Predictive Machine Control Using Forward-Looking Field Sensing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current control systems for mobile machines, such as agricultural and construction equipment, operate in a reactive manner, failing to dynamically adjust settings based on future conditions, leading to reduced productivity and efficiency.
Innovation Solution
A predictive control system using a policy map and a predictive controller that incorporates forward-looking sensors and a predictive vehicle model to adjust machine settings based on anticipated conditions, optimizing operations through a policy map generated by a pre-planning computer system.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If reactive control systems are used to control mobile machines, then the control system responds to current conditions, but productivity and efficiency are reduced due to inability to anticipate future conditions
Solution Approach 1:
The control system performs preliminary actions by using forward-looking sensors to detect future conditions before the machine encounters them. The controller proactively adjusts machine settings in advance based on predicted future conditions, rather than reacting after conditions are encountered. This preliminary action eliminates delays and improves productivity by preparing the machine optimally before operational changes are needed.
Solution Approach 2:
A predictive model acts as an intermediary between forward-looking sensors and the controller. The predictive model processes sensor data about future conditions and generates predicted machine responses, enabling the controller to make informed adjustments. This intermediary component bridges the gap between current machine state and future operational requirements, optimizing productivity.
2Productivity
If reactive control systems adjust machine settings based on current conditions, then the system responds to present state, but efficiency is reduced due to lack of proactive optimization
Solution Approach 1:
The system performs preliminary adjustments to machine settings based on predicted future conditions. Forward-looking sensors detect conditions that will be encountered ahead, and the controller proactively modifies settings before the machine reaches those conditions. This preliminary optimization improves efficiency by ensuring the machine is always configured optimally for upcoming operations.
Solution Approach 2:
The control system dynamically adjusts machine settings based on real-time predictions of future conditions. Rather than static or purely reactive control, the system continuously adapts settings as the machine moves through different terrain, maintaining optimal efficiency. The dynamic nature of the control allows the machine to seamlessly transition between different operational states.
3Productivity
If forward-looking sensors and predictive models are added to the control system, then proactive control is achieved, but device complexity increases
Solution Approach 1:
A predictive model serves as an intermediary layer between forward-looking sensors and the controller. This intermediary processes complex sensor data and generates predicted machine responses, simplifying the overall control architecture. The predictive model handles the computational complexity of predicting future conditions, allowing the controller to make decisions based on clear, processed information rather than raw sensor data.
Solution Approach 2:
The predictive control system is self-regulating, using forward-looking sensors to automatically detect future conditions and adjust machine settings without external intervention. The system serves itself by continuously monitoring, predicting, and optimizing operations autonomously. This self-service capability reduces the need for complex external control mechanisms while maintaining high productivity.
Data Source
AI summary
A policy map is obtained that includes prescribed machine settings values for controlling a machine to perform an operation at different locations in the field. Sensor signals indicating conditions that will be encountered by the machine in the future, as it moves through the site. A predictive model provides an expected machine response, based upon the future condition and a prescribed machine setting value. An adjusted machine setting value is generated based on the expected machine response. Control signals are generated, based on the adjusted machine setting value, to control a set of controllable subsystems.