Machine Time Usage Determination System for Mining Fleet Productivity
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current fleet management systems in mining and construction operations face challenges in determining the primary factors influencing productivity and efficiency at worksites, as they rely on manual data entry for categorizing machine activities as productive or unproductive, which is time-consuming and inefficient.
Innovation Solution
A machine time usage determination system that processes data from multiple sources using a data processing pipeline and a controller executing a machine time usage determination program to automatically assign activities to equipment, employing algorithms for classification and probabilistic modeling to categorize activities and determine probability values, thereby reducing the need for manual input.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual data entry is used to categorize machine activities, then data accuracy can be maintained through human judgment, but time consumption and operational efficiency deteriorate
Solution Approach 1:
The system enables automatic self-categorization of machine activities by processing sensor data through trained machine learning models. The system serves itself by automatically determining whether machines are performing productive or unproductive activities without requiring manual data entry or human judgment, thereby eliminating time consumption while maintaining accuracy through algorithmic classification
Solution Approach 2:
The patent replaces the mechanical process of manual data entry and human categorization with an automated electronic system. Machine learning models process sensor data electronically to categorize activities, substituting human manual operations with computational algorithms that achieve both speed and accuracy simultaneously
2Productivity
If automated activity classification is implemented, then productivity and time efficiency are improved, but system complexity and difficulty of implementation increase
Solution Approach 1:
The system employs universal machine learning models that can categorize multiple types of machine activities across different equipment types using a single unified approach. The same classification framework handles diverse activities (digging, hauling, loading, etc.) and various data sources, reducing implementation complexity despite the automated nature of the system
Solution Approach 2:
The patent introduces a data processing pipeline as an intermediary layer between raw sensor data and activity classification. This pipeline preprocesses, standardizes, and organizes data from multiple sources before feeding it to classification algorithms, simplifying the overall system architecture and making implementation more manageable by breaking down the complex task into structured intermediate steps
Data Source
AI summary
A machine time usage determination system includes a data processing pipeline configured to receive data from a plurality of sources, a machine time usage determination program, and a controller in communication with the data processing pipeline and configured to execute the machine time usage determination program. Thus, the controller is configured to review a set of data from the data processing pipeline, and assign a current activity of a set of predetermined machine activities to a piece of equipment based on the set of data. Each activity of the set of predetermined machine activities is categorized as a productive activity or an unproductive activity. The controller is also configured to determine a probability value associated with the assigned current activity.