Hydraulic Valve Neural Control for Nonlinear Pressure Curves

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current digital valves in hydraulic systems lack comprehensive adjustment capabilities for their characteristic curves, limiting precision and flexibility in controlling fluid flow due to non-linear relationships between solenoid current and pressure, which are influenced by manufacturing tolerances.

Innovation Solution

A computer-implemented method using an artificial neural network is employed to train a valve control unit, where the neural network is initialized with training data from the valve's characteristic curve, allowing it to determine the required solenoid current for precise pressure control by minimizing deviations through forward and backward propagation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual recording of characteristic curves is used, then measurement accuracy can be achieved, but time consumption increases significantly

Engineering Contradiction:
Improvecharacteristic curve measurement accuracyVSAvoidtime for recording characteristic curve
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces manual mechanical recording processes with automated electronic measurement and data processing systems. The control unit automatically records characteristic curves by electronically measuring pressure values and solenoid current values, then storing them in memory without manual intervention, thereby eliminating time-consuming manual operations while maintaining measurement accuracy.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The measurement system performs self-service by automatically conducting characteristic curve measurements without requiring manual operation. The control unit autonomously executes the measurement sequence, records data, and processes results, making the system self-sufficient and eliminating the time loss associated with manual recording.

Inventive Principle:
Principle #25Self-service

2Ease of operation

If fixed pressure value adjustments are used in digital valves, then control simplicity is maintained, but comprehensive characteristic curve adjustment capability is lost

Engineering Contradiction:
Improvevalve control simplicityVSAvoidcharacteristic curve adjustment capability
Core Design Contradiction:
Ease of operationVSAdaptability or versatility

Solution Approach 1:

The patent implements dynamic adjustment capabilities where the characteristic curve can be continuously modified through software parameters rather than being fixed. The control unit allows dynamic modification of pressure values, solenoid current values, and characteristic curve shapes, enabling the valve to adapt to different operational requirements while maintaining ease of operation through digital control interfaces.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system enables comprehensive characteristic curve adjustment by allowing changes to multiple parameters including pressure values, solenoid current values, and characteristic curve shapes. These parameter changes can be made independently and in combination, providing versatile adjustment capability while maintaining simple digital control through the control unit's interface.

Inventive Principle:
Principle #35Parameter changes

3Device complexity

If non-linear effects in solenoid current to pressure relationship are ignored, then control complexity is reduced, but pressure control precision deteriorates

Engineering Contradiction:
Improvecontrol system complexityVSAvoidpressure control precision
Core Design Contradiction:
Device complexityVSManufacturing precision

Solution Approach 1:

The patent implements feedback mechanisms where the control unit continuously monitors the actual pressure and solenoid current values, compares them with target values from the characteristic curve, and automatically adjusts the solenoid current to compensate for non-linear effects. This feedback loop maintains pressure control precision without requiring complex manual calculations or adjustments.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The system performs preliminary characterization by measuring and storing the complete characteristic curve (including all non-linear effects) in the control unit's memory before operation. During actual control, the pre-stored characteristic curve data is used to directly determine the required solenoid current for any given pressure setpoint, eliminating the need for real-time complex calculations while maintaining precision.

Inventive Principle:
Principle #10Preliminary action

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

This approach enables precise and adaptive control of hydraulic systems by compensating for manufacturing variations, ensuring accurate pressure regulation despite non-linear effects, thus enhancing the precision and flexibility of digital valve operation.

Implementation Method 1

The solenoid current is controlled by a digital electronic unit within the valve... The magnetic current is therefore crucial for the movement of the solenoid valve

Methodology Applied
Scientific EffectElectromagnetic conversion: Electromagnet

Data Source

PatentEP4657178A1Computer-implemented method for training an artificial neural network for controlling an electronic valve in a hydraulic system
Publication Date: 2025.12.03 ROBERT BOSCH GMBH
  • EP4657178A1 patent drawingFigure 1
  • EP4657178A1 patent drawingFigure 2
  • EP4657178A1 patent drawing

AI summary

The invention relates to a computer-implemented method for training an artificial neural network (10) for controlling an electronic valve in a hydraulic system, wherein the valve comprises a control unit, and the method comprises the steps of: - acquiring a characteristic curve for a valve, wherein the characteristic curve represents the relationship between a control variable of the valve and setpoints of a system variable of the hydraulic system; - providing training data from the characteristic curve (S10); - initializing an artificial neural network (S12, 10); - training the artificial neural network (S14, 10) with the training data, wherein the artificial neural network (10) is configured to receive a setpoint for the system variable of the hydraulic system as input (12) and is trained to output at least one value (20) for the control variable of the valve;and - providing the trained artificial neural network (S16, 10) for control of the valve by the control unit.;