Research on Deep Adaptive Clustering Method Based on Stacked Sparse Autoencoders for Concrete Truck Mixers Driving Conditions

Existing standard driving conditions fail to accurately characterize the complex characteristics of heavy-duty commercial vehicles such as concrete truck mixers (CTMs), while traditional dimensionality reduction methods have strong empirical dependence and an insufficient ability to capture nonlinea...

Full description

Saved in:
Bibliographic Details
Published in:World electric vehicle journal Vol. 16; no. 10; p. 581
Main Authors: Huang, Ying, Jiang, Fachao, Xie, Haiming
Format: Journal Article
Language:English
Published: Basel MDPI AG 15.10.2025
Subjects:
adaptive clustering algorithm
Algorithms
Clustering
Commercial vehicles
concrete truck mixers
Data collection
Data processing
deep features extraction
Driving conditions
Energy consumption
Energy management
Feature extraction
Machine learning
Mixers
Monitoring systems
Neural networks
Optimization
stacked sparse autoencoder
Vehicles
ISSN:2032-6653, 2032-6653
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Existing standard driving conditions fail to accurately characterize the complex characteristics of heavy-duty commercial vehicles such as concrete truck mixers (CTMs), while traditional dimensionality reduction methods have strong empirical dependence and an insufficient ability to capture nonlinear relationships. To address these issues, a novel method for constructing typical composite driving conditions that integrates deep feature learning and adaptive clustering is proposed. Firstly, a vehicle data monitoring system is used to collect real-world driving data, and a data processing and filtering criterion specific to CTMs is designed to provide effective input for feature extraction. Then, stacked sparse autoencoders (SSAE) are employed to extract deep features from normalized driving data. Finally, the K-means++ algorithm is improved using a nearest neighbor effective index minimization strategy to construct an adaptive driving condition clustering model. Validation results based on a real-world dataset of 8779 driving condition segments demonstrate that this method enables the precise extraction of complex driving condition features and optimal cluster partitioning. It provides a reliable basis for subsequent research on typical composite driving conditions construction and energy management strategies for heavy-duty commercial vehicles.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2032-6653
2032-6653
DOI:10.3390/wevj16100581