US-12619202-B2 - Power tool stall detection

Abstract

A power tool includes a housing, a motor supported by the housing, a battery pack interface configured to receive a battery pack, a plurality of sensors configured to generate sensor data indicative of an operational state of the power tool, and an electronic controller. The electronic controller includes an electronic processor and a memory. The memory includes a machine learning control program for execution by the electronic processor. The electronic controller is configured to receive the sensor data indicative of the operational state of the power tool, process the sensor data using the machine learning control program to determine whether the power tool is experiencing a stall condition, and disable the motor when the power tool is determined to be experiencing the stall condition.

Inventors

• Jack J. Glennon
• Lokeshwaran Rajendran

Assignees

• MILWAUKEE ELECTRIC TOOL CORPORATION

Dates

Publication Date

20260505

Application Date

20230503

Claims (17)

1. 1 . A power tool comprising: a housing; a motor supported by the housing; an inverter; a battery pack interface configured to receive a battery pack; a plurality of sensors configured to generate sensor data indicative of an operational state of the power tool, the plurality of sensors including a temperature sensor configured to sense a temperature associated with the inverter; and an electronic controller including an electronic processor and a memory, the memory including a machine learning control program for execution by the electronic processor, the electronic controller configured to: receive the sensor data indicative of the operational state of the power tool, process the sensor data using the machine learning control program to determine whether the power tool is experiencing a stall condition, process the sensor data using the machine learning control program to distinguish between the stall condition and a cold startup operation, and disable the motor when the power tool is determined to be experiencing the stall condition.
2. 2 . The power tool of claim 1 , wherein the power tool is a fastener driver.
3. 3 . The power tool of claim 2 , wherein the plurality of sensors includes a motion sensor.
4. 4 . The power tool of claim 3 , wherein the motion sensor is selected from a group consisting of an accelerometer, a gyroscope, and an inertial measurement unit.
5. 5 . The power tool of claim 1 , wherein the power tool is a sander.
6. 6 . The power tool of claim 5 , wherein the plurality of sensors includes a motion sensor.
7. 7 . A method of operating a power tool comprising: generating, by a plurality of sensors, sensor data indicative of an operational state of the power tool, the plurality of sensors including a temperature sensor configured to sense a temperature associated with an inverter of the power tool; receiving, by an electronic controller of the power tool, the sensor data indicative of the operational state of the power tool; processing, by the electronic controller of the power tool, the sensor data using a machine learning control program to determine whether the power tool is experiencing a stall condition; processing, by the electronic controller of the power tool, the sensor data using the machine learning control program to distinguish between the stall condition and a cold startup operation; and disabling a motor of the power tool when the power tool is determined to be experiencing the stall condition.
8. 8 . The method of claim 7 , wherein the power tool is a fastener driver.
9. 9 . The method of claim 8 , wherein the plurality of sensors include a motion sensor.
10. 10 . The method of claim 9 , wherein the motion sensor is selected from a group consisting of an accelerometer, a gyroscope, and an inertial measurement unit.
11. 11 . The method of claim 7 , wherein the power tool is a sander.
12. 12 . The method of claim 11 , wherein the plurality of sensors includes a motion sensor.
13. 13 . A power tool comprising: a housing; a motor supported by the housing; an inverter; a battery pack interface configured to receive a battery pack; a plurality of sensors configured to generate sensor data indicative of an operational state of the power tool, the plurality of sensors including a temperature sensor configured to sense a temperature associated with the inverter, a current sensor, a speed sensor, and a motion sensor; and an electronic controller including an electronic processor and a memory, the memory including a machine learning control program for execution by the electronic processor, the electronic controller configured to: receive the sensor data indicative of the operational state of the power tool, process the sensor data using the machine learning control program to determine whether the motor is experiencing a stall condition, process the sensor data using the machine learning control program to distinguish between the stall condition and a cold startup operation, and disable the motor when the motor is determined to be experiencing the stall condition.
14. 14 . The power tool of claim 13 , wherein the power tool is a fastener driver.
15. 15 . The power tool of claim 14 , wherein the plurality of sensors include a voltage sensor.
16. 16 . The power tool of claim 13 , wherein the power tool is a sander.
17. 17 . The power tool of claim 13 , wherein the machine learning controller program implements one or more of a group consisting of a decision tree learning, an artificial neural network, a recurrent artificial neural network, a long short term memory neural network, a support vector machine, clustering, a Bayesian network, reinforcement learning, representation learning, similarity and metric learning, sparse dictionary learning, and k-nearest neighbor.

Description

RELATED APPLICATIONS This application claims the benefit of U.S. Provisional Patent Application No. 63/340,671, filed May 11, 2022, the entire content of which is hereby incorporated by reference. FIELD Embodiments described herein relate to power tools. SUMMARY Motor stall conditions in a power tool can lead to overheating of the motor, which can permanently damage the motor. In higher power tools, such as some fastener drivers and sanders, the motor overheating is a greater issue due to size constraints that limit passive heatsinking. Additionally, for some fastener drivers (e.g., nailers), detecting a motor stall condition is complicated because a firing sequence initially appears to be a stall condition without actually being a stall condition. Detecting or identifying a stall condition can prevent nuisance dead trigger pulls and improve reliability by reducing the number of false positive stall condition detections. Additionally, cold temperatures make stall detection non-trivial because a cold firing mechanism (or other power tool mechanism) can increase loading significantly. Stall detection should be able to distinguish between a cold mechanism for the power tool from a motor stall condition to increase power tool usability at lower temperatures. Similar issues are experienced by other power tools, such as an orbital sander, that includes a large fan that is driven by the motor. Power tools described herein include a housing, a motor supported by the housing, a battery pack interface configured to receive a battery pack, a plurality of sensors configured to generate sensor data indicative of an operational state of the power tool, and an electronic controller. The electronic controller includes an electronic processor and a memory. The memory includes a machine learning control program for execution by the electronic processor. The electronic controller is configured to receive the sensor data indicative of the operational state of the power tool, process the sensor data using the machine learning control program to determine whether the power tool is experiencing a stall condition, and disable the motor when the power tool is determined to be experiencing the stall condition. In some aspects, the power tool is a fastener driver. In some aspects, the plurality of sensors include a voltage sensor, a current sensor, a speed sensor, and a motion sensor. In some aspects, the power tool further includes the motion sensor is selected from a group consisting of an accelerometer, a gyroscope, and an inertial measurement unit. In some aspects, the power tool is a sander. In some aspects, the plurality of sensors include a temperature sensor and a current sensor. In some aspects, the power tool further includes the machine learning controller implements one or more of the group consisting of a decision tree learning, an artificial neural network, a recurrent artificial neural network, a long short term memory neural network, a support vector machine, clustering, a Bayesian network, reinforcement learning, representation learning, similarity and metric learning, sparse dictionary learning, and k-nearest neighbor (KNN). Methods of operating a power tool described herein include generating, by a plurality of sensors, sensor data sensor data indicative of an operational state of the power tool, receiving, by an electronic controller of the power tool, the sensor data indicative of the operational state of the power tool, processing, by the electronic processor, the sensor data using a machine learning control program to determine whether the power tool is experiencing a stall condition of the motor, and disabling a motor when the power tool is determined to be experiencing the stall condition of the motor. In some aspects, the power tool is a fastener driver. In some aspects, the plurality of sensors include a voltage sensor, a current sensor, a speed sensor, and a motion sensor. In some aspects, the motion sensor is selected from a group consisting of an accelerometer, a gyroscope, and an inertial measurement unit. In some aspects, the power tool is a sander. In some aspects, the plurality of sensors include a temperature sensor and a current sensor. In some aspects, the machine learning controller implements one or more of the group consisting of a decision tree learning, an artificial neural network, a recurrent artificial neural network, a long short term memory neural network, a support vector machine, clustering, a Bayesian network, reinforcement learning, representation learning, similarity and metric learning, sparse dictionary learning, and k-nearest neighbor (KNN). Power tools described herein include a housing, a motor supported by the housing, a battery pack interface configured to receive a battery pack, a plurality of sensors configured to generate sensor data indicative of an operational state of the power tool, and an electronic controller. The electronic controller includes an electronic processo