Work Machine Shape Estimation Using Imaging and ML

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

In machine guidance and machine control for work machines, operators face challenges in preparing data for the target shape of constructing targets, especially in small-scale work sites where resources for data preparation are limited, leading to inefficiencies and increased preparation time.

Innovation Solution

A supporting device equipped with a processor and memory that estimates the target shape of a constructing target by obtaining data from parts already constructed, using imaging devices to capture images and apply machine learning models to generate accurate shape data, reducing the need for manual input and enhancing work efficiency.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual data preparation for target shape is performed, then data accuracy can be ensured, but preparation time and resource requirements increase significantly

Engineering Contradiction:

Improvedata accuracyVSAvoidpreparation time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The work machine performs self-measurement and self-data-preparation by using its own sensors and imaging devices to automatically capture and process shape data of the constructing target, eliminating the need for external manual surveying and data preparation activities

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

Manual mechanical surveying methods are replaced with automated optical and sensor-based measurement systems that capture shape data through imaging devices and process it using onboard computers, achieving both speed and accuracy

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Extent of automation

If manual data preparation is used, then resource requirements are high, but automation level remains low

Engineering Contradiction:

Improveautomation levelVSAvoidresource requirements

Core Design Contradiction:

Extent of automationVSDevice complexity

Solution Approach 1:

The work machine is equipped with multi-functional sensors and imaging devices that serve both construction operations and automatic shape measurement functions, allowing one set of equipment to perform multiple roles without adding significant complexity

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system uses the work machine's own existing sensors and computing resources to perform automatic measurement and data preparation, rather than requiring separate dedicated measurement equipment or external surveying resources

Inventive Principle:

Principle #25Self-service

3Manufacturing precision

If target shape data is prepared in advance, then construction accuracy can be maintained, but initial setup time increases

Engineering Contradiction:

Improveconstruction accuracyVSAvoidinitial setup time

Core Design Contradiction:

Manufacturing precisionVSDuration of action of moving object

Solution Approach 1:

The system performs preliminary measurement and shape estimation automatically at the start of construction by capturing images and processing them through the computer, preparing the target shape data without requiring manual surveying setup

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

Traditional manual surveying and data preparation processes are replaced with automated image capture and computer-based shape estimation, maintaining construction accuracy while eliminating time-consuming initial setup

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS20250003197A1Supporting device, work machine, and program

Publication Date: 2025.01.02 SUMITOMO HEAVY IND LTD

AI summary

A supporting device includes a memory, and a processor that is connected to the memory and configured to execute obtaining data related to a shape of a part that has already been constructed in a constructing target, and estimating a target shape of the constructing target based on the data obtained.