Mobile Machine Control With Real-Time ML Settings Adjustment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems for determining settings for mobile machines, such as agricultural or construction equipment, do not adequately consider complex interactions between factors like terrain, ground conditions, soil type, weather, and machinery capabilities, leading to suboptimal settings and increased operational costs.
Innovation Solution
The use of machine learning, specifically deep learning models, to control and adjust settings of mobile machines in real time, taking into account various environmental and performance data to optimize settings for efficiency and productivity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If manual planning and simple computations are used to determine mobile machine settings, then the system complexity is low, but the settings quality and operational efficiency deteriorate due to inability to consider complex interactions between terrain, ground conditions, soil type, weather conditions, and machinery capabilities
Solution Approach 1:
The patent replaces manual planning and simple computational systems with a machine learning-based system that automatically determines mobile machine settings. The ML model processes complex interactions between terrain, ground conditions, soil type, weather conditions, and machinery capabilities to generate optimized settings, substituting human expertise and simple algorithms with an intelligent system capable of handling complex multivariate relationships.
Solution Approach 2:
The patent introduces a machine learning model as an intermediary between environmental inputs (terrain, weather, soil conditions) and machine settings outputs. This intermediary processes the complex interactions between multiple factors and translates them into optimized machine settings, acting as a bridge that converts raw environmental data into actionable control parameters.
2Loss of energy
If preselected settings are used without considering complex environmental interactions, then the operational cost increases due to subpar settings, but the decision-making process remains simple
Solution Approach 1:
The patent replaces simple settings determination methods with a machine learning-based system that optimizes fuel consumption by considering complex environmental interactions. The ML model analyzes terrain, ground conditions, soil type, and weather conditions to generate settings that minimize energy loss and fuel consumption, substituting粗放式 (rough) settings with precision-optimized settings.
Solution Approach 2:
The machine learning system operates autonomously to determine optimal machine settings without requiring manual intervention or complex human decision-making processes. The system self-adjusts settings based on environmental conditions and performance data, enabling the machinery to optimize its own operation for fuel efficiency and energy consumption.
3Productivity
If manual settings adjustment is performed, then the operator has direct control, but the response time and adaptability to changing conditions deteriorate
Solution Approach 1:
The machine learning system enables continuous optimization of machine settings by constantly processing environmental data and adjusting parameters in real-time. Unlike manual adjustment which occurs intermittently, the automated ML-based system maintains continuous adaptation to changing conditions, ensuring optimal performance throughout operation and eliminating downtime associated with manual settings changes.
Solution Approach 2:
The patent replaces manual settings adjustment with an automated machine learning system that rapidly processes environmental data and generates optimized settings. This substitution eliminates the time lag inherent in manual observation and adjustment, providing immediate response to changing terrain, weather, and operational conditions, thereby improving productivity and reducing time loss.
4Manufacturing precision
If simple computational algorithms are used, then the computational resources required are minimal, but the ability to optimize settings based on multiple interacting factors deteriorates
Solution Approach 1:
The patent replaces simple computational algorithms with a machine learning model that delivers superior settings optimization accuracy. The ML system processes complex interactions between terrain, ground conditions, soil type, weather conditions, and machinery capabilities, providing precise optimization that simple algorithms cannot achieve, justifying the increased computational resource requirements through superior performance.
Solution Approach 2:
The machine learning system dynamically adjusts multiple parameters simultaneously based on environmental conditions and performance data. Rather than adjusting single parameters in isolation as simple algorithms might, the ML model optimizes multiple interacting parameters together, capturing the complex relationships between terrain, weather, soil conditions, and machine performance for superior optimization accuracy.
Data Source
Figure 1
Figure 2
Figure 3~4
AI summary
Embodiments include technologies that use machine learning to control mobile machines as well as to adjust settings of mobile machines in real time (e.g., agricultural machine settings, construction machine settings, forestry machine settings, or landscaping machine settings). Some embodiments include a method that includes using a mobile machine (110) to perform work in a field using first machine settings (step 302) and recording performance information (118). The performance information indicating a performance of the mobile machine while performing the work in the field (step 304). Also, the method includes using a computing system (102, 200) to input the performance information into a trained deep learning model (107b) and to receive new machine settings information (108) from the trained model (step 306), and using the computing system to control the machine according to the new settings information (step 308).