	0.499	0.763	0.025	0.255
Average driving speed V_d	0.778	0.315	0.112	0.358
Speed standard deviation V_std	0.198	0.033	0.034	0.189
Accelerate standard deviation a_std	0.145	0.267	−0.067	−0.121
Average acceleration a_a	0.014	0.223	0.033	0.024
Average deceleration a_d	0.566	−0.433	−0.052	0.315
Idle Time Ratio T_i	0.125	−0.351	0.843	0.467

Research on Driving Conditions and Fuel Consumption of Improved K-means Clustering Algorithm

Published Online: May 26, 2023

Page range: 1 - 10

DOI: https://doi.org/10.2478/ijanmc-2022-0011

Keywords
Driving Cycle, Influence Factors, Feature Weight, Weighted K-Means Clustering

© 2022 Shuping Xu et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1.

Figure 2.

Figure 3.

Figure 4.

Figure 5.

Figure 6.

Figure 7.

Figure 8.

Figure 9.

Figure 10.

Figure 11.

Figure 12.

Figure 13.

Figure 14.

Figure 15.

Four methods to compare the results of the experiment

Principal component loading matrix

Research on Driving Conditions and Fuel Consumption of Improved K-means Clustering Algorithm

Published Online: May 26, 2023

Page range: 1 - 10

DOI: https://doi.org/10.2478/ijanmc-2022-0011

KeywordsDriving Cycle, Influence Factors, Feature Weight, Weighted K-Means Clustering

© 2022 Shuping Xu et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1.

Figure 2.

Figure 3.

Figure 4.

Figure 5.

Figure 6.

Figure 7.

Figure 8.

Figure 9.

Figure 10.

Figure 11.

Figure 12.

Figure 13.

Figure 14.

Figure 15.

Four methods to compare the results of the experiment

Principal component loading matrix

Keywords
Driving Cycle, Influence Factors, Feature Weight, Weighted K-Means Clustering