Mobile Machine Supervisory Control for Multi-Objective Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current machine control systems for complex mobile machines like combine harvesters face challenges in optimizing performance across multiple dimensions, such as productivity and fuel economy, due to complex resource allocation and unintended subsystem interactions, especially when operating in varying environments and managing fleets of machines.
Innovation Solution
A supervisory and optimization system utilizing machine learning, specifically neural networks, that integrates situational data from machine sensors, operator feedback, and non-traditional sources like weather and terrain maps to generate performance indexes and control signals, allowing for automated or manual control adjustments to optimize machine performance across multiple dimensions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional machine control systems are used, then device complexity is reduced, but performance optimization across multiple dimensions (productivity, fuel economy) deteriorates
Solution Approach 1:
The control system is segmented into multiple specialized modules: performance index generator logic that processes sensor data, optimization system that accesses historical data and generates improvement signals, and control signal generator logic that executes specific control operations. Each module handles a distinct aspect of the control process, enabling comprehensive performance optimization without overwhelming system complexity.
Solution Approach 2:
The system implements continuous feedback loops where machine sensors and operator sensors constantly monitor performance, the performance index generator processes this data to assess current performance levels, and the optimization system uses historical circumstantial data to generate improvement signals that adjust control parameters. This closed-loop feedback mechanism enables dynamic performance optimization across multiple dimensions.
2Productivity
If resource allocation is optimized for one subsystem, then productivity improves, but other performance categories (fuel economy, grain loss) deteriorate
Solution Approach 1:
The system dynamically changes multiple operational parameters simultaneously based on real-time performance assessment and historical data analysis. The optimization system adjusts threshing speed, cleaning fan speed, conveyor belt speed, and other parameters in coordinated fashion to achieve overall performance optimization rather than maximizing single parameters, thereby balancing productivity with fuel economy and other performance categories.
Solution Approach 2:
The system transitions from single-dimensional optimization (focusing on one performance metric) to multi-dimensional optimization by considering multiple performance categories simultaneously through the performance index framework. The performance index generator evaluates productivity, fuel economy, grain loss, and other dimensions together, enabling the optimization system to find balanced solutions that optimize overall machine performance across all dimensions rather than sacrificing one for another.
3Ease of operation
If machine control is simplified for ease of operation, then operator ease of operation improves, but performance optimization capability deteriorates
Solution Approach 1:
The control system performs self-optimization through automated feedback loops and historical data analysis without requiring deep operator intervention. The performance index generator and optimization system automatically monitor performance, analyze circumstantial data, and generate improvement signals that adjust machine parameters. This self-service capability maintains operational simplicity while achieving advanced performance optimization, as the system handles complex optimization tasks autonomously.
Solution Approach 2:
The performance index generator acts as an intermediary between raw sensor data and control decisions, translating complex multi-dimensional performance data into actionable performance indexes. The optimization system then uses these indexes along with historical circumstantial data to generate improvement signals. This intermediary layer simplifies the operator's task by handling complex optimization calculations automatically while still achieving comprehensive performance optimization across multiple dimensions.
Data Source
AI summary
A mobile machine includes a propulsion subsystem that propels the mobile machine across an operational environment. The mobile machine also includes machine monitoring logic that receives a sensor signal indicative of a value of a sensed machine variable and operator monitoring logic that receives an operator sensor signal indicative of a value of a sensed operator variable. The mobile machine also includes performance index generator logic that receives the sensed machine variable and the sensed operator value and generates a performance index based on the sensed machine variable and the sensed operator value. The mobile machine also includes optimization system that accesses historic circumstantial data and receives the performance index and generates an optimization signal based on the performance index, and the historic circumstantial data and control signal generator logic that generates a control signal based on the optimization signal to perform a machine operation.