Intelligent perception adaptive wheel loader

By combining intelligent sensing systems and adaptive control technology with visual sensors, lidar, and convolutional neural networks, the wheel loader has achieved refined operation control in complex environments, solving the problems of inaccurate environmental perception and power output mismatch, and improving operation efficiency and equipment lifespan.

CN122169553APending Publication Date: 2026-06-09LAIZHOU DAYANG MASCH MFG CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
LAIZHOU DAYANG MASCH MFG CO LTD
Filing Date
2026-02-10
Publication Date
2026-06-09

AI Technical Summary

Technical Problem

Existing wheel loaders have poor environmental perception reliability under complex and harsh working conditions, and their power output cannot be adaptively matched according to the attributes of the work object, resulting in low operating efficiency and severe equipment wear.

Method used

The system employs an intelligent sensing system that combines visual sensors and lidar to fuse multi-source data. It uses a convolutional neural network to identify material properties and dynamically adjusts engine speed and hydraulic system parameters based on these properties, while also incorporating traction control logic to prevent wheel slippage.

Benefits of technology

It improves the accuracy of obstacle location calculation in complex environments, optimizes energy efficiency management, reduces tire wear, and enhances operational safety and stability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122169553A_ABST
    Figure CN122169553A_ABST
Patent Text Reader

Abstract

This application relates to an intelligent sensing and adaptive wheel loader, belonging to the technical field of engineering machinery control. It includes an intelligent sensing system, a data processing unit, and an adaptive control system. The loader uses the data processing unit to synchronize visual sensor and lidar data spatiotemporally, calculate light intensity and environmental noise indicators, and dynamically allocate sensor fusion weights to calculate obstacle positions. It utilizes a convolutional neural network to identify the material properties of the workpiece, and adaptively adjusts the engine target speed and hydraulic system overflow pressure based on the material's resistance and density coefficient. Furthermore, it combines the material type with real-time wheel speed differences to execute active traction control. This application solves the problem of sensing failure under harsh working conditions and achieves precise matching of power output and working load based on material characteristics, effectively improving the loader's operational efficiency, environmental adaptability, and driving stability.
Need to check novelty before this filing date? Find Prior Art