Agricultural Work System Controller Learning Routine
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing agricultural work systems face challenges in accurately determining input variables for control tasks, as these values are often unknown or difficult for operators to determine, leading to suboptimal machine performance.
Innovation Solution
The system controller assigns initial values to input variables, which can be updated through a learning process using measured values and optimization criteria, ensuring high-quality input values are used for control tasks, even in the absence of operator input, and these values are stored in an initial value matrix for efficient computation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If the system uses default initial values for input variables, then the system can operate without operator input, but the quality and accuracy of control tasks deteriorate
Solution Approach 1:
The system performs preliminary actions by pre-calculating and storing optimized initial values for input variables based on system variables (attachment configuration, machine configuration) before actual operation. This allows the system to start with high-quality values without requiring immediate operator input, thus maintaining both ease of operation and input variable quality.
Solution Approach 2:
The system implements feedback mechanisms where measured values from sensors during operation are used to update and refine the initial values for input variables. This continuous feedback loop ensures that the initial values improve over time based on actual operational data, maintaining high quality while keeping the system easy to operate.
2Measurement precision
If the system requires operator input for all input variables, then the quality of input variables improves, but the ease of operation deteriorates
Solution Approach 1:
The system performs self-service by automatically determining and updating initial values for input variables using measured values from sensors and optimization routines. This eliminates the need for operator intervention in providing these values, maintaining high input variable quality while significantly improving ease of operation.
3Adaptability or versatility
If the system stores and processes multiple initial values for different configurations, then the adaptability improves, but the device complexity increases
Solution Approach 1:
The system performs preliminary calculations to determine optimized initial values for various system variables (attachment configurations, machine configurations) and stores them in advance. This allows the system to quickly adapt to different configurations by simply retrieving pre-calculated values rather than performing complex real-time calculations, thus improving adaptability while managing device complexity.
Solution Approach 2:
The system applies local quality by storing specific initial values tailored to each combination of system variables (attachment configuration, machine configuration). Rather than using a single generic value, the system selects or calculates appropriate initial values for each specific configuration context, improving adaptability without requiring a completely complex system-wide redesign.
4Measurement precision
If the system performs real-time optimization of input variables, then the quality of control tasks improves, but the productivity deteriorates due to computation time
Solution Approach 1:
The system performs optimization calculations in advance, before real-time operation begins. Initial values for input variables are pre-calculated based on system variables and stored for quick retrieval during operation. This eliminates the need for time-consuming real-time optimization computations, maintaining high control task quality while preserving productivity.
Solution Approach 2:
The system implements a dynamic approach where the level of optimization varies based on operational context. During critical phases requiring high precision, more sophisticated optimization is applied, while during routine operations, pre-calculated values are used directly. This dynamic adjustment maintains control task quality without consistently sacrificing productivity.
Data Source
Figure 1
Figure 2
AI summary
The invention relates to an agricultural work system for processing an agricultural work order with an agricultural work machine (1) which can be equipped with at least one implement (3) via at least one device interface (2), wherein the work machine (1) is assigned a work machine configuration (KM), wherein the implement (3) is assigned an implement configuration (KA), wherein a system control (6) and an operating and display unit (7) assigned to the work machine (1) are provided, wherein in a control routine (8) the system control (6) performs predetermined control tasks based on a set of input variables (En).It is proposed that the system control (6) bases the execution of the control tasks on the initial values (in) of the input variables (En), in particular if no values (en) entered via the operating and display unit (7) exist for the input variable (En) in question, and that in a learning routine (12) the system control (7) determines a value (in') from the processing of the work order for at least one input variable (En) according to a determination rule and overwrites the old initial value (in) stored for this input variable (En) with the determined value (in') as the new initial value.