Impact Tool Torque Control Using Machine Learning Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing power tools with impact mechanisms lack effective torque control and calibration methods, leading to inconsistencies in torque delivery, which can affect the performance and reliability of tasks such as driving fasteners.
Innovation Solution
Implementing a controller with an electronic processor and memory that uses machine learning and physics models to predict and adjust torque based on sensor feedback, ensuring the actual torque matches a target value within an acceptable range, and storing the internal torque prediction value for future reference.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional torque control methods are used in power tools with impact mechanisms, then the device complexity is reduced, but the torque control accuracy and consistency deteriorate
Solution Approach 1:
The patent implements a feedback mechanism where a torque sensor measures the actual torque delivered by the impact mechanism, and a controller compares this measured torque with a target torque value. The controller then adjusts the motor operation based on the difference between actual and target torque, creating a closed-loop control system that continuously refines torque delivery accuracy.
Solution Approach 2:
The patent replaces traditional mechanical torque control mechanisms with an electronic control system that uses a processor, memory, and sensor feedback. This substitution allows for more precise and adaptable torque control by using electronic signals and algorithms rather than purely mechanical linkages and adjustments.
2Measurement precision
If torque calibration is performed without machine learning models, then the calibration process is simpler, but the torque prediction accuracy deteriorates
Solution Approach 1:
The patent performs torque calibration in advance during the manufacturing or setup phase. The controller systematically varies motor parameters and measures the resulting torque outputs to build a calibration dataset. This preliminary calibration action creates a reference model that enables accurate torque prediction during subsequent operation without requiring real-time complex calculations.
Solution Approach 2:
The patent divides the torque control system into distinct functional components: a calibration phase that establishes the relationship between motor parameters and torque output, and an operation phase that uses this calibration data for prediction. This segmentation allows the complex calibration process to be performed separately and stored as lookup tables or models, simplifying real-time operation.
3Reliability
If no torque calibration process is implemented, then the ease of operation is improved, but the reliability of torque delivery deteriorates
Solution Approach 1:
The patent implements an automated self-calibration process where the controller automatically performs torque measurements and adjustments without requiring manual intervention or specialized operator skills. The system self-regulates by comparing sensor feedback with target values and automatically adjusting motor parameters, making the calibration process transparent and eliminating the need for operator training on complex calibration procedures.
Data Source
AI summary
Systems and methods for determining output torque of a power tool. One example power tool includes a motor, an output drive device, an anvil couple to the output drive device, a hammer connected to the motor and configured to engage the anvil when driven by the motor, and a controller. The controller is configured to receive a target torque value, drive the motor based on an internal torque prediction value, and determine a difference between the target torque value and an actual torque value provided by the motor. The controller is configured to determine whether the difference between the target torque value and the actual torque value is within an acceptable range, and store, in response to the difference being within the acceptable range, the internal torque prediction value in the memory. The internal torque prediction value is associated with the target torque value in the memory.