Work Machine Maintenance Prediction Using Geological Site Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional shovel support devices struggle with inaccurate prediction of maintenance timing for work machines operating in new sites where past operations are unknown, leading to inefficiencies in maintenance planning.
Innovation Solution
A work machine management system that integrates positional and operation information with geological data to predict maintenance timing by calculating wear rates and service life based on actual work conditions, using a system comprising a management server, user server, and portable terminal to issue alerts and display maintenance information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional shovel support devices use only past operation data for maintenance prediction, then maintenance timing can be determined for known sites, but accuracy of prediction fails for new sites where the shovel has never operated
Solution Approach 1:
The system pre-acquires geological information (soil type, rock hardness, terrain conditions) for potential work sites before the shovel actually operates there. This preliminary data collection enables the maintenance prediction system to have reference data ready in advance, so when the shovel moves to a new site, the prediction can immediately incorporate geological factors without relying solely on past operation history at that location.
Solution Approach 2:
Geological information acts as an intermediary element that bridges the gap between known and unknown sites. By introducing this external data source (geological survey data, soil composition, rock hardness) as a mediator, the system can transfer maintenance prediction capabilities from sites with historical data to new sites without direct operational history, improving both accuracy and adaptability.
2Reliability
If maintenance timing is determined based only on operation time, then the system is simple to operate, but maintenance timing cannot be determined appropriately considering ground conditions
Solution Approach 1:
The system merges multiple data sources including operation time, operational load, geological information (soil type, rock hardness), and environmental conditions into a unified maintenance prediction model. This combination allows the system to determine maintenance timing more reliably by considering both temporal factors (operation time) and contextual factors (ground conditions), achieving accurate predictions without requiring overly complex individual measurement systems for each parameter.
Solution Approach 2:
The maintenance prediction system is designed to handle multiple types of input data (operation time, load data, geological information) and adapt to various work conditions and site types. This multi-functional approach allows the same system to accurately predict maintenance timing whether the shovel is operating in soft soil, hard rock, or mixed conditions, maintaining reliability across diverse scenarios without requiring separate specialized systems for each condition.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The present disclosure provides a work machine management system that can predict the maintenance timing of a work machine with higher accuracy than conventional techniques. A work machine management system 100 of the present disclosure includes an input/output unit 121 and a processing unit 122. The input/output unit 121 receives from work machines 200 positional information PI and operation information OI on the work machines 200, and also receives from a geographical information system server 300 geological information GI on an area where the work machines 200 are to perform an operation, based on the positional information PI. The processing unit 122 predicts the maintenance timing of each work machine 200 based on the operation information OI and the geological information GI. In response to a request from an external portable terminal 130, the input/output unit 121 outputs to the portable terminal 130 data on an alert based on the maintenance timing of the work machine 200 predicted by the processing unit 122.