Hydraulic Valve Control Mapping for Precise Component Velocity
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electrohydraulic control systems for hydraulic machines do not effectively translate electric current into desired velocities of machine components due to nonlinear relationships and variations in hydraulic cylinder pressures and component positions.
Innovation Solution
A machine control system using machine learning to train model weights that map input commands and machine state data into predicted valve displacements, enabling precise control of hydraulic valve movements to achieve desired velocities by correlating preset displacements with movement parameters through a parameter grid and sensor data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If electrohydraulic controls are used to translate input commands into electric currents for hydraulic valve actuation, then the complexity of direct mechanical control is reduced, but the precision of controlling machine component velocity deteriorates due to nonlinear relationships and variations in hydraulic cylinder pressures and component positions
Solution Approach 1:
The system performs preliminary action by training a machine learning model offline using extensive simulation data that captures the nonlinear relationships between valve displacements and component velocities under various operating conditions. This pre-trained model is then deployed in the electrohydraulic control system, allowing it to predict optimal valve displacements in real-time without requiring complex real-time calculations or extensive sensor arrays, thus achieving precise velocity control while maintaining system simplicity.
Solution Approach 2:
The invention replaces traditional mechanical control systems with an electrohydraulic control system enhanced by machine learning algorithms. Instead of relying on direct mechanical linkages and manual tuning, the system uses computational models trained on simulation data to predict valve displacements, substituting mechanical complexity with intelligent software-based control that adapts to nonlinear hydraulic behaviors and varying operating conditions.
2Ease of operation
If traditional calibration methods are used to determine electric current for desired flow conductance, then the valve control is simplified, but the ability to achieve desired component velocities deteriorates due to unaccounted variations in hydraulic pressures and machine state
Solution Approach 1:
The system implements feedback by training the machine learning model on comprehensive simulation data that includes various hydraulic cylinder pressures, component positions, and machine states. The model learns to compensate for these variations by predicting valve displacements that account for the current operating conditions. This feedback mechanism is embedded in the control algorithm, allowing the system to maintain reliable velocity control across different operating conditions without requiring complex real-time feedback sensors or manual recalibration.
Solution Approach 2:
The invention applies parameter changes by using the machine learning model to dynamically adjust valve displacement predictions based on the current machine state. The model was trained to recognize patterns in how hydraulic pressures, component positions, and other parameters affect the relationship between valve displacement and component velocity. During operation, the model automatically adapts its predictions to account for these parameter variations, maintaining reliable velocity control without requiring manual intervention or complex real-time calculations.
3Manufacturing precision
If extensive manual tuning is performed to achieve accurate velocity control, then the velocity precision is improved, but the time and resources required for setup and maintenance increase
Solution Approach 1:
The system performs preliminary action by conducting extensive offline training of the machine learning model using simulation data that covers a wide range of operating conditions. This pre-training process captures the complex nonlinear relationships between valve displacements and component velocities, eliminating the need for extensive manual tuning during system setup or maintenance. The model is ready to provide accurate velocity control predictions immediately upon deployment, saving significant time and resources compared to traditional calibration methods.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The system accurately predicts valve displacements and corresponding electric currents, ensuring that machine components move at velocities matching operator inputs, improving operational precision and reducing the need for extensive manual tuning.
Implementation Method 1
electrohydraulic controls can translate input commands into electric currents or signals that drive actuation of hydraulic components
Implementation Method 2
hydraulic pump linked to hydraulic cylinders can actuate a boom, stick, and/or bucket of an excavator
Implementation Method 3
A control mapping model can use the set of model weights to map a combination of the input command and the machine state data into a predicted displacement of the hydraulic valve
Data Source
AI summary
A machine control system can store model weights determined via machine learning using a training dataset correlating preset hydraulic valve displacements to measured movement parameters of a machine component. The machine control system can receive an input command for the component and machine state data from machine sensors. A control mapping model can use the model weights to map a combination of the input command and the machine state data into a predicted displacement of the hydraulic valve that causes movement of the component in response to the input command.